Authors - Aneesah Sabar, KA Dilini T Kulawansa Abstract - Federated Learning has emerged as a robust privacy-preserving framework that enables joint model training across multiple distributed clients without sharing raw data. However, the effectiveness of traditional federated learning frameworks is hindered by client heterogeneity, where participants differ in data distribution, computational resources, and communication capabilities. This survey investigates evolution of personalization techniques in Federated Learning that address these challenges by tailoring models to individual clients while maintaining the benefits of global collaboration. The paper categorizes existing personalization approaches into five major groups: local fine-tuning, model interpolation, meta-learning methods, clustered federated learning, and regularization-based techniques. Each method’s core idea, strengths, limitations, and suitability under different heterogeneity conditions are analyzed in detail. The findings indicate that personalization significantly improves fairness, accuracy, and adaptability across heterogeneous clients, though it introduces trade-offs in communication cost, scalability, and privacy. This review concludes that personalization is essential for deploying federated learning in realistic, diverse environments and highlights emerging directions in fairness-aware, resource-efficient, and privacy-preserving personalization. Future research should focus on scalable and dynamic personalization strategies capable of handling evolving client behaviors and large-scale federated systems.
Authors - Bhavanam Sruthi, Mettu Sai Preethi, Krishna Reddy Abstract - Driver drowsiness is a major reason for accidents on the road, hence it is important to detect it early to increase safety on the road. A driver drowsiness detection system based on deep learning algorithms is proposed and it uses images captured through a camera installed inside a car. Various deep learning algorithms, namely CNN, VGG16, DenseNet121, MobileNet, LeNet, AlexNet, RNN, patchTST,Vision Transformer and Swin Transformer are implemented and compared to assess their performance.The system detects the conditions of the driver, whether eyes are open, closed, yawning, or not yawning. Among all these algorithms, the highest accuracy of 97.61% was obtained by using the MobileNet model, which proves that deep learning can play a vital role in detecting drowsiness. In addition, an alert can also be sent to warn the driver.
Authors - Prachita Chaudhari, Shubham Kishor Kadam, Shiwani wagh, Pankajkumar Anawade, Deepak Sharma, Chhitij Raj Abstract - One of such industries is healthcare, where data-driven methods attract much attention, and one among them is the field of predictive analytics that is already making a great difference in the healthcare industry concerning its capacity to enhance early diagnosis and treatment. Through this, whole care is provided, and this implies that the problem of fragmented care addresses systemic issues such as inefficiencies and inflation of costs. Predictive analytics is the most effective in the prediction of risks of disease, i.e. making care a thing related to the individual patient. Besides, it can be utilized to monitor populations and enhance the management of population health utilizing its combination of machine learning, natural language processing and deep learning. Solutions that offer the following benefits, including reduced misdiagnosis, re-source utilization, and affordable access to health care, are also being created with the help of the main enabling technologies including AI, IoT, and big data. Nevertheless, issues like the quality of the data, technical issues, ethical concerns and compliance with laws persist. Future work still to be done areas can be seen in the application of new technologies like quantum computing to answer questions about the public health, real time data that uses IoT, and the application of other mediating technologies in underserved locations that can instill equity and sustainability. Being fueled by the collaboration of various professionals, e.g., clinicians, data scientists, and policy-makers, predictive analytics is bound to enhance patient outcomes and catalyze the better provision of preventive, personalized, and responsibility healthcare solutions.
Authors - Binh Pham Nguyen Thanh, Chau M. Truong, Nhan Thi Cao Abstract - ResNet is widely used in medical image classification due to its strong hierarchical feature extraction capability. This study investigates the integration of Kolmogorov–Arnold Networks (KAN) and ConvKAN into ResNet to analyze the effect of increasing nonlinearity at different stages within a hierarchical skin lesion classification framework. Convolutional KAN is applied at the initial layer to enhance low-level feature extraction, while KAN is introduced at the final layer to improve high-level decision boundary modeling. A combined configuration is also evaluated to examine potential complementary effects across different levels of label granularity. Results show that performance depends on both the integration stage and dataset characteristics. Convolutional KAN at early layers provides limited and inconsistent improvements, whereas KAN at the final layer yields more stable gains. In addition, models incorporating KAN-based architectures generally achieve better performance across metrics such as accuracy, precision, F1-score, and ROC AUC. As classification becomes more fine-grained, Recall consistently decreases despite high ROC AUC, indicating challenges in decision thresholding across hierarchical levels. Overall, KAN is more effective for high-level decision making, while dataset complexity has a greater impact than architectural modifications.
