Journal of Artificial Intelligence, Machine Learning and Soft Computing

Abstract

Fuzzy logic has emerged as a powerful tool for dealing with uncertainties in control systems, especially in environments where precise mathematical models are unavailable. This paper explores the application of fuzzy logic in designing robust control systems for industrial instrumentation. The use of fuzzy controllers in processes such as chemical plants, robotics, and automotive systems is discussed, along with their advantages over traditional control methods. Several case studies highlight the role of fuzzy logic in improving system adaptability and resilience.

Keywords: Fuzzy Logic, Robust Control, Uncertainty, Industrial Systems, Adaptability

Abstract

Sensor fusion has become an integral part of modern industrial control systems, where data from multiple sensors are combined to create a more accurate and reliable system response. This paper discusses the analytical methods used for sensor fusion, including Kalman filters, Bayesian networks, and machine learning techniques. The paper highlights how sensor fusion improves decision-making processes in control engineering by reducing noise and uncertainty in sensor data. Practical applications in fields like robotics, autonomous systems, and manufacturing processes are provided to illustrate the advantages of different fusion techniques.

Keywords: Sensor Fusion, Kalman Filters, Bayesian Networks, Machine Learning, Industrial Control

Abstract

This paper explores the recent advancements in Model Predictive Control (MPC) for nonlinear systems, particularly in industrial instrumentation and control engineering. The focus is on improving stability, robustness, and computational efficiency in real-time applications. The paper reviews several modified MPC algorithms, highlighting their impact on performance in controlling complex nonlinear processes. Several case studies in chemical, automotive, and aerospace industries are used to demonstrate the effectiveness of these advanced MPC methods. The importance of sensor fusion, real-time data processing, and optimization techniques is also discussed to address future challenges in nonlinear system control.

Keywords: Nonlinear Systems, Model Predictive Control, Real-Time Optimization, Robustness, Industrial Applications

Abstract

In recent years, the recognition of handwritten mathematical expressions has received an increasing amount of attention in pattern recognition research. The diversity of approaches to the problem and the lack of a commercially viable system, however, indicate that there is still much research to be done in this area. In this thesis, I will describe an on-line approach for solving a handwritten mathematical expression. For classification of specific characters we apply Convolutional Neural Network. Each of the correct detection, character string operations is used for the solution of the equation.  Finally the experimental results show the great effectiveness of our proposed system.

Keywords: Handwritten, Convolutional Neural Network, Pattern Recognition, Proposed system

Abstract

Rapid spread of Coronavirus disease COVID-19 leads to server pneumonia and it is estimated to create a high impact on the healthcare system. An urgent need for early diagnosis is required for precise treatment, which in turn reduces the pressure in the health care system. Some of the standard image diagnosis available is Computed Tomography (CT) scan and Chest X-Ray (CXR). Even though a CT scan is considered a gold standard in diagnosis, CXR is most widely used due to widespread, faster and cheaper. This study aims to provide a solution for identifying pneumonia dur to COVID-19 and healthy lungs (normal person) using CXR images. One of the remarkable methods used for extracting a high dimensional feature from medical images is the Deep learning method.

Keywords: Genetic Deep Learning Convolutional Neural Network (GDCNN), Computed Tomography (CT), Chest X-Ray (CXR), Artificial Intelligence (AI)

Abstract

Air Quality security has gotten one of the foremost fundamental exercises for the administration in numerous mechanical and concrete zones in today’s world. The meteorological and traffic factors, consuming crude oil derivatives and mechanical parameters perform critical jobs in air contamination which make an adverse effect on living beings. With this expanding pollution on the earth, we also had different executing models that can record data about centralizations of air pollutants (SO2, NO2, etc.). The affidavit of those unsafe gases is noticeable all around; is influencing the character of individuals’ lives, particularly in urban territories. Of late, numerous specialists began to study about this concern and mentioned several measures to manage these conditions with the assistance of the presidency and native people. Data Analytics is a leading approach as it includes natural detecting systems and sensor information accessible. Machine Learning strategies are utilized to predict the ratio with relation to other components present in the earth’s atmosphere. Various regression models are used to predict the air quality and their relative effects.

