Academic literature on the topic 'Supervised Machine Learning; Bayesian Belief Network'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Supervised Machine Learning; Bayesian Belief Network.'
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.
Journal articles on the topic "Supervised Machine Learning; Bayesian Belief Network"
1
Baitiles, R. Ye, та B. S. Omarov. "ВЫЯВЛЕНИЕ МОШЕННИЧЕСТВА С КРЕДИТНЫМИ КАРТАМИ С ИСПОЛЬЗОВАНИЕМ МАШИННОГО ОБУЧЕНИЯ". INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES 3, № 4(12) (2022): 57–69. http://dx.doi.org/10.54309/ijict.2022.12.4.005.
Full textAbstract:
Bank fraud is "The unauthorized use of an individual's confidential information to make purchases or withdraw funds from a user's account." E-commerce is growing rapidly, and the world is moving towards digitization, cashless transactions, the use of credit cards, the number of users is rapidly increasing, and with it the number of frauds associated with it. Due to the development of technology and the increase in the number of online transactions, fraud is also increasing, leading to huge financial losses. Therefore, effective methods to reduce losses are needed. In addition, scammers find ways to steal the user's credit card information by sending fake SMS and calls, as well as by masquerade attacks, phishing attacks, and so on. This article aims to use several machine learning algorithms such as Support Vector Machine (SVM), Decision Tree, Bayesian Belief Networks, Logistic Regression, k-Nearest Neighbor (Knn), and Artificial Neural Network (ANN) to predict the occurrence of fraud. In addition, we differentiate between the implemented supervised machine learning and deep learning methods to distinguish between fraudulent and non-fraudulent transactions.
2
Solomon, Osarumwense Alile. "A Supervised Machine Learning Model for Early Detection of Epilepsy and Seizure Disorders Based On Observed Side-Effects." International Journal of Computer Science Issues 17, no. 5 (2020): 1–14. https://doi.org/10.5281/zenodo.4418870.
Full textAbstract:
Epilepsy is a neurological disorder that is persistent and characterized by uncontrolled seizure which influences individuals in respective of age and sex, with the human brain being the major spot where it is instigated without any evidence of the cause of trigger, hence affecting any part of the body. Owing to its paroxysmal nature which has affected more than 50 million individuals globally, the World Health Organization categorized epilepsy as a major and most universal neurological disease worldwide with 80% of these infected individuals living in low and middle-income countries of Sub-Sahara Africa. Even so, in the recent past, several systems have been developed to detect this non-communicable ailment, yet they delivered a ton of bogus negative during testing and couldn't distinguish epilepsy because of the overlapping symptoms it imparts to other seizure disorders. Hence, in this paper, we proposed and built up a model to predict epilepsy and seizure disorders using an AI technique called Bayesian Belief Network. The model was structured using Bayes-Server and tested with data retrieved from the epilepsy machine learning repository. The model had an overall prediction exactness of 99.98%; 99.65% and 99.45% sensitivity of epilepsy and seizure disorders in that order.
3
Ren, Qing, Asim Zia, Donna M. Rizzo, and Nancy Mathews. "Modeling the Influence of Public Risk Perceptions on the Adoption of Green Stormwater Infrastructure: An Application of Bayesian Belief Networks Versus Logistic Regressions on a Statewide Survey of Households in Vermont." Water 12, no. 10 (2020): 2793. http://dx.doi.org/10.3390/w12102793.
