Browse Items (16481 total)
Sort by:
-
An Integrated Approach to Green Cloud Solutions for Energy-Efficient Sustainable IT and Carbon Footprint Reduction
Cloud computing has become a very important part in everyday life, but this has also made a lot of carbon footprint because of the energy consumption in the data centers. The pandemic had affected these emissions, and they quickly came back, which has shown the requirement for sustainable solutions which will help in fighting the increase in carbon footprint. For these problems, the green computing technology will give probable solutions by promoting the technology that would be responsible enough to decrease these effects of harming environment. It will have techniques like smarter system designs, operations that are energy efficient, and smart techniques for optimization. This study explores how the above set principles can reduce the overall digital carbon footprint and help to create economically viable businesses. This approach provides a forward path for technology progress and profitability aligning with the environment sustainability which is a necessary component for business longevity. 2025 IEEE. -
Enhancing Diagnostic Precision in Lung Cancer Detection Using Smote-Based Balancing Techniques
Worldwide, Lung cancer is the primary cause of death from cancer, and chances of surviving are considerably raised by early detection. While traditional diagnostic approaches heavily rely on imaging and specialized infrastructure, they often fail to serve low-resource or early screening environments. In this work, based on deep learning, lightweight framework for detecting lung cancer from structured survey data is presented. The research tackles the prevalent the problem of class disparity using the Synthetic Minority Over-sampling Technique (SMOTE), enhancing the sensitivity of predictive models. A comparative evaluation was conducted across six models Logistic Regression, SVM, KNN, Naive Bayes, Random Forest, and XGBoost. Among these, Random Forest and XGBoost achieved 95% accuracy, 0.98 recall, and ROC-AUC scores of 0.9943 and 0.9835 respectively. The proposed hybrid ensemble model (Random Forest + XGBoost) outperformed all with 96% accuracy, 0.95 precision, 0.98 recall, and a ROC-AUC score of 0.9961. These findings demonstrate that the hybrid strategy is effective in providing high diagnostic precision using clinical survey data that is not imaging. 2025 IEEE. -
Fraud Prevention in Banking: Machine Learning-driven Approaches for Detecting Payment Anomalies
The fast-paced development of digital banking has brought with it new convenience but also tremendous challenges in maintaining transaction security. Banks are confronted with mounting threats from malicious activities like identity theft, account takeover, and unauthorized access, which can lead to huge financial losses and loss of customer confidence. This study investigates the formulation of a cybersecurity framework for fraud prevention in banking through machine learning algorithms. A transactional real-world dataset of 200,000 instances from LOL Bank Pvt. Ltd. was used to construct and evaluate predictive models. Preprocessing included categorical encoding, temporal feature engineering, and synthetic minority oversampling (SMOTE) for class imbalance handling. Three machine learning classifiers - Logistic Regression, Random Forest, and XGBoost - have been compared using measures of accuracy, precision, recall, F1-score, and ROC-AUC. Results show that ensemble models significantly outperformed logistic regression by a wide margin, with Random Forest and XGBoost both achieving over 91% accuracy and very good discrimination power. The study emphasizes how well machine learning-based systems detect theft in real time and outlines avenues for future research to enhance detection using adaptive and interpretable AI models. 2025 IEEE. -
Synergistic Hybrid Segmentation for Handwritten Kannada Word Recognition Addressing Deep Learning Challenges
The handwritten Kannada script has an intricate aksharas that are formed by combining consonants, vowels, and ottus. These complex combinations pose significant hurdles for automated text segmentation. The inherent diversity in handwriting styles, coupled with prevalent character overlap, multi-touch connections, varied curve structures such as upper open curve(OC), upper closed curve (CC), and the highly condensed nature of Ottaksharas, routinely blurs character boundaries, leading to severe segmentation errors that propagate and compromise overall recognition accuracy. A hybrid approach that customizes adaptive traditional methods like vertical pixel count, to identify true character gaps in handwritten Kannada characters could effectively manage character overlap, or segment multi-touch characters or Ottaksharas. This pre-processing stage can allow subsequent deep learning models to recognize this segmented character. This will avoid significant hurdles: immense data requirements for pixel-level annotations, high computational costs for dense prediction, and significant architectural complexities for precise boundary delineation and handling connectivity. Given these constraints, particularly with less-resource language like Kannada, scaling deep learning models will lead to ever erroneous recognition. This paper argues that modified traditional approaches, by directly embedding customized knowledge and leveraging targeted feature engineering, can offer a computationally efficient and data-lean alternative. This strategy enables more robust segmentation for complex Kannada characters, providing a practical pathway for automated handwritten text processing in such linguistic domains. 2025 IEEE. -
