Journal of Science Engineering Technology and Management Science

The 360 - degree performance appraisal is a powerful multi-dimensional competence development tool that draws upon the knowledge of an individual within his own circle of influence: supervisors, peers, and direct reports. A review of successful organizations reveals that many are using 360 - degree appraisal for modern competence development, reinforced by similar systems for administrative performance appraisal. Research on 360 - degree appraisal reveals effectiveness conditions, design and implementation considerations, and some categories of potential benefits. The Simple random sampling was used in this study. The primary data was collected through questionnaire and analyzed with the help of statistical tool namely Percentage analysis. The findings of the study and recommendation are mentioned. It is concluded that majority of employees have the positive angle towards the prevailing performance appraisal.

Keywords :

Author : Nomula Mahendra Keerthi , (Dr) R Srinivasa Rao

Title : 360 DEGREES PERFORMANCE APPRAISAL AT BERGER PAINTS INDIA LIMITED

Volume/Issue : 2025;02(7(1))

Page No : 643-648

Mutual fund investment has lot of changes in the recent past, and investor’s mentality and their expectation are changing in the present scenario. Investor’s preference towards return, risk varies often. The investor should compare the risks and returns before investing in a particular fund. For this, he should get the advice from experts and consultants and distributors of mutual fund schemes. The investors can invest in the mutual fund and can be to get more benefits. Periodically checking up on how the mutual fund is doing is important, and there are lots of measures that the investor can use to perform the checking. A funds track record may be the single most important factor that an investor checks before opting for a mutual fund product. Hence evaluating funds is important before investing. But it is becoming increasingly important for investors to take note of other parameters too, while deciding between mutual funds. Of course, investors need to weigh the savings on expenses against the performance record before choosing a fund. Over the past decades mutual funds have grown intensely in popularity and have experienced a considerable growth rate. Mutual funds are popular because they make it easy for small investors to invest their money in a diversified pool of securities. As the mutual fund industry has evolved over the years, there have arisen many questions about the nature of operations and characteristics of these funds. Thus the fund evaluation process helps the investors to know more about the funds and its performance.

Keywords :

Author : Nyavanandi Chandhana, Dr K MADHU BABU

Title : MUTUAL FUNDS ON COMPARATIVE ANALYSIS AT ICICI DIRECT LTD

Volume/Issue : 2025;02(7(1))

Page No : 649-656

This study analyzes the financial metrics of several companies, including Adani Enterprise Ltd, ITC Ltd, HDFC Bank Ltd, Axis Bank Ltd, Wipro Ltd, and BPL Ltd, focusing on their average returns, variance, risk, and coefficient of variance. The findings reveal diverse risk profiles among the companies, with varying levels of average returns and risk. While some companies exhibit moderate risk levels, others demonstrate higher levels of risk. Negative average returns are prevalent across many companies, signaling challenges in generating positive returns over the observed period. The coefficient of variance provides insights into risk relative to return, urging cautious interpretation. The study underscores the importance of considering risk tolerance, investment goals, and time horizon when selecting investments and advocates for diversification to manage portfolio risk. It emphasizes the significance of evaluating long-term prospects, growth potential, and fundamental strength of companies for building a resilient investment portfolio. Continuous monitoring and periodic review of investment strategies are recommended, with a suggestion for investors to seek advice from financial professionals for tailored guidance. In essence, informed decision-making and a disciplined investment approach are crucial for navigating financial markets effectively and achieving investment objectives amidst inherent risks.

Keywords :

Author : Oggu srilatha, Dr G Sudhakar

Title : CAPITAL MARKET IN EQUITY AT SHAREKHAN STOCK BROKING LTD

Volume/Issue : 2025;02(7(1))

Page No : 657-664

The purpose of this study is to determine factors of work stress among the Data angle Technologies Pvt Ltd of the employees. This study also aims to determine whether there were any statistically significant differences in the respondents’ level of work stress by demographic factors (gender, status, education qualification, job position and length of service). The findings of this study showed that there was no statistically significant difference in the level of work stress by demographic factors (gender, status, education qualification, job position and length of service). However, the findings showed that only organizational factors have significant relationship with work stress level. Findings of this study also resulted in the overall level of work stress among respondent is moderate.

