Authors - Rajkiran R Nair, Arya k, Durga K V Abstract - The role of digital investment platforms in facilitating the participation of people in financial markets cannot be overstated. However, despite the ease of access, convenience, and cost savings provided by these platforms, their adoption among women in developing countries seems to be low. The objective of this research was to examine the factors that affect women’s intention to use digital investment platforms. The factors identified in this study were technology acceptance, trust, financial literacy, perceived security, social influence and perceived risk. The research findings showed that the perceived security was the most influential factor affecting the adoption intention of digital investment platforms among women, while the other factors had an indirect influence. The research also found that the traditional technology acceptance model has the limitations of predicting the behaviour of women in investing in the stock market. The research provided helpful insights for FinTech companies to create safer environments for their customers.
Authors - Akruti Dabas, Madhura Jangale, Rujuta Medhi, Shravani Patil and Kajal Joseph Abstract - Indian agriculture faces significant challenges due to the opacity of the supply chain system with exploitation by intermediaries that reduce profitability and market reach for the farmers. The Agrimitra project uses blockchain and machine learning technologies to solve these issues by facilitating farmer-to-consumer transactions while recording prices in immutable ledgers. In this platform, blockchain is used for implementing smart contracts to maintain transparent pricing whereas machine learning is used to analyze past market trends and generate price-recommendation. Through the use of blockchain technology, farmers can set prices autonomously while keeping transactional records on a blockchain ledger, which cannot be tampered with. The Agrimitra platform addresses several challenges faced by the rural communities in India such as access to real-time market analysis, transparent credit history, buyers’ database, and a community at the regional level to take care of logistics in the transportation network efficiently and effectively.
Authors - Arunangshu Giri, Dipanwita Chakrabarty, Manash Routray Abstract - Credit-based transaction in petrochemical retail sector is widely practiced, though highly challenging, as the sector operates with a thin margin, in spite of high transaction volume. The present study identifies crucial determinants for adoption of ICT-enabled credit and discount process in the petrochemical retail sector. Diffusion of Innovation (DOI) Theory was adopted to evaluate the factors that influence trialability of ICT and there by leads to users’ understanding of relative advantage, which subsequently enhances their demand and purchase intention. Structured questionnaire was used as survey tool and hypotheses were tested using Structural Equation Modelling (SEM). The findings show that trialability get induced by social, relational and economic factors, which in consequence enhance relative advantage and improves purchase intention. The result shows that traditional to ICT-enabled payment transition does not solely depend on the financial parameters rather behavioral factors play a pivotal role. The study extends DOI theory in the context of infrastructure-based retail operations and provides deep insights to managers so that they can adopt customeroriented ICT strategies to improve credit-to-cash payment transformations.
Authors - Mamatha Kurra, Ochin Sharma, G S Pradeep Ghantasala Abstract - Accurate segmentation of pulmonary nodules in low-dose CT (LDCT) scans plays a crucial role in the early detection of lung cancer. However, small and irregular nodules remain difficult to detect due to low contrast, anatomical variability, and imaging artifacts. In this study, we perform a comparative evaluation of widely used deep learning-based segmentation architectures-namely, vanilla U-Net, Feature Pyramid Network (FPN), and Mask R-CNN-on benchmark datasets LIDC-IDRI and LUNA16. Building on the observed limitations of these models, we introduce a refined Hybrid U-Net architecture augmented with attention gates and Squeeze-and-Excitation (SE) blocks. This enhancement improves the model’s ability to focus on clinically relevant features while maintaining strong spatial consistency across encoder-decoder layers. Preprocessing involves Hounsfield Unit (HU) windowing (−1000 to 400 HU) to isolate lung parenchyma, followed by patch extraction (128×128) to better represent small nodules and manage class imbalance. The model is trained using a compound loss function that combines Dice loss and Boundary loss in a 0.7:0.3 ratio to balance volumetric overlap and edge accuracy. Experimental results on the LIDC-IDRI dataset show that the proposed attention guided model achieves a Dice coefficient exceeding 0.85, outperforming the baseline U-Net (average Dice 0.78). Evaluation metrics such as sensitivity (true positive rate) further confirm the effectiveness of our approach in capturing subtle nodule features. This work demonstrates that integrating attention mechanisms and feature recalibration into U-Net significantly boosts segmentation performance on challenging medical imaging tasks. Our results provide a strong foundation for deploying more accurate and interpretable tools in computer-aided diagnosis pipelines for lung cancer screening.
