Authors: Vikash Sharma, Dr. Ramesh Patil

Abstract: The advancement of artificial intelligence (AI) has given rise to two major approaches: traditional machine learning (ML) and deep learning (DL). While traditional ML relies on feature engineering and structured learning approaches, deep learning automates feature extraction through artificial neural networks. This paper explores the differences between these methods, compares their performance across domains such as image recognition, natural language processing, and financial forecasting, and evaluates their advantages and limitations. Experimental results and literature reviews indicate that deep learning excels in handling large datasets and complex patterns, whereas traditional ML is more suitable for smaller datasets with structured features.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Jameer Shaikh, Dr. Usha B Shete, Dr. A. A. Khan, Dr. R. S. Deshpande

Abstract: Early and accurate detection of fruit diseases is critical for minimizing crop losses and ensuring food security. This study in- troduces a novel automated diagnostic framework that leverages hyperspectral imaging combined with deep convolutional neural networks to detect and classify common diseases affecting apples, including blotch, rot, and scab. By analyzing spectral reflectance patterns from 360 nm to 1000 nm, the proposed method identifies subtle biochemical changes in fruit tissues before visual symp- toms manifest. Extensive laboratory experiments demonstrate that the system achieves an overall classification accuracy of 93.7%, outperforming traditional RGB-based image analysis techniques. Furthermore, field trials conducted in commercial orchards validate the robustness and real-world applicability of the system, revealing a 28% reduction in false positive detections and a 35–40% potential decrease in yield losses through timely intervention. The integration of hyperspectral data with deep learning enables a cost-effective, non-destructive, and scalable solution for precision agriculture, supporting proactive crop management and sustainable farming practices.

 

 

Published by: vikaspatanker

Authors: Konka Kishan, Kondoju Prem Kumar, Shaik Feroz Pasha, Ajmeera Sagar Naik

 

Abstract: The recent growth of Deep learning has transformed the area of Image Super-Resolution (ISR) which enables the reconstruction of high-quality images from low-resolution images. The improvement of low quality images to high-quality resolution images. The complete guide provides an in-depth overview of the advanced methodologies and applications of ISR using deep learning. We discuss the basic of ISR, models and algorithms of ISR namely, Generative Adversarial Networks (GANs), Convolutional Neural Networks (CNNs) and attention-based models. We further discuss the applications of ISR such as Medical Imaging, Surveillance, Astronomy, and Autonomous driving. This compiled resource is intended to be a one-stop reference guide to the intricacies of ISR using deep learning and it's many prospects for real-world applications for researchers, practitioners, and students.

DOI: 10.61137/ijsret.vol.11.issue3.149

 

Published by: vikaspatanker

Authors: P.Lavanya, Bibhuti Bhusan Rath, A. Lashya, K. Kirankumar, B. Likitha

 

Abstract: Ensuring consistent and efficient energy harvesting from solar photovoltaic (PV) systems remains a challenge due to unpredictable environmental conditions. To address this, a hybrid Maximum Power Point Tracking (MPPT) technique is presented, combining a conventional perturb-and-adjust method with fuzzy logic-based control. This approach dynamically modifies the control signal for a step-up converter, allowing the PV array to maintain optimal power output. The system's performance was analysed using MATLAB/Simulink under both stable and varying sunlight conditions. Results confirm that the hybrid controller delivers better efficiency, quicker response to changes, and reduced output fluctuations when compared to traditional MPPT strategies. These findings highlight its potential for integration into intelligent solar energy systems.

DOI: http://doi.org/ijsret.vol.11.issue3.148

 

Published by: vikaspatanker

Authors: Ms. Neekita Singh, Dr.Jasbir Kaur, Mrs.Sandhya Thakkar

Abstract: This paper presents a comprehensive framework combining data science, geospatial analysis, and interactive visualizations to study crimes against women in India. Analyzing crime trends includes three key components: using data science, an interactive Power BI dashboard visualization [6], and a Python-based crime hotspot mapping application using Streamlit. The crime hotspot app allows users to search for any location in India and view crime data displayed on a map, potentially aiding in crime prevention by providing real- time awareness [5]. By integrating these tools, the framework offers a multi-faceted approach to crime analysis, enabling deeper insights into spatial and temporal crime patterns. The study aims to assist policymakers, law enforcement, and the public in understanding and mitigating crime.

