International Journal of Advanced Computer Science and Applications
The escalating student numbers in Moroccan universities have intensified the complexities of mana... more The escalating student numbers in Moroccan universities have intensified the complexities of managing ontime graduation. In this context, Machine learning methodologies were utilized to analyze the patterns and predict on-time graduation rates in a comprehensive manner. Our dataset comprised information from 5236 bachelor students who graduated in the years 2020 and 2021 from the Faculty of Law, Economic, and Social Sciences at Moulay Ismail University. The dataset incorporated a diverse range of student attributes including age, marital status, gender, nationality, socioeconomic category of parents, profession, disability status, province of residence, high school diploma attainment, and academic honors, all contributing to a comprehensive understanding of the factors influencing graduation outcomes. Implementation and evaluation of the performance of five different machine learning models: Support Vector Machines, Decision Tree, Naive Bayes, Logistic Regression, and Random Forest, were carried out. These models were assessed based on their classification reports, confusion matrices, and Receiver Operating Characteristic (ROC) curves. From the findings, the Random Forest model emerged as the most accurate in predicting on-time graduation, showcasing the highest accuracy and ROC AUC score. Despite these promising results, it is believed that performance enhancements can be achieved through further tuning and preprocessing of the dataset. Insights from this study could enable Moroccan universities, among others, to better comprehend the factors influencing on-time graduation and implement appropriate measures to improve academic outcomes.
The escalating student numbers in Moroccan universities have intensified the complexities of mana... more The escalating student numbers in Moroccan universities have intensified the complexities of managing ontime graduation. In this context, Machine learning methodologies were utilized to analyze the patterns and predict on-time graduation rates in a comprehensive manner. Our dataset comprised information from 5236 bachelor students who graduated in the years 2020 and 2021 from the Faculty of Law, Economic, and Social Sciences at Moulay Ismail University. The dataset incorporated a diverse range of student attributes including age, marital status, gender, nationality, socioeconomic category of parents, profession, disability status, province of residence, high school diploma attainment, and academic honors, all contributing to a comprehensive understanding of the factors influencing graduation outcomes. Implementation and evaluation of the performance of five different machine learning models: Support Vector Machines, Decision Tree, Naive Bayes, Logistic Regression, and Random Forest, were carried out. These models were assessed based on their classification reports, confusion matrices, and Receiver Operating Characteristic (ROC) curves. From the findings, the Random Forest model emerged as the most accurate in predicting on-time graduation, showcasing the highest accuracy and ROC AUC score. Despite these promising results, it is believed that performance enhancements can be achieved through further tuning and preprocessing of the dataset. Insights from this study could enable Moroccan universities, among others, to better comprehend the factors influencing on-time graduation and implement appropriate measures to improve academic outcomes.
Given the increasing number of COVID-19 cases and the risk of new variants, early prediction of d... more Given the increasing number of COVID-19 cases and the risk of new variants, early prediction of disease severity in critical care patients is essential to optimize treatment options. In this study, we set up an experiment on 236 patients infected with COVID-19 and hospitalized at the Sidi Said hospital in Meknes, Morocco. This work proposes a new multivariate classification model to predict which patients admitted to hospital with COVID-19 will require special care (oxygen therapy, intensive care, resuscitation) or will die following an abrupt deterioration in their state of health. This model will help healthcare professionals (doctors) make decisions about recommending appropriate medical treatments to patients. A comparative study of different multivariate machine learning algorithms (Support Vector Machine (SVM), K-nearest neighbor (KNN), Decision Tree (DT) and Random Forest (RF)) is also presented in this article. The result obtained shows that the SVM classifier is a reliable, powerful and efficient algorithm to predict the level of risk of patients contaminated with COVID-19.
The main goal of precision medicine in the fight against cancer is to predict effective treatment... more The main goal of precision medicine in the fight against cancer is to predict effective treatment modalities based on the unique molecular genetic profiles of a tumor. Understanding the factors that influence treatment success is critical because people with breast cancer at similar stages respond differently to treatment. In order to reduce the likelihood of recurrence of metastases in breast cancer patients, this study proposes a supervised multinomial logistic regression model. This model will help clinicians make decisions about which treatment plans they should recommend to patients. In addition, this article compares a number of polynomial machine learning technologies, including Naive Bayes, Decision Tree, Support Vector Machine, Random Forest, and Neural Network (ANN). Accuracy results for adjuvant treatment combination prediction show that the Random Forest classifier is more accurate.
