Sardar Vallabhbhai Patel Institute of Technology

The electrical energy demand has been increasing day by day that’s why renewable energy sources demand highly increasing in conventional power generation. Wind energy conversion system (WECS) has cover large area due to its environmental and economic advantages. When integration between WECS and power grids, they are include some additional dynamic complexities, posing difficulties to system stability. For enhance the system stability, reliable operation and effective control mechanism for damping controller are needed. In previous years, traditional controller designed with fixed parameters and some limitation in dynamic and nonlinear wind integrated problems. In this paper we presents detail review of various damping controller design for WECS integrated power system. This review is totally based on design methodologies, including evolutionary algorithms and artificial intelligence techniques. This review also highlights the strengths, limitations and performance improvements through various techniques. In this paper we aim to give insights for researcher and engineer in developing adaptive damping controller to enhance stability in wind integrated power systems.

Predicting the stock market is a highly important yet complex challenge. Among a large variety and types of indicators used for the market trend analysis, Moving Average (MA) based indicators are one of the most widely used tools in the stock market prediction. This paper presents a comprehensive review of various moving average based trend indicators supported by the empirical evaluation done using linear regression as a one of the basic machine learning model over the National Stock Exchange (NSE) data. The main objective of the study is to evaluate the Moving Average and its variants as feature transformations across multiple lag and smoothing windows. The study validates that the moving average based filtering improves forecasting performance more significantly for short-to-medium lag structures than the long lag. Insights are presented on the behaviour and effectiveness of moving average based indicators across different scenarios, with specific attention to error reduction, overall predictive accuracy as well as directional accuracy.

Detection of aircraft in aerial imagery is a very critical issue in surveillance, air traffic control as well as defense practice. But perception of aircraft is not easy in low-resolution aerial images at cloudy weather conditions because of low visibility, noise and interference of the background. To overcome these issues, the proposed research is the effective aircraft detection solution, which will be in the form of the YOLOv11n object detecting model. The suggested framework is expected to improve the performance of the detection in the weather-degraded aerial images by the proper acquisition of the spatial features in the low-quality images. This model was trained over 300 epochs using an annotated aerial dataset, which has aircraft images taken in different weather conditions, especially in cloud covered ones. The results of the experiment prove that the developed approach has an average Precision ( mAP 50 ) of 98.65, which means high accuracy in detection and resilience to unfavorable atmospheric conditions. YOLOv11n is also lightweight architecture, which guarantees efficient computation and fast inference and thus can be applied in real-time aerial surveillance. The findings confirm that the suggested solution is an effective way to increase the reliability of aircraft detection under problematic weather conditions and potential support of intelligent surveillance in remote sensing and aircraft security areas.

The escalating global burden of type 2 diabetes mellitus (T2DM) demands robust, interpretable, and privacy-preserving predictive frameworks that can operate reliably in federated clinical environments. Existing machine learning (ML) approaches for diabetes prediction are predominantly developed on single, demographically constrained datasets and lack mechanisms for transparent clinical decision support. This study introduces an Explainable Federated Machine Learning (EFML) framework that integrates five classification algorithms—Logistic Regression, Support Vector Machine (SVM), Random Forest, XGBoost, and Multi-Layer Perceptron (MLP)—applied to the Pima Indians Diabetes dataset with systematic preprocessing, domain-driven feature engineering, and multi-strategy class imbalance remediation. The proposed framework incorporates SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) as dual-layer explainability components, enabling both global and instance-level transparency. The MLP model achieved the highest classification accuracy of 88.6% with an AUC of 0.91, while XGBoost delivered superior precision-recall balance (F1 = 0.80, AUC = 0.83) with markedly lower computational overhead. SHAP analysis confirmed glucose concentration, BMI, and insulin resistance indices as the dominant predictive biomarkers. The study further delineates a federated learning integration pathway for privacy-compliant multi-institutional deployment using the FedAvg protocol, contributing a deployable, regulation-aware blueprint for AI-augmented diabetes screening systems.

Over the past ten years, India’s trash production has grown at the same rate as the country’s growth. Lots of trash is being generated because of more people living in cities, more factories, and changes in people’s living standards. This trash causes damage to the environment and the economy. Trash, which includes dry trash, wet trash, hazardous trash, and industrial trash, has grown along with the country’s growth. The current technologies for Waste to Energy projects include Incineration, Bio-methanation/Bio-CNG plants, Composting, and Gasification plants. This document presents the status, advantages, and disadvantages of each technology. To address this issue, efficient solid waste management, especially the recycling of materials, is crucial for sustainability. Thermochemical technologies have arisen as an effective and sustainable approach for transforming various waste materials into useful products, including fuels and chemicals. These are feasible methods to address the rising population and industrial expansion. Pretreatment methods have been used into waste conversion processes to improve energy generation. This study contributes to a better understanding of India’s solid waste management and helps lawmakers and practitioners come up with effective and long-lasting waste management policies for the country.