Keywords :

Author : P. Vaishnavi , (Dr) D Sushma Kiran

Title : STRESS MANAGEMENT AT DATA ANGLE TECHNOLOGIES PVT LTD

Volume/Issue : 2025;02(7(1))

Page No : 665-671

Food supply chain management is a critical domain in agriculture and retail industries, aiming to ensure the efficient production, transportation, and delivery of food products to consumers. In India, the food supply chain faces challenges such as excessive wastage, demand-supply mismatches, and delays in logistics. Reports suggest that 40% of food produced in India is wasted annually due to inefficiencies, costing the economy around ?92,000 crores ($12 billion). With rising demand due to population growth (expected to reach 1.6 billion by 2050), addressing inefficiencies is vital for food security and economic sustainability. To develop a machine learning-driven solution for optimizing food supply chain management by accurately forecasting demand using historical data and contextual features, minimizing food wastage, and improving resource allocation. Traditional system like Historical Averages predicting demand based on previous years' average sales. Rule-Based Systems like using static rules for inventory management and procurement. Human Intuition Manual forecasting by managers based on experience, often prone to errors and biases. Problems statement like fail to account for dynamic market conditions such as price fluctuations, seasonality, and promotional activities. These systems result in overproduction, underutilization, and wastage of resources, leading to significant economic losses. Motivation is the growing complexity of food supply chains, driven by urbanization, changing consumer preferences, and climate variability, necessitates the adoption of smarter forecasting techniques. The proposed system leverages a CNN regressor to revolutionize food supply chain management by extracting spatial and temporal features from historical and contextual data for precise demand forecasting. Convolutional layers capture patterns such as seasonality, promotions, and regional dynamics, enabling accurate weekly demand predictions for various meals. This enhances inventory optimization by aligning stock levels with forecasted demand, minimizing wastage. Additionally, the system facilitates dynamic pricing by accounting for pricing trends and promotional activities, while optimizing logistics by predicting demand patterns across supply chain nodes. By integrating CNN regressors, the system ensures accurate demand forecasts, reduced food wastage, and improved resource allocation, fostering efficient decision-making in pricing and inventory management.

Keywords : Driver Demand Prediction, Time Series Analysis, Convolutional Neural Network, Demand Forecasting in Logistics

Author : B. Ramesh, Nidhi Jadhav, Sai Charan Darshanam, Akash Rathod

Title : Smart Demand Forecasting: Time Series-Driven Ensemble Modelling for Optimizing Rideshare and Food Delivery Services

Volume/Issue : 2025;02(7(1))

Page No : 333-341

?abdabrahma, the identification of language (?abda) with the ultimate metaphysical principle (Brahman), is a key concept in Bhartr?hari’s V?kyapad?ya. It signifies a profound shift in understanding the relationship between language, thought, and reality. This paper critically examines the ontological, linguistic, and philosophical aspects of ?abda as the Absolute, viewing it not only as a means of expression but also as the essence of being, cognition, and consciousness. Bhartr?hari challenges the traditional distinction between word and world by presenting ?abda as an indivisible, self-manifesting reality from which all phenomena arise. Through analysing the Spho?a doctrine, the fourfold expression of v?k - Par?, Pa?yant?, Madhyam?, and Vaikhar? – and his critique of atomistic and referential linguistic models, the study presents Bhartr?hari’s vision of language as both immanent and transcendent. In this perspective, ?abda functions as both a pram??a (a valid source of knowledge) and a prameya (the object of knowledge), thus blurring the boundaries between epistemology and ontology. Using primary texts, classical commentaries, and comparative analysis with M?m??s?, Ny?ya, and Advaita Ved?nta, the paper asserts that Bhartr?hari’s concept of ?abdabrahma anticipates a non-dualistic semiotic metaphysics where actualising the ultimate truth involves recognising language as the foundation of all existence

Keywords : ?abdabrahma, V?kyapad?ya, Spho?a, Advaita, Sabda-tattva, Sabda-v?da, Para, Pasyanti, Madhyama and Vaikhari.

