Category Archives: Uncategorized

Authors: Harshitha T N, Soujanya R

Abstract: Oral cancer is a critical and life-threatening disease, where early detection plays a vital role in improving patient survival rates. However, traditional diagnostic approaches rely heavily on manual clinical examination and biopsy, which are time-consuming, invasive, and often lead to delayed diagnosis. To address these limitations, this paper proposes a deep learning framework for automated oral cancer detection using medical image analysis and lesion-focused classification techniques. The proposed system integrates image preprocessing, lesion segmentation, and deep convolutional neural networks (CNNs) for accurate classification. Preprocessing techniques such as contrast enhancement and noise reduction are applied to improve image quality. Lesion regions are extracted using Otsu thresholding and contour-based segmentation to isolate regions of interest (ROI), which enhances feature learning. Multiple deep learning architectures, including Baseline CNN and EfficientNet-B0 are evaluated for performance comparison. In addition, the proposed framework integrates lesion segmen-tation and deep feature extraction to improve classification robustness and diagnostic performance. To enhance model interpretability, Grad-CAM is employed to visualize the regions contributing to predictions, making the system more transpar-ent for medical applications. Experimental results demonstrate that the proposed EfficientNet-B0 based model achieves superior performance compared to baseline approaches, with improved accuracy and F1-score on the test dataset. The proposed framework provides an efficient, scalable, and interpretable solution for early-stage oral cancer detection, supporting clinical decision-making and reducing diagnostic delays.

Published by: vikaspatanker

Authors: Dr Nilani Sammuarachchi

Abstract: Type 2 Diabetes Mellitus (T2DM) constitutes a major and escalating global and national public health challenge, characterised by rising prevalence, substantial complication burden, and profound impacts on physical, psychological, and social wellbeing. Despite the availability of effective pharmacological treatments, evidence-based clinical guidelines, and structured diabetes education programmes, a significant proportion of individuals continue to experience suboptimal glycaemic control and diminished quality of life. These persistent gaps highlight the need for integrative approaches that extend beyond biomedical management to address behavioural, emotional, and contextual influences on diabetes self-management. This doctoral research applied the TAP-IT mixed-methods framework to examine the interrelationships between clinical indicators, self-care behaviours, emotional experiences, and lived realities of adults managing T2DM. A convergent mixed-methods design was employed, involving 150 adults diagnosed with T2DM who participated in quantitative surveys, clinical assessments, and in-depth qualitative interviews. Quantitative analyses demonstrated high levels of medication adherence (80%), moderate dietary adherence (65%), and comparatively low engagement in physical activity and psychological support behaviours. Significant associations were identified between self-care behaviours and key clinical indicators, including glycated haemoglobin (HbA1c), body mass index (BMI), and blood pressure, underscoring the central role of lifestyle and behavioural factors in glycaemic control and cardiometabolic risk. Qualitative thematic analysis revealed diabetes-related distress, cultural expectations, family and caregiving responsibilities, limited motivation, and time constraints as major barriers to sustained self-management, while strong family support, culturally responsive healthcare, and positive clinician–patient relationships emerged as critical facilitators. Triangulation of quantitative, qualitative, and clinical data generated a comprehensive and integrated understanding of how emotional burden and contextual constraints shape behavioural patterns and metabolic outcomes in T2DM. The TAP-IT framework proved effective in identifying misalignments between clinical recommendations and the lived experiences of individuals managing diabetes in everyday contexts. The findings emphasise the necessity of person-centred and culturally responsive care models that integrate emotional support, tailored health education, and community-based interventions alongside clinical management. This study contributes novel evidence demonstrating that effective T2DM management requires coordinated, multidimensional strategies addressing biological, behavioural, psychological, and sociocultural determinants simultaneously, with particular relevance for Māori, Pasifika, and South Asian populations in Aotearoa New Zealand.

