Category Archives: Uncategorized

Authors: Minocha Dr. Pramodkumar, Kothwala Dr. Deveshkumar, Pandya Kamna, Shinde Divya, Sharma Rahul, Chauhan Sargam, Ladumor Rahul, Kadam Aniket

Abstract: Biocompatibility evaluation is a critical regulatory requirement for establishing the preclinical safety of medical devices in accordance with the ISO 10993 series of standards. The present study aimed to comprehensively assess the biological safety of the OCT Imaging Catheter, in-vitro and in-vivo tests selected based on its intended use and blood-contacting nature. In-vitro cytotoxicity was evaluated using L929 mouse fibroblast cells by qualitative morphological assessment and quantitative MTT assay, followed by in-vivo assessments including skin sensitization, intracutaneous irritation, acute systemic toxicity, and material-mediated pyrogenicity. Hemocompatibility was investigated through hemolysis, platelet activation, coagulation parameters, leukocyte activation, and complement activation studies. Genotoxic potential was assessed using the bacterial reverse mutation (AMES) assay and an in-vitro mammalian chromosomal aberration test in human lymphocytes. The test item demonstrated no cytotoxic effects, with cell viability exceeding ISO acceptance criteria at all extract concentrations. In-vivo studies revealed no evidence of skin sensitization, irritation, systemic toxicity, or pyrogenic response. Hemocompatibility testing confirmed the non-hemolytic nature of the device and showed no adverse effects on platelet function, coagulation pathways, leukocyte activation, or complement system activation. Genotoxicity assessments indicated that the test item was non-mutagenic and non-clastogenic under all test conditions. Collectively, the results demonstrate that the OCT Imaging Catheter exhibits an acceptable biocompatibility profile and is biologically safe for its intended clinical application. These findings support its preclinical risk assessment and provide robust evidence for regulatory submissions in compliance with ISO 10993 requirements.

DOI: http://doi.org/10.5281/zenodo.20708577

Published by: vikaspatanker

Authors: Prof. Abhishek Dubey, Akshada Kale, Kashish Mahobiya, Kirti Thakur, Nikita Raj

Abstract: Clinical Decision Support Systems (CDSS) play a crucial role in helping healthcare professionals make accurate, timely, and evidence-driven decisions. However, the growing scale, speed, and diversity of healthcare data have revealed the limitations of traditional rule-based CDSS, especially when dealing with multimorbidity and personalized treatment. Recent advancements in artificial intelligence (AI)—including machine learning, deep learning, and natural language processing (NLP)—have enabled the development of intelligent CDSS that support adaptive learning, predictive analytics, and patient stratification. This paper provides a comprehensive, system-level review of AI-powered CDSS, examining their historical development, underlying technologies, architectural frameworks, and clinical applications. Unlike earlier surveys that focused mainly on individual algorithms, this review integrates AI methods with system architecture, clinical workflows, and ethical considerations. It explores key AI techniques for patient stratification, deep learning models for diagnosis and prognosis, and NLP-driven early warning systems. The paper also addresses critical challenges related to ethics, legal concerns, and explainability, while highlighting emerging trends such as federated learning, digital twins, and genomic-based CDSS. Overall, it aims to offer researchers and clinicians a thorough understanding of AI-CDSS design principles and their future potential.

DOI: http://doi.org/10.5281/zenodo.20706812

Published by: vikaspatanker

Authors: Sheri Srujan Reddy, Thota Ramanna Dora Prabhas, Mancholla Ranateja, Assistant Professor Dr. P Kiran Kumar

Abstract: Traditional control surfaces on aircraft have been based on rigidly hinged flap sections that create unavoidable geometric discontinuities. These generate early flow separation and parasite drag, hindering aerodynamic performance in different flight conditions. This study explores the application of camber morphing, a biological concept involving wing deformation similar to those seen in bird-like flying organisms. The main goal of this study was to develop an adaptable mechanism, capable of changing the average camber line of the airfoil while keeping its structural integrity intact. The focus is put on a “Fishbone Active Camber” (Fish BAC), or [add name of the mechanism used, for instance, SMA or Rib-Linkage] based structure which replaces a hinge mechanism at the rear-spar position of the wing with a continuous flexible skin allowing for an even pressure distribution along the wingspan. The method involved a two-step approach. First, numerical simulations were carried out using an omega SST turbulence model to compare the aerodynamic parameters of the standard NACA 2412 airfoil with a morphing one. It is evident that the morphing wing has successfully reduced pressure drag significantly by removing the "hinge-gap" problem. More precisely, when the Angle of Attack (AOA) is 6 degrees, the morphing wing has shown a Lift-to-Drag ratio improvement of about 12 to 15 percent over the conventional flaps wing system. Also, flow visualization proved that the onset of turbulence occurred much later, thus broadening the aircraft's range of efficient flight.

