Support Vector Machine Technique Research Articles

Modelling some stand parameters using Landsat 8 OLI and Sentinel-2 satellite images by machine learning techniques: a case study in Türkiye

Remote sensing technologies have been extensively used in forest management in predicting stand parameters. The goal of this study is to use Landsat 8 and Sentinel-2 satellite images to estimate stand volume, basal area, number of trees, mean diameter, and top height. 180 temporary sample plots were taken in pure Crimean pine stands with varied structure. Reflectance, vegetation indices, and eight texture values were generated from Landsat 8 and Sentinel-2 satellite images. The stand parameters were modelled with the remotely sensed data using multiple linear regression, support vector machine, and deep learning techniques. The results showed that the support vector machine technique provided the highest level of model performance with 45° orientation for number of trees (R2 = 0.98, RMSE%=5.97) and 90° orientation for basal area (R2=0.91, RMSE%=15.22). The results indicated that the texture values presented better results than the reflectance and the vegetation indices in estimating the stand parameters.

Vision-based Pakistani sign language recognition using bag-of-words and support vector machines

In order to perform their daily activities, a person is required to communicating with others. This can be a major obstacle for the deaf population of the world, who communicate using sign languages (SL). Pakistani Sign Language (PSL) is used by more than 250,000 deaf Pakistanis. Developing a SL recognition system would greatly facilitate these people. This study aimed to collect data of static and dynamic PSL alphabets and to develop a vision-based system for their recognition using Bag-of-Words (BoW) and Support Vector Machine (SVM) techniques. A total of 5120 images for 36 static PSL alphabet signs and 353 videos with 45,224 frames for 3 dynamic PSL alphabet signs were collected from 10 native signers of PSL. The developed system used the collected data as input, resized the data to various scales and converted the RGB images into grayscale. The resized grayscale images were segmented using Thresholding technique and features were extracted using Speeded Up Robust Feature (SURF). The obtained SURF descriptors were clustered using K-means clustering. A BoW was obtained by computing the Euclidean distance between the SURF descriptors and the clustered data. The codebooks were divided into training and testing using fivefold cross validation. The highest overall classification accuracy for static PSL signs was 97.80% at 750 × 750 image dimensions and 500 Bags. For dynamic PSL signs a 96.53% accuracy was obtained at 480 × 270 video resolution and 200 Bags.

Two-phase flow pattern identification in CAES systems with dimensional analysis coupled with support vector machine

Two-phase bubbly flow can lead to challenges during the charging period for hydraulically-compensated Compressed Air Energy Storage systems. In this study, upward two-phase flow systems have been investigated in large diameter vertical pipes to better understand when the transitions to problematic flow regimes occur. A comprehensive dimensional analysis was conducted, considering vertical pipe geometry and fluid thermophysical properties. Nine dimensionless parameters and three two-phase flow maps were created. The plot of liquid Reynolds number, ReL, over the Two-phase Reynolds number, Retp,made classification between the Bubbly, Slug, and Churn flow difficult for large diameter pipes. The plot of the two-phase Capillary number,Catp, over the liquid Reynolds number, ReL, showed large overlap of the data sets extracted from the literature. This may have been due to the weakness of the capillary number in defining the larger pipe flow behaviours. The last flow map based on the Slippage number, Sltp, versus the two-phase Froude number, Frtp, showed an exponential decay relationship between the Froude and Slippage parameter. When this was converted to the semi-log scale it provided a valuable classification map of two-phase flow. Finally, a Support Vector Machine (SVM) technique applied to the 2D plot of (Sltp- Frtp), gave a useful transition boundary to separate regimes in air-water upward flows in large diameter pipes.

