Dissertations / Theses on the topic 'Predictive Patterns'
To see the other types of publications on this topic, follow the link: Predictive Patterns.
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 'Predictive Patterns.'
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
Villaume, Erik. "Predicting customer level risk patterns in non-life insurance." Thesis, KTH, Matematisk statistik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-103590.
Full textAbstract:
Several models for predicting future customer profitability early into customer life-cycles in the property and casualty business are constructed and studied. The objective is to model risk at a customer level with input data available early into a private consumer’s lifespan. Two retained models, one using Generalized Linear Model another using a multilayer perceptron, a special form of Artificial Neural Network are evaluated using actual data. Numerical results show that differentiation on estimated future risk is most effective for customers with highest claim frequencies.
2
Ferguson, Haylie Anne. "A GIS Approach to Archaeological Settlement Patterns and Predictive Modeling in Chihuahua, Mexico." BYU ScholarsArchive, 2018. https://scholarsarchive.byu.edu/etd/7069.
Full textAbstract:
In this study I analyzed the pattern of settlement for known Medio period (A.D. 1200–1450) sites in the Casas Grandes region of Chihuahua, Mexico. Locational data acquired from survey projects in the Casas Grandes region were evaluated within a Geographic Information Systems (GIS) framework to reveal patterns in settlement and site distribution. Environmental and cultural variables, including aspect, cost distance to nearest ballcourt, ecoregion, elevation, local relief, cost distance to nearest oven, cost distance to Paquimé, slope, soil, terrain texture, topographic position index, cost distance to nearest trincheras, vegetation, vegetation variety to 100 meters, vegetation variety to 500 meters, cost distance to nearest intermittent lake, cost distance to nearest intermittent stream, cost distance to nearest perennial lake, and cost distance to nearest perennial stream were calculated for each site in this region. It was expected that the relationships of correspondence between known sites and these variables would provide a quantitative framework that could be used to model the locational probability of unknown sites in the region. Through the use of GIS and statistical analyses, the results of this study were used to produce an archaeological site sensitivity map for this region of northern Mexico.
3
Ferguson, Megan Caton. "Cetacean population density in the Eastern Pacific Ocean : analyzing patterns with predictive spatial models /." Online version in PDF format, 2005. http://swfsc.noaa.gov/uploadedFiles/Divisions/PRD/Programs/Coastal_Marine_Mammal/Ferguson2005dissertation.pdf.
Full textAbstract:
Thesis (Ph. D.)--University of California, San Diego, 2005.Vita. Includes bibliographical references. Also available online in PDF format via the National Marine Fisheries Service Coastal Marine Mammal Program (CMMP) home page.
4
Daughtrey, Cannon Stewart. "Pima County's Open Space Ranch Preserves: Predictive Modeling of Site Locations for Three Time Periods at Rancho Seco." Thesis, The University of Arizona, 2014. http://hdl.handle.net/10150/318809.
Full textAbstract:
The initiatives of open space conservation, as outlined in the Sonoran Desert Conservation Plan, have been implemented through the purchase of nearly 65 thousand acres by Pima County. This land abuts sections of grazing leases held by state and federal agencies, forming largely unfragmented landscapes surrounding the city's urban core. Much of the outlying acreage is rural historic working ranches, now managed as open space conservation preserves. Ranches are landscapes of low-intensity impact, where the archaeological record of centuries of human land use is well preserved. Much of the land, however, remains relatively unstudied. To refine spatial predictions of archaeologically sensitive areas in southern Pima County, I use multivariate logistic regression to develop predictive models of probable archaeological site locations for three time periods at Rancho Seco as a case study. Results suggest portions Rancho Seco might contain additional Preceramic and Historic cultural resources but additional data collection is needed.
5
Brownlow, Briana Nicole. "Patterns of Heart Rate Variability Predictive of Internalizing Symptoms in a Non-Clinical Youth Sample." The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1518179804584445.
Full text
6
Beam, Lauren. "Are holding patterns predictive of infant attachment classification in 12 to 18 month old infants?" Click here to access thesis, 2009. http://www.georgiasouthern.edu/etd/archive/spring2009/lauren_d_beam/beam_lauren_d_200905_ms.pdf.
Full textAbstract:
Thesis (M.S.)--Georgia Southern University, 2009."A thesis submitted to the Graduate Faculty of Georgia Southern University in partial fulfillment of the requirements for the degree Master of Science." Directed by Janice Kennedy. ETD. Includes bibliographical references (p. 54-61) and appendices.
7
Castillo, Guevara Ramon Daniel. "The emergence of cognitive patterns in learning: Implementation of an ecodynamic approach." University of Cincinnati / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1396531855.
Full text
8
Saha, Sourabh Kumar. "Predictive design and fabrication of complex micro and nano patterns via wrinkling for scalable and affordable manufacturing." Thesis, Massachusetts Institute of Technology, 2014. http://hdl.handle.net/1721.1/93860.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2014.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 189-193).
There is a demonstrated need for scalable and affordable manufacturing of complex micro and nano scale structures for applications such as fluidics-based medical diagnostics and photonicsbased sensing. Although high-rate patterning of these structures is feasible via template/stamp based processes, scalability and affordability are often limited by expensive and slow template fabrication processes. The purpose of this work was to develop a wrinkling-based manufacturing process that eliminates the need for an expensive and slow template fabrication step. Wrinkling of thin films is a low-cost buckling-driven patterning process that provides an alternate route to manufacturing scale-up. However, this process is currently of limited practical import because predictive design is restricted to a small set of simple/elementary patterns. In this work, predictive models, tools, and techniques were developed to enable the design and fabrication of a variety of complex wrinkled patterns. The shape and size of wrinkled patterns is determined by the interaction among geometry, material properties, and loading. Complexity in wrinkle patterns often arises due to uncontrolled/undesirable non-uniformities in these process parameters. Due to the confounding effect of simultaneously acting non-uniformities, it is difficult to link wrinkle shape/size to process parameters for such systems. To solve this problem, experimental and computational tools were developed to (i) individually tune/control the non-uniformities in these parameters and (ii) probe the effect of these parameters on the wrinkled pattern. The data generated from these tools was then used to link process parameters to pattern complexity. Contributions were made in the following specific areas: (1) Tunable hierarchical wrinkled patterns via geometric pre-patterning Although complex hierarchical wrinkled patterns have been fabricated via geometric prepatterning in the past, predictive design of such patterns is not feasible. This is primarily because of lack of appropriate process models that can accurately capture the physical effect of prepatterns on the wrinkle generation process. Herein, an analytical model was developed and verified to predict the hierarchical patterns that arise due to geometric non-uniformity. This model elucidates and captures the fundamental energetic response of the system to pre-patterns that distinguishes a pre-patterned system from a flat non-patterned system. The ability to capture this essential physics provides valuable insight into the process that is not available via empirical models that are based on a limited data set. This insight enables one to (i) explore the full design space and identify optimal operating regions, (ii) design and fabricate tunable wrinkled patterns that can be deterministically switched across hierarchical and non-hierarchical states and (iii) explain and predict patterns that are theoretically feasible yet practically inaccessible. (2) Period doubling via high compressive strains Although period doubling at high compressive strains has been demonstrated in the past, models that accurately predict the onset of period doubling are not available. This is due to the inability of existing models to capture the nonlinear stress versus strain material response as the physical basis for period doubling. For example, existing models erroneously assume that the onset of period doubling is independent of stiffness moduli. Herein, models driven by finite element analysis were developed to accurately link the onset of period doubling to nonlinearities that arise during large deformations. These models enable one to accurately separate the effect of individual process parameters on the onset of period doubling. This enables one to extract valuable process-relevant information from the observation of the period doubling phenomenon that is otherwise not available. (3) Attractors and repellers as localized material defects for curved wrinkles Curved wrinkles have been demonstrated in the past during equibiaxial compression of nonuniform materials. However, predictive design of target patterns via curved wrinkles is not feasible at present due to the lack of simple yet effective design rules. Generation of such design rules is hindered by the confounding effect of biaxial compression and localized material nonuniformities. Herein, an elegant design rule for in-plane bending of wrinkles has been generated for the case of uniaxial compression. Based on this, the concept of attractors and repellers as distinct localized material defects has been proposed and experimentally verified. Attractors are relatively compliant defects that pull wrinkles toward them; whereas repellers are relatively stiffer defects that push wrinkles away. These defects may be used as the building blocks to locally alter the in-plane orientation of otherwise uniformly aligned wrinkles during uniaxial compression. The set of predictive models generated in this work would enable a designer to perform inverse pattern design of complex wrinkled structures, i.e., to select the appropriate set of process parameters that are required to fabricate the desired pattern. By replacing other expensive processes for complex patterning, this would reduce the time and cost of manufacturing a variety of functional micro and nano scale patterns by a factor of ~10 for low-volume applications and by ~10% for high-volume applications.
