Category Archives: Uncategorized

Authors: Miss . Chilantharajula Tejasri, Dr. K.Venkata Rao

Abstract: The opioid crisis, a pressing global public health issue, has led to a significant rise in overdose deaths, particularly among individuals under 50, with profound social and economic impacts. This study proposes a comprehensive forecasting system to predict drug use and overdose trends by integrating diverse data sources, including police reports, social network data, medical records, and sewage-based drug epidemiology. Utilizing Recurrent Neural Networks (RNNs), the system aims to identify individuals at risk of opioid abuse by analysing demographic information, medical histories, and prescription records, while distinguishing between therapeutic and harmful usage. Emphasizing privacy protection, ethical data handling, and model interpretability, this approach seeks to enhance the accuracy and timeliness of overdose risk predictions. The findings have the potential to inform clinical decision-making, shape public health policies, and drive targeted interventions to mitigate the opioid epidemic.

DOI: https://doi.org/10.5281/zenodo.17430579

Published by: vikaspatanker

Authors: Shamli Gaikwad, Dixsha Wasnik, Stuti Tripathi, Shubhangi Rahangdale, Prof. Pooja H. Rane

Abstract: A web-based interactive platform called The Virtual Herbal Garden was created to close the knowledge gap between conventional medical procedures and contemporary digital accessibility. The platform, which has its roots in the AYUSH (Ayurveda, Yoga & Naturopathy, Unani, Siddha, and Homeopathy) healthcare system, uses multimedia integration, 3D visualization, AI chatbot support, and sharing and bookmarking tools to educate users about medicinal plants.This study describes how the project was developed and put into use utilizing cutting-edge web technologies like React.js, MongoDB, and APIs like Sketchfab and OpenAI. One major gap in the current digital herbal databases, according to the research, is the absence of easily accessible, interactive, and multilingual resources. To overcome these obstacles, an agile development methodology and user-centered design were applied.Improved user engagement, efficient plant discovery using search and filters, and improved instruction through interactive features are some of the main outcomes. Future improvements are suggested, such as mobile apps, AR integration, and AI-driven plant identification, while limitations like internet dependence and content scope are examined. In the end, this project shows how technology can be used to support natural health education, preserve indigenous knowledge, and stimulate interest in sustainable, traditional healing methods.

Published by: vikaspatanker

Authors: Ali Akbar, Komal Sarwar

Abstract: Heavy metals, prevalent in various environmental matrices due to industrial and agricultural activities, pose significant health risks, including the promotion of cancer through the induction of oxidative stress. This paper reviews the mechanisms by which heavy metals such as arsenic, cadmium, chromium, and lead contribute to oxidative stress, leading to cellular damage and cancer development. We explore the complex interplay between heavy metal exposure, oxidative stress, and the activation of key signaling pathways involved in carcinogenesis. Understanding these mechanisms is crucial for developing effective strategies to mitigate the health impacts of heavy metal exposure and improve cancer prevention efforts.

DOI: https://doi.org/10.5281/zenodo.17424408

Published by: vikaspatanker

Authors: S.Gayathri, Dr.S.Siva Ranjani, Dr.B.Lalitha

Abstract: This project presents an AI-based thermographic weld joint inspection system designed to automatically detect defects in weld joints using deep learning models, specifically Convolutional Neural Networks (CNN) and the YOLO (You Only Look Once) object detection algorithm. By leveraging thermographic imaging, which captures the thermal profile of welded joints, this system aims to identify inconsistencies and anomalies indicative of defects such as cracks, porosity, and lack of fusion. The proposed approach utilizes CNN for image classification to determine whether a weld is defective or not, while YOLO is employed for precise localization and detection of defects within the thermographic images. The dataset comprises labeled thermographic images of weld joints, preprocessed and augmented to enhance model performance. The CNN model is trained to distinguish between defective and non-defective welds, achieving high classification accuracy. Simultaneously, YOLO is trained to detect multiple types of defects in real-time with high precision and recall. The combination of CNN and YOLO ensures both robust classification and efficient object detection. Evaluation metrics such as accuracy, F1-score, mean Average Precision (mAP), and Intersection over Union (IoU) are used to assess model performance. Experimental results demonstrate the effectiveness of deep learning in automating weld inspection, reducing human error, and increasing inspection speed. The system is scalable and adaptable to various welding processes and materials. Deployment of this AI solution can significantly improve quality assurance in manufacturing.

