Student performance predictor using multiclass support vector classification algorithm

Education can be utilized as a tool to face many problems, overcome many hurdles in life. The knowledge obtained from education helps to enhance opportunities in one's employment development. To extract useful information from the knowledge obtained, Educational Data Mining is widely used. Educational data mining provides the process of applying different data mining tools and techniques to analyze and visualize the data of an institution (school) and can be used to discover a unique pattern of students' academic performance and behavior. The present work intends to enhance students' academic performance in secondary school using data mining techniques. Real data was collected using school reports and questionnaire method by the Portugal school which has been used in this paper. Naive Bayesian algorithm can be easily implemented to predict the students' academic performance and behavior. Classification of students into two classes, pass and fail, involves training phase and testing phase. In training phase, Naive Bayes classifier is built and in the testing phase, Naive Bayes classifier is used to make the prediction. The accuracy of the classifier is calculated using WEKA tool in which confusion matrix is generated. The accuracy of the classifier obtained is 87% which can be further improved by the selection of appropriate attributes. Developing the classification algorithms in this way helps to obtain a more efficient student performance predictor tool using other data mining algorithms and it also helps to improve the quality of education in an educational institution.

Metabolic brain imaging with 2-[18F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can improve diagnostic accuracy. We aimed to build two machine learning classifiers, based on two sets of FDG PET-derived features, for differential diagnosis of common dementia syndromes. We analyzed FDG PET scans from three dementia cohorts [63 dementia due to Alzheimer's disease (AD), 79 dementia with Lewy bodies (DLB) and 23 frontotemporal dementia (FTD)], and 41 normal controls (NCs). Patients' clinical diagnosis at follow-up (25 ± 20 months after scanning) or cerebrospinal fluid biomarkers for Alzheimer's disease was considered a gold standard. FDG PET scans were first visually evaluated. Scans were pre-processed, and two sets of features extracted: (1) the expressions of previously identified metabolic brain patterns, and (2) the mean uptake value in 95 regions of interest (ROIs). Two multi-class support vector machine (SVM) classifiers were tested and their diagnostic performance assessed and compared to visual reading. Class-specific regional feature importance was assessed with Shapley Additive Explanations. Pattern- and ROI-based classifier achieved higher overall accuracy than expert readers (78% and 80% respectively, vs. 71%). Both SVM classifiers performed similarly to one another and to expert readers in AD (F1 = 0.74, 0.78, and 0.78) and DLB (F1 = 0.81, 0.81, and 0.78). SVM classifiers outperformed expert readers in FTD (F1 = 0.87, 0.83, and 0.63), but not in NC (F1 = 0.71, 0.75, and 0.92). Visualization of the SVM model showed bilateral temporal cortices and cerebellum to be the most important features for AD; occipital cortices, hippocampi and parahippocampi, amygdala, and middle temporal lobes for DLB; bilateral frontal cortices, middle and anterior cingulum for FTD; and bilateral angular gyri, pons, and vermis for NC. Multi-class SVM classifiers based on the expression of characteristic metabolic brain patterns or ROI glucose uptake, performed better than experts in the differential diagnosis of common dementias using FDG PET scans. Experts performed better in the recognition of normal scans and a combined approach may yield optimal results in the clinical setting.

The rate at which students succeed in their academic pursuits contributes significantly to the academic achievement of their educational institutions because it is used as a measure of the institution’s performance. Many factors could be responsible for students’ academic performance and student success. Quick understanding of weak students and providing solutions to improve their performance will significantly increase their academic success rate. Educational data mining using artificial neural network plays a crucial role in determining their likely performance and helps them to initiate measures that can reposition the students’ performance in the future. This study developed a model that predicts students’ failure and success rates with the aid of a machine learning algorithm. The study sampled 720 students from three selected tertiaries institutions in Adamawa State, Nigeria. Three hundred students were selected from Modibbo Adama University, Yola, 300 students were selected from Adamawa State University, Mubi, and 120 students were selected from Adamawa State Polytechnic, Yola. The research makes use of descriptive statistics to identify the variables that likely affect students’ academic performance. The collected data were preprocessed, cleaned, and modeled using Jupyter Notebook, a Python Anaconda development platform for artificial neural to build the student’s academic performance predictive model. The neural network is modeled with 12 input variables, two layers of hidden neurons, and one output layer. The dataset is trained using the backpropagation learning algorithm. The performance of the neural network is evaluated using k-fold cross-validation. The neural network model has achieved a good accuracy of 97.36%. Received: 14 October 2022 | Revised: 15 December 2022 | Accepted: 29 December 2022 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data available on request from the corresponding author upon reasonable request.