by Sourabh Kumar Saha.
Ph. D.
9
Burton, A. Kim. "Patterns of lumbar sagittal mobility and their predictive value in the natural history of back and sciatic pain." Thesis, University of Huddersfield, 1987. http://eprints.hud.ac.uk/id/eprint/8663/.
Full text
10
Chhaya, Mohamed. "Traditional and modern medicine in primary care - prevalence, patterns and predictive factors of utilisation in Makwarela township, Vhembe district, Limpopo." Thesis, Stellenbosch : University of Stellenbosch, 2015. http://hdl.handle.net/10019.1/97229.
Full textAbstract:
C. ABSTRACT
Introduction: Medical pluralism is a worldwide phenomenon. The reality in South Africa is that healthcare is provided by both orthodox and traditional healthcare providers. There is a great reliance on traditional medicine (TM) especially in rural communities. The complex interplay between patient centeredness and empowerment, health economics, failure of the biomedical approach and many other factors has resulted in an increasing prevalence of medical pluralism.
Aim: The aim of the study was to explore the existence and extent of medical pluralism in my practice population, to quantify the prevalence of use and to qualify the determinants of choice.
Methods: A cross sectional community household survey was conducted in the Makwarela Township of the Thulamela municipality (which forms part of the Vhembe district in the Limpopo Province in South Africa) using systematic sampling based on interval numbers. Interviewer administered questionnaires were used to obtain information from 65 households. Information was collected regarding the dependent variables (illness episodes, consultation behaviour, choice of primary health care provider) and the independent variables (socio-demographics, characteristics of illness, characteristics of health services). These were then analysed to assess prevalence of use and to elucidate significant associations.
Results: Only 48 households representing 73,8% of the sample agreed to be interviewed. The total household members numbered 242. There were 364 illness episodes experienced by the household members in the 6 months prior to the survey. The ever use of TM in the sample was 70,8% (57,9% - 83,7%, 95% CI), whereas the ever use of orthodox medicine was 100%. The percentage of respondents who feel that they would probably use TM in future was 50%. The only significant correlates of TM use were highest education, household size, health belief model, waiting times at OM practitioner and past utilisation of TM.
Conclusion: The study confirms the hypothesis of the existence of a pluralistic primary healthcare system and high prevalence of use of TM in the sample. The pattern of use of TM is that of an adjunct rather than as exclusive therapy. The study also confirms the complex interplay of a myriad of factors in healthcare choice. Despite the limitations of the study it can serve as a preliminary investigation prompting further studies to elucidate healthcare utilisation in the province and nationally. There are many ensuing implications for healthcare providers, funders and health system planners.
11
Cox, Susan M. "It's not a secret but.., predictive testing and patterns of communication about genetic information in families at risk for Huntington disease." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/nq46334.pdf.
Full text
12
Martin, Camie Frandsen. "A Survey of Invasive Exotic Ants Found on Hawaiian Islands: Spatial Distributions and Patterns of Association." BYU ScholarsArchive, 2012. https://scholarsarchive.byu.edu/etd/3854.
Full textAbstract:
An intensive sampling of all ant species encountered on 6 Hawaiian Islands: Big Island, Maui, Oahu, Kauai, Molokai, and Lanai took place between 1988 and 1996. Species presence and absence was recorded at each site. Using remote sensing, variables were added insitu and used throughout my analysis. Species accumulation curves suggest that sampling was comprehensive. There is a significant trend between island area and species richness which validates the Theory of Island Biogeography for invasive species. Islands were found to be significantly nested by area, order, and tourism. Cluster analysis shows a link between elevation, land-use and island, and species presence. Predictive models can be built to predict spread of particular ant species as they continue toward equilibrium.
13
Leitch, David B. "Predictive patterns of institutional misconduct, pro-social behavior, and length of stay of incarcerated youth in a secure, long-term, juvenile rehabilitation facility." Kent State University / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=kent1529614192152508.
Full text
14
Li, Hancao. "Modeling and control of a pressure-limited respirator and lung mechanics." Diss., Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/47667.
Full textAbstract:
The lungs are particularly vulnerable to acute, critical illness. Respiratory failure can result not only from primary lung pathology, such as pneumonia, but also as a secondary consequence of heart failure or inflammatory illness, such as sepsis or trauma. When this occurs, it is essential to support patients with mechanical ventilation while the fundamental disease process is addressed. The goal of mechanical ventilation is to ensure adequate ventilation, which involves a magnitude of gas exchange that leads to the desired blood level of carbon dioxide, and adequate oxygenation that ensures organ function. Achieving these goals is complicated by the fact that mechanical ventilation can actually cause acute lung injury, either by inflating the lungs to excessive volumes or by using excessive pressures to inflate the lungs. Thus, the challenge to mechanical ventilation is to produce the desired blood levels of carbon dioxide and oxygen without causing further acute lung injury.
In this research, we develop an analysis and control synthesis framework for a pressure-limited respirator and lung mechanics system using compartment models. Specifically, a general mathematical model is developed for the dynamic behavior of a multicompartment respiratory system. Then, based on this multicompartment model, an optimal respiratory pattern is characterized using classical calculus of variations minimization techniques for inspiratory and expiratory breathing cycles. Furthermore, model predictive controller frameworks are designed to track the given optimal respiratory air flow pattern while satisfying control input amplitude and rate constrains.
15
Kee, Kok Eng. "A Study of Flow Patterns and Surface Wetting in Gas-Oil-Water Flow." Ohio University / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1401985339.