Development of Preventing Myofascial Pain Syndrome Automation with Ultrasonic-based and Machine Learning

Physical readiness is one factor that promotes student learning achievement. However, sitting for long periods can lead to myofascial pain syndrome, affecting undergraduate students’ learning outcomes who took lecturebased and computer-based sessions online for long periods. This study aims to develop a set of economic reminders using the Internet of Things and prediction modeling by the Machine Learning technique. The developed preventing myofascial pain syndrome automation system reminds the student to change sitting postures or get up and prevent myofascial pain syndrome. This system applies consecutively to students for two academic semesters. Further, this system applied the prediction models by four Machine Learning techniques. The evaluation results of model efficiency revealed that the model developed with Multi-Layer Perceptron Neural Network has the highest accuracy of 93.98%. The model with the second highest accuracy performance was the Support Vector Machine, k-Nearest Neighbor, and Decision Tree techniques were modeled with accuracy values of 91.77%, 91.31%, and 90.56%, respectively. Furthermore, the results showed that the preventing myofascial pain syndrome automation system promoted higher student learning outcomes than the group without the preventing myofascial pain syndrome automation system at a significance level of 0.05. The developed system with the prediction model also effectively prevents and reduces the number of students from myofascial pains. Thus, the developed system has shown that educational management focusing on the learners’ health will enhance learning effectiveness.

Joint mechanical properties estimation with a novel EMG-based knee rehabilitation robot: A machine learning approach.

Joint dynamic properties play essential roles in a wide range of biomechanical movement control. This paper develops a device with a novel mechatronic design to apply small-amplitude perturbations to the human knee. Surface Electromyography is employed to record such information; at the same time, force and position sensors collect measurements to be sent to identify human joint dynamics. For classification and estimation of force, support vector machine and support vector regression techniques are applied, respectively. We devise a genetic algorithm for parameter optimization and feature extraction within the proposed methods to improve the estimation accuracy. These are then analyzed and compared to the output of our estimation model to provide a reliable comparison. Our extensive experimental results reveal a high estimation accuracy for lower limb muscles to regulate robot impedance parameters. Although the identification method sounds similar to traditional ones, knee joint properties can be estimated by the machine learning approach from the surface Electromyography without perturbations.

A combined convolutional neural network model and support vector machine technique for fault detection and classification based on electroluminescence images of photovoltaic modules

Nowadays, photovoltaic (PV) systems are gaining increasing momentum due to their ability to generate clean and affordable electric power. However, many factors can impede the production of the PV panels totally or partially. As such, it has become imperative to develop fault detection/classification models to ensure best operating conditions at the maximum energy conversion efficiencies. To address this challenge, a new model for detecting and classifying the faults in electroluminescence images of PV panels has been proposed in this paper. The model combines two machine learning algorithms named Convolutional Neural Network (CNN) and Support Vector Machine (SVM) that are employed for features exaction and classification, respectively. The current model is trained and evaluated using two databases D1 and D2 that contains the electroluminescence images of PV cells. By comparing the proposed model with the previous similar works, this study demonstrates that the CNN combined with SVM provides a higher classification performance with an accuracy of 99.49 % and 99.46 % for databases D1 and D2, respectively.

A Novel K-Means Clustered Support Vector Machine Technique for Prediction of Consumer Decision-Making Behaviour

A greater number of consumers are using social networks to express their feedback about the level of service provided by hotels. Online reviews from patrons can be used as a forum to enhance the level of service of hotels. Customer reviews are indeed a reliable and dependable source that aid diners in determining the quality of their cuisine. It is critical to develop techniques for evaluating client feedback on hotel services. In order to accurately anticipate the consumers' decision-making behaviors based on hotel internet evaluations, this study proposes a novel K-Means Clustered Support Vector Machine (KMC+SVM) technique. Principal Component Analysis (PCA) is employed to determine the characteristics from the preprocessed data while the Min-Max normalization approach is used to standardize the raw data. The performance of the suggested technique is then evaluated and contrasted with a few other methods that are currently in use in terms of accuracy, sensitivity, RMSE, and MAE. The findings demonstrated that segmenting customers based on their online evaluations can accurately predict their choices and assist hotel management in establishing priorities for service quality enhancements.