DOI: http://doi.org/ijsret.vol.11.issue3.147

 

Published by: vikaspatanker

Authors: Ogundare, Adaramola, Raji, Raji, Ajenikoko, Adebeshin, Onot

Abstract: Every power system comprises many generators that are connected in parallel. For the system to operate in steady-state stability, all the generators must run synchronously. If any of the connected generators loses synchronism, system stability is lost, and voltage collapse may occur. To avoid this situation, steady-state stability (SSS), which involves voltage stability and synchronisation of generators, must be monitored. This paper, therefore, focuses on the SSS using the 6-bus IEEE test network and the Nigerian 30-bus, 330 kV grid network as case studies. Power-flow analysis was carried out for the case studies. Static var compensator (SVC) and additional parallel transmission lines were used to carry out voltage improvement for each network. The use of SVC for both IEEE and Nigerian networks indicates better voltage compensation than using transmission line enhancement, but the reverse is true for power loss reduction. The power losses in the 6-bus IEEE for original and improved networks with SVC and additional transmission lines are 1.8 %, 1.6 %. and 1.2 % respectively. At the same time, those of the Nigerian 30-bus, 330 kV network are 4.3%, 3.7%, 3.10%, respectively. Synchronous Power Coefficient (SPC) was used to carry out SSS by considering load additions in steps of 20% to the original and modified networks. SSS of the modified network with SVC and the original network were approximately the same. In contrast, the SSS was improved for the networks modified with additional transmission lines. Since SSS depends on the system inertia during load variation, the inertia of the network modified with the transmission lines is improved, while SVC does not exhibit noticeable inertia properties.

Published by: vikaspatanker

Authors: Anay Sunilkumar Pandya

Abstract: This paper presents the conceptual design and testing of an AI-enhanced, terrain-adaptive energy optimization module for electric two-wheelers. Unlike traditional plug-and-play extenders, this system uses a combination of gyroscopic sensors and machine learning to predict driver behavior and road conditions, optimizing power delivery accordingly. Simulated testing shows potential range improvements of up to 38% while maintaining battery longevity. The innovation is particularly suited for urban EV users in mixed-terrain environments. The invention is novel and under consideration for intellectual property protection.

Published by: vikaspatanker

Authors: Y Kushi Reddy, Yallamanchi Himabindu, Anish NC, CV Anusha Reddy, S Harshit Sai,

 

 

Abstract: In recent years, the integration of artificial intelligence (AI) into healthcare has enabled innovative approaches for early disease detection and diagnosis. This paper presents the design and development of an AI-powered mobile application that performs preliminary health diagnosis based on user-reported symptoms. The proposed system utilizes machine learning models trained on verified medical datasets to identify possible health conditions from input symptoms, aiming to assist users in seeking timely medical consultation. The application is built using Python, TensorFlow, and a Flask-based backend, with a simple and interactive user interface. The system also emphasizes user privacy and data security. Testing demonstrates the model’s potential to deliver reliable symptom-based predictions, thereby offering a scalable and accessible solution to basic health assessment. This project showcases how AI technologies can be effectively applied in the medical domain to bridge gaps in early diagnosis and promote preventive healthcare.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Shankar.K, Mrs.J.ANITHA, M.E.

Abstract: Concrete is the most widely used construction material in the world, and its production is responsible for a significant amount of CO2 emissions, making it a major contributor to global warming. Selfcompacting concrete (SCC) is a type of concrete that can flow under its own weight and fill all the spaces in the formwork without the need for external vibration, which makes it more sustainable compared to traditional concrete. In this study, the performance of SCC using Sugarcane bagasse ash (SCBA) and Ground granulated blast furnace slag (GGBS) as mineral admixtures was investigated for sustainable construction. The study focused on determining the optimum percentages of both SCBA and GGBS to produce SCC with enhanced properties. The SCC mix with SCBA10 GGBS20 achieved a compressive strength, which is significantly higher than the control mix without any mineral admixtures. The flexural strength and tensile strength of SCC mixes with SCBA10 GGBS20 were also higher than the control mix. In terms of durability, the SCC mixes with SCBA10 GGBS20 exhibited better resistance to water penetration, chloride ion penetration, and acid attack compared to the control mix. The UPV test results showed that SCC mixes with SCBA10 GGBS20 had a more uniform and dense structure, which indicates better overall durability. The study is aligned with Sustainable Development Goal 12 (SDG 12) of the United Nations, which aims to ensure sustainable consumption and production patterns. The optimal mix of SCBA10 GGBS20 can lead to the production of high- performance SCC, which is crucial for sustainable construction practices. In conclusion, this study demonstrates the feasibility of using SCBA and GGBS as mineral admixtures in SCC production to enhance its performance and sustainability. The study's findings provide valuable insights for researchers, engineers, and construction professionals to develop sustainable and costeffective concrete mixes for construction projects.

Published by: vikaspatanker

Authors: Sonali Bahuguna, Professor Indu Sharma

Abstract: This research examines the connection between educational and vocational interests and the academic performance of secondary school students in Delhi. Considering the recent inclusion of vocational courses in more than 800 government schools as part of the samagra shiksha scheme, this study examines the correlation between students' interests and their academic achievements. The study employs a stratified random sample of 500 students from various socio-economic and institutional backgrounds, utilizing standardized interest inventories and academic data analysis. The findings indicate a strong positive relationship between educational and vocational interests and academic performance, with vocational interests having a greater predictive power. This supports the belief that incorporating student interests into educational content can enhance academic engagement and achievement.

 

 

Published by: vikaspatanker