Keywords: Air Quality Index, Machine Learning, Air Pollutants, Adverse Effects, Parameters, Air Quality prediction, Air Pollution, Linear Regression, Regression Analysis.

Abstract

Artificial Intelligence offers vast opportunities for application in agriculture; there still exists a lack of familiarity with high tech machine learning solutions in farms across most parts of the world. AI systems also need a lot of data to train machines and to make precise predictions. Tomatoes (Solanum lycopersicum) can be grown on almost any moderately well-drained soil type. This research presents an image based plant leaf disease identification by support vector machine learning technique. Simulation is performed using Python sypder 3.7 version. The overall accuracy is achieved 98% in different plant leaf disease identification.

Keywords: Sypder, Python, Accuracy, AL, Plant, Disease, Machine Learning

Abstract

Crime is one of the serious issues in our society. It is the most predominant aspect of our society. It is also predominant in society. So, the prevention of crime is one of the important tasks. The crime analysis should be done in a systematic way as the analysis makes it important in the detecting and prevention of crime. The analysis detects the investigating patterns and helps in the detection of trends in crime. The main of this paper is the analysis of the efficiency of the crime investigation. The model is designed for the detection of crime patterns from inferences. The inferences are collected from the crime scene, and these inferences, the paper demonstrates the prediction of the perpetrator. The paper gives the research way for the prediction of perpetrator age and gender. This paper gives two major aspects of crime prediction. One is perpetrator gender, and the other is perpetrator age. The parameters used are analysis of the various factors like the year, month, and weapon used in the unsolved crimes. The analysis part identifies the number of unsolved crimes. The prediction task involves the description of the perpetrator's age, sex, and relationship with the victim. The dataset used in this paper is taken from the Kaggle. The system predicts the output using Multilinear regression, K-Neighbor's classifier, and neural networks. It was trained and tested using a machine learning approach. 

Keywords: Crime Prediction, KNN, Decision Tree. Multilinear Regression; K-Neighbors Classifier, Artificial Neural Networks.

Abstract

Swarm Intelligence (SI) is a field inspired by the collective behavior of social organisms, such as ants, bees, birds, and fish. This paper presents a comprehensive review of swarm intelligence principles, popular optimization algorithms, and their applications in engineering and computer science. We analyze classical swarm-based algorithms like Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), and more recent hybrid and adaptive approaches. The strengths, limitations, and performance metrics of these algorithms are discussed in comparison with conventional optimization techniques. Furthermore, we explore emerging trends, including multi-objective optimization, dynamic optimization, and real-world applications in robotics, scheduling, and machine learning. The paper aims to provide researchers and practitioners with a structured understanding of SI-based optimization methods, highlighting challenges and potential future directions.

Keywords: Swarm Intelligence, Particle Swarm Optimization, Ant Colony Optimization, Artificial Bee Colony, Metaheuristic, Optimization Algorithms, Multi-objective Optimization

Abstract

Meta-learning, often described as “learning to learn,” is an emerging paradigm in artificial intelligence that focuses on enabling models to adapt quickly to new tasks with minimal data and training. Unlike traditional machine learning approaches that learn a single task from scratch, meta-learning aims to extract transferable knowledge from a variety of tasks so that learning new tasks becomes faster and more efficient. This paper presents a comprehensive review of meta-learning techniques, including metric-based, model-based, and optimization-based approaches. It also explores the relationship between meta-learning and few-shot learning, transfer learning, and continual learning. Various real-world applications such as robotics, healthcare, natural language processing, and computer vision are discussed. The paper highlights current challenges and future research directions, including scalability, interpretability, and integration with reinforcement learning. Meta-learning shows promise in creating adaptable and intelligent systems capable of generalization beyond conventional training methods.

