Authors - Deepali Newaskar, Saurabh Parhad, Anjali Yadav, Siddhi Shinde, Samika Karne, Atharva Nangare, Misbah Shaikh Abstract - This study investigates the effectiveness of a student-driven development (SDD) approach utilizing ChatGPT to create SQL-based inventory management systems for Micro, Small, and Medium Enterprises (MSMEs), with a focus on contributing to Sustainable Development Goal (SDG) 12 (Re-sponsible Consumption and Production). A mixed-method study involving 30 student-MSME collaborations was conducted to evaluate the resulting systems based on stock accuracy, reporting efficiency, and user satisfaction. The quantitative results demonstrate significant performance enhancements, with systems achieving average scores of 7.7 for stock accuracy, 7.63 for reporting efficiency, and 8.17 for user satisfaction (on a 10-point scale). Technical analysis showed ChatGPT's pivotal role in input validation (15 cases), SQL query construction (8 cases), and report optimization (7 cases). The most frequent SQL commands were SELECT (14 instances), UPDATE (11 instances) and INSERT (5 instances), highlighting robust data handling. The findings confirm that integrating AI tools like ChatGPT within an SDD framework can deliver practical, scalable, and sustainable digital solutions for MSMEs, advancing digital trans-formation while reinforcing the applied role of higher education in achieving global sustainability goals. These results highlight the potential of student-led AI-assisted development as a scalable model for MSME digital transformation aligned with SDG 12.
Authors - Lavanya K, Srinidhi G A Abstract - The pace with which artificial intelligence (AI) has been adopted in decision-critical applications has, in turn, elevated the need to have more than merely accurate AI systems that are also transparent and comprehendible. Although the complex machine learning models can be highly predictive, its black box strategy creates a question mark on the aspects of trust, accountability, and usability in real-world systems based on artificial intelligence. This paper examines the tradeoff between accuracy and transparency in interpretable machine intelligence and oranges by pointing to the trade-offs that exist between predictive accuracy and model explanation. There is a proposed structured framework which is used for comparing and investigating the black-box and interpretable models on the basis of quantitative performance measures and explainability measures. The article highlights the importance of explainable AI methods of post-hoc in improving the transparency of models without affecting the accuracy of the model significantly. Using a systematic assessment, the paper shows that interpretable machine intelligence may be used to help make reliable decisions and maintain competitive predictive performance. The results help in the creation of credible AI-based systems as it provides information about the creation of models that are effective in balancing the accuracy and interpretability when applied to different application settings.
Authors - Dev Kumar Prajapat, Chakshum Mittal, Abhishek Sharma, Jatin Yadav, Mohammad Shaad, Vishal Shrivastava, Ram Babu Buri, Akhil Pandey Abstract - This paper presents Printify, a real-time, location-based service platform revolutionizing document printing workflows via a dual-interface architecture: a Flutter-based mobile app for end-users and a React/TypeScript Progressive Web Application (PWA) for shopkeepers. Addressing inefficiencies like delays, security vulnerabilities, and service discovery limitations, Printify leverages Firebase for instantaneous cross-platform state synchronization. The PWA utilizes Service Workers for offline functionality and secure protocols enabling paymentconditional document release. Evaluations show a 73% reduction in processing latency, 95% improvement in service discovery, and Lighthouse scores exceeding 92. The platform achieves PCI-DSS compliance and end-to-end encryption, establishing a novel hybrid mobile-web paradigm for location-based services.