Utilizing Transforming Portfolio Management Through Automation Using Advanced Deep Reinforcement Learning Algorithms for Optimized Investment Strategies
This paper focuses on the future possibility of enhancing the applications of DRL in autonomously managing a portfolio for better investment plans. Having used past financial data and a highly developed case of DRL, the proposed system shows better performance compared to conventional investment strategies and indices. This process includes data gathering from the financial databases, the steps of preprocessing and feature extraction, and the use of the DQN structure. After that, the system's training and validation are done by a finite portion of real-world data and a large number of synthesized data to improve stability. The result shows that the new method achieves superior cumulative return, Sharpe ratio, maximum drawdown, and annualized volatility; therefore, it suggests that the proposed system can flexibly predict the fluctuating stock market trends and make appropriate investment decisions. Thus, the present research adds importance to the use of DRL in improving return potential and risk management in portfolio management. Thus, this study adds to the existing literature and practice by allowing for the automation of the optimization and testing for investment solutions at a larger scale, while opening up opportunities for future developments in the application of financial technology and investment tools. 2025 IEEE. -
Optimizing Retail Operations with Big Data-Driven Insights: From Inventory Management to Personalized Marketing
In this paper, we look into the role of big data analytics in the strategic transition of retail businesses particularly on inventory management, supply chain and marketing. Using such technologies as big data and machine learning, retailers can find new patterns within such information that can lead to improved efficiency, and satisfaction of consumers. The study also shows noteworthy performance gain in areas of stock out and overstock, inventory Turns and delivery correctness. Even more, the approach to the customer targeting, that stemmed from the principles of the customer segmentation and recommendation systems, led to the growth of the conversion, customer loyalty, and customer lifetime value. The research evidence suggests that information-based management strategies contribute to organizational performance and sustained competitive advantage of firms operating in the retail sector. Issues like data integration, privacy and infrastructural, components are also addressed and hence making it easy form the basis of any future learning and trying out on the real life challenges. The current research focuses on the significance of big data for designing growth and innovation strategies in the changing retail environment. 2025 IEEE. -
Scalable AI Models for Real-Time Ethical Decision-Making in Autonomous Business Operations
This study explores the application of scalable AI for real-time ethical decision-making in autonomous business running. The study takes into an account the crucial concerns i.e., the bias, fairness, robustness etc., working on the congruency of ethics and operational efficiency. This research investigates AI's impact on decision quality through a series of analyses interpreting visuals (in the form of decision accuracy comparisons, stakeholder satisfaction, and resilience when facing adversarial scenarios). Results show that scalable AI models display higher ethical adaptability and an ability to learn from changing regulatory and operational environments. The research emphasises the need for proper balance of morals and technological advancement in order to enable transparency, accountability, and reliability in autonomous devices. 2025 IEEE. -
Detecting Abusive Comments in Mizo: A Machine Learning Approach for a Low-Resource Language
The detection of abusive language in online spaces is crucial for ensuring a safe digital environment, particularly for low-resource languages like Mizo. Mizo, a tonal Tibeto-Burman language spoken primarily in Mizoram, India, poses significant computational challenges due to its phonetic complexity and limited linguistic resources. This research presents a method based on machine learning for abusive comment detection in Mizo, addressing the lack of annotated datasets and specialized NLP tools. A structured pipeline involving data collection, preprocessing, feature engineering, and model evaluation was implemented. Our study compares the effectiveness of several conventional machine learning methods, such as Random Forest, Support Vector Machines (SVM), Logistic Regression, and XGBoost, against transformer-based models such as Multilingual BERT(mBERT) and MizBERT. According to experimental data, MizBERT achieves the highest accuracy and F1-score, outperforming all other models by a substantial margin. This work contributes to the development of computational tools for Mizo NLP, laying a foundation for automated moderation systems and fostering digital inclusivity for Mizo-Speaking communities. 2025 IEEE. -
IoT Enabled Patient Monitoring System with Fall Detection