Full text
16
Hutton, Simon. "An analysis of Candlestick charting: the predictive power of the three-outside-up and three-outside-down Candlestick patterns in the context of small capitalization stocks in the USA." Master's thesis, University of Cape Town, 2015. http://hdl.handle.net/11427/28975.
Full textAbstract:
This paper examines the predictive power of two Japanese Candlestick patterns for a 49-stock sample of small capitalization stocks drawn from the S&P 600 for the period 1 June 2005 to 15 May 2015. Using the normal approximation to the binomial for statistical testing and a dynamic holding period strategy to test the threeoutside- up and three-outside-down patterns, this study contradicts earlier works that used dynamic holding period strategies for large capitalization stocks and showed moderate levels of statistically significant predictive power. This study finds no statistically significant evidence of the predictive power of the three-outside-up and three-outside- down patterns for the sample and time period considered. Hence, the findings imply that there is no evidence to challenge the Efficient Market Hypothesis.
17
Helgason, Ívar S. (Ívar Sigurjón). "Predicting prescription patterns." Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/43873.
Full textAbstract:
Thesis (S.M.)--Harvard-MIT Division of Health Sciences and Technology, 2008.Includes bibliographical references (leaves 43-49).
Electronic prescription software is replacing traditional handwritten medication orders. This development however doesn't come without a cost and speed has been one of the most complained about issues. It is important to address this problem and develop methods to reduce the time spent entering medication orders into computerized prescription software. The objective of this study was to understand the structure of prescription patterns and explore the possibility of designing a method that will predict prescription patterns with only the knowledge of past prescription history. Various machine-learning methods were used and their performance measured by the accuracy of prediction as well as their ability to produce desirable results, within practical time limits. This paper presents a method to transform prescription data into a stochastic time series for prediction. The paper also presents a new nonlinear local algorithm based on nearest neighbor search. In analyzing the database the drug patterns were found to be diverse and over 30% of the patients were unique, in the sense that no other patient had been prescribed the same set of active ingredients. In spite of this diversity, it was possible to create a list of 20 drugs that contained the drug to be prescribed next for 70.2% of patients. This suggests that probabilistically created pick lists, tailored specifically for one patient at the time of prescription, might be used to ease the prescription process. However, further research is needed to evaluate the impact of such lists on prescription habits.
by Ívar S. Helgason.
S.M.
18
Merah, Amar Farouk. "Vehicular Movement Patterns: A Sequential Patterns Data Mining Approach Towards Vehicular Route Prediction." Thèse, Université d'Ottawa / University of Ottawa, 2012. http://hdl.handle.net/10393/22851.
Full textAbstract:
Behavioral patterns prediction in the context of Vehicular Ad hoc Networks (VANETs)has been receiving increasing attention due to enabling on-demand, intelligent traffic analysis and response to real-time traffic issues. One of these patterns, sequential patterns, are a type of behavioral patterns that describe the occurence of events in a timely-ordered fashion. In the context of VANETs, these events are defined as an ordered list of road segments traversed by vehicles during their trips from a starting point to their final intended destination, forming a vehicular path. Due to their predictable nature, undertaken vehicular paths can be exploited to extract the paths that are considered frequent. From the extracted frequent paths through data mining, the probability that a vehicular path will take a certain direction is obtained. However, in order to achieve this, samples of vehicular paths need to be initially collected over periods of time in order to be data-mined accordingly. In this thesis, a new set of formal definitions depicting vehicular paths as sequential patterns is described. Also, five novel communication schemes have been designed and implemented under a simulated environment to collect vehicular paths; such schemes are classified under two categories: Road Side Unit-Triggered (RSU-Triggered) and Vehicle-Triggered. After collection, extracted frequent paths are obtained through data mining, and the probability of these frequent paths is measured. In order to evaluate the e ciency and e ectiveness of the proposed schemes, extensive experimental analysis has been realized. From the results, two of the Vehicle-Triggered schemes, VTB-FP and VTRD-FP, have improved the vehicular path collection operation in terms of communication cost and latency over others. In terms of reliability, the Vehicle-Triggered schemes achieved a higher success rate than the RSU-Triggered scheme. Finally, frequent vehicular movement patterns have been effectively extracted from the collected vehicular paths according to a user-de ned threshold and the confidence of generated movement rules have been measured. From the analysis, it was clear that the user-de ned threshold needs to be set accordingly in order to not discard important vehicular movement patterns.
19
Poulson, Kerrie. "Predicting Patterns of Posttraumatic Growth." Thesis, University of Essex, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.520125.
Full text
20
Brown, Andrew D. "Looking Outward from the Village: The Contingencies of Soil Moisture on the Prehistoric Farmed Landscape near Goodman Point Pueblo." Thesis, University of North Texas, 2016. https://digital.library.unt.edu/ark:/67531/metadc862755/.
Full textAbstract:
Ancestral Pueblo communities of the central Mesa Verde region (CMVR) became increasingly reliant on agriculture for their subsistence needs during Basketmaker III (BMIII) through Terminal Pueblo III (TPIII) (AD 600–1300) periods. Researchers have been studying the Ancestral Pueblo people for over a century using a variety of methods to understand the relationships between climate, agriculture, population, and settlement patterns. While these methods and research have produced a well-developed cultural history of the region, studies at a smaller scale are still needed to understand the changes in farming behavior and the distribution of individual sites across the CMVR. Soil moisture is the limiting factor for crop growth in the semi-arid region of the Goodman Watershed in the CMVR. Thus, I constructed the soil moisture proxy model (SMPM) that is on a local scale and focuses on variables relevant to soil moisture – soil particle-size, soil depth, slope, and aspect. From the SMPM output, the areas of very high soil moisture are assumed to represent desirable farmland locations. I describe the relationship between very high soil moisture and site locations, then I infer the relevance of that relationship to settlement patterns and how those patterns changed over time (BMIII – TPIII). The results of the model and its application help to clarify how Ancestral Pueblo people changed as local farming communities. The results of this study indicates that farmers shifted away from use of preferred farmland during Terminal Pueblo III, which may have been caused by other cultural factors. The general outcome of this thesis is an improved understanding of human-environmental relationships on the local landscape in the CMVR.
21
Boucher-Lalonde, Véronique. "Predicting Broad-scale Patterns in Species Distributions." Thesis, Université d'Ottawa / University of Ottawa, 2016. http://hdl.handle.net/10393/34306.
Full textAbstract:
Species richness of virtually all high-level taxonomic groups is strongly statistically related to climatic variables such as temperature and precipitation, and consistently so across space and time. These observations are consistent with a causal link between the number of species that occur in a given region and its climate. Although dozens of hypotheses have been proposed, the main mechanisms underlying this pattern remain largely unresolved. And, few ecological studies have attempted to identify regularities in the individual species distributions that make up the richness–climate relationship. Despite the complexities of species’ biologies, I found that, to a first approximation, species’ probability of occupancy at continental scales were generally well statistically explained by a Gaussian function of temperature and precipitation. This simple model appeared general among species, taxa and regions. However, although individual species’ ranges are strongly statistically related to climate, spatial variations in richness cannot be explained by systematic variations in species’ climatic niches. And, individual species track changes in climatic variables through time much more weakly than species richness tracks these changes, suggesting that richness is at least partly constrained by mechanisms independent of species identities. Moreover, at macro-scales, species richness was also not strongly predictable from the temperature at which clades have originated, from historical variability in climatic variables nor from local short-term extirpation rates. In sum, I rejected several prominent hypotheses aiming to explain richness–climate relationship and found several lines of evidence inconsistent with the common idea that climatic constraints on individual species, by themselves, can explain richness–climate relationship. I propose a mechanism to explain, as a first approximation, the continental biogeography of species distributions that relies on neutral processes of dispersal and local extinctions within species’ broad deterministic thermal tolerances.
