This research presents a novel architectural paradigm for digital image and video processing systems, featuring an integrated graphical user interface component designed to facilitate interactive operation. The framework integrates multiple image processing techniques including edge detection, smoothing, geometric transformations, morphological operations, seg- mentation, enhancement, color space manipulation, and noise management within a cohesive environment. The implementation leverages computer vision libraries and modern GUI components to provide real-time visual feedback, mathematical equation display, and intuitive parameter control. Experimental evaluations demonstrate the effectiveness of the framework for both educational purposes and practical image analysis tasks. The system’s modular architecture enables extensibility and facilitates incorporation of additional algorithms. Performance analysis indicates the framework maintains interactive response rates across various processing operations while providing high- quality output. This integrated approach addresses the need for accessible, comprehensive tools in digital image processing education and research.

Keywords : Image Processing, Interactive GUI, Edge Detection, Segmentation, Image Enhancement, Color Processing.

Authors : R. Chaitanyaraju

Title : A Comprehensive Digital Image and Video Processing Framework with Interactive Graphical User Interface

Volume/Issue : 2025;7(4 (July - August))

Page No : 54 - 59

Encryption makes it possible to send private information via unprotected channels without worrying about data loss or modification by unauthorized parties. For data security in various contexts, many encryption algorithms have developed throughout time. This paper focuses on symmetric encryption, often used for key exchange due to its large key size. In the context of data centers and cloud computing, security is paramount. This paper proposes a quantum computing algorithm for encrypting cloud data. This combination leverages quantum computing's rapid complex computations. The quantum computing algorithm offers fast, efficient, and secure data protection in cloud environments, reducing computational power requirements while enhancing overall efficiency. Moreover, it addresses the limitations of traditional encryption methods and provides a scalable solution for large-scale data encryption. By integrating quantum computing, we can achieve unprecedented levels of security and performance. The potential impact of this approach could revolutionize data protection standards in the cloud industry.

Keywords : Encryption, Cloud Computing, Security, Quantum Computing, Data Protection Standards.

Authors : SUJANA

Title : Advancing Cloud Data Protection with Cryptographic Algorithms

Volume/Issue : 2025;7(4 (July - August))

Page No : 47 - 53

Kidney diseases such as cysts, stones, and tumors are among the most prevalent health issues worldwide. Early and accurate diagnosis is critical to preventing severe complications, and computed tomography (CT) imaging plays a key role in this process. However, manual interpretation of CT scans is time-consuming and prone to subjectivity. To address this, we propose a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) units for the automated multiclass classification of kidney diseases using CT images. The CNN component extracts spatial features from the input scans, while the LSTM layers model spatial dependencies and enhance the learning of complex patterns. The model was trained and evaluated on a curated dataset consisting of four kidney conditions: Cyst, Normal, Stone, and Tumor. Extensive experimentation demonstrates that the proposed CNN- LSTM model achieves a classification accuracy of 99.6%, with precision, recall, and F1-score values exceeding 99% across all classes. Additionally, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed for model interpretability, enabling visualization of discriminative regions in the images responsible for predictions. The results indicate the potential of the model to serve as a reliable decision-support tool for radiologists and clinicians. This framework paves the way for enhanced diagnostic accuracy and faster clinical workflows in nephrological imaging.

Keywords : Admin, Jobseeker/Student, Recruiter/Company, MERN Stack, Online Assessments.

Authors : Dillibabu

Title : Automated and Explainable Kidney Abnormality Detection from CT Images Using CNN-LSTM Architecture

Volume/Issue : 2025;7(4 (July - August))

