Category Archives: Uncategorized

Authors: Mr. Appalla Yazna Surya Sai Kiran, Miss. Savarapu Suhasini

Abstract: The rapid growth of social media platforms and online communication has significantly increased the volume of user-generated content, creating new challenges in identifying toxic language, hate speech, cyberbullying, and abusive comments. These harmful interactions negatively affect online communities, user well-being, and digital safety, highlighting the need for intelligent and automated content moderation systems. This paper presents ToxiShield, a next-generation intelligent framework for toxic comment detection that integrates Machine Learning (ML) and Natural Language Processing (NLP) techniques to accurately classify online comments as toxic or non-toxic. The proposed framework employs comprehensive text preprocessing, including tokenization, stop-word removal, text normalization, lemmatization, and feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF) and word embedding techniques to generate meaningful textual representations. To evaluate the effectiveness of the proposed framework, multiple classification algorithms, including Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), Random Forest, and Convolutional Neural Networks (CNN), are implemented and comparatively analysed using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that deep learning-based models, particularly CNN, achieve superior performance in identifying complex contextual toxicity patterns compared with traditional machine learning methods. The proposed ToxiShield framework provides an efficient, scalable, and intelligent solution for automated online content moderation, contributing to safer digital communication environments and promoting respectful interactions across social media platforms and online communities.

DOI: http://doi.org/10.61137/ijsret.vol.12.issue3.472

Published by: vikaspatanker

Authors: Professor Mayuri Dongre, Saurabh Bhoyar, Sanskar Karnewar

Abstract: Fraudulent voice calls have become a prominent cyber threat in the contemporary telecommunication environment as the usage of online banking, UPI transactions, mobile wallets, and instant messaging services becomes widespread. The perpetrators of cybercrime resort to fraudulent activities such as voice calls, phishing attacks, OTP manipulation, lottery scams, insurance scams, loan scams, and identity deception. The consequences include substantial monetary damage and grave security vulnerabilities. Existing techniques for spam detection in phone calls depend upon manual reporting, blacklisting, and basic rules-based filtering algorithms. However, these methods prove ineffective against newly emerging and evolving forms of fraud, particularly when the perpetrator changes their phone number and employs advanced social engineering techniques. Therefore, there is a need to develop an efficient and automated fraud detection system. In this paper, we propose a machine learning-based method to detect and analyze fraudulent phone calls. Using the following indicators for call behavior analysis, duration of a call, frequency of calls, suspicious phrases, time of calls, and voice pattern recognition, our approach is intended to identify and classify every call as either fraudulent or legitimate. For better prediction and detection, such machine learning models as Naive Bayes, Logistic Regression, Random Forest, and Support Vector Machine (SVM) will be applied.

DOI: https://doi.org/10.5281/zenodo.20956340

Published by: vikaspatanker

Authors: Mayuri Dongre, Hrutuja Meshram, Vidhi Ugale

Abstract: Digital transformation is really changing the way we learn in education. This is why Learning Management Systems are so important now. Even though a lot of schools are using Learning Management Systems they often do not keep students because the content is not interactive and it is not personalized for each student. This paper is about a kind of Learning Management Platform that we call Interactive Learning Management Platform. The Interactive Learning Management Platform uses four ideas to make learning more engaging for students: combining different ways of teaching, making the content fit each student’s needs, using games to make learning fun for students, analysing how students learn. We based our ideas for the Interactive Learning Management Platform on what other researchers have found and, on theories that are well established. We think that our Interactive Learning Management Platform can really help students stay engaged when they are learning online. We talk about how each part of our Interactive Learning Management Platform's based on research and how all these parts work together to help students. Our goal is to help students behave think and feel in a way that makes them want to learn. At the end we discuss how to make our Interactive Learning Management Platform a reality and what we need to do to test it.

