Статті в журналах з теми "Concept-Drift Management"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Concept-Drift Management.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Concept-Drift Management".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Cano, Andrés, Manuel Gómez-Olmedo, and Serafín Moral. "A Bayesian approach to abrupt concept drift." Knowledge-Based Systems 185 (December 2019): 104909. http://dx.doi.org/10.1016/j.knosys.2019.104909.
Повний текст джерела
2
Bayram, Firas, Bestoun S. Ahmed, and Andreas Kassler. "From concept drift to model degradation: An overview on performance-aware drift detectors." Knowledge-Based Systems 245 (June 2022): 108632. http://dx.doi.org/10.1016/j.knosys.2022.108632.
Повний текст джерела
3
Elkhawaga, Ghada, Mervat Abuelkheir, Sherif I. Barakat, Alaa M. Riad, and Manfred Reichert. "CONDA-PM—A Systematic Review and Framework for Concept Drift Analysis in Process Mining." Algorithms 13, no. 7 (July 3, 2020): 161. http://dx.doi.org/10.3390/a13070161.
Повний текст джерелаАнотація:
Business processes evolve over time to adapt to changing business environments. This requires continuous monitoring of business processes to gain insights into whether they conform to the intended design or deviate from it. The situation when a business process changes while being analysed is denoted as Concept Drift. Its analysis is concerned with studying how a business process changes, in terms of detecting and localising changes and studying the effects of the latter. Concept drift analysis is crucial to enable early detection and management of changes, that is, whether to promote a change to become part of an improved process, or to reject the change and make decisions to mitigate its effects. Despite its importance, there exists no comprehensive framework for analysing concept drift types, affected process perspectives, and granularity levels of a business process. This article proposes the CONcept Drift Analysis in Process Mining (CONDA-PM) framework describing phases and requirements of a concept drift analysis approach. CONDA-PM was derived from a Systematic Literature Review (SLR) of current approaches analysing concept drift. We apply the CONDA-PM framework on current approaches to concept drift analysis and evaluate their maturity. Applying CONDA-PM framework highlights areas where research is needed to complement existing efforts.
4
Zheng, Xiulin, Peipei Li, Xuegang Hu, and Kui Yu. "Semi-supervised classification on data streams with recurring concept drift and concept evolution." Knowledge-Based Systems 215 (March 2021): 106749. http://dx.doi.org/10.1016/j.knosys.2021.106749.
Повний текст джерела
5
Mwitondi, Kassim S., and Raed A. Said. "Dealing with Randomness and Concept Drift in Large Datasets." Data 6, no. 7 (July 19, 2021): 77. http://dx.doi.org/10.3390/data6070077.
Повний текст джерелаАнотація:
Data-driven solutions to societal challenges continue to bring new dimensions to our daily lives. For example, while good-quality education is a well-acknowledged foundation of sustainable development, innovation and creativity, variations in student attainment and general performance remain commonplace. Developing data -driven solutions hinges on two fronts-technical and application. The former relates to the modelling perspective, where two of the major challenges are the impact of data randomness and general variations in definitions, typically referred to as concept drift in machine learning. The latter relates to devising data-driven solutions to address real-life challenges such as identifying potential triggers of pedagogical performance, which aligns with the Sustainable Development Goal (SDG) #4-Quality Education. A total of 3145 pedagogical data points were obtained from the central data collection platform for the United Arab Emirates (UAE) Ministry of Education (MoE). Using simple data visualisation and machine learning techniques via a generic algorithm for sampling, measuring and assessing, the paper highlights research pathways for educationists and data scientists to attain unified goals in an interdisciplinary context. Its novelty derives from embedded capacity to address data randomness and concept drift by minimising modelling variations and yielding consistent results across samples. Results show that intricate relationships among data attributes describe the invariant conditions that practitioners in the two overlapping fields of data science and education must identify.
6
Cabral, Danilo Rafael de Lima, and Roberto Souto Maior de Barros. "Concept drift detection based on Fisher’s Exact test." Information Sciences 442-443 (May 2018): 220–34. http://dx.doi.org/10.1016/j.ins.2018.02.054.
Повний текст джерела
7
Barros, Roberto Souto Maior, and Silas Garrido T. Carvalho Santos. "A large-scale comparison of concept drift detectors." Information Sciences 451-452 (July 2018): 348–70. http://dx.doi.org/10.1016/j.ins.2018.04.014.
Повний текст джерела
8
Delany, Sarah Jane, Pádraig Cunningham, Alexey Tsymbal, and Lorcan Coyle. "A case-based technique for tracking concept drift in spam filtering." Knowledge-Based Systems 18, no. 4-5 (August 2005): 187–95. http://dx.doi.org/10.1016/j.knosys.2004.10.002.
Повний текст джерела
9
Li, Yanhong, Deyu Li, Suge Wang, and Yanhui Zhai. "Incremental entropy-based clustering on categorical data streams with concept drift." Knowledge-Based Systems 59 (March 2014): 33–47. http://dx.doi.org/10.1016/j.knosys.2014.02.004.
Повний текст джерела
10
Thaipisutikul, Tipajin. "An Adaptive Temporal-Concept Drift Model for Sequential Recommendation." ECTI Transactions on Computer and Information Technology (ECTI-CIT) 16, no. 2 (June 11, 2022): 222–36. http://dx.doi.org/10.37936/ecti-cit.2022162.248019.
Повний текст джерелаАнотація:
Recently, owing to the great advances in Web 2.0 and mobile devices, various online commercial services have emerged. Recommendation systems play an important role in dealing with abundant product information from massive numbers of online e-commerce transactions. Providing an accurate recommendation at the correct time to customers can contribute to a surge in business success. In this paper, an adaptive temporal-concept drift learning-based recommendation system, ATCRec, is developed for precisely tackling the sequential recommendation problem. We embed sequences of items into the latent spaces and learn both general preferences and sequential patterns concurrently via a recurrent neural network. Specifically, ATCRec captures dynamic changes in the temporal and concept drift contexts by modifying the gate units in a traditional recurrent neural network. The proposed model provides a unified and flexible network structure to learn and reveal the opaque variation of user preferences over time. We evaluate the robustness and performance of ATCRec on two real-world datasets, and the experimental results demonstrate that ATCRec consistently outperforms existing sequential recommendation approaches on various metrics. This indicates that integrating users' temporal information and concept drift variation through time are indispensable in improving the performance of recommendation systems.
11
Thaipisutikul, Tipajin. "An Adaptive Temporal-Concept Drift Model for Sequential Recommendation." ECTI Transactions on Computer and Information Technology (ECTI-CIT) 16, no. 2 (June 7, 2022): 221–35. http://dx.doi.org/10.37936/ecticit.2022162.248019.
Повний текст джерелаАнотація:
Recently, owing to the great advances in Web 2.0 and mobile devices, various online commercial services have emerged. Recommendation systems play an important role in dealing with abundant product information from massive numbers of online e-commerce transactions. Providing an accurate recommendation at the correct time to customers can contribute to a surge in business success. In this paper, an adaptive temporal-concept drift learning-based recommendation system, ATCRec, is developed for precisely tackling the sequential recommendation problem. We embed sequences of items into the latent spaces and learn both general preferences and sequential patterns concurrently via a recurrent neural network. Specifically, ATCRec captures dynamic changes in the temporal and concept drift contexts by modifying the gate units in a traditional recurrent neural network. The proposed model provides a unified and flexible network structure to learn and reveal the opaque variation of user preferences over time. We evaluate the robustness and performance of ATCRec on two real-world datasets, and the experimental results demonstrate that ATCRec consistently outperforms existing sequential recommendation approaches on various metrics. This indicates that integrating users' temporal information and concept drift variation through time are indispensable in improving the performance of recommendation systems.
