Category Archives: Uncategorized

Authors: Dr. Bayomock Linwa André Claude, Mrs. Diagone Grace

Abstract: In modern days, getting his first job is a very hard process for newly graduated students. Several factors contribute to this issue: no experience, poor resume qualities, few knowledge of job market and required skills for a given job title, no real exposure to job interview (phone, virtual, physical). In the past 30 to 50 years, structured human resources agencies played great role helping young graduates to be well prepared for job readiness. Techniques as how to write a good resume, determining job title and job profile in a particular domain, how to handle a phone, virtual and physical interview were taught to a candidate. Traditional advisory systems are often insufficient in addressing these structural issues at scale. This paper presents an AI-powered web-based career development platform designed to enhance employability among students and job seekers in Côte d'Ivoire. The built application is called DIJOB (Digitalized Job), DIJOB integrates Groq’s LLaMA 3.3-70B large language model to provide four core services: intelligent job search with AI-based CV matching, automated résumé quality assessment, skill compatibility scoring against job descriptions, and a personalized eleven-module career coaching system. The coaching module includes salary estimation in FCFA, LinkedIn profile optimization, and interview preparation guidance. The system is implemented using Jakarta EE 10, GlassFish 7, MySQL 8, and a responsive XHTML frontend, following a three-tier architecture with a RESTful API layer. Results indicate that the platform provides real-time, actionable career insights, including résumé scoring, skill gap analysis, and personalized career recommendations. DIJOB shows strong potential in improving alignment between job seekers and employer expectations, thereby contributing to reduced skills mismatch and improved employability outcomes.

DOI: http://doi.org/10.5281/zenodo.21505674

Published by: vikaspatanker

Authors: Research Scholar Krishnapriya T S, Associate Professor Dr.P Arumugam

Abstract: Inflation is one of the most significant macroeconomic indicators influencing the stability and sustainable growth of an economy. During periods of economic uncertainty, particularly the COVID-19 pandemic, inflation exhibited substantial fluctuations characterized by extreme observations and increased volatility, indicating the presence of fat-tailed behaviour. Such characteristics often reduce the effectiveness of conventional statistical measures, making robust estimation techniques essential for reliable analysis. This study investigates the behaviour of inflation in India and examines its relationship with the Reserve Bank of India's (RBI) monetary policy, represented by the repo rate, over the period from 2014 to 2022. Monthly data obtained from the Reserve Bank of India (RBI) Database on Indian Economy (DBIE) are used for the empirical analysis. To obtain a robust measure of central tendency in the presence of extreme observations, a 25% trimmed mean is employed and compared with the conventional arithmetic mean. Furthermore, a simple linear regression model is developed to examine the relationship between inflation and the repo rate, and the model parameters are estimated using the Maximum Likelihood Estimation (MLE) method. The empirical findings indicate that inflation exhibited noticeable fat-tailed characteristics during the pandemic period, while the trimmed mean provided a more stable and representative estimate than the conventional mean. The regression analysis further demonstrates a significant association between inflation and the repo rate, highlighting the effectiveness of monetary policy interventions in maintaining price stability during periods of economic uncertainty. The study concludes that robust statistical techniques, such as trimmed mean estimation combined with maximum likelihood methods, provide valuable tools for analysing inflation dynamics and supporting evidence-based monetary policy decisions.

Published by: vikaspatanker

Authors: Mr. Nikhil Barapatre, Ms. Ruchika Kadu, Mr. Uday Mahure, Ms. Vaishnavi Nawale

Abstract: The rapid advancement of digital technologies has significantly transformed the education sector by introducing intelligent learning environments, online learning platforms, Learning Management Systems (LMS), Massive Open Online Courses (MOOCs), and virtual classrooms. These technological developments generate enormous volumes of educational data that capture students' learning activities, academic performance, attendance, assignment submissions, examination scores, participation in online discussions, and interaction with digital learning resources. The availability of such educational data has created new opportunities for educational institutions to improve teaching strategies, personalize learning experiences, and enhance academic outcomes through data-driven decision-making. Learning Analytics has emerged as a multidisciplinary research field that combines Artificial Intelligence (AI), Educational Data Mining (EDM), Machine Learning (ML), Data Analytics, and statistical techniques to analyze educational data and predict student performance with greater accuracy. By identifying learning patterns and behavioral characteristics, learning analytics enables educators to provide timely interventions that support student success and reduce academic failure. Student performance prediction has become one of the most important applications of learning analytics because academic achievement directly influences educational quality, institutional effectiveness, and workforce development. Traditional evaluation methods primarily depend on periodic examinations and manual assessment, which often identify learning difficulties only after students experience poor academic performance. Such delayed identification limits the opportunity for educators to provide timely academic support. In contrast, learning analytics continuously monitors students' learning behavior throughout the educational process, enabling early detection of students who may be at risk of poor performance, course failure, or dropout. This proactive approach allows instructors to implement personalized learning strategies and academic interventions before significant learning problems occur. This research investigates the application of learning analytics for predicting student academic performance using multiple educational indicators collected from both traditional and digital learning environments. The proposed study considers a comprehensive set of predictive variables, including attendance records, assignment completion rates, quiz performance, laboratory activities, examination marks, participation in online learning platforms, classroom engagement, discussion forum activities, learning duration, assessment consistency, and demographic information.