DOI: http://doi.org/10.5281/zenodo.20560629

Published by: vikaspatanker

Authors: Raushan Kumar, Dr. Navneet Seth

Abstract: The rapid growth of social media platforms has significantly transformed consumer behavior and purchasing patterns across India. While extensive research has examined the influence of social media marketing in metropolitan regions, limited attention has been given to its impact on consumers residing in Tier-II cities. This study explores the effect of key social media marketing factors, namely influencer endorsements, online reviews, targeted advertisements, brand interaction, and user-generated content (UGC), on consumers' purchase intentions in Bathinda city. A quantitative research approach was adopted, and primary data were collected through structured questionnaires administered to 150 respondents, primarily college students aged between 18 and 35 years, who constitute one of the most active segments of social media users. The data were analyzed using multiple linear regression techniques to determine the relationship between social media marketing variables and purchase intention. The findings reveal that all five variables exert a significant positive influence on consumers' buying intentions, explaining a substantial proportion of the variation in purchase behavior (R² = 0.68, p < .001). Among the examined factors, influencer endorsements (β = 0.41) and online reviews (β = 0.33) emerged as the most influential predictors of purchase intention. Furthermore, reliability analysis demonstrated strong internal consistency across all measurement constructs, with Cronbach's alpha values exceeding 0.79. The study enriches the existing literature by providing empirical evidence from a Tier-II Indian city and highlights the growing importance of social media marketing in shaping consumer decisions beyond major urban centers. The findings offer valuable insights for marketers and businesses seeking to develop effective digital marketing strategies targeted at increasingly connected and socially engaged consumers.

Published by: vikaspatanker

Authors: Akash katheria, Dr Vinod Kumar

Abstract: Employment generation remains one of the most significant indicators of economic development in India. The country's workforce is distributed across both organised and unorganised sectors, each playing a distinct role in creating employment opportunities. While the organised sector offers formal employment, job security, social protection, and regulated working conditions, the unorganised sector continues to absorb a substantial share of the labour force, particularly among low-skilled and economically vulnerable populations. This study examines and compares the contribution of organised and unorganised sectors to employment generation in India. The research analyses trends in employment, sectoral distribution of workers, wage structures, job security, and the quality of employment opportunities available in both sectors. It also explores the challenges faced by workers, including issues related to income stability, social security benefits, and working conditions. The study is based on secondary data collected from government reports, labour surveys, and published literature. The findings reveal that although the organised sector contributes significantly to productivity and economic growth, the unorganized sector remains the largest source of employment in India. However, employment in the unorganised sector is often characterized by low wages, limited social protection, and higher job insecurity. The study highlights the need for policies that promote formalization, skill development, and social security coverage to improve the quality of employment across sectors

Published by: vikaspatanker

Authors: Ajay Malviya, Dr. Satnam Singh

Abstract: The present work focuses on the CFD-based evaluation of thermal performance and Nusselt number enhancement in a heat exchanger using modified twisted tape inserts. Twisted tape inserts are widely used passive methods for improving heat transfer in internal flow systems. In this study, four geometries were analyzed: Plain Twisted Tape (PTT), Double-Hole Perforated Twisted Tape (DHPTT), Curved-Slot Twisted Tape (CSTT), and Multi-Hole Perforated Twisted Tape (MHPTT). A circular pipe of 44 mm outer diameter, 42 mm inner diameter, and 400 mm length was modeled with a 1 mm thick twisted tape. The total twist angle was 1800°, forming five complete rotations with an 80 mm twist pitch. The CFD model was developed in ANSYS Fluent using a polyhedral mesh of 472,350 cells. Water was used as the working fluid, while the pipe and tape were modeled as aluminum. The inlet velocity and temperature were 0.6 m/s and 293 K, and the pipe wall temperature was 365 K. The standard k-epsilon model was used for turbulent flow analysis. Results showed that MHPTT achieved the highest outlet temperature of 345.99 K, temperature rise of 52.99 K, and 18.09% change. The Nusselt number also increased with Reynolds number. Overall, MHPTT gave the best thermal performance.

DOI: http://doi.org/10.5281/zenodo.20556413

Published by: vikaspatanker

Authors: K. Chaitanya, Assistant Professor Nekuri Jyothsna

Abstract: Diabetes mellitus is a growing chronic health condition that needs to be detected at an early stage to avoid complications. Machine learning (ML) is proving to be an efficient solution for developing Clinical Decision Support Systems (CDSS), which aid doctors in diagnosing and predicting diseases. The research aims to develop an artificial intelligence-based CDSS for diabetes prediction using supervised machine learning algorithms such as Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB). The results of the experiments prove that the ensemble methods are better than traditional methods. The proposed CDSS is a solution for predicting diabetes mellitus and shows its potential for providing accurate insights for decision-making in the health care industry. The use of such artificial intelligence-based CDSS is significant for decision-making in health care.

DOI: https://doi.org/10.5281/zenodo.20555588

Published by: vikaspatanker

Authors: Assistant Professor Prajina V K, Assistant Professor Bhargavi M R

Abstract: Despite the technological advancements in agriculture, it continues to be vulnerable to climate change effects, and poor crop choice due to unfavorable conditions results in low yields and monetary hardship to farmers. This paper proposes a hybrid machine learning approach for crop recommendation that takes into account not only the weather forecast (rainfall, temperature, humidity) but also soil characteristics (pH, nitrogen, phosphorus, potassium). It consists of two stages: the Random Forest algorithm for feature selection and prediction followed by the XGBoost algorithm for correction of predicted values. Applying the approach to the data set of 50,000 crop images tagged by location for 15 main crops within a period of 10 years (2015-2025) in India, the hybrid algorithm reaches the accuracy level of 94.2% compared to Random Forest (89.3%), XGBoost (91.6%), SVM (84.2%), and KNN (81.5%). Rainfall and minimum temperature were recognized as crucial features by the algorithm. The proposed algorithm is implemented in a smartphone application for farmers that provides recommendations based on weather forecasts for the next 5 days, which allows increasing crop yields up to 20-30%.

