Dissertations / Theses on the topic 'Forest mining'
To see the other types of publications on this topic, follow the link: Forest mining.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Forest mining.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
com, ronaldchapman1@bigpond, and Ron Chapman. "Fighting for the Forests: A History of The Western Australian Forest Protest Movement 1895-2001." Murdoch University, 2008. http://wwwlib.murdoch.edu.au/adt/browse/view/adt-MU20090121.162055.
Full textAbstract:
As the first comprehensive study of Western Australian forest protest the thesis analyses the protest movement's organisation, campaigns and strategies. Its central argument is that the contemporary Western Australian forest protest movement established a network of urban and south-west activist groups which encouraged broad public support, and that a diversity of protest strategies focused public attention on forest issues and pressured the state government to change its forest policies. The forest protest movement was characterised by its ability to continually adapt its organisation and strategies to changing social and political conditions. This flexible approach to protest not only led to victories in the Shannon River Basin, Lane-Poole Reserve and old growth forest campaigns, but also transformed forest protest into an influential social movement which contributed to the downfall of the Court Liberal Government in 2001.
2
Mehlhope, Stephanie H. "MODELING BEDROCK MINING HOTSPOTS WITHIN THE OUACHITA NATIONAL FOREST, ARKANSAS." UKnowledge, 2013. http://uknowledge.uky.edu/geography_etds/3.
Full textAbstract:
This study, concentrating on the Ouachita Mountain Range in western-central Arkansas, extends prior work on treethrows and their influence on soil development in the region by supplying a method of determining hotspots of bedrock mining by treethrow. Binary logistic regression analysis was employed to determine the abiotic and biotic factors that are highly correlated with the rate of bedrock detachment found in uprooted rootwads from three study sites within the Ouachita National Forest. The produced logistic regression models suggest topographic factors, tree specific characteristics, as well as the local geology and soil characteristics all have a significant effect upon the probability of bedrock mining activity by treethrow throughout the Ouachita National Forest, Arkansas. This methodology has demonstrated that the forcing mechanism that causes the uprooting event intrinsically changes the relationship between the abiotic and biotic factors that control bedrock mining. Finally, the computed probabilities of bedrock being mined were geographically assigned to the appropriate environmental setting using a geographic information system to identify areas of highest odds of mining, hotspots, and lowest odds of mining highlighted.
3
Kalamandeen, Michelle. "Forest loss dynamics and impacts from gold mining in Amazonia." Thesis, University of Leeds, 2019. http://etheses.whiterose.ac.uk/22904/.
Full textAbstract:
Amazonian rainforests are home to Earth's largest reservoir of biodiversity, providing crucial ecosystem services and storing approximately 17% of all global terrestrial carbon. Today, these forests are experiencing rapid, unprecedented changes due to climate impacts and anthropogenic disturbances. In recent decades, the region has experienced marked variability in deforestation, and after a long period of increase, the deforestation rates in countries like Brazil have sharply declined in recent years. However, little is known about the forest trends and the impact of different drivers in other Amazonian countries. The aim of this thesis, therefore, is to better understand and examine the current dynamics of forest loss across Amazonia and how intensive land uses such as gold mining influence forest loss, nutrient cycling and recovery patterns. Using remote sensing coupled with field observations, this research highlights new spatial patterns in Amazonian forest loss which point to a more complex pattern where new smaller-scale drivers of forest loss are becoming progressively more important (Chapter 2). The expansion of small-scale events were primarily driven by gold mining activities, particularly in northern Amazonia, with underestimation of forest loss occurring at sites driven by a mosaic of small-scale clearings (Chapter 3). Nutrient depletion was found to be the most important factor driving low biomass recovery in previously mined areas, with mercury contamination being of secondary importance (Chapters 4 and 5). Overall, small-scale gold mining can severely impair the forest's ability to recover at abandoned mining pits and tailing ponds while recovery rates of woody biomass on the overburden zone were comparable to other secondary forests across the Neotropics following abandonment of pastures and agriculture (Chapter 5). Gold mining across the Amazon could potentially result in ~90,000 t C yr-1 less carbon being accumulated in relation to what would have accumulated under agriculture/pasture. Important conclusions from this work suggests that (1) national deforestation statistics need to include these small-scale events which are currently excluded from important official estimates such as Brazil's PRODES, and (2) active rehabilitation and restoration are required in order to assist the disrupted successional processes at gold mining sites. The results presented here highlight the vulnerability of Amazonian forests to newer, more intense types of land uses such as small-scale gold mining.
4
MacKinnon, Richard Kyle. "Seeing the forest for the trees: tree-based uncertain frequent pattern mining." Springer International Publishing, 2014. http://hdl.handle.net/1993/31059.
Full textAbstract:
Many frequent pattern mining algorithms operate on precise data, where each data point is an exact accounting of a phenomena (e.g., I have exactly two sisters). Alas, reasoning this way is a simplification for many real world observations. Measurements, predictions, environmental factors, human error, &ct. all introduce a degree of uncertainty into the mix. Tree-based frequent pattern mining algorithms such as FP-growth are particularly efficient due to their compact in-memory representations of the input database, but their uncertain extensions can require many more tree nodes. I propose new algorithms with tightened upper bounds to expected support, Tube-S and Tube-P, which mine frequent patterns from uncertain data. Extensive experimentation and analysis on datasets with different probability distributions are undertaken that show the tightness of my bounds in different situations.February 2016
5
Dement, Wesley T. "AN INVESTIGATION OF TREE GROWTH AND WOODY VEGETATION COLONIZATION ON A 19 YEAR-OLD FORESTRY RECLAMATION SITE." UKnowledge, 2017. https://uknowledge.uky.edu/forestry_etds/37.
Full textAbstract:
Survival, growth and biomass accumulation of 19 year-old trees planted on an Appalachian surface mine site were evaluated to determine the effect of spoil grading and surface amendment treatments. Three spoil grading treatments (loose-dump, strike-off and graded control) were established to create a range of operationally feasible spoil compaction capable of impacting tree establishment and growth. Likewise, three surface amendment treatments (straw/manure mulch, hardwood bark mulch and control) were applied to determine their effects on tree development. Trees grown under low-compaction grading treatment levels (strike-off and loose-dump) consistently outperformed trees planted in a high-compaction control treatment. Loose-dump preparation resulted in higher survival for five of six tree species and greater biomass in three species for which this metric was estimated. Strike-off preparation resulted in higher diameter at breast height (DBH) values. The addition of straw/manure surface amendment increased biomass for hardwood species for which this value was estimated.
Volunteer woody vegetation growing in the same experimental plots was measured and characterized by species. Loose-dump plots exhibited highest overall volunteer stem and native stem density and compacted control plots had lowest volunteer stem density and lowest proportion of native stems. Strike-off plots exhibited intermediate values for both of these measures.
6
Luud, Aarne. "Evaluation of moose habitats and forest reclamation in Estonian oil shale mining areas /." Online version, 2006. http://dspace.utlib.ee/dspace/bitstream/10062/684/5/luudaarne.pdf.
Full text
7
Oliveira, Leandro de. "Soil recuperation in forest settlements in mining areas in the Tremembé municipality - SP." Universidade de Taubaté, 2006. http://www.bdtd.unitau.br/tedesimplificado/tde_busca/arquivo.php?codArquivo=77.
Full textAbstract:
The recuperation of degraded areas due to mining activity namely sand mining is carried out by the forest recomposition with native species. In the present work the availability of nutrients along with amount of living matter cover accumulated in a native ciliary wood and in five fragments of forest recomposition of areas previously used for sand mining in the municipality of Tremembe SP. Such areas are currently at different phases of vegetative development process, ranging from 1, 5 and 11 years. The content of nutrient, organic matter, soil acidity and total
production of living matter cover and coarse living matter leaves ,twigs and roots were analyzed .The living matter cover was sampled in 1 m2 fragments the 0-20 and 20-40 cm layers at five different random points in the beds and between the beds in all areas. The soil samples were analyzed in terms of the attributes pH, organic matter, P, K, Ca , Mg , H , Al , base aggregation , cation exchange capacity and base saturation percentage. The comparison of the living matter cover production and the chemical attributes between the areas were analyzed by means of variance analysis complemented by the Tukey test. A smaller production of total living matter cover was observed in the fragments over 6, 5 reforestation years. As from that period
however, the relation between the content of the organic matter and the amount of living matter cover in the superficial layer of the soil tends to differ. There is an increase in the nature of organic matter and the reduction of the production of living matter cover possibly due to the
cumulative effect of the organic matter in the soil through the organic composts that are more resistant to decomposition and respond for the humus formation. By means of the analyses of the chemical attributes the soils of the forest fragments were classified as dystrophic and moderately fertile. The nature and level of nutrients presented average values for Ca and Mg, high for P and low for K. The higher values for Ca, Mg and P may be a result of the residual effect of the fertilization carried out during the planting process.A recuperação de áreas degradadas devido à exploração mineraria, notadamente pela extração de areia, é realizada pela recomposição florestal com espécies nativas. No presente trabalho analisou-se a disponibilidade de nutrientes e a quantidade de serapilheira acumulada em um fragmento de mata ciliar nativa e em cinco fragmentos de recomposição florestal de áreas anteriormente utilizadas para exploração de areia no município de Tremembé, SP. Estas áreas apresentam-se em processo de desenvolvimento vegetativo com períodos diferentes, variando de 1,5 a 11 anos. Foi analisado o teor de nutrientes, matéria orgânica, acidez do solo e a produção da serapilheira total e fracionada em folhas, ramos e raízes. As serapilheira foi amostrada em parcelas de 1m2, nas camadas 0-20 e 20-40 cm em cinco pontos escolhidos aleatoriamente nas leiras e entre leiras, em todas as áreas. Nas amostras de solo analisaram-se os atributos pH, matéria orgânica, Fósforo, Potássio, Cálcio, Magnésio, Hidrogênio, Alumínio, soma de bases, capacidade de troca catiônica e porcentagem de saturação de base. A comparação da produção de serapilheira e dos atributos químicos entre as áreas foi analisada por meio de análise de variância complementada pelo teste de Tukey. Observou-se menor produção de serapilheira total nos fragmentos a partir de 6,5 anos de reflorestamento. Entretanto, a partir deste período, a relação entre o teor de matéria orgânica e a quantidade de serapilheira da camada superficial do solo tende a diferir, com aumento no teor de matéria orgânica e redução da produção de serapilheira, decorrente, possivelmente, do efeito acumulativo da matéria orgânica no solo através de compostos orgânicos mais resistentes à decomposição responsáveis pela formação do húmus. Por meio das análises dos atributos químicos, os solos dos fragmentos florestais foram classificados como distróficos e de fertilidade moderada. Os teores dos nutrientes apresentaram valores médios para cálcio e magnésio, alto para o fósforo e baixo para o potássio. Os valores mais elevados de cálcio, magnésio e fósforo podem ser decorrentes do efeito residual da adubação realizada na época do plantio.
8
Adriansson, Nils, and Ingrid Mattsson. "Forecasting GDP Growth, or How Can Random Forests Improve Predictions in Economics?" Thesis, Uppsala universitet, Statistiska institutionen, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-243028.
