scholarly journals Aprendizagem de Máquina Aplicada a Consumidores Comerciais Buscando Identificar Padrões Atípicos de Consumo de Energia Elétrica Utilizando o Software R

2021 ◽  
Author(s):  
Lucas Evangelista de Souza ◽  
Raimundo Ghizoni Teive
Keyword(s):  
Real Data ◽  
Machine Learning Techniques ◽  
Svm Classifier ◽  
Electricity Distribution ◽  
Functional Information ◽  
Interconnected System ◽  
Learning Techniques ◽  
Precision And Accuracy ◽  
Input Variables ◽  
Typical Consumer

The electricity distribution network is responsible for supplying energy to consumers in the National Interconnected System, serving 99% of consumers in Brazil. There are two types of losses in this network: technical losses and non-technical losses or commercial losses. In the case of non-technical losses, the focus of this work, the existence of these results in a higher tariff for all consumers, so that the concessionaire can compensate for such reduction in revenue. Non-technical losses are usually associated with fraud (meter tampering or deviations). The main objective of this work is the application of machine learning techniques, using software R, to identify possible fraudulent behaviors of commercial consumers in the state of Santa Catarina. Considering data from typical consumer load curves and functional information from the company. Preliminary results, using real data from consumers, indicate that the SVM classifier used performed well in the cases studied, achieving precision and accuracy greater than 90%. The input variables selected for the classifier, based mainly on data and information from typical load curves, are the differential of this work, as well as the main reason for the success in the initial tests.

Improved argumentative paragraphs detection in academic theses supported with unit segmentation

2021 ◽  
pp. 1-11
Author(s):  
Jesús Miguel García-Gorrostieta ◽  
Aurelio López-López ◽  
Samuel González-López ◽  
Adrián Pastor López-Monroy
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Automatic Detection ◽  
Machine Learning Techniques ◽  
Svm Classifier ◽  
Complex Task ◽  
Decision Tree Classifier ◽  
Learning Techniques ◽  
Tree Classifier ◽  
Academic Author

Academic theses writing is a complex task that requires the author to be skilled in argumentation. The goal of the academic author is to communicate clear ideas and to convince the reader of the presented claims. However, few students are good arguers, and this is a skill that takes time to master. In this paper, we present an exploration of lexical features used to model automatic detection of argumentative paragraphs using machine learning techniques. We present a novel proposal, which combines the information in the complete paragraph with the detection of argumentative segments in order to achieve improved results for the detection of argumentative paragraphs. We propose two approaches; a more descriptive one, which uses the decision tree classifier with indicators and lexical features; and another more efficient, which uses an SVM classifier with lexical features and a Document Occurrence Representation (DOR). Both approaches consider the detection of argumentative segments to ensure that a paragraph detected as argumentative has indeed segments with argumentation. We achieved encouraging results for both approaches.

scholarly journals Intelligent Machine Learning: Tailor-Making Macromolecules

Polymers ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 579 ◽  
Author(s):  
Yousef Mohammadi ◽  
Mohammad Saeb ◽  
Alexander Penlidis ◽  
Esmaiel Jabbari ◽  
Florian J. Stadler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Kinetic Monte Carlo ◽  
Engineering Problem ◽  
Optimization Techniques ◽  
Machine Learning Techniques ◽  
Coordination Polymerization ◽  
Intelligent Modeling ◽  
Learning Techniques ◽  
Input Variables ◽  
Architectural Characteristics

Nowadays, polymer reaction engineers seek robust and effective tools to synthesize complex macromolecules with well-defined and desirable microstructural and architectural characteristics. Over the past few decades, several promising approaches, such as controlled living (co)polymerization systems and chain-shuttling reactions have been proposed and widely applied to synthesize rather complex macromolecules with controlled monomer sequences. Despite the unique potential of the newly developed techniques, tailor-making the microstructure of macromolecules by suggesting the most appropriate polymerization recipe still remains a very challenging task. In the current work, two versatile and powerful tools capable of effectively addressing the aforementioned questions have been proposed and successfully put into practice. The two tools are established through the amalgamation of the Kinetic Monte Carlo simulation approach and machine learning techniques. The former, an intelligent modeling tool, is able to model and visualize the intricate inter-relationships of polymerization recipes/conditions (as input variables) and microstructural features of the produced macromolecules (as responses). The latter is capable of precisely predicting optimal copolymerization conditions to simultaneously satisfy all predefined microstructural features. The effectiveness of the proposed intelligent modeling and optimization techniques for solving this extremely important ‘inverse’ engineering problem was successfully examined by investigating the possibility of tailor-making the microstructure of Olefin Block Copolymers via chain-shuttling coordination polymerization.