Full textAbstract:
There is growing environmental psychology and behavior literature with mixed empirical evidence about the influence of public risk perceptions on the adoption of environmentally friendly “green behaviors”. Adoption of stormwater green infrastructure on residential properties, while costlier in the short term compared to conventional greywater infrastructure, plays an important role in the reduction of nutrient loading from non-point sources into freshwater rivers and lakes. In this study, we use Bayesian Belief Networks (BBNs) to analyze a 2015 survey dataset (sample size = 472 respondents) about the adoption of green infrastructure (GSI) in Vermont’s residential areas, most of which are located in either the Lake Champlain Basin or Connecticut River Basin. Eight categories of GSI were investigated: roof diversion, permeable pavement, infiltration trenches, green roofs, rain gardens, constructed wetlands, tree boxes, and others. Using both unsupervised and supervised machine learning algorithms, we used Bayesian Belief Networks to quantify the influence of public risk perceptions on GSI adoption while accounting for a range of demographic and spatial variables. We also compare the effectiveness of the Bayesian Belief Network approach and logistic regression in predicting the pro-environmental behaviors (adoption of GSI). The results show that influencing factors for current adoption differ by the type of GSI. Increased perception of risk from stormwater issues is associated with the adoption of rain gardens and infiltration trenches. Runoff issues are more likely to be considered the governments’ (town, state, and federal agencies) responsibility, whereas lawn erosion is more likely to be considered the residents’ responsibility. When using the same set of variables to predict pro-environmental behaviors (adoption of GSI), the BBN approach produces more accurate predictions compared to logistic regression. The results provide insights for further research on how to encourage residents to take measures for mitigating stormwater issues and stormwater management.
4
Sahu, Abhijeet, and Katherine Davis. "Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach." Sensors 22, no. 6 (2022): 2100. http://dx.doi.org/10.3390/s22062100.
Full textAbstract:
False alerts due to misconfigured or compromised intrusion detection systems (IDS) in industrial control system (ICS) networks can lead to severe economic and operational damage. However, research using deep learning to reduce false alerts often requires the physical and cyber sensor data to be trustworthy. Implicit trust is a major problem for artificial intelligence or machine learning (AI/ML) in cyber-physical system (CPS) security, because when these solutions are most urgently needed is also when they are most at risk (e.g., during an attack). To address this, the Inter-Domain Evidence theoretic Approach for Inference (IDEA-I) is proposed that reframes the detection problem as how to make good decisions given uncertainty. Specifically, an evidence theoretic approach leveraging Dempster–Shafer (DS) combination rules and their variants is proposed for reducing false alerts. A multi-hypothesis mass function model is designed that leverages probability scores obtained from supervised-learning classifiers. Using this model, a location-cum-domain-based fusion framework is proposed to evaluate the detector’s performance using disjunctive, conjunctive, and cautious conjunctive rules. The approach is demonstrated in a cyber-physical power system testbed, and the classifiers are trained with datasets from Man-In-The-Middle attack emulation in a large-scale synthetic electric grid. For evaluating the performance, we consider plausibility, belief, pignistic, and general Bayesian theorem-based metrics as decision functions. To improve the performance, a multi-objective-based genetic algorithm is proposed for feature selection considering the decision metrics as the fitness function. Finally, we present a software application to evaluate the DS fusion approaches with different parameters and architectures.
5
Tian, Shengwei, Yilin Yan, Long Yu, Mei Wang, and Li Li. "Prediction of Anti-Malarial Activity Based on Deep Belief Network." International Journal of Computational Intelligence and Applications 17, no. 03 (2018): 1850012. http://dx.doi.org/10.1142/s1469026818500128.
Full textAbstract:
Malaria is a kind of disease that greatly threatens human health. Nearly half of the world’s population is at risk of malaria. Anti-malarial drugs which are sought, developed and synthesized keep malaria under control, having received increasing attention in drug discovery field. Machine learning techniques have been used widely in drug research and development. On the basis of semi-supervised machine learning for molecular descriptions, this research develops a multilayer deep belief network (DBN) that can be used to identify whether compounds have the anti-malarial activity. Firstly, the influence of feature dimensions on predicting accuracy is discussed. Furthermore, the proposed model is applied to contrast shallow machine learning and supervised machine learning with the similar deep architecture. The research results show that the proposed model can predict anti-malarial activity accurately. The stable performance on the evaluation metrics confirms the practicability of our model. The proposed DBN model performs better than other shallow supervised models and deep supervised models. Moreover, it could be applied to reduce the cost and the time of drug discovery.