12
Johansen, Øistein. "DOOSIM—A NEW SIMULATION MODEL FOR OIL SPILL MANAGEMENT." International Oil Spill Conference Proceedings 1987, no. 1 (April 1, 1987): 529–32. http://dx.doi.org/10.7901/2169-3358-1987-1-529.
Повний текст джерелаАнотація:
ABSTRACT A new oil spill simulation model has been developed as a part of the research program Dispersion of Oil On Sea (DOOS). The model includes features such as simulation of drift and fate of oil on the surface and in the water column, as well as effects of cleanup measures (mechanical recovery, application of chemical dispersants). The model utilizes the particle-in-fluid concept, where the oil spill is represented by a large number of particles in different states, i.e., on the surface, entrained in the water column, or evaporated. The near surface current shear is taken into account in the wind induced component of the drift, in terms of a two layer approach (reduced wind drift factor for entrained oil). In the design of the model, major efforts have been made to obtain a system which is easy to operate. This has led to a system consisting of three modules: one for entry of user-specified inputs, one for simulating an actual spill, and one for graphical presentation.
13
Toquica, David, Kodjo Agbossou, Roland Malhamé, Nilson Henao, Sousso Kelouwani, and Alben Cardenas. "Adaptive Machine Learning for Automated Modeling of Residential Prosumer Agents." Energies 13, no. 9 (May 4, 2020): 2250. http://dx.doi.org/10.3390/en13092250.
Повний текст джерелаАнотація:
An efficient participation of prosumers in power system management depends on the quality of information they can obtain. Prosumers actions can be performed by automated agents that are operating in time-changing environments. Therefore, it is essential for them to deal with data stream problems in order to make reliable decisions based on the most accurate information. This paper provides an in-depth investigation of data and concept drift issues in accordance with residential prosumer agents. Additionally, the adaptation techniques, forgetting mechanisms, and learning strategies employed to handle these issues are explored. Accordingly, an approach is proposed to adapt the prosumer agent models to overcome the gradual and sudden concept drift concurrently. The suggested method is based on triggered adaptation techniques and performance-based forgetting mechanism. The results obtained in this study demonstrate that the proposed approach is capable of constructing efficient prosumer agents models with regard to the concept drift problem.
14
Feitosa Neto, Antonino, and Anne M. P. Canuto. "EOCD: An ensemble optimization approach for concept drift applications." Information Sciences 561 (June 2021): 81–100. http://dx.doi.org/10.1016/j.ins.2021.01.051.
Повний текст джерела
15
Guo, Husheng, Hai Li, Qiaoyan Ren, and Wenjian Wang. "Concept drift type identification based on multi-sliding windows." Information Sciences 585 (March 2022): 1–23. http://dx.doi.org/10.1016/j.ins.2021.11.023.
Повний текст джерела
16
Nagendhiran, Nalini, and Lakshmanan Kuppusamy. "Adaptive Drift Detection Mechanism for Non-Stationary Data Stream." Journal of Information & Knowledge Management 20, no. 01 (March 2021): 2150008. http://dx.doi.org/10.1142/s0219649221500088.
Повний текст джерелаАнотація:
Mining is a challenging and important task in a non-stationary data stream. It is used in financial sectors, web log analysis, sensor networks, network traffic management, etc. In this environment, data distribution may change overtime and is called concept drift. So, it is necessary to identify the changes and address them to keep the model relevant to the incoming data. Many researchers have used Drift Detection Method (DDM). However, DDM is very sensitive to detect gradual drift where the detection delay is high. In this paper, we propose Adaptive Drift Detection Method (ADDM) which improves the performance of the drift detection mechanism. The ADDM uses a new parameter to detect the gradual drift in order to reduce the detection delay. The proposed method, ADDM, experiments with six synthetic datasets and four real-world datasets. Experimental results confirm that ADDM reduces the drift detection delay and false-positive rate (FPR) while preserving high classification accuracy.
17
Li, Shengzeng, Yiwen Zhong, and Jiaxiang Lin. "AWS-DAIE: Incremental Ensemble Short-Term Electricity Load Forecasting Based on Sample Domain Adaptation." Sustainability 14, no. 21 (October 31, 2022): 14205. http://dx.doi.org/10.3390/su142114205.
Повний текст джерелаАнотація:
Short-term load forecasting is a prerequisite and basis for power system planning and operation and has received extensive attention from researchers. To address the problem of concept drift caused by changes in the distribution patterns of electricity load data, researchers have proposed regular or quantitative model update strategies to cope with the concept drift; however, this may involve a large number of invalid updates, which not only have limited improvement in model accuracy, but also insufficient model response timeliness to meet the requirements of power systems. Hence, this paper proposes a novel incremental ensemble model based on sample domain adaptation (AWS-DAIE) for adapting concept drift in a timely and accurate manner and solves the problem of inadequate training of the model due to the few concept drift samples. The main idea of AWS-DAIE is to detect concept drift on current electricity load data and train a new base predictor using Tradaboost based on cumulative weighted sampling and then dynamically adjust the weights of the ensemble model according to the performance of the model under current electricity load data. For the purposes of demonstrating the feasibility and effectiveness of the proposed AWS-DAIE algorithm, we present the experimental results of the AWS-DAIE algorithm on electricity load data from four individual households and compared with several other excellent algorithms. The experimental results demonstrated that the proposed AWS-DAIE not only can adapt to the changes of the data distribution faster, but also outperforms all compared models in terms of prediction accuracy and has good practicality.
18
Liu, Weike, Hang Zhang, Zhaoyun Ding, Qingbao Liu, and Cheng Zhu. "A comprehensive active learning method for multiclass imbalanced data streams with concept drift." Knowledge-Based Systems 215 (March 2021): 106778. http://dx.doi.org/10.1016/j.knosys.2021.106778.
Повний текст джерела
19
Li, Zeng, Wenchao Huang, Yan Xiong, Siqi Ren, and Tuanfei Zhu. "Incremental learning imbalanced data streams with concept drift: The dynamic updated ensemble algorithm." Knowledge-Based Systems 195 (May 2020): 105694. http://dx.doi.org/10.1016/j.knosys.2020.105694.
Повний текст джерела
20
Tan, Chang How, Vincent C. S. Lee, and Mahsa Salehi. "Information resources estimation for accurate distribution-based concept drift detection." Information Processing & Management 59, no. 3 (May 2022): 102911. http://dx.doi.org/10.1016/j.ipm.2022.102911.
Повний текст джерела
21
Ren, Siqi, Bo Liao, Wen Zhu, and Keqin Li. "Knowledge-maximized ensemble algorithm for different types of concept drift." Information Sciences 430-431 (March 2018): 261–81. http://dx.doi.org/10.1016/j.ins.2017.11.046.