Authors - Suresh Reddy, Immanuel Anupalli, P.Sudheer Abstract - This paper presents a comparative framework for detecting knee and elbow form errors in overhead press videos using machine learning. Using more than 2,000 videos from the Fitness-AQA dataset, three models are evaluated: an Inception-based Long Short-Term Memory (LSTM) network with residual connections, a custom stacked LSTM network, and a feedforward neural network baseline. Human pose keypoints are extracted using MediaPipe, and frame-to-frame differences are computed to encode motion dynamics. The dataset includes temporally localized annotations with explicit start and end timestamps for knee and elbow errors, resulting in a class-imbalanced classification task. Model performance is evaluated using accuracy, precision, recall, F1- score, and confusion matrices. Experimental results demonstrate that the Inception-based LSTM consistently outperforms the alternative architectures, followed by the custom LSTM, while the feedforward baseline performs substantially worse. These findings highlight the importance of temporal modeling and multi-scale feature extraction for fine-grained Action Quality Assessment in weightlifting.
Authors - Tanvir Ahmed Fahim, Md. Sohel Rana, Shamsul Arefin Bipul, Tanvir Hasan, Niyaz Mahmud MD. Mujahid, Hridoy Datta Abstract - The rapid expansion of Information and Communication Technologies (ICT) has transformed financial inclusion from a policy objective centered on access into a data-driven process mediated by digital identity systems, algorithmic credit assessment, and fintech platforms. While ICT-enabled financial inclusion promises efficiency, scalability, and outreach to marginalized populations, it simultaneously raises profound concerns relating to personality rights, including identity, dignity, autonomy, privacy, and reputation. This paper advances a normative and conceptual analysis of Personality Rights–Based Financial Inclusion through ICT, arguing that contemporary financial systems increasingly construct a digital economic identity that determines an individual’s financial opportunities and exclusions. Such identities, often generated through opaque algorithms and data profiling, risk reducing individuals to abstract data points, thereby undermining human dignity and meaningful self-determination. The paper develops a conceptual framework that positions ICT as the mediating layer between individuals and financial inclusion outcomes, with personality rights functioning as essential normative safeguards. Central to this framework is the articulation of the Right to Economic Self-Representation, which recognizes the individual’s entitlement to access, understand, contest, and contextualize their digital financial profile. By reframing financial inclusion as a rights-dependent process rather than a purely technological or developmental intervention, the paper highlights the dangers of algorithmic exclusion, permanent economic stigmatization, and surveillance-based inclusion. The study contributes to interdisciplinary scholarship at the intersection of ICT law, financial regulation, and human rights by proposing a rights-compatible model of inclusive finance. It argues that embedding personality rights into the design and governance of financial technologies is crucial to ensuring that financial inclusion operates as a mechanism of empowerment rather than control. The paper concludes that sustainable and legitimate digital financial inclusion must balance technological innovation with the preservation of human dignity and agency.
Authors - Janina Odette S. Vidallon, Apolinar P. Datu, Dominic T. Urgelles, Aljen B. Cabrera, Erika Joy F. Lagos, Lady Anne R. Logdat, Shenclaire A. Galero, Ericka Jean M. Amparo Abstract - Brain-computer interface systems can help people who are unable to communicate due to paralysis or severe motor disabilities. In this work, we im plemented an EEG-based P300 speller that allows users to select characters by focusing on a visual stimulus.The system functions by means of the P300 signal that appears when the user identifies their target character. We developed a com plete pipeline that includes feature extraction, machine learning model classifi cation, and preprocessing of EEG data. The system was tested using the BNCI Horizon 2020 P300 dataset, and the results showed that character selection accu racy ranged from 82% to 86%.Random Forest performed better compared to other classifiers in our implementation. The system was designed in a modular way so that future improvements can be added easily. This implementation shows that EEG-based communication systems can be developed using accessible tools and can support basic communication for people with severe motor impairments.