Keywords: Meta-learning, Few-shot learning, Transfer learning, Optimization-based learning, Metric learning, Adaptation, Artificial Intelligence

Abstract

Remote sensing and satellite imagery have become very important sources of data for monitoring Earth’s surface, environment, agriculture, urban growth, and disaster events. However, the large volume, high dimensionality, and complexity of satellite data makes manual analysis very difficult. Machine Learning (ML) methods provides automatic and efficient techniques to extract meaningful patterns and information from such data. This review paper discusses how different ML techniques are applied in remote sensing and satellite data processing. Traditional algorithms such as k-Nearest Neighbors, Support Vector Machines, and Random Forest are compared with modern deep learning approaches like Convolutional Neural Networks and Recurrent Neural Networks. The paper also covers applications in land use classification, crop monitoring, disaster management, weather forecasting, and environmental analysis. Challenges such as data heterogeneity, limited labeled data, and computational issues are also discussed. The aim of this paper is to present a comprehensive overview for researchers who are working in this emerging interdisciplinary domain.

Keywords: Remote Sensing, Satellite Imagery, Machine Learning, Deep Learning, Land Use Classification, Environmental Monitoring

Abstract

Financial markets generate huge volume of data every second in the form of price movements, order books, news feeds, and economic indicators. Traditional statistical models often fail to capture nonlinear patterns and fast changing dynamics of such markets. Machine Learning (ML) techniques are increasingly used in finance and especially in algorithmic trading to predict market behavior, manage risks, and optimize trading strategies. This paper reviews the role of ML in finance with special focus on algorithmic trading systems. It discusses supervised, unsupervised and reinforcement learning approaches used for prediction of asset prices, portfolio optimization, high frequency trading, sentiment analysis from financial news, and risk management. Various ML algorithms like regression models, support vector machines, neural networks, deep learning architectures and reinforcement learning frameworks are explained with their applications in trading. Advantages, limitations and practical challenges of ML in financial markets are also presented. Tables and figures summarize different methods and their use cases. Finally, the paper concludes with future directions of ML-driven finance systems.

Keywords: Machine Learning, Algorithmic Trading, Financial Prediction, Deep Learning, Reinforcement Learning, Quantitative Finance, Sentiment Analysis, Portfolio Optimization.

Abstract

Science and technology have improved our quality of life, but some industries' rapid development has given up people's future living environment and harms survival. Chest X-Ray (CXR) plays an essential role in the detection. Yet, the less availability of expert radiologists to interpret the CXR images and the subtle appearance of disease radiographic responses remains the major issue in manual diagnosis. Manual diagnosis is very complex and time-consuming. Automatic COVID (coronavirus) screening (ACoS) system uses radiomics texture descriptors extracted from CXR images to detect the normal, suspected, and nCOVID-19 infected patients. But this system is also time-consuming. Hence we propose a System for COVID-19 detection. The diagnosis of COVID-19 is typically associated with both the symptoms of pneumonia and Chest X-ray tests. CXR is the first imaging method that plays a vital role in the diagnosis of COVID-19 disease. In the existing system, we find some disadvantages; to overcome this, we will use X-ray data of normal and COVID 19 positive patients and train a model to differentiate between them. We present COVID 19 AI Detector using a deep convolutional neural network model (CNN) to triage patients for appropriate testing.

Keywords: - CNN, Machine Learning, Classification Algorithm, Covid-19 Detection.

Abstract

The 20th century is tech savvy and social media is a bug part of our day to day lives. The best part of social media is how it enables individuals to stay connected even if they stay miles apart or in two separate continents. This has created a huge market for businesses via social media. They can connect with customers and potential buyers virtually, without having them physically attend the stores. Products have been successfully selling online and are marketed through Twitter, Facebook, Instagram and other social media platforms that give business splendid reach. This paper is looking at the usefulness of Artificial Intelligence on Social Media Marketing in the real life such as running ads on Facebook and Instagram by companies as their marketing strategy.

Keywords: Social Media Marketing, SEP, Social Media Optimization, Artificial Intelligence

Authors

Siddhant Sambodhi Rahul, Shubham Kumgonda Patil, Prasad Shamu Kamble, Siddharth Mukul Goenka, F. A. Patel Abstract:-Real estate properties are a very profitable and healthy future investment, as it can also be risky, cause it's hard to predict the value of the land as it can go higher or lower, as our main goal is to achieve the accuracy to predict the value of that property. As our main idea is to give users the most accurate value of the property they desire. We are using technology like NumPy and scikit learn to predict the datasets. We can say research in these topics can open a wide variety of fields to explore and get an advantage in the future.