DOI: https://doi.org/10.5281/zenodo.20706107

Published by: vikaspatanker

Authors: Mr. Hemant Vanjari, Mr. Jay Deshmukh, Assistant Professor Ms.Pratibha Makar, Dr.Vijaykumar Kale, Dr.Mahesh Thakre

Abstract: Lately, more people pay notice to plant-based beauty products – main reason being they tend to be gentler, work well, rarely cause trouble unlike lab-made versions. This research zeroes in on crafting and testing a multi-plant shampoo made entirely from nature's lineup: Amla joins shikakai, those mix with soap nuts while bhringraj slips in beside hibiscus; fenugreek seeds blend with rice extract, stick amaltas pairs up with flaxseeds, then rosemary teams with aloe vera plus curry leaves tag along too. Long before labs existed, these plants earned rep for helping hair grow stronger, cutting down flakes, keeping strands from dropping, boosting scalp condition, adding glow to locks. Put together with earth-friendly carriers, the mix faced checks on looks, acidity level, thickness, how rich the bubbles get, if gunk spreads out when washed, how fast water soaks into fabric, pull at liquid surfaces, even how steady it stays over time. Results? Cleans thoroughly, makes foam just fine, hits the right acid balance, conditions like a charm – all without making scalps itch. From roots up, plant-based mix fed each strand what it needed. Hair grew stronger, smoother – no harsh stuff involved. Results showed this blend worked just as well as lab-made options. Cost stayed low, safety held steady. Folks using it daily found fewer issues than expected. Not one person reported serious irritation. Science backed its role in regular

Published by: vikaspatanker

Authors: R A Shasank

Abstract: In the rapidly evolving landscape of financial technology, the imperative for model interpretability often conflicts with the pursuit of predictive accuracy. Financial institutions heavily rely on automated credit scoring models; however, the lack of transparency in conventional "black-box" approaches—such as deep neural networks and complex ensemble methods—poses significant regulatory and ethical risks. This paper introduces a hybrid credit risk assessment framework that bridges the gap between performance and interpretability. By leveraging First-Order Inductive Learners (specifically the RIPPER algorithm), the proposed model transforms raw financial data into a structured set of human-auditable domain rules. Furthermore, we implement a novel "Abstention-Driven Human Audit" layer, which identifies cases with marginal prediction confidence and redirects them for manual expert review. The experimental analysis, conducted on standard benchmark datasets, demonstrates that this architecture maintains competitive predictive power while providing a clear, logical rationale for every automated decision. The results highlight that the integration of rule-based logic not only fosters regulatory compliance but also enhances stakeholder trust in automated financial systems. This study contributes a scalable, transparent, and robust alternative for modern credit risk management.

Published by: vikaspatanker

Authors: Nikita Khawase, Nishant Kadam, Swarup Chaudhari, Rushikesh Patil, Hrishikesh Kakade

Abstract: Automated vehicle monitoring is a cornerstone of modern security infrastructure, essential for maintaining safety and operational efficiency in high-traffic environments such as industrial complexes, gated communities, and public facilities. Traditional manual surveillance methods are frequently plagued by human error, significant labor costs, and operational bottlenecks that compromise the integrity of security protocols. This paper presents a robust framework for an automated Vehicle Entry Monitoring System (VEMS) utilizing the state-of-the-art You Only Look Once (YOLO) object detection architecture. The proposed system integrates real-time video stream processing with advanced deep learning models to achieve high-speed detection and classification of various vehicle types, including cars, trucks, and motorcycles. A critical component of the methodology involves the integration of Optical Character Recognition (OCR) and tracking algorithms, such as DeepSORT, to automatically extract alphanumeric license plate data and maintain unique vehicle identities across consecutive frames. This integration enables the creation of a comprehensive, searchable database that cross-references detected plates with authorized whitelists for proactive access control. Experimental results demonstrate that the system ensures near 100% operational uptime by automating the data trail for security auditing and regulatory compliance. The framework provides a scalable solution for intelligent transportation management, significantly reducing manpower dependency while enhancing the reliability of entry logs. By combining real-time detection overlays with a centralized monitoring dashboard, this research offers a sophisticated, data-driven approach to facility security, fostering safer and more efficient urban mobility environments.

