Harnessing Computer Vision for Precision Agriculture: Advancements in Crop Monitoring, Yield Prediction, and Disease Identification
Authors:-Swaraj Kawade, Anurag Kawade, Rohit Kashid, Aditya Jedhe, Rajdeep Jagtap

Abstract-The use of modern technologies such as computer vision and artificial intelligence individually or in tandem are modifying farming methods. These technologies are assisting in agricultural practices as the world population is expected to peak at 9.7 billion by 2050. The objective of this paper is to analyze major advancements within the years 2020 to 2024 regarding the role of computer vision in agriculture, specifically in crop health monitoring, yield prediction, and early detection of plant diseases. Some impressive progress includes: Autonomous weed management systems with 96% accuracy (Praveenraj et al., 2024). Near 99% accuracy in crop yield predictions from machine learning models (Sharma et al., 2023). Deep learning algorithms correctly identifying plant diseases at a rate of 99.35% (Li et al., 2021). Additionally, the development of autonomous vehicles has contributed to safety within agricultural fields, while AI image generation contributes to predicting potential yield imagery, along with real-time field monitoring robotic systems. These developments are positive strides towards sustainable agriculture. On the other hand, these systems always carry limitations like dealing with dynamic field conditions, insufficient amounts of data, and the need for high-end processing units. This paper evaluates the advancement to date, what it means in terms of practical agriculture, and how we can further progress:

DOI: 10.61137/ijsret.vol.11.issue2.348

Published by: Kajal Tripathi

Image Fusion of MRI and CT Scan for Brain Tumor Detection Using VGG-19
Authors:-Professor Kirti Digholkar, Shreyas Depura, Adwait Mali, Vedant Latthe, Rohan Patil

Abstract-For a patient’s prognosis, the careful examination of image bio-analytics, including Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) imaging, is crucial for the patient’s tumor detection. Moreover, interpreting these images manually remains challenging owing to the required expertise and time needed to properly analyze the images. To address this issue, we propose an image improvement model that enhances the accuracy of MRI and CT scans using Wavelet- based fusion and the VGG-19 architecture. Image fusion, or the merging of medical images, synergistically uses and adapts the various modalities’ strengths and weaknesses. In our research, we apply the Wavelet approach to MRI and CT images by splitting them into frequency sub-bands. Structural details are important for the image’s low-frequency LL band. The VGG- 19 network which consists of several convolutional layers and pooling layers is then used to merge the LL bands and form the fused images. Our method undergoes a series of preprocessing, feature extraction, and fusion stages on brain MRI and CT scans. This method saves time for medical practitioners and enables efficient tumor identification through automation, improving the overall quality of patient care.

DOI: 10.61137/ijsret.vol.11.issue2.347

Published by: Kajal Tripathi

Next-Gen Health Solutions
Authors:-Assistant Professor Priti Bharambe, Vikas Mahandule, Shraddha Phulsundar, Priti Aivale, Shivanjali Shinde

Abstract-The integration of Information Technology (IT) in healthcare has transformed patient care, data management, and operational efficiency. This paper explores the role of IT solutions in enhancing healthcare delivery, focusing on electronic health records (EHRs), telemedicine, artificial intelligence (AI), and blockchain technology. IT innovations facilitate real-time data sharing, improve diagnostic accuracy, and enable remote patient monitoring, thereby increasing accessibility and reducing costs. Despite significant advancements, challenges such as data safety, compatibility, and ethical concerns persist. This study examines both the advantages and limitations of IT-driven healthcare, proposing strategies to optimize its implementation. By leveraging technology effectively, healthcare systems can enhance patient results and overall efficiency, clearing the path for a more connected and intelligent healthcare ecosystem.

DOI: 10.61137/ijsret.vol.11.issue2.346

Published by: Kajal Tripathi

A Machine Learning Approach to Heart Disease Prediction: 5-Fold Cross Validation and Hyperparameter Optimization
Authors:-Dr.N.Chandrasekhar

Abstract-The primary objective of this research is to develop an effective predictive model for heart disease using various Machine Learning (ML) algorithms. In this study, four different ML models—Gradient Boosting (GB), Random Forest (RF), LightGBM (LGBM), and AdaBoost (AB)—were implemented and evaluated for their prediction accuracy. To ensure the reliability and generalization of the models, 5-fold cross-validation was applied along with Grid Search Cross Validation (Grid Search CV) for hyperparameter tuning. This technique helped in identifying the optimal parameters for each algorithm, thereby improving their performance. Among all the models, Gradient Boosting achieved the highest accuracy of 95.08%, followed by Random Forest and LightGBM, both with 91.80%, and AdaBoost with 90.16%. These results highlight the effectiveness of ensemble-based ML models, particularly Gradient Boosting, in accurately predicting the risk of heart disease.

DOI: 10.61137/ijsret.vol.11.issue2.345

Published by: Kajal Tripathi

The Impact of Personalization on E-commerce Conversion Rates: An Empirical Analysis of 100 Respondents
Authors:-Hitesh Ramdasani

Abstract- This study investigates the impact of personalization strategies on e-commerce conversion rates, examining the perceptions of 100 online shoppers. Through a simulated survey approach, the research explores the relationship between the level of perceived personalization experienced by consumers and their likelihood of making a purchase. The findings from the simulated data analysis suggest a positive correlation between higher levels of perceived personalization and increased conversion likelihood. These results underscore the importance of implementing effective personalization techniques for e-commerce businesses seeking to enhance customer engagement and drive sales.