Keywords:Pharmacy,Onlinepharmacy,Medical,Online Medicine,Medicines.

Abstract

Appearing for a job interview can be a mentally frustrating and emotionally draining experience for students, especially when it's their very first time. So, the idea of building an AI-based Interview Bot came in order to help students/fresher prepare for their job interview through an AI-based automated interview. AI-based Interview Bot is a platform that will take real-time interviews and extract the optimum candidate potential in an unbiased stress-free environment. It consists of an emotion recognition model, an automated interview model, a result generator, etc. it provides mock automated AI-based interviews for the student to prepare them for good interview performance.

Keywords: - AIML, Artificial Intelligence, Chatbot, NLP, Emotion Recognition, Real-time analysis.

Author: Harikrishnan R

Abstract: In the Energy sector, many parameters are involved for obtaining the transmission and distribution of Power process, efficient and effective by reducing various power transmission and distribution losses. The parameters concerning Energy are interdependent and relatively close together in various aspects. The parameters such as Cost of Energy production, Plant capacity, Efficiency of Power production etc., are interdependent. They can be related to two variables such as independent variables and dependent variables. Optimization of these parameters is being carried out with the help of an Artificial Neural Network. Maximum error formed in the relationship can be found out and is easily be reducible. An analysis is being made in the optimization model using ANN.

Abstract

Artificial intelligence is the hot topic of today’s world of science. It is the ability of machines to take and process unstructured data and autonomously perform tasks. Machine learning is another hot topic.

Keywords: - Machine learning, data, Artificial intelligence.

Evolutionary Computing (EC) is a subfield of artificial intelligence inspired by natural evolutionary processes. Among the various techniques under EC, Genetic Algorithms (GAs) have emerged as a robust optimization and search paradigm. This review provides an in-depth examination of evolutionary computing, with a focus on genetic algorithms, their theoretical foundations, algorithmic structures, and diverse applications across engineering, computer science, and industry. The paper also discusses hybrid approaches, recent advancements, limitations, and future research directions. By synthesizing findings from multiple studies, this review highlights the versatility, adaptability, and performance of genetic algorithms in solving complex, real-world problems.

KEYWORDS: Evolutionary Computing, Genetic Algorithms, Optimization, Selection, Crossover, Mutation, Heuristic Search, Hybrid Algorithms

ABSTRACT

Deep learning (DL) has emerged as a cornerstone of modern artificial intelligence (AI), enabling significant advancements in computer vision, natural language processing, speech recognition, and robotics. The effectiveness of deep learning systems largely depends on the architecture of neural networks and the optimization techniques employed during training. This paper provides a comprehensive review of key deep learning architectures, including feedforward networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and graph neural networks (GNNs). Furthermore, it explores optimization strategies, such as gradient-based methods, adaptive learning rates, regularization techniques, and neural architecture search (NAS), that improve model performance and convergence. Challenges related to computational complexity, overfitting, and training stability are discussed. The paper concludes with future directions, emphasizing lightweight architectures, energy-efficient optimization, and explainable deep learning models.

KEYWORDS: Deep Learning, Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Transformers, Optimization Techniques, Neural Architecture Search

ABSTRACT

Continual or lifelong learning (CL/LL) is a fundamental paradigm in artificial intelligence (AI) that enables systems to learn continuously from data streams, adapt to new tasks, and retain knowledge without catastrophic forgetting. Unlike traditional machine learning models, which are typically trained offline on fixed datasets, continual learning mimics human learning capabilities by integrating knowledge incrementally. This review paper provides a comprehensive overview of continual learning, including its theoretical foundations, main strategies, recent advances, benchmark datasets, evaluation protocols, and applications. Key challenges, such as catastrophic forgetting, transfer learning, and task interference, are discussed along with proposed mitigation approaches. The paper also highlights emerging trends, including meta-learning, memory-augmented networks, and hybrid approaches combining neural and symbolic methods. Finally, future research directions are outlined, emphasizing the potential of lifelong learning to enable robust, adaptive, and generalizable AI systems.

