Vol. 1, Issue 2 • 2026
Rahul Soni, Bhinal Mehta, Mihir Bhatt, Raymon Antony Raj, Bishal Silwal, Rahman Azis Prasojo, M. M. F. Darwish, Norazhar Abu Bakar, Sherif S. M. Ghoneim
Power transformers are an essential part of smart city infrastructure and are also one of the most expensive components in this type of infrastructure. The insulation of the transformers is made from mineral oil and cellulose, both of which can deteriorate as a result of multiple stresses (electrical/mechani- cal/thermal/chemical). This paper presents a new computational model for mak- ing asset decisions that incorporates various significant variables, including dis- solved gas analysis (DGA), water content, furan levels, interfacial tension, and degree of polymerization. Different stresses on its insulating structure are also analyzed using contour plots and surface viewers. To test and validate this expert model, 200 transformer’s data driven analysis is used. Gas ratio techniques, the Duval Triangle technique, the degree of polymerization and furans-based paper deterioration, the moisture and IFT-based insulation degradation, and other dis- solved gas analysis-based diagnostic procedures are used and its shows the higher accuracy analysis and efficiency for incipient faults diagnosis and analysis with AI based computational intelligence.
Siddharth Kumar, Aaqib Abdullah, Maneet Singh
Stress impacts students in a great number of ways, influencing not only how they feel but also their in-class performance and the management of day-to-day responsibilities. Actually measuring it, though, is difficult because most measures rely on self-reporting by students, which often lacks reliability. In this work, we investigate whether machine-learning methods can contribute to better stress level predictions based on data from a short online survey. The online survey consisted of basic demographic information, a few questions related to lifestyle, and all 21 items of the University Stress Scale (USS). It yielded a total of 110 completed responses. Four widely used classification models, namely Logistic Regression, Support Vector Machine (SVM), Random Forest, and XGBoost, were trained on three feature combinations to investigate the individual and combined contributions of psychological and non-psychological variables to the prediction. Their performance was estimated using Accuracy, Weighted F1-Score, and Matthews Correlation Coefficient (MCC). In all the experiments, the greatest contribution towards raising the quality of the prediction was made by the psychological features, while among the different models, the best results were obtained using the XGBoost model. We have also compared the self-reported stress of students with their stress categories computed from the USS and found significant mismatches between the two. These point to the suspicion that personal judgment may not reflect the actual stress pattern. These results indicate that a combination of structured psychological scales and machine-learning methods may provide a more reliable approach to understanding student stress.
Sumedha Dangi, Deepak Kumar, Vipin Khurana
Deep learning pipelines play a crucial role in the perception, planning, and control of autonomous vehicles (AVs). The optimization method, which gov- erns the effectiveness of models in learning and generalizing within dynamic en- vironments, represents a crucial yet underexplored component of these pipelines. Existing techniques, including SGD, Adam, and hybrid variations like BAAO and GASGD, remain static throughout the training process and are unable to adapt to the diverse conditions of the real world. By utilizing training inputs such as gradient variance and convergence rate, we present a Meta-Optimization Framework for Fault Prediction (MOCAFP) that functions as an adaptive con- troller, selecting and refining optimizers in a dynamic manner. The assessment of the system involved four datasets, which comprised both simulated and real- world driving environments: Udacity Jungle, Udacity Lake, KITTI, and a real- world Urban Roads dataset. Experimental results indicate that MOCAFP demon- strates superior performance compared to baseline optimizers regarding conver- gence speed and learning stability. Specifically, it achieves competitive training durations while enhancing the coefficient of determination (R2) by 12%, decreas- ing prediction variance by 15%, and minimising mean absolute error (MAE) by as much as 18%. The enhancements indicate that MOCAFP serves as a depend- able and scalable method for advancing fault prediction in AV pipelines.
Shubham Gupta, Meenu Gupta
The traditional methods of identifying academically at-risk students often include manual assessment and a retrospective analysis, both of which are time-consuming and are not predictive. In order to overcome these challenges, this paper suggests using machine learning techniques to develop a predictive analytics framework for student performance and dropouts that is based on Explainable Artificial Intelligence (XAI). The method proposed combines data preprocessing, feature selection, and predictive modeling using XGBoost and explainability using SHAP to make accurate and interpretable predictions of students' academic performance. This study uses the “Predict Students' Dropout and Academic Success” data set from the UCI Machine Learning Repository, which includes demographic, academic, financial, and institutional data for 4,424 students. Various machine learning algorithms, such as Decision Tree, Support Vector Machine (SVM), Random Forest, and XGBoost models, were applied and compared based on the following performance metrics: Accuracy, Precision, Recall, F1 score, and ROC-AUC score. The experimental results showed the proposed XGBoost model has higher accuracy, precision, recall, F1 score, and ROC-AUC score (94.18%, 93.74%, 93.21%, 93.47%, and 95.62%, respectively). In addition, curricular unit performance, admission grades, and tuition fee payment status were the most important factors for student academic outcomes and dropout that were identified through SHAP-based explainability analysis. The proposed framework facilitates the identification of academically at-risk learners at an early age and helps to make intelligent decisions with transparent and interpretable analytics. The results show that the suggested system can be very useful in educational institutions to improve student retention, provide better academic support mechanisms, and lower dropouts due to proactive intervention systems.
Nisha Pal, Sanjay Kumar, Anurag Tomar, Pakhi Rajpoot, Aakanshi Garg, Shayan Ahmad
Deep learning has majorly taken over the field of computer vision, especially with regard to spotting objects in images. Models based on Convolutional Neural Net- works, or CNNs, have totally altered the situation. Instead of spending hours and hours selecting the features manually, models just do it by themselves. Object detection is not only limited to recognizing objects in an image, It is also about determining the exact locations of them. This has become important for applications such as autonomous vehicles, medical imaging tasks, security cameras, and even smart shopping systems. However, there exists a problem. Deep learning models require massive, varied datasets in order to perform well. The process of collecting images and labeling. It is costly and time consuming. The place where data augmentation comes in. People use many methods such as image flipping, image rotating, cropping or brightness changing to extend their raw datasets. It is quite helpful, but those changes are very simple. They do not handle for example the case in which one object is in front of the other or that there are complex backgrounds or poor lighting or even that some categories are barely present in the data. Therefore, models are still struggling with the disorder that exists outside the lab. The idea was taken to create a more intelligent data augmentation pipeline. The idea is to make training data look more like authentic. It means that changes that matter most for the task should be added, context should be mixed in, and occlusions should be simulated. So, the model will learn better patterns, not get stuck on the training data and just be able to perform better in the real world.