-
Research Article
Opinion Mining of Student Regarding Educational System Using Online Platform
Muhammad Irfan*,
Khadija Bibi,
Adeeba Aslam,
Saima Bibi,
Anwar Khan
Issue:
Volume 10, Issue 2, December 2025
Pages:
91-109
Received:
27 January 2025
Accepted:
19 May 2025
Published:
4 August 2025
Abstract: Covid-19 is new virus that is spreading rapidly in all over the world. It is a communicable disease. World Health Organization announced social distancing to control the spread of that virus. All institutions are closed in Pakistan. Education was also effecting with this shutdown. In the age of computing, social computing has emerged as a means of sharing knowledge, conveying ideas, and forming academic discussion groups, to name a few. Social websites or apps are also used for online study due to some critical situation as if nowadays we are facing many problems due to COVID-19. Due to the COVID-19 educational system is disturbed for that purpose we are introducing a different online platform for delivering knowledge and continue the educational system many data mining techniques are applied to social network data for online analysis due to a large number of users and widespread use. This paper describes a method for extracting and analyzing master’s student comments from the online survey that which platform is better for online study and also giving the opinion about most used platform. The proposed technique is implemented using different models or algorithms. By providing various proformas and analyzing vary- iOS student opinions, the said system may assist the administration in improving the learning environment.
Abstract: Covid-19 is new virus that is spreading rapidly in all over the world. It is a communicable disease. World Health Organization announced social distancing to control the spread of that virus. All institutions are closed in Pakistan. Education was also effecting with this shutdown. In the age of computing, social computing has emerged as a means of ...
Show More
-
Research Article
Comparative Analysis of Machine Learning Algorithms for Predicting Under-Five Mortality: Evidence from Tanzania Demographic and Health Survey
Issue:
Volume 10, Issue 2, December 2025
Pages:
110-123
Received:
9 July 2025
Accepted:
24 July 2025
Published:
20 August 2025
Abstract: Under-five mortality remains a global health challenge with the rates of 43 deaths per every 1000 live births in Tanzania and 37 deaths per every 1000 live births globally. Although child mortality has significantly declined in the last twenty years, the current rates are far from reaching the anticipated Sustainable Development Goal of atmost 25 deaths per 1000 live births in 2030. This study intended to find the best performing classifier of under-five mortality status by comparing ten supervised machine learning algorithms. These machine learning algorithms are Decision Trees, Random Forest, Support Vector Machines, SMOTE-Based Boosted Random Forest, XGBoost, LightGBM, CatBoost, Logistic Regression, K-Nearest Neighbors and Stacked Ensemble Methods. The class imbalance of the dataset detected in the pre-processing stage was addressed using weighted categorical cross-entropy and SMOTE with a 5-folds cross validation and data splitting ratio of 80% for training set and 20% for testing set. With 20 experiments for each of the nine algorithms, the average results were reported to ensure that the findings were not by chance. Further, the stacking ensemble model was developed integrating six of the best performing algorithms using an inclusion criterion of AUC > 0.97. The findings revealed that ensemble algorithm consistently outperformed the other nine algorithms by achieving 100%, 100%, 99.97% and 99.24% for AUC, Accuracy, F1-Score and MCC respectively. This implies that stacking ensemble can uncover more insights than the individual algorithms in predicting under-five mortality status. This study recommends designing policies on under-five mortality that integrate insights from the stacking ensemble algorithm which shows the highest predictive performance.
Abstract: Under-five mortality remains a global health challenge with the rates of 43 deaths per every 1000 live births in Tanzania and 37 deaths per every 1000 live births globally. Although child mortality has significantly declined in the last twenty years, the current rates are far from reaching the anticipated Sustainable Development Goal of atmost 25 d...
Show More
-
Research Article
Statistical Test-Based Feature Selection and Classification Techniques for Breast Cancer Data
Murfia Rahman Muna,
Md. Alamgir Sarder*
Issue:
Volume 10, Issue 2, December 2025
Pages:
124-130
Received:
19 June 2025
Accepted:
7 July 2025
Published:
28 August 2025
Abstract: Breast cancer is a disease that affects the majority of women and it is the second most common cause of death among women globally. Medical scientists have proven that there are a vast number of genes that are responsible for breast cancer. Among them, all genes are not equally responsible. Therefore, the most relevant and informative genes are needed to find out to control the disease. The objectives of our study are: (i) To find the most informative and significant genes using different statistical test-based feature selection techniques (FST) as well as find the best classifier and (ii) To validate our experimental results using a simulated dataset. The breast cancer dataset is a benchmark dataset provided by Kent Ridge Biomedical Data Repository, USA. In our study, we have used different statistical test-based feature selection techniques such as the t-test and Wilcoxon signed rank sum (WCSRS) test. Naïve Bayes (NB), Adaboost (AB), linear discriminant analysis (LDA), artificial neural network (ANN), k-nearest neighbor (KNN), and random forest (RF) are treated as classification techniques. Our analysis included 24,188 genes and 97 patients. Among them, 46 patients were with cancer and 51 were in control. We considered 70% of the dataset as a training set and the rest is a test set and repeated this procedure about 1000 times. Among all the combinations of FST and classification techniques t-test-based Naive Bayes classifier gives us the highest classification accuracy. The analysis of our study indicates that the integration of t-test-based FST and Naïve Bayes classifier produces the maximum classification accuracy.