The growth in demand for remote and prolonged healthcare monitoring has led to a strong growth in adoption of wearable technologies and Internet of Things -based solutions. These technologies are meant to help solve real-time health supervision challenges, particularly for older adults and those suffering from long-term conditions, through reduced need for constant onsite medical care. Here, we describe the design and deployment of an intelligent health monitoring system that utilizes low-cost sensors and wireless communication to enable real-time, continuous monitoring of important physiological and environmental parameters. The suggested system combines an array of sensors: the DHT11 sensor to measure environmental temperature and humidity, the MAX30102 sensor for heart rate and SpO2 monitoring in real-time, and the MPU6050 sensor to sense body posture, orientation, and motion. The sensors are connected to an ESP8266 Wi-Fi MCU, which serves as the hub node for data sensing and transmission. Sensor data that is aggregated is processed locally and then sent to a cloud-based platform for analysis, storage, and visualization. To improve the functionality of the system, the system utilizes a cloud-hosted rule-based Artificial Intelligence (AI) engine for interpreting physiological patterns, identifying signs of abnormal health conditions at an early stage, and offering context-aware, personalized health suggestions. The platform provides dual output modes for added accessibility and reliability: an OLED display for local feedback, and an offdevice cloud dashboard for caregivers and health workers to view patients in real time. This study demonstrates the potential for the integration of embedded systems, cloud computing, and light AI methods to make predictive health analytics and facilitate proactive healthcare interventions possible. Through emphasizing modular design, low power, and scalability, the system is particularly suitable for deployment in elderly care, post-surgery recovery, and chronic disease management. Experimental assessments suggest that the system offers a credible, cost-efficient alternative. 2025 IEEE. -
Semantic-Contextual Automation of Scriptless BDD Testing for Intelligent Test Coverage Enhancement
This work proposes a framework to improve test automation for Android applications using Behavior-Driven Development (BDD). It addresses the challenges posed by dynamic user interfaces, complex view hierarchies, and unstable locators by capturing user interactions through browser-mirrored Android screens. The framework integrates AI-based widget classification, image-based object detection, and dynamic XPath generation to enhance locator reliability. Test scenarios-including positive, negative, and boundary cases are structured in JSON and automatically converted into BDD feature files, increasing test coverage and minimizing redundancy. Automation of script generation and locator healing reduces manual effort while improving scalability, accuracy, and efficiency in test case management. The optimized validation pipeline supports comprehensive scenario generation and accelerates functional testing, thereby improving software quality in dynamic Android environments. 2025 IEEE. -
Explainable AI for Diabetic Retinopathy Screening: Enhancing Clinician Trust in Deep Learning Predictions
Diabetic retinopathy (DR) remains a leading cause of preventable blindness worldwide, with early detection being critical for effective intervention. While deep learning models have demonstrated exceptional performance in automated DR screening, their black box nature has limited clinical adoption due to concerns about interpretability and trust. This paper presents a comprehensive explainable AI (XAI) framework that integrates multiple visualization techniques, including Gradient-weighted Class Activation Mapping (Grad-CAM), attention mechanisms, and feature attribution methods, to provide clinically meaningful explanations for DR predictions. We evaluate our approach on the publicly available EyePACS and Messidor-2 datasets, achieving 94.3% accuracy while generating interpretable heatmaps that highlight lesion-specific regions. A clinical validation study involving 15 ophthalmologists demonstrates that our XAI-augmented system increases diagnostic confidence by 23% and reduces review time by 31% compared to non-explainable models. Our findings suggest that transparent AI systems can effectively bridge the gap between algorithmic performance and clinical trust, paving the way for broader adoption of AI-assisted DR screening in healthcare settings. 2026 IEEE. -
Exploring AI-Driven Accessibility Solutions: A Comprehensive Study on Assistive Tools for the Visually Impaired
Artificial intelligence (AI) has significant access to visually impaired persons, which enables more freedom in digital interactions. This article examines the role of AI-operated equipment, including chatbots, speech recognition, and natural language processing (NLP) models, to improve communication, education, and navigation for blind users. It undergoes the largest progress of AI-driven accessibility solutions, especially in examination and interactive virtual scriptures. Despite the remarkable progress, challenges in speech remain accreditation accuracy, user interface targeted, and real -time treatment efficiency. The study highlights the ongoing research trends, identifies significant intervals, and emphasizes the need for better training data, adaptive AI interfaces, and improved user experience to promote more inclusion in education and the professional environment. 2026 IEEE. -
