Supervised Learning Algorithms Research Articles

COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS FOR SENTIMENT ANALYSIS OF TEXTS IN AZERBAIJANI AND ENGLISH

The prediction of sentiment of the text within different business spheres has been one of the challenging problems for a variety of linguistics. In this paper, the sentiment analysis of the texts is carried out using different machine learning (ML) techniques. Various feature extraction techniques and supervised learning algorithms are employed on the movie review dataset sourced from the Internet Movie Database and translated into Azerbaijani. Specifically, the techniques utilized encompass Support Vector Machine, Logistic Regression, Decision Trees, Random Forest, AdaBoost, XGBoost, and Naïve Bayes. The proposed models depict the importance of language corpus that Azerbaijani language lacks by comparing the results obtained from both Azerbaijani and English versions of the dataset.

Application and Comparison of Machine Learning Methods for Mud Shale Petrographic Identification

Machine learning is the main technical means for lithofacies logging identification. As the main target of shale oil spatial distribution prediction, mud shale petrography is subjected to the constraints of stratigraphic inhomogeneity and logging information redundancy. Therefore, choosing the most applicable machine learning method for different geological characteristics and data situations is one of the key aspects of high-precision lithofacies identification. However, only a few studies have been conducted on the applicability of machine learning methods for mud shale petrography. This paper aims to identify lithofacies using commonly used machine learning methods. The study employs five supervised learning algorithms, namely Random Forest Algorithm (RF), BP Neural Network Algorithm (BPANN), Gradient Boosting Decision Tree Method (GBDT), Nearest Neighbor Method (KNN), and Vector Machine Method (SVM), as well as four unsupervised learning algorithms, namely K-means, DBSCAN, SOM, and MRGC. The results are evaluated using the confusion matrix, which provides the accuracy of each algorithm. The GBDT algorithm has better accuracy in supervised learning, while the K-means and DBSCAN algorithms have higher accuracy in unsupervised learning. Based on the comparison of different algorithms, it can be concluded that shale lithofacies identification poses challenges due to limited sample data and high overlapping degree of type distribution areas. Therefore, selecting the appropriate algorithm is crucial. Although supervised machine learning algorithms are generally accurate, they are limited by the data volume of lithofacies samples. Future research should focus on how to make the most of limited samples for supervised learning and combine unsupervised learning algorithms to explore lithofacies types of non-coring wells.

Achieving the third 95 in sub-Saharan Africa: application of machine learning approaches to predict viral failure.

Viral failure in people with HIV (PWH) may be influenced by multiple sociobehavioral, clinical, and context-specific factors, and supervised learning approaches may identify novel predictors. We compared the performance of two supervised learning algorithms to predict viral failure in four African countries. Cohort study. The African Cohort Study is an ongoing, longitudinal cohort enrolling PWH at 12 sites in Uganda, Kenya, Tanzania, and Nigeria. Participants underwent physical examination, medical history-taking, medical record extraction, sociobehavioral interviews, and laboratory testing. In cross-sectional analyses of enrollment data, viral failure was defined as a viral load at least 1000 copies/ml among participants on antiretroviral therapy (ART) for at least 6 months. We compared the performance of lasso-type regularized regression and random forests by calculating area under the curve (AUC) and used each to identify factors associated with viral failure; 94 explanatory variables were considered. Between January 2013 and December 2020, 2941 PWH were enrolled, 1602 had been on antiretroviral therapy (ART) for at least 6 months, and 1571 participants with complete case data were included. At enrollment, 190 (12.0%) had viral failure. The lasso regression model was slightly superior to the random forest in its ability to identify PWH with viral failure (AUC: 0.82 vs. 0.75). Both models identified CD4 + count, ART regimen, age, self-reported ART adherence and duration on ART as important factors associated with viral failure. These findings corroborate existing literature primarily based on hypothesis-testing statistical approaches and help to generate questions for future investigations that may impact viral failure.