Повний текст джерела
22
Bonnemaire, Basile. "Arctic Offshore Loading Downtime Due to Variability in Ice Drift Direction." Journal of Navigation 59, no. 1 (December 15, 2005): 9–26. http://dx.doi.org/10.1017/s0373463305003474.
Повний текст джерелаАнотація:
Four arctic offshore loading concepts are selected, loading from the corner of a platform, loading in the wake of a loading tower, Submerged Turret Loading (STL) and Single Anchor Loading (SAL). The influence of variations in the ice drift direction on the performance of these concepts is discussed and critical drift events are determined. Ice drift measurements from eight ARGOS/GPS buoys deployed in the Pechora Sea in winters 1995 and 1998 are analysed to estimate downtime rates of these loading systems due to ice drift heading changes. Depending on the location in the Pechora Sea and the chosen concept, downtime rates range from 6 to 72%. A discussion on how these rates will vary with different assumptions, different ice conditions or different ice management is given. Finally the loading concepts are compared through a qualitative risk analysis.
23
Id, Ibnu Daqiqil, Masanobu Abe, and Sunao Hara. "Acoustic Scene Classifier Based on Gaussian Mixture Model in the Concept Drift Situation." Advances in Science, Technology and Engineering Systems Journal 6, no. 5 (September 2021): 167–76. http://dx.doi.org/10.25046/aj060519.
Повний текст джерела
24
Santos, Silas G. T. C., Roberto S. M. Barros, and Paulo M. Gonçalves. "A differential evolution based method for tuning concept drift detectors in data streams." Information Sciences 485 (June 2019): 376–93. http://dx.doi.org/10.1016/j.ins.2019.02.031.
Повний текст джерела
25
Hammoodi, Mahmood Shakir, Frederic Stahl, and Atta Badii. "Real-time feature selection technique with concept drift detection using adaptive micro-clusters for data stream mining." Knowledge-Based Systems 161 (December 2018): 205–39. http://dx.doi.org/10.1016/j.knosys.2018.08.007.
Повний текст джерела
26
Sun, Jie, Hamido Fujita, Peng Chen, and Hui Li. "Dynamic financial distress prediction with concept drift based on time weighting combined with Adaboost support vector machine ensemble." Knowledge-Based Systems 120 (March 2017): 4–14. http://dx.doi.org/10.1016/j.knosys.2016.12.019.
Повний текст джерела
27
Bing-quan, Li, and Liang Chun-xi. "Mortality Anxiety Management of Chinese Undergraduates in the Horizon of Cultural Psychology." Journal of Asian Research 4, no. 3 (August 25, 2020): p50. http://dx.doi.org/10.22158/jar.v4n3p50.
Повний текст джерелаАнотація:
The death attitude and personality questionnaire was used to investigate and analyze Chinese undergraduates’ views on death. The results showed that: (1) The mortality concept of Chinese undergraduates is divided into nine dimensions, which sequence ranked from high to low according to their scores is unfinished feeling, interpersonal relationship, life review, calmness, life attachment, liberation, spiritual concept, terror and pain. This result is obviously inconsistent with Terror Management Theory (TMT), reflecting the characteristics of Chinese culture. (2) The mortality cognition of Chinese undergraduates is divided into seven dimensions, which sequence ranked from high to low according to their scores is body’s becoming cold, body’s decay, sensory loss, consciousness loss, loss of control, soul drift away, and body’s becoming stiffness. This result is consistent with TMT. However, the subjects’ statements about the cognition of the process of spiritual change at death salience reflected the color of Chinese culture, consistent with Taoist and Buddhist thoughts in Chinese traditional culture. This shows that there are the thoughts of death anxiety management in Chinese culture, which are of great value and Enlightenment to the effective development of life education.
28
Elzinga, Aant. "The science-society contract in historical transformation: with special reference to “epistemic drift”." Social Science Information 36, no. 3 (September 1997): 411–45. http://dx.doi.org/10.1177/053901897036003002.
Повний текст джерелаАнотація:
This paper locates the discussion around the finalization thesis in a broader science policy context, linking it to the recent discourse on a changing science-society contract. It is argued that the broadening of the Kuhnian concept of the paradigm, making it amenable to science policy studies, was an important move. Further development of this notion, however, standed on the prongs of critique coming from both the worlds of politics and science. At the same time, advances in the cognitive sociology of science undermined the internalist/externalist distinction. Today, with certain changes in the conditions of research due to the introduction of the concept of “strategic research”, politicians are more apt to accept certain points of the thesis; scientific communities, on the other hand, perceive new threats to their autonomy. This paper tries to make sense of this new situation by translating the question of interplay between internal and external dynamics of research into one involving boundary management and epistemic criteria. The notion of “epistemic drift” is introduced and the internalist/externalist distinction refurbished in neo-institutionalist terms, making use of the concept of interfoliating credibility cycles.
29
Kahraman, Abdulgani, Mehmed Kantardzic, Muhammet Mustafa Kahraman, and Muhammed Kotan. "A Data-Driven Multi-Regime Approach for Predicting Energy Consumption." Energies 14, no. 20 (October 17, 2021): 6763. http://dx.doi.org/10.3390/en14206763.
Повний текст джерелаАнотація:
There has been increasing interest in reducing carbon footprints globally in recent years. Hence increasing share of green energy and energy efficiency are promoted by governments. Therefore, optimizing energy consumption is becoming more critical for people, companies, industries, and the environment. Predicting energy consumption more precisely means that future energy management planning can be more effective. To date, most research papers have focused on predicting residential building energy consumption; however, a large portion of the energy is consumed by industrial machines. Prediction of energy consumption of large industrial machines in real time is challenging due to concept drift, in which prediction performance deteriorates over time. In this research, a novel data-driven method multi-regime approach (MRA) was developed to better predict the energy consumption for industrial machines. Whereas most papers have focused on finding an excellent prediction model that contradicts the no-free-lunch theorem, this study concentrated on adding potential concept drift points into the prediction process. A real-world dataset was collected from a semi-autonomous grinding (SAG) mill used as a data source, and a deep neural network was utilized as a prediction model for the MRA method. The results proved that the MRA method enables the detection of multi-regimes over time and provides a highly accurate prediction performance, thanks to the dynamic model approach.
30
da Motta, Lucas Marchi, Elírio Ernestino Toldo, Luiz Emílio de Sá, Brito de Almeida, and José Carlos Nunes. "Sandy sediment budget of the midcoast of Rio Grande do Sul, Brazil." Journal of Marine Research 73, no. 3 (May 1, 2015): 49–69. http://dx.doi.org/10.1357/002224015815848839.
