This research paper examines the integration of Solar powered Electric Vehicle (EV) Technology into sprayer systems designed for small-scale and horticultural farming. As sustainable agriculture gains importance, there is an increasing need for eco-friendly and efficient farming methods. Traditional diesel-powered sprayers contribute to both air and noise pollution and face challenges with maintenance and fuel availability. To address this, the study explores the feasibility and advantages of shifting to solar -powered sprayer systems that leverage adaptable EV platforms. By proposing an innovative solution to update spraying operations for small-scale and horticultural farms, this research contributes to the field of sustainable agriculture. The findings highlight the potential of Solar powered EV-integrated sprayer systems to transform farming practices, providing a cleaner, more efficient alternative to conventional diesel-powered equipment and significantly reducing environmental impact.

Keywords : Solar, Electric Vehicle, Farming, Sprayer, Agriculture.

Authors : SIVA KUMARI

Title : Solar Powered Electric Vehicle Integrated Sprayer System for Sustainable Small Scale and Horticultural Farming

Volume/Issue : 2025;7(2 (March - April))

Page No : 47 - 51

Talent acquisition and placement are critical processes in human resource management, yet they often face inefficiencies due to manual screening, bias, and mismatched hiring decisions. Finding suitable candidates for an open role could be a daunting task, especially when there are many applicants. It can impede team progress for getting the right person on the right time. In traditional models, they use ML technologies like KNN, and NLP on text based screen resuming which has limitations such as a bias, inefficiency and lack of personality assessment. To addressing this challenges we proposed a deep learning based framework for talent acquisition and placement using CNN and RNN. Comparing to the traditional models this system enhances improving accuracy, reduces recruiter workload to better workflows placement and talent acquisition. This enhances efficiency, improves decision-making, and ensures optimal talent placement in organizations.

Keywords : Academic Talents, Industry Opportunities, Higher Education, Graduate Skills, Workforce Alignment.

Authors : K.S.Shaheena

Title : A Deep Learning Framework for Optimizing Talent Acquisition and Placement

Volume/Issue : 2025;7(2 (March - April))

Page No : 47 - 51

UniRetail is an innovative mobile application designed to revolutionize retail operations by integrating advanced machine learning ML capabilities and modern technologies. The platform enables retailers to centralize and streamline critical functions, including inventory management, dynamic pricing, and targeted promotions, while delivering a seamless, personalized shopping experience for customers. Machine learning algorithms are at the core of UniRetail, empowering store owners with predictive analytics for demand forecasting, personalized product recommendations using collaborative filtering, and customer segmentation through clustering techniques. Natural language processing NLP enhances product search and filtering, while sentiment analysis refines customer feedback to improve service quality. Additionally, fraud detection models ensure secure and efficient multi-payment checkouts. UniRetail’s robust, cloud-based architecture, built on microservices, supports scalability and integrates seamlessly with existing retail systems. The use of technologies like TensorFlow, PyTorch, and Apache Spark ensures efficient data processing and real-time ML model deployment through Kubernetes and AWS SageMaker. By uniting operational efficiency, data driven insights, and customer engagement, UniRetail aims to be a transformative tool for modern retail enterprises, helping them thrive in the digital landscape.

Keywords : Retail Operations, ML, Personalized Shopping,, Inventory Management, NLP, Fraud Detection.

Authors : M. Anjankumar

Title : A Personalized Digital Billing For Modern Retailers

Volume/Issue : 2025;7(2 (March - April))

Page No : 40 - 46

The By employing a machine learning algorithm to analyse traffic and identify intrusions, intrusion detection systems assist in identifying damaging hostile attacks in wireless sensor networks. The RSA encryption method is used to boost the performance of the wireless sensor network while also improving the security of data transmission. The goal of this research is to develop a hybrid algorithm for network intrusion detection in wireless sensor networks. This approach combines the principles of decision tree, convolutional neural networks (CNNs), and RSA encryption. Through the integration of these cutting-edge techniques, a comprehensive security solution for crucial applications is offered. This integration improves not only the detection and prevention of intrusions but also guarantees the confidentiality and integrity of sensitive data transmitted across wireless sensor networks.

Keywords : Convolutional Neural Network, Decision Tree Algorithm, RSA Encryption.

Authors : Adline Jancy

Title : A Hybrid Cnn and Decision Tree Based Intrusion Detection System For Secure Wireless Sensor Networks

Volume/Issue : 2025;7(2 (March - April))

Page No : 33 - 39

The goal of this project is to develop a sophisticated and intelligent system that tracks soil moisture levels and detects human and animal movement when it approaches crops and PIR motion sensors. Please notify us of any changes so that we can address them, identify them, and set up crop protection strategies to stop insect-related losses. Temperature sensors can also be used to track humidity and temperature. It aids in comprehending how plants behave under various weather circumstances. The humidity and temperature will be shown so that the farmer can take appropriate action if the weather is excessively hot and the soil's moisture content percentage is low. In advance. shields your house from flooding and extreme heat. In In order to enable IOT devices, such as sensors, to take actions depending on predetermined conditions and to store and display real-time data on the microcontroller, we will utilise the ESP8266 microcontroller Wi-Fi module in this project. Users may see the sensor readings displayed on both the Android app and the I2C LCD display, enabling convenient access to data from the device.

Keywords : Soil, Android application, IoT, Humidity, Microcontroller.