22
Gangadharaiah, Dayananda Sagar. "PATTERNS OF DIPEPTIDE USAGE FOR GENE PREDICTION." Wright State University / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=wright1279304144.
Full text
23
Davuluri, Pavani. "Prediction of Breathing Patterns Using Neural Networks." VCU Scholars Compass, 2008. http://scholarscompass.vcu.edu/etd/718.
Full textAbstract:
During the radio therapy treatment, it has been difficult to synchronize the radiation beam with the tumor position. Many compensation techniques have been used before. But all these techniques have some system latency, up to a few hundred milliseconds. Hence it is necessary to predict tumor position to compensate for the control system latency. In recent years, many attempts have been made to predict the position of a moving tumor during respiration. Analyzing external breathing signals presents a methodology in predicting the tumor position. Breathing patterns vary from very regular to irregular patterns. The irregular breathing patterns make prediction difficult. A solution is presented in this paper which utilizes neural networks as the predictive filter to determine the tumor position up to 500 milliseconds in the future. Two different neural network architectures, feedforward backpropagation network and recurrent network, are used for prediction. These networks are initialized in the same manner for the comparison of their prediction accuracies. The networks are able to predict well for all the 5 breathing cases used in the research and the results of both the networks are acceptable and comparable. Furthermore, the network parameters are optimized using a genetic algorithm to improve the performance. The optimization results obtained proved to improve the accuracy of the networks. The results of both the networks showed that the networks are good for prediction of different breathing behaviors.
24
Mathieson, Mark James. "Ordinal models and predictive methods in pattern recognition." Thesis, University of Oxford, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.299155.
Full text
25
Hagnell, Fredrik. "Predicting Human Movement Patterns in an Office Environment." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-188787.
Full textAbstract:
This project is built on the idea of predicting future human movement in an area. The algorithm’s predictions are based on previous movements in the area which has to be recorded somehow. For this a device with a motion sensor was setup to monitor the movement in a hallway in an office. This data was then used to test and evaluate the prediction algorithm. To give feedback about the movement and how it is changing to the people working in the office the setup device shows sentences on a monitor which describes the movement. The project resulted in a fully working application which measures people walking by, both when and how fast, and predicts future movement. Due to time constraints of the project the device was only up and running for two weeks. This is enough time to get some understanding of how well the prediction algorithm works, but a longer experiment time would have further helped the evaluation. The results showed that the algorithm can predict most of the events during the day, but is bad at predicting sudden spikes or other unusual behavior.Projektet är baserat på idén att förutse framtida mänsklig rörelse i ett område. För att noggrant kunna förutse framtida rörelse så behöver man kunna mäta tidigare rörelse. För detta så sattes en anordning upp med en rörelse detektor för att mäta rörelsen i en korridor i ett kontor. Data som samlades in användes sedan för att testa och utvärdera förutsägelse algoritmen. För att ge feed-back om rörelsen och hur den ändras till människorna som jobbade i kontoret så visade anordningen meningar på en skärm som beskrev rörelsen. Projektet resulterade i en fullt fungerade applikation som mäter folk som går förbi, både när och hur snabbt, och förutser framtida rörelse. På grund av tids begränsningar i projektet så var anordningen bara uppe och mätte data i två veckor. Detta är tillräckligt mycket tid för att få någon förståelse över hur bra förutsägelse algoritmen fungerar, men en längre experiment tid skulle ha hjälpt utvärderingen. Resultaten visade att algoritmen kan förutse de flesta händelserna under dagen, men är dålig på att förutse plötsliga spikar eller annat ovanligt beteende.
26
Higgins, Steven Ian. "Predicting rates and patterns of alien plant spread." Doctoral thesis, University of Cape Town, 1998. http://hdl.handle.net/11427/23675.
Full textAbstract:
The invasion of alien plants into natural ecosystems is a widespread phenomenon that impacts negatively on ecosystem structure and functioning. The invasion and subsequent spread of an alien plant population is equivalent to the processes of colonisation and migration. This implies that the existing toolbox of techniques developed for plant succession research should be useful for predicting plant invasions. Practitioners of invasion biology . have, however, found biological invasions frustratingly difficult to predict. The aim of this thesis was to use succession models to develop a modelling protocol for predicting rates and patterns of alien plant spread. The rationale was that such a model would both improve our understanding of the determinants of invasions and allow us to make predictions on the rates and patterns of alien plant spread. Such predictions are likely to be extremely valuable for the tactical and strategic management of plant invasions. Many modelling approaches could be .. adopted: the need to transcend the gap from general models of plant spread to management models led me to select a spatially explicit simulation modelling approach. The modelling approach is developed by comparing the behaviour of an individual based spatially explicit simulation (SEIBS) model of plant spread to the behaviour of the classic Skellam reaction diffusion model. This process also served to define the model's sensitivity and data requirements. The model's heuristic value is demonstrated by exploring why it is so difficult .to predict which plant will invade which environment. The model also ·provides a useful tool for exploring the role of long-distance dispersal in determining invasion rates. I show that long-distance dispersal is extremely difficult to define statistically, but is a key determinant of invasion rates. The model is validated using independent data on the spatial demography of two invasive species, Acacia cyclops and Pinus pinaster, and independent historical reconstructions of invasions. This validated model was then used to develop a dynamic landscape-extent model. This scaled-up model explores the optimal strategies for clearing alien plants and the ability of different clearing strategies and funding schedules to mitigate the threat that alien plants pose to native species. I conclude that models that are tightly linked to understanding of ecological processes and to field data can be used to rapidly develop predictive models. The development of these models challenges our fundamental ecological understanding and, therefore, emphasises the interplay between data, theory and prediction.
27
Poulsen, Franklin Owen. "Adult Attachment: A Framework for Predicting Dating Patterns." BYU ScholarsArchive, 2011. https://scholarsarchive.byu.edu/etd/2786.
Full textAbstract:
Although adult attachment has been the focus of a great deal of relationship research, few studies have attempted to examine how adult attachment style may be related to relationship initiation. This study investigates how adult attachment is associated with dating processes and patterns in a sample (N = 587) of college students at a private religious university. Results indicate that attachment anxiety and attachment avoidance are related to a pattern of being mostly dateless in a twenty-five week period. Furthermore, attachment avoidance but not anxiety is related to having fewer relationships in the period. Along with attachment avoidance and anxiety, being less attractive was also predictive of being mostly dateless in the measured period, as was being female. Physical attractiveness is the strongest predictor of having dates, as well as having relationships, but is not predictive of relationship length.
28
Wang, Wei. "Predictive modeling based on classification and pattern matching methods." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape7/PQDD_0019/MQ51498.pdf.
