Volume 15 Issue 13

The rapid growth of digital communication requires data security. Steganography is most used method for data hiding. Steganography is an art of hiding secrete data for secure communication. Among various methods of steganography video steganography is widely used due to its high embedding capacity. Video signal is a combination of frames so it brings maximum possibilities to hide maximum amount of data. This paper presents unified framework of video steganography. The proposed method includes video steganography where we can used text, image or small video as a secrete data. Huffman coding is used to compress secrete data, reducing the embedding capacity requirements and enabling a higher payload. Huffman coding is lossless compression technique. The compressed secrete data then embedded into the cover video by transform domain technique. The effectiveness of the proposed technique is given by experimental results. Peak signal to noise ratio (PSNR), Mean square error (MSE), Signal to noise ratio (SNR), Pixel similarity accuracy are some of output terms which are compared for different size of secrete data.

The Jal Jeevan Mission (JJM), launched by the Government of India in 2019, aims to provide safe and adequate drinking water through Functional Household Tap Connections (FHTC) to all rural households. This research paper evaluates the environmental impacts of rural water supply schemes implemented under JJM. The study analyzes positive impacts such as improved water quality, reduction in waterborne diseases, and sustainable water management, as well as potential environmental challenges including groundwater depletion and infrastructure-related ecological disturbances. The findings suggest that while JJM significantly improves rural living standards, proper environmental management and sustainable water resource planning are essential for long-term success.

Generative Artificial Intelligence (Gen AI) is revolutionizing the education sector by facilitating personalized self-guided learning with intelligence. In this paper, we propose an AI-based Smart Study Assistant by using Generative AI methods for supporting students in academic works. It uses artificial intelligence for subject-related questions, summarizing lengthy study materials, making notes and assignment help. It achieves this through the application of natural language processing (NLP) and large language models, which allow the system to understand user queries and generate relevant responses. Also provides concept explanation, question generation, doubt solving in real time, making learning more interactive and efficient. According to this study, Generative AI can leverage student productivity and maximize their learning curve. This proposed solution provides an example of how AI can transform education by making learning more intelligent and responsive. Future improvements might encompass voice interactivity, multilingual service, and academic database integration.

Accurate atmospheric data is essential for weather forecasting, aviation safety, and climate research. However, real-world data collection methods such as ra-diosonde launches are limited by high operational costs, sparse temporal availability, and restricted geographical coverage. To address these challenges, this paper proposes AtmosGen (Atmospheric Synthetic Data and Image Generator), a condition-aware syn-thetic atmospheric data and image generation framework that combines numerical data synthesis with atmospheric image generation. The system utilizes historical radiosonde data to generate realistic synthetic atmospheric parameters, including temperature, pres-sure, humidity, wind speed, and altitude, using machine learning-based generative mod-els. In addition, a conditional image generation model is employed to generate atmo-spheric and weather-condition images corresponding to different environmental states such as clear sky, cloudy, foggy, and stormy conditions. To ensure the reliability of the generated data, a compatibility evaluation model is introduced, which verifies the consistency between input atmospheric conditions and the generated images using sta-tistical similarity metrics and regression-based validation. Furthermore, a compara-tive analysis between original radiosonde datasets and model-generated datasets is per-formed using distribution analysis, correlation metrics, and downstream task perfor-mance evaluation. The proposed approach reduces dependency on continuous real-time data acquisition while providing scalable, diverse, and scientifically consistent datasets. This framework is particularly useful for aviation simulations, machine learning model training, and atmospheric research where large labeled datasets are required.

Diabetic Retinopathy (DR) is one of the most common causes of preventable blindness among diabetic patients worldwide. Early detection and timely treatment are essential to prevent severe vision impairment. However, manual screening of retinal fundus images is a time-consuming process that requires expert ophthalmologists and may lead to diagnostic inconsistencies. Recent advancements in artificial intelligence and medical image analysis have enabled the development of automated diagnostic systems capable of assisting clinicians in detecting retinal abnormalities. This research proposes an en- hanced fundus image analysis framework for accurate detection of diabetic retinopathy using advanced image preprocessing and deep learning techniques. The proposed system incorporates image enhancement methods including noise removal, contrast limited adaptive histogram equalization, and image normalization to improve the visibility of retinal lesions such as microa- neurysms, hemorrhages, and exudates. A convolutional neural network (CNN) architecture is employed to automatically extract discriminative features and classify retinal images into different stages of diabetic retinopathy. The model is trained and evaluated using publicly available retinal image datasets. Experimental results demonstrate that the proposed approach achieves high classification accuracy and improved sensitivity compared to traditional machine learning approaches. The system provides a reliable computer-aided diagnostic tool for large-scale screening programs and can significantly assist ophthalmologists in early detection of diabetic retinopathy. Future research will focus on integrating explainable artificial intelligence techniques to improve interpretability and clinical acceptance of automated diagnostic systems.

This paper presents a technological solution that uses a collaborative robotic (cobot) system to boost both sustainability and productivity in agriculture. The system architecture is built around ROS 2 and a Raspberry Pi, which control a mobile rover and a robotic arm that work together to monitor plants and apply precise treatments. The rover navigates the environment using sensor fusion and cameras to collect real-time data on plant health. A comprehensive plant database allows the cobot to identify plant species and diagnose diseases by cross-referencing this data stream with known symptoms. Once a problem is found, the robotic arm uses its precise, multi-axis control to deliver a minimal, targeted dose of pesticide. This data-driven approach significantly cuts down on pesticide use, minimizes environmental impact, and saves resources while also improving crop yield and quality through accurate, immediate treatment. The paper details the system's design, its ROS 2-based algorithms for navigation and plant recognition, and its mechanisms for precision application, demonstrating its potential to transform sustainable agriculture.

