Journal of Artificial Intelligence, Machine Learning and Soft Computing

Abstract

Recommendation and personalization systems have become integral components of modern digital platforms, enhancing user experiences across e-commerce, entertainment, social media, and online education. Machine Learning (ML) techniques lie at the core of these systems, enabling the prediction of user preferences and delivering tailored content. This paper provides a comprehensive review of ML approaches used in recommendation and personalization systems, including collaborative filtering, content-based filtering, hybrid methods, and deep learning approaches. Challenges such as scalability, cold-start problems, and bias in recommendations are also discussed. Future research directions, including reinforcement learning and federated recommendation systems, are highlighted. This review aims to provide researchers and practitioners with a consolidated understanding of current trends, methodologies, and applications in ML-driven recommendation systems.

Keywords: Machine Learning, Recommendation Systems, Personalization, Collaborative Filtering, Deep Learning, Hybrid Models, User Experience

Abstract

Natural Language Processing (NLP) is a subfield of artificial intelligence (AI) that focuses on enabling machines to understand, interpret, and generate human language. The integration of machine learning (ML) techniques in NLP has led to remarkable advancements, transforming how computers interact with text and speech data. This paper provides a comprehensive review of machine learning methods applied to NLP, highlighting traditional approaches, deep learning architectures, and recent innovations. Key applications, including sentiment analysis, machine translation, chatbots, and text summarization, are discussed. Challenges such as data sparsity, ambiguity, and ethical considerations are addressed, along with recent trends such as pre-trained language models and transformers. The paper concludes with insights into future directions and potential research areas in ML-driven NLP.

Keywords: Natural Language Processing, Machine Learning, Deep Learning, Transformers, Sentiment Analysis, Language Models, Text Classification

Abstract

Knowledge Representation and Reasoning (KRR) is a cornerstone of artificial intelligence (AI), providing machines with the capability to model, store, and reason about information in a way that mimics human intelligence. KRR facilitates understanding, decision-making, and problem-solving by formalizing knowledge in structured forms such as logic, semantic networks, ontologies, and probabilistic models. This paper presents a comprehensive review of knowledge representation paradigms, reasoning mechanisms, and their applications across various AI domains, including expert systems, natural language understanding, robotics, and intelligent agents. Additionally, the paper discusses challenges in scalability, uncertainty handling, and real-time reasoning, offering insights into future research directions in KRR.

Keywords: Knowledge Representation, Reasoning, Ontologies, Semantic Networks, Logic-Based AI, Probabilistic Reasoning, Expert Systems, Artificial Intelligence

Abstract

Human–Agent Interaction (HAI) has become an important field as Artificial Intelligence (AI) systems are increasingly integrated into daily life through chatbots, recommender systems, virtual assistants, and autonomous devices. While AI agents offer efficiency and automation, the issue of trust remains central to user acceptance and ethical deployment. Trustworthy AI involves transparency, fairness, explainability, privacy, accountability, and safety. This paper reviews the relationship between human-agent interaction and trustworthy AI, discussing how user trust is built or broken through interaction design, explainability methods, ethical considerations, and system reliability. It explores models of human trust, design principles for interaction, evaluation techniques, and real-world applications across healthcare, finance, education, and smart systems. The paper also highlights challenges and future directions in creating AI agents that humans can rely upon and collaborate with effectively.

Keywords: Human-Agent Interaction, Trustworthy AI, Explainable AI, Human-Centered Design, Ethical AI, User Trust, AI Transparency

Author: Dr. Ramesh Tiwari

Abstract: Predictive maintenance leverages AI and machine learning to minimize downtime and operational costs in instrumentation systems. This paper explores predictive models trained on sensor data to forecast equipment failures. Results demonstrate a substantial reduction in unplanned downtimes and increased equipment lifespan.

Keywords: Predictive maintenance, AI, machine learning, sensor data, instrumentation.

Authors: Vishal Kapoor, Ananya Mukherjee

Abstract: As artificial intelligence continues to advance, the ethical implications of its development and deployment become increasingly important. This paper explores the ethical challenges and considerations associated with AI, including fairness, accountability, transparency, and privacy. We analyze case studies where AI has both positively and negatively impacted society, highlighting the importance of ethical guidelines and regulations. The paper also discusses frameworks for developing ethical AI, such as human-centered design and value-sensitive design. Finally, we propose future directions for ethical AI research, emphasizing the need for interdisciplinary collaboration and the inclusion of diverse perspectives.