Full text
29
Karunaratne, Thashmee M. "Learning predictive models from graph data using pattern mining." Doctoral thesis, Stockholms universitet, Institutionen för data- och systemvetenskap, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-100713.
Full textAbstract:
Learning from graphs has become a popular research area due to the ubiquity of graph data representing web pages, molecules, social networks, protein interaction networks etc. However, standard graph learning approaches are often challenged by the computational cost involved in the learning process, due to the richness of the representation. Attempts made to improve their efficiency are often associated with the risk of degrading the performance of the predictive models, creating tradeoffs between the efficiency and effectiveness of the learning. Such a situation is analogous to an optimization problem with two objectives, efficiency and effectiveness, where improving one objective without the other objective being worse off is a better solution, called a Pareto improvement. In this thesis, it is investigated how to improve the efficiency and effectiveness of learning from graph data using pattern mining methods. Two objectives are set where one concerns how to improve the efficiency of pattern mining without reducing the predictive performance of the learning models, and the other objective concerns how to improve predictive performance without increasing the complexity of pattern mining. The employed research method mainly follows a design science approach, including the development and evaluation of artifacts. The contributions of this thesis include a data representation language that can be characterized as a form in between sequences and itemsets, where the graph information is embedded within items. Several studies, each of which look for Pareto improvements in efficiency and effectiveness are conducted using sets of small graphs. Summarizing the findings, some of the proposed methods, namely maximal frequent itemset mining and constraint based itemset mining, result in a dramatically increased efficiency of learning, without decreasing the predictive performance of the resulting models. It is also shown that additional background knowledge can be used to enhance the performance of the predictive models, without increasing the complexity of the graphs.
30
Zhang, Kejing. "Traffic pattern prediction in cellular networks." Thesis, Queen Mary, University of London, 2011. http://qmro.qmul.ac.uk/xmlui/handle/123456789/2442.
Full textAbstract:
Increasing numbers of users together with a more use of high bit-rate services complicate radio resource management in 3G systems. In order to improve the system capacity and guarantee the QoS, a large amount of research had been carried out on radio resource management. One viable approach reported is to use semi-smart antennas to dynamically change the radiation pattern of target cells to reduce congestion. One key factor of the semi-smart antenna techniques is the algorithm to adjust the beam pattern to cooperatively control the size and shape of each radio cell. Methods described in the literature determine the optimum radiation patterns according to the current observed congestion. By using machine learning methods, it is possible to detect the upcoming change of the traffic patterns at an early stage and then carry out beamforming optimization to alleviate the reduction in network performance. Inspired from the research carried out in the vehicle mobility prediction field, this work learns the movement patterns of mobile users with three different learning models by analysing the movement patterns captured locally. Three different mobility models are introduced to mimic the real-life movement of mobile users and provide analysable data for learning. The simulation results shows that the error rates of predictions on the geographic distribution of mobile users are low and it is feasible to use the proposed learning models to predict future traffic patterns. Being able to predict these patterns mean that the optimized beam patterns could be calculated according to the predicted traffic patterns and loaded to the relevant base stations in advance.
31
Chunsheng, Guo. "Relationship between Consumption patterns and Waste Composition." Thesis, KTH, Industriell ekologi, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-101246.
Full textAbstract:
The purpose of this study is to explore whether changes in consumption patterns contributed to the changes in waste composition in Jinan during 1999-2008 and to predict trend of the waste composition relevant total household consumer expenditure in the future 10 years. The results reveal that household consumption is the most significant contributors in changes of waste composition. Although this study points to the possibility of predictions for several important fraction such as food scraps, metal, glass, paper and plastic by according to household consumption, these predictions has not been strong enough to decrease errors, a trend can only be given in the future 10 years.
32
Stark, Colin Peter. "The influence of active extensional tectonics on patterns of fluid flow." Thesis, University of Leeds, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.305934.
Full text
33
Zuloaga, Villamizar Juan Gerardo. "Species Endemism: Predicting Broad-Scale Patterns and Conservation Priorities." Thesis, Université d'Ottawa / University of Ottawa, 2018. http://hdl.handle.net/10393/37149.
Full textAbstract:
Do thermal barriers limit biotic composition and community similarity, potentially helping to shape biodiversity patterns at continental scales? Are environmental variables responsible for broad-scale patterns of species endemism? Are these patterns predictable? And, how can patterns of endemism can inform global conservation strategies? These are some of the questions that I attempted to answer during my doctoral research.
In the first chapter, I tested one of the most contentious hypotheses in ecology: Do thermal barriers, which grow stronger along elevational gradients across tropical mountains, create a dispersal barrier to organisms and consequently contribute to the isolation and divergence of species assemblages? If so, do patterns potentially generated by this mechanism detectably relate to dissimilarity of biotic assemblages along altitudinal gradients across the mountains in the Americas? We found that mountain passes are not only higher in tropical realms, as initially thought by Janzen (1967), and extensively popularized and assumed in further research, but they are also present in temperate regions along the western coast of North America. We also found that the stronger the thermal barrier, the higher the dissimilarity between communities. However, the variance explained was low, suggesting thermal barriers play a minor role in creating and maintaining patterns of biodiversity.
The second chapter raises the question of why are there more small-ranged species in some places than in others. I tested four macroecological hypotheses (H1: climate velocity; H2: climate seasonality; H3: climate distinctiveness or rarity; and, H4: spatial heterogeneity in contemporary climate, topography or habitat) to predict broad-scale patterns of species endemism, using a cross-continental validation approach. We found that there is no empirical reason, from the standpoint of model fitting, parameter estimates, and model validation, to claim that any of these hypotheses creates and maintains broad-scale patterns of endemism. Although we found statistically significant relationships, they failed stronger tests of a causal relationship, namely accurate prediction. That is, the hypotheses did not survive the test of cross-continental validation, failing to predict observed patterns of endemism. Climate velocity was dropped from some models, suggesting that early correlations in some places probably reflect collinearity with topography. The effect of richness on endemism was in some cases negligible, suggesting that patterns of endemism are not driven by the same variables as total richness. Despite low explained variance, spatial heterogeneity in potential evapotranspiration was the most consistent predictor in all models.
The third chapter is aimed to evaluate the extent to which global protected areas (PAs) have included endemic species (species with small range size relative to the median range size). We measure the relative coverage of endemic species by overlapping species geographic ranges for amphibians, mammals, and birds, with the world database of PAs (1990-2016). Then we measure the rate of expansion of the global PA network and the rate of change in endemic species coverage.
We found that ~30% of amphibian, ~6% of bird and ~10% of mammal endemic species are completely outside PAs. Most endemic species’ ranges intersect the PA network (amphibian species = 58%; birds = 83%; mammals = 86%), but it usually covers less than 50% of their geographic range. Almost 50% of species outside the PA network are considered threatened (critically endangered, endangered and vulnerable). We identified that ecoregions in tropical Andes, Mesoamerica, Pacific Islands (e.g., New Guinea, Solomon), Dry Chaco, and Atlantic forests are major conservation priorities areas.
