Authors: Asst. Prof. Rutuja Gautam, Prof. Rohan B. Kokate, St. Ankit R. Dhole

Abstract: Heart disease is one of the leading causes of death worldwide, making early prediction and diagnosis extremely important. This review paper focuses on the use of machine learning techniques for predicting heart disease based on medical data. Various algorithms such as Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine are analyzed for their effectiveness in prediction. The system uses patient health parameters like age, blood pressure, cholesterol level, and heart rate to determine the risk of heart disease. A web-based application is also discussed, developed using Python for backend processing and HTML/CSS for user interaction. The results show that machine learning models can significantly improve prediction accuracy and assist doctors in decision-making. This paper highlights the importance of data preprocessing, model selection, and performance evaluation in building an efficient heart disease prediction system.

DOI: https://doi.org/10.5281/zenodo.19975051

Published by: vikaspatanker

Authors: Vishal Tandale, Shabbir Ahmed, Hitesh Shewale

Abstract: The dairy sector remains a cornerstone of Indian agriculture, facing persistent challenges such as manual inefficiency, data fragmentation, and increasing demands for quality and traceability. This paper analyzes contemporary dairy management systems, focusing on the adoption of digital technologies—Internet of Things (IoT), Artificial Intelligence (AI), and integrated Enterprise Resource Planning (ERP)—to streamline operations, optimize productivity, and improve animal welfare. Evidence from recent deployments and technology pilots demonstrates that technologically- augmented management not only boosts efficiency but also aligns the sector with Food Safety and Standards Authority of India (FSSAI) compliance and export requirements. Implementation challenges and recommendations for scalable, farmer-friendly solutions are discussed.

Published by: vikaspatanker

Authors: Vrushabh Jitendra Patil, Pratik Prakash Patil, Ganesh Rajendra Mote

Abstract: Traditional irrigation systems depend heavily on manual inspection to detect leaks, pipe blockages, and abnormal water flow, resulting in significant water wastage, reduced irrigation efficiency, and increased maintenance expenditure. This paper presents AquaVision BI, an intelligent IoT-enabled irrigation monitoring system that integrates three Hall-effect flow-rate sensors, an ESP32 Wi-Fi microcontroller, and an AI-driven differential-threshold anomaly-detection algorithm to achieve real-time surveillance of irrigation pipelines. The system continuously samples sensor pulse counts at one-second intervals, computes volumetric flow rates, and applies pairwise differential analysis to localise leakage to specific pipeline segments (upstream, mid-stream, or downstream). Upon anomaly detection, automated alerts are dispatched via the Blynk IoT cloud dashboard and a local buzzer actuator. Experimental evaluation on a controlled testbed confirms accurate leak localisation across all three sensor nodes, with end-to-end alert latency consistently below two seconds. The proposed system significantly reduces water wastage, lowers operational costs, and promotes sustainable agricultural water management practices.

Published by: vikaspatanker

Authors: Khushi, Rajat Takkar, Mugdha, Himanshi, Muskan

Abstract: Schools are embracing the use of data-driven information to track student achievement and performance. Conventional ways of tracking performances are not effective in the intricate nature of the relationships among diverse academic contributions. This research works on the necessity of an efficient, but simple, artificial intelligence based framework to examine and visualize the factors mentioned and to take proactive measures that will help find out students who might not need more than a top-quality academic assistance. The main purpose of the research is to come up with a machine learning model that is easy to interpret, has the predictive strength of the end-of-year academic scores and classifies students into groups of "pass" and "fail." Also, the research will visualise the relationship between particular inputs (ex: hours of study, attendance) and performance in general and characterize a feature importance analysis to determine which factors have the most profound impact on student achievement. The research works with the artificial data including major academic variables: study hours, attendance, assignment grades, internal grades, and past GPA. The methodology will use two different machine learning models: Linear Regression to predict continuous performance scores and Decision Tree Classification to perform binary categorisation (Pass/Fail). Visualisation tools were combined to plot interactions among variables, and parameter analysis was performed in terms of standard accuracy measurements of regression as well as classification problems. The results indicate that the most important predictors of academic success are study hours, internal marks and attendance. Linear Regression model largely was able to predict final scores with high correlation to input data whereas the Decision Tree classifier offered a simple, interpretable logic with which students can be categorised. Analysis of feature importance provided a reason on why the consistent engagement and incremental assessment has a greater influence on the outcome rather than just the previous GPA. The offered AI-based framework is a scalable and understandable research proposal method of analysing educational data. The system facilitates informed, data-driven decisions made by educators by highlighting its critical performance drivers, and it helps to deliver timely interventions to at-risk students. Further work would entail the application of the framework on bigger datasets, and real-life contexts to improve predictive accuracy in diverse education settings.

