Abstract : This paper proposes a methodology leveraging Data Science and IoT to enhance precision farming practices in the old Mysuru region villages. The aim is to optimize agricultural yield and resource management through advanced technology integration. The proposed system utilizes IoT sensors for real-time data collection on soil parameters such as nutrient levels, moisture content, and temperature across 500 farm lands. These sensors, including the JXCT Soil NPK Sensor, facilitate continuous monitoring and data acquisition, overcoming the limitations of traditional periodic sampling. Data Science techniques are employed to analyze the collected data, utilizing machine learning algorithms to derive actionable insights. This analysis aids in understanding soil health dynamics, predicting crop yields, and optimizing fertilizer and water usage. The system also incorporates an Android-based mobile application for seamless data visualization, remote monitoring, and decision support for farmers. The block diagram illustrates the architecture of the proposed system, highlighting the integration of IoT devices, cloud-based data storage, and machine learning models. Data flows from the sensors to the cloud, where it undergoes preprocessing, analysis, and storage. Farmers access the processed information through the mobile app, enabling informed decision-making in real time. This approach aims to transform traditional farming practices into data-driven precision agriculture, enhancing productivity, sustainability, and economic viability in the old Mysuru region villages. The effectiveness of the proposed methodology is validated through the analysis of 500 datasets, demonstrating its potential to revolutionize agricultural practices in the region..
Full article

Abstract : The rapid expansion of 5G mobile communication networks, driven by the development of new services and mobile applications, is expected to increase the demand for frequency and bandwidth resources. This growing demand can lead to issues such as reduced speed and increased latency in future cellular networks. Non-Orthogonal Multiple Access (NOMA) is a promising method to address these challenges. NOMA strives to improve user equity, dependability, spectral efficiency, and connectivity, while simultaneously boosting data speeds, adaptability, and decreasing transmission delays. It also improves cell-edge throughput and overall network performance, making it an essential technology for the next generation of mobile networks. several methods have been developed based on the NOMA techniques, however ever increasing demand of mobile communication raised several challenges therefore a robust mechanism is required to deal with the performance related issues in 5G and 6G communication systems. In this work, we focus on these issues and introduced a novel and hybrid mechanism of NOMA where puncturing, interleaving and Turbo coding methods are combined together to develop a robust communication system for both uplink and downlink communication setups. Integrating Turbo codes with interleaving and puncturing in a NOMA 5G system enhances performance by mitigating burst errors, optimizing code rate for bandwidth efficiency, and providing robust error correction. This combination ensures advanced data rates, enhanced spectral efficiency, and improved the quality of service. A thorough experimental analysis is conducted to authenticate the effectiveness of the proposed model. The experimental analysis reveals that the proposed model outperforms existing cooperative, zero forcing (ZF) and maximal ratio combining (MRC) based NOMA systems..
Full article

Abstract : This study explores the enhancement of speech intelligibility in hearing aids using spectral subtraction techniques. Environmental noise often degrades the quality of speech signals, posing significant challenges for individuals with hearing impairments. Spectral subtraction, a widely recognized noise reduction method, is employed to mitigate these challenges. The study investigates the effectiveness of spectral subtraction in improving speech intelligibility by evaluating objective metrics. Objective measures such as the Perceptual Evaluation of Speech Quality (PESQ), Short-Time Objective Intelligibility (STOI), and Log Likelihood Ratio (LLR) are utilized to assess the performance of the spectral subtraction algorithm. The results demonstrate that spectral subtraction significantly enhances speech intelligibility and quality, making it a viable solution for improving hearing aid performance in noisy environments. PESQ scores improved by approximately 5% to 58%, and STOI scores improved by around 2% to 23%, while LLR scores improved by around 40% to 68% at low SNR levels. This research contributes to the development of more effective hearing aids, ultimately improving the quality of life for individuals with hearing impairments..
Full article