DOI: https://doi.org/10.5281/zenodo.20956129

Published by: vikaspatanker

Authors: Mayuri Dongre, Kalyani Parihar

Abstract: This paper describes the design and implementation of a CMS system using the Salesforce CRM platform. Our goal is to automate current processes for educational institutions with a cloud-based, user-friendly system replacing manual, and paper-based procedures. It has four most important modules: Student Module, Fee Management Module, Teacher/Faculty Module and Admin Module. These modules modernize academic processes, reducing operational costs, minimize data redundancy, and enhancing efficiency. Unlike the traditional data warehouse, where problems arise with storage systems and access to remote data usually takes time as well, this system utilizes Salesforce cloud infrastructure. The appropriate communication and streamlined processes are the key steps to attracting and retaining more students, as well as staying competitive; therefore, an adequate use of a CRM system can support taking advantage of these success factors. The paper proposes a comparative analysis of existing leading CRM systems in the field of higher education, a summarization of the benefits and the need for their deployment.

DOI: https://doi.org/10.5281/zenodo.20955858

Published by: vikaspatanker

Authors: Professor Mayuri Dongre, Aniket Manoj Singh, Deepak Albankar

Abstract: With the exponential growth of user-generated con-tent on social media platforms, recommendation systems have become the primary mechanism for content curation, user engagement, and personalized information delivery. Traditional recommendation approaches, such as collaborative filtering and content-based filtering, increasingly struggle with inherent limi-tations, including data sparsity, cold-start issues, and the highly dynamic, multimodal nature of modern social media networks. This paper provides a comprehensive analysis of contemporary optimization techniques designed to enhance the precision, scala-bility, and diversity of social media recommendation engines. We systematically review the integration of deep learning architec-tures, Graph Neural Networks (GNNs) for structural relationship mapping, and advanced embedding strategies. Furthermore, we investigate critical operational challenges, including algorithmic bias, real-time computational latency, and data privacy regula-tions. Finally, this study outlines pivotal future research direc-tions, highlighting the paradigm shift toward Large Language Model (LLM) integration and autonomous agentic workflows to build next-generation, context-aware, and explainable recommen-dation frameworks.

DOI: https://doi.org/10.5281/zenodo.20955477

Published by: vikaspatanker

Authors: Mayuri Dongre, Tanmay Lanjewar, Vedant Chaple

Abstract: With the rapid expansion of internet-based applications, cloud services, and digital communication platforms, cybersecurity threats have become increasingly complex and harmful. Among these threats, Distributed Denial of Service (DDoS) attacks are considered one of the most disruptive network-based attacks because they overwhelm targeted servers or networks with excessive traffic, causing downtime, service interruption, and financial loss. Traditional security mechanisms such as firewalls and rule-based intrusion detection systems often fail to detect evolving DDoS attack patterns in their early stages. This research focuses on applying supervised machine learning techniques for early DDoS attack detection by analyzing network traffic behavior and classifying malicious activities. The proposed system performs data preprocessing, feature extraction, traffic analysis, model training, and attack classification using supervised learning algorithms such as Decision Tree, Random Forest, Support Vector Machine (SVM), Logistic Regression, and K-Nearest Neighbors (KNN). The study aims to improve detection accuracy, reduce false alarms, and strengthen real-time cybersecurity monitoring. Results indicate that supervised learning models provide reliable performance in identifying suspicious traffic patterns and can significantly enhance proactive defense mechanisms in network infrastructures.

DOI: https://doi.org/10.5281/zenodo.20955167

Published by: vikaspatanker

Authors: Deepa Barethiya, Kajal Lanjewar, Damini Mondhe

Abstract: Malware — malicious software — represents one of the most pervasive and rapidly evolving threats in modern cybersecurity. Traditional signature-based detection systems, while effective against known threats, are fundamentally inadequate against polymorphic, metamorphic, and zero-day malware variants. This paper presents a comprehensive study and implementation of a machine-learning-based malware detection framework that overcomes the limitations of conventional approaches. The proposed system employs static analysis (PE header features, API call sequences, n-gram byte patterns), dynamic analysis (system call traces, network behaviors), and hybrid analysis to extract discriminative feature sets. Several supervised classification algorithms — including Random Forest, Support Vector Machine (SVM), Gradient Boosting (XGBoost), and a custom Convolutional Neural Network (CNN) — are evaluated on the EMBER 2018 and VirusShare benchmark datasets. Experimental results demonstrate that the ensemble model achieves a detection accuracy of 98.7%, a false-positive rate below 0.4%, and an average inference time of 12 ms, outperforming state-of-the-art baselines by a significant margin. The paper further discusses real-time deployment considerations, adversarial robustness, and future research directions.