Emotion Recognition of Down Syndrome People Based on the Evaluation of Artificial Intelligence and Statistical Analysis Methods

This article presents a study based on evaluating different techniques to automatically recognize the basic emotions of people with Down syndrome, such as anger, happiness, sadness, surprise, and neutrality, as well as the statistical analysis of the Facial Action Coding System, determine the symmetry of the Action Units present in each emotion, identify the facial features that represent this group of people. First, a dataset of images of faces of people with Down syndrome classified according to their emotions is built. Then, the characteristics of facial micro-expressions (Action Units) present in the feelings of the target group through statistical analysis are evaluated. This analysis uses the intensity values of the most representative exclusive action units to classify people’s emotions. Subsequently, the collected dataset was evaluated using machine learning and deep learning techniques to recognize emotions. In the beginning, different supervised learning techniques were used, with the Support Vector Machine technique obtaining the best precision with a value of 66.20%. In the case of deep learning methods, the mini-Xception convolutional neural network was used to recognize people’s emotions with typical development, obtaining an accuracy of 74.8%.

Predicting Kurdish EFL University Learners' Oral Reading Fluency Using Support Vector Machine

Investigating learners’ English Oral Reading Fluency (ORF) in the contexts where English is used as a foreign language (EFL) or second language (ESL) has recently become a trending subject. This study was carried out to predict the ORF of 100 Kurdish EFL university students of the English language department, college of Basic Education, university of Duhok, Iraq in 2020 during covid-19 using the support vector machine (SVM) technique. This technique is one of the supervised machine learning techniques, and it is considered the most powerful algorithm in machine learning in terms of high accuracy; therefore, it was employed in this study. Participants’ ORF was measured by two experienced human raters using the four dimensions of the Multidimensional Fluency Scale (MDFS) including expression & volume, phrasing, smoothness, and pacing, which were used as the input variables to predict the ORF as an output. Six kernels of the SVM were used in the prediction process. The results indicated that the highest accuracy of testing result was obtained on the use of SVM Linear kernel with a value of 96.2%. Confusion matrix was utilized to assess the outcomes of data classification. The results of precision, recall, and F1-score were the highest for the SVM linear kernel and their values were the same for all performance metrics with a value of 96.1%. Accordingly, it can be concluded that the performance of the SVM is considerably accurate in predicting the oral reading fluency.

Predicting and avoiding hazardous occurrences of stuck pipe for the petroleum wells at offshore Vietnam using machine learning techniques

Over many years, the petroleum industry has been facing the hazardous occurrences associated with drilling stuck pipe. It is actually one of the most challenging and costly problems at offshore drilling rigs, especially in the high-risk, high-cost environments as the ultra-deep or deep water. Nowadays, with the development of Artificial Intelligence these problems can be predicted and avoided by applying machine learning techniques. The purpose of study is to apply the two most powerful machine learning techniques including Artificial Neural Network (ANN) and Support Vector Machine (SVM) to predict and avoid stuck pipe occurrences for the petroleum wells at offshore Vietnam. Modeling ANN and SVM using Matlab programming language based on many actual drilling parameters to estimate the risk of stuck pipe. The output of the models of both ANN and SVM machine learning techniques is the probability of non-stuck or stuck pipe at different measured depth points. Predictive results from both ANN and SVM techniques are compared to real measurements with the accuracy of all models above 85%. These machine learning techniques can help predicting stuck pipe occurrences as well as avoiding them by considering the changes of some important drilling operational parameters.

Discovery of Intentional Self-Harm Patterns from Suicide and Self-Harm Surveillance Reports.