Authors - Mouna Meghana Nagala, Anjan Babu G Abstract - Social Anxiety Disorder (SAD) remains one of the most pervasive mental health challenges globally, characterized by a debilitating “perception gap” where individuals consistently overestimate the visibility of their internal distress while underestimating their social performance. This paper introduces an Explainable AI (XAI) multi-modal sensing system designed for automated social anxiety monitoring and self-perception recalibration. The architecture is founded on an event-driven framework integrating real-time threedimensional facial feature encoding (DeepFace), acoustic prosody extraction (Librosa), and Natural Language Processing (NLP) for cognitive distortion detection. The system implements a Cognitive Behavioral Therapy (CBT) logic layer that provides interpretable feedback on linguistic patterns. System performance was benchmarked against the FER-2013 and RAVDESS repositories, yielding an anxiety detection sensitivity of 92.4% and a specificity of 94.7%. The findings affirm that coupling volumetric affective computing with generative AI constitutes a viable pathway toward trustworthy computer-aided detection (CAD) in behavioral health screening programs.
Authors - Theresa T. Limos, Sheena Sapuay-Guillen Abstract - This study developed PU-Serv: A Tool in Analyzing Student Services Using Machine Learning, a web-based system designed to enhance the evaluation of student services through automated sentiment analysis. The study assessed the existing student services evaluation form in terms of adequacy, efficiency, and reliability and aimed to develop a machine learning–based model to support the analysis of student feedback.A descriptive and developmental research design guided by Agile methodology and the CRISP-DM framework was employed. Data were gathered from focus group discussions, questionnaires, and institutional student feedback records. Natural language processing techniques were used to preprocess narrative feedback, and the Support Vector Machine (SVM) algorithm was integrated into the system due to its high accuracy in sentiment classification. The developed PU-Serv system automatically analyzes student feedback and presents summarized results through a web-based dashboard. The system provides administrators with actionable insights that support data-driven decision-making, helping institutions identify service issues, improve responsiveness, and enhance the overall quality of student services.
Authors - Neel Lathiya, Akshita Kadam, Amit Thakkar Abstract - Industrial tracking tools have led to the development of Quick Response codes, which are an essential component of digital engagement and provide simple access to payments, authentication, and online services with a single scan. However, they are very vulnerable to exploitation, particularly zero-click attacks, which start destructive operations without the user’s consent, due to their architecture, which is based on visual legitimacy, automatic intent execution, and plaintext encoding. This survey looks at the technical aspects of making and reading QR codes, charts the evolution of threats based on QR codes, ranging from physical manipulation to silent deep link hijacking, and explains how these attacks go beyond the robust security models of iOS and Android by utilizing trusted system paths. Based on five significant studies, we analyze real-world attack scenarios, user behavior gaps, and the efficacy of novel defenses like scanner assessment frameworks, zero-trust architecture approaches, and AI-driven payload inspection (AP3X, QRShield). Certain recommendations are made regarding system hardening, cryptographic integration, and user awareness in order to transform QR codes from a latent risk into a safe and verifiable medium.
Authors - Maria Cecilia L. Pangan , Jolou Vincent M. Jala, Ralph Vendel E. Musni, Everly A. Nacalaban, Nenon Roy A. Sandinao, Randy Joy M. Ventayen Abstract - As digital revolution, globalization, and cross-border collaboration re-shape academic landscapes, internationalization of higher education has emerged as a strategic focus for institutions globally. With this, technology-driven innovations particularly learning management systems (LMS), digital platforms, virtual mobility tools and artificial intelligence (AI) have augmented international engagement beyond physical boundaries. Artificial intelligence has immense potential to be a universal technology that boosts product innovation and productivity across a range of industries. This study explores how technological innovations improve internationalization in higher education. Most specifically by how technological innovations improve internationalization in higher education through Technology-Enabled Teaching and Learning, Virtual Mobility and Global Collaboration, Research and Knowledge Exchange, Institutional Governance and Global Competitiveness. Notably, the rapid growth of digital and global academic engagement also causes meaningful implications for students’ and faculty members’ mental health and well-being. This is because when internationalization becomes progressively technology-mediated, matters such as academic pressure, digital fatigue, time-zone differences in global collaboration, and constant online connectivity may contribute to anxiety, stress, and burnout. To attain this goal, the proponents critically examined 156 papers in the body of literature that were indexed by Scopus to examine the advancement of Internationalization in Higher Education through Technology-Driven Innovations Using a systematic review of recent literature, this paper synthesizes global and international perspectives. The findings emphasize that Technology-driven revolutions have redefined the practices and scope of internationalization in higher education. Conversely, obstacles and challenges such as deficient infrastructure, Digital divides, and unfair access to technology deter inclusive involvement and participation
Authors - Gaurav Gupta, Kumar Shashvat, Gunjan Abstract - In India, dengue fever poses a significant threat to public health which continues to worsen. Forecasting methods are crucial to developing effective disease surveillance systems. This study provides an empirical comparison between classical time series forecasting methods, and various machine learning techniques, applied to dengue forecasting for the period of 2013 - 2019 in Chandigarh, India. Seven methods are explored - ARIMA, SARIMA, Exponential Smoothing (ETS), AutoReg, Linear Regression with lagged variables, Decision Tree Regression, and Random Forest Regression. The models are evaluated on multiple criteria which include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Scaled Error (MASE), and for the statistical models, the Akaike Information Criterion and the Bayesian Information Criterion (AIC/BIC) are used. Random Forest Regression produced the lowest predicted error (MAE 26.95, MASE 0.19), while SARIMA, with seasonal modeling, demonstrated the best and most useful epidemiological interpretability (MAE 45.36, MASE 0.39) of the models. The outcome of the study shows the balance between predictive power of a public health forecasting model, and the interpretability of the model. In this case, SARIMA had the best balance of both and thus, is recommended as the best model for dengue surveillance systems.