Recommender systems based on collaborative filtering have been widely used in many online learnin... more Recommender systems based on collaborative filtering have been widely used in many online learning systems, in order to help learners, find appropriate learning resources. However, these systems are based on classical similarity measures exploiting only learners' ratings for learning objects said subjective preferences, to form groups of learners with similar interests. This paper aims at exploiting also pedagogical criteria of the learning objects, in order to improve the classical similarity measures to generate qualitative recommendations. For this reason, we adopt a Shannon Entropy approach, combining heuristic weights with classical similarity measures, in order to produce recommendations evaluated by their subjective quality, and by their objective usefulness to support learners in their learning process.
International Journal of Advanced Computer Science and Applications
Computerised electroencephalography (EEG) is one of a wide variety of brain imaging techniques us... more Computerised electroencephalography (EEG) is one of a wide variety of brain imaging techniques used in addiction medicine. It is a sensitive measure of the effects of addiction on the brain and has been shown to show changes in brain electrical activity during addiction. But, the clinical value of computerised EEG recording in addictions is not yet clearly established. However, several studies argue that this non-invasive technique has an undeniable contribution to the understanding, prediction, diagnosis and monitoring of addictions. The aim of this article is to assess, through a systematic review, the contribution and interest of computerised EEG in the study and understanding of substance abuse by describing the different electrical activities that underlie it across the main frequency ranges: delta, theta, alpha, beta and gamma. We have been conducting a systematic review according to the recommendations of Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) and the Cochrane Group. We included 25 studies with a total of 1897 cases of addiction and 1504 controls. The studies dealt with addictions related to 05 licit and illicit psychoactive substances (alcohol, nicotine, cannabis, heroin and cocaine). The group of addicted patients showed significantly different brain electrical characteristics from the group of controls in the different EEG rhythms, whether during acute substance intoxication, abuse, withdrawal, abstinence, relapse, progression or response to treatment. The majority of studies have used EEG for diagnostic, predictive, monitoring purposes and also to discover electro-physiological markers of certain addictions.
International Journal of Advanced Computer Science and Applications
The prediction of breast cancer recurrence is a crucial problem in cancer research that requires ... more The prediction of breast cancer recurrence is a crucial problem in cancer research that requires accurate and efficient prediction models. This study aims to compare the performance of different machine learning techniques in predicting types of breast cancer recurrence. In this study, the performance of logistic regression, decision tree, K-Nearest Neighbors, and artificial neural network algorithms was compared on a breast cancer recurrence dataset. The results show that the artificial neural network algorithm outperformed the other algorithms with 91% accuracy, followed by the decision tree (DT) algorithm and K-Nearest Neighbors (kNN) also performed well with accuracies of 90.10% and 88.20%, respectively, while the logistic regression algorithm had the lowest accuracy of 84.60%. The results of this study provide insight into the effectiveness of different machine learning techniques in predicting types of breast cancer recurrence and could guide the development of more accurate prediction models.
International Journal of Advanced Computer Science and Applications
The prediction of breast cancer recurrence is a crucial problem in cancer research that requires ... more The prediction of breast cancer recurrence is a crucial problem in cancer research that requires accurate and efficient prediction models. This study aims to compare the performance of different machine learning techniques in predicting types of breast cancer recurrence. In this study, the performance of logistic regression, decision tree, K-Nearest Neighbors, and artificial neural network algorithms was compared on a breast cancer recurrence dataset. The results show that the artificial neural network algorithm outperformed the other algorithms with 91% accuracy, followed by the decision tree (DT) algorithm and K-Nearest Neighbors (kNN) also performed well with accuracies of 90.10% and 88.20%, respectively, while the logistic regression algorithm had the lowest accuracy of 84.60%. The results of this study provide insight into the effectiveness of different machine learning techniques in predicting types of breast cancer recurrence and could guide the development of more accurate prediction models.
