Search
349 articles for “Machine Learning Optimization”
-
Wear and Tribological Characteristics of Novel Metal Matrix Composites
Abstract: The development of advanced metal matrix composites (MMCs) with enhanced tribological performance has become increasingly important due to the premature failure of critical engineering components operating under severe wear conditions in automotive, aerospace, marine, defense, and power generation systems. Conventional composites such as Copper–Alumina and Aluminium–Silicon Carbide have demonstrated improved mechanical and wear characteristics; however, their widespread application is often limited by issues including particle agglomeration, non-uniform reinforcement distribution, porosity …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 1326–1346 Read article
-
Copper Sulfide Semiconducting Nanoparticles for Antibacterial Applications: Synthesis Strategies, Mechanisms and Performance – A Review
Abstract: Copper sulfide nanoparticles (CuS NPs) have drawn growing attention as a next-generation antibacterial platform, owing to their tunable structural, optical, and catalytic properties. This review consolidates current evidence on CuS NP synthesis, mechanisms, and antibacterial performance, comparing chemical and green synthesis routes alongside the effects of morphology, doping, and surface modification. Mechanistically, CuS NPs act through several overlapping pathways, including reactive oxygen species generation, bacterial membrane disruption, ion release, and …
Published in Journal of Polymer & Composites · Vol. 14, Issue 4, 2026 Read article
-
An Investigative Study on Cache-Oblivious Data Structures
Abstract: Cache-oblivious data structures and data management systems have emerged as critical components in modern computing environments, aiming to optimize memory access patterns across different levels of the memory hierarchy without explicit knowledge of cache sizes or configurations. This study presents an overview of cache-oblivious techniques, including adaptive data structures, compression, parallel processing, and security considerations. The workexplores future directions in cache-oblivious systems, such as non-volatile memory support, graph processing, edge …
Published in International Journal of Data Structure Studies · Vol. 1, Issue 2, 2023 · pp. 33–37 Read article
-
Intelligent Systems: A study on AI and Machine learning
Abstract: Artificial Intelligence (AI) and Machine Learning (ML) are dynamic branches of computer science that focus on developing systems capable of executing tasks commonly associated with human intelligence. These activities encompass making choices, resolving issues, understanding language, identifying patterns, and learning through experience. Artificial Intelligence refers to the broad area of designing systems and frameworks that enable machines to perform tasks resembling human thought and behavior. This field integrates diverse technologies …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 13, Issue 1, 2025 Read article
-
Optimizing Marketing Campaigns Using Random Forest and A/B Testing
Abstract: Marketing initiatives play a vital role in driving business growth by reaching targeted consumer segments through tailored strategies across multiple channels. The success of these initiatives is influenced by various factors, including the type and duration of the campaign, the characteristics of the target audience, the communication channels employed, and the overall efficiency of each strategy. These factors collectively impact key performance metrics such as conversion rates, customer acquisition costs, …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 3, 2025 · pp. 01–09 Read article
-
AI and ML in the Chemical Industry: A Review of Transformative Applications and Future Prospects
Abstract: The chemical industry, a key growth indicator of the global manufacturing ecosystem, is experiencing a digital transformation driven mainly by advancements in Artificial Intelligence (AI) and Machine Learning (ML) in this sector. These technologies are totally revolutionizing current and traditional methodologies by significantly improving process efficiency, reducing costs of manufacturing, accelerating R&D, and improving safety and sustainability standards. Proper utilization of Artificial intelligence (AI) and machine learning (ML) in chemical …
Published in International Journal of Cheminformatics · Vol. 3, Issue 2, 2025 · pp. 1–6 Read article
-
The Integration of Machine Learning in VLSI IC Design
Abstract: It represents the first use of AI in the domain of integrating circuits, which has been impacted by it. The conventional VLSI design process that is now in use is replaced by this technology. The laborious manual concepts created by people have been replaced with automated design innovations. This development would trigger a profound change in the fields of AI education and hardware computation. With the introduction of contemporary chips, …