The historic rates of new PAs added every year to the network is between ~6,000 to ~15,000. In contrast, we found that rates of including endemic species within the PA network have been fairly slow. Historic data shows that every year, the entire geographic range of 3 (amphibians) to 6 (birds and mammals) endemic species is 100% included inside the PA network (amphibians = from 162 to 233; mammals = 10 to 84; and, amphibians = 16 to 99). Based on these trends, it is very unlikely PAs will include all endemic species (14% total endemic species, that is ~1,508 out of 11,274) currently outside the PA network by 2020. It will require five times the effort made in the last two decades. However, projections also showed that is very likely that some portions of the geographic ranges for all endemic birds and mammals, but not for all endemic amphibians, will be covered by the future PA network.
I sum, I found that none of the hypotheses tested here can explain broad-scale patterns of total species richness and total species endemism. My main contribution on this research area is clearly rejecting these hypotheses from potential candidates that may explain biodiversity patterns. By removing them, we advance in this field and open possibilities to test new hypotheses and evaluate their mechanisms. I proposed that other drivers and mechanisms (whether biotic and biotic) acting at local scales, and escaping the detection of macroecological approaches, might be responsible for these patterns. Finally, in terms of conservation planning, I proposed that the international community has an opportunity to protect a great number of endemic species and their habitats before 2020, if they strategically create new PAs.
34
da, Costa Joel. "Online Non-linear Prediction of Financial Time Series Patterns." Master's thesis, Faculty of Science, 2020. http://hdl.handle.net/11427/32221.
Full textAbstract:
We consider a mechanistic non-linear machine learning approach to learning signals in financial time series data. A modularised and decoupled algorithm framework is established and is proven on daily sampled closing time-series data for JSE equity markets. The input patterns are based on input data vectors of data windows preprocessed into a sequence of daily, weekly and monthly or quarterly sampled feature measurement changes (log feature fluctuations). The data processing is split into a batch processed step where features are learnt using a Stacked AutoEncoder (SAE) via unsupervised learning, and then both batch and online supervised learning are carried out on Feedforward Neural Networks (FNNs) using these features. The FNN output is a point prediction of measured time-series feature fluctuations (log differenced data) in the future (ex-post). Weight initializations for these networks are implemented with restricted Boltzmann machine pretraining, and variance based initializations. The validity of the FNN backtest results are shown under a rigorous assessment of backtest overfitting using both Combinatorially Symmetrical Cross Validation and Probabilistic and Deflated Sharpe Ratios. Results are further used to develop a view on the phenomenology of financial markets and the value of complex historical data under unstable dynamics.
35
Flint, Anthony David. "The development of predictive maintenance systems based on the Hough transform." Thesis, University of Huddersfield, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307836.
Full text
36
Hepplewhite, C. L. "Radiometric observation of the atmospheric boundary layer : the ROSSA project." Thesis, University of Oxford, 1989. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.329921.
Full text
37
Brown, Nigel P. "Patterns in protein secondary structure packing : a database for prediction." Thesis, University College London (University of London), 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.315268.
Full text
38
Charitidis, Theoharis. "Sequence Prediction for Identifying User Equipment Patterns in Mobile Networks." Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-266380.
Full textAbstract:
With an increasing demand for bandwidth and lower latency in mobile communication networks it becomes gradually more important to improve current mobile network management solutions using available network data. To improve the network management it can for instance be of interest to infer future available bandwidth to the end user of the network. This can be done by utilizing the current knowledge of real-time user equipment (UE) behaviour in the network. In the scope of this thesis interest lies in, given a set of visited radio access points (cells), to predict what the next one is going to be. For this reason the aim is to investigate the prediction performance when utilizing the All-K-Order Markov (AKOM) model, with some added variations, on collected data generated from train trajectories. Moreover a method for testing the suitability of modeling the sequence of cells as a time-homogeneous Markov chain is proposed, in order to determine the goodness-of- t with the available data. Lastly, the elapsed time in each cell is attempted to be predicted using linear regression given the prior history window of previous cell and elapsed times pairs. The results show that moderate to good prediction accuracy on the upcoming cell can be achieved with AKOM and associated variations. For predicting the upcoming sojourn time in future cells the results reveal that linear regression does not yield satisfactory results and possibly another regression model should be utilized.Med en ökande efterfrågan på banbredd och kortare latens i mobila nätverk har det gradvis blivit viktigare att förbättra nuvarande lösningar för hantering av nätverk genom att använda tillgänglig nätverksdata. Specifikt är det av intresse att kunna dra slutsatser kring vad framtida bandbredsförhållanden kommer vara, samt övriga parametrar av intresse genom att använda tillgänglig information om aktuell mobil användarutrustnings (UE) beteende i det mobila nätverket. Inom ramen av detta masterarbete ligger fokus på att, givet tidigare besökta radio accesspunkter (celler), kunna förutspå vilken nästkommande besökta cell kommer att vara. Av denna anledning är målet att undersöka vilken prestanda som kan uppnås när All-$K$-Order Markov (AKOM) modellen, med associerade varianter av denna, används på samlad data från tågfärder. Dessutom ges det förslag på test som avgör hur lämpligt det är att modelera observerade sekvenser av celler som en homogen Markovkedja med tillgänglig data. Slutligen undersöks även om besökstiden i en framtida cell kan förutspås med linjär regression givet ett historiskt fönster av tidigare cell och besökstids par. Erhållna resultat visar att måttlig till bra prestanda kan uppnås när kommande celler förutspås med AKOM modellen och associerade variationer. För prediktering av besökstid i kommande cell med linjär regression erhålles det däremot inte tillfredsställande resultat, vilket tyder på att en alternativ regressionsmetod antagligen är bättre lämpad för denna data.
39
Abar, Orhan. "Rule Mining and Sequential Pattern Based Predictive Modeling with EMR Data." UKnowledge, 2019. https://uknowledge.uky.edu/cs_etds/85.
Full textAbstract:
Electronic medical record (EMR) data is collected on a daily basis at hospitals and other healthcare facilities to track patients’ health situations including conditions, treatments (medications, procedures), diagnostics (labs) and associated healthcare operations. Besides being useful for individual patient care and hospital operations (e.g., billing, triaging), EMRs can also be exploited for secondary data analyses to glean discriminative patterns that hold across patient cohorts for different phenotypes. These patterns in turn can yield high level insights into disease progression with interventional potential. In this dissertation, using a large scale realistic EMR dataset of over one million patients visiting University of Kentucky healthcare facilities, we explore data mining and machine learning methods for association rule (AR) mining and predictive modeling with mood and anxiety disorders as use-cases. Our first work involves analysis of existing quantitative measures of rule interestingness to assess how they align with a practicing psychiatrist’s sense of novelty/surprise corresponding to ARs identified from EMRs. Our second effort involves mining causal ARs with depression and anxiety disorders as target conditions through matching methods accounting for computationally identified confounding attributes. Our final effort involves efficient implementation (via GPUs) and application of contrast pattern mining to predictive modeling for mental conditions using various representational methods and recurrent neural networks. Overall, we demonstrate the effectiveness of rule mining methods in secondary analyses of EMR data for identifying causal associations and building predictive models for diseases.
40
Sammouri, Wissam. "Data mining of temporal sequences for the prediction of infrequent failure events : application on floating train data for predictive maintenance." Thesis, Paris Est, 2014. http://www.theses.fr/2014PEST1041/document.