DOI: https://doi.org/10.5281/zenodo.20555541

Published by: vikaspatanker

Authors: Assistant Professor Gargi Mishra, Assistant Professor S Anantha Priyadharsini

Abstract: Access to quality healthcare in developing nations often remains challenging due to several factors including geographical distance, shortage of competent medical professionals, and lack of diagnostic facilities. This study proposes an efficient cloud-based smart health kiosk that facilitates the delivery of cost-effective, easy-to-access, and quality diagnostic services. The design of the kiosk involves the use of IoT enabled medical sensors (digital stethoscope, infrared thermometer, pulse oximeter, blood pressure measurement device, glucometer, ECG, and urinalysis dipstick reader) and edge computing gateway for capturing the data and pre-processing the acquired data. Telemedicine is used for establishing a video connection between the patient and remote physician. Medical data is transferred to the cloud storage through an HIPAA compliant network for long-term storage and initial triaging using artificial intelligence. After deployment at 50 rural areas in India serving 250,000 patients in 18 months, average travel time decreased from 32 km to 1.5 km and out-of-pocket costs were minimized by 68%. Patient satisfaction rate was recorded to be 94%.

DOI: https://doi.org/10.5281/zenodo.20555450

Published by: vikaspatanker

Authors: Prof. Ashwini Sawant, Ajinkya Shriram Gurav, Prasad Nagnath Londe, Prasanna Motiram Kasabe

Abstract: The integration of Information and Communication Technology (ICT) in rural governance is a critical step towards a "Digital India." This research discusses the design and development of E-Grampanchayat, an automated administration portal. The system addresses the inefficiencies of the traditional manual ledger-based system by digitizing document requests, notice dissemination, and tax collection. A unique contribution of this paper is the Hybrid Fiscal Verification Module, which allows asynchronous verification of UPI-based tax payments. The system was developed using a PHP-MySQL architecture and tested in a localized server environment, demonstrating high data consistency, reduced processing latency, and improved transparency in local self-government operations.

Published by: vikaspatanker

Authors: Gunta Deekshitha Raj, Yasa Shivanandhan Reddy, Suragoni Vaishnav Sai Goud, Mrs. H. Meenal

Abstract: Gold is one of the most valuable and widely traded commodities in the world, playing a significant role in global financial markets, investment portfolios, and economic stability. Due to its ability to act as a hedge against inflation, currency fluctuations, and economic uncertainties, the analysis of gold prices and supply has become increasingly important for researchers, investors, and policymakers. This project focuses on the analysis and visualization of global gold price and supply trends from 2010 to 2025 using Tableau, a powerful data visualization tool. The dataset used in this study contains information related to gold prices, gold supply, demand, trading volume, countries, regions, market types, and other economic attributes. The dataset was collected from reliable sources and processed to ensure consistency and accuracy. Data preprocessing techniques were applied to organize and prepare the dataset for visualization and analysis. Various dimensions and measures present in the dataset enabled a comprehensive study of gold market behavior across different geographical regions and time periods. To gain meaningful insights, multiple visualization techniques were implemented using Tableau. These include line charts, bar charts, dual-axis charts, funnel charts, waterfall charts, heat maps, highlight tables, geographical maps, timelines, crosstabs, and interactive dashboards. The visualizations were designed to explore trends in gold prices, compare gold supply across countries and regions, analyze trading volumes, and identify patterns over time. Interactive features such as filtering, highlighting, and dashboard actions were also incorporated to improve user exploration and data interpretation. The analysis revealed noticeable variations in gold prices and supply over the years, highlighting the influence of market conditions and regional factors on gold-related activities. Comparative visualizations helped identify differences among countries and regions, while time-series analysis provided insights into long-term trends and fluctuations. The dashboards enabled users to interact with the data and obtain a clearer understanding of relationships between different variables. Overall, this project demonstrates the effectiveness of data visualization in transforming complex financial datasets into meaningful and easily understandable insights. The findings contribute to a better understanding of global gold market trends and showcase how Tableau can be used as an effective tool for exploratory data analysis, decision-making, and financial market research.

Published by: vikaspatanker