DOI: http://doi.org/10.5281/zenodo.21486978

Published by: vikaspatanker

Authors: Maaz Bahauddin Naveed

Abstract: Research on composite materials has gradually replaced traditional materials and alloys in an effort to create effective and cost-effective solutions for a range of applications. Metal Matrix Composites (MMCs) offer several benefits over traditional composites, including a lower thermal expansion coefficient, improved resistance to wear and abrasion, a higher strength-to-weight ratio, and reduced density. This review focuses on MMCs based on aluminium, magnesium, copper, titanium, and zinc as well as their alloys. It examines their physical and mechanical properties, manufacturing techniques (such as in-situ, liquid-phase, and solid-phase manufacture), and recent advancements. The properties of MMCs have been enhanced. As a result, they are suitable for critical applications in electronics, autos, and aerospace. Significant findings show how they can overcome the shortcomings of conventional materials by improving a range of mechanical properties. Their tensile characteristics, density, thermal expansion coefficient, elasticity modulus, hardness and fracture resistance, fatigue resistance, creep stiffness, and electrical conductivity can all be enhanced by using reinforcing techniques. The text also emphasises how important it is to select the right production processes to obtain the necessary characteristics while lowering costs and defects. This evaluation is a comprehensive resource for researchers and business professionals. It highlights current advancements, challenges, and the vast potential of MMCs as future resources.

DOI: http://doi.org/10.5281/zenodo.21473843

Published by: vikaspatanker

Authors: Manjusha Chennareddy, Assistant Professor Ch. Lavanya

Abstract: The integration of Artificial Intelligence in Decision Support Systems has revolutionized the process of business strategic management through making data-driven, predictive, and adaptive decisions possible. The following paper provides an extensive analysis of AI-Driven Decision Support Systems (AI-DSS) for strategic business management, with the focus on the system architecture, implementation strategies, and results of the performance. The paper proposes a hybrid approach to implementing AI-DSS, using such methods as machine learning predictive analytics, Explainable AI, and multi-criteria decision-making. The empirical analysis shows that the implementation of AI-DSS results in improving the decision accuracy by 16.4%, decreasing decision time by 35.6%, and increasing user satisfaction by 22.8%. The comparative analysis proves that the implementation of AI-DSS outperforms the traditional approach of using spreadsheets on all measures.

DOI: https://doi.org/10.5281/zenodo.21473763

Published by: vikaspatanker

Authors: Sukeshni Moon

Abstract: Artificial Intelligence (AI) has become an important part of modern households, transforming the way people communicate, work, learn, and manage daily activities. Once considered a technology limited to research laboratories and large organizations, AI is now available to common people through smartphones, smart home devices, virtual assistants, recommendation systems, healthcare applications, and educational tools. This paper examines the evolution of artificial intelligence in homes, its advantages and disadvantages, and how it has improved the lives of ordinary individuals. It also discusses concerns related to privacy, security, dependence on technology, and ethical challenges. The study highlights that AI has the potential to make life more convenient and efficient, but responsible use and awareness are necessary to maximize its benefits.

DOI: https://doi.org/10.5281/zenodo.21469831

Published by: vikaspatanker

Authors: R.Kanimozhi, Dr.V.Maniraj

Abstract: Coconut is an economically important plantation crop whose productivity is significantly affected by leaf diseases such as Leaf Rot, Grey Leaf Spot, and Bud Rot. Early detection of these diseases is essential to reduce crop losses and improve yield. Conventional disease diagnosis through manual inspection is time-consuming, subjective, and unsuitable for large-scale plantations. This paper proposes an Attention-Based Deep Learning Framework for the early detection and classification of coconut leaf diseases. The proposed framework integrates image preprocessing, data augmentation, transfer learning, and a Convolutional Block Attention Module (CBAM) to enhance feature extraction. The attention mechanism enables the model to focus on disease-affected regions while suppressing irrelevant background information. A convolutional neural network is used to classify healthy and diseased leaf images with improved accuracy. The model is evaluated using standard performance metrics, including accuracy, precision, recall, F1-score, and confusion matrix. Experimental results demonstrate that the attention-based framework outperforms conventional CNN models in detecting early-stage disease symptoms. The proposed approach is computationally efficient and suitable for real-time deployment on mobile and edge devices. It provides an effective decision-support tool for farmers and agricultural experts, contributing to improved disease management and sustainable coconut cultivation.