Full textAbstract:
GDP is used to measure the economic state of a country and accurate forecasts of it is therefore important. Using the Economic Tendency Survey we investigate forecasting quarterly GDP growth using the data mining technique Random Forest. Comparisons are made with a benchmark AR(1) and an ad hoc linear model built on the most important variables suggested by the Random Forest. Evaluation by forecasting shows that the Random Forest makes the most accurate forecast supporting the theory that there are benefits to using Random Forests on economic time series.
9
Johansson, Filip, and Jesper Wikström. "Result Prediction by Mining Replays in Dota 2." Thesis, Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2288.
Full textAbstract:
Context: Real-time games like Dota 2 lack the extensive mathematical modeling of turn-based games that can be used to make objective statements about how to best play them. Understanding a real-time computer game through the same kind of modeling as a turn-based game is practically impossible. Objectives: In this thesis an attempt was made to create a model using machine learning that can predict the winning team of a Dota 2 game given partial data collected as the game progressed. A couple of different classifiers were tested, out of these Random Forest was chosen to be studied more in depth. Methods: A method was devised for retrieving Dota 2 replays and parsing them into a format that can be used to train classifier models. An experiment was conducted comparing the accuracy of several machine learning algorithms with the Random Forest algorithm on predicting the outcome of Dota 2 games. A further experiment comparing the average accuracy of 25 Random Forest models using different settings for the number of trees and attributes was conducted. Results: Random Forest had the highest accuracy of the different algorithms with the best parameter setting having an average of 88.83% accuracy, with a 82.23% accuracy at the five minute point. Conclusions: Given the results, it was concluded that partial game-state data can be used to accurately predict the results of an ongoing game of Dota 2 in real-time with the application of machine learning techniques.
10
Linusson, Henrik, Robin Rudenwall, and Andreas Olausson. "Random forest och glesa datarespresentationer." Thesis, Högskolan i Borås, Institutionen Handels- och IT-högskolan, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-16672.
Full textAbstract:
In silico experimentation is the process of using computational and statistical models to predict medicinal properties in chemicals; as a means of reducing lab work and increasing success rate this process has become an important part of modern drug development. There are various ways of representing molecules - the problem that motivated this paper derives from collecting substructures of the chemical into what is known as fractional representations. Assembling large sets of molecules represented in this way will result in sparse data, where a large portion of the set is null values. This consumes an excessive amount of computer memory which inhibits the size of data sets that can be used when constructing predictive models.In this study, we suggest a set of criteria for evaluation of random forest implementations to be used for in silico predictive modeling on sparse data sets, with regard to computer memory usage, model construction time and predictive accuracy.A novel random forest system was implemented to meet the suggested criteria, and experiments were made to compare our implementation to existing machine learning algorithms to establish our implementation‟s correctness. Experimental results show that our random forest implementation can create accurate prediction models on sparse datasets, with lower memory usage overhead than implementations using a common matrix representation, and in less time than existing random forest implementations evaluated against. We highlight design choices made to accommodate for sparse data structures and data sets in the random forest ensemble technique, and therein present potential improvements to feature selection in sparse data sets.Program: Systemarkitekturutbildningen
11
Halmann, Marju. "Email Mining Classifier : The empirical study on combining the topic modelling with Random Forest classification." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-14710.
Full textAbstract:
Filtering out and replying automatically to emails are of interest to many but is hard due to the complexity of the language and to dependencies of background information that is not present in the email itself. This paper investigates whether Latent Dirichlet Allocation (LDA) combined with Random Forest classifier can be used for the more general email classification task and how it compares to other existing email classifiers. The comparison is based on the literature study and on the empirical experimentation using two real-life datasets. Firstly, a literature study is performed to gain insight of the accuracy of other available email classifiers. Secondly, proposed model’s accuracy is explored with experimentation. The literature study shows that the accuracy of more general email classifiers differs greatly on different user sets. The proposed model accuracy is within the reported accuracy range, however in the lower part. It indicates that the proposed model performs poorly compared to other classifiers. On average, the classifier performance improves 15 percentage points with additional information. This indicates that Latent Dirichlet Allocation (LDA) combined with Random Forest classifier is promising, however future studies are needed to explore the model and ways to further increase the accuracy.
12
Jones, Andy Thomas. "Site Quality Classification for Mapping Forest Productivity Potential on Mine Soils in the Appalachian Coalfield Region." Thesis, Virginia Tech, 2005. http://hdl.handle.net/10919/33355.
Full textAbstract:
Surface mining for coal in the Appalachian region destroys native forests and replaces them with reclaimed landscapes that are often revegetated as grasslands and are unacceptable for managed forest production without extensive remediation. Tree survival and growth are dependent on many reclaimed mine land properties. However, conventional mapping techniques using USDA soil series does not identify these critical soil property differences. This study was conducted to create a forest site quality classification system to be used to evaluate the potential productivity of specific tree species on mine soils. High soil bulk density is the most common limitation on mine soils and methods to efficiently measure this property were evaluated. No valid quantitative method of measuring mine soil bulk density was found due to the high rock fragment content in the soil profile, but a method for estimating relative soil density class was developed. Other soil chemical and physical properties were analyzed at abandoned mine sites in Virginia, West Virginia, and Ohio. Mine soil properties differed throughout the Appalachian region, with Ohio sites having finer textures and less rock fragments, West Virginia sites having coarser textures and a high quantity of dark-colored shale, and Virginia sites dominated by sandstone rock types. Selected field-measured soil and site properties were regressed with site index (SI) base age 50 at 52 sample locations in 10- to 18-year old white pine (Pinus strobus L.) stands on reclaimed mine lands. Sufficiency curves for nine soil and site properties were produced and a general productivity index (PI) calculated. Regression of the general PI and measured SI of white pine produced an R2 of 0.61. The general PI was simplified to four soil properties (soil density, rooting depth, texture, and pH) most significantly related to the SI of white pine, and the properties were weighted based on their importance to white pine growth on mine soils. The modified PI model produced an R2 of 0.69 for a linear relationship between PI and measured SI. The SI values were divided into five classes of equal interval and the corresponding PI values were used to define five forest site quality classes that could be identified by measuring and mapping differences in the PI on older mine soils. The model may be modified for determination of hardwood productivity after validation sites are located. Soil and site properties that are correlated with seedling survival appear different than those properties important for tree productivity. The forest site quality classification system proposed here proved practical for mapping a selected mine site, and the maps may be used as a validation test after future reforestation.Master of Science
13
Aldous, P. J. "The groundwater geology of an abandoned coal mined aquifer : a case study from the Forest of Dean coalfield." Thesis, University of Bristol, 1987. http://hdl.handle.net/1983/62066205-5e54-45a2-9dee-6cdc47103516.
Full text
14
Kazar, Sheila A. "Surface mines as landscape features contrasting microclimate and forest composition among open, edge, and interior /." Morgantown, W. Va. : [West Virginia University Libraries], 2003. http://etd.wvu.edu/templates/showETD.cfm?recnum=3149.
Full textAbstract:
Thesis (M.A.)--West Virginia University, 2003.Title from document title page. Document formatted into pages; contains vii, 56 p. : ill. (some col.), maps (some col.). Vita. Includes abstract. Includes bibliographical references (p. 50-55).
15
Andrews, Jeffrey Adam. "Soil productivity model to assess forest site quality on reclaimed surface mines." Thesis, This resource online, 1992. http://scholar.lib.vt.edu/theses/available/etd-09052009-040211/.
Full text
16
Taalab, Khaled Paul. "Modelling soil bulk density using data-mining and expert knowledge." Thesis, Cranfield University, 2013. http://dspace.lib.cranfield.ac.uk/handle/1826/8273.
Full textAbstract:
Data about the spatial variation of soil attributes is required to address a great number of environmental issues, such as improving water quality, flood mitigation, and determining the effects of the terrestrial carbon cycle. The need for a continuum of soils data is problematic, as it is only possible to observe soil attributes at a limited number of locations, beyond which, prediction is required. There is, however, disparity between the way in which much of the existing information about soil is recorded and the format in which the data is required. There are two primary methods of representing the variation in soil properties, as a set of distinct classes or as a continuum. The former is how the variation in soils has been recorded historically by the soil survey, whereas the latter is how soils data is typically required. One solution to this issue is to use a soil-landscape modelling approach which relates the soil to the wider landscape (including topography, land-use, geology and climatic conditions) using a statistical model. In this study, the soil-landscape modelling approach has been applied to the prediction of soil bulk density (Db). The original contribution to knowledge of the study is demonstrating that producing a continuous surface of Db using a soil-landscape modelling approach is that a viable alternative to the ‘classification’ approach which is most frequently used. The benefit of this method is shown in relation to the prediction of soil carbon stocks, which can be predicted more accurately and with less uncertainty. The second part of this study concerns the inclusion of expert knowledge within the soil-landscape modelling approach. The statistical modelling approaches used to predict Db are data driven, hence it is difficult to interpret the processes which the model represents. In this study, expert knowledge is used to predict Db within a Bayesian network modelling framework, which structures knowledge in terms of probability. This approach creates models which can be more easily interpreted and consequently facilitate knowledge discovery, it also provides a method for expert knowledge to be used as a proxy for empirical data. The contribution to knowledge of this section of the study is twofold, firstly, that Bayesian networks can be used as tools for data-mining to predict a continuous soil attribute such as Db and that in lieu of data, expert knowledge can be used to accurately predict landscape-scale trends in the variation of Db using a Bayesian modelling approach.
17
Nasution, Zaid Perdana. "Forest conservation, mining and local responses : drawing the boundaries in Batang Gadis National Park, North Sumatra, Indonesia." Thesis, University of Leeds, 2018. http://etheses.whiterose.ac.uk/19809/.
Full textAbstract:
After more than 32 years under centralized government, Indonesia underwent a process of political decentralization starting in 1999. However, the management and control of natural resources, particularly in the forestry and mining sectors, is still largely under the authority of central government. At the same time, global calls for conservation and sustainable development that require state territorialization have also influenced policy and practice at the local and national levels. They have encouraged a process of state territorialization that has had a distinct affect on the land-based institutions that form the customary sense of territoriality of rural villagers. Within this overall context, this thesis starts by introducing an international conservation project that led to confrontation involving local government and a mining company. The thesis focuses on the establishment of Batang Gadis National Park in North Sumatra, the drawing of forest conservation boundaries and the impact this had on the mining company and in particular on the rural villagers and their customary territoriality. Through interviews and analysis of documents and media, this work discusses conflict over competing land claims by conservation and development forces and their entanglement with the customary institutions of territoriality. My findings lead me to argue firstly that the process of state territorialization engenders elite conflict over land and resources and that this usually undermines the interest of local villagers and their customary territoriality. Secondly, local government can switch its allegiance – in this case, from conservation to development – without accounting for this change either to central government or in particular to rural villagers. Thirdly, customary territoriality has the potential to be the basis for the formation of cogent demands for accountability of powerful actors. In reflecting these findings, this study concludes that, in the context of a decentralized Indonesia, it is important that the state territorialization process recognize and entertain a dialogue with the institutions of customary territoriality, which it sees as best placed to protect the interests of local people and the environment from external and elite intervention.
18
Elagamy, Mazen Nabil. "Stock Market Random Forest-Text Mining (SMRF-TM) approach to analyse critical indicators of stock market movements." Thesis, Staffordshire University, 2017. http://eprints.staffs.ac.uk/4285/.