Повний текст джерелаАнотація:
Calculation of the coastal sediment budget involves estimation of the timing and intensity of processes of erosion, transport, and deposition, as well as an understanding of local and regional sediment dynamics. The modern sedimentary deposits present in the coastal zone constitute the physical basis of coastal ecosystems. Knowledge of the dynamics of these sediments from the source to sink area, through regional sediment management, is critical to understanding the long-term stability of the coastal zone and the fate of these important natural resources. In this article, the littoral cell concept has been applied to the midcoast of Rio Grande do Sul, a wave-dominated and dissipative-intermediate sandy coast in southern Brazil. To analyze littoral drift variations along the 275 km long study area, the shoreline was divided into 12 cells. Littoral drift rates were estimated and compared using the energy flux method. Wave parameters were obtained from WAVEWATCH III. The sand volume of the coastal dune field (4.20 billion m3) was quantified using satellite imagery and the aeolian transport rates estimated utilizing the sediment budget residual. The net annual longshore transport rates obtained with the Coastal Engineering Research Center equation range from 0.60 to 2.63 million m3 per year. The littoral drift rates obtained with the Van Rijn (2001) and Kamphuis (1991) equations range between 0.15 and 1.00 million m3 per year. Based on the sediment budget and dune field age, the CERC formula seems more appropriate to estimate longshore transport.
31
Tota, Antonio, Enrico Galvagno, Luca Dimauro, Alessandro Vigliani, and Mauro Velardocchia. "Energy Management Strategy for Hybrid Multimode Powertrains: Influence of Inertial Properties and Road Inclination." Applied Sciences 11, no. 24 (December 10, 2021): 11752. http://dx.doi.org/10.3390/app112411752.
Повний текст джерелаАнотація:
Multimode hybrid powertrains have captured the attention of automotive OEMs for their flexible nature and ability to provide better and optimized efficiency levels. However, the presence of multiple actuators, with different efficiency and dynamic characteristics, increases the problem complexity for minimizing the overall power losses in each powertrain operating condition. The paper aims at providing a methodology to select the powertrain mode and set the reference torques and angular speeds for each actuator, based on the power-weighted efficiency concept. The power-weighted efficiency is formulated to normalize the efficiency contribution from each power source and to include the inertial properties of the powertrain components as well as the vehicle motion resistance forces. The approach, valid for a wide category of multimode powertrain architectures, is then applied to the specific case of a two-mode hybrid system where the engagement of one of the two clutches enables an Input Split or Compound Split operative mode. The simulation results obtained with the procedure prove to be promising in avoiding excessive accelerations, drift of powertrain components, and in managing the power flow for uphill and downhill vehicle conditions.
32
Ojugo, Arnold Adimabua, and Andrew Okonji Eboka. "Inventory prediction and management in Nigeria using market basket analysis associative rule mining: memetic algorithm based approach." International Journal of Informatics and Communication Technology (IJ-ICT) 8, no. 3 (November 13, 2019): 128. http://dx.doi.org/10.11591/ijict.v8i3.pp128-138.
Повний текст джерелаАнотація:
<p class="Text">A key challenge in businesses today is determining inventory level for each product (to be) sold to clients. A pre-knowledge will suppress inventory stock-up and help avert unnecessary demurrage. It will also avoid stock out and avert loss of clients to competition. Study aims to unveil customer’s behavior in purchasing goods and thus, predict a next time purchase as well as serve as decision support to determine the required amount of each goods inventory. Study is conducted for Delta Mall (Asaba and Warri branches) department store. We adapt the memetic algorithm on market basket dataset to examine buying behavior of customers, their preference and frequency at which goods are purchased in common (basket). Result shows some items placed in basket allow customers to purchase items of similar value, or best combined with the selected items due to shelf-placement via concept of feature drift. Model yields 21-rules for eight items obtained from data transaction mining dataset acquired from Delta Mall.</p>
33
Niu, Huifang, Jianchao Zeng, Hui Shi, Bin Wang, and Tianye Liu. "A Nonlinear Prognostic Model Based on the Wiener Process with Three Sources of Uncertainty." Shock and Vibration 2021 (December 29, 2021): 1–12. http://dx.doi.org/10.1155/2021/6475056.
Повний текст джерелаАнотація:
Estimation of the remaining useful life (RUL) is an important component of prognostics and health management (PHM). The accuracy of the RUL estimation for complex systems is mainly affected by three sources of uncertainty, i.e., the temporal uncertainty, the product-to-product uncertainty, and measurement errors. To improve PHM and account for the effects of the three sources of uncertainty, a nonlinear prognostic model with three sources of uncertainty is presented here. An approximated analytical expression for the probability density function (PDF) of the RUL is obtained based on the concept of first hitting time (FHT). Model parameters are then obtained by the expectation maximization (EM) algorithm, and the drift parameter is estimated adaptively using a Bayesian procedure. Finally, in order to illustrate the practical applications of the presented approach, a comparative study of real data on fatigue crack propagation is presented. Results demonstrate that our method improves model fit and increases the accuracy of the lifetime estimation.
34
Venkatesiah, Sowmya Samudrala, Dominic Augustine, Deepika Mishra, Neethi Gujjar, Vanishri C. Haragannavar, Kamran Habib Awan, and Shankargouda Patil. "Immunology of Oral Squamous Cell Carcinoma—A Comprehensive Insight with Recent Concepts." Life 12, no. 11 (November 7, 2022): 1807. http://dx.doi.org/10.3390/life12111807.
Повний текст джерелаАнотація:
This review aims to understand the concept of oral cancer immunology through the notion of immune profiling, immunoediting and immunotherapy, and to gain knowledge regarding its application for the management of oral cancer patients. Oral cancer is an immunogenic tumor where the cells of the tumor microenvironment play an important role in tumorigenesis. Understanding the mechanism of these modulations can help design immunotherapeutic strategies in oral cancer patients. This article gives an overview of immunomodulation in the oral cancer tumor microenvironment, with concepts of immune profiling, immunoediting and immunotherapy. English literature searches via Google Scholar, Web of Science, EBSCO, Scopus, and PubMed database were performed with the key words immunology, tumor microenvironment, cells, cross talk, immune profiling, biomarkers, inflammation, gene expression, techniques, immunoediting, immunosurveillance, tumor escape, immunotherapy, immune checkpoint inhibitors, vaccines in cancer, oral cancer, and head and neck cancer. Original research articles, reviews, and case reports published from 2016–2021 (n = 81) were included to appraise different topics, and were discussed under the following subsections. Literature published on oral cancer immunology reveals that oral cancer immune profiling with appropriate markers and techniques and knowledge on immunoediting concepts can help design and play an effective role in immunotherapeutic management of oral cancer patients. An evaluation of oral cancer immunology helps to determine its role in tumorigenesis, and immunotherapy could be the emerging drift in the effective management of oral cancer.
35
Ikken, Naima, Nour-Eddine Tariba, Abdelhadi Bouknadel, Ahmed Haddou, Hafsa El Omari, and Hamid El Omari. "Analysis of active islanding detection techniques for grid-connected inverters systems." Indonesian Journal of Electrical Engineering and Computer Science 25, no. 3 (March 1, 2022): 1287. http://dx.doi.org/10.11591/ijeecs.v25.i3.pp1287-1296.