DOI: http://doi.org/10.5281/zenodo.21468251

Published by: vikaspatanker

Authors: Mr. Santhosh Kumar .S, Dr.Anix joel singh

Abstract: The increasing demand for sustainable energy resources, along with growing environmental concerns related to fossil fuel consumption, has accelerated research into alternative fuels for internal combustion engines. This study focuses on the experimental investigation and performance analysis of an internal combustion engine operated with alternative fuel as a potential replacement for conventional diesel fuel. The experimental investigation was conducted to evaluate the effects of alternative fuel usage on engine performance and exhaust emission characteristics under different operating conditions. The performance evaluation was carried out based on key parameters, including brake power, torque, brake thermal efficiency (BTE), and brake-specific fuel consumption (BSFC). In addition, the emission characteristics were analyzed by measuring exhaust gases such as carbon monoxide (CO), unburned hydrocarbons (HC), oxides of nitrogen (NOx), carbon dioxide (CO₂), and smoke opacity. The results demonstrated that alternative fuel operation produced comparable engine performance with conventional diesel fuel. Variations in brake power, torque, thermal efficiency, and fuel consumption were observed due to differences in fuel properties, combustion behavior, and energy content. The alternative fuel showed a slight increase in fuel consumption due to its lower calorific value; however, it provided improved emission characteristics by reducing CO, HC, and smoke opacity emissions. A minor change in NOx emissions was observed, which was mainly associated with variations in combustion temperature and oxygen availability during the combustion process. Overall, the experimental findings indicate that alternative fuels can be effectively utilized in internal combustion engines while maintaining satisfactory performance and reducing harmful exhaust emissions. The study highlights the potential of alternative fuels as sustainable energy solutions for cleaner and more efficient engine operation.

DOI: http://doi.org/10.5281/zenodo.21468929

Published by: vikaspatanker

Authors: Bhavana N, Kumar Siddamallappa. U, Neelamma. G, Anusha Jajur. J

Abstract: Kidney disease is a significant health concern worldwide, and identifying renal abnormalities at an early stage is essential for preventing disease progression and improving treatment outcomes. Manual interpretation of medical images can be time-consuming and may vary depending on clinical expertise. To address this challenge, this study presents a convolutional neural network (CNN)-based kidney disease classification system that incorporates transfer learning with ResNet101 and VGG16 architectures. The proposed model is trained and evaluated using an augmented dataset of renal ultrasound and CT images categorized into four classes: normal, cyst, stone, and tumor. Image preprocessing and data augmentation techniques are applied to improve image quality, increase dataset diversity, and enhance the model's generalization capability. By utilizing pre-trained deep learning models, the system effectively extracts meaningful image features while reducing training time and computational complexity. Experimental evaluation shows that ResNet101 achieves a classification accuracy of 97.4% while VGG16 achieves 95.8 %. Performance assessment using precision, recall, and F1-score further confirms the reliability of the proposed approach for multi-class kidney disease classification. The developed framework demonstrates the effectiveness of transfer learning for medical image analysis, particularly when labeled datasets are limited. In addition, the system has the potential to support radiologists by providing faster and more consistent diagnostic assistance, leading to improved clinical decision-making. Overall, the proposed approach ResNet101 offers an efficient and accurate solution for automated kidney disease detection and classification using deep learning techniques.

DOI: http://doi.org/10.5281/zenodo.21453407

Published by: vikaspatanker

Authors: Geofrey Nyabuto, Peters Anselemo Ikoha, Samuel Mungai Mbuguah

Abstract: Background: Binary depression screening does not distinguish patients with mild symptoms from those with clinically urgent symptom burden. Among people living with HIV (PLHIV), depressive-symptom severity may reflect nonlinear interactions among anxiety, immune status, treatment adherence, stigma, behavioural exposures, and demographic characteristics. Routine electronic medical records (EMRs) provide an opportunity to model these relationships using computationally reproducible methods. Objective: To develop and internally validate a polynomial regression machine learning model for predicting continuous PHQ-9 depressive-symptom severity among PLHIV using routine HIV-care EMR data. Methods: A cross-sectional patient-level analytical dataset was constructed from 54,301 de-identified EMR records from Bungoma and Busia counties, Kenya. Fifteen clinical, treatment, psychosocial, behavioural, and demographic predictors were processed using training-derived imputation, encoding, log transformation, and standardisation. Stratified training (n=38,010), validation (n=8,145), and held-out test (n=8,146) partitions were used. Ordinary least-squares regression with degree-1, degree-2, and degree-3 polynomial feature expansions was compared using R², adjusted R², mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). Results: The degree-3 model comprised 816 fitted parameters and achieved the strongest held-out performance: R² 0.753, adjusted R² 0.730, MAE 1.808, MSE 6.359, and RMSE 2.522 PHQ-9 points. The linear model achieved R² 0.729, MAE 1.939, and RMSE 2.641. Mean and median cubic-model residuals were 0.040 and 0.005, respectively, although the maximum positive residual was 15.186, indicating important underprediction in a small number of high-severity cases. The largest reported terms were anxiety × CD4 (β=−0.444) and anxiety² (β=0.413). Conclusions: Degree-3 polynomial regression modestly improved prediction of PHQ-9 depressive-symptom severity over linear and quadratic alternatives. Its average error may support broad risk stratification, but threshold crossing, model complexity, coefficient instability, and severe case underprediction preclude autonomous clinical use.

DOI: http://doi.org/10.61137/ijsret.vol.12.issue4.198

Published by: vikaspatanker