Page No : 39 – 46

This project is an interactive job and internship portal developed using the MERN stack with custom Admins, Jobseekers/Students, and Recruiters/Companies modules. The portal has been designed to transform the recruitment industry by eliminating the inefficiencies of the conventional recruitment procedures and creating a hassle-free, user-friendly portal. By incorporating advanced features like individualization-based job suggestions, web-based testing, and live application status, the portal provides maximum convenience and transparency to all the stakeholders. Admin module provides a good group of admin features with functionality to enable recruiters to control recruiter activity, user registrations, and job postings. This has the advantage of data integrity, system security, and simplicity of platform functions. Job candidates, via the User module, can establish extensive profiles, find the right job by qualification, and be suggested by skill and interest level. They can also attempt online tests organized by the recruiters, inquire about the application status, and receive real-time feedback on their performance during the recruitment procedure. The Recruiter module aids organizations in job posting functionalities, designing and administering web-based tests, and efficiently screening candidate resumes. Test scores and candidate qualifications are now utilized by recruiters to make the hiring decision, making the recruitment process more streamlined. Development was carried out through a platform incorporating MERN stack that combines MongoDB with Express.js and React.js and Node.js —such a setting supports the latest web technology in delivering optimum performance, scalability, and interfaces. It tackles the diversity of recruiter and applicant requirements through abilities such as recommendations based on skill and web tests that simplify recruitment and make the process more streamlined. The project not only meets the requirement of filling the gap for end-to-end recruitment but also raises the challenge of compliance with next-gen technology in next-gen recruitment trends.

Keywords : Admin, Jobseeker/Student, Recruiter/Company, MERN Stack, Online Assessments.

Authors : K S JAYANTH

Title : Smart Hire : A Platform To Bridge Freelancers and Software Projects

Volume/Issue : 2025;7(4 (July - August))

Page No : 31 – 38

Predicting the length of hospital stay (LOS) is critical for improving healthcare resource management and patient care. This study investigates the application of explainable machine learning techniques to forecast hospital stay duration using a dataset from Kaggle, comprising various patient and hospital-related features. The primary goal is to develop accurate predictive models and elucidate the underlying factors influencing hospital stay lengths. The study employs multiple machine learning algorithms, including Logistic Regression, Multi-Layer Perceptron (MLP), Random Forest, Gradient Boosting, and XGBoost. Each model's performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-score. Additionally, explainability tools such as SHapley Additive exPlanations (SHAP) are utilized to interpret model predictions and identify the most significant predictors of LOS. The findings demonstrate that advanced machine learning models, particularly ensemble methods, achieve superior predictive accuracy. Moreover, the explainability analysis provides valuable insights into the critical factors influencing hospital stays, thereby enabling healthcare practitioners to make informed decisions and optimize hospital resource allocation. This research underscores the potential of integrating explainable machine learning into healthcare analytics to enhance operational efficiency and patient outcomes

Keywords : Hospital Stay Length, Machine Learning, Logistic Regression, MLP, Random Forest, XGBoost, SHAP.

Authors : SATHYA LAHARI

Title : Predicting Hospital Stay Length Using Explainable Machine Learning

Volume/Issue : 2025;7(4 (July - August))

Page No : 25 – 30

Stroke remains one of the foremost causes of mortality and long-term disability worldwide. Early prediction of stroke is crucial in enabling timely medical interventions and minimizing its adverse outcomes. This study presents a robust ensemble- based machine learning framework that integrates the predictive strengths of XGBoost, a Multi-Layer Perceptron (MLP), and a hybrid Bidirectional LSTM-GRU neural network to enhance the accuracy of stroke prediction. The model is trained and validated using a publicly available healthcare dataset containing a diverse set of clinical and demographic features such as age, hypertension, heart disease, smoking status, and body mass index (BMI). Comprehensive data preprocessing steps, including missing value imputation, feature encoding, and class balancing using Random Over Sampler, were implemented to prepare the dataset for training. Each individual model was optimized for performance and then combined in an ensemble using weighted averaging to maximize generalization and robustness. The pro- posed ensemble model demonstrated superior performance with an accuracy of 94.58%, precision of 90.64%, recall of 99.45%, F1- score of 94.84%, and an impressive ROC-AUC score of 98.73%. The high recall indicates that the model is particularly effective in identifying stroke-positive cases, which is critical in a clinical setting. The confusion matrix and classification report further support the model’s reliability and effectiveness. Additionally, visualization techniques such as ROC curves, precision-recall curves, and calibration plots confirmed the model’s strong predictive confidence. Feature importance analysis highlighted the significant impact of variables such as age, hypertension, and BMI. This ensemble framework presents a powerful tool for clinical decision support, with potential deployment in real- time health monitoring systems for early stroke detection and intervention.