Author : DR. BABULI NAIK

Title : THE CONCEPT OF ?ABDABRAHMA: LANGUAGE, CONSCIOUSNESS, AND NON-DUAL REALITY IN BHARTR?HARI’S V?KYAPAD?YA

Volume/Issue : 2025;02(7(1))

Page No : 672-678

Coal mining is one of the most hazardous industries, where workers are constantly exposed to life-threatening risks such as toxic gas leakage, fire, flooding, rock falls, and lack of ventilation. Traditional monitoring systems in mines are often manual, delayed, and incapable of providing real-time data, which results in accidents and casualties. To address these challenges, this project proposes an IoT and Wireless Sensor Network (WSN) based coal mine monitoring system that ensures continuous, real-time, and remote surveillance of underground conditions.The system integrates multiple sensors including gas sensors (for methane, carbon monoxide, and carbon dioxide), temperature sensors, humidity sensors, and pressure sensors, which are deployed in the mining environment and connected through a WSN framework. The sensor data is transmitted wirelessly to a central gateway, which forwards it to the IoT cloud platform. Using cloud connectivity, the collected data is visualized and analyzed in real time on a web dashboard or mobile application, enabling remote monitoring by authorities. Additionally, the system triggers automatic alerts and notifications via SMS, email, or app notifications in case of abnormal parameters such as high methane concentration, low oxygen level, or sudden temperature rise, thereby reducing response time and enhancing worker safety.This IoT-WSN based coal mine monitoring system ensures scalability, energy efficiency, and low-cost deployment while providing a predictive safety mechanism that improves decision-making and prevents disasters. By combining the capabilities of IoT and WSN technologies, the system creates a reliable and intelligent safety framework for modern coal mining operations

Keywords :

Author : S.Chandrabhanu, T.Sumadhuri, G.Sanjana, K.Tejasri, M.Bhavani

Title : COAL MINE MONITOR USING IOT AND WSN TECHNOLOGY

Volume/Issue : 2025;02(7(1))

Page No : 679-686

Healthcare is one of the most critical sectors where continuous patient monitoring can play a significant role in saving lives. Traditional health monitoring systems often require patients to be physically present in hospitals, leading to delays in diagnosis and treatment during emergencies. To address this limitation, this work proposes an IoT-based Health Monitoring System using Raspberry Pi that enables real-time remote monitoring of vital signs. The system employs biomedical sensors such as heart rate, temperature, blood pressure, and SpO? sensors, which are interfaced with the Raspberry Pi microcontroller. These sensors continuously capture patient health parameters and transmit the data to a cloud server or web application using Wi-Fi.The Raspberry Pi acts as the processing hub, collecting, analyzing, and forwarding sensor data for visualization and storage. Doctors and caregivers can access this information remotely via a secure web dashboard or mobile application, allowing for early diagnosis and timely medical intervention. In critical situations, the system can automatically generate alerts or notifications via SMS/Email to medical professionals and family members, ensuring rapid response.The proposed IoT-enabled solution provides a low-cost, scalable, and efficient health monitoring framework that reduces hospital visits, supports remote patient care, and improves overall healthcare accessibility. By combining Raspberry Pi, IoT, and cloud computing, this system contributes toward the development of smart healthcare solutions, paving the way for personalized and preventive healthcare services in both urban and rural areas

Keywords :

Author : A.Haripriya, K.Sandya, T.Esha, P.Pooja, A.Pallavi

Title : IOT BASED HEALTH MONITORING SYSTEM USING RASPBERRY PI

Volume/Issue : 2025;02(7(1))

Page No : 687-695

Road accidents are a major global concern, leading to significant loss of life, property damage, and delayed emergency response. Traditional accident detection methods often rely on eyewitness reporting, which results in time delays that can worsen casualties. To address this challenge, this paper proposes a Real-Time Accident Detection and Reporting System using Internet of Things (IoT). The system integrates smart sensors such as accelerometers, gyroscopes, GPS, and vibration sensors with a microcontroller to detect sudden impacts, abnormal vehicle motion, or rollovers that indicate an accident. Once an accident is detected, the system automatically collects critical information including location coordinates, speed, and impact force, and transmits it to a cloud server through a wireless communication module (e.g., GSM/4G, LoRa, or Wi-Fi). This data is then instantly relayed to emergency services, nearby hospitals, and registered contacts, ensuring rapid response.The proposed IoTenabled framework eliminates human dependency in accident reporting, reducing the time gap between accident occurrence and medical assistance. Additionally, the system can be integrated with traffic management systems for enhanced road safety and real-time monitoring. By leveraging IoT, cloud computing, and intelligent communication, this solution aims to minimize fatalities, improve emergency response times, and enhance overall road safety.