Authors - Sejal Vaishnav, Sanskrati Jain, Suman Dikshit, Vashvi Srivastava, Shailendra Sharma, Vaishnav Preeti Prakash, Vishal Shrivastava, Ram Babu Buri, Mohit Mishra Abstract - Traditional object detection systems are limited in their ability to capture the complexity of urban scenes, often overlooking critical spatial, contextual, and functional relationships required. This paper introduces Urban Scene Intelligence, a Semantic Anchor-and-Expand (SAE) framework that integrates multi-modal perception, structured scene graph construction, and controlled narrative generation to produce grounded descriptions of urban environments. The proposed modular architecture incorporates OWL-ViT for open-vocabulary object detection, SegFormer for semantic segmentation, DepthAnything for spatial depth estimation, Qwen2-VL for attribute enrichment, and OCR for extracting textual context. Unlike end-to-end multimodal models, the threestage pipeline explicitly separates visual perception, symbolic reasoning, and language generation, thereby improving interpretability and factual grounding. By unifying heterogeneous visual cues into a symbolic representation and generating context-aware descriptions from this representation, the SAE framework establishes a transparent and extensible approach to urban scene understanding in complex real-world environments.
Authors - Sara OULED LAGHZAL, Abdelmajid El Ouadi Abstract - Musculoskeletal disorders (MSDs) are a significant occupational health problem in the automotive industry [1].Manual and semiautomated assembly work often exposes workers to repetitive movements and non-neutral wrist positions. Conventional ergonomic assessments are often ad hoc and subjective, limiting their ability to capture positional variations and cumulative strain over time. This article proposes a framework for continuous improvement using artificial intelligence that combines a convolutional neural network-based classification of wrist position (CNN) and a rapid upper limb assessment (RULA)[2] in real time. The convolutional neural network distinguishes between acceptable and unacceptable wrist postures during task execution, and the RULA layer translates the posture data into standardised biomechanical risk indicators. Empirical tests in an industrial context have shown that the CNNRULA hybrid system reliably detects even subtle deviations in wrist position that are difficult to detect by visual observation. This enables comfortable, data-driven proactive interventions in an Industry 4.0 environment.
Authors - Darshika Dudhat, Riya Jagani, Sarita Thummar Abstract - Plant diseases represent one of the major threats for the world's food security and agricultural productivity. In this paper, we present a novel deep CNN model which is improved by the Squeeze-and-Excitation (SE) modules and the Attention Gates (AGs), for multi-class plant disease classification based on five crops including apple, maize, grape, potato, tomato. With large number of image data set and a well-designed training strategy, the established model demonstrates good performance in all aspects including 99% accuracy, 0.99 F1-score and excellent specificity. Exploratory studies are performed through feature visualization and Grad-CAM interpretability. The intense robustness and interpretability of the model give it high potential for practical agricultural applications. The main research methodologies of this paper have: • The proposed Method of Attention-based Deep CNN Model combines (SE) blocks and Attention Gates (AGs), which further improve the channel-wise spatial feature leaning for plant disease classification. • Proposes the Grad-CAM visualizations to show disease-specific regions on leaves and achieves the state-of-the-art performance on five representative crop disease classification tasks. •Introducing attention mechanisms greatly improved the model's ability to focus on disease-related features, as evidenced by its strong generalization performances across a wide array of disease classes.
Authors - Ekanand Mungra, Roopesh Kevin Sungkur Abstract - Today's increasing energy demand, particularly in developing regions, supports both economic growth and the improvement of living conditions. However, these regions experience power outages frequently, due to the high energy consumption of commercial buildings. This research examines energy usage in smart commercial buildings by analyzing data from in-building sensors, collected at ten-minute intervals for more than four months. The aim is to forecast the consumption of energy of these buildings while utilizing AI generated scenarios to generate simulations resembling real-life energy usage situations, thereby improving our model’s predictions. In the era of smart buildings, accurate predicting energy usage does not only facilitate cost savings for businesses, but it also presents an opportunity for revenue generation, particularly through the surplus energy supplied back to the grid from renewable sources such as solar panels. Unlike conventional approaches, this research employs MLPRegressor, a sophisticated model, to analyze and predict intricate patterns of energy usage from the sensor data. This research is particularly significant for advancing energy management strategies in commercial sectors of developing countries, promoting energy independence and efficiency.
