Engineering Genesis

AI- Powered Deaf Companion System for Inclusive Communication between Deaf and Hearing Individuals

I. Janani, S. Brindhashree, M. Boomika, M. Sahana Preethi — Thu, 10 Jul 2025 00:00:00 +0000

Sign language is the usual means of communication used by speech and hearing disabled people, and Bengali Sign Language (BdSL) is especially difficult with its large vocabulary, alphabet, and diverse expressions. Conventional remedies like mastering BdSL or employing an interpreter tend to be expensive and hard to obtain. Machine translation of sign language provides a more accessible solution, and deep learning, especially computer vision, holds much promise. To meet this, we created KUNet, a CNN-based classifier optimized with Genetic Algorithms (GA) to classify BdSL gestures.
KUNet attained 99.11% accuracy on the KU-BdSL dataset and surpassed a number of state-of-the-art models. Explainable AI (XAI) was also utilized to explain the model’s decision process, increasing its transparency. The study seeks to develop a BdSL machine translator, which will benefit the non-verbal and hearing-impaired community since it will facilitate easy communication and less dependency on expensive interpreters.

Breaking Boundaritrges: Intelligent Systems in the Next Era

Thu, 10 Jul 2025 00:00:00 +0000

The sudden emergence of intelligent systems heralds a revolutionary change in various industries, but their potential is still not fully tapped in areas such as agriculture, tourism, healthcare, network security, education, banking, and social media. This study examines how intelligent systems, driven by machine learning and anytime algorithms, can solve intricate problems in these areas. Existing applications show promise in signal interpretation, real-time diagnostics, repair automation, and mobile control, yet their integration across different industries will necessitate novel approaches. Our approach takes advantage of artificial intelligence methods, such as supervised learning, reinforcement learning, and anytime algorithms, to construct and test experiments specific to different domains. We model intelligent systems for applications ranging from crop yield prediction, analysis of tourist behavior, medical diagnosis, intrusion detection, adaptive learning platforms, preventing financial fraud, and social media trend prediction. Main findings identify that these systems attain up to 92% predictive accuracy and minimize operational latency by 40% over the conventional approach with anytime algorithms ensuring flexibility under timing constraints. We find that smart systems, when designed to niche markets, provide scalable, effective solutions, setting the stage for increased adoption. Interoperability and ethics frameworks will be the areas of future work to continue the momentum.

The Silent Battle: State Sponsered Cyber Attacks

S. Kaviya, R. Shanmugapriya, V. Balaji, N. Sabariraja, S. Kumaravel — Thu, 10 Jul 2025 00:00:00 +0000

State-sponsored cyberattacks have become a significant instrument of statecraft in the digital age, influencing global security dynamics and international relations. The synthesis of current research and case studies including high-profile events like the Dark Seoul attack this review paper investigates the motivations, techniques, and effects of such cyber operations from 2005 to 2024. Emphasizing the growing frequency and complexity of cyberattacks, especially those aimed at espionage, disruption, and sabotage, the paper investigates the political, economic, and military elements driving state action in cyberspace. Key trends are highlighted, including the concentration of cyberattacks among a small number of state actors and the increasing targeting of both government and private sector organizations. The study also highlights the rising use of cyberspace in continuous geopolitical wars and the weaknesses in vital infrastructure. The article argues for the creation of thorough cybersecurity plans including international norms, legal systems, and diplomatic initiatives to improve global cooperation and reduce risks in reaction to these challenges. This study lays a basis for comprehending the consequences of state-sponsored cyberattacks by means of the intricate interaction between cyberspace and geopolitical interests and provides ideas for future policy creation and research to handle this changing global security issue.

The Dark Web Threat Intelligence

R. Hemavarshini, R. Deepika, V. Nandhakumar, A. Surendher, S. Kumaravel — Thu, 10 Jul 2025 00:00:00 +0000

The dark web is a hidden part of the internet that is often used for illegal activities, including cybercrime, data breaches, and illicit trade. As cyber threats continue to evolve, organizations and security professionals are increasingly leveraging dark web threat intelligence to detect risks, monitor criminal activities, and prevent cyberattacks. This paper explores the significance of dark web threat intelligence, its sources, and the challenges associated with collecting and analyzing data from hidden marketplaces forums, and encrypted networks. Additionally, we discuss the role of automated tools and machine learning in identifying threats, along with ethical and legal concerns in dark web monitoring. By understanding dark web intelligence, organizations can strengthen their cybersecurity defenses and mitigate potential risks before they escalation.

AI Application for Sustainable Agriculture Crop Disease and Pest Detection

P. Libisha, K. Babi Kumar, M. Karthik, R. Visinruban, R. Mohana Santhiya — Mon, 08 Dec 2025 07:59:05 +0000

The use of AI and remote sensing (RS) technologies is transforming the agricultural pest and disease management with the ability to monitor, detect, and predict early and in real-time. Such innovations are aiding in solving major problems in agriculture like climate change, resources scarcity, and pest infestation. The use of AI-driven tools is especially successful in precision agriculture, optimization of irrigation, soil management and pesticide application. Pest outbreaks are now forecasted, pest actions examined, and intervention targeted to minimize crop loss through the use of satellite imaging, drones, machine learning models, and decision support systems (DSS). Already, AI applications such as Plantix, Leaf-Byte, and Cotton Ace are helping farmers detect pests and diseases to enable them to practice farming in a more sustainable and efficient manner. With the further development of these technologies, farmers are turning to AI to enhance the health and productivity of crops and reduce environmental effects.

In-House Product Transportation using IOT

B. Lalitha, D Salem Noel, K. Sudarshan, S. Ashish Prithvi — Mon, 08 Dec 2025 08:16:01 +0000

This project introduces an innovative Electric Vehicle (EV) system designed to automate the internal transportation of industrial products, making operations more efficient, safer, and less physically demanding for workers. By replacing traditional fuel-powered vehicles with electric ones, the system helps reduce carbon emissions and significantly lowers operational costs. It integrates seamlessly with existing infrastructure and operates 24/7 with minimal downtime, ensuring continuous productivity. With its low-maintenance design, the system offers long-term reliability and scalability, making it a cost effective investment for businesses. Additionally, the system’s ability to reduce reliance on fossil fuels aligns with sustainability goals, contributing to a greener, more eco-friendly industrial environment. Ultimately, this EV system presents a smarter, more sustainable approach to internal transportation, benefiting both businesses and the planet.