Keywords :

Author : P.Swamy, K.Akhila, D.Vijaya Laxmi, G.Sadhalaxmi, T.Navaneetha

Title : REAL TIME ACCIDENT DETECTION AND REPORTING USING IOT

Volume/Issue : 2025;02(7(1))

Page No : 696-704

Vehicle-to-Vehicle (V2V) communication protocol is an emerging technology in the field of Intelligent Transportation Systems (ITS) that enables vehicles to exchange real-time information such as speed, location, direction, and traffic conditions. By establishing a wireless communication link, usually based on Dedicated Short-Range Communication (DSRC), 5G, or Cellular-V2X (C-V2X), vehicles can share critical safety and mobility data with one another to reduce accidents, improve traffic efficiency, and enhance driver awareness. The protocol defines standardized communication rules that ensure interoperability among different manufacturers and vehicles, thereby creating a reliable vehicular network. V2V communication supports applications such as collision avoidance, lane-change assistance, traffic congestion management, and emergency vehicle prioritization. With growing advancements in IoT and AI, V2V is expected to play a crucial role in enabling autonomous driving and the development of fully connected smart transportation systems.

Keywords :

Author : K.Deepa, T.Samatha, N.Sravani, Ch.Hemalatha, Beena Sahu

Title : VEHICLE TO VEHICLE COMMUNICATION PROTOCOL

Volume/Issue : 2025;02(7(1))

Page No : 705-712

The detection and classification of banknotes are crucial tasks for preventing financial fraud, especially counterfeit currency circulation. This project proposes an efficient machine learning (ML)-based system to classify and detect the authenticity of banknotes using their statistical features. By training models such as Support Vector Machines (SVM), Random Forest, and KNearest Neighbors (KNN) on attributes like variance, skewness, kurtosis, and entropy extracted from images of banknotes, the system achieves high accuracy in distinguishing genuine and forged notes. The solution aims to assist financial institutions and ATM systems in automating the validation process with real-time results and minimal human intervention

Keywords :

Author : T.Sruthi, D Mamatha, R Navya, S Sravani, K Sravani, D Bhuvaneshwari, N Shravani

Title : CLASSIFICATION AND DETECTION OF BANK NOTES USING ML

Volume/Issue : 2025;02(7(1))

Page No : 713-720

The integration of Artificial Intelligence (AI) into healthcare training systems has revolutionized the way medical and support staff, especially crew members in critical environments such as hospitals, emergency response units, and even aviation medical teams, are trained and assessed. This project focuses on the development and application of an AI-driven system to enhance the training process of healthcare crew members, ensuring they receive personalized, adaptive, and data-driven instruction. The system utilizes machine learning algorithms to analyze trainee performance, identify knowledge gaps, and provide real-time feedback through intelligent tutoring mechanisms. It incorporates natural language processing for simulated patient interaction, computer vision for gesture and procedure recognition, and predictive analytics to evaluate long-term skill retention and readiness. By automating the monitoring and evaluation of training sessions, the AI system not only reduces the dependency on human instructors but also standardizes the training outcomes across varied scenarios. The proposed solution aims to improve the efficiency, accuracy, and effectiveness of healthcare crew training, ultimately leading to better patient care and safety

Keywords :

Author : G.Vinoda, A Manasa, S Saritha, A Naveena, Y Chandini, D Sandhya

Title : APPLICATION OF AI SYSTEM IN THE PROCESS OF CREW TRAINING HEALTH CARE

Volume/Issue : 2025;02(7(1))

Page No : 721-726

Nowadays, malware has become a more and more concerning matter in the security of information and technology proven by the huge increase in the number of attacks seen over the past few years on all kinds of computers, the internet and mobile devices. Detection of zero-day malware has become a main motivation for security researchers. Since one of the most widely used mobile operating systems is Google’s Android, attackers have shifted their focus on developing malware that specifically targets Android. Many security researchers used multiple Machine Learning algorithms to detect these new Android and other malwares. In this paper, we propose a new system using machine learning classifiers to detect Android malware, following a mechanism to classify each APK application as a malicious or a legitimate application. The system employs a feature set of 27 features from a newly released dataset (CICMalDroid2020) containing 18,998 instances of APKs to achieve the best detection accuracy. Our results show that the methodology using Random Forest has achieved the best accuracy of 98.6% compared to other ML classifiers.

