Category Archives: Uncategorized

Authors: Abhendra Pratap Singh, Riya Rani, Devanshi Sharma, Nandini Sharma, Prince Kumar Sharma, Vanshika Dua

Abstract: Exchange of information, social interaction, and behavior are all impacted by autism spectrum disorder (ASD), which is a complicated neurodevelopmental disorder. Traditional therapies have demonstrated benefits in increasing quality of life, but they are still resource intensive and have limitations due to high costs and an inadequate number of specialists. With recent technical advancements, robotics has emerged as a promising addition to traditional treatment options. Socially Assistive Robots (SARs) are being investigated as therapies for assisting children with autism by increasing engagement, boosting social skills, also providing constant and compatible interaction. This study looks at the growing amount of research on the use of robotics in autism therapy, with an importance of robot design, human robot interaction, and medical applications. SARs can promote focus, emotional expression, and social communication. However, obstacles remain in terms of robot design, ethical considerations, and the necessity for standardized methods of assessing effectiveness in the real world. This paper's contribution is to thoroughly analyze existing methodologies and present a framework for designing robotic therapies based on individual needs. By synthesizing information related to education, healthcare, and robotics, this review identifies critical areas for further study and outlines future options for developing effective, accessible, and ethically feasible robotic therapy for children with ASD.

DOI: http://doi.org/10.5281/zenodo.17490817

Published by: vikaspatanker

Authors: Ms. Vaibhavi P. Gawande, Dr. R. S. Durge

Abstract: Decentralized crowdfunding platforms represent a paradigm shift in fundraising, harnessing blockchain technology to disrupt traditional models dominated by intermediaries. By leveraging smart contracts on networks like Ethereum, these platforms facilitate direct interactions between creators and backers globally, ensuring transparency, security, and reduced transaction costs. Core features include immutable transaction records, automated fund releases governed by smart contracts, and enhanced trust through decentralized validation. Key benefits encompass increased accessibility for global participants, lower fees compared to conventional platforms, and improved security against fraud. Technologically, these platforms integrate Web3 interfaces, cryptocurrency wallets like MetaMask, and programming languages such as Solidity for smart contract development.

Published by: vikaspatanker

Authors: Vaishnavi F. Thakare, Prof .D. G. Ingale, Dr. A. P. Jadhav, Prof. S. V. Raut, Prof .S. V. Athawale, Dr.D.S.Kalyankar, Prof. R. N. Solanke

Abstract: The evolution of wireless communication has reached a critical juncture with the emergence of the sixth generation (6G) technology, envisioned to revolutionize global connectivity beyond the capabilities of 5G. 6G aims to deliver ultra-high data rates up to terabits per second, near-zero latency, enhanced reliability, and seamless integration of terrestrial and non-terrestrial networks. It leverages advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), Terahertz (THz) frequency bands, Blockchain, and Quantum Communication to enable applications like holographic communication, digital twins, autonomous systems, and immersive extended reality (XR). This paper explores the fundamental principles, key enabling technologies, potential applications, and challenges of 6G, offering insight into its role in shaping the future of intelligent and sustainable communication systems.

Published by: vikaspatanker

Authors: Abhijit Ranjan, Chandraveer Singh

Abstract: In the recent years, the demand for intelligent medication recommender systems has increased tremendously with the evolution of digital health technology. This research targets the development of a symptom-based medication recommender system from a structured and diversified healthcare database. The database is descriptive in nature with information regarding patient symptoms, associated medicines, dietary advice, exercise plans, precautions, and doctor specialties. Early steps of this project include extensive data exploration and preparation from several CSV files to create a clean and solid base for model training. For building the central recommendation engine, traditional machine learning algorithms such as Decision Tree, Random Forest, Naive Bayes, and Logistic Regression were utilized, which try to predict symptoms and suggest the most suitable medicines out of a pre-defined list. Among the models used, the Decision Tree classifier had the best performance, followed by Random Forest, Naive Bayes, and Logistic Regression. The system is smart enough for users to put in symptoms and get suggested medicines for the same, providing useful help for non-emergency medical conditions and employment in resource-constrained environments. Future developments will involve incorporating patient medical history, dosage calculation, drug interaction screening, and implementing the system through a mobile platform to enhance accessibility and real-time use.

DOI: http://doi.org/10.5281/zenodo.17482512

Published by: vikaspatanker

Authors: Dr Anitha S, Mohammed Muzammil S, Prince P, Sridhar L

Abstract: This proposed work designs an Automatic Waste Segregation System that focuses on separating metallic waste using a magnetic belt mechanism. This IoT based system uses a conveyor belt that carries mixed waste materials through a detection unit containing an electromagnet. When the magnet is activated, it attracts and separates the metallic components from the remaining waste. The metallic waste is then released into a separate compartment once the magnet is deactivated. A sensor is used to measure how much of the metal compartment is filled, and the fill level is displayed as a percentage on a digital screen. The entire operation is controlled by a microcontroller to ensure smooth and accurate functioning. This system helps reduce manual labor, increases sorting efficiency, and supports effective recycling management. It offers a simple, low-cost, and eco-friendly device to waste segregation that can be applied in both domestic and industrial settings

DOI: https://doi.org/10.5281/zenodo.17482056

 