Keywords: Ethical AI, Fairness, Accountability, Transparency, Privacy

Authors: Geeta Gupta, Rohini Rathore

Abstract: Artificial General Intelligence (AGI) represents a leap in AI research, aiming to create machines with cognitive abilities comparable to humans. Unlike narrow AI, which excels in specific tasks, AGI seeks to understand, learn, and apply knowledge across a broad range of domains. This paper explores the evolution of AGI, from early concepts to the current state of research, highlighting key advancements, challenges, and future directions. It discusses interdisciplinary approaches, the importance of scalability and generalization, ethical considerations, and the potential societal impacts of AGI. The paper concludes by emphasizing the need for continued research, ethical frameworks, and collaboration to realize the promise of AGI.

Keywords: Artificial General Intelligence, AGI, machine learning, cognitive architectures, neural-symbolic systems, scalability, transfer learning, ethics, neuromorphic computing

Authors: V. P. Kharge, Shreya Sadanand Dalwai, Madhavi Sanjay Gurav, Shraddha Uttam Jong, Sejal Arvind Mane

Abstract: LeafScan: AI Assistant for Farmers is a groundbreaking project aimed at revolutionizing agriculture by empowering farmers with advanced technology. This project combines a web application and a chatbot, termed "Farmers Assistant," to provide farmers with a comprehensive solution for identifying and managing plant diseases. Utilizing Python, LeafScan employs a deep learning model tailored for classifying plant diseases based on user-uploaded images. The model, derived from deep learning techniques, preprocesses images and offers the top five predictions with associated class labels, probabilities, and confidence scores, ensuring accurate disease identification. LeafScan also aims to enhance disease detection capabilities through the development of a Convolutional Neural Network (CNN) model. Additionally, the project emphasizes the importance of a user-friendly interface, utilizing HTML, CSS, and JavaScript, to facilitate seamless interaction for farmers. Furthermore, the Farmer's Assistant chatbot is poised to provide holistic support beyond disease identification, catering to farmer queries and offering comprehensive agricultural assistance. LeafScan stands at the forefront of leveraging AI to address real-world challenges in agriculture, promising significant advancements in crop management and sustainable farming practices.

Keywords: LeafScan, AI Assistant, Plant Diseases, Deep Learning Model, Farmers Assistant

Author’s: Dr. Meenakshi, Karumanchi Brundhakshitha, Abhishek, Dr. Soumyalatha

Abstract: This paper investigates how Industry 4.0 technologies contribute to environmental sustainability in today’s industry. It introduces key Industry 4.0 technologies, emphasizing their role and the importance of environmental awareness. The article outlines how these technologies advance sustainability. A concise literature review summarizes key findings and improvements needed in this area. This work explores the environmental impact of Industry 4.0 technologies using case studies and empirical evidence. It also highlights data analytics and machine learning for sustainable decision-making, along with energy efficiency and resource optimization in manufacturing, referencing quantifying studies. The study delves into Industry 4.0’s role in a circular economy and waste reduction, by addressing implementation challenges and opportunities. Concluding with a brief discussion on emerging trends and their implications for sustainability, the article underscores the ongoing relevance of Industry 4.0 in promoting environmental awareness and sustainability.

Keywords: Sustainable decision-making, Circular economy, Machine Learning, Green manufacturing, Resource optimization, Energy-efficient processes, Smart production systems, Food supply chain, Sustainable Development Goals, over engineering.

Abstract

Artificial Intelligence is an important application in the development of enterprises, having most essential part to play in taking advantages of independent operational efficiency. One of such areas of artificial intelligence is the textile industry that has seen proper growth. AI is a computer generated system to imitate human intelligence processes. Textile industry has a great future in manufacturing by the application of AI With the application of in textile industry it has been possible to produce smart clothing using IoT and electronic sensors. In the present scenario of industry the new technology is the beginning to change the prospect of textile industry. AI has not only improved the efficiency in industry but also overall industry operations. AI covers a vast area of applications. With the help of AI designs identify trends, optimise patterns and generate 3D model garments. Revolutionary change in textile industry may come by the application of AI in the near future.

Keywords-operational efficiency, pattern making, quality products, machine learning, smart clothes, innovative textiles

Abstract

Recommender systems have become an integral part of our daily lives, assisting users in discovering personalized content such as movies, music, products, and more. These systems employ various techniques to provide recommendations and one of the emerging approaches is soft computing-based recommender systems. This paper explores the use of soft computing techniques, including fuzzy logic, neural networks, and evolutionary algorithms, in developing recommender systems that offer highly personalized content recommendations. We discuss the advantages, challenges, and future prospects of employing soft computing in recommendation engines, highlighting the potential for enhanced user experiences.