Keywords :

Author : P. Renuka, K Rajeswari, U Madhumathi, S Surekha, K Sunitha, K Sreelatha

Title : ANDROID MALWARE DETECTION USING ML

Volume/Issue : 2025;02(7(1))

Page No : 727-733

As the problem of urban traffic congestion intensifies, there is a pressing need for the introduction of advanced technology and equipment to improve the state-of-the-art of traffic control. The current methods used such as timers or human control are proved to be inferior to alleviate this crisis. In this paper, a system to control the traffic by measuring the real-time vehicle density using canny edge detection with digital image processing is proposed. This imposing traffic control system offers significant improvement in response time, vehicle management, automation, reliability and overall efficiency over the existing systems. Besides that, the complete technique from image acquisition to edge detection and finally green signal allotment using four sample images of different traffic conditions is illustrated with proper schematics and the final results are verified by hardware implementation.

Keywords :

Author : A.Sushmitha, B Anupriya, M Ratnamala, C Prasanna, N Mamatha, V Chandana

Title : DENSITY BASED SMART TRAFFIC CONTROL SYSTEM USING EANNY EDGE DETECTION ALGORITHM

Volume/Issue : 2025;02(7(1))

Page No : 734-741

The real estate sector is one of the most dynamic and data-rich investment domains, yet it traditionally relies on manual assessments and intuition-based decision-making. With the advent of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL), investment management in real estate is undergoing a transformative shift. This study explores how intelligent technologies can be leveraged to enhance the accuracy, efficiency, and profitability of real estate investment strategies.The research applies predictive modeling to historical property data, economic indicators, market trends, and customer behavior to forecast price appreciation, rental yields, and investment risks. ML algorithms such as Random Forest, Gradient Boosting, and Support Vector Machines are used to analyze factors influencing property values across residential, commercial, and industrial segments. Additionally, clustering techniques are applied to segment locations and property types based on investment potential. Sentiment analysis using Natural Language Processing (NLP) helps assess market sentiment by mining news articles, social media, and buyer reviews.Further, Deep Learning models such as LSTMs are employed to perform time-series analysis of real estate prices, enabling long-term trend forecasting and early detection of market shifts. Image-based DL models also support property condition assessment using aerial and on-site photographs. The findings suggest that integrating AI, ML, and DL into investment management not only improves forecasting precision but also automates routine analysis, reduces decision-making bias, and enhances portfolio performance.This study concludes that intelligent investment systems can empower real estate investors—whether individuals, developers, or institutions—to make datadriven, timely, and optimized decisions, ultimately maximizing returns while managing risks in a volatile market environment.

Keywords :

Author : S.Swathi, Ragiri Manisha, R.Srilekha

Title : INVESTMENT MANAGEMENT IN REAL ESTATE

Volume/Issue : 2025;02(7(1))

Page No : 742-750

Financial modeling forms the backbone of strategic decision-making in the investment banking sector. Traditionally based on spreadsheets and historical data analysis, financial modeling has evolved significantly in the wake of digitization and algorithmic intelligence. This study explores the multifaceted applications of financial modeling in investment banking, focusing on equity valuation, mergers and acquisitions (M&A), leveraged buyouts (LBO), and risk management. As capital markets become more dynamic and complex, the reliance on traditional models becomes insufficient to capture real-time fluctuations and high-volume data analytics. Hence, this research integrates contemporary technological advancements, including machine learning (ML) and deep learning (DL), to develop predictive financial models. Using historical stock data, economic indicators, financial statements, and macroeconomic trends, this study employs supervised learning models such as Random Forest, Support Vector Machines (SVM), and LSTM (Long Short-Term Memory) networks for sequence prediction. The results demonstrate that AI-enabled models provide more robust, adaptable, and forward-looking financial insights compared to legacy models. Ultimately, the study proposes a hybrid ML-DL-based financial modeling framework that can be embedded into investment banking software to assist analysts and stakeholders in making more informed and data-driven decisions.

Keywords :

Author : S.Chaitanya, Shaik.Aseen Babu, A.Srikanth

Title : FINANCIAL MODELING FOR INVESTMENT BANKING

Volume/Issue : 2025;02(7(1))