DOI: 10.61137/ijsret.vol.11.issue2.344

Published by: Kajal Tripathi

Student Council Election Portal
Authors:-Professor Bharati Bisane, Vaishnavi Rajendra Borse, Resham Sanjay Umale, Sharddha Bhagwan Borate

Abstract- Traditional paper-based voting has been used for many years, but it comes with several challenges, such as security risks, lack of transparency, human errors, and privacy concerns. To solve these issues, we propose a blockchain-based voting system for college elections. Blockchain technology is in high demand because it offers security, transparency, and decentralization. Our goal is to use blockchain to create a secure and tamper-proof election system at the college level. This system will also help developers build and deploy smart contracts, which ensure accuracy and provide quick voting results.
Smart contracts automate the voting process, making vote counting secure and preventing fraud. Blockchain stores all transactions in blocks within a decentralized network, ensuring that no single person can manipulate the results. Overall, th is system will make the voting process faster, more secure, and more reliable. It will also reduce costs since there is no need to print ballots.

DOI: 10.61137/ijsret.vol.11.issue2.343

Published by: Kajal Tripathi

Mall Customer Segmentation System for Retail Analytics and Personalized Marketing
Authors:-Dr.Prabakaran, S.M.Rafi Saddam, T.Narendra, B.Venkateswarlu, T.Venkatesu

Abstract- This paper presents a comprehensive customer seg- mentation system for retail businesses, specifically designed for shopping mall environments. Using advanced clustering tech- niques and RFM (Recency, Frequency, Monetary) analysis, we develop a robust framework for identifying distinct customer segments with similar purchasing behaviors. The system pro- cesses transactional data to create meaningful customer profiles, enabling businesses to implement targeted marketing strategies and improve customer relationship management. Our approach integrates data preprocessing, feature engineering, clustering algorithms, and interactive visualization to provide actionable insights. The implemented dashboard facilitates segment com- parison, geographical distribution analysis, and automated per- sonalized email campaigns tailored to each segment’s prefer- ences. Experimental results demonstrate the effectiveness of this approach in identifying five key customer segments with distinct behavioral patterns. The system’s practical application is validated through its ability to generate segment-specific market- ing recommendations and predict customer preferences, leading to more efficient resource allocation and potentially increased customer engagement. This research contributes to both the theoretical understanding of customer behavior modeling and provides a practical tool for retail analytics in real-world business environments.

DOI: 10.61137/ijsret.vol.11.issue2.342

Published by: Kajal Tripathi

Multimodal Emotion Classification Using Machine Learning and Deep Learning
Authors:-Professor Mr. V. K. Sabari Rajan, B. Mukesh, C. Narendra, M. Shivanand, B. Ajay Kumar

Abstract- In the rapidly evolving field of artificial intelligence, emotion recognition has emerged as a pivotal area of research, with significant applications in human-computer interaction, mental health analysis, and social robotics. This project focuses on the development of a multimodal emotion recognition system capable of classifying emotions from text, audio, images, and live video. The system employs advanced machine learning algorithms tailored to each modality: BERT for text, CNN and LSTM for audio, and CNN for both images and live video frames. Each modality is designed to recognize a set of core emotions, with slight variations to account for the unique characteristics of each data type. The text module identifies emotions such as anger, fear, joy, love, surprise, and sadness, while the audio, image, and live video modules detect emotions including angry, disgust, fear, happy, neutral, and surprise. The system architecture encompasses dataset creation and preprocessing, model training, and emotion classification. User interaction is facilitated through a web interface, allowing users to input text, audio, images, or live video and receive real-time emotion classification results. This multimodal approach enhances the accuracy and robustness of emotion detection, providing a comprehensive tool for analyzing human emotions across different communication mediums.

DOI: 10.61137/ijsret.vol.11.issue2.341

Published by: Kajal Tripathi

IoT-Based Smart temperature controlled Fan for Energy-Efficient Cooling
Authors:-Megha Narwade, Diksha Patil, Akanksha Patil, Chetan Aher

Abstract- This paper gives a new and creative IoT-based smart fan system for cooling with energy efficiency in various applications – residential, commercial as well as industrial surroundings. Traditional cooling systems usually depend on static control mechanisms. These cannot adjust to actual environmental conditions and result in extra energy consumption and reduced efficiency too. In order to tackle these challenges, our proposed system integrates an advanced temperature-controlled fan that makes use of a dynamic Pulse Width Modulation (PWM) algorithm that lets us adjust fan speed based on real-time temperature variations around the fan. The system consists of – an NTC thermistor for precise temperature measurement, an Arduino Uno microcontroller for data processing, and an IoT-enabled mobile interface that automates user interactions, and reducing manual adjustments. Strict testing results show that the system successfully achieves a temperature stability of ±0.2°C and reduces power consumption by 27.1% as compared to traditional methods. Also, the modular design supports both DC as well as AC fans, increasing scalability and adaptability. This work bridges the gap between academic research and practical applications and sets a new standard for smart, future focused, thermal management solutions.

DOI: 10.61137/ijsret.vol.11.issue2.340

Published by: Kajal Tripathi

AI-Driven Business Intelligence and Decision Making: Turning Data into Actionable Insights
Authors:-Aditya Kokate/strong>

Abstract- The integration of Artificial Intelligence (AI) into Business Intelligence (BI) is revolutionizing how organizations make decisions by automating data analysis and enhancing predictive capabilities. Traditional BI systems rely on static reporting and retrospective data interpretation, limiting their responsiveness in dynamic environments. In contrast, AI-powered BI systems leverage Machine Learning (ML), Natural Language Processing (NLP), and cognitive computing to transform raw data into actionable insights. This paper explores the architecture, implementation, and impact of AI-driven BI systems, emphasizing real-time analytics, predictive modeling, and explainable AI. The study demonstrates how AI enhances operational efficiency, data accuracy, and strategic foresight, offering a competitive advantage to modern enterprises.

DOI: 10.61137/ijsret.vol.11.issue2.339

Published by: Kajal Tripathi