Stella Mary's College of Engineering is a private engineering college located in Azhikal, Kanyakumari District, India. The college was established in the year 2012 by Dr. Nazerath Charles, an entrepreneur and founder of Nova Educational Trust. The college offers both undergraduate and post-graduate courses in engineering.
This research study simulates the behavior of all the components of a multi-port DC/DC converter with Sliding Mode Control (SMC) for energy flow in an electric vehicle. The converter is a bidirectional single-way DC-DC converter with a fixed 48V battery and a 400V DC link, so that the energy can be transmitted in both directions during the charging and discharging process. Since the converter is a nonlinear system, the dynamics of the converter were modeled in MATLAB/Simulink to check the performance under different loads. The surface sliding slope of SMC law is determined by the current and voltage deviations between the real and the desired value. This control ensures that the switching trajectory does not exceed the sliding boundary and the steady state error will be low thus reducing overshoot. The response time of the converter is 15 ms, and the results are overshoot of 25.04% and oscillation less than 1.8%. It provides an overall efficiency of 96.2% and a total harmonic distortion (THD) of the current of 2.84%. The control system with gradient of 9.5 10-8 attains steady state in 569 cycles. The results show the smooth operation under load change, indicating that SMC has good performance in voltage regulation, current sharing, and load adaptation.
In recent years, digital financial transactions have grown rapidly worldwide, especially via bank ATM cards, credit or debit cards, digital wallets, and payment gateways. This growth increases the risk of financial fraud, as traditional rule-based detection systems are limited and public awareness of protecting sensitive banking information is low. This study explores AI-driven solutions for fraud detection. A survey-based analysis was conducted among banking customers in Oman’s Al Dhahirah Region to examine perceptions of trust, accuracy, privacy, and transparency in AI-based systems. Based on the analysis, a novel framework combining federated learning and explainable AI is proposed to enhance fraud detection accuracy while preserving customer data privacy and improving model interpretability. The results provide a foundation for secure, transparent, and privacy-preserving AI-driven fraud detection systems in banking and fintech sectors, offering actionable insights for future implementation.
Gastrointestinal (GI) tract diseases pose significant challenges to medical professionals due to their complex nature and diverse manifestations. This study presents a novel approach to tackle these challenges by integrating advanced deep learning techniques. The proposed method employs an Inception-Residual based Deep Convolutional Neural Network (IRDCNN) for the automated classification of colorectal cancer. Initially, the input image undergoes contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the visibility of infected regions. Through extensive training on annotated datasets, proposed model learns to identify the colorectal cancer with high accuracy and reliability. By automating the classification process, the proposed approach streamlines the diagnostic workflow, enabling faster and more efficient detection of colorectal cancer. Overall, the proposed IRDCNN-based framework represents a promising avenue for enhancing the diagnosis of colorectal cancer with achieving accuracy of 96.8%, ultimately contributing to improved healthcare delivery and patient care.
Electric vehicles (EVs) are increasingly becoming crucial components of both transportation and energy sectors, necessitating efficient charging to support their growing use. A promising solution is integration of EV charging system with photovoltaic (PV) panels. This is because it offers cost savings, promotes environmental sustainability, and benefits from the continuous advancements in PV module efficiency. This research presents an innovative EV charging system with a novel Bidirectional Cuk converter and a bio-inspired Social Spider Optimized Proportional Integral (SSO-PI) controller. The proposed converter supports in managing the voltage flow between EV battery and grid, enabling charging and discharging operation. The SSO-PI controller effectively regulates the converter and offers better system performance with faster response time and stable control. Additionally, grid system is incorporated to charge EV battery at times of energy demand or failure of PV system. This integration ensures EV battery remains charged using either PV or grid supply, enhancing reliability and system sustainability. The proposed work modelled and simulated using MATLAB to validate its EFFICIENCY. Simulation outcomes reveals that the proposed accomplishes an enhanced efficiency of 96.38