6
Nisha.C.M and N. Thangarasu. "Deep learning algorithms and their relevance: A review." International Journal of Data Informatics and Intelligent Computing 2, no. 4 (2023): 1–10. http://dx.doi.org/10.59461/ijdiic.v2i4.78.
Full textAbstract:
Nowadays, the most revolutionary area in computer science is deep learning algorithms and models. This paper discusses deep learning and various supervised, unsupervised, and reinforcement learning models. An overview of Artificial neural network(ANN), Convolutional neural network(CNN), Recurrent neural network (RNN), Long short-term memory(LSTM), Self-organizing maps(SOM), Restricted Boltzmann machine(RBM), Deep Belief Network (DBN), Generative adversarial network(GAN), autoencoders, long short-term memory(LSTM), Gated Recurrent Unit(GRU) and Bidirectional-LSTM is provided. Various deep-learning application areas are also discussed. The most trending Chat GPT, which can understand natural language and respond to needs in various ways, uses supervised and reinforcement learning techniques. Additionally, the limitations of deep learning are discussed. This paper provides a snapshot of deep learning.
7
Karpagaselvi, S., and M. Thiyagarajan. "Online Decision Support System and Machine Learning Modeling using Bayesian Belief Network." International Journal of Computer Applications 44, no. 1 (2012): 34–36. http://dx.doi.org/10.5120/6231-8335.
Full text
8
Olofintuyi, S. S., and T. O. Omotehinwa. "Performance Evaluation of Supervised Ensemble Cyber Situation Perception Models for Computer Network." advances in multidisciplinary & scientific research journal publication 12, no. 1 (2021): 1–14. http://dx.doi.org/10.22624/aims/cisdi/2021/v12n1p1.
Full textAbstract:
The trend at which cyber threats are gaining access to companies, industries and other sectors of the economy is becoming alarming, and this is posting a serious challenge to network administrators, governments and other business owners. A formidable intrusion detection system is needed to outplay the activities of the cyberattacks. An ensemble system is believed to perform better than a single classifier. With this fact, five different Machine Learning (ML) ensemble algorithms are suggested at the perception phase of Situation Awareness (SA) model for threat detection and the algorithms include; Artificial Neural Network Based Decision Tree (ANN based DT), Bayesian Based Artificial Neural Network (BN based ANN), J48 Based Naïve Bayes Model (J48 based NB), Decision Tree based Bayesian Network (BN) and Random Forest based on Support Vector Machine (RF based SVM). The efficiency and effectiveness of all the aforementioned algorithms were evaluated based on precision, recall and accuracy. ANN based DT gave 98.87% accuracy, BN based ANN gave 99.72% accuracy, J48 based NB gave 98.90% accuracy, DT based BN gave 89.92% accuracy and FR based SVM gave 98.40% accuracy. The implication of these results is that BN based ANN is more suitable in the perception phase of SA for threats detection. Keywords- Cyber-threats, Ensemble Algorithms, Computer Network, Intrusion Detection System, Machine Learning
9
Khozouie, Nasim, Omid Rahmani Seryasat, and Sadegh Moshrefzadeh. "Prediction of Diabetes using Supervised Learning Approach." Health Nexus 2, no. 2 (2024): 103–11. http://dx.doi.org/10.61838/kman.hn.2.2.12.
Full textAbstract:
This paper provides an in depth evaluate of diverse supervised machine getting to know fashions used for predicting diabetes. It discusses the strengths and barriers of various algorithms together with decision bushes, Random Forest, Rotation Forest Ensemble Classifier diabetic, okay-superstar, Simple Bayes, Logistic Regression, Functional tree, belief neural network, dataset to expect the diabetes, a publically to be had diabetes dataset from the website online /chistio. which include 520 Samples which can be patients and these samples have 200 diabetic sufferers and 320 non-diabetic sufferers and assessment sixteen Features in it. Results are testified on the weka3.6 open-source platform and proven the use of AUC, CA, F1, precision, and recall parameters.