Authors : Yashwanth

Title : Low-Cost Embedence Meter for Soil Water Content Measurement using Internet of Things

Volume/Issue : 2025;7(2 (March - April))

Page No : 26 - 32

Automated detection and diagnosis of pulmonary diseases such as pneumonia, tuberculosis, lung cancer, and COVID-19 play a crucial role in improving patient outcomes and reducing healthcare burdens, especially in the context of the ongoing global pandemic. In this research, we propose a deep learning-based approach for the accurate and efficient detection of these diseases from medical imaging data. Leveraging convolutional neural networks (CNNs) and advanced image processing techniques, we develop models capable of analyzing chest X-rays and CT scans to identify pathological features indicative of pneumonia, tuberculosis, lung cancer, and COVID-19. Through rigorous experimentation and optimization, we achieve high sensitivity and specificity in disease detection, addressing key challenges such as data scarcity, model interpretability, and integration into clinical workflows. Evaluation on diverse datasets and real-world clinical scenarios demonstrates the clinical utility and feasibility of our approach, paving the way for its adoption in healthcare practice. Our findings contribute to advancing the field of medical image analysis and hold promise for improving diagnostic accuracy and patient care in pulmonary medicine, particularly in the context of the COVID-19 pandemic.

Keywords : Deep Learning, CNNs, Medical Imaging, Pneumonia, Tuberculosis, Lung Cancer ,COVID-19 Detection

Authors : Y.Tejaswini

Title : Implementation of Pulmonary Disease Detection Model using Deep Learning

Volume/Issue : 2025;7(2 (March - April))

Page No : 19 - 25

Because of the inherent volatility and complexity of the financial markets, accurately predicting stock prices is a challenging task. By assessing the performance of many predictive models, including Random Forest, Stacked LSTM, Stacked GRU, ARIMA (Auto Regression Integrated Moving Average), network with long short-term memory (LSTM) and support vector machine (SVM), the study seeks to tackle this challenge. We thoroughly evaluate these model’s performance by looking at their capacity for generalization and prediction accuracy. The GRU model outperformed the LSTM model with a substantially lower validation loss of 0.0101 and a training loss of 0.0067, whereas the LSTM model obtained a validation loss 0.5048 with a training loss of 0.0130. The SVM with Support Vector regression (SVR) demonstrated a much larger Mean Squared Error (MSE) of 2878.20, whereas Random Forest model produced an MSE of 85.57. The GRU and LSTM models were further improved by the stacked architectures; the Stacked GRU achieved loss of 0.0361 and the Stacked LSTM achieved a validation loss of 0.9658. Despite being simpler, the ARIMA model yielded a Mean Squared Error of 11.8594. The results of this through investigation show that the GRU and Stacked GRU models perform the best

Keywords : Res-Next CNN, RNN, Deep Neural Network, Computer Vision

Authors : Hari Krishna

Title : Stock Market Price Forecasting Using LSTM And GRU Networks

Volume/Issue : 2025;7(2 (March - April))

Page No : 13 - 18

The rapid advancement in processing power has empowered deep learning algorithms to produce remarkably convincing human-synthesized videos, commonly referred to as "deep fakes." This technological progression raises concerns about potential malicious applications, such as blackmail, manipulation through revenge porn, or the exploitation of political unrest using realistic face-swapping deepfakes. In response to these challenges, we propose a novel deep learning-based technique designed to reliably differentiate between genuine videos and those generated by artificial intelligence. Our approach introduces an innovative method for automatically detecting replacement and recreation deep fakes. Leveraging the capabilities of Artificial Intelligence (AI) to combat AI-driven threats, our system employs a two-step process. Initially, frame-level features are extracted using a Res-Net Convolutional Neural Network (CNN). Subsequently, these features serve as input for training a Deep Neural Network (DNN) based on a Recurrent Neural Network (RNN) architecture. To assess the effectiveness of our method, we conducted extensive evaluations on a substantial and diverse dataset. This dataset was meticulously curated by combining various sources, including Face-Forensic++, Deepfake Detection Challenge, and Celeb-DF, aiming to simulate real-time scenarios and enhance the model's performance on real-world data. Our results demonstrate the system's capability to discern alterations in videos, effectively distinguishing between deep fakes and authentic content. Furthermore, we showcase the simplicity and reliability of our approach, illustrating its competitive performance. This research contributes to the ongoing efforts in developing robust solutions for identifying and mitigating the risks associated with the proliferation of AI-generated deep fake content in various contexts.

Keywords : Res-Next CNN, RNN, Deep Neural Network, Computer Vision.

Authors : Harshitha

Title : A Robust Deep Learning approach for Discriminating between Authentic and AI-Generated Videos

Volume/Issue : 2025;7(2 (March - April))

Page No : 8 -12

The increasing prevalence of Internet of Things (IoT) devices in various domains underscores the necessity for robust security mechanisms to mitigate the evolving landscape of cyber threats. This abstract provides a concise overview of the comprehensive study on IoT secure mechanisms. The interconnected nature of IoT introduces unique challenges stemming from the heterogeneity of devices, diverse communication protocols, and often resource-constrained environments. This research delves into the current state of IoT security, emphasizing the critical importance of safeguarding data integrity, user privacy, and the overall functionality of IoT ecosystems. The study explores a spectrum of security mechanisms designed to fortify IoT deployments against unauthorized access, data breaches, and malicious activities. Techniques such as device authentication, secure communication protocols, and encryption methods are analysed in-depth to understand their applicability and effectiveness in diverse IoT scenarios. Acknowledging the dynamic nature of IoT, this research assesses the state-of-the-art advancements in secure mechanisms, considering both theoretical frameworks and practical implementations. Through a thorough examination of the challenges posed by emerging cyber threats, the article contributes to the ongoing discourse on bolstering the security posture of IoT systems.

Keywords : IoT secure Mechanism, Encryption methods, Cyber security basics, Security Protocols.

Authors : SujilathaTada

Title : Securing the Internet of Things: A Comprehensive Overview of IoT Security Mechanisms

Volume/Issue : 2025;7(2 (March - April))

Page No : 1 - 7