Published by: vikaspatanker

Authors: Jatin Nikhade, Professor Ar. Vaishali Sharma

Abstract: Vernacular architecture offers a viable and underutilized framework for addressing the sustainability failures of contemporary construction in India. Through a comparative literature review and analysis of documented case studies from Kerala, Rajasthan, Assam, and Ladakh, this study finds that traditional building systems consistently achieve lower embodied energy, superior passive thermal performance, and stronger cultural continuity than their modern counterparts — without reliance on mechanical systems. The study also critically examines the limitations of vernacular methods, including structural vulnerability, maintenance demands, and inability to scale in rapidly urbanizing contexts. It concludes that a hybrid model — integrating vernacular passive design, traditional materials upgraded through modern engineering, and digital fabrication tools — presents the most feasible pathway to a sustainable built environment in India.</

Published by: vikaspatanker

Authors: Deepika Kashyap, Durgesh Singh, Harsh Pandey, Nikhil Ahirwar, Nikhil Gautam, Nishant Kumar, Rahul Singh

Abstract: The increasing use of electric bicycles (E-bikes) in rural areas has created a need for effective security solutions to prevent theft and unauthorized access. Conventional locking mechanisms often provide limited protection and may not alert owners during theft attempts. This paper presents an E-Bike Lock and Anti-Theft Alarm System for Rural Areas that combines electronic locking, motion detection, alarm generation, and wireless communication technologies. The proposed system uses a microcontroller, sensors, GSM/Bluetooth modules, and an electronic locking mechanism to secure the E-bike. When unauthorized movement or tampering is detected, the system activates an alarm and sends notifications to the owner. Performance parameters such as detection accuracy, response time, power consumption, and communication reliability are analyzed. Experimental results indicate that the system provides enhanced security, low power consumption, and improved protection against theft in rural environments.

DOI: http://doi.org/10.5281/zenodo.20701189

Published by: vikaspatanker

Authors: Deendayal Dhakad, Deependra Rajak, Navneet Dhakad, Pooja Kewat, Ritik Dhakad, Dr. Prakhar Singh Bhadoria

Abstract: The advancement of smart home technologies has transformed the way people interact with household appliances. Conventional home automation systems often require manual operation or mobile applications, which may not be convenient for all users. This paper proposes an Intelligent Household System Using Voice Tag that enables users to control household devices through voice commands. The system utilizes voice recognition technology, microcontrollers, wireless communication modules, and smart sensors to automate home appliances efficiently. Voice commands are processed and converted into control signals that operate electrical devices such as lights, fans, air conditioners, and security systems. The proposed system improves user convenience, enhances accessibility for elderly and disabled individuals, and supports energy-efficient operation. Performance parameters such as voice recognition accuracy, response time, communication reliability, and energy consumption are analyzed. The study concludes that voice-based intelligent household systems offer a practical and user-friendly solution for modern smart homes.

DOI: http://doi.org/10.5281/zenodo.20700978

Published by: vikaspatanker

Authors: Dr Ansari Pulickal Abdul Azeez, Farooq Sajjad

 

Abstract: Digitization of business education at an unprecedented rate has made available to educators large amounts of student interaction data that can inform data-driven learning interventions. In this paper, we propose an Artificial Intelligence-driven Learning Analytics (AI-LA) system architecture, which incorporates multi-stream data sources (Learning Management System (LMS) logs, clickstream analysis, test/assignment submissions, and engagement data) to model, explain, and improve student engagement and performance. Our approach leverages a novel combination of techniques that include a Temporal Fusion Transformer (TFT) model for sequential behavior prediction, SHapley Additive exPlanations (SHAP) for interpretable feature importance, and reinforcement learning (RL) engine for personalized intervention recommendations. Our model was tested using longitudinal data from 3,400+ business management students in 24 courses over three academic years (2022-2025). It predicted at-risk students with up to 89.5% accuracy si

DOI: https://doi.org/10.5281/zenodo.20700051

 

Published by: vikaspatanker