KEYWORDS: Continual Learning, Lifelong Learning, Catastrophic Forgetting, Incremental Learning, Neural Networks, Memory-Augmented Networks, Meta-Learning, Transfer Learning, Adaptive AI

ABSTRACT

Computer vision (CV) has emerged as a pivotal area of artificial intelligence (AI), enabling machines to perceive, analyze, and understand visual information from the world. Among the various CV applications, real-time object detection plays a critical role in domains such as autonomous vehicles, surveillance systems, healthcare, and robotics. This paper provides a comprehensive review of the current state-of-the-art in computer vision and real-time object detection, focusing on classical techniques, deep learning-based approaches, and their real-time deployment strategies. Furthermore, the paper examines the challenges associated with object detection, including speed, accuracy, occlusion handling, and dataset limitations. It also highlights recent advances in convolutional neural networks (CNNs), region-based approaches, single-shot detectors, and transformer-based models that enhance real-time performance. Finally, the paper discusses potential future directions, including edge computing integration, lightweight models, and multi-modal fusion for robust object detection.

KEYWORDS: Computer Vision, Real-Time Object Detection, Deep Learning, Convolutional Neural Networks, YOLO, SSD, Transformer, Autonomous Systems

ABSTRACT

Cognitive architectures and AI thinking models represent foundational frameworks for developing intelligent systems that simulate human-like reasoning, learning, and decision-making. These architectures provide structured methodologies for integrating perception, memory, reasoning, and action into coherent computational systems. This paper provides a comprehensive review of the field, examining classical cognitive architectures such as ACT-R, SOAR, and Sigma, as well asmodern AI thinking models inspired by neural-symbolic systems, hybrid reasoning, and reinforcement learning. Additionally, the paper discusses applications in robotics, natural language understanding, and autonomous decision-making, highlighting the challenges and future directions of cognitive architectures. The synthesis aims to guide researchers and practitioners in designing AI systems with improved adaptability, generalization, and cognitive fidelity.

KEYWORDS: Cognitive architectures, AI thinking models, ACT-R, SOAR, neural-symbolic AI, hybrid reasoning, intelligent systems, human-like cognition

ABSTRACT

Automated Machine Learning (AutoML) is transforming the field of artificial intelligence by automating traditionally manual and labor-intensive tasks such as feature engineering, model selection, hyperparameter tuning, and deployment. By reducing the need for deep technical expertise, AutoML democratizes AI, enabling businesses and researchers to develop robust models efficiently. This paper provides a comprehensive review of AutoML, including its key components, recent advances, challenges, and future directions. We discuss popular AutoML frameworks, evaluation metrics, and applications across various domains such as healthcare, finance, and autonomous systems. Additionally, we highlight ongoing research trends, including neural architecture search (NAS) and automated deep learning pipelines, and emphasize the importance of interpretability and fairness in automated systems.

KEYWORDS: AutoML, Automated Machine Learning, Neural Architecture Search, Hyperparameter Optimization, Machine Learning Pipelines, Model Selection, Feature Engineering

ABSTRACT

Environmental monitoring is becoming very important due to rapid climate change, pollution, deforestation and loss of biodiversity across the world. Traditional monitoring techniques are often slow, expensive and limited in coverage. Artificial Intelligence (AI) offers new capabilities to analyze large volumes of environmental data coming from satellites, sensors, drones and IoT devices. AI models can detect patterns, predict environmental changes and assist in decision making for sustainable development. This paper presents a comprehensive review of how AI techniques are being used in environmental monitoring. It discusses machine learning, deep learning, computer vision and data analytics methods applied for air quality monitoring, water pollution detection, wildlife tracking, forest monitoring and climate prediction. The paper also highlights challenges such as data quality, computational cost and ethical concerns. Finally, future directions are discussed where AI can significantly support global environmental protection efforts.

KEYWORDS:  Artificial Intelligence, Environmental Monitoring, Machine Learning, Remote Sensing, IoT Sensors, Climate Change, Deep Learning