Повний текст джерелаАнотація:
<span>An island is a section of the electrical grid that contains producing assets and loads that are separated from the main grid and powered by these generators, such as solar systems, with voltage and frequency maintained at nominal levels. It's worth noting that the concept of islanding is linked to time. When the inverter detects an isolated grid activity for a particular period of time, the inverter is compelled to decouple from the general grid, according to the criteria that dictate the working principle of a photovoltaic (PV) systemThis paper presents research and comparisons of the main islanding detection techniques for single-phase systems based on various structures, as well as a comparison of the improvement of the traditional islanding detection method using three different methods (active frequency drift (AFD), slip mode phase shift (SMS) and Sandia frequency shift (SFS)). Under normal and abnormal operating conditions, a comparison of these three examined improvements was made. Additionally, physical security information management (PSIM) software simulation results are generated to test the performance and effectiveness of the effective technique plan.</span>
36
Wood, Michael, Emanuele Ogliari, Alfredo Nespoli, Travis Simpkins, and Sonia Leva. "Day Ahead Electric Load Forecast: A Comprehensive LSTM-EMD Methodology and Several Diverse Case Studies." Forecasting 5, no. 1 (March 2, 2023): 297–314. http://dx.doi.org/10.3390/forecast5010016.
Повний текст джерелаАнотація:
Optimal behind-the-meter energy management often requires a day-ahead electric load forecast capable of learning non-linear and non-stationary patterns, due to the spatial disaggregation of loads and concept drift associated with time-varying physics and behavior. There are many promising machine learning techniques in the literature, but black box models lack explainability and therefore confidence in the models’ robustness can’t be achieved without thorough testing on data sets with varying and representative statistical properties. Therefore this work adopts and builds on some of the highest-performing load forecasting tools in the literature, which are Long Short-Term Memory recurrent networks, Empirical Mode Decomposition for feature engineering, and k-means clustering for outlier detection, and tests a combined methodology on seven different load data sets from six different load sectors. Forecast test set results are benchmarked against a seasonal naive model and SARIMA. The resultant skill scores range from −6.3% to 73%, indicating that the methodology adopted is often but not exclusively effective relative to the benchmarks.
37
Bagutdinov, R. A. "APPROACH OF PROCESSING, CLASSIFICATION AND DETECTION OF NEW CLASSES AND ANOMALIES IN HETEROGENIOUS AND DIFFERENT STREAMS OF DATA." Herald of Dagestan State Technical University. Technical Sciences 45, no. 3 (May 12, 2019): 85–93. http://dx.doi.org/10.21822/2073-6185-2018-45-3-85-93.
Повний текст джерелаАнотація:
Objectives. The aim of the study is to search for effective methods and approaches to the processing of heterogeneous data streams and the management of problems of infinite length, conceptual evolution and conceptual drift. A heterogeneous data stream can have infinite length and contain structured or unstructured data. Processing a heterogeneous and multi-scale data flow is a major challenge for researchers. Most of the research focuses on solving problems of infinite length and concept-drift.Method. New class detection strategies are classified as parametric and non-parametric. This work is based on a non-parametric approach. The classifier works on the ensemble of three models. The separation generates a different number of classes in each fragment. Classes are calculated by applying the K-Medoid clustering method on each fragment. The effectiveness of the K-media clustering method is more suitable for a data set containing anomalies.Result. The developed algorithm is capable of processing heterogeneous and multi-scale data. Each instance that is present in the model belongs to only one class. Experimental work was performed on four samples of stream data of 2000 lines each. After performing the pre-processing, the multi-valued characteristics of the data were found in the data set.Conclusion. This paper presents an effective approach for processing heterogeneous data streams and managing tasks of infinite length, conceptual evolution and conceptual drift. The developed approach is based on the string matching parameter instead of the distance for processing the four tasks of data streams. The level of false positives in the developed algorithm is rather low and can be considered insignificant. The approach does not classify a new instance of the class as an existing class, but can effectively handle the functional evolution.
38
SCHATZMANN, JOST, KARL WEILHAMMER, MATT STUTTLE, and STEVE YOUNG. "A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies." Knowledge Engineering Review 21, no. 2 (June 2006): 97–126. http://dx.doi.org/10.1017/s0269888906000944.
Повний текст джерелаАнотація:
Within the broad field of spoken dialogue systems, the application of machine-learning approaches to dialogue management strategy design is a rapidly growing research area. The main motivation is the hope of building systems that learn through trial-and-error interaction what constitutes a good dialogue strategy. Training of such systems could in theory be done using human users or using corpora of human–computer dialogue, but in practice the typically vast space of possible dialogue states and strategies cannot be explored without the use of automatic user simulation tools.This requirement for training statistical dialogue models has created an interesting new application area for predictive statistical user modelling and a variety of different techniques for simulating user behaviour have been presented in the literature ranging from simple Markov models to Bayesian networks. The development of reliable user simulation tools is critical to further progress on automatic dialogue management design but it holds many challenges, some of which have been encountered in other areas of current research on statistical user modelling, such as the problem of ‘concept drift’, the problem of combining content-based and collaboration-based modelling techniques, and user model evaluation. The latter topic is of particular interest, because simulation-based learning is currently one of the few applications of statistical user modelling that employs both direct ‘accuracy-based’ and indirect ‘utility-based’ evaluation techniques.In this paper, we briefly summarize the role of the dialogue manager in a spoken dialogue system, give a short introduction to reinforcement-learning of dialogue management strategies and review the literature on user modelling for simulation-based strategy learning. We further describe recent work on user model evaluation and discuss some of the current research issues in simulation-based learning from a user modelling perspective.
39
Uriarte-Arcia, Abril Valeria, Itzamá López-Yáñez, Cornelio Yáñez-Márquez, João Gama, and Oscar Camacho-Nieto. "Data Stream Classification Based on the Gamma Classifier." Mathematical Problems in Engineering 2015 (2015): 1–17. http://dx.doi.org/10.1155/2015/939175.
Повний текст джерелаАнотація:
The ever increasing data generation confronts us with the problem of handling online massive amounts of information. One of the biggest challenges is how to extract valuable information from these massive continuous data streams during single scanning. In a data stream context, data arrive continuously at high speed; therefore the algorithms developed to address this context must be efficient regarding memory and time management and capable of detecting changes over time in the underlying distribution that generated the data. This work describes a novel method for the task of pattern classification over a continuous data stream based on an associative model. The proposed method is based on the Gamma classifier, which is inspired by the Alpha-Beta associative memories, which are both supervised pattern recognition models. The proposed method is capable of handling the space and time constrain inherent to data stream scenarios. The Data Streaming Gamma classifier (DS-Gamma classifier) implements a sliding window approach to provide concept drift detection and a forgetting mechanism. In order to test the classifier, several experiments were performed using different data stream scenarios with real and synthetic data streams. The experimental results show that the method exhibits competitive performance when compared to other state-of-the-art algorithms.
40
Bellazzi, Riccardo. "Big Data and Biomedical Informatics: A Challenging Opportunity." Yearbook of Medical Informatics 23, no. 01 (August 2014): 08–13. http://dx.doi.org/10.15265/iy-2014-0024.