Published by: vikaspatanker

Authors: Abeshin Ayodele

Abstract: The integration of Artificial Intelligence (AI) is transforming strategic operations across global industries, yet its impact on multi-channel distribution networks particularly in complex sectors like heating, ventilation, and air conditioning (HVAC) remains underexplored. This study explains a theoretical framework for understanding the strategic implications of AI integration within the multi-channel networks of multinational HVAC manufacturers. The traditional HVAC distribution network comprising direct sales, retailers, contractors, digital platforms and third-party service providers; has been characterized by manual processes and legacy systems. AI's emergence introduces predictive analytics, automated CRM systems, intelligent routing, and real-time data integration that collectively shift how firms manage and interact with their channel partners. These changes, while beneficial, raise critical challenges such as channel conflict, role redundancy, partner resistance, and uneven digital maturity across regions. Thus, there is a pressing need for a structured theoretical framework that captures the complexity and strategic relevance of AI’s role in reshaping these networks. To address this gap, the study draws on four complementary theoretical lenses: the Resource-Based View (RBV), Actor-Network Theory (ANT), Technology- Organization-Environment (TOE) framework, and Diffusion of Innovation (DOI) theory. The RBV positions AI as a valuable, rare, and inimitable resource that, when aligned with internal capabilities and existing assets, can provide a sustainable competitive advantage through differentiated channel management strategies. ANT broadens this view by conceptualizing AI not just as a technological tool but as an active agent within the distribution network. It highlights how human and non-human actors (e.g., AI systems, managers, distributors) negotiate roles and power relations, co-creating new channel configurations and organizational behaviors. The TOE framework provides a holistic understanding of how technological, organizational, and environmental factors interact to influence AI adoption. It explains how firms' internal readiness, market pressures, and regulatory environments shape the pace and depth of AI integration within channel strategies. Finally, the DOI theory offers insights into the diffusion process of AI across channel partners, emphasizing how adoption is influenced by the perceived attributes of AI technologies and the social systems through which innovation spreads. It identifies early adopters within the network and highlights strategies to accelerate diffusion through communication, training, and observable results. Together, these theoretical perspectives present a robust framework for examining the strategic transformation of multi-channel networks in the HVAC industry due to AI. The study contributes to scholarly understanding of digital transformation in B2B networks while offering practical guidance for HVAC manufacturers aiming to align AI capabilities with channel strategy

DOI: https://doi.org/10.5281/zenodo.17414506

Published by: vikaspatanker

Authors: Arun Prabhu S, Dr. chetan V Hiremath

Abstract: Kerala, known as the “Spice Garden of India,” plays a vital role in India’s spice trade, with Small and Medium Enterprises (SMEs) forming the backbone of the sector. However, these SMEs face significant sustainability challenges due to climate variability, market volatility, certification hurdles, and infrastructural limitations. This study aims to analyze the key risk factors affecting the supply chains of Kerala’s spice SMEs and their impact on sustainable supply chain performance (SSCP). Using a structured questionnaire and descriptive analysis, the study identifies five major risk dimensions—climate and environmental risks, market price volatility, certification and regulatory compliance, financial constraints, and logistics and infrastructure gaps. Findings reveal that climate and environmental risks and price volatility negatively influence SSCP, while certification and compliance contribute positively. Financial and infrastructural challenges show limited but notable effects on resilience. The study concludes that effective risk management, improved access to finance, climate adaptation training, and sustainable practice adoption are essential for enhancing supply chain resilience and competitiveness. Recommendations include establishing price stabilization mechanisms, upgrading infrastructure, and promoting sustainability certifications. The research offers valuable insights for policymakers and SMEs to strengthen Kerala’s spice supply chain against sustainability risks.

Published by: vikaspatanker

Authors: NahulRaj.K

Abstract: The study titled “A Study on Quality Management Practices in Small-Scale Manufacturing Units in Karur, Tamil Nadu” aims to examine the extent of adoption, challenges, and impact of quality management practices (QMPs) in the region’s manufacturing sector. Small-scale industries (SSIs) play a vital role in Karur’s industrial landscape, particularly in textile and allied manufacturing, contributing significantly to local employment and exports. However, these units often face barriers in implementing structured quality systems due to constraints such as limited financial resources, lack of technical expertise, and inadequate awareness.This research investigates the various quality management tools and practices adopted by SSIs, including Total Quality Management (TQM), ISO certification, and continuous improvement initiatives. It also analyses the challenges faced in implementing these systems and evaluates their influence on business performance indicators such as customer satisfaction, productivity, competitiveness, and profitability. The findings reveal that while awareness of quality management practices is increasing, the degree of implementation remains moderate due to cost and resource limitations. Units that have adopted structured QMPs report noticeable improvements in product quality and customer satisfaction. The study concludes that fostering government support, providing technical training, and promoting awareness can significantly enhance the quality performance of small-scale manufacturing units in Karur