Published in Trends in Machine design · Vol. 11, Issue 2, 2024 · pp. 1–8 Read article
-
Predicting Dielectric Constants of Polymers Using Molecular Structural Descriptors and Explainable Machine Learning: A Data-Driven Approach
Abstract: Accurate prediction of dielectric constants in polymeric materials is fundamental to the rational design of advanced electronic components, energy storage capacitors, flexible substrates, and high-frequency communication circuits. Conventional approaches to identifying suitable polymer dielectrics rely on extensive experimental synthesis and characterisation, which are both time-consuming and resource-intensive. In this work, an explainable machine learning framework is developed to predict the dielectric constant of polymers directly from molecular structural descriptors derived …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 297–304 Read article
-
Artificial Intelligence in Robotics: Current Trends, Applications, and Future Challenges
Abstract: The incorporation of artificial intelligence (AI) into robotics has transformed the industry by greatly improving robots' capacity to carry out complex and autonomous functions in a wide range of sectors. This paper explores the evolution, applications, and challenges associated with AI-driven robotics. It examines key AI methodologies employed in robotics, including machine learning, natural language processing (NLP), computer vision, and planning/control algorithms, which enable robots to perceive, learn, and interact …
Published in Journal of Advancements in Robotics · Vol. 12, Issue 2, 2025 · pp. 31–43 Read article
-
The Future of Robotics: A Review of AI-Enabled Robotics Research, Development, and Applications
Abstract: Robotics powered by artificial intelligence (AI) is transforming contemporary industries by empowering machines to learn, adapt, and operate on their own in intricate, changing contexts. The breadth and capabilities of automation have been greatly expanded by the convergence of AI technologies with robots, including machine learning, deep learning, computer vision, and natural language processing (NLP). With an emphasis on technological advancements, application areas, and research advances, this study examines current …
Published in International Journal of Robotics and Automation in Mechanics · Vol. 3, Issue 2, 2025 · pp. 33–38 Read article
-
An Overview on AI-Driven IoT Based Decision Making in Climate change Study: KSK approach in Climate Change Study
Abstract: As the Earth’s climate enters a state of unprecedented volatility, the traditional methods of ecological observation—characterized by delayed reporting and fragmented data—are no longer sufficient. This study investigates the paradigm shift toward AI-driven IoT (KSK Approach)-based decision-making frameworks as the primary frontier in climate science. By deploying a "planetary nervous system" of interconnected sensors—measuring everything from soil moisture in the Sahel to glacial melt rates in the Arctic—we generate a …
Published in International Journal of Climate Conditions · Vol. 3, Issue 1, 2026 · pp. 1–10 Read article
-
Enhanced Multimodal Disease Prediction Using Hybrid Ensemble Learning and AutoML Techniques
Abstract: The integration of hybrid ensemble learning and automated machine learning (AutoML) is revolutionizing disease prediction by addressing the complexity, imbalance, and high dimensionality inherent in medical datasets. This paper proposes an advanced pipeline that combines diverse ensemble learning models with AutoML-based optimization to predict chronic diseases such as kidney diseas-e, Parkinson’s disease, and lung cancer. Publicly available datasets from UCI and PhysioNet repositories were preprocessed using outlier removal, normalization, and …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 1, 2026 Read article
-
Parallel Privacy-Preserving Adaptive Federated Learning on GPU-Enabled Multi-Core Architectures
Abstract: The increasing deployment of parallel and distributed intelligent systems has intensified the need for privacy-preserving learning frameworks that can exploit multi-core and GPU-based architectures without centralizing sensitive data. This work proposes a parallel Adaptive Federated Learning (AFL) framework that integrates Differential Privacy and Secure Aggregation over heterogeneous multi-core and GPU platforms to enhance both data confidentiality and convergence efficiency. The framework dynamically adjusts client participation, learning rates, and aggregation weights …
Published in Recent Trends in Parallel Computing · Vol. 13, Issue 1, 2026 Read article
-
Diabetes Risk Prediction from Survey Data Using Machine Learning Algorithms