Authors - Jonalyn Joy B. Labayne, Joey Aviles, Ronald Cordova Abstract - This empirical study examines regional and demographic disparities in BMI and Waist-Hip Ratio (WHR) as indicators of nutritional and cardiometabolic health in the Philippines. Using the 2013 FNRI National Nutrition Survey dataset (n = 69,505 adults aged 20 years and above), data were processed with Apache Spark for distributed handling of large-scale heterogeneous records. A Random Forest classifier was trained with 10-fold stratified cross-validation and inverse class-weighting to mitigate severe class imbalance. The model achieved an accuracy of 0.81, macro-F1 score of 0.67, and area under the precision-recall curve (AUCPR) of 0.75. These FNRI-specific results are discussed in the context of existing literature. Genc and Arıcan (2025) compared eight machine learning algorithms on a Latin American obesity dataset (n = 2,111), excluding height and weight variables; Random Forest achieved the highest ROC AUC of 0.98 and macro-F1 of 0.87 in that study. The inclusion of WHR alongside BMI in the FNRI analysis provides enhanced cardiometabolic risk stratification. The findings underscore the value of ensemble methods in future Philippine research to better detect minority classes and support regionally targeted public health interventions in resource-limited settings.
Authors - Ruhi Sethi, Sambhram Pattanayak, Prachi Trivedi Abstract - Despite substantial investments in India's digital governance infrastructure, the adoption of mobile governance in ICT services among rural citizens remains critically low. Existing literature treats trust as a monolithic construct and fails to distinguish trust in government institutions, digital platforms, intermediaries, and social trust. This conceptual paper proposes the Human Digital Trust Bridge framework which integrates multidimensional trust theory with three mediation mechanisms. These mechanisms include human intermediaries such as Common Service Centre operators, low technology interfaces like voice-based services and assisted kiosks, and social networks including peer influence. Synthesizing evidence from 50 studies published between 2020 and 2026 and contrasting the cases of UMANG success and Sanchar Saathi trust failure, the framework demonstrates that rural adoption of mobile governance in ICT is not driven by digital trust alone but is mediated through these bridges. The paper deconstructs trust into four distinct dimensions: institutional, technological, intermediary, and social. It shows how each dimension differentially affects rural and urban adoption. The framework yields testable propositions for empirical research and offers actionable policy implications for inclusive mobile governance in ICT design.
Authors - Dimo Valev, Sambhram Pattanayak Abstract - In an era saturated with visual communication and digital interaction, the effectiveness of advertising increasingly depends on the strategic integration of graphic design principles, artificial intelligence (AI), and Digital Marketing and Social Media Intelligence. Good design can determine whether an advertisement is ignored or remembered, making visual communication a central component of successful contemporary advertising campaigns. This study investigates the roles of graphic design principles and AI‑driven design in advertising effectiveness in contemporary media environments. It focuses on how core visual elements—such as visual hierarchy, color theory, typography, layout composition, branding consistency, imagery, and interactivity interact with data‑driven and generative technologies to shape consumer perception, engagement, and recall. Drawing on theoretical frameworks from visual communication and empirical evidence from real‑world campaigns, the research analyzes how these principles are applied across print, digital, and social media platforms, often augmented by AI systems for personalization, layout optimization, and content generation. The findings show that advertisements that systematically apply key graphic design principles while integrating AI‑driven design tools—such as generative visuals, dynamic layouts, and data‑driven personalization—tend to achieve higher levels of attention, comprehension, and brand recall than those with weak or inconsistent design. The study also highlights how artificial intelligence has expanded the role of graphic design into functional, predictive, and experiential dimensions, enabling responsive, real‑time, and context‑aware advertising. The paper concludes with practical guidelines for designers and marketers on integrating graphic design principles with AI‑driven design processes to optimize attention, message retention, and overall campaign effectiveness.