DOI: https://doi.org/10.5281/zenodo.19960357

Published by: vikaspatanker

Authors: Soundrya Mallappa Biradar, Nikhil Gurudev Lonari, Aniket Ramesh Bhandare, Vishwaraj Pradip Pawar, Mrs. Pallavee Bavane-Patil

Abstract: Government subsidy programs play a crucial role in socio-economic development by supporting vulnerable populations in sectors such as agriculture, education, healthcare, energy, and food security. However, traditional subsidy management systems are often plagued by inefficiencies, fraud, leakage, lack of transparency, and poor targeting. The advent of digital governance and data-driven technologies has opened new avenues for reforming subsidy allocation and monitoring mechanisms. Machine learning (ML), in particular, offers powerful tools for automating eligibility assessment, predicting beneficiary behavior, detecting anomalies, and optimizing policy outcomes. This review paper presents a comprehensive analysis of online subsidy management systems integrated with machine learning techniques, with a specific focus on Logistic Regression, Decision Tree, and Random Forest algorithms. The paper discusses system architecture, data sources, preprocessing methods, algorithmic frameworks, evaluation metrics, real-world use cases, challenges, ethical considerations, and future research directions. The review aims to serve as a ready reference for researchers, policymakers, and system designers working toward intelligent, transparent, and efficient subsidy management platforms.

DOI: https://doi.org/10.5281/zenodo.19959139

Published by: vikaspatanker

Authors: Nirnayak Talukdar, Vulli Sai Rishika, Dr. Sadiya Nair. S

Abstract: Workforce restructuring has become a persistent feature of corporate life in the modern global economy. Driven by technological disruption, shifting market conditions, mergers, and competitive pressures, organizations regularly resort to workforce reductions and operational downsizing. The financial and strategic rationale behind such decisions has attracted considerable scholarly attention, but the way organizations communicate those decisions to employees has remained comparatively underexamined. This white paper examines internal corporate communication during workforce restructuring crises. The central argument is that the problem facing organizations in such circumstances is not the restructuring decision itself, but the quality, timing, tone, and ethical character of how that decision is communicated to employees. Evidence drawn from organizational communication theory, crisis communication scholarship, psychological contract research, and documented corporate case studies shows that poor internal communication during restructuring consistently produces measurable, lasting damage: trust erodes, rumours spread, morale falls, and voluntary turnover among retained employees rises substantially. The paper is organized around three concerns. First, it reviews and synthesizes the academic literature on internal communication, crisis communication, organizational trust, and psychological contracts. Second, it identifies research gaps that persist in the field, particularly the absence of structured, employee-centred communication frameworks and the limited empirical attention given to message tone, narrative framing, and listening mechanisms. Third, it proposes an original conceptual model, the Ethical Workforce Crisis Communication (EWCC) Model, offering a four-stage framework for guiding organizational communication through the full arc of a restructuring event. The paper concludes with ten targeted recommendations for corporate leaders, HR professionals, and communication practitioners. The core recommendation is that ethical, transparent, and empathetic communication is not merely a courtesy extended to departing employees; it is a strategic necessity for organizational continuity, survivor morale, and long-term institutional legitimacy.

DOI: https://doi.org/10.5281/zenodo.19956659

Published by: vikaspatanker

Authors: Sharvil M. Palvekar, Shreyas P. Jadhav, Ninad V. Sarpole, Soham B. Gharat, Dr. Sandeep B. Raskar

Abstract: Wildlife conservation increasingly relies on auto-mated monitoring systems to overcome the limitations of tradi-tional field-based observation methods, which are labor-intensive, subjective, and constrained in spatial and temporal coverage. This paper presents an AI-based animal monitoring and behavior analysis framework that integrates deep learning-based object detection, multi-object tracking, and spatio-temporal analytics for real-time wildlife surveillance. A YOLO26l detection model is employed to identify animal species from camera trap im-agery and video streams, followed by location-aware tracking to analyze movement patterns and population density. Heatmap-based visualization and statistical analysis are used to infer behavioral trends across different time intervals. Experimental results demonstrate robust detection accuracy and reliable species classification, supported by confusion matrix-based evaluation. The proposed system offers a scalable and interpretable solution for intelligent wildlife monitoring and conservation planning.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Mr. Harish B N, Prarthana S, Phalguni M H, Anushree T D, Sinchana K L, S N Meghana