Full textAbstract:
De nos jours, afin de répondre aux exigences économiques et sociales, les systèmes de transport ferroviaire ont la nécessité d'être exploités avec un haut niveau de sécurité et de fiabilité. On constate notamment un besoin croissant en termes d'outils de surveillance et d'aide à la maintenance de manière à anticiper les défaillances des composants du matériel roulant ferroviaire. Pour mettre au point de tels outils, les trains commerciaux sont équipés de capteurs intelligents envoyant des informations en temps réel sur l'état de divers sous-systèmes. Ces informations se présentent sous la forme de longues séquences temporelles constituées d'une succession d'événements. Le développement d'outils d'analyse automatique de ces séquences permettra d'identifier des associations significatives entre événements dans un but de prédiction d'événement signant l'apparition de défaillance grave. Cette thèse aborde la problématique de la fouille de séquences temporelles pour la prédiction d'événements rares et s'inscrit dans un contexte global de développement d'outils d'aide à la décision. Nous visons à étudier et développer diverses méthodes pour découvrir les règles d'association entre événements d'une part et à construire des modèles de classification d'autre part. Ces règles et/ou ces classifieurs peuvent ensuite être exploités pour analyser en ligne un flux d'événements entrants dans le but de prédire l'apparition d'événements cibles correspondant à des défaillances. Deux méthodologies sont considérées dans ce travail de thèse: La première est basée sur la recherche des règles d'association, qui est une approche temporelle et une approche à base de reconnaissance de formes. Les principaux défis auxquels est confronté ce travail sont principalement liés à la rareté des événements cibles à prédire, la redondance importante de certains événements et à la présence très fréquente de "bursts". Les résultats obtenus sur des données réelles recueillies par des capteurs embarqués sur une flotte de trains commerciaux permettent de mettre en évidence l'efficacité des approches proposéesIn order to meet the mounting social and economic demands, railway operators and manufacturers are striving for a longer availability and a better reliability of railway transportation systems. Commercial trains are being equipped with state-of-the-art onboard intelligent sensors monitoring various subsystems all over the train. These sensors provide real-time flow of data, called floating train data, consisting of georeferenced events, along with their spatial and temporal coordinates. Once ordered with respect to time, these events can be considered as long temporal sequences which can be mined for possible relationships. This has created a neccessity for sequential data mining techniques in order to derive meaningful associations rules or classification models from these data. Once discovered, these rules and models can then be used to perform an on-line analysis of the incoming event stream in order to predict the occurrence of target events, i.e, severe failures that require immediate corrective maintenance actions. The work in this thesis tackles the above mentioned data mining task. We aim to investigate and develop various methodologies to discover association rules and classification models which can help predict rare tilt and traction failures in sequences using past events that are less critical. The investigated techniques constitute two major axes: Association analysis, which is temporal and Classification techniques, which is not temporal. The main challenges confronting the data mining task and increasing its complexity are mainly the rarity of the target events to be predicted in addition to the heavy redundancy of some events and the frequent occurrence of data bursts. The results obtained on real datasets collected from a fleet of trains allows to highlight the effectiveness of the approaches and methodologies used
41
Lee, Gareth E. "Multi-modal prediction and modelling using artificial neural networks." Thesis, University of East Anglia, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.293823.
Full text
42
VENKATESAN, JAYARAM. "A PATTERN RECOGNITION APPROACH TO POSTURAL STABILITY AND PREDICTION OF WORKPLACE INJURY." University of Cincinnati / OhioLINK, 2006. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1163598728.
Full text
43
Wang, Yuanxun. "Radar signature prediction and feature extraction using advanced signal processing techniques /." Digital version accessible at:, 1999. http://wwwlib.umi.com/cr/utexas/main.
Full text
44
Singh, Shailendra. "Smart Meters Big Data : Behavioral Analytics via Incremental Data Mining and Visualization." Thesis, Université d'Ottawa / University of Ottawa, 2016. http://hdl.handle.net/10393/35244.
Full textAbstract:
The big data framework applied to smart meters offers an exception platform for data-driven forecasting and decision making to achieve sustainable energy efficiency. Buying-in consumer confidence through respecting occupants' energy consumption behavior and preferences towards improved participation in various energy programs is imperative but difficult to obtain. The key elements for understanding and predicting household energy consumption are activities occupants perform, appliances and the times that appliances are used, and inter-appliance dependencies. This information can be extracted from the context rich big data from smart meters, although this is challenging because: (1) it is not trivial to mine complex interdependencies between appliances from multiple concurrent data streams; (2) it is difficult to derive accurate relationships between interval based events, where multiple appliance usage persist; (3) continuous generation of the energy consumption data can trigger changes in appliance associations with time and appliances. To overcome these challenges, we propose an unsupervised progressive incremental data mining technique using frequent pattern mining (appliance-appliance associations) and cluster analysis (appliance-time associations) coupled with a Bayesian network based prediction model. The proposed technique addresses the need to analyze temporal energy consumption patterns at the appliance level, which directly reflect consumers' behaviors and provide a basis for generalizing household energy models. Extensive experiments were performed on the model with real-world datasets and strong associations were discovered. The accuracy of the proposed model for predicting multiple appliances usage outperformed support vector machine during every stage while attaining accuracy of 81.65\%, 85.90\%, 89.58\% for 25\%, 50\% and 75\% of the training dataset size respectively. Moreover, accuracy results of 81.89\%, 75.88\%, 79.23\%, 74.74\%, and 72.81\% were obtained for short-term (hours), and long-term (day, week, month, and season) energy consumption forecasts, respectively.
45
Uwagbole, Solomon. "A pattern-driven corpus to predictive analytics in mitigating SQL injection attack." Thesis, Edinburgh Napier University, 2018. http://researchrepository.napier.ac.uk/Output/1538260.
Full textAbstract:
The back-end database provides accessible and structured storage for each web application's big data internet web traffic exchanges stemming from cloud-hosted web applications to the Internet of Things (IoT) smart devices in emerging computing. Structured Query Language Injection Attack (SQLIA) remains an intruder's exploit of choice to steal confidential information from the database of vulnerable front-end web applications with potentially damaging security ramifications. Existing solutions to SQLIA still follows the on-premise web applications server hosting concept which were primarily developed before the recent challenges of the big data mining and as such lack the functionality and ability to cope with new attack signatures concealed in a large volume of web requests. Also, most organisations' databases and services infrastructure no longer reside on-premise as internet cloud-hosted applications and services are increasingly used which limit existing Structured Query Language Injection (SQLI) detection and prevention approaches that rely on source code scanning. A bio-inspired approach such as Machine Learning (ML) predictive analytics provides functional and scalable mining for big data in the detection and prevention of SQLI in intercepting large volumes of web requests. Unfortunately, lack of availability of robust ready-made data set with patterns and historical data items to train a classifier are issues well known in SQLIA research applying ML in the field of Artificial Intelligence (AI). The purpose-built competition-driven test case data sets are antiquated and not pattern-driven to train a classifier for real-world application. Also, the web application types are so diverse to have an all-purpose generic data set for ML SQLIA mitigation. This thesis addresses the lack of pattern-driven data set by deriving one to predict SQLIA of any size and proposing a technique to obtain a data set on the fly and break the circle of relying on few outdated competitions-driven data sets which exist are not meant to benchmark real-world SQLIA mitigation. The thesis in its contributions derived pattern-driven data set of related member strings that are used in training a supervised learning model with validation through Receiver Operating Characteristic (ROC) curve and Confusion Matrix (CM) with results of low false positives and negatives. We further the evaluations with cross-validation to have obtained a low variance in accuracy that indicates of a successful trained model using the derived pattern-driven data set capable of generalisation of unknown data in the real-world with reduced biases. Also, we demonstrated a proof of concept with a test application by implementing an ML Predictive Analytics to SQLIA detection and prevention using this pattern-driven data set in a test web application. We observed in the experiments carried out in the course of this thesis, a data set of related member strings can be generated from a web expected input data and SQL tokens, including known SQLI signatures. The data set extraction ontology proposed in this thesis for applied ML in SQLIA mitigation in the context of emerging computing of big data internet, and cloud-hosted services set our proposal apart from existing approaches that were mostly on-premise source code scanning and queries structure comparisons of some sort.