Analysis of Intrusion Detection and Classification using Machine Learning Approaches

2017 ◽  
Vol 3 (10) ◽  
Author(s):  
Anjum Khan ◽  
Anjana Nigam
Keyword(s):  
Machine Learning ◽  
Network Security ◽  
Intrusion Detection ◽  
Detection System ◽  
Real Data ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
High Detection Rate ◽  
Learning Techniques ◽  
Result Analysis

 As the network primarily based applications are growing quickly, the network security mechanisms need a lot of attention to enhance speed and preciseness. The ever evolving new intrusion types cause a significant threat to network security. Though varied network security tools are developed, however the quick growth of intrusive activities continues to be a significant issue. Intrusion detection systems (IDSs) are wont to detect intrusive activities on the network. Analysis showed that application of machine learning techniques in intrusion detection might reach high detection rate. Machine learning and classification algorithms facilitate to design “Intrusion Detection Models” which might classify the network traffic into intrusive or traditional traffic. This paper discusses some usually used machine learning techniques in Intrusion Detection System and conjointly reviews a number of the prevailing machine learning IDS proposed by researchers at different times. in this paper an experimental analysis is performed to demonstrate the performance analysis of some existing techniques in order that they will be used further in developing Hybrid Classifier for real data packets classification. The given result analysis shows that KNN, RF and SVM performs best for NSL-KDD dataset.

Blog Backlinks Malicious Domain Name Detection via Supervised Learning

2021 ◽  
Vol 17 (3) ◽  
pp. 1-17
Author(s):  
Abdulrahman A. Alshdadi ◽  
Ahmed S. Alghamdi ◽  
Ali Daud ◽  
Saqib Hussain
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Svm Classifier ◽  
Financial Loss ◽  
Domain Name ◽  
Hybrid Features ◽  
Learning Techniques ◽  
Web Spam ◽  
Social Media Platforms

Web spam is the unwanted request on websites, low-quality backlinks, emails, and reviews which is generated by an automated program. It is the big threat for website owners; because of it, they can lose their top keywords ranking from search engines, which will result in huge financial loss to the business. Over the years, researchers have tried to identify malicious domains based on specific features. However, lighthouse plugin, Ahrefs tool, and social media platforms features are ignored. In this paper, the authors are focused on detection of the spam domain name from a mixture of legit and spam domain name dataset. The dataset is taken from Google webmaster tools. Machine learning models are applied on individual, distributed, and hybrid features, which significantly improved the performance of existing malicious domain machine learning techniques. Better accuracy is achieved for support vector machine (SVM) classifier, as compared to Naïve Bayes, C4.5, AdaBoost, LogitBoost.

scholarly journals A three-stage quality diagnosis platform for laser-based manufacturing processes

2020 ◽  
Vol 110 (11-12) ◽  
pp. 2991-3003
Author(s):  
Panagiotis Stavropoulos ◽  
Alexios Papacharalampopoulos ◽  
John Stavridis ◽  
Kyriakos Sampatakakis
Keyword(s):  
Technical Assistance ◽  
Image Data ◽  
Real Data ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Web Based ◽  
Learning Techniques ◽  
Weld Defect ◽  
Readiness Level ◽  
Quality Diagnosis

Abstract Diagnosis systems for laser processing are being integrated into industry. However, their readiness level is still questionable under the prism of the Industry’s 4.0 design principles for interoperability and intuitive technical assistance. This paper presents a novel multifunctional, web-based, real-time quality diagnosis platform, in the context of a laser welding application, fused with decision support, data visualization, storing, and post-processing functionalities. The platform’s core considers a quality assessment module, based upon a three-stage method which utilizes feature extraction and machine learning techniques for weld defect detection and quality prediction. A multisensorial configuration streams image data from the weld pool to the module in which a statistical and geometrical method is applied for selecting the input features for the classification model. A Hidden Markov Model is then used to fuse this information with earlier results for a decision to be made on the basis of maximum likelihood. The outcome is fed through web services in a tailored User Interface. The platform’s operation has been validated with real data.

scholarly journals PV Module Fault Detection Using Combined Artificial Neural Network and Sugeno Fuzzy Logic

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2150
Author(s):  
Romênia G. Vieira ◽  
Mahmoud Dhimish ◽  
Fábio M. U. de Araújo ◽  
Maria I. S. Guerra
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Fault Detection ◽  
Machine Learning Techniques ◽  
Photovoltaic Systems ◽  
The Neural Network ◽  
Learning Techniques ◽  
Network Output ◽  
Input Variables ◽  
Power Point

This work introduces a new fault detection method for photovoltaic systems. The method identifies short-circuited modules and disconnected strings on photovoltaic systems combining two machine learning techniques. The first algorithm is a multilayer feedforward neural network, which uses irradiance, ambient temperature, and power at the maximum power point as input variables. The neural network output enters a Sugeno type fuzzy logic system that precisely determines how many faulty modules are occurring on the power plant. The proposed method was trained using a simulated dataset and validated using experimental data. The obtained results showed 99.28% accuracy on detecting short-circuited photovoltaic modules and 99.43% on detecting disconnected strings.