10
Muhammad, Anwarul Azim, and Hasan Bhuiyan Mahmudul. "Text to Emotion Extraction Using Supervised Machine Learning Techniques." TELKOMNIKA Telecommunication, Computing, Electronics and Control 16, no. 3 (2018): 1394–401. https://doi.org/10.12928/TELKOMNIKA.v16i3.8387.
Full textAbstract:
Proliferation of internet and social media has greatly increased the popularity of text communication. People convey their sentiment and emotion through text which promotes lively communication. Consequently, a tremendous amount of emotional text is generated on different social media and blogs in every moment. This has raised the necessity of automated tool for emotion mining from text. There are various rule based approaches of emotion extraction form text based on emotion intensity lexicon. However, creating emotion intensity lexicon is a time consuming and tedious process. Moreover, there is no hard and fast rule for assigning emotion intensity to words. To solve these difficulties, we propose a machine learning based approach of emotion extraction from text which relies on annotated example rather emotion intensity lexicon. We investigated Multinomial Naïve Bayesian (MNB) Classifier, Artificial Neural Network (ANN) and Support Vector Machine (SVM) for mining emotion from text. In our setup, SVM outperformed other classifiers with promising accuracy.
Dissertations / Theses on the topic "Supervised Machine Learning; Bayesian Belief Network"
1
Narasimha, Rajesh. "Application of Information Theory and Learning to Network and Biological Tomography." Diss., Georgia Institute of Technology, 2007. http://hdl.handle.net/1853/19889.
Full textAbstract:
Studying the internal characteristics of a network using measurements obtained from endhosts is known as network tomography. The foremost challenge in measurement-based approaches is the large size of a network, where only a subset of measurements can be obtained because of the inaccessibility of the entire network. As the network becomes larger, a question arises as to how rapidly the monitoring resources (number of measurements or number of samples) must grow to obtain a desired monitoring accuracy. Our work studies the scalability of the measurements with respect to the size of the network. We investigate the issues of scalability and performance evaluation in IP networks, specifically focusing on fault and congestion diagnosis. We formulate network monitoring as a machine learning problem using probabilistic graphical models that infer network states using path-based measurements. We consider the theoretical and practical management resources needed to reliably diagnose congested/faulty network elements and provide fundamental limits on the relationships between the number of probe packets, the size of the network, and the ability to accurately diagnose such network elements. We derive lower bounds on the average number of probes per edge using the variational inference technique proposed in the context of graphical models under noisy probe measurements, and then propose an entropy lower (EL) bound by drawing similarities between the coding problem over a binary symmetric channel and the diagnosis problem. Our investigation is supported by simulation results. For the congestion diagnosis case, we propose a solution based on decoding linear error control codes on a binary symmetric channel for various probing experiments. To identify the congested nodes, we construct a graphical model, and infer congestion using the belief propagation algorithm. In the second part of the work, we focus on the development of methods to automatically analyze the information contained in electron tomograms, which is a major challenge since tomograms are extremely noisy. Advances in automated data acquisition in electron tomography have led to an explosion in the amount of data that can be obtained about the spatial architecture of a variety of biologically and medically relevant objects with sizes in the range of 10-1000 nm A fundamental step in the statistical inference of large amounts of data is to segment relevant 3D features in cellular tomograms. Procedures for segmentation must work robustly and rapidly in spite of the low signal-to-noise ratios inherent in biological electron microscopy. This work evaluates various denoising techniques and then extracts relevant features of biological interest in tomograms of HIV-1 in infected human macrophages and Bdellovibrio bacterial tomograms recorded at room and cryogenic temperatures. Our approach represents an important step in automating the efficient extraction of useful information from large datasets in biological tomography and in speeding up the process of reducing gigabyte-sized tomograms to relevant byte-sized data. Next, we investigate automatic techniques for segmentation and quantitative analysis of mitochondria in MNT-1 cells imaged using ion-abrasion scanning electron microscope, and tomograms of Liposomal Doxorubicin formulations (Doxil), an anticancer nanodrug, imaged at cryogenic temperatures. A machine learning approach is formulated that exploits texture features, and joint image block-wise classification and segmentation is performed by histogram matching using a nearest neighbor classifier and chi-squared statistic as a distance measure.