Повний текст джерелаАнотація:
SummaryBig data are receiving an increasing attention in biomedicine and healthcare. It is therefore important to understand the reason why big data are assuming a crucial role for the biomedical informatics community. The capability of handling big data is becoming an enabler to carry out unprecedented research studies and to implement new models of healthcare delivery. Therefore, it is first necessary to deeply understand the four elements that constitute big data, namely Volume, Variety, Velocity, and Veracity, and their meaning in practice. Then, it is mandatory to understand where big data are present, and where they can be beneficially collected. There are research fields, such as translational bioinformatics, which need to rely on big data technologies to withstand the shock wave of data that is generated every day. Other areas, ranging from epidemiology to clinical care, can benefit from the exploitation of the large amounts of data that are nowadays available, from personal monitoring to primary care. However, building big data-enabled systems carries on relevant implications in terms of reproducibility of research studies and management of privacy and data access; proper actions should be taken to deal with these issues. An interesting consequence of the big data scenario is the availability of new software, methods, and tools, such as map-reduce, cloud computing, and concept drift machine learning algorithms, which will not only contribute to big data research, but may be beneficial in many biomedical informatics applications. The way forward with the big data opportunity will require properly applied engineering principles to design studies and applications, to avoid preconceptions or over-enthusiasms, to fully exploit the available technologies, and to improve data processing and data management regulations.
41
Bagge-Petersen, Claudia M., Henriette Langstrup, Jakob E. Larsen, and Anne Frølich. "Critical user-configurations in mHealth design: How mHealth-app design practices come to bias design against chronically ill children and young people as mHealth users." DIGITAL HEALTH 8 (January 2022): 205520762211095. http://dx.doi.org/10.1177/20552076221109531.
Повний текст джерелаАнотація:
Mobile health smartphone applications (mHealth-apps) are increasingly emerging to assist children's and young people's management of chronic conditions. However, difficulties persist in applying design approaches in mHealth projects that return apps that are useful to this group. In this article, we explore ethnographically two self-proclaimed ‘user-driven’ projects designing mHealth apps for Danish patients below the age of 18 living with, respectively, haemophilia and rheumatoid arthritis. These projects initially included the perspectives of children and young people to inform the designs, however, eventually launched the final apps for adult patients only. Through a concept of ‘critical user-configuration’, we examine the projects’ challenges with attuning the designs to children and young people and how these drove their exclusion as users of the emerging mHealth apps. Critical user-configuration draws attention to critical moments in design practices where significant shifts in user-configurations take place, shaping who can become a user. More specifically, we uncover three critical moments: where mHealth projects expand the group of prospective users; where test subjects are selected; and where data governance systems and digital health infrastructures are mobilised in the design process. Throughout these critical moments, there is a drift from user-driven to data-driven design approaches which increasingly exclude groups of users who are less datafiable – in our case children and young people. We argue that besides giving voice to minors in mHealth design processes, we need to be mindful of the design practices that become decisive for – often implicitly – who can be configured as a user.
42
Floury, Paul, Jérôme Gaillardet, Eric Gayer, Julien Bouchez, Gaëlle Tallec, Patrick Ansart, Frédéric Koch, Caroline Gorge, Arnaud Blanchouin, and Jean-Louis Roubaty. "The potamochemical symphony: new progress in the high-frequency acquisition of stream chemical data." Hydrology and Earth System Sciences 21, no. 12 (December 7, 2017): 6153–65. http://dx.doi.org/10.5194/hess-21-6153-2017.
Повний текст джерелаАнотація:
Abstract. Our understanding of hydrological and chemical processes at the catchment scale is limited by our capacity to record the full breadth of the information carried by river chemistry, both in terms of sampling frequency and precision. Here, we present a proof-of-concept study of a lab in the field called the River Lab (RL), based on the idea of permanently installing a suite of laboratory instruments in the field next to a river. Housed in a small shed, this set of instruments performs analyses at a frequency of one every 40 min for major dissolved species (Na+, K+, Mg2+, Ca2+, Cl−, SO42−, NO3−) through continuous sampling and filtration of the river water using automated ion chromatographs. The RL was deployed in the Orgeval Critical Zone Observatory, France for over a year of continuous analyses. Results show that the RL is able to capture long-term fine chemical variations with no drift and a precision significantly better than conventionally achieved in the laboratory (up to ±0.5 % for all major species for over a day and up to 1.7 % over 2 months). The RL is able to capture the abrupt changes in dissolved species concentrations during a typical 6-day rain event, as well as daily oscillations during a hydrological low-flow period of summer drought. Using the measured signals as a benchmark, we numerically assess the effects of a lower sampling frequency (typical of conventional field sampling campaigns) and of a lower precision (typically reached in the laboratory) on the hydrochemical signal. The high-resolution, high-precision measurements made possible by the RL open new perspectives for understanding critical zone hydro-bio-geochemical cycles. Finally, the RL also offers a solution for management agencies to monitor water quality in quasi-real time.
43
Kronberg, Magnus, Jan Gugala, and Keijo Haapala. "State-of-the-art and proof-of-concept installations for repository concepts based in crystalline rock." Mineralogical Magazine 79, no. 6 (November 2015): 1665–73. http://dx.doi.org/10.1180/minmag.2015.079.6.43.
Повний текст джерелаАнотація:
AbstractOver the last five decades private and national energy programmes worldwide have been producing a variety of radioactive wastes. One of the safest ways of disposing of this waste is to bury it deep underground in purpose-built geological disposal facilities. Currently, there is no operating geological repository in Europe for high-level waste but the goal of the IGD-TP is that the first repository shall be fully operational before the year 2025. Several studies and experiments are ongoing at various potential repository sites in Europe with the goal to establish general approaches that can be adapted for any country in need of a geological repository.The Swedish Nuclear Fuel and Waste Management Co (SKB) in Sweden and Posiva Oy in Finland are developing a method for geological disposal of high-level long-lived nuclear waste in crystalline rock, the KBS-3 method. KBS-3V (vertical) is both organizations reference design, but KBS-3H (horizontal) emplacement is also being researched as a potential alternative. Of high importance in the development is demonstrating the technical feasibilityin situof safe and reliable construction, manufacturing, disposal and sealing of such geological disposal facilities. Parts of these demonstrations are carried out under the framework of EurAtom/FP7 and one of these projects is the LUCOEX project where SKB is demonstrating horizontal emplacement, the Multi Purpose Test (MPT), and Posiva is demonstrating vertical buffer installation processes.The MPT includes the key components of the horizontal design and comprises all essential steps; manufacturing of the full-scale components, their assembly, installation in the drift and monitoring of the early buffer evolution. The MPT installation was successfully performed in late 2013. By combining the components, an initial verification of the design implementation has been achieved. At the same time, integrating the components has meant the recognition of some design weaknesses and the design will be updated accordingly.Posiva's KBS-3V buffer installation equipment that places buffer blocks with high precision in vertical deposition holes is currently being developed and will be tested during 2014 and 2015 in real underground conditions. The machine uses vacuum lifting tools for moving the buffer blocks and laser scanning technology to position both the machine and blocks. Functionality of the concept and equipment selected will be confirmed by the tests and the installation tests will provide important information about the suitability of the selected buffer dimensions and tolerances.
44
Harahsheh, H. A. "OIL SPILL DETECTION AND MONITORING OF ABU DHABI COASTAL ZONE USING KOMPSAT-5 SAR IMAGERY." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B8 (June 24, 2016): 1115–21. http://dx.doi.org/10.5194/isprs-archives-xli-b8-1115-2016.