Full textAbstract:
The Stock Market is a significant sector of a country’s economy and has a crucial role in the growth of commerce and industry. Hence, discovering efficient ways to analyse and visualise stock market data is considered a significant issue in modern finance. The use of data mining techniques to predict stock market movements has been extensively studied using historical market prices but such approaches are constrained to make assessments within the scope of existing information, and thus they are not able to model any random behaviour of the stock market or identify the causes behind events. One area of limited success in stock market prediction comes from textual data, which is a rich source of information. Analysing textual data related to the Stock Market may provide better understanding of random behaviours of the market. Text Mining combined with the Random Forest algorithm offers a novel approach to the study of critical indicators, which contribute to the prediction of stock market abnormal movements. In this thesis, a Stock Market Random Forest-Text Mining system (SMRF-TM) is developed and is used to mine the critical indicators related to the 2009 Dubai stock market debt standstill. Random forest and expectation maximisation are applied to classify the extracted features into a set of meaningful and semantic classes, thus extending current approaches from three to eight classes: critical down, down, neutral, up, critical up, economic, social and political. The study demonstrates that Random Forest has outperformed other classifiers and has achieved the best accuracy in classifying the bigram features extracted from the corpus.
19
Cook, Shannon R. "The Hydrogeology of an Old Growth Forest with Implications for Defining Impact Zones Associated with Underground Mining." Ohio University / OhioLINK, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1226165787.
Full text
20
Naji, Adel Ali. "Data Mining for Accurately Estimating Residential Natural Gas Energy Consumption and Savings Using a Random Forest Approach." University of Dayton / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1557422487896673.
Full text
21
Wright, Lindsey. "Classifying textual fast food restaurant reviews quantitatively using text mining and supervised machine learning algorithms." Digital Commons @ East Tennessee State University, 2018. https://dc.etsu.edu/honors/451.
Full textAbstract:
Companies continually seek to improve their business model through feedback and customer satisfaction surveys. Social media provides additional opportunities for this advanced exploration into the mind of the customer. By extracting customer feedback from social media platforms, companies may increase the sample size of their feedback and remove bias often found in questionnaires, resulting in better informed decision making. However, simply using personnel to analyze the thousands of relative social media content is financially expensive and time consuming. Thus, our study aims to establish a method to extract business intelligence from social media content by structuralizing opinionated textual data using text mining and classifying these reviews by the degree of customer satisfaction. By quantifying textual reviews, companies may perform statistical analysis to extract insight from the data as well as effectively address concerns. Specifically, we analyzed a subset of 56,000 Yelp reviews on fast food restaurants and attempt to predict a quantitative value reflecting the overall opinion of each review. We compare the use of two different predictive modeling techniques, bagged Decision Trees and Random Forest Classifiers. In order to simplify the problem, we train our model to accurately classify strongly negative and strongly positive reviews (1 and 5 stars) reviews. In addition, we identify drivers behind strongly positive or negative reviews allowing businesses to understand their strengths and weaknesses. This method provides companies an efficient and cost-effective method to process and understand customer satisfaction as it is discussed on social media.
22
Lalor, Briony Maree. "An assessment of the recovery of the microbial community in jarrah forest soils after bauxite mining and prescription burning." University of Western Australia. School of Earth and Geographical Sciences, 2009. http://theses.library.uwa.edu.au/adt-WU2010.0037.
Full textAbstract:
[Truncated abstract] Recovery of soil nutrients, microbial populations and carbon (C) and nitrogen (N) cycling processes are critical to the success of rehabilitation following major ecosystem disturbance. Bauxite mining represents a major ecosystem disturbance to the jarrah (Eucalyptus marginata) forest in the south-west of Western Australia. Mining has created a mosaic of mined areas in various stages of succession surrounded by non-mined forest areas. Initial site preparations within rehabilitation areas such as contour ripping alter soil structure (creation of mound and furrows) and over time also influence the distribution of vegetation and litter. Current performance criteria developed by industry, government and other stakeholders have determined that before post-bauxite mined areas of jarrah forest can be integrated back into normal forest management practises they should be functional and demonstrate resilience to normal forest disturbances such as fire. Furthermore, resilience should be of a manner comparable to non-mined analogue forest sites. Currently little is known of the resilience of microbial communities and C and N cycling in rehabilitation sites to normal forest disturbances such as prescription burning. As such, before rehabilitated jarrah forests can be successfully integrated into broad scale forest management regimes, a more thorough knowledge of the potential impacts of burning practises on the soil microbial community and C and N cycling processes in these systems is required. ... While there are similar rates of C and N cycling the underlying microbial community structure was distinctly different; implying a high degree of functional redundancy with respect to C and N cycling. Differences in the C and N cycling and structure of the microbial communities were likely to be due to differences in soil environmental conditions (i.e. soil alkalinity/acidity, soil moisture) and C substrate availability which influence the physiological status of the microbial community and in turn are related to successional age of the forests. Results also suggest that the measurement of CLPP can be a useful approach for assessment of changes in the functional ability of microbial communities. However, the interpretation of how well these rehabilitation forests have recovered heterotrophic abilities was greatly affected by the methodological approach used (e.g. MicroRespTM or Degens and Harris, 1997). Importantly, results from Chapter 4 and 5 suggested that the effects of a moderate prescription fire on C and N processes, CLPP and microbial community structure of 18 year old rehabilitation forests are likely to be short-lived (< 2 years). Furthermore, the effects of the moderate spring prescription fire were not large enough to decouple C and N cycling processes over the short-term (< 1 years) which suggests that by 18 years of age rehabilitation forests demonstrate comparable functional resilience to a moderate prescription burn.
23
Benac, David T. "This land is all terrible rough : a history of access to forest resources in Carter County, Missouri /." free to MU campus, to others for purchase, 2003. http://wwwlib.umi.com/cr/mo/fullcit?p3099609.
Full text
24
Freytag, Sara B. "Effects of Mountaintop Removal Mining on Population Dynamics of Stream Salamanders." UKnowledge, 2016. http://uknowledge.uky.edu/forestry_etds/27.
Full textAbstract:
Mountaintop removal mining (MTR) is a notorious stressor of stream ecosystems in the Central Appalachians. Valley fills (VF) lead to reduced occupancy, abundance, and species richness of stream salamanders. Multiple factors may be responsible for these reductions, but specifically habitat fragmentation and degradation may reduce colonization rates and increase local extinction rates. From 2013-2015, repeated counts of salamanders were conducted in stream reaches impacted by MTR/VF and compared to counts in reference reaches to answer the question: do stream salamander population dynamics differ between stream reaches impacted by MTR/VF and reference stream reaches? I also investigated dynamics of stream habitat using measures relevant to stream salamander persistence. Accordingly, I examined number of cover objects, percent detritus, hydroperiod, and specific conductance. From the salamander capture data, colonization and survival probabilities were lower in MTR/VF reaches than reference reaches. MTR/VF reaches also had fewer cover objects, higher percent detritus, constant stream flow, and elevated specific conductance. Although specific conductance was increased in MTR/VF reaches, it was not strongly correlated with colonization and survival. I suggest reduced rates of colonization and survival in MTR/VF stream reaches are driven by inhibited dispersal and reduced individual survival due to degraded terrestrial and aquatic environments.
25
Moreno, Vanessa de Souza. "Restauração florestal de áreas mineradas de bauxita: é necessário o uso de gramíneas exóticas para o recobrimento inicial do solo?" Universidade de São Paulo, 2015. http://www.teses.usp.br/teses/disponiveis/11/11150/tde-08042015-150943/.
Full textAbstract:
A mineração modifica profundamente os ecossistemas naturais e, embora a recuperação dessas áreas seja exigida pela legislação, trata-se ainda de um grande desafio técnico. Geralmente, as estratégias de recuperação envolvem a distribuição de solo florestal superficial, a semeadura de gramíneas exóticas para cobrir o solo, chamada de \"tapete verde\", e o plantio de mudas de árvores exóticas e/ou nativas. No entanto, a semeadura de gramíneas exóticas pode restringir a regeneração de espécies nativas, sendo a avaliação da sua viabilidade ecológica necessária para determinar sua real necessidade. Nesse contexto, o objetivo desse trabalho foi avaliar se é necessário o uso de gramíneas exóticas para o recobrimento inicial do solo na recuperação de florestas tropicais em áreas de mineração de bauxita, bem como se a trajetória ecológica gerada apresenta potencial de retorno às condições pré-distúrbio. Sendo assim, utilizamos um estudo de caso de recuperação de minas de exploração de bauxita na Mata Atlântica do Brasil na região de Poços de Caldas-MG, na qual foram comparadas cronossequências de dois métodos de restauração de minas de bauxita - restauração florestal sem tapete verde (Rs) e restauração florestal com tapete verde (Rc) - tendo-se trechos de floresta nativa como ecossistema de referência. Foram avaliados dados de estrutura (cobertura de gramínea, cobertura de dossel, área basal, densidade de indivíduos com DAP ≥ 1 cm e altura ≥130 cm - classe 1 - e densidade de indivíduos com DAP < 1 cm e altura ≥ 50 cm - classe 2) e composição (riqueza, diversidade, equabilidade, riqueza e porcentagem de espécies por síndrome de dispersão). A definição da trajetória ecológica foi realizada por meio de regressões lineares. O método de restauração florestal sem tapete verde alcançou resultados superiores ao método Rc em parâmetros importantes para o estabelecimento da floresta, como cobertura de gramíneas, cobertura de dossel, riqueza e diversidade da classe 1. O método Rs também teve resultados semelhantes à Rc em vários parâmetros, apesar da idade inferior. Os dois métodos apresentaram tendências de evolução em direção aos parâmetros do ecossistema de referência, porém o método Rs, se mantiver a trajetória atual, pode alcançá-los mais rapidamente, o que reduz gastos com manutenção e manejo. Tais evidências mostram que o uso de gramíneas exóticas para recobrimento inicial de áreas mineradas não é necessário em projetos que visem à restauração florestal de áreas de mineração, pois essas prejudicam o restabelecimento da dinâmica florestal. Adicionalmente, mostrou-se ser possível recuperar áreas mineradas de bauxita com metas ecológicas mais ambiciosas, que visem o retorno de condições similares às existentes pré-distúrbio.Mining profoundly alters natural ecosystems and, although the recovery of these areas is required by law, it is still a major technical challenge. Generally, recovery strategies involve the distribution of surface forest soil, planting of exotic grasses to cover the ground and the planting of exotic and/or native trees. However, the sowing of exotic grasses may restrict native species regeneration, therefore, context specific diagnosis must be carried out to determine the actual need of using such technique. In this context, the aim of this study was to evaluate whether the use of exotic grasses for initial soil covering in the recovery of tropical forests in areas of bauxite mining is necessary, as well as if the restored community has potential to return to the pre-disturbance conditions. Therefore, we use a case study of recovery of bauxite exploration in the Atlantic Forest region of Brazil in Pocos de Caldas, Minas Gerais, where chronosequences of two methods of restoration of bauxite mines were compared - restoration without exotic grasses (Rs) and forest restoration with exotic grasses (Rc) - taking up stretches of native forest ecosystem as a reference. We collected data on tree community structure (grass cover, canopy cover, basal area, and density of individuals CBH ≥3.1 cm and height ≥ 130 cm (1 class) and density of individuals DAP < 3.1 cm and height ≥ 50 cm (class 2) and composition (richness, diversity, evenness and richness and percentage of species by dispersion syndrome). The successional path was analyzed by linear regression. In class 1, the method of forest restoration without exotic grasses (Rs) achieved better results than Rc in key parameters for forest establishment, such as exotic grass cover, canopy cover, richness and diversity. The Rs method also had similar results to Rc in several parameters, despite being represented by younger communities. Both methods showed trends toward the parameters values found in reference ecosystem, but Rs method, if it remain the current way, can reach these values more quickly, which reduces maintenance costs and management. Such evidence shows that the use of exotic grasses for initial covering of mined areas is not necessary in projects aimed at forest restoration of mining areas, as these hinder the restoration of forest dynamics. Additionally, we proved to be possible to recover the bauxite mined areas with more ambitious ecological goals, aiming at the return of pre-disturbance conditions.