The purpose of this study was to identify patterns of self-harm risk factors from suicide and self-harm surveillance reports in Thailand. This study analyzed data from suicide and self-harm surveillance reports submitted to Khon Kaen Rajanagarindra Psychiatric Hospital, Thailand. The process of identifying patterns of self-harm risk factors involved: data preprocessing (namely, data preparation and cleaning, missing data management using listwise deletion and expectation-maximization techniques, subgrouping factors, determining the target factors, and data correlation for learning); classifying the risk of self-harm (severe or mild) using 10-fold cross-validation with the support vector machine, random forest, multilayer perceptron, decision tree, k-nearest neighbors, and ensemble techniques; data filtering; identifying patterns of self-harm risk factors using 10-fold cross-validation with the classification and regression trees (CART) technique; and evaluating patterns of self-harm risk factors. The random forest technique was most accurate for classifying the risk of self-harm, with specificity, sensitivity, and F-score of 92.84%, 93.12%, and 91.46%, respectively. The CART technique was able to identify 53 patterns of self-harm risk, consisting of 16 severe self-harm risk patterns and 37 mild self-harm risk patterns, with an accuracy of 92.85%. In addition, we discovered that the type of hospital was a new risk factor for severe selfharm. The procedure presented herein could identify patterns of risk factors from self-harm and assist psychiatrists in making decisions related to self-harm among patients visiting hospitals in Thailand.

DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis

Automatic analysis of medical images and endoscopic images, in particular, is an attractive research topic in recent years. To achieve this goal, many tasks must be conducted for example lesion detection, segmentation, and classification. However, existing methods for such problems still face challenges due to the spreading characteristic of the lesions as well as some artifacts caused by motion, specularities, low contrast, bubbles, debris, bodily fluid, and blood. As a consequence, single segmentation or detection could not deal with those issues. Besides, although deep learning has achieved impressive results in many tasks, lacking a large annotated dataset could lead to overfitting problems. In this paper, we tackle these issues by taking particular characteristics of lesions of interest and advantages of deep segmentation models into account. We propose a dual-path framework (namely, DCS-UNet) that combines both segmentation and classification. We first segment lesions from the image using U-Net architecture with different encoder backbones (ResNet-50, VGG-16, DenseNet-201). The segmented regions will be then refined in the second path where we classify every patch in the whole image or the Inner or Outer regions extended from the contours given by the segmentation results. For the refinement scheme, we utilize the color-dependent and texture features as doctors’ advice and deploy the support vector machine (SVM) technique to classify a patch into disease region or not. Extensive experiments were conducted on three datasets of gastroesophageal reflux disease (GERD) endoscopic images as GradeM, GradeA, GradeB, which are defined as modified Los Angeles classification. The experimental results show the improvements of the proposed method compared to the single U-Net or a segmentation using the hand-designed features-based scheme. The proposed method improves mDice and mIoU by 0.5% and 0.36% on GradeA dataset, which is the most challenging dataset with ambiguous separations of GERD vs. normal regions, and by 0.82% and 0.81% on GradeM dataset, which is clearer to segment GERD regions. This proposed framework shows the potential to develop a diagnosis assistance system to help endoscopists reduce burden in examining GERD in the future.

Comparison of classification techniques for the control of EOG-based HCIs

Electrooculogram (EOG) is the measurement of the biopotential generated by eye movement. These signals are crucial for people with severe motor disabilities because they rarely suffer alterations in eye movement. Therefore, the correct classification of these signals could find application in the design of simple user interfaces that allow independence and communication skills. This paper presents a comparison of the main classification techniques in the literature for the control of EOG-based human–computer interfaces (HCIs). Static threshold, K-nearest neighbor (KNN), artificial neural network (ANN), and support vector machine (SVM) techniques, together with two new ensembles of classifiers. One is based on a voting scheme while the other employs two stages to encode the outcomes from the KNN, SVM, and ANN classifiers. All classifiers were compared based on four parameters – precision, specificity, sensitivity, and accuracy – to select the most appropriate approach in real-time. This work also provides a novel data set consisting of signals from nine healthy participants and compares the above methods also on another public data set. Machine learning-based models proved to be more robust for continuous use of an EOG-based HCI, while static thresholds are better for specific and repetitive actions.