Повний текст джерелаАнотація:
Abu Dhabi Government endorsed vision for its Maritime Strategy ‘A safe, secure and sustainable maritime domain for Abu Dhabi'. This research study share this vision using the concept of monitoring as tool for marine protection against any possible oil pollution. The best technology to detect and monitor oil pollution and in particularly oil spill is SAR imagery In this case study we chose KOMPSAT-5 SAR. <br><br> KOMPSAT-5 carries X-band SAR for earth observation, and is capable of day-and-night imaging under all weather condition. It provides three operation modes: High Resolution Mode to provide 1 m resolution, Standard Mode to provide 3 m resolution and Wide Swath Mode to provide 20 m resolution with 100 km swath at 550 km altitude, with four modes of polarization. KOMPSAT-5 provides products for various applications; security and defense, mapping, and natural resource management, environmental monitoring, disaster monitoring and more. For our case study we chose to work with Wide Swath mode (WS) with Vertical polarization (VV) to cover a wide area of interest located to the north west of Abu Dhabi including some important islands like ”Zirku Island”, and areas with oil production activities. <br><br> The results of data acquired on 4<sup>th</sup> May 2015 show some spot of oil spill with length estimated about 3 KM, and the daily satellite data acquisition over the period July 24 through July 31 shows serious and many oil spill events some are small, but many others are considered to be big with area size around 20 km<sup>2</sup>. <br><br> In the context of oil spill pollution in the seas, we have to consider the development and increase of overseas transportation, which is an important factor for both social and economic sectors. The harmful effects of marine pollution are numerous, from the damage of marine life to the damage of the aquatic ecosystem as whole. As such, the need for oil slick detection is crucial, for the location of polluted areas and to evaluate slick drift to protect the coastline. Satellite-based oil spill monitoring system now can be used to take precautions and even to determine the possible polluter; it has a vital importance on the detection and protection of national and international waters from the possible damages of petroleum hazard. Finally, and as we suggested in previous studies, we recommend to the national authorities to establish a national near-real time oil spill monitoring system based on SAR satellite imagery, with the support of other tools like AIS and navigation radars
45
Harahsheh, H. A. "OIL SPILL DETECTION AND MONITORING OF ABU DHABI COASTAL ZONE USING KOMPSAT-5 SAR IMAGERY." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B8 (June 24, 2016): 1115–21. http://dx.doi.org/10.5194/isprsarchives-xli-b8-1115-2016.
Повний текст джерелаАнотація:
Abu Dhabi Government endorsed vision for its Maritime Strategy ‘A safe, secure and sustainable maritime domain for Abu Dhabi'. This research study share this vision using the concept of monitoring as tool for marine protection against any possible oil pollution. The best technology to detect and monitor oil pollution and in particularly oil spill is SAR imagery In this case study we chose KOMPSAT-5 SAR. <br><br> KOMPSAT-5 carries X-band SAR for earth observation, and is capable of day-and-night imaging under all weather condition. It provides three operation modes: High Resolution Mode to provide 1 m resolution, Standard Mode to provide 3 m resolution and Wide Swath Mode to provide 20 m resolution with 100 km swath at 550 km altitude, with four modes of polarization. KOMPSAT-5 provides products for various applications; security and defense, mapping, and natural resource management, environmental monitoring, disaster monitoring and more. For our case study we chose to work with Wide Swath mode (WS) with Vertical polarization (VV) to cover a wide area of interest located to the north west of Abu Dhabi including some important islands like ”Zirku Island”, and areas with oil production activities. <br><br> The results of data acquired on 4<sup>th</sup> May 2015 show some spot of oil spill with length estimated about 3 KM, and the daily satellite data acquisition over the period July 24 through July 31 shows serious and many oil spill events some are small, but many others are considered to be big with area size around 20 km<sup>2</sup>. <br><br> In the context of oil spill pollution in the seas, we have to consider the development and increase of overseas transportation, which is an important factor for both social and economic sectors. The harmful effects of marine pollution are numerous, from the damage of marine life to the damage of the aquatic ecosystem as whole. As such, the need for oil slick detection is crucial, for the location of polluted areas and to evaluate slick drift to protect the coastline. Satellite-based oil spill monitoring system now can be used to take precautions and even to determine the possible polluter; it has a vital importance on the detection and protection of national and international waters from the possible damages of petroleum hazard. Finally, and as we suggested in previous studies, we recommend to the national authorities to establish a national near-real time oil spill monitoring system based on SAR satellite imagery, with the support of other tools like AIS and navigation radars
46
Scott, J. S., and R. A. Gibb. "Results of geoscience research in the Canadian Nuclear Fuel Waste Management Program: Introduction." Canadian Journal of Earth Sciences 26, no. 2 (February 1, 1989): 341–44. http://dx.doi.org/10.1139/e89-032.
Повний текст джерелаАнотація:
Canada, along with other countries that are considering the permanent disposal of high-level radioactive wastes from nuclear power generation, is undertaking a program of research into deep geological disposal. This program, led by Atomic Energy of Canada Limited (AECL) with support from Energy, Mines and Resources Canada, other federal government departments, universities, and industrial consultants, has been in progress since early in 1973. Geoscience research, the subject of this symposium, complements research on fuel waste immobilization to provide the data and information essential to the design and assessment of a complete disposal concept involving both natural and engineered barriers to the migration of radioactive material from the waste vault.During the early phases of the program, prior to 1975, an evaluation of the potential of Canadian salt deposits for nuclear waste disposal, as well as a preliminary assessment of the suitability of other geological formations, was made. Because the Province of Ontario was, and remains, the principal region in Canada for nuclear power development and because resources available for geoscience research would not permit simultaneous, intensive research on a number of rock types, the decision was taken to direct the main thrust of the geoscience research toward plutonic igneous rocks of the Canadian Shield in Ontario (Scott 1979). Lesser studies of salt and other sedimentary formations, including seabed, are continuing within the Geological Survey of Canada.Because the rock mass surrounding the vault will provide the principal barrier to the migration of radionuclides, should these be released from the emplaced wastes, knowledge and understanding of potential pathways through the rock mass and of the mechanisms of radionuclide transport and retention within the rock mass over the functional lifetime of the vault are fundamental requirements.Accordingly, the objectives of the geoscience research program (Dormuth and Scott 1984) are the following:(1) Develop and apply techniques to define the physical and chemical properties of large rock masses and of fluids within these rock masses.(2) Use these techniques in selected field research areas to calibrate and evaluate models developed to calculate fluid flow and mass transport through a large rock mass containing a hypothetical underground nuclear fuel waste-disposal vault.(3) Establish procedures to evaluate quantitatively rock bodies for their potential as disposal sites and thereby acquire the capability to compare different rock bodies.