26
Schaaf, Wolfgang. "Development of element cycling in forest ecosystems after anthropogenic disturbances : case studies at long-term atmospheric polluted and post-mining sites /." Cottbus : Brandenburgische Techn. Univ, 2004. http://www.gbv.de/dms/bs/toc/488098432.pdf.
Full text
27
Virkkala, Linda, and Johanna Haglund. "Modelling of patterns between operational data, diagnostic trouble codes and workshop history using big data and machine learning." Thesis, Uppsala universitet, Datalogi, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-279823.
Full textAbstract:
The work presented in this thesis is part of a large research and development project on condition-based maintenance for heavy trucks and buses at Scania. The aim of this thesis was to be able to predict the status of a component (the starter motor) using data mining methods and to create models that can predict the failure of that component. Based on workshop history data, error codes and operational data, three sets of classification models were built and evaluated. The first model aims to find patterns in a set of error codes, to see which codes are related to a starter motor failure. The second model aims to see if there are patterns in operational data that lead to the occurrence of an error code. Finally, the two data sets were merged and a classifier was trained and evaluated on this larger data set. Two machine learning algorithms were used and compared throughout the model building: AdaBoost and random forest. There is no statistically significant difference in their performance, and both algorithms had an error rate around ~13%, ~5% and ~13% for the three classification models respectively. However, random forest is much faster, and is therefore the preferable option for an industrial implementation. Variable analysis was conducted for the error codes and operational data, resulting in rankings of informative variables. From the evaluation metric precision, it can be derived that if our random forest model predicts a starter motor failure, there is a 85.7% chance that it actually has failed. This model finds 32% (the models recall) of the failed starter motors. It is also shown that four error codes; 2481, 2639, 2657 and 2597 have the highest predictive power for starter motor failure classification. For the operational data, variables that concern the starter motor lifetime and battery health are generally ranked as important by the models. The random forest model finds 81.9% of the cases where the 2481 error code occurs. If the random forest model predicts that the error code 2481 will occur, there is a 88.2% chance that it will. The classification performance was not increased when the two data sets were merged, indicating that the patterns detected by the two first classification models do not add value toone another.
28
Bitara, Matúš. "Srovnání heuristických a konvenčních statistických metod v data miningu." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2019. http://www.nusl.cz/ntk/nusl-400833.
Full textAbstract:
The thesis deals with the comparison of conventional and heuristic methods in data mining used for binary classification. In the theoretical part, four different models are described. Model classification is demonstrated on simple examples. In the practical part, models are compared on real data. This part also consists of data cleaning, outliers removal, two different transformations and dimension reduction. In the last part methods used to quality testing of models are described.
29
Rodrigue, Jason Adam. "Woody Species Diversity, Forest and Site Productivity, Stumpage Value, and Carbon Sequestration of Forests on Mined Lands Reclaimed Prior to the Passage of the Surface Mining Control and Reclamation Act of 1977." Thesis, Virginia Tech, 2001. http://hdl.handle.net/10919/35629.
Full textAbstract:
The present state of forestry post mining land uses has prompted concern among researchers, landowners, and the public. Surface mines reclaimed to forests under the provision of the Surface Mining Control and Reclamation Act (SMCRA) may not achieve site productivity levels required by the law. Anecdotal evidence suggests that many pre-law reforested mined sites are growing productive forests. The purpose of this study was to characterize these forests and the mine soils in which they are growing, and use them to benchmark forest development on mined land. Using 14 mined and 8 non-mined sites in the midwestern and eastern coalfields research to address the following objectives was undertaken: (i) characterize the development, composition, and diversity of woody species on pre-SMCRA, forested surface mined land; (ii) estimate forest and site productivity on surface mined land and determine the soil and site properties most influencing forest growth; (iii) estimate projected rotation-age timber product value; (iv) quantify current carbon sequestration pools associated with the developing woody plant biomass, the forest floor, and developing soil medium; (v) compare the diversity, forest and site productivity, commercial value, and carbon capture of reclaimed mined sites to that of regional non-mined forest systems.
Species richness between non-mined and mined sites was about the same within each region with 14 to 15 tree species in the canopy. Canopy richness of eastern mined sites was less than that on midwestern mined sites (12 species compared to 17 species, respectively). Species richness of the understory and woody ground layer were similar between sites planted to pines versus hardwoods. White pine (Pinus strobus) monocultures, planted on many sites in the eastern region, caused species unevenness throughout all forest strata. Midwestern mined sites and eastern sites planted to hardwoods closely approximated non-mined sites in commercial species composition. Planted species represented the majority of canopy layer dominance and abundance (82% relative dominance and 56% relative abundance). Site productivity between non-mined sites and 12 of the 14 mined sites was similar. Regression analysis identified the five most influential soil properties affecting site quality, which included soil profile base saturation, total coarse fragments, total available water, C horizon total porosity, and soil profile electrical conductivity. These five properties explained 52 % of the variation in tree growth. Forest productivity of these mined sites was equal to or greater than that of non-mined forests, ranging between 3.3 m3ha-1yr-1 and 12.1 m3ha-1yr-1. Management activities such as planting pine and valuable hardwood species increased the stumpage value of forests on reclaimed mine sites. Rotation-age stumpage values on mined study sites ranged between $3,064 ha-1 and $19,528 ha-1 and were commonly greater than stumpage values on non-mined reference sites. After 20 to 55 years, total site carbon levels on mined study sites averaged 217 Mg ha-1, while total carbon amounts on natural sites averaged 285 Mg ha-1. The amounts of carbon captured within the plant biomass and litter layer were the same on mined and natural sites. However, the soil carbon content of mined sites averaged 39 % lower than natural soils. The amount of carbon captured across mined sites was largely a function of forest stand age. Pre-SMCRA forests growing on mined sites with productivity levels similar to non-mined sites are capable of developing forest attributes comparable to or greater than those found on non-mined land within a period of 60 years, the length of a commercial hardwood rotation. These mature forests can serve as benchmarks for forest development on mined lands being reclaimed under current state and federal regulations.Master of Science
30
Costa, Julio César da. "Efeito de alterações do habitat na composição e estrutura da comunidade de aves de sub-bosque no Planalto Paulista, Sudeste do Brasil." Universidade de São Paulo, 2008. http://www.teses.usp.br/teses/disponiveis/11/11150/tde-15072008-130253/.
Full textAbstract:
Aves são um grupo tradicionalmente estudado em trabalhos de avaliação de impacto ambiental, os quais buscam entender efeitos de atividades antrópicas nas comunidades e/ou populações. Tal entendimento é fundamental para criar diretrizes para futuros empreendimentos ou ordenamento do uso do solo, com o objetivo de mitigar os efeitos negativos das atividades humanas. Nessa perspectiva, neste trabalho foram estudados dois efeitos em diferentes escalas na comunidade de aves de sub-bosque em região de Mata Atlântica no Planalto Paulista. O primeiro trabalho refere-se a uma escala ampla, na qual existe um gradiente de perda de habitat na paisagem amostrada, oriundo de diversas atividades humanas. No segundo procurou-se identificar os efeitos de atividades de mineração, numa escala mais restrita. Os resultados mostram que cerca de 50% das espécies de aves de sub-bosque devem se prejudicar com a perda de habitat e atingir níveis críticos de abundância ou se tornarem extintas em locais com baixa proporção de habitats florestais. Por outro lado, cerca de 30% das espécies tendem a se beneficiar com a perda de habitat e aumentar os tamanhos das populações. As espécies mais prejudicadas pela perda de habitat são as endêmicas do bioma Mata Atlântica e aquelas mais sensíveis a alterações no habitat. Quando analisado o gradiente de distância em relação a cava da Mina de extração de calcário, não foram verificadas diferenças significativas na riqueza e abundância total de aves e riqueza e abundância de grupos de sensibilidade a perturbações no habitat, o que sugere que as atividades da Mina não tenham um efeito tão drástico na comunidade de aves de sub-bosque. Porém, é sugerido que uma avaliação temporal das populações, assim como outros aspectos da comunidade, como reprodução, comportamento, consumo de frutos e dispersão de sementes, talvez sejam mais adequados para verificar os impactos da atividade de mineração na comunidade de aves na área estudada.Birds are one of the traditionally studied groups on environmental impact assessments, which seek to understand the effects of human activities on communities and/or populations. This understanding is essential to create guidelines for future enterprises or for planning the use of land, with the objective of mitigating the negative effects of human activities. From this perspective, this work studied two effects at different scales in the understory bird community of the Atlantic Forest in the Planalto Paulista. The first refers to a broad scale, in which there is a gradient of habitat loss in the sampled landscape resulting from various human activities. The second sought to identify the effects of the mining activities in a more delimited scale. The results show that about 50% of the understory bird community shall be affected by habitat loss and reach critical levels of abundance or become extinct in areas with low proportions of forest habitats. On the other hand, about 30% of the species tend to benefit from the habitat loss and increase the size of the population. The species most affected by the loss of habitat are those endemic to the Atlantic Forest and those most sensitive to changes in habitat. The analysis of the distance gradient from the limestone mine has found no significant differences in the richness and abundance of birds and richness and abundance of groups of sensitivity to disturbances in the habitat. That suggests that the mining has no drastic effect in the understory bird community. It is suggested that other aspects of the community, such as reproduction, behaviour, consumption of fruit and seed dispersal may be more appropriate for evaluating the impacts of the mining in the community of birds in the study area. Also, a time series evaluation of the sampled populations\' size might reveal fluctuations resulting from the activities in the mine.
31
Öberg, Johanna. "Time prediction and process discovery of administration process." Thesis, Uppsala universitet, Institutionen för biologisk grundutbildning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-432893.
Full textAbstract:
Machine learning and process mining are two techniques that are becoming more and more popular among organisations for business intelligence purposes. Results from these techniques can be very useful for organisations' decision-making. The Swedish National Forensic Centre (NFC), an organisation that performs forensic analyses, is in need of a way to visualise and understand its administration process. In addition, the organisation would like to be able to predict the time analyses will take to perform. In this project, it was evaluated if machine learning and process mining could be used on NFC's administration process-related data to satisfy the organisation's needs. Using the process mining tool Mehrwerk Process Mining implemented in the software Qlik Sense, different process variants were discovered from the data and visualised in a comprehensible way. The process variants were easy to interpret and useful for NFC. Machine learning regression models were trained on the data to predict analysis length. Two different datasets were tried, a large dataset with few features and a smaller dataset with more features. The models were then evaluated on test datasets. The models did not predict the length of analyses in an acceptable way. A reason to this could be that the information in the data was not sufficient for this prediction.