Page No : 751-758

The financial statement analysis of a company serves as a vital instrument in assessing its performance, sustainability, and long-term value creation for stakeholders. In this research, we conduct a detailed financial statement analysis of Hero MotoCorp Ltd., the world’s largest manufacturer of two-wheelers, by integrating conventional ratio analysis with advanced software-enabled techniques, including machine learning (ML) and deep learning (DL). The purpose of this hybrid framework is to not only evaluate historical and current financial performance but to also develop models that can forecast future trends, detect anomalies, and support strategic decision-making. Traditional financial analysis is often constrained by human interpretation, limited dimensions, and backward-looking metrics. To counter this, we utilize intelligent systems that leverage historical data, industry variables, macroeconomic factors, and financial indicators to build predictive models. ML algorithms such as Random Forest and SVM assist in classification and regression tasks, while deep learning models like LSTM offer robust forecasting capabilities. The integration of NLP-based sentiment analysis further enriches insights drawn from financial news and earnings calls. This approach is novel in the Indian automotive context and provides Hero MotoCorp with a framework for automated financial monitoring, credit risk profiling, and strategic planning. Our results highlight how data science and financial expertise can converge to create intelligent platforms that reduce decision latency and increase financial accuracy, thereby setting a new benchmark in corporate finance.

Keywords :

Author : S.Raj Kumar, M.Rajeshwar Reddy,R.Gowthami

Title : FINANCIAL STATEMENT ANALYSIS OF HEROMOTOCORP

Volume/Issue : 2025;02(7(1))

Page No : 759-767

The COVID-19 pandemic has had a seismic impact on global economies, social systems, and industrial frameworks. Among the most affected domains was entrepreneurship—a sector known for innovation, flexibility, and economic stimulation. As lockdowns, travel bans, and social distancing measures disrupted supply chains and consumer behavior, many entrepreneurial ventures faced existential threats. Yet, in the shadow of crisis, a wave of digital innovation emerged, reshaping the entrepreneurial ecosystem across the globe. This paper explores the duality of the pandemic’s impact—devastation on one hand, and digital reinvention on the other. Startups and small businesses that survived or thrived during the pandemic shared one common factor: rapid technological adoption. Entrepreneurs began integrating Machine Learning (ML) and Deep Learning (DL) models to forecast demand, assess risks, personalize customer engagement, and automate logistics. Software solutions enabled businesses to move online, manage remote teams, automate inventory, and deliver digitally. Entrepreneurs in EdTech, HealthTech, AgriTech, and E-commerce adopted AI tools, mobile applications, cloud platforms, and low-code development environments to continue operations and enter new markets. This research delves into the magnitude of these transformations, using quantitative and qualitative analysis, real-world startup case studies, and insights from modern technological implementations. It concludes that the entrepreneurial landscape post-COVID is deeply technological, adaptive, and data-centric.

Keywords :

Author : S.Manirud, Arun Reddy, K.Archana

Title : IMPACT OF COVID-19 ON ENTREPRENEURSHIP

Volume/Issue : 2025;02(7(1))

Page No : 768-779

The establishment of banks in rural areas has long been a strategic imperative aimed at inclusive economic growth, poverty alleviation, and financial empowerment. However, persistent challenges such as poor infrastructure, low financial literacy, high operational costs, and limited customer bases have hindered rural banking penetration. This study examines these traditional obstacles and investigates how contemporary solutions—especially software-driven innovations like Machine Learning (ML), Deep Learning (DL), mobile banking apps, and cloud-hosted micro services—are transforming the rural financial landscape. We employ a mixed-method research design combining surveys of rural residents, interviews with banking professionals, and ML-powered data insights. Our findings highlight key barriers such as connectivity gaps, regulatory complexities, trust deficits, and cash-dependent cultures. Yet, through pilot digital schemes, AI-based credit scoring, agent networks supported by mobile apps, and predictive analytics for crop financing, rural banking is gaining momentum. This paper offers policy insights, architectural frameworks, and practical recommendations to scale digital-friendly rural banking services sustainably

Keywords :

Author : Subhangi Yadav, Ragiri Manisha, R.Srilekha

Title : PROBLEMS OF ESTABLISHMENT OF BANK IN RURAL AREAS

Volume/Issue : 2025;02(7(1))

Page No : 780-787

Income inequality remains one of the most pressing socio-economic challenges in India. While India has made remarkable progress in various development indicators over the past few decades, the economic benefits have not been equitably distributed across different sections of society. A complex interplay of structural, historical, and policy-related factors contributes to persistent disparities in income across caste, gender, religion, region, and educational backgrounds. This study aims to investigate the depth, determinants, and dynamics of income inequality in India by combining traditional economic analysis with modern computational tools such as Machine Learning (ML) and Deep Learning (DL). We use a comprehensive dataset drawn from national surveys and government records to analyze income distribution and socio-economic correlates. Statistical tools, regression analysis, clustering, and neural networks are applied to model and interpret the inequalities. The novelty of this study lies in its interdisciplinary approach, where we integrate Artificial Intelligence (AI) techniques with socio-economic theory to simulate real-world scenarios and forecast future trends in inequality. By training ML algorithms on demographic and economic data, we identify key predictors and build forecasting models. We also use DL models for understanding non-linear relationships, image-based poverty mapping, and time-series projections. Our findings can aid policymakers, economists, and technocrats in designing data-driven, inclusive, and sustainable solutions to curb income inequality in India.