Farming plays an essential role in supporting the economy of many nations. In developing countries particularly, a large number of people depend on agriculture as their main source of income and daily sustenance. Cotton is regarded as one of the most valuable commercial crops because it provides the primary raw material for textile manufacturing industries worldwide. However, cotton cultivation is frequently affected by several leaf diseases that weaken plant growth and reduce both the amount and quality of harvested fiber. When such infections remain unnoticed during early growth stages, they can spread quickly and cause serious losses for farmers. For this reason, identifying cotton leaf diseases at an early stage is extremely important for protecting crop health and maintaining agricultural productivity. In many agricultural settings, farmers determine plant health by visually examining leaves in the field. Although this practice has been used for generations, it often requires considerable effort and time and may not always result in correct diagnosis. Environmental variations and the limited availability of trained agricultural specialists in rural areas can further complicate disease recognition. With the advancement of artificial intelligence and deep learning, researchers are increasingly exploring automated techniques to assist in plant disease identification. This study proposes an intelligent system that analyzes cotton leaf images to detect disease symptoms. A Convolutional Neural Network is used to learn visual characteristics from the images. Image preparation steps such as resizing, normalization, and augmentation improve model learning ability. Such systems can support farmers in recognizing infections earlier, reducing losses and encouraging technology-driven farming

Plant diseases significantly affect agricultural productivity and food security worldwide. Recent advances in deep learning have enabled automated plant disease detection systems with high classification accuracy. Among these approaches, convolutional neural networks (CNNs), ensemble learning techniques, and explainable artificial intelligence (XAI) methods have emerged as promising solutions. This review presents a comprehensive analysis of recent developments in plant disease detection from 2022 to 2026, focusing on deep learning architectures, ensemble models, benchmark datasets, and explainability techniques. Various publicly available datasets, including PlantVillage, PlantDoc, Plant Pathology 2021, and PlantCLEF, are systematically compared. Furthermore, performance benchmarks of CNN-based models, Vision Transformers (ViTs), hybrid architectures, and ensemble frameworks are reviewed. Research gaps, challenges, and future research directions are identified to guide the development of reliable, interpretable, and field-deployable plant disease detection systems.

The construction industry is undergoing a significant transformation due to the adoption of advanced digital technologies such as Artificial Intelligence (AI), Building Information Modeling (BIM), and data analytics. Among these innovations, generative artificial intelligence has emerged as a powerful tool capable of improving decision-making processes and automating complex analytical tasks. One of the major challenges in construction project management is achieving accurate cost estimation and maintaining effective budget control throughout the project lifecycle. Traditional cost estimation methods mainly depend on historical data, manual calculations, and professional experience, which can sometimes result in inaccurate forecasts and financial inefficiencies.   Generative AI offers new possibilities for construction management by analysing large datasets, identifying hidden patterns, and generating predictive models that assist project managers in making informed financial decisions. This research paper examines the potential role of generative AI in improving construction cost estimation and optimizing project budgets. The study explores how AI-based systems can support automated quantity take-offs, predictive cost modelling, real-time cost monitoring, and efficient resource allocation.   The research also analyses the advantages and limitations associated with implementing generative AI technologies in the construction sector. The findings suggest that generative AI can significantly improve cost estimation accuracy, reduce financial risks, and enhance project planning. However, effective implementation requires reliable digital infrastructure, high-quality datasets, and trained professionals with expertise in AI technologies. The study concludes that generative AI has the potential to transform construction cost management practices and contribute to more efficient and sustainable project execution.

The rapid growth of digital communication requires data security. Steganography is most used method for data hiding. Steganography is an art of hiding secrete data for secure communication. Among various methods of steganography video steganography is widely used due to its high embedding capacity. Video signal is a combination of frames so it brings maximum possibilities to hide maximum amount of data. This paper presents unified framework of video steganography. The proposed method includes video steganography where we can used text, image or small video as a secrete data. Huffman coding is used to compress secrete data, reducing the embedding capacity requirements and enabling a higher payload. Huffman coding is lossless compression technique. The compressed secrete data then embedded into the cover video by transform domain technique. The effectiveness of the proposed technique is given by experimental results. Peak signal to noise ratio (PSNR), Mean square error (MSE), Signal to noise ratio (SNR), Pixel similarity accuracy are some of output terms which are compared for different size of secrete data.

Drug discovery traditionally is a long and expensive process. It requires huge financial investment and can possibly take more than a decade to develop a single drug. In this paper, It has been explored how generative AI is changing this process. By using advanced models, generative AI can design new drug molecules, predict their properties, improve efficiency by reducing both time and cost required for research to get precise and accurate data. These models can generate drug candidates with better binding affinity and drug like properties, making the selection process more reliable. It is also being used across different stages of drug discovery, from identifying targets to monitoring drug safety. Although generative AI has great potential to transform drug discovery by making it faster, more efficient and accurate, there are still some challenges like the need for high quality data, lack of model transparency, regulatory concerns and more real world testing and comparison. These improvements are still needed for its full adoption.