32
Rabeiy, Ragab Elsayed [Verfasser]. "Spatial modeling of heavy metal pollution of forest soils in an historical mining area using geostatistical methods and air despersion modeling / Ragab Elsayed Rabeiy." Clausthal-Zellerfeld : Universitätsbibliothek Clausthal, 2010. http://d-nb.info/1007800925/34.
Full text
33
Kwame, Osei Eric. "Machine Learning-based Quality Prediction in the Froth Flotation Process of Mining : Master’s Degree Thesis in Microdata Analysis." Thesis, Högskolan Dalarna, Mikrodataanalys, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:du-31643.
Full textAbstract:
In the iron ore mining fraternity, in order to achieve the desired quality in the froth flotation processing plant, stakeholders rely on conventional laboratory test technique which usually takes more than two hours to ascertain the two variables of interest. Such a substantial dead time makes it difficult to put the inherent stochastic nature of the plant system in steady-state. Thus, the present study aims to evaluate the feasibility of using machine learning algorithms to predict the percentage of silica concentrate (SiO2) in the froth flotation processing plant in real-time. The predictive model has been constructed using iron ore mining froth flotation system dataset obtain from Kaggle. Different feature selection methods including Random Forest and backward elimination technique were applied to the dataset to extract significant features. The selected features were then used in Multiple Linear Regression, Random Forest and Artificial Neural Network models and the prediction accuracy of all the models have been evaluated and compared with each other. The results show that Artificial Neural Network has the ability to generalize better and predictions were off by 0.38% mean square error (mse) on average, which is significant considering that the SiO2 range from 0.77%- 5.53% -( mse 1.1%) . These results have been obtained within real-time processing of 12s in the worst case scenario on an Inter i7 hardware. The experimental results also suggest that reagents variables have the most significant influence in SiO2 prediction and less important variable is the Flotation Column.02.air.Flow. The experiments results have also indicated a promising prospect for both the Multiple Linear Regression and Random Forest models in the field of SiO2 prediction in iron ore mining froth flotation system in general. Meanwhile, this study provides management, metallurgists and operators with a better choice for SiO2 prediction in real-time per the accuracy demand as opposed to the long dead time laboratory test analysis causing incessant loss of iron ore discharged to tailings.
34
Allen, Jared Seth. "DETERMINING SOUTH MISSISSIPPI FOREST SUSCEPTIBILITY TO WINDTHROW AND SHEAR DAMAGE IN A HURRICANE ENVIRONMENT THROUGH DATA MINING OF METEOROLOGICAL, PHYSIOGRAPHICAL,PEDOLOGICAL, AND TREE LEVEL DATA." MSSTATE, 2009. http://sun.library.msstate.edu/ETD-db/theses/available/etd-08262009-143122/.
Full textAbstract:
An estimated 39 million m3 of timber was damaged across the Southeast Forest District of Mississippi due to Hurricane Katrina. Aggregated forest plot-level biometrics was coupled with wind, topographical, and soil attributes using a GIS. Data mining through Regression Tree Analysis (RTA) was used to determine factors contributing to shear damage of pines and wind-throw damage of hardwoods. Results depict Loreys Mean Height (LMH) and Quadratic Mean Diameter (QMD) are important variables in determining the percentage of trees and basal area damaged for both forest classes with sustained wind speed important for wind-throw and peak wind gusts for shear. Logistic regression based on stand damage classification compared to RTA revealed LMH, stand height to diameter ratio, and sustained wind variable concurrence. Reclassification of MIFI plot damage calls based on percentage of trees damaged increased predictability of wind-throw and shear classification. This research can potentially aid emergency and forest managers for better mitigation and recovery decisions following a hurricane.
35
Mistry, Pritesh. "A Knowledge Based Approach of Toxicity Prediction for Drug Formulation. Modelling Drug Vehicle Relationships Using Soft Computing Techniques." Thesis, University of Bradford, 2015. http://hdl.handle.net/10454/14440.
Full textAbstract:
This multidisciplinary thesis is concerned with the prediction of drug formulations for the reduction of drug toxicity. Both scientific and computational approaches are utilised to make original contributions to the field of predictive toxicology. The first part of this thesis provides a detailed scientific discussion on all aspects of drug formulation and toxicity. Discussions are focused around the principal mechanisms of drug toxicity and how drug toxicity is studied and reported in the literature. Furthermore, a review of the current technologies available for formulating drugs for toxicity reduction is provided. Examples of studies reported in the literature that have used these technologies to reduce drug toxicity are also reported. The thesis also provides an overview of the computational approaches currently employed in the field of in silico predictive toxicology. This overview focuses on the machine learning approaches used to build predictive QSAR classification models, with examples discovered from the literature provided. Two methodologies have been developed as part of the main work of this thesis. The first is focused on use of directed bipartite graphs and Venn diagrams for the visualisation and extraction of drug-vehicle relationships from large un-curated datasets which show changes in the patterns of toxicity. These relationships can be rapidly extracted and visualised using the methodology proposed in chapter 4. The second methodology proposed, involves mining large datasets for the extraction of drug-vehicle toxicity data. The methodology uses an area-under-the-curve principle to make pairwise comparisons of vehicles which are classified according to the toxicity protection they offer, from which predictive classification models based on random forests and decisions trees are built. The results of this methodology are reported in chapter 6.
36
Gurung, Kumari. "ASSESSING ECOSYSTEM SERVICES FROM THE FORESTRY-BASED RECLAMATION OF SURFACE MINED AREAS IN THE NORTH FORK OF THE KENTUCKY RIVER WATERSHED." UKnowledge, 2018. https://uknowledge.uky.edu/forestry_etds/43.
Full textAbstract:
Land Use Land Cover (LULC) changes can take place at the expense of degrading environmental conditions and undermining ecosystem’s capacity to deliver benefits to people. In the Appalachian region, surface mining for coal is a major driver of LULC change. The Surface Mining Control and Reclamation Act (SMCRA) of 1977 requires mine site reclamation but typical reclamation practices often result in land cover dominated by grass and shrubs. The Forestry Reclamation Approach (FRA) is a promising reclamation strategy but not in widespread use by industry. Assessing ecosystem services that can be obtained from a forest landscape may help policy-makers and other stakeholders fully understand the benefits of forestry based reclamation. The objectives of this study are to 1) identify how surface mining and reclamation changed the LULC of a watershed encompassing the north fork of the Kentucky River 2) assess the biophysical value of four major ecosystem services under the contemporary LULC condition and 3) assess the benefits of the FRA scenario in the provision of ecosystem services. Geographic Information System (GIS) was used to study the LULC change and InVEST software models for ecosystem services assessment. The results indicate that watershed’s forest area has decreased by 7,751 hectares from 2001 to 2011 and mining activity may have contributed 75% of the change in LULC. Barren and grassland land covers provide less carbon storage, yield more water, and export more sediments and nutrients than forests. At the watershed level, the FRA modeled scenario increased carbon storage (13%) and reduced water yield (5%), sediment export (40%) and nutrient export (7%). This study provides critical information regarding the ecological benefits of Forestry Reclamation Approach to assist policy and decision making in this region even considering the modeling and data limitations.
37
Fernandez, Sanchez Javier. "Knowledge Discovery and Data Mining Using Demographic and Clinical Data to Diagnose Heart Disease." Thesis, KTH, Skolan för kemi, bioteknologi och hälsa (CBH), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233978.
Full textAbstract:
Cardiovascular disease (CVD) is the leading cause of morbidity, mortality, premature death and reduced quality of life for the citizens of the EU. It has been reported that CVD represents a major economic load on health care sys- tems in terms of hospitalizations, rehabilitation services, physician visits and medication. Data Mining techniques with clinical data has become an interesting tool to prevent, diagnose or treat CVD. In this thesis, Knowledge Dis- covery and Data Mining (KDD) was employed to analyse clinical and demographic data, which could be used to diagnose coronary artery disease (CAD). The exploratory data analysis (EDA) showed that female patients at an el- derly age with a higher level of cholesterol, maximum achieved heart rate and ST-depression are more prone to be diagnosed with heart disease. Furthermore, patients with atypical angina are more likely to be at an elderly age with a slightly higher level of cholesterol and maximum achieved heart rate than asymptotic chest pain patients. More- over, patients with exercise induced angina contained lower values of maximum achieved heart rate than those who do not experience it. We could verify that patients who experience exercise induced angina and asymptomatic chest pain are more likely to be diagnosed with heart disease. On the other hand, Logistic Regression, K-Nearest Neighbors, Support Vector Machines, Decision Tree, Bagging and Boosting methods were evaluated by adopting a stratified 10 fold cross-validation approach. The learning models provided an average of 78-83% F-score and a mean AUC of 85-88%. Among all the models, the highest score is given by Radial Basis Function Kernel Support Vector Machines (RBF-SVM), achieving 82.5% ± 4.7% of F-score and an AUC of 87.6% ± 5.8%. Our research con- firmed that data mining techniques can support physicians in their interpretations of heart disease diagnosis in addition to clinical and demographic characteristics of patients.
38
Badayos, Noah Garcia. "Machine Learning-Based Parameter Validation." Diss., Virginia Tech, 2014. http://hdl.handle.net/10919/47675.
Full textAbstract:
As power system grids continue to grow in order to support an increasing energy demand, the system's behavior accordingly evolves, continuing to challenge designs for maintaining security. It has become apparent in the past few years that, as much as discovering vulnerabilities in the power network, accurate simulations are very critical. This study explores a classification method for validating simulation models, using disturbance measurements from phasor measurement units (PMU). The technique used employs the Random Forest learning algorithm to find a correlation between specific model parameter changes, and the variations in the dynamic response. Also, the measurements used for building and evaluating the classifiers were characterized using Prony decomposition. The generator model, consisting of an exciter, governor, and its standard parameters have been validated using short circuit faults. Single-error classifiers were first tested, where the accuracies of the classifiers built using positive, negative, and zero sequence measurements were compared. The negative sequence measurements have consistently produced the best classifiers, with majority of the parameter classes attaining F-measure accuracies greater than 90%. A multiple-parameter error technique for validation has also been developed and tested on standard generator parameters. Only a few target parameter classes had good accuracies in the presence of multiple parameter errors, but the results were enough to permit a sequential process of validation, where elimination of a highly detectable error can improve the accuracy of suspect errors dependent on the former's removal, and continuing the procedure until all corrections are covered.Ph. D.
39
Johansson, Fredrik, and Markus Lindgren. "Hybridmodeller för prediktiv modellering skapade med genetisk programmering." Thesis, Högskolan i Borås, Institutionen Handels- och IT-högskolan, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-17316.