2
Lockett, Daniel Edwin IV. "A Bayesian approach to habitat suitability prediction." Thesis, 2012. http://hdl.handle.net/1957/28788.
Full textAbstract:
For the west coast of North America, from northern California to southern
Washington, a habitat suitability prediction framework was developed to
support wave energy device siting. Concern that wave energy devices may
impact the seafloor and benthos has renewed research interest in the
distribution of marine benthic invertebrates and factors influencing their
distribution. A Bayesian belief network approach was employed for learning
species-habitat associations for Rhabdus rectius, a tusk-shaped marine
infaunal Mollusk. Environmental variables describing surficial geology and
water depth were found to be most influential to the distribution of R. rectius.
Water property variables, such as temperature and salinity, were less
influential as distribution predictors. Species-habitat associations were used to
predict habitat suitability probabilities for R. rectius, which were then mapped
over an area of interest along the south-central Oregon coast. Habitat
suitability prediction models tested well against data withheld for crossvalidation
supporting our conclusion that Bayesian learning extracts useful
information available in very small, incomplete data sets and identifies which
variables drive habitat suitability for R. rectius. Additionally, Bayesian belief
networks are easily updated with new information, quantitative or qualitative,
which provides a flexible mechanism for multiple scenario analyses. The
prediction framework presented here is a practical tool informing marine
spatial planning assessment through visualization of habitat suitability.<br>Graduation date: 2012
Book chapters on the topic "Supervised Machine Learning; Bayesian Belief Network"
1
Vijaya Lakshmi, Adluri, Sowmya Gudipati Sri, Ponnuru Sowjanya, and K. Vedavathi. "Prediction using Machine Learning." In Handbook of Artificial Intelligence. BENTHAM SCIENCE PUBLISHERS, 2023. http://dx.doi.org/10.2174/9789815124514123010005.
Full textAbstract:
This chapter begins with a concise introduction to machine learning and the classification of machine learning systems (supervised learning, unsupervised learning, and reinforcement learning). ‘Breast Cancer Prediction Using ML Techniques’ is the topic of Chapter 2. This chapter describes various breast cancer prediction algorithms, including convolutional neural networks (CNN), support vector machines, Nave Bayesian classification, and weighted Nave Bayesian classification. Prediction of Heart Disease Using Machine Learning Techniques is the topic of Chapter 3. This chapter describes the numerous heart disease prediction algorithms, including Support Vector Machines (SVM), Logistic Regression, KNN, Random Forest Classifier, and Deep Neural Networks. Prediction of IPL Data Using Machine Learning Techniques is the topic of Chapter 4. The following algorithms are covered in this chapter: decision trees, naive bayes, K-Nearest Neighbour Random Forest, data mining techniques, fuzzy clustering logic, support vector machines, reinforcement learning algorithms, data analytics approaches and Bayesian prediction techniques. Chapter Five: Software Error Prediction by means of machine learning- The AR model and the Known Power Model (POWM), as well as artificial neural networks (ANNs), particle swarm optimisation (PSO), decision trees (DT), Nave Bayes (NB), and linear classifiers, are among the approaches (K-nearest neighbours, Nave Bayes, C-4.5, and decision trees) Prediction of Rainfall Using Machine Learning Techniques, Chapter 6: The following are discussed: LASSO (Least Absolute Shrinkage and Selection Operator) Regression, ANN (Artificial Neural Network), Support Vector Machine, Multi-Layer Perception, Decision Tree, Adaptive Neuro-Fuzzy Inference System, Wavelet Neural Network, Ensemble Prediction Systems, ARIMA model, PCA and KMeans algorithms, Recurrent Neural Network (RNN), statistical KNN classifier, and neural SOM Weather Prediction Using Machine Learning Techniques that includes Bayesian Networks, Linear Regression, Logistic Regression, KNN Decision Tree, Random Forest, K-Means, and Apriori's Algorithm, as well as Linear Regression, Polynomial Regression, Random Forest Regression, Artificial Neural Networks, and Recurrent Neural Networks.