Keywords :

Author : Thaduri Divya, M.Rajeshwar Reddy, R.Gowthami

Title : A STUDY OF INCOME IN EQUALITY IN INDIA

Volume/Issue : 2025;02(7(1))

Page No : 788-796

Artificial Intelligence (AI) in Smart Agricultural Facilities (SAF) often lacks explainability, hindering farmers from taking full advantage of their capabilities. This study tackles this gap by introducing a model that combines eXplainable Artificial Intelligence (XAI), with Predictive Maintenance (PdM). The model aims to provide both predictive insights and explanations across four key dimensions, namely data, model, outcome, and end-user. This approach marks a shift in agricultural AI, reshaping how these technologies are understood and applied. The model outperforms related studies, showing quantifiable improvements. Specifically, the Long-Short-Term Memory (LSTM) classifier shows a 5.81% rise in accuracy. The eXtreme Gradient Boosting (XGBoost) classifier exhibits a 7.09% higher F1 score, 10.66% increased accuracy, and a 4.29% increase in Receiver Operating Characteristic-Area Under the Curve (ROC-AUC). These results could lead to more precise maintenance predictions in real-world settings. This study also provides insights into data purity, global and local explanations, and counterfactual scenarios for PdM in SAF. It advances AI by emphasising the importance of explainability beyond traditional accuracy metrics. The results confirm the superiority of the proposed model, marking a significant contribution to PdM in SAF. Moreover, this study promotes the understanding of AI in agriculture, emphasising explainability dimensions. Future research directions are advocated, including multi-modal data integration and implementing Human-in-the-Loop (HITL) systems aimed at improving the effectiveness of AI and addressing ethical concerns such as Fairness, Accountability, and Transparency (FAT) in agricultural AI applications.

Keywords :

Author : Vanam Gopinath

Title : PREDICTIVE MAINTENANCE IN SMART AGRICULTURAL FACILITIES WITH AN EXPLAINABLE AI MODEL

Volume/Issue : 2025;02(7(1))

Page No : 797-801

Secure storage model for digital forensics represents essential progress in the domain, addressing the major problems associated with protecting and maintaining digital evidence. This method employs recent encryption systems and optimal key generation methods to ensure the confidentiality and integrity of data throughout the investigative process. Cloud forensics is an intelligent development of digital forensics to be preserved against online hacking. But, centralized evidence gathered and preservation reduces the reliability of digital evidence. The architecture for digital forensics in an Infrastructure as a Service (IaaS) cloud platform is a crucial structure intended to simplify the collection and protection of evidence while preserving the integrity and origin of digital objects within cloud-based methods. This architecture integrates numerous modules and methods to address the exclusive tasks modeled by cloud computing (CC) environments in the framework of forensic investigations. This paper develops a new digital forensic architecture utilizing the Authentication with Optimal Key Generation Encryption (DFA-AOKGE) technique. The main intention of the DFAAOKGE method is to use a BC-distributed design to allocate data between numerous peers for data collection and safe storage. Additionally, the DFA-AOKGE model uses the Secure Block Verification Mechanism (SBVM) for the authentication procedure. Also, the secret keys can be produced by the usage of the Enhanced Equilibrium Optimizer (EEO) model. Furthermore, the encryption of the data takes place using a multikey homomorphic encryption (MHE) approach and is then saved in the cloud server. The simulation value of the DFA-AOKGE methodology takes place in terms of different aspects. The simulation results exhibited that the DFA-AOKGE system shows prominent performance over other recent approaches in terms of different measures.

Keywords :

Author : Shyamala Nagajyothi

Title : OPTIMAL KEY GENERATION AND AUTHENTICATION FOR A SECURE STORAGE MODEL TO ENHANCE DIGITAL FORENSIC SECURITY

Volume/Issue : 2025;02(7(1))

Page No : 802-812