Educational Data Mining (EDM) is used to extract and discover interesting patterns from educational institution datasets using Machine Learning (ML) algorithms. There is much academic information related to students available. Therefore, it is helpful to apply data mining to extract factors affecting students’ academic performance. In this paper, a web-based system for predicting academic performance and identifying students at risk of failure through academic and demographic factors is developed. The ML model is developed to predict the total score of a course at the early stages. Several ML algorithms are applied, namely: Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Linear Regression (LR). This model applies to the data of female students of the Computer Science Department at Imam Abdulrahman bin Faisal University (IAU). The dataset contains 842 instances for 168 students. Moreover, the results showed that the prediction’s Mean Absolute Percentage Error (MAPE) reached 6.34%, and the academic factors had a higher impact on students’ academic performance than the demographic factors, the midterm exam score in the top. The developed web-based prediction system is available on an online server and can be used by tutors.

Predicting students’ academic performance at an early stage of a semester is one of the most crucial research topics in the field of Educational Data Mining (EDM). Students are facing various difficulties in courses like “Programming” and “Data Structures” through undergraduate programs, which is why failure and dropout rates in these courses are high. Therefore, EDM is used to analyze students’ data gathered from various educational settings to predict students’ academic performance, which would help them to achieve better results in their future courses. The main goal of this paper is to explore the efficiency of deep learning in the field of EDM, especially in predicting students’ academic performance, to identify students at risk of failure. A dataset collected from a public 4-year university was used in this study to develop predictive models to predict students’ academic performance of upcoming courses given their grades in the previous courses of the first academic year using a deep neural network (DNN), decision tree, random forest, gradient boosting, logistic regression, support vector classifier, and K-nearest neighbor. In addition, we made a comparison between various resampling methods to solve the imbalanced dataset problem, such as SMOTE, ADASYN, ROS, and SMOTE-ENN. From the experimental results, it is observed that the proposed DNN model can predict students’ performance in a data structure course and can also identify students at risk of failure at an early stage of a semester with an accuracy of 89%, which is higher than models like decision tree, logistic regression, support vector classifier, and K-nearest neighbor.

Security assessment and classification are the major concerns in real-time operation of electric power systems. This paper proposes a multiclass support vector machine (SVM) classifier for static and transient security assessment and classification. A straightforward and quick procedure called the sequential forward selection method is used for a feature selection process. The security status of any given operating condition is classified into four modes, viz., secure, critically secure, insecure, and highly insecure, based on the computation of a security index. The proposed SVM-based pattern classifier system is implemented and tested on standard benchmark systems. The simulation results of the multiclass SVM classifier are compared with least-squares, probabilistic neural network, extreme learning machine, and extreme SVM classifiers. The feasibility of implementation of the proposed classifier system for online security evaluation is also discussed.

Automatic Speech Recognition (ASR) is essentially a problem of pattern classification, however, the time dimension of the speech signal has prevented to pose ASR as a simple static classification problem. Support Vector Machine (SVM) classifiers could provide an appropriate solution, since they are very well adapted to high-dimensional classification problems. Nevertheless, the use of SVMs for ASR is by no means straightforward, mainly because SVM classifiers require an input of fixed-dimension. In this paper we study the use of a HMM-based segmentation as a mean to get the fixed-dimension input vectors required by SVMs, in a problem of isolated-digit recognition. Different configurations for all the parameters involved have been tested. Also, we deal with the problem of multi-class classification (as SVMs are initially binary classifers), studying two of the most popular approaches: 1-vs-all and 1-vs-1.