46
Herbst, Gernot. "Short-Time Prediction Based on Recognition of Fuzzy Time Series Patterns." Universitätsbibliothek Chemnitz, 2010. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-201001012.
Full textAbstract:
This article proposes knowledge-based short-time prediction methods for multivariate streaming time series, relying on the early recognition of local patterns. A parametric, well-interpretable model for such patterns is presented, along with an online, classification-based recognition procedure. Subsequently, two options are discussed to predict time series employing the fuzzified pattern knowledge, accompanied by an example. Special emphasis is placed on comprehensible models and methods, as well as an easy interface to data mining algorithms.
47
Barends, Jody Michael. "Predicting reptile species distributions and biogeographic patterns within Kruger National Park." University of the Western Cape, 2018. http://hdl.handle.net/11394/6745.
Full textAbstract:
Magister Scientiae (Biodiversity and Conservation Biology) - MSc (Biodiv and Cons Biol)Knowledge of global reptile ecology is limited and there remains much to understand in terms of detailed reptile species information, including that of their distributions. In South Africa, despite being one of SANParks best-studied reserves, surprisingly little is known about the distributions and spatial ecology of reptiles within Kruger National Park (KNP). Management within KNP follows a strategic adaptive management strategy which monitors the statuses of animals using species or group specific indicators. Indicators are given predetermined upper and lower ranges of acceptable fluctuation before actions are taken. These ranges are referred to as thresholds of potential concern (TPCs), and for reptiles these are based on changes to their distributions across the landscape of KNP. An apparent lack of high-quality reptile distribution data inhibits the effective monitoring of the statuses of these animals within KNP, which in turn limits management and conservation options. In this study, I use several methods to quantify available reptile occurrence data which formed the foundations for predicting the distributions of these species across KNP by means of species distribution modelling, with a view to gaining novel insight into reptile assemblage structure across the landscape of KNP.
48
Bahrami, Mohsen, and Bane Vasic. "Noise Predictive Information Rate Estimation for TDMR Channels." International Foundation for Telemetering, 2016. http://hdl.handle.net/10150/624263.
Full textAbstract:
In this paper, we use the forward recursion BCJR algorithm to estimate the symmetric
information rate for Two Dimensional Magnetic Recording (TDMR) channels. In particular, we
consider a TDMR read/write channel whose all components, including recording medium, write
and readback processes are modeled in software. Since the primary source of noise in TDMR
arises from irregularities in the recording medium and leads to highly colored and data-dependent
jitter, the pattern dependent noise predictive (PDNP) algorithm is implemented to improve the
accuracy and performance of SIR estimation. Furthermore, we study the performance gain of
using the PDNP algorithm in SIR estimation through simulations over the Voronoi based media
model for different TDMR channel configurations.
49
Nguyen, Thuy Thi Thu. "Predicting cardiovascular risks using pattern recognition and data mining." Thesis, University of Hull, 2009. http://hydra.hull.ac.uk/resources/hull:3051.
Full textAbstract:
This thesis presents the use of pattern recognition and data mining techniques into risk prediction models in the clinical domain of cardiovascular medicine. The data is modelled and classified by using a number of alternative pattern recognition and data mining techniques in both supervised and unsupervised learning methods. Specific investigated techniques include multilayer perceptrons, radial basis functions, and support vector machines for supervised classification, and self organizing maps, KMIX and WKMIX algorithms for unsupervised clustering. The Physiological and Operative Severity Score for enUmeration of Mortality and morbidity (POSSUM), and Portsmouth POSSUM (PPOSSUM) are introduced as the risk scoring systems used in British surgery, which provide a tool for predicting risk adjustment and comparative audit. These systems could not detect all possible interactions between predictor variables whereas these may be possible through the use of pattern recognition techniques. The thesis presents KMIX and WKMIX as an improvement of the K-means algorithm; both use Euclidean and Hamming distances to measure the dissimilarity between patterns and their centres. The WKMIX is improved over the KMIX algorithm, and utilises attribute weights derived from mutual information values calculated based on a combination of Baye’s theorem, the entropy, and Kullback Leibler divergence. The research in this thesis suggests that a decision support system, for cardiovascular medicine, can be built utilising the studied risk prediction models and pattern recognition techniques. The same may be true for other medical domains.
50
Albtoosh, Amal Aqeel Odeh. "Prediction of naso-labial morphology from dental pattern assessments." Thesis, University of Dundee, 2016. https://discovery.dundee.ac.uk/en/studentTheses/aca9f6fc-3259-4c54-b629-3734db89ee51.
Full textAbstract:
This project aims to develop standards to predict vermillion border shape and appearance - i.e. the outline of the vermillion border and the fullness of lips, based on assessment of an individual dental pattern using a combination of three methods: morphological, cephalometric and GMM. This study tests a hypothesis that the skeletal and dental pattern in antero-posterior and vertical dimensions and the upper and the lower incisor inclinations can predict the morphology of the soft tissue of the lips. This hypothesis was examined by analysing retrospective facial data, which consists of two-dimensional, pre-orthodontic treatment photographs and cephalograms of individuals of four malocclusion classes: Class I, Class II: divisions 1 and 2, and Class III from two sample populations: 56 Scottish and 56 Jordanians, aged 11-14 years. All the Scottish participants had been recipients of treatment at the Dental Hospital at the University of Dundee, and the Jordanian sample were selected from the Orthodontic archive held by Jordan University Hospital. The results reveal that a cephalogram analysis offers a statistically significant correlation differing from one type of malocclusion to another, in addition, analysis of cephalograms showing the value of angles and linear dimensions differed from one type of malocclusion to another. Photographic analysis using GMM afforded a statistically reliable correlation between naso-labial traits, and particularly between the vermillion border outline and malocclusion patterns. Due to their shared ancestry (Caucasian), both Jordanian and Scottish populations showed the same morphological trends for the lips, for example: long lower facial height, a deep philtrum, V-shaped Cupid’s bow, thin upper vermillion border. GMM results suggest that vermillion border variation could be computed, at least when distinguishing between malocclusion classes from the same ethnic group. Morphological, GMM, and cephalograms analyses confirmed that the shape and diversity in the Vermillion XIV border outline differed between malocclusion classes, but few or no differences could be shown between the sexes.