Data‐Driven Approach Using Supervised Learning for Predicting Endpoint Temperature of Molten Steel in the Electric Arc Furnace

This study presents the development of a decision support system that focuses on predicting the endpoint temperature of molten steel to manage the process of an electric arc furnace more systematically. The decision support system leverages a data‐driven approach that consists of the following modules: 1) a data preprocessing module that specifically includes raw data filtering, feature engineering, and outlier detection; 2) a feature selection module based on domain knowledge; 3) regression modeling module that employs a supervised learning algorithm to forecast an endpoint temperature; and 4) sensitivity analysis module to identify the correlation between input and output metric. The applicability of the system is demonstrated through a validation study using real‐world operational data from Hyundai Steel located in Pohang, South Korea. The validation results show that the endpoint temperatures predicted by the system are evenly scattered to a perfect‐fit line within 5% errors of the actual temperatures. The results also indicate that CaO, power, and melting score have the most significant impact on the endpoint temperature, in which temperature decreases as CaO increases and increases as the power and melting score increase.

Learned Gaussian quadrature for enriched solid finite elements

We propose a novel Gaussian quadrature, referred to as the learned Gaussian quadrature, that is obtained by employing a supervised learning algorithm to find improved weights for the matrix integrations of 2D and 3D enriched solid finite elements. As the algorithm employs the intuitive relationship between a target matrix and improved Gaussian weights, it successfully finds the learned Gaussian quadrature only using a simple network. The learned Gaussian quadrature accurately calculates the matrix with fewer integration points than the standard Gaussian quadrature, thereby increasing the computational efficiency of the enriched finite elements. Using various numerical examples, the theoretical convergence behavior of the enriched solid finite elements with the learned Gaussian quadrature is first investigated, and then, the practical performances are measured.

Efficient Capture of Solar Energy in Romania: Approach in Territorial Profile Using Predictive Statistical Techniques

Abstract Nowadays, the renewable energy sector is an area of interest for every state. Global regulations and policies encourage the development of these technologies, given the current political context, but also environmental issues. Romania, due to its geographical position and climate, is considered a country with high potential regarding the implementation of alternative sources of renewable energy. This research presents the importance of solar energy and provides a statistical analysis on the sectors influencing the implementation of green energy. At the same time, those counties that are eligible are identified and different scenarios are created for the ineligible counties that lead to their eligibility. The research develops 3 main objectives. To begin with, it is desired to be created an overview of the indicators included in the analysis, in order to develop a detailed statistical analysis of the situation of each county of Romania. Following this extracted information, the second objective is outlined, which is to create an indicator that groups counties into counties eligible for solar energy and counties ineligible for solar energy using the K-Means Cluster-unsupervised learning algorithm. Finally, using the supervised learning algorithm - Logistic Regression, predictions will be made with the help of which those sectors of activity that can be improved in order to implement green energy will be identified.

Spatio-Temporal Mapping and Monitoring of Mangrove Forests Changes from 1991 to 2021 in Panay Island, Philippines using Machine Learning

Mangrove forests hold a crucial role in our social, economic, and ecological activities. Despite this immense importance, they are constantly threatened by reclamation, deforestation, and climate change. In order to forward conservation and restoration efforts, accurate and cost-effective mangrove mapping and monitoring must be done. This paper explores the use of a supervised learning algorithm called Random Forest (RF) in mapping mangrove extent in Panay Island, Philippines from 1991-to 2021. Using land cover data from Landsat, maps of the mangrove extent from 1991to 2021 were developed. Results revealed that there has been an 8% decline from 1991 to 1996; 24% decrease in 1996 to 2001; 6% increase in 2001 to 2006; 21% decline from 2006 to 2011; 17% increase in 2011-2016; and 16% increase in 2016 to 2021. Over the past three (3) decades, the Philippines has lost 20% of its mangrove forests. From 31713 ha in 1991 to only 25313 ha in 2021. Through a confusion matrix, the model was evaluated and it showed a specificity, sensitivity, and AUC(Area Under the ROC Curve) above 70%. This suggests that, machine learning, when integrated with remote sensing, can provide an effective yet low-cost approach to mapping mangrove extent at a large-scale.

DSQNet: A Deformable Model-Based Supervised Learning Algorithm for Grasping Unknown Occluded Objects

DSQNet: A Deformable Model-Based Supervised Learning Algorithm for Grasping Unknown Occluded Objects

A low-cost real-time IoT human activity recognition system based on wearable sensor and the supervised learning algorithms

Activity recognition systems can detect human physical activities to support the assessment of health conditions. Among approaches of activity recognition systems were researched and implemented, the wearable systems based on accelerometers and machine learning classifiers offer one of the most viable solutions. These systems are cheap, comfortable, easy to use, with high recognition accuracy. The major challenge in this classification problem is required directly performed in a low-performance microcontroller. In this manuscript, an optimal time frame of an activity, a feature set, and a simple machine learning model were proposed to build a low-cost and responsive recognition system in real-time. The proposed device was verified on both public data and our experiment data. An excellent recognition rate resulted in 99.2% on the recorded dataset for four critical daily activities (standing, sitting, running, and walking).