Digital circuits are preferred over its analog counterpart with the invention of microprocessors, microcontrollers, digital signal processors and Field Programmable Gate Arrays (FPGA). Digital circuits in the form of digital arithmetic and digital logics are employed for various applications. On the other side, Support Vector Machine (SVM) is considered as a state-of-the-art tool for pattern recognition. In this paper, a novel attempt is made to study, assess and design digital circuits using two-class and multi class support vector machine classifiers. It is reported in literature that computational complexity and the classification time for SVM classifier depends on the number of support vectors required for classification. In order to reduce the number of support vectors, an optimum threshold technique based SVM classifier is employed for the design of digital circuits and it is observed that a maximum of 87.5% of total support vectors are pruned on using the technique.

Classifiers in Automatic Speech Recognition (ASR) aims to improve the generalization ability of the machine learning and improve the recognition accuracy in noisy environments. This paper discusses the classification performance of Hidden Markov Models (HMM) and Support Vector Machines (SVM) applied to a wavelet front end based ASR. The experiments are performed on speaker independent TIMIT database which are trained in a clean environment and later tested in the presence of Additive White Gaussian Noise (AWGN) for various SNR levels using the HTK toolkit and SVM Light software tool. Experiments indicate that for large vocabulary the wavelet front end and the Multiclass SVM classifier with RBF kernel performs better than the conventional HMM classifier.

Face recognition (FR) has drawn considerable interest and attention in the area of pattern recognition. FR is still a challenging task in real time applications even though they are a number of face recognition algorithms which are available and work in various constrained environment. The paper proposes a FR algorithm using Modified Local Ternary Pattern (MLTP) with multi class Support Vector Machine (SVM) classifier. The MLTP features of the face images are classified by an Error-Correcting Output Code (ECOC) multiclass model with SVM. The proposed method is tested on six standard face databases. The experimental results have been demonstrated that the performance of MLTP with SVM can achieve higher recognition accuracy compared to the conventional methods.

A simple and effective body-centric localization algorithm has been proposed in this article using ultra-wideband (UWB) wearable technology. The algorithm has been validated through measurement campaigns with a human subject volunteer in an indoor environment. The algorithm takes into account statistical channel parameter analysis, machine learning (ML) algorithms, and time-of-arrival (TOA)-based range estimation/data fusion techniques. Two channel parameters namely path loss magnitude and rms delay spread are proposed as classification features to be applied to the ML algorithm to accurately classify the off-body channel links into LOS, PNLOS, and NLOS scenarios. Multiclass support vector machine (MC-SVM) classifier along with SMOTE algorithm to take into account class imbalance is applied with the channel classification accuracy of 98.63%. Threshold-based range estimation algorithms are applied in order to mitigate NLOS scenarios caused mainly due to the presence of the human subject. Results report human localization accuracy in 0.5–3 cm range using TDOA data fusion technique for target estimation. Further validation is presented considering wide range of Tx–Rx distance, presence of another obstruction between the Tx and Rx links, and performance in different environment which shows the suitability of the proposed methodology.

Recently, focus on maintenance strategies has been shifted towards prognostic health management (PHM) and a number of state of the art algorithms based on data-driven prognostics have been developed to predict the health states of degrading components based on sensory data. Amongst these algorithms, Multiclass Support Vector Machines (MC-SVM) has gained popularity due to its relatively high classification accuracy, ability to classify multiple patterns and capability to handle noisy / incomplete data. However, its application is limited by the difficulty in determining the required kernel function and penalty parameters. To address this problem, this paper proposes a hybrid differential evolution – particle swarm optimization (DE-PSO) algorithm to optimize the MC-SVM kernel function and penalty parameters. The differential algorithm (DE) obtains the search limit for the SVM parameters, while the particle swarm optimization algorithm (PSO) determines the global optimum parameters for a given training data set. Since degrading machinery components display several degradation stages in their lifetime, the MC-SVM trained with optimum parameters are used to estimate the health states of a degrading machinery component, from which the remaining useful life (RUL) is predicted. This method improves the classification accuracy of MC-SVM in predicting the health states of a machinery component and consequently increases the accuracy of RUL predictions. The feasibility of the method is validated using bearing prognostic run-to-failure data obtained from NASA public data repository. A comparative study between MC-SVM with parameters obtained using simple grid search with n-fold cross validation and MC- SVM with DE-PSO based on prognostic performance metrics reveals that the proposed method has better performance, with all the cases considered falling within a 10 % error margin. The method also outperforms other soft computing methods proposed in literature.