Abstract: Plant diseases are also known to place huge burden on food security structure and agriculture to the global world; it is approximated that all plant diseases development costs a giant (an estimated 220 billion/year). To address this, the computer vision -specific and deep learning based automated disease detection systems are expandingly viewed as rather interesting as an option instead of the traditional forms of diagnosing that involve a significant amount of new employees . However, the literature screening is saturated with models that have been alleged to be super high in accuracy with regard to classifications when they are under some form of controlled conditions in the laboratory that must in no way imply any trustworthy depiction that they can be relayed over the situation in the real field. It can be said that such discrepancy in performance can stress the idea that there is a dire necessity to carry out more related and stiffer analysis of existing measures of data mining and optimization. This article has such an experimental alloy of which the plant disease variable models can be detected multi faceted in, which is discussed in detail on three axes parametric axis, combinatorial axis, computational axis. The rate of model performances to the hyperparameter options enshrined in the parametric assessment that may also be the optimizers are called counting. The combinatorial work involves the study of connections pertaining to the utility of various Convolutional Neural Network Convolutional designs, as well as the use of spectacular measures of data augmentation and fold up learning methods. The computational verification provided is a practical test of the feasibility of the model, comparison of statistics on the training time, model complexity, and speed of inference. According to the opinion that our experimental findings indicate, our individual models (as well as our EfficientNet) that come with the highest classification performance of about above 98 percent accuracy would always be the best trade off between accuracy and efficiency whereas ensemble models would adopt a combination of soft voting as the best trade off prerogative. The paper further estimates the radical performance augmentation with the generative data augmentation models against the conventional geometric transformations to apply the models in the truly competitive use. The primary accomplishment of this project is the system, which surpasses those pathetic signs of precision and rests upon the familiarization of scientists and performers with how to create, alter, and put to practical practice the scaleable, resilient, and effective plant disease detection methods used in the enhancement of the designated work in the agricultural forerunners.

Published by: vikaspatanker

Authors: Ansh Jena, Sujit Kakade, Arya Kedar

Abstract: Sentiment analysis can help track passengers’ per- ceptions and improve the service offered by an airline due to the increasing importance of social media, such as Twitter. It is about conducting a comparative analysis of three models of natural language processing, namely lexicon-based, machine learning, and transformer-based classification techniques for determining sentiments of airline tweets. Twitter US Airline Sentiment was chosen to be analyzed as it comprised labeled tweets from the major U.S. airlines. Data quality was improved by applying methods of text preprocessing, such as removing noise, tokeniz- ing, and eliminating stopwords. Lexicon-based sentiment analysis relied on VADER polarity baselines, machine-learning approach entailed extraction of TF-IDF features and further application of Random Forest classification technique while transformer model applied RoBERTa to identify the context of sentiment. As a result of the analysis, it was found out that while the lexicon model was faster and provided more easily understandable results, machine- learning model allowed identifying sentiments more accurately. Transformer-based RoBERTa performed the best in terms of handling more complex linguistic structures, such as negations and sarcasm.

DOI: https://doi.org/10.5281/zenodo.19948612

Published by: vikaspatanker

Authors: Dr. Dolley Srivastava

Abstract: The increasing problem of environmental pollution requires a new level of innovation going beyond the scope of existing monitoring systems. In this paper, we propose EnviroSense-ML – an end-to-end architecture leveraging IoT sensors together with machine learning algorithms for environmental monitoring and predictions. Our solution consists of a combination of inexpensive electrochemical sensors, LoRaWAN-based communication channels, and novel approaches in the field of hybrid machine learning techniques, which include the spatiotemporal GCN-LSTM model and CNN-BiGRU model using 8-bit quantization. The performance evaluations performed using the real-world dataset showed that our GCN-LSTM model demonstrated the highest interpolation accuracy (R² = 0.96), due to the inclusion of additional information about altitude and land cover into graph connections of the sensors. At the same time, 8-bit quantization resulted in 66% compression of the model's size with less than 1% degradation of its accuracy. Moreover, experiments showed that ML algorithms can improve sensor measurements' accuracy up to 46%. Also, our two-stage approach based on XGBoost reached near-perfect Air Quality Index prediction results (R² = 1.00, MAE = 0.35).

DOI: https://doi.org/10.5281/zenodo.19946681

Published by: vikaspatanker