(4) Determine the long-term stability of plutonic rock masses by assessing the potential disturbance by seismic activity, glaciation, meteorite impact, and other disruptive events and processes.To achieve these objectives it has been necessary to undertake simultaneously a large number of research tasks involving the disciplines of geology, geophysics, hydrogeology, geomechanics, geochemistry, and mathematics. Some of these tasks are concerned primarily with regional aspects of the Canadian Shield, such as stress distribution, glaciation, and tectonic history; others with details of the surface and subsurface geology and hydrogeology of specific field research areas; and still others with the development and application of exploration technology to detect and evaluate the structural characteristics of igneous rock masses of relatively high integrity and uniformity. Field and office studies are supported by laboratory investigations of the physical and chemical properties of plutonic rocks, with specific reference to origin, history, and ability to retard or transmit radionuclides.Deep exploratory drilling and detailed surface mapping are carried out at designated field research areas in the Canadian Shield. Geoscience work at research areas has the two-fold purpose of (i) testing new and existing exploration techniques for the evaluation of rock masses; and (ii) through application of these airborne, surface, and subsurface techniques, providing the field data necessary for the development of concepts and models that form the basis for establishing site-selection criteria and performing safety analyses.The latest research areas have been established at Atikokan, Ontario, an area underlain by granitic rocks, and at East Bull Lake north of Massey, Ontario, where gabbroic rocks are the dominant type. These research areas complement previously established research areas developed on granitic rocks at AECL properties at Chalk River, Ontario, and Pinawa, Manitoba, and at a research area, also on granitic terrane, near White Lake, Ontario, where work was done early in the program to test geophysical exploration and borehole-logging equipment.The ability to predict subsurface geological and hydrogeological conditions at future waste-disposal sites is one of the primary goals of geoscience research in the Canadian Nuclear Fuel Waste Management Program (CNFWMP). One of the most important program elements designed to test this predictive capability was the construction of the Underground Research Laboratory (URL) in the Lac du Bonnet Batholith near the site of the Whiteshell Nuclear Research Establishment. Airborne, surface, and borehole methods were used to develop a geological model on the site, and hydrogeological investigations were carried out to establish preconstruction groundwater characteristics. As the excavation of the URL facilities proceeded, the geological features encountered and the changes in the hydrogeological systems were carefully monitored. These data are being used to assess and improve the geological and hydrogeological models being developed for the rock mass surrounding the URL.The URL provides an excellent opportunity to (i) study the effect of excavation techniques, heat, and stress on a rock mass; (ii) simulate and study the complex systems that may exist in a disposal vault environment; and (iii) develop and test shaft- and drift-sealing techniques. Recently, a bilateral agreement between AECL and the United States Department of Energy was signed for co-operative research on nuclear fuel waste disposal. A substantial part of this co-operative effort will be directed toward extension of the URL shaft beyond its present depth of 240 m and conducting a variety of nonnuclear experiments within the shaft and excavated chambers of the URL.From the time of formalization of CNFWMP over 10 years ago, a concerted effort has been made by AECL and other program participants to ensure both peer review of and widespread accessibility to results of research arising from CNFWMP. This symposium is the third to be sponsored by the Geological Association of Canada (GAC)—the two previous symposiums were held at GAC annual meetings in Winnipeg in 1982 and Toronto in 1978. In addition to these major symposia, general information meetings sponsored by AECL have been held annually at various centres across Canada, and research elements of CNFWMP formed a significant part of the technical program for an international meeting held by the Canadian Nuclear Society in Winnipeg in September 1986.Since 1979 the CNFWMP review process has been further enhanced by the Technical Advisory Committee chaired by L. W. Shemilt, McMaster University. This committee, comprising members nominated by major Canadian scientific and technical societies including the Canadian Geoscience Council, has annually provided a publicly available report of constructive criticism and recommendations for improvement in the research content of CNFWMP.During the second half of 1988 it is expecte
47
Schrader, Mark J., Anura P. Rathnayake, and Lav R. Khot. "Horticultural Oil Thermotherapy Delivery System for Perennial Specialty Crops: A-Proof-of-Concept and Preliminary Results." Applied Engineering in Agriculture 38, no. 2 (2022): 461–68. http://dx.doi.org/10.13031/aea.14786.
Повний текст джерелаАнотація:
HighlightsHorticultural oil thermotherapy sprayer was developed for use in perennial fruit crops.Prototype design included air-shear nozzles to spray at eight customized heights.Field evaluation provided adequate spray coverage.Abstract. Spray drift and residues of synthetic chemicals used in crop pest management are major concerns in agricultural industry. Therefore, exploration of alternative pest management technologies is necessary to minimize lasting pesticide residues without compromising biological efficacy. As such, this study reports the design and evaluation of a new horticultural oil thermotherapy (HOT) application system intended to increase biological efficacy of low-residue horticultural oils through addition of heat. A field-scale system has been constructed to apply thermotherapy onto tree fruit and berry crop canopies. This system uses a custom heating unit to preheat the spray liquid, reaching the nozzles at temperatures up to 99°C depending on application requirement. The spray delivery and temperature profiles generated by the prototyped HOT system were evaluated at three horizontal distances from the nozzle exit (0.6, 1.5, and 2.1 m) using a smart spray analytical system developed by our research group. Typical to tree fruit sprayers, higher spray delivery was collected at 0.6 m distance and trended to decrease with increasing distance from the nozzles. The spray plume temperature also decreased with increasing distance from the nozzle. The prototype was evaluated in a pear orchard providing adequate spray coverage at bottom (75% average at 1.2 m AGL) and middle (53% average at 2.4 m AGL) canopy zones. However, the coverage in the top canopy zone (3.6 m AGL) was less than 8% and will require adjustments to the nozzle assembly. Overall, configuration refinements and calibration adjustments will be required in the prototyped HOT system depending on the crop growth stage and canopy architecture for optimal application efficacy. The developed system, with due optimization, will be critical in providing evidence supporting the feasibility of HOT applications. Keywords: Alternative pest management, Application technology, Horticultural oil, Thermotherapy, Spray efficacy.
48
Riess, Mike. "Automating model management: a survey on metaheuristics for concept-drift adaptation." Journal of Data, Information and Management, August 22, 2022. http://dx.doi.org/10.1007/s42488-022-00075-5.
Повний текст джерелаАнотація:
AbstractThis study provides an overview of the literature on automated adaptation of machine learning models via metaheuristics, in settings with concept drift. Drift-adaptation of machine learning models presents a high-dimensional optimisation problem; hence, stochastic optimisation via metaheuristics has been a popular choice for finding semi-optimal solutions with low computational costs. Traditionally, automated concept drift adaptation has mainly been studied in the literature on data stream mining; however, as data drift is prevalent in many areas, analogous solutions have been proposed in other fields. Comparing the conceptual solutions across multiple fields is thereby helpful for the overall progress in this area. The found literature is qualitatively classified in terms of relevant aspects of concept drift, adaptation/automation approach and type of metaheuristic. It is found that population-based metaheuristics are by far the most widely used optimisation methods across the domains in the retrieved literature. Methodological problems such as evaluation method and transparency in terms of concept drift type tested in the experiments are discovered and discussed. Over a ten-year period, the usage of metaheuristics in the found literature transitioned from automating single tasks in model development to full model selection in recent years. More transparency in terms of evaluation method and data characteristics is important for future comparison of solutions across drift types and patterns. Furthermore, it is proposed that future studies in this area evaluate the metaheuristics as models themselves, in order to enhance the general understanding of their performance differences in drift adaptation problems.
49
Riso, Luigi, and Marco Guerzoni. "Concept Drift Estimation with Graphical Models." Information Sciences, May 2022. http://dx.doi.org/10.1016/j.ins.2022.05.056.
Повний текст джерела
50
Tian, Xing, Wing W. Y. Ng, and Huihui Xu. "Deep Incremental Hashing for Semantic Image Retrieval with Concept Drift." IEEE Transactions on Big Data, 2023, 1–13. http://dx.doi.org/10.1109/tbdata.2022.3233457.
Повний текст джерела