2
Chander, Bhanu. "Clustering and Bayesian Networks." In Handbook of Research on Big Data Clustering and Machine Learning. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-7998-0106-1.ch004.
Full textAbstract:
The goal of this chapter is to present an outline of clustering and Bayesian schemes used in data mining, machine learning communities. Standardized data into sensible groups is the preeminent mode of understanding as well as learning. A cluster constitutes a set regarding entities that are alike and entities from different clusters are not alike. Representing data by fewer clusters inevitably loses certain fine important information but achieves better simplification. There is no training stage in clustering; mostly, it's used when the classes are not well-known. Bayesian network is one of the best classification methods and is frequently used. Generally, Bayesian network is a form of graphical probabilistic representation model that consists of a set of interconnected nodes, where each node represents a variable, and inter-link connection represents a causal relationship of those variables. Belief networks are graph symbolized models that successfully model familiarity via transmitting probabilistic information to a variety of assumptions.
3
A, Arivarasi, Gayathri S, and Sathya Sree J. "SUPERVISED LEARNING MODELS FOR THE PREDICTION OF MATERIAL PROPERTIES." In Futuristic Trends in Artificial Intelligence Volume 2 Book 16. Iterative International Publishers, Selfypage Developers Pvt Ltd, 2023. http://dx.doi.org/10.58532/v2bs16ch1.
Full textAbstract:
Machine learning (ML) techniques play a major role in engineering world. In this sequence the manufacturing industries also utilize the ML techniques for the various applications. Among them material properties prediction or forecasting is a noticeable process of manufactures using ML techniques. The ML techniques are broadly categorized into three types such as supervised; semi supervised and unsupervised learning techniques. The learning approach can be preferred based on the problem to solve using ML technique. In this chapter, the supervised learning for the prediction of material properties is presented. Initially the properties of materials and the necessity of ML technique for the prediction of material properties is described. Then four different supervised learning such as Random Forest (RF), Naive Bayesian (NB), Support Vector Machine (SVM), and Artificial Neural Network (ANN) are described for the prediction of material properties. Finally, the performance of these four techniques is evaluated based on accuracy. The performance analysis shows that the ANN with accuracy of 98% provides better than other techniques
4
Thangavel M., Abiramie Shree T. G. R., Priyadharshini P., and Saranya T. "Review on Machine and Deep Learning Applications for Cyber Security." In Handbook of Research on Machine and Deep Learning Applications for Cyber Security. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-5225-9611-0.ch003.
Full textAbstract:
In today's world, everyone is generating a large amount of data on their own. With this amount of data generation, there is a change of security compromise of our data. This leads us to extend the security needs beyond the traditional approach which emerges the field of cyber security. Cyber security's core functionality is to protect all types of information, which includes hardware and software from cyber threats. The number of threats and attacks is increasing each year with a high difference between them. Machine learning and deep learning applications can be done to this attack, reducing the complexity to solve the problem and helping us to recover very easily. The algorithms used by both approaches are support vector machine (SVM), Bayesian algorithm, deep belief network (DBN), and deep random neural network (Deep RNN). These techniques provide better results than that of the traditional approach. The companies which use this approach in the real time scenarios are also covered in this chapter.
Conference papers on the topic "Supervised Machine Learning; Bayesian Belief Network"
1
Kharya, Shweta, Sunita Soni, and Tripti Swarnkar. "Weighted Bayesian Association Rule Mining Algorithm to Construct Bayesian Belief Network." In 2019 International Conference on Applied Machine Learning (ICAML). IEEE, 2019. http://dx.doi.org/10.1109/icaml48257.2019.00013.
Full text
2
Ravichandran, Naresh Balaji, Anders Lansner, and Pawel Herman. "Semi-supervised learning with Bayesian Confidence Propagation Neural Network." In ESANN 2021 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Ciaco - i6doc.com, 2021. http://dx.doi.org/10.14428/esann/2021.es2021-156.