Published by: vikaspatanker

Authors: Koushal.M

Abstract: The outbreak of the COVID-19 pandemic brought severe disruptions to global and local supply chains, impacting production, labour, transportation, and market dynamics across various sectors. The tea industry, a vital component of Tamil Nadu’s agricultural economy, was particularly affected due to its heavy reliance on manual labor and complex distribution networks. This study investigates the post-pandemic supply chain challenges faced by tea estates in Tamil Nadu, focusing on major tea-producing regions such as the Nilgiris, Coimbatore, and Anamalai Hills. The research aims to identify key factors influencing supply chain resilience and sustainability after the pandemic. Primary data were collected through structured questionnaires from 160 respondents, including estate managers, supervisors, and supply chain personnel. The study examines the role of technology adoption, supplier relationships, workforce flexibility, risk management practices, and market access in strengthening supply chain resilience. The collected data were analysed using SmartPLS (Partial Least Squares Structural Equation Modelling) to validate the conceptual model and assess the significance of hypothesised relationships. The model demonstrated a good fit (SRMR = 0.047, NFI = 0.868), confirming the reliability of the proposed framework. The findings revealed that all five independent variables have a positive and significant impact on supply chain resilience, indicating that digital transformation, strong supplier networks, flexible labor practices, and proactive risk management collectively enhance post-pandemic recovery. This study contributes to the limited literature on supply chain resilience in the Indian plantation sector and provides practical insights for tea estate managers and policymakers. It emphasises the need for modernising the supply chain through technology integration, digital forecasting tools, and workforce development to ensure long-term competitiveness and sustainability.

Published by: vikaspatanker

Authors: Vijayalakshmi. G, Ms. P. Kalaiselvi, B. Lalitha

Abstract: Crack detection in building structures is critical for ensuring safety and preventing costly repairs. Traditional crack detection methods often face challenges in accurately identifying cracks due to the complexity of the structure and the subtlety of the damage. This work proposes a hybrid deep learning framework that integrates CaTNet (ConvNeXt + Transformer Block) and Vision Transformer (ViT) for effective feature extraction, followed by XGBoost for classification. CaTNet combines ConvNeXt-style convolutional blocks and Transformer encoders to capture both fine-grained spatial details and global contextual relationships within the building images, while ViT processes the images as patch sequences to further enhance the capture of global structural patterns. The extracted features from both models are fused using dense layers with dropout for refinement. XGBoost is then employed for classification, optimized using multi-log loss (mlogloss) and evaluated with classification reports, confusion matrices, and training loss curves. Experimental results show that the proposed model significantly outperforms conventional crack detection methods in terms of accuracy, robustness, and real-time applicability, positioning it as a promising approach for crack detection in building infrastructure

Published by: vikaspatanker

Authors: Tejinder Sandhu

Abstract: The integration of Salesforce AI agents across hybrid multi-cloud environments is redefining the enterprise Customer Relationship Management (CRM) landscape. Middleware solutions, particularly Apache Tomcat and JBoss, play a critical role in enabling seamless interoperability between Salesforce’s AI-driven services and diverse enterprise systems hosted on Unix/Linux and cloud infrastructures. This review explores how Tomcat’s lightweight architecture and JBoss’s enterprise-grade features collectively support API management, workflow orchestration, transaction integrity, and scalability. It also examines performance optimization strategies, industry-specific applications, and comparative insights with alternative middleware platforms such as MuleSoft, WebSphere, and Apache Kafka. Furthermore, the study highlights future directions, including AI-driven orchestration, edge computing integration, generative AI for middleware automation, and security-first architectural models. By providing a comprehensive analysis, this review underscores how middleware technologies are foundational for deploying Salesforce AI agents in complex enterprise ecosystems, ultimately enabling organizations to achieve resilience, compliance, and customer-centric innovation in the digital age.

DOI: https://doi.org/10.5281/zenodo.17368656

 

Published by: vikaspatanker