Analysis of Methods of Machine Learning Techniques for Detection and Classification of Brown Spot (Rice) Disease

Rice is a major crop and the increased production is pertinent to ensure our food security. Modern techniques and advancements are required in agriculture to enable us to improve productivity and environment-friendliness as well as improve their farming conditions. Automatic disease detection techniques can help in identifying the various rice plant diseases. In agriculture, image processing is commonly used to obtain valuable information about crops. Images are often considered a source of information and data. Machine learning (ML) is a promising modern technique for image processing, and it has been successfully used in various areas such as agriculture. This paper aims to study the various research efforts that are focused on this technology in the field of agriculture. One particular class of ML that is commonly used in this work is convolutional neural networks. Here convolutional neural networks (CNNs) have been developed over the support vector machine (SVM) techniques to identify rice diseases (Brown spot) and measure their accuracy. Their potential applications include the development of screening tools and solutions for agricultural production. This paper presents an overview and research outcomes using SVM and CNN techniques in the study of agricultural problems. This study includes a dataset of 1488 healthy leaves and 523 brown spot leaf data samples. The research outcomes are based on studies and development using SVM and CNN. ML techniques give 82% accuracy using the SVM classification method, while the CNN method gives 95% accuracy.

Supervised learning using support vector machine applied to sentiment analysis of teacher performance satisfaction

Satisfaction with teaching performance is an important measurement process in higher education institutions, for this reason, applying sentiment analysis to the opinions of university students through the support vector machine (SVM) Fine Gaussian supervised learning algorithm represents an important contribution to the academic literature. This article identifies the best classification algorithm according to performance parameters for predicting student satisfaction with teaching performance through sentiment analysis; the subsequent implementation of the research has the purpose of strengthening teaching practices, in addition to allowing continuous training of teaching for the benefit of student learning. This article has provided a compact predictive model, with literature review based on SVM and sentiment analysis techniques. Through the machine learning classification learner technique, it is identified that the SVM algorithm: Fine Gaussian SVM is the one with the best accuracy equal to 98.3%. Likewise, the performance metrics for the four classes of the model were identified, which have a sensitivity equal to 88.89%, a specificity of 98.04%, a precision of 99.21% and an accuracy of 98.85%.

Prediction of Bed-Load Sediment Using Newly Developed Support-Vector Machine Techniques

Prediction of Bed-Load Sediment Using Newly Developed Support-Vector Machine Techniques

Predicting individual learning performance using machine‐learning hybridized with the teaching‐learning‐based optimization

AbstractReliable prediction of individual learning performance can facilitate timely support to students and improve the learning experience. In this study, two well‐known machine‐learning techniques, that is, support vector machine (SVM) and artificial neural network (ANN), are hybridized by teaching–learning‐based optimizer (TLBO) to reliably predict the student exam performance (fail‐pass classes and final exam scores). For the defined classification and regression problems, the TLBO algorithm carries out the feature selection process of both ANN and SVM techniques in which the optimal combination of the input variables is determined. Moreover, the ANN architecture is determined using the TLBO algorithm parallel to the feature selection process. Finally, four hybrid models containing anonymized information on both discrete and continuous variables were developed using a comprehensive data set for learning analytics. This study provides scientific utility by developing hybridized machine‐learning models and TLBO, which can improve the predictions of student exam performance. In practice, individual performance prediction can help to advise students about their academic progress and to take appropriate actions such as dropping units in subsequent teaching periods. It can also help scholarship providers to monitor student progress and provision of support.

Support vector machine deep mining of electronic medical records to predict the prognosis of severe acute myocardial infarction.