Full text
3
Shekhawat, Dushyant Singh, Vishal Devgun, Bhartendu Bhatt, et al. "Well Intervention Opportunity Management Using Artificial Intelligence and Machine Learning." In ADIPEC. SPE, 2022. http://dx.doi.org/10.2118/211824-ms.
Full textAbstract:
Abstract Operators face many challenges when selecting well-intervention candidates and evaluating a field’s potential because the process is highly time consuming, labor intensive, and susceptible to cognitive biases. An operator can lose up to USD 10 million/year because of ineffective well-intervention strategies in a single field. The objective of this study is to reduce such losses and standardize the well-intervention process by intelligently using the domain knowledge with artificial-intelligence (AI) and machine-learning (ML) techniques. The workflow developed in this study can automatically and autonomously analyze the surface-subsurface data to expeditiously recommend the top intervention candidates. The workflow leverages proven petroleum-engineering methods and customizable business logic to identify underperforming wells and then recommend workover techniques, post-workover production, success probability, and profitability. It uses production, petrophysics, reservoir, and economics data to run a series of AI/ML techniques. The data-analytics engine runs k-nearest neighbors to predict post-workover rates, followed by a decision tree to identify the remedies. Artificial neural network, random forest, and Monte-Carlo simulation are adapted to identify new perforation opportunities in existing wells. Analytic hierarchy process ranks the top intervention candidates based on post-workover rate, permeability, remaining reserves, and reservoir-production trends. Finally, Bayesian belief network calculates the probability of success. With this implementation, the manual benchmarking process of opportunity identification, which usually takes weeks to months, can now be completed within minutes. Once the opportunity is identified and reviewed, it gets registered in the opportunity tracker list for the final evaluation by the asset team. The results are displayed on web-based applications with customizable dashboards and can be integrated with any existing online/offline systems. Because the whole process is now automated and takes very little execution time, petroleum engineers can review the field’s performance on a daily basis. With more than 80% predictive accuracy and 90% time saving compared to the manual process, this workflow presents a step-change in the operator’s well-intervention management capacity. In this paper, the authors discuss the adaptations to the industry-standard AI/ML algorithms and the best practices to provide a faster, more accurate, and efficient well-intervention advisory system.
4
Zhou, Taotao, Enrique López Droguett, and Mohammad Modarres. "A Hybrid Probabilistic Physics of Failure Pattern Recognition Based Approach for Assessment of Multi-Unit Causal Dependencies." In 2016 24th International Conference on Nuclear Engineering. American Society of Mechanical Engineers, 2016. http://dx.doi.org/10.1115/icone24-61017.
Full textAbstract:
The recent dependencies studies have mainly been done in context of single unit, which means the failures involving components in different units are not explicitly treated. The major scopes are also limited to the simultaneous failures as the direct results of shared causes, namely the Common Cause Failures (CCFs). The causal relations among components or units are rarely addressed. Thus it’s the prime topic of this investigation that the dependencies among multiple units co-located at a site which is called multi-unit dependencies. This paper seeks to propose a hybrid approach by combining physics-based models and supervised learning techniques. The essential idea is to account for the multi-unit dependencies by explicitly modeling the interactions of the underlying physical failure mechanisms. Ultimately a hybrid Dynamic Bayesian Belief Network is developed to model the possible dependencies, and supervised learning techniques are adopted to quantify the likelihood of failures due to dependency effects. Furthermore, an experiment has been designed and presented involving redundant pumping system, the performance of which are monitored by an advanced sensing system. The experiment is now operating and the gathered multi-sensor data will be used to illustrate the proposed approach as the next stage of this research. These sensor data should be of good quality to allow revealing the underlying failure behavior and dependent failures. This study provides an understanding of the inherent risk significance of dependencies among multiple units, and can also work as the basis for the reliability of multi-unit systems where causal dependencies play a relevant role.