Most contemporary businesses are embracing software defined networking (SDN), a developing architecture that enables an aerial-like perspective of the entire network. SDN operates by virtualizing the network and provides advantages including improved performance, visibility, speed, and scalability. SDN attempts to divide the network control plane from the forwarding plane. The control plane, which includes one or more controllers and incorporates complete intelligence, is thought of as the brain of the SDN. However, SDN has challenges with controller vulnerability, flexibility, and hardware security. But distributed denial of service (DDoS) assaults constitutes a serious threat to the SDN. Transmission control protocol-synchronized (TCP-SYN) floods, a common cyberattack that can harm SDNs, can deplete network resources by opening an excessive number of illegitimate TCP connections. In this research, we provide an OpenFlow port statistic-based architecture for machine learning (ML) enabled TCP-SYN flood detection. This research showed that ML models like support vector machine (SVM), Navie Bayes, and multi-layered perceptron can distinguish between regular traffic and SYN flood traffic and can mitigate the impacts of the attacking node on the network. Results showed that the multilayered perceptron can classify the traffic with highest accuracy of 99.75% for the simulation dataset.

Sustainable agricultural management relies heavily on accurate soil fertility prediction. Traditional assessment techniques are often labour-intensive, time-consuming, and may involve hazardous chemicals. Recent advances in machine learning (ML) and artificial intelligence (AI) offer promising alternatives by integrating soil metrics, meteorological data, and other environmental factors for precise and efficient fertility estimation. This study investigates the application of ML and deep learning algorithms for soil fertility prediction. A hardware prototype incorporating sensors and a microcontroller was developed to capture soil parameters, including pH, temperature, humidity, moisture content, NPK (nitrogen, phosphorus, potassium), carbon content, and organic matter, alongside weather and climatic conditions. Real-time sensor data were compared against predictions from ML models. Laboratory soil test results were used as ground truth for validation. Ensemble classifiers (Random Forest, Extra Trees) and deep learning models (Multilayer Perceptron, Long Short-Term Memory networks) were evaluated using accuracy, F1-score, recall, and precision metrics. The Random Forest algorithm achieved the highest prediction accuracy of approximately 92%, with Extra Trees and other ensemble methods also demonstrating strong performance. The deep learning models further enhanced predictive capabilities for crop selection, with MLP and LSTM achieving high accuracy, recall, and F1-scores while maintaining consistent precision. The hardware prototype’s real-time measurements closely aligned with laboratory results, confirming the reliability of the system. The findings highlight the potential of ML and AI-based approaches in advancing soil fertility prediction and crop recommendation systems. By combining real-time sensor data with predictive models, the proposed system enables rapid, reliable, and scalable soil health assessment. This integrated approach empowers farmers to make data-driven decisions, optimize soil fertility, and improve sustainable agricultural practices.

The advent of digital technology has revolutionized the way we keep track of time. Digital watches have become an essential part of our daily lives and provide us with accurate and reliable time measurement. However, battery reliability is a long-standing issue in the digital watch industry. Batteries require frequent replacement and are a major source of waste. To solve this problem, a digital watch that runs on a lithium-polymer battery that is recharged by a voltage generated by a thermoelectric generator (TEG) placed on the hand. The proposed model uses TEG1-19913 that generates power in the range of 11.5 W to 14.5 W with hot end basking at 250 °C and a cold end between 30 °C and 50 °C. The TEG voltage is used to charge the lithium polymer battery, eliminating the need for conventional charging methods. The watch is designed to be compact and lightweight, so it can be worn comfortably for extended periods of time. The TEG is integrated into the watch strap and ensures that it is constantly in contact with the skin. The lithium-polymer battery used in the watch is a high-performance rechargeable battery that has high energy density and long life. In summary, the proposed digital watch is an innovative ecological solution to the problems associated with traditional battery-powered watches. The compact and light design of the watch combined with the energy-efficient display makes it a convenient and efficient timekeeping device.

Tamil is a language that has the most extended history and is a conventional language of India. It has antique origins and a distinct tradition. A study reveals that at the beginning of the twenty-first century, more than 66 million people spoke Tamil. In the present time, image synthesis from text emerged as a promising advancement in computer vision applications. The research work done so far in intelligent systems is trained in universal language but still has not achieved the desired development level in regional languages. Regional languages have a greater scope for developing applications and will enhance more research areas to be explored, ruling out the barrier. The current work using Auto Encoders failed at the point of providing vivid information along with essential descriptions of the synthesised images. The work aims to generate embedding vectors using a language model headed by image synthesis using GAN (Generative Adversarial Network) architecture. The proposed method is divided into two stages: designing a language model TBERTBASECASE model for generating embedding vectors. Synthesising images using Generative Adversarial Network called BASEGAN, the resolution has been improved through two-stage architecture named HYBRID SUPER RESOLUTION GAN. The work uses Oxford-102 and CUB-200 datasets. The framework efficiency has been measured using F1 Score, Fréchet inception distance (FID), and Inception Score (IS). Language and image synthesis architecture proposed can bridge the gap between the research ideas in regional languages.