Machine learning based canine posture estimation using inertial data.

The aim of this study was to design a new canine posture estimation system specifically for working dogs. The system was composed of Inertial Measurement Units (IMUs) that are commercially available, and a supervised learning algorithm which was developed for different behaviours. Three IMUs, each containing a 3-axis accelerometer, gyroscope, and magnetometer, were attached to the dogs' chest, back, and neck. To build and test the model, data were collected during a video-recorded behaviour test where the trainee assistance dogs performed static postures (standing, sitting, lying down) and dynamic activities (walking, body shake). Advanced feature extraction techniques were employed for the first time in this field, including statistical, temporal, and spectral methods. The most important features for posture prediction were chosen using Select K Best with ANOVA F-value. The individual contributions of each IMU, sensor, and feature type were analysed using Select K Best scores and Random Forest feature importance. Results showed that the back and chest IMUs were more important than the neck IMU, and the accelerometers were more important than the gyroscopes. The addition of IMUs to the chest and back of dog harnesses is recommended to improve performance. Additionally, statistical and temporal feature domains were more important than spectral feature domains. Three novel cascade arrangements of Random Forest and Isolation Forest were fitted to the dataset. The best classifier achieved an f1-macro of 0.83 and an f1-weighted of 0.90 for the prediction of the five postures, demonstrating a better performance than previous studies. These results were attributed to the data collection methodology (number of subjects and observations, multiple IMUs, use of common working dog breeds) and novel machine learning techniques (advanced feature extraction, feature selection and modelling arrangements) employed. The dataset and code used are publicly available on Mendeley Data and GitHub, respectively.

ReachingBot: An automated and scalable benchtop device for highly parallel Single Pellet Reach-and-Grasp training and assessment in mice

BackgroundThe single pellet reaching and grasp (SPRG) task is a behavioural assay widely used to study motor learning, control and recovery after nervous system injury in animals. The manual training and assessment of the SPRG is labour intensive and time consuming and has led to the development of multiple devices which automate the SPRG task. New methodHere, using robotics, computer vision, and machine learning analysis of videos, we describe a device that can be left unattended, presents pellets to mice, and, using two supervised learning algorithms, classifies the outcome of each trial with an accuracy of greater than 94% without the use of graphical processing units (GPUs). Our devices can also be operated using our cross-platform Graphical User Interface (GUI). ResultsWe show that these devices train and assess mice in parallel. 21 out of 30 mice retrieved > 40% of pellets successfully following the training period. Following ischaemic stroke; some mice showed large persistent deficits whilst others showed only transient deficits. This highlights the heterogeneity in reaching outcomes following stroke. Comparison with existing method(s)Current state-of-the-art desktop methods either still require supervision, manual classification of trial outcome, or expensive locally-installed hardware such as graphical processing units (GPUs). ConclusionsReachingBots successfully automated SPRG training and assessment and revealed the heterogeneity in reaching outcomes following stroke. We conjecture that reach-and-grasp is represented in motor cortex bilaterally but with greater asymmetry in some mice than in others.

Affective state estimation based on Russell’s model and physiological measurements

Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel’s model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.

Rapid quantification of the adulteration of pomegranate juices by Raman spectroscopy and chemometrics

The juice drink industry has repeatedly been exposed to adulteration. Unscrupulous producers, for example, use cheap juice for substitution in the pursuit of more significant economic benefits, which presents a tremendous challenge for the control of the quality of drinks. The objective of this study was to apply Raman spectroscopy combined with chemometrics to rapidly quantify the adulteration concentration of apple juice or grape juice in pomegranate juice. Two supervised learning algorithms: partial least squares regression (PLSR) and support vector machine regression (SVR) were used to analyze the Raman spectra of 114 samples. The coefficient of determination (R2), root mean square error (RMSE), and residual prediction deviation (RPD) of the prediction set when using PLSR and SVR to predict the adulterated concentration of apple juice in pomegranate juice were 0.9357 and 0.9465, 6.446% and 5.974%, 3.945 and 4.322, respectively. The R2, RMSE, and RPD of the prediction set when using PLSR and SVR to predict the adulteration concentration of grape juice in pomegranate juice were 0.9501 and 0.9502, 6.334% and 5.571%, and 4.475 and 4.481, respectively. It was concluded that Raman spectroscopy combined with chemometrics has excellent potential for application as a rapid quantitative method to detect adulterated concentrations of pomegranate juice.