Cardiovascular disease is currently one of the most important diseases causing death in China and the world, and acute myocardial infarction is a major cause of cardiovascular disease. This study provides an analytical technique for predicting the prognosis of patients with severe acute myocardial infarction using a support vector machine (SVM) technique based on information gleaned from electronic medical records in the Medical Information Marketplace for Intensive Care (MIMIC)-III database. The MIMIC-III database provided 4785 electronic medical records data for inclusion in the model development after screening 7070 electronic medical records of patients admitted to the intensive care unit for treatment of acute myocardial infarction. Adopting the APS-III score as the criterion for identifying anticipated risk, the dimensions of data information incorporated into the mathematical model design were found using correlation coefficient matrix heatmaps and ordered logistic analysis. An automated prognostic risk-prediction model was developed using SVM, and the fit was evaluated by 5× cross-validation. We used a grid search method to further optimize the parameters and improve the model fit. The excellent generalization ability of SVM was fully verified by calculating the 95% confidence interval of the area under the receiver operating characteristic curve (AUC) for six algorithms (linear discriminant, tree, Kernel Naive Bayes, RUSBoost, KNN, and SVM). Compared to the remaining five models, its confidence interval was the narrowest with higher fitting accuracy and better performance. The patient prognostic risk prediction model constructed using SVM had a relatively impressive accuracy (92.2%) and AUC value (0.98). In this study, a model was designed for fitting that can maximize the potential information to be gleaned in the electronic medical records data. It was demonstrated that SVM models based on electronic medical records data can offer an effective solution for clinical disease prognostic risk assessment and improved clinical outcomes and have great potential for clinical application in the clinical treatment of myocardial infarction.

Information Retrieval for Cancer Cell Detection Based on Advanced Machine Learning Techniques

In this research paper, we focus on designing and developing a fully automated gene regulation from cancerous cell heterogeneity using advanced machine learning techniques. There are several modern technologies developed to make DNA sequencing easier and cheaper. Among them, gene regulation produces the longest read sequences and the lengths of the reads are growing day by day. Machine learning technique like Support Vector Machine (SVM) is developed to align these gene sequences. Every technique faced some challenges, but facing the desired challenges introduce some new challenges on the other side. So, no one tool is perfect for every work. The SVM technique is a new aligner tool that does a tradeoff and performs better from different aspects. For the model with the best generator loss, an average maximum validation accuracy of 91.29% was achieved. The gene regulation with SVM is like a mini-map that takes a few times more memory to index the whole genome of a reference sequence. The single-cell data are the main target of SVM. It is shown that it would help the SVM and similar techniques to align better with long insertions and deletions of single-cell gene regulation. Single-cell data is run against the well-known reference sequence and a randomly generated synthetic reference.

Evaluation Method of Writing Fluency Based on Machine Learning Method

In light of society's rapid advancement, more and more people worldwide are placing importance on education. There are several domains in China where the importance of writing exceeds the importance of reading, listening, or speaking. It has been shown that many Chinese students commit grammar problems if they are writing an article. Several researchers attempted to determine students' writing talents in terms of amount and complexity, on the one side, and then also focused on identifying conclusions on the accuracy, the organization of ideas, and the barriers to fluent writing via qualitative data gathering approaches. This research uses a machine learning technique to measure students' writing fluency. Writing fluency capabilities can be predicted using a novel adaptive generative adversarial network-based deep support vector machine (AGAN-DSVM) technique. The trace-oriented approach can be used to examine the features like accuracy, syntactic complexity, and organization of ideas aspects. The prediction rate of lexical complexity and sentence complexity of our proposed method achieves 90 and 95%, respectively. Plots created with origin's graphing tool display the results of a comparison between the proposed approach and several other ways already in use. The proposed method is evaluated and compared using several different metrics, including the accuracy dimension, syntactic complexity dimension, organization of ideas dimension, distributions of the mistakes in the text, lexical complexity, sentence complexity, essay particularities, and comparison of accuracy, F1 score, and syntactic complexity.