Abstract: Breast cancer is a disease that affects the majority of women and it is the second most common cause of death among women globally. Medical scientists have proven that there are a vast number of genes that are responsible for breast cancer. Among them, all genes are not equally responsible. Therefore, the most relevant and informative genes are nee...
Show More
-
Research Article
A Hybrid Machine Learning Model for Detecting and Preventing Corruption in Kenya’s Public Procurement Contracts
Issue:
Volume 10, Issue 2, December 2025
Pages:
131-136
Received:
6 September 2025
Accepted:
22 September 2025
Published:
10 October 2025
Abstract: Corruption in public procurement undermines fiscal sustainability, distorts competition, and reduces service quality. Conventional anti-corruption controls-manual audits, rule-based checks, and ex-post reviews-struggle to flag sophisticated, evolving fraud patterns in real time. This study proposes and empirically evaluates a hybrid machine-learning (ML) framework that integrates interpretable supervised models (logistic regression) with high-accuracy ensemble methods (random forest) and unsupervised learning (k-means clustering and anomaly detection) to identify corruption-prone contracts within Kenya’s public procurement ecosystem. Using secondary procurement data-contract values, procurement methods, bidder histories, award timelines-and text-derived indicators from public audit narratives, we construct features representing red flags such as single-bid tenders, repeated awards, and significant deviations from estimated costs. Logistic regression provides transparent coefficient-level evidence, while random forest captures non-linear interactions; clustering approximates high-risk groupings where labels are incomplete. Results indicate that single-bid tenders, prior supplier allegations, and execution irregularities (e.g., substandard deliveries, unusual extensions) are the most predictive factors of corruption labels. The ensemble achieved strong classification performance (AUC ≈ 0.98 on cross-validation), while the baseline logistic model offered high precision and policy-friendly interpretability. We outline a deployment roadmap for integrating the model into e-procurement workflows (IFMIS/PPRA) with explainable-AI (XAI) dashboards for risk-based audits. The contribution is twofold: a context-aware, reproducible pipeline for low- and middle-income settings, and governance guidance for embedding ML in accountability processes to prevent rather than merely detect procurement corruption.
Abstract: Corruption in public procurement undermines fiscal sustainability, distorts competition, and reduces service quality. Conventional anti-corruption controls-manual audits, rule-based checks, and ex-post reviews-struggle to flag sophisticated, evolving fraud patterns in real time. This study proposes and empirically evaluates a hybrid machine-learnin...
Show More
-
Research Article
A Project Management Framework for Implementing AI-Driven Fault Mitigation Systems
Isaac Buyondo*,
Konstantinos Kiousis
Issue:
Volume 10, Issue 2, December 2025
Pages:
137-150
Received:
22 September 2025
Accepted:
9 October 2025
Published:
12 November 2025
DOI:
10.11648/j.mlr.20251002.15
Downloads:
Views:
Abstract: The research seeks to establish a Project Management Framework for the Implementation of AI-Driven Fault Mitigation Systems by utilizing quantitative methodologies such as machine learning, in conjunction with insights from telecommunications engineers. This study integrates empirical data with practical expertise. The research was conducted using data obtained from Savanna Fibre Limited, resulting in a dataset comprising fault logs. Hybrid AI models, specifically a combination of CNN-LSTM with certain physics-based modifications, were trained and tested to detect faults at an early stage, identify the nature of the problems, locate the source of the issues, and assess the potential severity of the faults. Data preprocessing pipelines were developed to tackle challenges including imbalanced classes and sparse records of submarine cable faults, while domain knowledge also played a crucial role in guiding feature engineering and model interpretation. The framework demonstrates impressive performance: it achieves a 94.3% F1-score in fault classification, forecasts issues up to 72 hours ahead with a 92% confidence level, and accurately identifies fault locations within ±25 meters. To enhance its practicality, a versatile deployment configuration integrates model outputs into real-world workflows through CI/CD pipelines and even utilizes AR tools to assist in field repairs, resulting in a 42% reduction in repair times during actual tests. This research indicates that AI-driven, proactive maintenance is not merely theoretical; it is achievable with the appropriate data, interdisciplinary collaboration, and practical testing. Looking forward, there is significant potential to expand this approach for 5G and IoT networks or to refine our management of uncertainty in critical systems.
Abstract: The research seeks to establish a Project Management Framework for the Implementation of AI-Driven Fault Mitigation Systems by utilizing quantitative methodologies such as machine learning, in conjunction with insights from telecommunications engineers. This study integrates empirical data with practical expertise. The research was conducted using ...
Show More