Using Machine Learning to Protect Social Media Accounts from Spam Emails

Spam refers to all forms of bulk, unsolicited, unwelcome digital communication. Spam can be transmitted by text messages, phone calls, social media, or email, which is how it is frequently done. The rise of social media websites like Facebook, Twitter, YouTube, etc. has given spammers increased access to people. Most spam filtering solutions employ text-based algorithms. The fundamental difficulty is classification because it is a significant one. In this study, features are extracted from emails using classifications of rules. To automatically categorize emails, numerous systems have been created, a few of them include systemic decision-making. The use of Bayesian classifiers, networked neurons, support vector machines, and sample-based approaches. A sizable and time-consuming labelled dataset is required for the supervised model training phase. SVM and Naive Bayes, two supervised learning algorithms, outperform other models in terms of spam identification. It provides comprehensive explanations of these methods in addition to several likely areas for future research in spam filtering and detection. Because most spammers employ obfuscation techniques, the rules set need ongoing updating and improvement. Refinement is occasionally necessary, and in most situations, it is automated, so end users have less bother

Enhanced Adaptable and Distributed Access Control Decision Making Model Based on Machine Learning for Policy Conflict Resolution in BYOD Environment

Organisations are adopting new IT strategies such as “Bring Your Own Device” (BYOD) and remote working. These trends are highly beneficial both for enterprise owners and employees in terms of increased productivity and reduced costs. However, security issues such as unauthorised access as well as privacy concerns pose significant obstacles. These can be overcome by adopting access control techniques and a dynamic security and privacy policy that governs these issues where they arise. Policy decision points in traditional access control systems, such as role-based access control (RBAC), attribute-based access control (ABAC), or relationship-based access control (ReBAC), may be limited because the status of access control can vary in response to minor changes in user and resource properties. As a result, system administrators rely on a solution for constructing complex rules with many conditions and permissions for decision control. This results in access control issues, including policy conflicts, decision-making bottlenecks, delayed access response times and mediocre performance. This paper proposes a policy decision-making and access control-based supervised learning algorithm. The algorithm enhances policy decision points (PDPs). This is achieved by transforming the PDP’s problem into a binary classification for security access control that either grants or denies access requests. Also, a vector decision classifier based on the supervised machine learning algorithm is developed to generate an accurate, effective, distributed and dynamic policy decision point (PDP). Performance was evaluated using the Kaggle-Amazon access control policy dataset, which compared the effectiveness of the proposed mechanism to previous research benchmarks in terms of performance, time and flexibility. The proposed solution obtains a high level of privacy for access control policies because the PDP does not communicate directly with the policy administration point (PAP). In conclusion, PDP-based ML generates accurate decisions and can simultaneously fulfill multiple massive policies and huge access requests with 95% Accuracy in a short response time of around 0.15 s without policy conflicts. Access control security is improved by making it dynamic, adaptable, flexible and distributed.

Optimizing Neural Networks for Imbalanced Data

Imbalanced datasets pose pervasive challenges in numerous machine learning (ML) applications, notably in areas such as fraud detection, where fraudulent cases are vastly outnumbered by legitimate transactions. Conventional ML methods often grapple with such imbalances, resulting in models with suboptimal performance concerning the minority class. This study undertakes a thorough examination of strategies for optimizing supervised learning algorithms when confronted with imbalanced datasets, emphasizing resampling techniques. Initially, we explore multiple methodologies, encompassing Gaussian Naive Bayes, linear and quadratic discriminant analysis, K-nearest neighbors (K-NN), support vector machines (SVMs), decision trees, and multi-layer perceptron (MLP). We apply these on a four-class spiral dataset, a notoriously demanding non-linear classification problem, to gauge their effectiveness. Subsequently, we leverage the garnered insights for a real-world credit card fraud detection task on a public dataset, where we achieve a compelling accuracy of 99.937%. In this context, we compare and contrast the performances of undersampling, oversampling, and the synthetic minority oversampling technique (SMOTE). Our findings highlight the potency of resampling strategies in augmenting model performance on the minority class; in particular, oversampling techniques achieve the best performance, resulting in an accuracy of 99.928% with a significantly low number of false negatives (21/227,451).