Full textAbstract:
Det finns idag ett stort behov av att kunna klassificera stora mängder data på ett effektivt sätt. Prediktiv modellering är ett område inom data mining där prediktioner kan utföras baserat på tidigare erfarenheter. Dessa prediktioner presenteras sedan i en modell. Avvägningen mellan tolkningsbarhet och träffsäkerhet är ett begrepp som beskriver hur träffsäkra modeller ofta är ogenomskinliga, medan genomskinliga modeller ofta har lägre träffsäkerhet. Detta är ett problem eftersom det finns ett behov av modeller som är både träffsäkra och tolkningsbara.I denna studie visas hur man kan gå till väga för att skapa en modell som har en träffsäkerhet i klass med en ogenomskinlig modell, men samtidigt har en högre tolkningsbarhet. Två algoritmer presenteras för att ta fram en hybridmodell som bygger på beslutsträd där en implementering av Random Forest hanteras som alternativa lövnoder. Kontrollerade experiment och statistiska tester genomfördes för att mäta hybridmodellens träffsäkerhet mot träffsäkerheten hos J48 och Random Forest. Träffsäkerheten mättes även mot beslutsträd som genererats av den genetiska programmeringen som finns implementerad i ramverket G-REX.Resultatet visar att hybridmodellen kan uppnå en träffsäkerhet som är jämförbar med Random Forest men samtidigt hanterar de vanliga prediktionslöven i genomsnitt 39,21% av instanserna. Alltså är den hybridmodell som presenteras i studien mer tolkningsbar än Random Forest utan att ha någon signifikant skillnad i träffsäkerhet.Program: Systemarkitekturutbildningen
40
Lamprou, Sokrates. "A study in alcohol : A comparison of data mining methods for identifying binge drinking risk factors in university students." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-174087.
Full textAbstract:
Hazardous alcohol consumption is an issue that affects a lot of university students today. Consuming alcohol tend to have a negative impact on both mental and physical aspects, which can lead to severe alcohol addictions in the future. This study investigates which background factors that causes the phenomenon of binge drinking by collecting and analysing data from Linköping University. The results were analysed with data mining techniques such as: decision trees, random forest, and logistic regression. The results showed that logistic regression were the most reliable method in predicting binge drinking with an accuracy of (86.50 %), precision (92.64 %) and recall (90.96 %). The findings also showed that participation in student events together with higher weekly alcohol consumption predicted binge drinking. Additionally, other risk factors were the amounts of time the students spent with their friends and the students activity in partaking in their programs section (program association). The results from this study suggest that the student culture not only influence alcohol consumption but it induces the habits of binge drinking.
41
Bleby, Timothy Michael. "Water use, ecophysiology and hydraulic architecture of Eucalyptus marginata (jarrah) growing on mine rehabilitation sites in the jarrah forest of south-western Australia." University of Western Australia. School of Plant Biology, 2003. http://theses.library.uwa.edu.au/adt-WU2004.0004.
Full textAbstract:
[Truncated abstract. Please see the pdf format for the complete text. Also, formulae and special characters can only be approximated here. Please see the pdf version for an accurate reproduction.] This thesis examines the water use, ecophysiology and hydraulic architecture of Eucalyptus marginata (jarrah) growing on bauxite mine rehabilitation sites in the jarrah forest of south-western Australia. The principal objective was to characterise the key environment and plant-based influences on tree water use, and to better understand the dynamics of water use over a range of spatial and temporal scales in this drought-prone ecosystem. A novel sap flow measurement system (based on the use of the heat pulse method) was developed so that a large number of trees could be monitored concurrently in the field. A validation experiment using potted jarrah saplings showed that rates of sap flow (transpiration) obtained using this system agreed with those obtained gravimetrically. Notably, diurnal patterns of transpiration were measured accurately and with precision using the newly developed heat ratio method. Field studies showed that water stress and water use by jarrah saplings on rehabilitation sites were strongly seasonal: being greatest in summer when it was warm and dry, and least in winter when it was cool and wet. At different times, water use was influenced by soil water availability, vapour pressure deficit (VPD) and plant hydraulic conductance. In some areas, there was evidence of a rapid decline in transpiration in response to dry soil conditions. At the end of summer, most saplings on rehabilitation sites were not water stressed, whereas water status in the forest was poor for small saplings but improved with increasing size. It has been recognised that mature jarrah trees avoid drought by having deep root systems, however, it appears that saplings on rehabilitation sites may have not yet developed functional deep roots, and as such, they may be heavily reliant on moisture stored in surface soil horizons. Simple predictive models of tree water use revealed that stand water use was 74 % of annual rainfall at a high density (leaf area index, LAI = 3.1), high rainfall (1200 mm yr-1) site, and 12 % of rainfall at a low density (LAI = 0.4), low rainfall (600 mm yr-1) site, and that water use increased with stand growth. A controlled field experiment confirmed that: (1) sapling transpiration was restricted as root-zone water availability declined, irrespective of VPD; (2) transpiration was correlated with VPD when water was abundant; and (3) transpiration was limited by soil-to-leaf hydraulic conductance when water was abundant and VPD was high (> 2 kPa). Specifically, transpiration was regulated by stomatal conductance. Large stomatal apertures could sustain high transpiration rates, but stomata were sensitive to hydraulic perturbations caused by soil water deficits and/or high evaporative demand. No other physiological mechanisms conferred immediate resistance to drought. Empirical observations were agreeably linked with a current theory suggesting that stomata regulate transpiration and plant water potential in order to prevent hydraulic dysfunction following a reduction in soil-to-leaf hydraulic conductance. Moreover, it was clear that plant hydraulic capacity determined the pattern and extent of stomatal regulation. Differences in hydraulic capacity across a gradient in water availability were a reflection of differences in root-to-leaf hydraulic conductance, and were possibly related to differences in xylem structure. Saplings on rehabilitation sites had greater hydraulic conductance (by 50 %) and greater leaf-specific rates of transpiration at the high rainfall site (1.5 kg m-2 day1) than at the low rainfall site (0.8 kg m-2 day1) under near optimal conditions. Also, rehabilitation-grown saplings had significantly greater leaf area, leaf area to sapwood area ratios and hydraulic conductance (by 30-50 %) compared to forest-grown saplings, a strong indication that soils in rehabilitation sites contained more water than soils in the forest. Results suggested that: (1) the hydraulic structure and function of saplings growing under the same climatic conditions was determined by soil water availability; (2) drought reduced stomatal conductance and transpiration by reducing whole-tree hydraulic conductance; and (3) saplings growing on open rehabilitation sites utilised more abundant water, light and nutrients than saplings growing in the forest understorey. These findings support a paradigm that trees evolve hydraulic equipment and physiological characteristics suited to the most efficient use of water from a particular spatial and temporal niche in the soil environment.
42
Schmidt, Anel. "Strip-mine rehabilitation in Namaqualand." Thesis, Stellenbosch : Stellenbosch University, 2002. http://hdl.handle.net/10019.1/53068.
Full textAbstract:
Thesis (MScFor)--Stellenbosch University, 2002.ENGLISH ABSTRACT: Namaqualand has a very unusual diversity of plant life, with many endemic plant species. The fundamental question of this thesis is how this system, damaged by strip-mining activities, can be rehabilitated. The aim was to base the rehabilitation methods on ecological processes. In order to answer this question an overview of the relevant literature was needed in order to identify possible research needs and also to evaluate the work that has been done in the field of strip-mine rehabilitation in arid areas. An understanding of community and ecosystem dynamics would help to establish aims and methods for site-specific rehabilitation. In Namaqualand, South Africa, there is also a need for experimentation to establish which of the many factors is most limiting to long-term ecosystem recovery. It is important to have a good knowledge of the successional processes and disturbance history of the land which needs to be rehabilitated. The vegetation on unmined areas and mined areas of different ages and treatments after mining, were sampled. It was shown that some areas could be expected to show a large degree of recovery in the space of a few years, whilst others would show little or no recovery over a period of decades. It is important to recognise rehabilitation as a gradual process that takes place at different rates in different areas and in different years. The planting of Atriplex nummularia and sowing of Atriplex semibaccata did not facilitate the return of indigenous, perennial species, but rather seem to inhibit their return. In view of the importance of topsoil in terms of the fertility of the soil and the seed bank present in the topsoil, the influence of topsoil removal and stockpiling due to strip-mining activities were tested. The soil fertility was tested by means of radish bioassays and soil laboratory analysis, whilst species diversity and richness were tested with seedling emergence trials. As expected a higher plant species diversity was found on the unmined soils and radishes grew larger on these soils. The topsoil deteriorated in terms of plant species richness, diversity and soil fertility whilst it was stockpiled. Direct replacement of topsoil would ensure a planting medium closer to the pre-disturbance level that could lead to fairly rapid and successful recolonization of the mined area. Successful plant recruitment also depends on the microsites to which seeds are dispersed. The effect that different microsites had on seed germination, seedling growth and survival was tested. It was found that micro catchments always yielded the highest numbers. The establishment and survival of seedlings in the other microsite types (under single shrubs, under clumped shrubs and in the open) varied, depending on the amount of rainfall received in the particular year. Lastly, I experimented with the translocation of three local, indigenous, succulent plant species. These plants were transplanted either in clumps of three together or alone, since I hypothesized that planting them together would facilitate their survival. However, it was found that it depended largely on the morphology of the plant and the amount of rainfall received in a particular year, whether these plants will compete with each other for limiting resources or facilitate each other's survival. The thesis contributes to the understanding of vegetation dynamics in the Succulent Karoo after strip-mining has taken place. Guidelines are provided based on ecological processes, for strip-mine rehabilitation in the Succulent Karoo.
AFRIKAANSE OPSOMMING: Namakwaland is bekend vir sy ongewone diversiteit van plante, met baie endemiese spesies. Die fundamentele vraag wat deur hierdie tesis gevra word is hoe hierdie sisteem, wat beskadig is deur oppervlak mynbou, gerehabiliteer kan word. Die doel is om die rehabilitasie metodes te baseer op ekologiese prosesse. 'n Oorsig van die relevante literatuur was nodig om moontlike areas van verdere navorsing te identifiseer en ook die navorsing wat reeds gedoen is oor rehabilitasie van oppervlak myne in ariede gebiede, te evalueer. 'n Goeie begrip van gemeenskap en ekosisteem dinamika sal help om doelwitte en metodes daar te stel vir die rehabilitasie van spesifieke areas. Dit is ook nodig om in Namakwaland, Suid -Afrika, uit te vind watter van die baie faktore, die lang-termyn herstel van 'n ekosisteem, die meeste verhinder. Dit is baie belangrik om In goeie kennis te hê van die versteurings geskiedenis van die area wat gerehabiliteer moet word, asook die suksessionele prosesse wat werksaam is. Plantegroei van areas wat op verskillende tye gemyn en verskillend behandel is, asook ongemynde areas is ondersoek. Sekere areas het In groot mate van herstel gewys in 'n tydperk van 'n paar jaar, terwyl ander, min of geen hersteloor 'n periode van dekades getoon het nie. Dit is belangrik om rehabilitasie as 'n geleidelike proses te sien, wat teen verskillende tempos plaasvind tydens verskillende jare en in verskillende areas. Daar is bevind dat die plant van Atriplex nummularia asook die saai van Atriplex semibaccata nie die terugkeer van inheemse, meerjarige spesies bevoordeel nie, maar dit eerder inhibeer. Aangesien die bo-grond so belangrik is in terme van die grondvrugbaarheid en ook die saadbank wat teenwoordig is, word die invloed van die verwydering en opberging van die bogrond getoets. Die grondvrugbaarheid was bepaal deur groei-toetse op radyse en laboratorium analise op die grond te doen. Die plant spesie diversiteit en rykheid was bepaal met In saad ontkieming studie. In ooreenstemming met die verwagte uitkoms, was die plant spesie diversiteit hoër op die ongemynde bo-grond en die radyse het groter geword op dieselfde grond. Dit kom voor asof die plant spesie diversiteit en rykheid, asook die grond vrugbaarheid afneem met tyd wat die bo-grond geberg word. Die direkte verspreiding van die bo-grond nadat dit verwyder is, sal In medium vir die plante verseker wat nader is aan die vlak voordat die grond versteur is. Dit sal oak sorg vir redelike vinnige en suksesvolle terugkoms van plante op die gemynde grond. Die suksesvolle vestiging van plante hang ook af van die mikro areas (klein areas in terme van die grootte van 'n saad, wat In eie mikro-klimaat vorm), waarna saad versprei word. Die effek van sulke mikro-gebiede op die ontkieming van saad, die groei van die saailinge en die oorlewing van die saailinge was bepaal. Mikro-water- opvanggebiede het in al drie bogenoemde gevalle die hoogste syfers getoon. Die vestiging en oorlewing van saailinge in die ander mikro-gebiede (die area onder enkel struike, die area onder groepe struike en oop areas) het gevarieer afhangend van die hoeveelheid reënval wat ontvang is in die spesifieke jaar. Laastens, is daar ge-eksperimenteer met die oorplant van drie plaaslike, inheemse, sukkulente spesies. Hierdie plante was alleen geplant of in groepies van drie, bymekaar. Die hipotese was dat huloorlewingskanse beter sal wees as hulle saam geplant word. Dit was egter bevind dat die hoeveelheid reënval in 'n spesifieke jaar en die morfologie van die plant, bepaal of hulle sal kompeteer vir die beperkte bronne en of hulle deur saam te groei huloorlewingskanse sal verhoog. Hierdie tesis dra by tot die verstaan van die plantegroei dinamika in die Sukkulente Karoo nadat oppervlak mynbou plaasgevind het. Riglyne vir die rehabilitasie van oppervlak myne, gebasseer op ekologiese prosesse, word ook voorgestel.