Published by: vikaspatanker

Authors: Kanak Patil

Abstract: This paper provides an overview of cybersecurity and digital forensics, two related fields that are critical for digital security. It explains the basic idea that cybersecurity is about preventing attacks (like a shield), while digital forensics is about investigating them after they happen (like a sword). The paper will look at how both fields developed over time, the main areas within cybersecurity, and the standard frameworks used, like the one from NIST. It will also cover the step-by-step process of a digital forensics investigation, including the importance of keeping a "chain of custody" for evidence. Using real-world examples like the Stuxnet worm, the Equifax data breach, and the WannaCry ransomware attack, this paper shows how these concepts are used in practice. It also discusses the legal and ethical challenges, such as data privacy laws like GDPR and CCPA. Finally, the paper looks at future challenges, including the shortage of skilled professionals, new ways hackers are hiding their tracks, the role of Artificial Intelligence, and the threat of quantum computing to modern encryption. The main point is that to be effective, cybersecurity and digital forensics must work together, with the results of investigations helping to build stronger defenses for the future.

 

 

Published by: vikaspatanker

Authors: Abhendra Pratap Singh, Nandini Sharma, Prince Kumar Sharma, Arpit Dwivedi, Aakriti Sharma

Abstract: The growing use of Artificial Intelligence (AI) in surveillance technologies changes how societies observe, predict, and manage security. From predictive policing to facial recognition, AI surveillance technologies offer real-time analysis, risk detection, and improved efficiency. Still, the rapid proliferation of such technologies brings issues of privacy, ethics, and accountability to the forefront. This review assesses the balance between human rights, AI ethics, and the surveillance technologies themselves. It demonstrates how China, the UK, and the USA have vastly different approaches toward data regulation, transparency, and consent. It also illustrates the major technical issues of algorithmic bias, data abuse, interoperability of privacy frameworks, and the ethics of large-scale surveillance and digital autonomy. By defining the gaps and analyzing the global pattern of such technologies, the paper aims to provide the most responsible and human-centric AI surveillance possible to guarantee privacy while also providing the oversight that people need

DOI: http://doi.org/10.5281/zenodo.17481315

Published by: vikaspatanker

Authors: Abhendra Pratap Singh, Nandini Sharma, Vanshika Dua, Arpit Dwivedi, Aakriti Sharma

Abstract: Composite materials are generated by intermingling two or more diverse components that are individually not able to do various tasks but when put together have become critically important in modern engineering due to their superior mechanical and structural traits. Fiber reinforced polymer (FRP) composites are utilized frequently in the aerospace automotive and construction industries more prominently. Despite their growing adoption, a continuing dilemma involves assessing natural fiber reinforced polymers (NFRP) over synthetic fiber reinforced polymers (SFRP) which differ greatly at the levels of performance cost and environmental impact. Both natural and synthetic composites have their own benefits and drawbacks such that synthetic composites offer excellent strength and durability and natural composites are gaining popularity due to their lightweight renewability and sustainability. This lack of unambiguous data driven comparison often leads to unclear judgment and leads to confusion in choosing the most viable composite for certain technical objectives. To eradicate this gap, the study examines three natural composites flax FRP, hemp FRP and jute FRP and three synthetic composites glass FRP, carbon FRP and aramid FRP. The paper uses computationally intensive analysis and machine learning methods such as linear regression and support vector machine (SVM) to figure out four crucial properties which mostly defines about the composite materials namely density, tensile strength, elastic modulus and moisture absorption. The visualized results of matplotlib based graphs provide a clear insight of how natural and synthetic composites perform individually and collectively through comparative analysis. This research incorporates AI assisted analytical modeling with scientific visualization to give a systematic and sustainable structure for selecting innovative composite materials.

DOI: http://doi.org/10.5281/zenodo.17481163

Published by: vikaspatanker

Authors: Om Dwivedi, Neelam Singh Parihar

Abstract: Skin cancer remains one of the most prevalent and life-threatening diseases globally, necessitating early and precise diagnosis. This research proposes an optimized deep learning framework using ResNet152 for automated skin lesion classification. The model integrates preprocessing, segmentation, and feature extraction to enhance lesion detection and classification accuracy. Experimental results demonstrate superior performance, achieving 97% accuracy, 98% precision, and 97% recall, outperforming existing ResNet variants. The framework’s robustness and adaptability make it suitable for clinical and remote diagnostic applications, promoting early intervention and reducing diagnostic errors.

Published by: vikaspatanker

Authors: Sakshi Keshri, Nitin Namdev

Abstract: This paper presents a comprehensive review of deep learning techniques designed to enhance violence detection in surveillance systems. With the rapid advancement of surveillance technologies, the accurate identification of violent activities has become crucial for ensuring public safety. Conventional approaches often fail to cope with the complexity of video data, which inherently involves both spatial and temporal dynamics. To overcome these limitations, modern deep learning models such as Convolutional Neural Networks (CNNs), InceptionV3, Long Short-Term Memory (LSTM) networks, and hybrid architectures have been widely adopted. These methods excel at capturing spatial representations while simultaneously modeling temporal dependencies, making them well-suited for real-time violence detection tasks. The review further discusses essential preprocessing strategies—including noise reduction, feature extraction, and data augmentation—that significantly improve model robustness. In addition, it outlines persistent challenges such as class imbalance, scalability issues, and high computational costs, which remain key barriers to practical deployment

Published by: vikaspatanker