Keywords: Recommender Systems, Soft Computing, Fuzzy Logic, Neural Networks, Evolutionary Algorithms, Personalized Content Recommendation, User Preferences, Collaborative Filtering, Deep Learning, Context-aware Recommendations

Abstract

Environmental sustainability is a pressing global concern, with climate change and biodiversity loss posing significant threats to the planet. Artificial Intelligence (AI) has emerged as a powerful tool in addressing these challenges. This paper explores the applications of AI in climate modeling and conservation efforts, highlighting its potential to revolutionize environmental sustainability. We discuss the use of AI in data analysis, predictive modeling, and decision support systems, providing real-world examples and presenting the impact of AI on the field. Additionally, we provide insights into challenges, ethical considerations, and future directions for the integration of AI in environmental sustainability efforts.

Keywords: Artificial Intelligence, Environmental Sustainability, Climate Modeling, Climate Prediction, Conservation, Biodiversity Monitoring, Ecosystem Restoration, Quantum Computing, Climate Adaptation, Policy and Regulation

Abstract

The rapid growth of biological data generated through high-throughput sequencing technologies has created a strong need for intelligent computational techniques to analyze, interpret, and extract meaningful knowledge from complex datasets. Machine Learning (ML) has emerged as a powerful tool in bioinformatics and genomics for handling large-scale biological data, identifying patterns, predicting biological functions, and assisting in disease diagnosis. This paper reviews the role of ML in genomics and bioinformatics, discussing commonly used algorithms, data preprocessing techniques, and key application areas such as gene prediction, protein structure prediction, disease classification, and drug discovery. We also highlight challenges like data imbalance, dimensionality, and interpretability issues. Recent advancements including deep learning and hybrid approaches are also discussed. This review provides an overview for researchers interested in applying ML to biological datasets and shows how computational intelligence is transforming modern biology.

Keywords: Machine Learning, Bioinformatics, Genomics, Gene Prediction, Deep Learning, Protein Structure, Disease Classification

Abstract

Transfer learning has emerged as a powerful paradigm in machine learning, allowing models to leverage knowledge gained from one task to improve performance on another. This paper explores the principles, techniques, and applications of transfer learning in the context of machine learning, with a focus on the use of pre-trained models. We delve into the advantages, challenges, and best practices associated with transfer learning, presenting a comprehensive overview of its applications in various domains.

Keywords: Transfer Learning, Pre-trained Models, Fine-tuning, Inductive Transfer Learning, Transductive Transfer Learning, Advantages, Challenges, Image Classification, Natural Language Processing, Medical Imaging, Speech Recognition, Robotics.

Abstract

Time-series and sequential data are ubiquitous in fields ranging from finance and healthcare to weather forecasting and IoT sensor networks. Analyzing such data presents unique challenges due to temporal dependencies, non-stationarity, and complex patterns that evolve over time. Machine learning (ML) methods, including traditional statistical approaches, deep learning architectures, and hybrid models, have demonstrated significant promise in handling these challenges. This paper provides a comprehensive review of the current state-of-the-art ML techniques for time-series and sequential data, focusing on their applications, strengths, and limitations. It also explores recent advances in sequence modeling, including recurrent neural networks (RNNs), long short-term memory networks (LSTMs), gated recurrent units (GRUs), and transformer-based models. Finally, we highlight key challenges, future research directions, and practical considerations for deploying ML solutions in time-series forecasting and sequential data analysis.

Keywords: Time-Series Analy, Sequential Data, Machine Learning, Recurrent Neural Networks, LSTM, Transformer Models, Forecasting, Temporal Dependencies

Authors:Gaurav Saxena

Abstract:Artificial Intelligence (AI) has emerged as a transformative technology with the potential to revolutionize various industries and aspects of our daily lives. This paper provides an overview of AI, its advancements, applications across diverse domains, and the ethical considerations surrounding its implementation. It explores the underlying concepts of AI, including machine learning, neural networks, and natural language processing, while discussing the potential benefits and challenges associated with AI adoption. Additionally, the paper examines key ethical concerns such as bias, privacy, and the impact of AI on the workforce. Finally, it concludes with a discussion on the future of AI and the importance of responsible development and deployment.

Keywords:Artificial Intelligence, AI, ethics, bias, fairness, privacy, data security, accountability, transparency, employment, social equality, algorithmic transparency, responsible AI, ethical considerations.

Aurhors:  Manjusha Tatiya, Neel Chitre, Anmol Dhage , Neha Sharma

Abstract: Prescription reading is an important task in the healthcare industry, as it helps to ensure that patients receive the correct medications and dosages. However, manual prescription reading can be time-consuming and error-prone, leading to potential harm for patients. Machine learning has the potential to automate this task, improving efficiency and accuracy. In this paper, we review the state-of-the-art in prescription reading using machine learning techniques, including support vector machines, deep learning, and recurrent neural networks. We also propose a novel approach using convolutional neural networks for handwritten prescription recognition.