43
Subburayalu, Sakthi Kumaran. "Application of machine learning for soil survey updates a case study in southeastern Ohio /." Columbus, Ohio : Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1199992659.
Full text
44
BOOTH, Micael Cortopassi. "Cen?rios de ?reas degradadas em recupera??o na FLONA do Jamari/RO." Universidade Federal Rural do Rio de Janeiro, 2017. https://tede.ufrrj.br/jspui/handle/jspui/2232.
Full textAbstract:
Submitted by Jorge Silva (jorgelmsilva@ufrrj.br) on 2018-03-23T18:33:28Z
No. of bitstreams: 1
2017 - Micael Cortopassi Booth.pdf: 3109489 bytes, checksum: 01bce83a5a84e68b19faf1907d31a751 (MD5)Made available in DSpace on 2018-03-23T18:33:28Z (GMT). No. of bitstreams: 1 2017 - Micael Cortopassi Booth.pdf: 3109489 bytes, checksum: 01bce83a5a84e68b19faf1907d31a751 (MD5) Previous issue date: 2017-02-22
CAPES
The use of geotechnologies assists in the monitoring and quantification of the development and modification of the landscape. The Amazon region has high diversity and plant richness and it is in this biome that is the study area, in the National Forest of Jamari, is a Conservation Unit of Multiple Use. In this FLONA there are eight mines under a PRAD because there has been since the 1960s the exploration and mining of cassiterite to obtain tin. The opening of cavas for the exploration is done in the open, performed almost mechanically, leaving the environment at the end very degraded and its restoration demands resources and time. In general, the recovery of the landscape of an area of cultivation is done with the use of planting heterogenous species of the same biome, aiming to cover the soil and induce natural regeneration. In the areas of mines the type of substrate influences in the development and fixation of the vegetal species in the area. The objectives were to map the soil cover, the creation of future scenarios of revegetation using a prediction program. In these mines the types of substrates that were classified in tillage (PL), dry tail (RS), wet tail (RU), washed tail and washing plant (WP) were mapped. Using four high spatial resolution images of the years 2009, 2011, 2013 and 2015, the typologies were classified as soil exposed, field dirty, capoeira, vegetation thin, intermediate, dense. The areas occupied by each typology for each of the years studied in the mines were compared in order to quantify the converted areas of exposed soil in vegetated areas and the dynamics of the present vegetation cover. Future scenarios for the years 2020 to 2065 were modeled using the Dinamica-EGO, a program used for simulation and prediction of natural environments in particular deforestation. The validation of the generated maps was done using fuzzy similarity. The results obtained for the future scenarios were similar to those observed and the dynamics of the five typologies used evolved in a manner consistent with that observed, with some mines having a better development in a shorter time according to the type of substrate and age of the plantations.
A utiliza??o de geotecnologias auxilia no acompanhamento e quantifica??o do desenvolvimento e modifica??o da paisagem. A regi?o Amaz?nica tem alta diversidade e riqueza vegetal e ? nesse bioma que est? a ?rea de estudo, na Florestal Nacional do Jamari, uma Unidade de Conserva??o de uso m?ltiplo. Nessa FLONA h? oito minas sob um PRAD pois houve desde a d?cada de 1960 a explora??o e lavra de cassiterita para obten??o de estanho. A abertura de cavas para a explora??o ? feita a c?u aberto, realizada de forma quase toda mec?nica, ficando o ambiente ao final muito degradado e sua restaura??o demanda recursos e tempo. De modo geral, a recupera??o da paisagem de uma ?rea de lavra ? feita com o uso de plantio de esp?cies heterogenias do mesmo bioma, visando recobrir o solo e induzir a regenera??o natural. Nas ?reas de minas o tipo de substrato influencia no desenvolvimento e fixa??o das esp?cies vegetais na ?rea. Os objetivos foram mapear a cobertura do solo, a cria??o de cen?rios futuros de revegeta??o usando um programa de predi??o. Nestas minas foram mapeados os tipos de substratos que s?o classificadas em piso de lavra (PL), rejeito seco (RS), rejeito ?mido (RU), rejeito capeado e washing plant (WP). Utilizando quatro imagens de alta resolu??o espacial dos anos 2009, 2011, 2013 e 2015, foram classificados as tipologias solo exposto, campo sujo, capoeira, vegeta??o rala, intermedi?ria, densa. As ?reas ocupadas por cada tipologia, para cada um dos anos estudados nas minas foram comparados visando quantificar as ?reas convertidas de solo exposto em ?reas vegetadas e a din?mica da cobertura vegetal presente. Cen?rios futuros para os anos de 2020 a 2065 foram modelados utilizando o Din?mica-EGO, programa utilizado para simula??o e predi??o de ambientes naturais em especial desmatamento. A valida??o dos mapas gerados foi feita utilizando similaridade fuzzy. Os resultados obtidos para os cen?rios futuros foram em similares ao observado e a din?mica das cinco tipologias utilizadas evolu?ram de forma condizente com o observado, tendo algumas minas melhor desenvolvimento em um menor tempo de acordo com o tipo de substrato e idade dos plantios.
45
Pedron, Leandra. "MIRMECOFAUNA EM ÁREA DE MINERAÇÃO DE CARVÃO NO RIO GRANDE DO SUL." Universidade Federal de Santa Maria, 2016. http://repositorio.ufsm.br/handle/1/8775.
Full textAbstract:
Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorThe aim of this study was to evaluate the biodiversity of ants in coal mining area in the city of Candiota, Rio Grande do Sul. Thus, two methods of sampling were used and, as a result, this work was divided into two chapters. In the first chapter, the survey of the mirmecofauna was carried out monthly with attractive bait in the period from July 2014 to June 2015. It was used the Completely Randomized Design (CRD) with seven treatments, which are: native grassland, non-mined area; native grassland, mined area; plantation of Acacia mearnsii, non-mined area; plantation of Acacia mearnsii, mined area; plantation of Eucalyptus dunnii, non-mined area; plantation of Eucalyptus dunnii, mined area 1; and plantation of Eucalyptus dunnii, mined area 2. Each treatment was composed of 10 baits, in every date of collection. 35,389 specimens belonging to five subfamilies, nine tribes, 15 genera and 40 species were collected. In the area with native grassland, non-mined area, there was the largest number of species and the in the planted area of Acacia mearnsii, mined area, there was the highest level of species richness (Sobs = 25). There was no statistical difference between the mean plenty of treatments, but there was a difference between the means of richness of the treatments. The genera such as Pheidole, Camponotus and Solenopsis were the most abundant in all treatments. It is concluded that nonmined areas and mined areas that passed through the recovery process does not interfere with the total of collected specimens and species richness. In the second chapter, soil mirmecofauna sampling was carried out with use of Berlese Funnel. The survey was performed monthly from July 2014 to June 2015. CRD was used in six treatments: native grassland, non-mined area; native grassfield, mined area; plantation of Acacia mearnsii, non-mined area; plantation of Acacia mearnsii, mined area; plantation of Eucalyptus dunnii, non-mined area; and plantation of Eucalyptus dunnii, mined area. Four soil samples were collected in each treatment, in every date of collection. In the laboratory, the samples were placed in Berlese Funnels, where they remained seven days under incandescent light. 2,105 specimens were collected, divided into four subfamilies, eight tribes, 16 genera and 31 species. The highest abundance and the largest number of collected species was in the area with native grassland, non-mined area (Sobs = 18). There was statistical difference between the means of abundance and species richness among treatments. Thus, it is possible to conclude that the total number of collected and the richness of specimens differ between mined and non-mined areas.
O objetivo deste trabalho foi avaliar a biodiversidade de formigas em área de mineração de carvão, no município de Candiota, Rio Grande do Sul. Para isso foram utilizados dois métodos de amostragem e assim este trabalho foi dividido em dois capítulos. No primeiro capítulo, o levantamento da mirmecofauna foi realizado mensalmente com isca atrativa, no período de julho de 2014 a junho de 2015. Foi utilizado Delineamento Inteiramente Casualizado (DIC) com sete tratamentos, sendo eles: campo nativo, área não minerada; campo nativo, área minerada; plantio de Acacia mearnsii, área não minerada; plantio de Acacia mearnsii, área minerada; plantio de Eucalyptus dunnii, área não minerada; plantio de Eucalyptus dunnii, área minerada 1; e plantio de Eucalyptus dunnii, área minerada 2. Cada tratamento esteve constituído por 10 iscas, a cada data de coleta. Foram coletados 35.389 espécimes, pertencentes à cinco subfamílias, nove tribos, 15 gêneros e 40 espécies. Na área com campo nativo, área não minerada observou-se o maior número de espécimes e na área plantio de Acacia mearnsii, área minerada a maior riqueza de espécies (Sobs = 25). Não houve diferença estatística entre as médias de abundância dos tratamentos, mas houve diferença entre as médias de riqueza dos tratamentos. Os gêneros Pheidole, Camponotus e Solenopsis foram os mais abundantes em todas as tratamentos. Conclui-se que as áreas não mineradas e as áreas mineradas que sofreram o processo de recuperação não interferem no total de espécimes coletados e na riqueza de espécies. No segundo capítulo, foi realizada amostragem da mirmecofauna de solo com utilização de Funil de Berlese. O levantamento foi realizado mensalmente de julho de 2014 a junho de 2015. O delineamento utilizado foi DIC com seis tratamentos: campo nativo, área não minerada; campo nativo, área minerada; plantio de Acacia mearnsii, área não minerada; plantio de Acacia mearnsii, área minerada; plantio de Eucalyptus dunnii, área não minerada; e plantio de Eucalyptus dunnii, área minerada. Foram coletadas quatro amostras de solo em cada tratamento, em cada data de coleta. Em laboratório, essas amostras foram colocadas em funis de Berlese, onde permaneceram sete dias sob luz incandescente. Foram coletados 2.105 espécimes, distribuídos em quatro subfamílias, oito tribos, 16 gêneros e 31 espécies. A maior abundância e o maior número de espécies coletadas foi na área com campo nativo, área não minerada (Sobs = 18). Houve diferença estatística entre as médias de abundância e riqueza de espécies entre os tratamentos. Assim, pode-se concluir que o total de espécimes de formigas coletadas e a riqueza de espécies diferem entre as áreas mineradas e não mineradas.
