Journal of Soft Computing and Computational Intelligence <p class="contentStyle"><strong>JoSCCI</strong> is a peer reviewed journal of Computer Science domain published by MAT Journals Pvt. Ltd. It is a print and e-journal focused towards the rapid publication of novel research based on experimental and theoretical topics in Soft Computing and Computational Intelligence. It also focuses on theory, design, application and development of biologically and linguistically motivated Computational Paradigms. It includes Neural Networks, Knowledge Mining, Fuzzy Logic, Evolutionary Algorithms. Machine Learning, Expert Systems, Evolutionary Computing, Rough Sets and other similar techniques to address real world complexities is the primary focus of this journal.</p> <h6 class="mt-2"> </h6> <div class="card"> </div> en-US Wed, 10 Jan 2024 07:20:22 +0000 OJS 60 A Study on Hybrid-GWO Algorithm-based PID Controller for Quadcopters <p>As Unmanned Aerial Vehicles (UAVs), or drones, continue to evolve in importance across diverse applications, optimizing their control systems stands out as a crucial point for achieving superior performance. This research paper delves into the integration of a Hybrid Grey Wolf Optimizer (GWO) algorithm with Proportional-Integral-Derivative (PID) controllers, addressing the important task of tuning PID parameters for drone control. The study is in its early stages and has an initial focus on preliminary simulations. The literature review consists of existing research on PID controllers, as well as a review of different outputs of Hybrid-GWO. Also, we have conducted simulations to study the output of a basic GWO, laying the foundation for incorporating GWO in PID optimization and tuning. Furthermore, we have done simulations specific to PID control for quadcopters, marking the initial steps towards understanding the complexities and parameters required in drone control systems. While the project is still in progress, these early investigations already show promise. The findings from the preliminary simulations are a good fit for a comprehensive examination of the Hybrid-GWO algorithm's potential in optimizing PID controllers for quadcopters. This research aims to contribute valuable insights to the field, ultimately enhancing the efficiency and improvement of the existing drone systems.</p> Akshay Kalash, Lakshmish T.G, Koritala Gopi Chowdary, Kavya N Pujari, Sumaiya M N Copyright (c) 2024 Journal of Soft Computing and Computational Intelligence Thu, 25 Jan 2024 00:00:00 +0000 Real-Time Sign Language Translation using the KNN Algorithm <p>Addressing the imperative of bridging communication barriers between the deaf and non-verbal communities this project centres on advancing automated American Sign Language (ASL) recognition through key-point detection-based methodologies. A comprehensive analysis of the model‘s efficacy is conducted, employing rigorous testing methodologies and metrics like F1 score, precision, and recall to ascertain optimal performance. By delving into the nuances of ASL recognition, the project seeks to enhance the accuracy and reliability of machine learning models in deciphering sign language gestures. Additionally, the implementation of a user-friendly graphical user interface (GUI) facilitates seamless interaction, empowering users to effortlessly engage with the system and generate predictions utilizing the most proficient machine learning algorithms. Through this endeavour, the aim is not only to enhance accessibility for the deaf and non-verbal communities but also to foster inclusivity by providing a platform for effective communication between individuals utilizing ASL and those who rely on verbal communication. This interdisciplinary approach merges technological innovation with social responsibility, paving the way for a more inclusive and connected society.</p> Manish Kumar, Sridevi G M, Gourav Mishra, Ayush Kumar, Aditi Patni Copyright (c) 2024 Journal of Soft Computing and Computational Intelligence Sat, 06 Apr 2024 00:00:00 +0000 Applying Reinforcement Learning as Part of Recursive Privacy in Cyber Space <p>In the rapidly evolving landscape of cyberspace, ensuring privacy has become a paramount concern. Traditional privacy-enhancing techniques often fall short of addressing the dynamic and complex nature of modern cyber threats. In response to this challenge, the concept of Recursive Privacy has emerged, offering a layered approach to privacy protection. This paper explores the integration of reinforcement learning, a powerful machine learning paradigm, into the Recursive Privacy framework to enhance privacy preservation in cyberspace. We begin by reviewing existing literature on privacy-preserving techniques and reinforcement learning algorithms. We then propose a framework for Recursive