A Micro-Cluster-Based Data Stream Clustering Method for P2P Traffic Classification

2012 ◽  
Vol 263-266 ◽  
pp. 1121-1126
Author(s):  
Guang Hui Yan ◽  
Ming Hao Ai
Keyword(s):  
Concept Drift ◽  
Real Data ◽  
Streaming Data ◽  
Machine Learning Techniques ◽  
Traffic Classification ◽  
Limited Memory ◽  
Learning Techniques ◽  
Data Stream Clustering ◽  
Effectiveness And Efficiency ◽  
P2p Applications

Many machine learning techniques were proposed to classify P2P traffic and each with reasonable successes. But in the real P2P network environment, new communities of peers often attend and old communities of peers often leave. It requires the identification methods to be capable of coping with concept drift and updating the model incrementally. In this paper, we presented a concept-adapting algorithm MCStream which was based on streaming data mining techniques to identify P2P applications in Internet traffic. The MCStream used two micro-cluster structures, potential micro-cluster structures and outlier micro-cluster structures, to classify the P2P traffic and discovered the concept drift with limited memory. Our performance studied over a number of real data which was captured at a main gateway router demonstrates the effectiveness and efficiency of our method.

scholarly journals Prediction of defects using machine learning techniques in order to improve quality management system – A case study

2021 ◽  
Vol 343 ◽  
pp. 05010
Author(s):  
Adina Sârb ◽  
Cristina Burja Udrea ◽  
Daniela Nagy – Oniţa ◽  
Liliana Itul ◽  
Maria Popa
Keyword(s):  
Machine Learning ◽  
Quality Management ◽  
Management System ◽  
Quality Management System ◽  
Real Data ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Learning Techniques ◽  
Different Types ◽  
The Future

According to ISO 9000, a quality management system is part of a set of related or interacting elements of an organization that sets policies and objectives, as well as the processes necessary to achieve the quality objectives. Quality is the extent to which a set of intrinsic characteristics of an object meets the requirements. Based on these definitions, the factory, considered in this paper, S.C. APULUM S.A.,decided to implement a quality management system since 1998. Subsequently, the organization’s attention is focus on the continuous improvement of the implemented quality management system. The purpose of this paper is to study the percent of specified defects specific to ceramic products in the future to improve the quality management system. In this regard, machine learning techniques were applied for defects forecasting for different types of products: mugs, pressed plates and jiggered plates. The experimental evaluation was performed on real data sets that contain percentages about different types of defects collected in 2018-2019. The experimental results show that for each type of product exists an algorithm that forecasts the future defects.

scholarly journals Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques

2020 ◽  
Author(s):  
Hao Li ◽  
Liqian Cui ◽  
Liping Cao ◽  
Yizhi Zhang ◽  
Yueheng Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Bipolar Disorder ◽  
Functional Mri ◽  
Added Value ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Svm Classifier ◽  
Accurate Identification ◽  
Learning Techniques ◽  
Svm Model

Abstract Background: Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD.Methods: In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed.Results: After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5-95.3%), sensitivity of 86.4% (95%CI: 64.0-96.4%), and specificity of 88.9% (95%CI: 63.9-98.0%) in the test data (p=0.0022). Conclusions: A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Prediction of Severity of Non Proliferated Diabetic Retinopathy Using Machine Learning Techniques

2020 ◽  
Vol 17 (9) ◽  
pp. 4219-4222
Author(s):  
ManjulaSri Rayudu ◽  
Srujana Pendam ◽  
Srilaxmi Dasari
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Diversity Index ◽  
Research Work ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Svm Classifier ◽  
Linear Discriminant ◽  
Learning Techniques

All the patients of Type1 and more than 60% of Type2 Diabetes suffer from Diabetic Retinopathy (DR). Diabetic retinopathy causes damage to retina of eye and slowly leads to complete vision loss. The longer the patients are suffering from diabetes the probability of presence of DR is more. Hence diabetic retinopathy is to be identified in early stage to avoid blindness. The objective of this research work is to predict the severity of diabetic retinopathy (Non Proliferated) using machine learning techniques. Proliferated diabetic retinopathy (later stage) is characterized by neovasculature in the retinal veins and is the final stage. Non proliferated DR (earlier stage) is identified by any of the abnormalities out of microaneurysms, Hard exudates and hemorrhages. Then Machine learning techniques are employed to identify the class of DR. The following Classification and regression techniques are employed for categorizing the DR: Gini Diversity Index method, Linear discriminant analysis, Ensemble method with bagged and boosted trees, K-Nearest Neighbor, and Support Vector Machine classification methods. 89 images from DRIVE database (DiaRet DB1) are classified using the machine learning techniques cited above. It is observed the maximum accuracy is achieved as 88.8% with Linear SVM classifier.

Sign in / Sign up

Export Citation Format

Share Document