Abstract: Diabetes mellitus represents one of the most significant global health challenges, affecting millions worldwide and leading to severe complications if left undiagnosed or poorly managed. Early detection and risk assessment are crucial for preventing the progression of this chronic condition. This research presents a comprehensive machine learning approach for predicting diabetes risk using survey-based health parameters. The study implements and compares four prominent classification algorithms: Logistic Regression, K-Nearest Neighbors (KNN), …
Published in International Journal of Bioinformatics and Computational Biology · Vol. 4, Issue 2, 2026 Read article
-
Harvestify: ML Based Tool for Home Gardening and Farming
Abstract: This study presents a cutting-edge application that will transform home gardening and agriculture practices using machine learning (ML) approaches. The main goal is to provide data-driven insights to home gardeners and farmers, enabling them to implement efficient and sustainable farming practices. Crop disease detection, fertiliser recommendation, and a community section for user engagement comprise the three main elements that make up the system's architecture. The Crop Disease Detection module analyses …
Published in International Journal of Electrical and Communication Engineering Technology · Vol. 2, Issue 2, 2024 · pp. 18–28 Read article
-
Cognitive AI-Based Quality Control and Operational Optimization of Polymer Composites for Healthcare Applications
Abstract: The use of polymer composite materials in healthcare is on the rise because of their adjustable mechanical characteristics, biocompatibility and structural flexibility. Yet, it is difficult to ensure stable quality of such composites due to process-related defects, heterogeneity of the material and the lack of real-time adaptive control. The proposed study suggests the use of cognitive AI-based framework of quality control and optimization of operation of polymer composite systems which …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 571–591 Read article
-
Enhancing Credit Card Fraud Detection Using Device Fingerprinting and Behavioral Biometrics
Abstract: Credit card fraud is a growing global concern, with financial losses projected to reach $ 43.47 billion by 2028. Credit card fraud poses a major challenge in the financial industry, resulting in substantial financial losses and security risks. This research introduces a Machine Learning-based Credit Card Fraud Detection System designed to improve the accuracy of fraud identification. Due to the imbalanced nature of fraud datasets, SMOTE (Synthetic Minority Over-sampling Technique) …
Published in Journal Of Network security · Vol. 13, Issue 2, 2025 · pp. 40–50 Read article
-
Data Mining for E-Commerce and Social Media: Insights and Future Research Directions
Abstract: The fast expansion of e-commerce and social media has heralded a new era of data-rich settings, with enormous quantities of user interactions, preferences, and transactions generated on a daily basis. Data mining has developed as a critical strategy for leveraging big datasets, allowing businesses to gain concrete knowledge and drive decision-making. Data mining in e-commerce improves operational efficiency and user pleasure by allowing for personalized recommendations, consumer segmentation, fraud detection, …
Published in E-Commerce for Future & Trends · Vol. 12, Issue 1, 2025 · pp. 14–23 Read article
-
Utilizing AWS Advanced Services for Modernizing and Refactoring Legacy Systems to Achieve Cloud-Native Capabilities
Abstract: Updating and restructuring outdated systems is essential for organizations seeking to harness the scalability, adaptability, and robustness offered by cloud-native architectures. Legacy systems can obstruct innovation because of their rigid structure, expensive maintenance, and inability to scale effectively. Amazon Web Services (AWS) provides a comprehensive suite of advanced services that enable the efficient transformation of such systems into modern, cloud-native solutions. This paper explores strategies and best practices for utilizing …
Published in Recent Trends in Parallel Computing · Vol. 12, Issue 1, 2025 · pp. 44–65 Read article
-
Time Series Sales Forecasting Using ARIMA Model
Abstract: Sales forecasting is a critical application in various industries and presents one of the most challenging problems worldwide. One method of prediction involves identifying patterns in historical data, where the outcome is known in advance and can be validated using more recent data. If a pattern consistently leads to the same outcome, it can be considered a genuine relationship. This method is highly flexible and can be utilized with diverse …
Published in International Journal of Algorithms Design and Analysis Review · Vol. 2, Issue 1, 2024 · pp. 17–27 Read article