Enhancing Human Resource Management With Fuzzy Logic and Neural Networks for Personalized Performance Management
Human resource management (HRM) encounters that is making more challenging some exact, fair and person related performance appraisals on a large scale. Traditional methods often fail to capture the richness of human behaviour and tend to be opaque to interpretation. The proposed study contributes a new hybrid approach of Fuzzy Logic and Neural Network for enhanced personalized performance management. The facts are presented qualitatively by the fuzzy inference system in linguistic terms while for numerical features, the neural network analyses such that it can find complex relationship patterns. This methodology ensures the simplicity and high predictability. The model trained on Kaggle dataset achieved an accuracy of 94.7%, F1-score of 0.942, precision of 0.945, recall of 0.940 and AUC-ROC of. 976 which were higher compared to baseline approaches like Logistic Regression and Decision Trees respectively. The solution helps HR professionals make sense of relevant information into employee performance and developmental needs, which are highlighted in real time. The results suggest that combining rule-based reasoning and machine learning enhances personalisation and offers more transparent human resources practices. This study provides a foundation for the next generation of intelligent HRM systems enabling adaptive decision support in various organizational settings. 2026 IEEE. -
IoT and Supply Chain Management: Enhancing Efficiency and Security through Smart Technologies
By offering real-time visibility, increased efficiency, and better security, the Internet of Things (IoT) is revolutionizing supply chain management, this paper investigates. IoT devices enable seamless connectivity between products, warehouses, and logistics networks, allowing businesses to manage inventory, forecast demand, and prevent theft or fraud. Examining case studies of IoT implementations in supply chains, the article explores how data-driven insights maximize logistics, lower running costs, and lower risk-profile. It also suggests ways to improve IoT security in supply chains and tackles the security issues raised by IoT like data leaks and illegal access. IoT-based Supply Chain Management (SCM) solutions notably increase operational efficiency, cost reduction, security, inventory correctness, responsiveness, data processing time, downtime, energy consumption, scalability, and customer happiness, according the comparison table. IoT solutions save costs by 30% and have 95% efficacy-a 26.67% improvement over conventional systems. With only one documented security event year instead of five in conventional systems, security is also enhanced. Response time to disturbances drops and inventory accuracy rises as well. IoT solutions additionally provide 400% scalability increase. 2025 IEEE. -
Integrating Sustainable Development Goals (SDGs) into Corporate Marketing Strategies: A Technological Approach to Responsible Business
The navigation of businesses increased sustainability with integrated conscious marketplace integration of Sustainable Development Goals in strategies of corporate marketing has emerged as the crucial driver of the business practices. The study explores the company's leveraging technology for aligning the marketing efforts using the objectives of SDG that fosters brand trust for long-term, competitive advantage and stakeholder engagement. The study examines the impact of digital innovation includes artificial intelligence Internet of Things and blockchain technology to promote consumer awareness, ethical sourcing and transparency. Moreover, the present study highlights the case examples of corporations with successful embedded SDG principles in the Framework of marketing to demonstrate the advantages of branding with technological approach to responsible business. Integration of Sustainability in the corporate narratives Using technology driven marketing and the businesses can enhance the environmental and social impact as well as it can strengthen the consumer loyalty based on ethical considerations to shape the purchasing behaviours. A novel approach is developed for integration of SDG in corporate marketing and compared with conventional marketing and the achievement has been recorded. The findings of the study show the importance of strategic marketing enabled with technology for corporate sustainability communication that can emphasise aligned marketing with business necessity. 2025 IEEE. -
Using Recurrent Neural Networks to Forecast Climate Change: A Time Series Analysis of Global Temperature Variability