Keywords:  Machine Learning, Handwritten Prescription, Medications and Dosages

Authors:  Diksha Tardekar, Swayam Suryavanshi, Vaishnavi Chavan, Sagar Chavan

Abstract: Thyroid diseases are affecting millions of people globally, and timely detection is crucial for effective treatment. However, traditional methods such as blood tests and ultrasounds have limitations in terms of accuracy, cost, and availability. In recent years, machine learning techniques have shown promise in thyroid detection by leveraging large datasets and advancements in computational power. This paper reviews state-of-the-art machine learning techniques for thyroid detection, including classification, clustering, and deep learning methods. We discuss the challenges and limitations of existing approaches, such as data imbalance, interpretability, and model generalization. Additionally, we highlight potential future research directions, including the integration of multi-modal data, explainable AI, and personalized medicine.

Keywords: Machine Learning, Thyroid Detection, Thyroid Detection Using Machine Learning

Authors:  Rahul Patil , Sandip Chavan , Ameya Bhupendra Deodhar , Chinmayi Kamalakar Juikar , Pradnya Sham Jagtap, Samruddhi Murlidhar Jadhav

Abstract: In today’s pace forward generation, it is convenient and functional to make daily tasks automated and digitized. Digitization opens many possibilities to make our repetitive tasks easier using assistive technology. Artificial assistants make use of machine learning, artificial intelligence and natural language processing to provide a personalized and conversational experience. This paper discusses about Pixie which is a desktop voice assistant aiming to provide a personalized, interactive and secure experience. Pixie also has face recognition system and is gesture enabled. Voice assistants are an emerging technology with a great future. In this paper, we discuss the development of a voice assistant in desktop.

Keywords:  Artificial Intelligence, Virtual Assistant, Natural Language Processing, Machine Learning.

Authors: Dr. Nemailal Tarafder

Abstract: The term artificial intelligence (AI) is associated to any machine that exhibits traits related to a human mind such as learning and problem solving. For the manufacturing, artificial intelligence is reshaping their production process and the way they conduct business. Textile is such an industry where a wide variety of technologies can be applied to advance processes and provide fresh new varieties of clothing fabrics and fibres.

 

Textile manufacturing businesses with access to historical and real-time operational data can leverage artificial intelligence to improve efficiency and augment the capabilities of their human employees. Automated inspection can be performed by the use of artificial intelligence and image processing for inspection of the quality of the product. Based on the improvement of the machine vision theory, industry can use industrial robot technology to realize the automation of cut pieces cutting and replace manual labour. Artificial intelligence is the field of study that deals with the synthesis and analysis of computational agents that act intelligently. One area of apparel manufacturing where artificial intelligence improves quality control is grading of yarn and other base materials. Automation in garment product is becoming a reality due to technical development and the use of modelling and simulation. Artificial intelligence is one of the technologies that can help in extensive data management as it uses the gained information from big data machine to do things that once were the human domain.

Keywords: Artificial intelligence, smart textiles, new technologies, fabric inspection, sewing technology, digital components, quality control.

Abstract

The increasing complexity and volume of cyber threats in today’s digital era necessitate advanced detection and mitigation strategies. Traditional signature-based security systems are often inadequate against sophisticated attacks such as zero-day exploits, ransomware, and phishing campaigns. Machine Learning (ML) has emerged as a powerful tool to enhance cybersecurity measures, offering predictive, adaptive, and automated threat detection capabilities. This paper provides a comprehensive review of ML applications in cybersecurity, focusing on threat detection, intrusion detection systems (IDS), malware analysis, and anomaly detection. We discuss the advantages, limitations, and current challenges of integrating ML into cybersecurity frameworks. Moreover, the paper presents comparative analyses of various ML algorithms used in threat detection and highlights future research directions.

Keywords: Machine Learning, Cybersecurity, Threat Detection, Intrusion Detection Systems, Anomaly Detection, Malware Analysis

Abstract

PID (Proportional-Integral-Derivative) controllers are widely used in industrial control systems, but tuning these controllers can be a complex and time-consuming process. This paper investigates the application of machine learning techniques to optimize PID controller parameters for various industrial processes. The proposed methods include genetic algorithms, neural networks, and reinforcement learning, which aim to automate the tuning process and improve controller performance. Case studies in process control and robotics demonstrate the effectiveness of these machine learning-driven optimizations.

Keywords: PID Controllers, Machine Learning, Genetic Algorithms, Neural Networks, Tuning Optimization