KIT- KalaignarKarunanidhi Institute of Technology is an Autonomous Institution located in Coimbatore, Tamil Nadu, India. The college has been approved by the All India Council for Technical Education, affiliated to Anna University, Chennai and accredited by NBA and accredited with 'A' grade by NAAC.The Kalaignar Karunanidhi Institute of Technology was established by Vijayalakshmi Palanisamy Charitable Trust in the year of 2008 in Coimbatore. The colleges offers 8 undergraduate and 7 postgraduate courses.
The integration of solar photovoltaic systems with electric vehicle technology is emerging as a sustainable and promising method to cope with increasing energy demands, mitigate environmental impact, and reduce carbon emissions within residential and transportation sectors. This research focuses on the residential application of a grid-connected solar photovoltaic and electric vehicle integrated system. Also, underscores the benefits of bi-directional electric vehicle batteries in conjunction with rooftop photovoltaic systems. In addition to heuristic price signal dispatch algorithms in the System Advisor Model (SAM) software tool, which rely on manual dispatch and peak shaving analyses, a novel Chaotic Fitness-Dependent Quasi-Reflected Crayfish Optimizer (CFDQRCO) algorithm within the domain of machine learning methodology is employed to enhance the understanding of system dynamics. The innovative technique increases energy efficiency by 54.12% by employing low-cost hybrid renewable energy sources. It achieves a high efficiency of 99.32%, harmonic distortion reduction to 2.67%, while reducing power loss to 0.184kW, outperforming previous research methodologies.
Secure transmission of speech signals has become a critical requirement in modern communication systems such as military networks, telemedicine platforms, and Internet-of-Things (IoT) voice applications. Traditional encryption techniques are not well suited for real-time speech signals due to their large data size and high temporal correlation. Chaos-based cryptography is highly effective because it leverages ergodicity and inherent stochasticity, ensuring that even minor changes in initial conditions result in vastly different outputs. In this paper, a Chaotic Quasi-Oppositional Farmland Fertility Optimization Algorithm (CQOFFA) is proposed for robust speech encryption and decryption. The proposed scheme integrates a chaotic logistic map with Quasi-Oppositional Farmland Fertility Optimization to generate optimized encryption keys and improve search efficiency. Experimental results demonstrate that the proposed method achieves entropy close to 7.99, correlation values near zero, NPCR of 99.62
This paper proposed the methodology for developing a real-time sign language recognition system using web-scraped datasets and image annotation through Roboflow. Models like CNN and RetinaNet were trained using Python frameworks, and text-to-speech tools translated gestures into native and English languages. The system is deployed as a Streamlit-based web application with robust security measures to protect user data. The system provides high accuracy in gesture classes, low latency, and high throughput. This application can be given to the accessibility and human-computer interaction application.
Humans still play a vital role in managing and supervising most chicken farms in Brunei, where factors such as air quality, temperature, lighting, air circulation, humidity, and feeding must be carefully monitored and controlled, as they directly affect productivity. Currently, Brunei faces a high mortality rate among broiler chickens. This study aims to automate the monitoring and control of humidity, temperature, air quality, and feeding systems using Internet of Things (IoT) and Wireless Sensor Networks (WSN) technologies to enhance productivity, reduce mortality, and improve flock health. It reviews the latest developments in both hardware and software for data collection and analysis in poultry farming, supported by examples from existing studies. The software components include data acquisition, analysis, and processing tools, while the hardware setup consists of cameras, lighting systems, and sensor placements for real-time monitoring. A prototype was developed integrating IoT and WSN technologies, enabling continuous evaluation of farm conditions against predefined thresholds. When key performance indicators exceed set limits, the system initiates corrective measures to prevent losses. Additionally, an attention encoder model was proposed for extracting features from chicken images to enhance detection accuracy. Experimental results indicate that incorporating this encoder with DenseNet improves the precision of identifying chicken maturity. The system also includes an SMS alert function to notify users automatically and a web-based interface for visualizing and monitoring key parameters. This study concludes by identifying future directions and challenges for large-scale implementation to ensure sustainable and efficient poultry production in Brunei.
In recent years, bias in textual data has become a major challenge for fairness and inclusivity in AI systems. The proposed work introduces a span-level bias detection model that can find biased phrases and suggest neutral alternatives. Unlike sentence-level classifiers, this system analyzes text at the token level to identify biased segments like stereotypes, generalizations, and unfair assumptions. The model combines contextual embeddings with a fine-tuned transformer-based design inspired by the GUS-Net framework to capture subtle language cues. This approach improves text fairness and supports applications in chatbots, social media moderation, and automated writing assistants. Experimental evaluations show better precision and clarity in detecting biased spans, helping to build responsible and inclusive AI communication systems.