Predicting the upcoming weather instances is very crucial. It depends on different climatic parameters like humidity, pressure, temperature, etc. In this paper, the historical data of the weather in the India area is used for future weather instances of the India for farmers' convenience in terms of the agricultural instance which depends on the weather and, functioning according to that which will restore the energy. For weather forecasting we have use the machine learning algorithm and probabilistic predictions of the predictive analytics based on soft computing and. NGBoost algorithm and. Linear models of the machine learning for predictive. Comparative weather incidence spaced on the historical data. We have also used, sliding window algorithm of the statistics for predicting the ideology of the concept of different contrasted windows and year. We've also used utility thirds and machine learning algorithm, classified for predicting the weather based on different features The overall implementation in this paper, shows the accuracy which we have gathered from the data set. An implementation of algorithm which ranges between 80% to 90% and the entire algorithm have been compared based on the feature instances. Work can be concluded on the measurement of the algorithm, which we have got after the implementation of Models. Which rely upon the different data features and thus it can be beneficial for preserving the energy and materials in the India agriculture area and forecasting the weather as per day Agricultural conditions. 2025 IEEE. -
AI-Driven Enhancements in Indian Payment Systems: A Futuristic Perspective on Financial Applications and Modifications
This study explores the application of machine learning (ML) to improve Indian payment systems, with a focus on AI-driven developments for tasks including fraud detection, transaction validation, and consumer behaviour research. We evaluate the effectiveness of several machine learning (ML) systems, including K-Nearest Neighbours (KNN), Random Forest (RF), Decision Trees (DT), Support Vector Machine (SVM), and Logistic Regression (LR), using a variety of criteria. The results, which include precision, F1 score, accuracy, recall, and AUC, show how well Random Forest and Logistic Regression work to detect fraudulent transactions. Important elements including transaction amount, payment method, and user behaviour patterns are also revealed by the feature importance evaluation. Significant differences exist between models in terms of training times and hyperparameter optimisation outcomes. All things considered, this study highlights how ML models can spur innovation in Indian payment systems, enhancing security, effectiveness, and consumer satisfaction while offering a thorough assessment structure for potential future implementation in the fintech industry. 2025 IEEE. -
Analyzing the Impact of Blockchain Technology on Financial Transactions and Accounting Practices in Global Trade
Financial transactions and accounting practises in global trade are transformed using blockchain technology with enhanced security efficiency and transparency. The study examines the role of Blockchain in real time financial reports smart contracts and cross border transactions by highlighting the potentiality to ensure regulatory compliance streamlined reconciliation process and fraudulence reduction. Decentralisation of financial data using blockchain enable record keeping a stamper proof and also minimises the transaction cost and the intermediaries and to accelerate the settlement times. The study explores the challenges such as integration regulatory uncertainties and scalability in the existing financial system. The study involves trade finance platforms and multinational corporations in reshaping the financial management and accounting standards using blockchain adoption in the global trade. The study employs mixed method approach for quantitative and qualitative analysis based on the ability of the blockchain to enhance the financial transactions in global trade. 2025 IEEE. -
Lightweight Zero Trust Access Control with Behavior-Based Anomaly Detection in Cloud
As cloud services become more popular, static security models must give way to dynamic, identity-centric ones. This paper introduces a serverless AWS architecturebased Lightweight Zero Trust Access (LZTA) framework with Behavior-Based Anomaly Detection (BBAD) designed for the cloud. Through the use of AWS Lambda to process CloudTrail logs and DynamoDB to store profiles, our system automatically learns user behavior. Using this profile, a Lambda Authorizer at the API Gateway determines a risk score in real time for every access request, preventing unusual activity such as attempts from unidentified IP addresses. This scalable, reasonably priced frame- work proved to be an effective modern cloud security solution by successfully blocking simulated credential theft attacks with a latency of less than 150 ms while running at no cost within the AWS Free Tier. 2025 IEEE. -
A Multi-Layer Security Framework for Adversarial SQL Injection in Machine Learning Systems
Adversarial machine learning (AML) is a field that works with attacks from hackers that deliberately cause machine learning systems to work incorrectly or identify data wrongly. Modern day machine learning systems grow in a very fast manner. This often introduces new threats and vulnerabilities that are above the capacity of the traditional cyber security measures. These attacks can in turn affect the trustworthiness and security of artificial systems across many domains like healthcare, education, finance, etc. This paper introduces a multi-layer security framework. It focuses on modelling and defending against SQL injection based attacks in machine learning. The paper emphasizes technical defences, governance and collaboration across various domains. By combining the risks with the existing cybersecurity frameworks such as NIST, MITRE ATLAS, and the EU AI Act, the framework provides a way to develop resilient, ethical and secure AI systems. 2025 IEEE.