International Journal of Advanced Computer Science and Applications
Computerised electroencephalography (EEG) is one of a wide variety of brain imaging techniques us... more Computerised electroencephalography (EEG) is one of a wide variety of brain imaging techniques used in addiction medicine. It is a sensitive measure of the effects of addiction on the brain and has been shown to show changes in brain electrical activity during addiction. But, the clinical value of computerised EEG recording in addictions is not yet clearly established. However, several studies argue that this non-invasive technique has an undeniable contribution to the understanding, prediction, diagnosis and monitoring of addictions. The aim of this article is to assess, through a systematic review, the contribution and interest of computerised EEG in the study and understanding of substance abuse by describing the different electrical activities that underlie it across the main frequency ranges: delta, theta, alpha, beta and gamma. We have been conducting a systematic review according to the recommendations of Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) and the Cochrane Group. We included 25 studies with a total of 1897 cases of addiction and 1504 controls. The studies dealt with addictions related to 05 licit and illicit psychoactive substances (alcohol, nicotine, cannabis, heroin and cocaine). The group of addicted patients showed significantly different brain electrical characteristics from the group of controls in the different EEG rhythms, whether during acute substance intoxication, abuse, withdrawal, abstinence, relapse, progression or response to treatment. The majority of studies have used EEG for diagnostic, predictive, monitoring purposes and also to discover electro-physiological markers of certain addictions.
Accurately predicting effective treatment methods based on personalized tumor genetic profiles is... more Accurately predicting effective treatment methods based on personalized tumor genetic profiles is a major goal of precision cancer medicine. Because people with breast cancer at comparable stages respond differently to treatment, it is essential to gain insight into the variables that influence treatment success. This study presents a supervised multinomial logistic regression model for predicting the best adjuvant therapy for breast cancer patients to lower the probability of metastatic recurrence. This model will assist health professionals (physicians) in making judgments about which medicinal regimens to suggest to patients. In addition, this article presents a comparison of several multinomial machine learning methods (Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Neural Network (ANN)). The results reveal that the Random Forest classifier is more effective in terms of adjuvant therapy combination prediction accuracy.
International Journal of Advanced Computer Science and Applications, 2022
The volume and amount of data in cancerology is continuously increasing, yet the vast majority of... more The volume and amount of data in cancerology is continuously increasing, yet the vast majority of this data is not being used to uncover useful and hidden insights. As a result, one of the key goals of physicians for therapeutic decision-making during multidisciplinary consultation meetings is to combine prediction tools based on data and best practices (MCM). The current study looked into using CRISP-DM machine learning algorithms to predict metastatic recurrence in patients with early-stage (non-metastatic) breast cancer so that treatmentappropriate medicine may be given to lower the likelihood of metastatic relapse. From 2014 to 2021, data from patients with localized breast cancer were collected at the Regional Oncology Center in Meknes, Morocco. There were 449 records in the dataset, 13 predictor variables and one outcome variable. To create predictive models, we used machine learning techniques such as Support Vector Machine (SVM), Nave Bayes (NB), K-Nearest Neighbors (KNN) and Logistic Regression (LR). The main objective of this article is to compare the performance of these four algorithms on our data in terms of sensitivity, specificity and precision. According to our results, the accuracies of SVM, kNN, LR and NB are 0.906, 0.861, 0.806 and 0.517 respectively. With the fewest errors and maximum accuracy, the SVM classification model predicts metastatic breast cancer relapse. The unbiased prediction accuracy of each model is assessed using a 10-fold cross-validation method.
The volume and amount of data in cancerology is continuously increasing, yet the vast majority of... more The volume and amount of data in cancerology is continuously increasing, yet the vast majority of this data is not being used to uncover useful and hidden insights. As a result, one of the key goals of physicians for therapeutic decision-making during multidisciplinary consultation meetings is to combine prediction tools based on data and best practices (MCM). The current study looked into using CRISP-DM machine learning algorithms to predict metastatic recurrence in patients with early-stage (non-metastatic) breast cancer so that treatmentappropriate medicine may be given to lower the likelihood of metastatic relapse. From 2014 to 2021, data from patients with localized breast cancer were collected at the Regional Oncology Center in Meknes, Morocco. There were 449 records in the dataset, 13 predictor variables and one outcome variable. To create predictive models, we used machine learning techniques such as Support Vector Machine (SVM), Nave Bayes (NB), K-Nearest Neighbors (KNN) and Logistic Regression (LR). The main objective of this article is to compare the performance of these four algorithms on our data in terms of sensitivity, specificity and precision. According to our results, the accuracies of SVM, kNN, LR and NB are 0.906, 0.861, 0.806 and 0.517 respectively. With the fewest errors and maximum accuracy, the SVM classification model predicts metastatic breast cancer relapse. The unbiased prediction accuracy of each model is assessed using a 10-fold cross-validation method.
Uploads
Papers by Merouane ERTEL