Privacy, outlining its key principles and layering approach. Next, we delve into the potential applications of reinforcement learning in privacy enhancement, discussing how reinforcement learning algorithms can optimize privacy-preserving mechanisms at each layer of the Recursive Privacy framework. Through case studies and real-world examples, we illustrate the practical implications of applying reinforcement learning in privacy protection. Despite its promises, challenges such as the need for large-scale training data, model interpretability, and robustness to adversarial attacks remain. We identify research gaps and opportunities for future exploration in the integration of reinforcement learning and Recursive Privacy. By leveraging reinforcement learning techniques within the Recursive Privacy framework, organizations can establish a more adaptive and resilient approach to privacy protection in cyberspace, safeguarding sensitive information and preserving individual privacy in the face of evolving cyber threats.</p> Mangadevi Atti, Manas Kumar Yogi Copyright (c) 2024 Journal of Soft Computing and Computational Intelligence Sat, 06 Apr 2024 00:00:00 +0000 Sign Language Recognition for Dumb & Deaf People using Python, OpenCv & Tensor Flow <p>This study examines the various stages of an automatic system for the identification of sign language (SLR). A large dataset and the best algorithms must be used to train a system that can read and understand a sign. In current society, there is a lack of communication with the deaf. The use of Sign Language (SL) helped to break down this barrier as it uses visually conveyed sign patterns to communicate meaning to non-sign language users. It is also useful in communicating with individuals suffering from autism spectrum disorder (ASD). Normal people cannot understand the signs used by deaf people, as they do not know the meaning of a particular sign. The system presented is intended to address this issue. The system captures various gestures of the hand by using a webcam. Pre-processing of the image takes place, then, determination of edges occurs by using object detection. Finally, a template-matching algorithm identifies the sign and displays the text. The output is in a textual format so one can easily interpret the meaning of a particular sign. This also curtails the difficulty of communicating with the deaf. The implementation of the system is by creating libraries then using tensor flow object detection pipeline configuration for object detection and finally running the model in real-time by using OpenCV in Python in real time and obtaining an audio message of the indicated hand sign.</p> Abhishek Pandey, Snehal Demapure Copyright (c) 2024 Journal of Soft Computing and Computational Intelligence Fri, 12 Apr 2024 00:00:00 +0000 Design and Implementation of Agri Farm Application Using ResNet Deep Learning Model <p>This project introduces an innovative website designed to enhance agricultural productivity and support farmers in India, where a significant portion of the population relies on agriculture for their livelihood. Leveraging the potential of machine learning and deep learning technologies, the website offers three applications: crop recommendation, fertilizer recommendation, and plant disease prediction. The crop recommendation application allows users to input soil data, based on which the system suggests the most suitable crops to cultivate, thereby aiding farmers in making informed decisions about their farming practices. In the fertilizer recommendation application, users specify their soil data along with the crop they are cultivating. In India, where a sizable section of the population depends on agriculture for a living, this project provides a cutting-edge website created to support farmers and increase agricultural output. Crop recommendation, fertilizer recommendation, and plant disease prediction are the three applications offered by the website, which make use of the capabilities of machine learning and deep learning technology. The datasets that have been tested and trained have been taken from Kaggle. In existing,&nbsp;they only offer crops that are healthy or harmful. They only provided 96% accuracy.&nbsp; Crop disease treatment fertilizer recommendations are not made for that particular plant. They have no idea what to do next.&nbsp; It will indicate whether the plant is healthy or unwell. It will indicate the cause of any illness in the plant. Why the plant was impacted and offers the plant a remedy. Additionally, it recommends fertilizer based on the plant's needs we have achieved 99% accuracy.&nbsp;</p> Logeshwari S, Padma Priya K, Dharani S, Yoga Lakshmi S Copyright (c) 2024 Journal of Soft Computing and Computational Intelligence Fri, 12 Apr 2024 00:00:00 +0000