46
Manilich, Elena A. "Hereditary Colorectal Cancer: Information-Based Approach." Cleveland, Ohio : Case Western Reserve University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=case1252247671.
Full textAbstract:
Thesis(Ph.D.)--Case Western Reserve University, 2010Title from PDF (viewed on 2009-12-30) Department of Electrical Engineering and Computer Science Includes abstract Includes bibliographical references and appendices Available online via the OhioLINK ETD Center
47
Silva, Edmilson Alves da. "Avalia??o da recupera??o natural de ?reas degradadas pelo garimpo de diamante no Vale do Rio S?o Jos? em Len??is/BA." Universidade Estadual de Feira de Santana, 2013. http://localhost:8080/tede/handle/tede/198.
Full textAbstract:
Submitted by Verena Bastos (verena@uefs.br) on 2015-09-16T22:20:18Z
No. of bitstreams: 1
Disserta??o finalpdf.pdf: 1860889 bytes, checksum: ee87b81fe0a21430df0bad836a2fe39f (MD5)Made available in DSpace on 2015-09-16T22:20:18Z (GMT). No. of bitstreams: 1 Disserta??o finalpdf.pdf: 1860889 bytes, checksum: ee87b81fe0a21430df0bad836a2fe39f (MD5) Previous issue date: 2013-03-27
Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior - CAPES
The present work examined the floristic compositions and structures, and the similarities between seven areas degraded by mechanized diamond mining along the S?o Jos? River Valley (12o34? to 12?36? S - 41o22? to 41?35? W), in the municipality of Len??is, Bahia State, Brazil, after 23 years of abandonment and natural regeneration and compared them to an area of intact gallery forest along the same river. The collections were made between the months of April and December/2011 along 1 x 100 m transects established in each of the seven areas, applying the point method. A previously compiled species list was used to compare the seven recovering areas with an intact riverine forest site. A total of 62 species were encountered, distributed among 53 genera and 26 families. The families demonstrating the greatest species richness were Leguminosae (16), Poaceae (11), Cyperaceae (7), Melastomataceae (6), Malvaceae (4), and Lycopodiaceae (2). The sum of the richnesses of these families represented fully 74% of the total number of species recorded in the present study. In terms of the plant habits, 11 species (15%) were arboreal, 17 (26%) shrubs, 28 (42%) herbaceous, 07(11%) sub-shrubs, and 04 (6%) vines. The species demonstrating the greatest Relative Vigor and Cover were Sebastiania corniculata, Aristida setifolia, and Homolepis aturensis. The slow natural regeneration of these areas was apparently due to the modification of the soil structure by the mechanized mining, as judged by the greater similarity (although low) between the areas regenerating for the longest periods and the intact gallery forest site along the same river as performing solo one little more structured.c
Este trabalho verificou a composi??o flor?stica, estrutura e similaridade entre sete ?reas degradadas pelo garimpo de diamantes no vale do rio S?o Jos? (12o34? e 12?36? S - 41o22? e 41?35? W), munic?pio de Len??is, Bahia, ap?s decorridos 13 anos de registros sobre a regenera??o natural, e comparou com a floresta ciliar do mesmo rio. As coletas foram realizadas entre abril a dezembro de 2011 ao longo de um transecto de 1m x 100m em cada uma das ?reas onde foi aplicado o m?todo de pontos em cada uma das ?reas. Para comparar com o remanescente florestal do entorno, foi usada a lista de esp?cies da floresta ciliar elaborada previamente. Foram amostradas 62 esp?cies distribu?das em 53 g?neros e 26 fam?lias. As fam?lias com maior riqueza de esp?cies s?o Leguminosae (16), Poaceae (11), Cyperaceae (7), Melastomataceae (6), Malvaceae (4), Lycopodiaceae (2). O somat?rio da riqueza destas fam?lias representa 74% do total das esp?cies levantadas neste estudo. Em termos de h?bito foram encontradas 11 (15%) esp?cies arb?reas, 17 (26%) esp?cies arbustivas, 28 (42%) herb?ceas, 07(11%) subarbustivas e 04 (6%) trepadeiras. As esp?cies que mais se destacaram por Vigor Relativo e Cobertura foram Sebastiania corniculata, Aristida setifolia e Homolepis aturensis. A lenta regenera??o natural das ?reas se deve ?s m?s condi??o do solo que apresenta-se modificado pelas a??es do garimpo, tendo sido evidenciada uma maior similaridade, embora baixa, entre as ?reas de maior tempo de abandono que apresentam solo um pouca mais estruturado e o remanescente florestal ciliar do rio S?o Jos?.
48
Daume, Stefan [Verfasser], Klaus von [Akademischer Betreuer] Gadow, Winfried [Akademischer Betreuer] Kurth, and Jürgen [Akademischer Betreuer] Nagel. "Social media mining as an opportunistic citizen science model in ecological monitoring: a case study using invasive alien species in forest ecosystems. / Stefan Daume. Betreuer: Klaus von Gadow. Gutachter: Klaus von Gadow ; Winfried Kurth ; Jürgen Nagel." Göttingen : Niedersächsische Staats- und Universitätsbibliothek Göttingen, 2015. http://d-nb.info/1077648448/34.
Full text
49
Laudisa, Costanza. "Identificazione di utenti in base a come digitano sullo smartphone tramite reti neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19618/.
Full textAbstract:
Negli ultimi anni i metodi di autenticazione tradizionali sui dispositivi elettronici, come password e token, si sono rivelati obsoleti a causa della capacità sempre più avanzata di malintenzionati di risalire a tali informazioni sfruttando debolezze nei sistemi informatici. I sistemi di riconoscimento biometrico nascono come sostitutivi di questi metodi tradizionali e offrono una soluzione più affidabile in quanto si basano su attributi distintivi e propri di un individuo, che non possono essere rubati, manipolati o condivisi. Ad oggi i sistemi di riconoscimento biometrico su smartphone si limitano alla valutazione di caratteristiche fisiche, come la geometria del viso e l'impronta del dito, ma da anni vengono studiate alternative che sfruttano invece caratteristiche comportamentali come l'apposizione di una firma o il pattern di digitazione su una tastiera. I primi studi sul riconoscimento di utenti basato sulla digitazione utilizzavano le tastiere dei computer, ma ben presto si sono estesi anche agli smartphone sfruttando le Application Programming Interface (API) dei sistemi operativi. I metodi più utilizzati per questo compito finora si sono affidati ad algoritmi come 'Random Forest', 'k-Nearest Neighbor' e 'Support Vector Machine'. Questa tesi studia invece la possibilità di utilizzare reti neurali per l'identificazione di utenti sulla base di dati estratti dai pattern di digitazione ('keystroke dynamics') e dai sensori di movimento dello smartphone, mettendole a confronto con i tradizionali classificatori. I risultati indicano che è possibile ottenere risultati soddisfacenti, se non addirittura migliori, anche con l’utilizzo di reti neurali, ma rimane il fatto che le reti neurali sono computazionalmente più complesse dei classici algoritmi di classificazione, il che potrebbe rappresentare un limite per gli smartphone che hanno potenza computazionale ridotta.
50
Carvalho, Andréa Siqueira. ""Mamíferos de médio e grande porte na Floresta Nacional de Carajás, Pará: riqueza, abundância e efeitos da fitofisionomia e do impacto da mineração"." Universidade do Estado do Rio de Janeiro, 2011. http://www.bdtd.uerj.br/tde_busca/arquivo.php?codArquivo=3161.
Full textAbstract:
A Floresta Nacional de Carajás é uma unidade de conservação federal
localizada no sudeste da Amazônia, região Norte do Brasil. Juntamente com outras
cinco áreas formam o Mosaico de Carajás com um contínuo de 1.307.000 hectares
de área protegida. As principais fitofisionomias presentes no interior da unidade são
a Floresta Ombrófila Densa e a Savana Metalófila. A unidade abriga a maior
província mineral do mundo. A atividade de mineração promove diferentes impactos
sobre a fauna principalmente através da modificação de paisagem originada pela
supressão vegetal. O objetivo desse trabalho foi estudar a composição da
comunidade de mamíferos de médio e grande porte através do levantamento de
informações sobre a riqueza, a abundância e as diferenças entre a composição da
mastofauna nas fitofisionomias de Savana Metalófila e Floresta Ombrófila Densa e
suas alterações ocasionadas pelo impacto da mineração. Foram realizadas quatro
campanhas em 19 trilhas que se distribuíram em áreas de Savana Metalófila e
Floresta Ombrófila Densa impactadas e controle. A metodologia utilizada foi de
transecção linear e armadilhamento fotográfico com um esforço total empregado de
432 km e 85.920 horas, para cada um dos métodos, respectivamente. A comunidade
de mastofauna de médio e grande porte apresentou 43 espécies distribuídas em oito
ordens, com um aumento de 41% de novos registros para a região. A composição
da comunidade de mastofauna apresentou diferenças quanto a riqueza e a
abundância das espécies nas duas fitofisionomias e quanto ao efeito do impacto da
mineração. O presente trabalho trouxe avanços em relação à lista de espécies de
mamíferos de médio e grande porte e aumentou o conhecimento a respeito da
composição desta fauna em ambientes de floresta e de savana na Floresta Nacional
de Carajás. Trouxe informações acerca dos impactos sobre a mastofauna e
identificou importantes sensibilidades de algumas espécies frente à mineração,
contribuindo para a busca do equilíbrio entre a mineração e a conservação.The National Forest of Carajás is a federal conservation unit located in the southeast of the Amazon, northern Brazil. Together with other five areas make up the mosaic of Carajás with a continuum of 1.307 million hectares of protected area. The main vegetation types present within the unit are the Dense Montane Forest and Savana Metalófila. The unit houses the largest mineral reserves in the world. Mining activity promotes different impacts on fauna mainly by alteration of the landscape caused by vegetation removal and stacking sterile. The aim of this work was to study the composition of the mammal community of medium and large through the collection of information about richness, abundance and differences between vegetation types in the mammalian species composition of Savana Metalófila and Dense Montane Forest and its changes caused by the impact. Were conducted four campaigns and 19 tracks that were distributed in areas of Savana Metalófila and Dense Montane Forest impacted and control. The methodology used was to linetransect and camera trapping employee with a total effort of 432 km and 85.920 hours for each method, respectively. The mammal community of medium and large showed 43 species in eight orders, showing an increase of 41% of new registrations for the region. The community composition of mammal species show differences in richness and abundance of species in two vegetation types and the effect of the impact of mining. This work has brought about improvements to the list of mammalian species of medium and large size and increased knowledge about the composition of this fauna in environments of forest and savanna in the Carajás National Forest. Brought information about the impacts on mammals and identified important sensitivities of some species facing the mining, contributing to the quest for balance between mining and conservation.