An optimization-based supervised learning algorithm for PXRD phase fraction estimation

In powder diffraction data analysis, phase identification is the process of determining the crystalline phases in a sample using its characteristic Bragg peaks. For multiphasic spectra, we must also determine the relative weight fraction of each phase in the sample. Machine learning algorithms (e.g., Artificial Neural Networks) have been applied to perform such difficult tasks in powder diffraction analysis, but typically require a significant number of training samples for acceptable performance. We have developed an approach that performs well even with a small number of training samples. We apply a fixed-point iteration algorithm on the labelled training samples to estimate monophasic spectra. Then, given an unknown sample spectrum, we again use a fixed-point iteration algorithm to determine the weighted combination of monophase spectra that best approximates the unknown sample spectrum. These weights are the desired phase fractions for the sample. Our approach gave the best accuracy and lowest mean absolute error when compared with several machine learning algorithms, including a single hidden-layer neural network.

Machine Learning Implementation for Profit Estimation

The company must have a unique strategy to help grow its business. One of the ways to strengthen the company's business is by estimating the company's profit. This is because with an estimated profit, the company can manage the transactions made. Some companies still use a manual profit determination process that requires several steps. Processes that are carried out manually result in a long time, which can cause delays in completing tasks and results that are less accurate than desired. Multiple linear regression is an algorithm used to determine the relationship between the dependent variable and at least two independent variables. This algorithm is a type of supervised learning algorithm that develops estimation models based on input data. The use of this algorithm is included in part of machine learning. Implementation of machine learning to calculate company profit estimates using the Python programming language. From the estimation results using multiple linear regression and Python programming, the result is that multiple linear regression can be utilized or used to predict company profits. 98% of Profit is influenced by independent factors, namely R&D Spend and Marketing Spend, while the remaining 2% is influenced by variables that are not included in this calculation.

Detection and classification of pavement damages using wavelet scattering transform, fractal dimension by box-counting method and machine learning algorithms

Pavement condition assessment is essential for roadway maintenance and rehabilitation processes. Image-based inspection methods provide information regarding the surface of the pavement and allow quantitative analyses of pavement conditions. A methodology for the detection of damages in the pavement, by applying pattern recognition and image analysis and machine learning algorithms, is presented in the paper. This methodology consists of image acquisition, image processing using the wavelet scattering transform (WST), feature extraction employing the fractal dimension by box-counting method, and finally classification. The methodology was applied for the detection of three common types of damages: potholes, longitudinal and alligator cracks. Two different supervised learning algorithms, Artificial Neural Networks (ANN) and Support Vector Machine (SVM), were used for classification and results are compared training Convolutional Neural Networks (CNN). The multilayer ANN an overall accuracy of 98.36% and an F-score of 98.33%, while the SVM an accuracy of 97.22% and an F-score of 97.22%.

Supervised recommendations of gas metal arc welding parameters

In gas metal arc welding, a weld quality and performance depends on many parameters. Selecting the right ones can be complex, even for an expert. One generally proceeds through trial and error to find a good set of parameters. Therefore, the current experts’ method is not optimized and can require a lot of time and materials. We propose using supervised learning techniques to help experts in their decision-making. To that extent, a two-part recommendation system is proposed. The first step is dedicated to identify, through classification, the number of weld passes. The second one suggests the seven remaining parameter values for each pass: layer, amperage, voltage, wire feed rate, frequency offset, trimming and welding speed. After extracting data from historical Welding Procedure Specification forms, we tested 11 different supervised learning algorithms. The recommendation system is able to provide good results for all the different settings mentioned above even if the data is noisy due to the heuristic nature of the experts’ process. The best classification model is CatBoost with 82.22% average F1 Weighted-Score and the best regression models are Extra Trees or a boosting algorithm with a reduced mean absolute percentage error compared to our baseline.