Every year students success rate was analysed by the Educational Institutions to develop their Academic standard. To identify the success rate many kinds of techniques are used such as statistics, physical examination and currently ongoing datamining techniques. Data mining Techniques was widely used in many fields, it is also used in the Educational environment known as Educational Data Mining (EDM). Educational data mining generate prototype in solving the research problems in students data and used to locate the unseen patterns in the students detailed dateset. This paper uses the EDM to characterize the distinct factors affecting the students performance by making predictions with efficient algorithms. Educational professionals have to identify the causes for the student failure in academic performance and the students not succeed in completing their education which becomes a social problem these days. The machine learning algorithms help the researchers for evaluation of student’s learning habits, their academic performance and added enhancement if required. This paper would discuss different kinds of algorithms to analyse the economic background of the students which mainly affects the students performance. The dataset was utilized from the UCI Repository of secondary school students performance and analysed using the Weka tool for the datamining process.

In this paper, we present an approach for image-based surface classification using multi-class Support Vector Machine (SVM). Classifying surfaces in aerial images is an important step towards an increased aircraft autonomy in emergency landing situations. We design a one-vs-all SVM classifier and conduct experiments on five data sets. Results demonstrate consistent overall performance figures over 88% and approximately 8% more accurate to those published on multi-class SVM on the KTH TIPS data set. We also show per-class performance values by using normalised confusion matrices. Our approach is designed to be executed online using a minimum set of feature attributes representing a feasible and ready-to-deploy system for onboard execution.

The aim of this study is to extract impervious surfaces and show their spatial distribution, using different machine learning algorithms. For this purpose, geoprocessing and remote sensing techniques were used and three classification methods for digital images were compared, namely Support Vector Machines (SVM), Maximum Likelihood (ML) and Random Trees (RT) classifiers. The study area is one of the most prestigious and the largest housing estates in Warsaw (Poland), the Fort Bema housing complex, which is also an exemplary model for hydrological solutions. The study was prepared on the Geographic Information System platform (GIS) using aerial optical images, orthorectified and thus provided with a suitable coordinate system. The use of these data is therefore supported by the accuracy of the resulting infrared channel product with a pixel size of 0.25 m, making the results much more accurate compared to satellite imagery. The results of the SVM, ML and RT classifiers were compared using the confusion matrix, accuracy (Root Mean Square Error /RMSE/) and kappa index. This showed that the three algorithms were able to successfully discriminate between targets. Overall, the three classifiers had errors, but specifically for impervious surfaces, the highest accuracy was achieved with the SVM classifier (the highest percentage of overall accuracy), followed by ML and RT with 91.51%, 91.35% and 84.52% of the results, respectively. A comparison of the visual results and the confusion matrix shows that although visually the RT method appears to be the most detailed classification into pervious and impervious surfaces, the results were not always correct, e.g., water/shadow was detected as an impervious surface. The NDVI index was also mapped for the same spatial study area and its application in the evaluation of pervious surfaces was explained. The results obtained with the GIS platform, presented in this paper, provide a better understanding of how these advanced classifiers work, which in turn can provide insightful guidance for their selection and combination in real-world applications. The paper also provides an overview of the main works/studies dealing with impervious surface mapping, with different methods for their assessment (including the use of conventional remote sensing, NDVI, multisensory and cross-source data, ‘social sensing’ and classification methods such as SVM, ML and RT), as well as an overview of the research results.