Keywords : Stroke Prediction, Ensemble Learning, XG- Boost, MLP, Bidirectional LSTM-GRU.

Authors : INDIRAPRIYADARSHINI

Title : Ensemble Deep Learning Approach for Stroke Prediction Using Healthcare Data

Volume/Issue : 2025;7(4 (July - August))

Page No : 18 – 24

With the increasing global energy demand and the depletion of fossil fuel resources such as coal, lignite, oil, and natural gas, there is a pressing need to explore and expand renewable energy sources. Particularly in countries like India, power shortages and grid transmission issues are prevalent. Among renewable energy sources—solar, wind, biomass, and tidal—solar energy stands out due to its wide availability and eco-friendly nature. However, solar photovoltaic (PV) systems often face limitations in efficiency and grid integration compared to other renewable sources. This paper presents a simulation and analysis of a photovoltaic (PV) panel system integrated with a high-efficiency boost converter. The converter is designed to significantly increase the output voltage from the PV panel to levels suitable for grid connection. The proposed converter takes an input of 15V and successfully boosts it to 55.64V, demonstrating effective voltage amplification. This design is a step towards making PV systems more practical and efficient for real-world applications.

Keywords : AC Module, Coupled Inductor, High Step-Up Voltage Gain, Single Switch

Authors : T. Anvitha

Title : Efficient Photovoltaic Energy Production Using High Step Up Voltage Converter

Volume/Issue : 2025;7(4 (July - August))

Page No : 11 -17

Concerned citizens might be reassured that this research examines a deep learning method for identifying fraud in online recruitment. Traditional systems for spotting rising fraud trends predominantly depend on rule-based screening, rendering them susceptible. In comparison to alternative methods, deep learning models, especially CNNs and RNNs, exhibit superior performance in identifying bogus job advertisements. The research utilizes a database of real and fabricated job adverts to derive pertinent textual and metadata for categorization objectives. A hybrid deep learning model integrates an attention mechanism with LSTM techniques to improve detection accuracy. The experimental findings indicate that the proposed model surpasses existing machine learning techniques in accuracy and reliability. The model's stability and generalizability are assessed through multiple datasets. Researchers may explore explainable AI systems for fraud detection in the future. This research significantly aids in the development of dependable online job boards.

Keywords : Deep Learning, Fraud Detection, Online Recruitment, Job Scams, CNNs, RNNs.

Authors : K.S.ASIF MOHIDDIN

Title : Deep Learning based Detection of Fraud in Online Recruitment

Volume/Issue : 2025;7(4 (July - August))

Page No : 5 – 10

Neurological disorder primarily caused by the depletion of dopamine a neurotransmitter essential for regulating movement and coordination. As dopamine-producing cells in the brain’s basal ganglia deteriorate, individuals begin to experience symptoms such as tremors, muscle stiffness, speech difficulties, and postural instability. Early signs like finger tremors often affect handwriting, leading to micrographic a condition where writing becomes small and cramped. This subtle change can serve as a key indicator for early detection. However, diagnosing PD in its initial stages remains challenging due to the lack of definitive clinical tests. With the evolution of artificial intelligence, particularly deep learning, the potential for early and accurate diagnosis has significantly improved. Convolutional Neural Networks (CNNs) and transfer learning methods now enable the automated analysis of medical data, including handwriting patterns. These approaches have shown exceptional accuracy and promise in identifying PD, offering hope for better symptom management and timely intervention.

Keywords : Disease, SVM, Parkinson’s Disease, Deep Learning, ML, AI.

Authors : Manoj Kumar

Title : A Hybrid Deep Learning Approach for Early Parkinson’s Detection from Handwriting

Volume/Issue : 2025;7(4 (July - August))

Page No : 1 - 4