DOI: https://doi.org/10.5281/zenodo.20954815

Published by: vikaspatanker

Authors: Deepa Barethiya, Prajwal Suklal Bankar

Abstract: Artificial Intelligence (AI), particularly Generative AI (GenAI) tools such as ChatGPT, has significantly influenced programming education by providing instant code generation, debugging support, and conceptual explanations. These tools are increasingly used by beginner programmers to assist in learning and problem-solving tasks. While AI has the potential to enhance learning efficiency and boost learner confidence through immediate feedback, concerns remain regarding its impact on independent thinking and long-term skill development.This study investigates the influence of AI tools on the problem-solving ability and confidence of beginner programmers. The research examines how learners interact with AI-assisted systems, how frequently they rely on generated solutions, and how such usage affects their understanding of programming concepts. Data was collected through a survey-based analysis of beginner programmers using AI-assisted tools. The findings indicate that AI tools can improve problem-solving efficiency and significantly enhance learner confidence by reducing frustration and providing instant support. However, excessive reliance on AI-generated solutions may limit the development of critical thinking and independent problem-solving skills. The study highlights the importance of balanced AI integration in programming education. This research contributes to the growing field of computing education by providing insights into both the benefits and limitations of AI-assisted learning. It also offers recommendations for educators to design effective learning strategies that leverage AI tools while preserving core problem-solving abilities.

DOI: https://doi.org/10.5281/zenodo.20954427

Published by: vikaspatanker

Authors: Deepa Barethiya, Pratik Gajbhiye, Siddhi Lokhande

Abstract: This paper explores the extent to which artificial intelligence (AI) systems, increasingly capable of creating visual artworks indistinguishable from human-created ones, are part of the broader conversation about creativity and the role of AI in the creative process. Expanding on existing research that considers AI creativity as a whole construct, this paper focuses on a component-based approach to creativity, examining it as a series of discrete components. An empirical analysis is also presented to compare AI-created and human-created artworks with respect to the most important factors traditionally associated with human creativity: emotional depth, intentionality, originality, awareness of context, and experiential authenticity. A quantitative approach was taken using a survey-based methodology, in which a series of artworks were evaluated using a structured Likert-scale survey. The results were analyzed using comparative statistics to determine performance differences between AI-created and human-created artworks across each creativity component. The results show that AI-created artworks exhibit uneven creative performance, with higher visual originality and significant shortcomings in emotional depth and intentionality compared to human-created artworks. These results suggest that creativity is a multidimensional construct and that current AI systems have difficulties in recreating several core components of human creativity. This paper contributes to the existing literature on AI and creativity by providing a structured approach to evaluating AI-created artworks beyond superficial visual aesthetics and highlighting implications for the role of AI as a creative tool versus an autonomous artist.

DOI: https://doi.org/10.5281/zenodo.20954101

Published by: vikaspatanker

Authors: Mwinilombe Joseph Mushabati, Dr. Sampa Nkonde

Abstract: This study investigates the design and implementation of a Smart Healthcare System (SHS) integrated into a Disaster Management and Mitigation System (DMMS), using Lusaka, Zambia as a case study. The increasing frequency of disasters such as cholera outbreaks, floods, and the COVID-19 pandemic have demonstrated the limitations of conventional healthcare systems in responding effectively. The SHS aims to enhance real-time data collection, health monitoring, early warning systems, and coordinated emergency response. Through qualitative methodology, data were collected from healthcare professionals, ICT experts, and disaster management personnel. Findings show that a well-integrated SHS can significantly improve response time, resource allocation, and resilience during disasters. The research contributes to local and continental knowledge on digital health innovations in disaster-prone regions.

DOI: http://doi.org/10.5281/zenodo.20953794

Published by: vikaspatanker