Authors - Made Ratih Nurmalasari, Putu Diah Kumalasari, Mirah Candra Adi Saputri Abstract - Through an emphasis on the function of Audit Committee in trying to enhance the correlation of Green Banking Disclosure and also Sustainable Firm Value, this study tried to do investigating how banking firms in Indonesia might have benefits from this practice. As sustainability gets increasingly significant for businesses and also stakeholders alike, banks are under pressure to show transparent of the environmental initiatives. By applying data from Indonesian banks registered in the year of 2021, 2022, and also 2023, this study tended to examine whether banks that actively disclose their efforts of green banking are better allocated to help enhancing their value. The Committee is defined as a moderating variable, shown the significant role to help ensuring good governance and also the disclosures credibility. Data analysis was done by using SPSS with models of multiple regression, as like terms of interaction to help assessing the moderation influences. The outcomes stated that Sustainable Firm Value is greatly improved by Green Banking Disclosure. It is also getting amplified at the time an effective Audit Committee is in place, hoping that good governance is able to increase the influence and also value of sustainability. This research also emphasizes the merging necessity of transparent sustainability measures with strong frameworks of governance to help providing enduring value. The out-comes have actionable information for banking regulators, executives, and also legislators to help integrating sustainability with expansion of corporate.
Authors - Made Ermawan Yoga Antara Abstract - This study is to examine how sustainable MSMEs are impacted by digital innovation and entrepreneurial mindset, mediated by entrepreneurial resilience. This study was carried out in the province of Bali using a quantitative methodology, focusing on MSMEs in the creative economy craft sub-sector. The study sample consisted of 361 MSME owners and leaders selected using proportional random sampling from a total population of 3,745 business units. Data were collected using a Likert-scale questionnaire and analyzed using SEM-PLS with the assistance of SmartPLS software. The results showed that digital innovation and entrepreneurial mindset have a positive and significant effect on both entrepreneurial resilience and sustainability in MSMEs. Additionally, sustainable MSMEs benefit greatly from entrepreneurial resilience. The association between digital innovation and entrepreneurial mindset on sustainable MSMEs is partially mediated by entrepreneurial resilience, according to the mediation test results. Digital innovation has the largest influence on entrepreneurial resilience, while entrepreneurial mindset has the largest direct influence on sustainable MSMEs. These findings emphasize the importance of integrating digital technology adoption and internal entrepreneurial capabilities in driving business sustainability. This research supports dynamic capabilities theory, which emphasizes sensing, seizing, and transforming capabilities in enhancing the resilience and sustainability of MSMEs. Practically, MSMEs need to strengthen digital innovation, entrepreneurial mindsets, and business resilience to adapt to environmental dynamics. This research contributes to the development of sustainable entrepreneurship literature, particularly in the creative economy in developing countries.
Authors - Criscel Jay F. Nayve, Lord Francis B. Navarro,Karen Aparicio Doblas, Elvan Budiongan, Darrel A. Cardana, Max Angelo D. Perin Abstract - This study evaluates online tourist feedback on the Chocolate Hills in Carmen, Bohol, Philippines, using Natural Language Processing (NLP) techniques. Although the destination consistently receives high ratings, negative reviews contain critical insights that can guide tourism management. A total of 4,059 Google Maps reviews were collected, of which 2,011 contained textual content suitable for analysis. The dataset underwent preprocessing using Python and Orange Data Mining before applying sentiment analysis and Latent Dirichlet Allocation (LDA) topic modeling. Results show that, while overall sentiment toward the Chocolate Hills remains strongly positive, negative reviews highlight key concerns related to accessibility, and crowding. Topic modeling identified five dominant themes: scenic appreciation, environmental ambience, crowd density and photo-taking behavior, physical effort required for climbing viewpoints, and perceived cost–benefit value. Sentiment trends from 2020 to 2025 indicate stable positive perceptions despite pandemic-related fluctuations in review volume. Findings suggest that tourists’ satisfaction is primarily driven by the site’s natural beauty, but logistical challenges require targeted management interventions. The study contributes to localized tourism analytics in the Philippines and demonstrates the usefulness of NLP for extracting actionable insights from large volumes of user-generated content.
Authors - Sarvesha Nakharekar, Seedhi Kundap, Suman Madan Abstract - When cyberattacks become ever more extensive and complicated, the demand for intelligent systems capable of executing cyber threat intelligence, digital forensics, and risk management efficiently has increased. We have focused on the important point where digital forensics and cyber threat intelligence meet through this article. In order to build and evaluate the classification models, a publicly accessible intrusion detection dataset was used. The models are Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, and Multilayer Perceptron .The models were evaluated from the perspective of their probable employment in cyber threat intelligence and forensics, based on their performance indicators such as accuracy, precision, recall, F1- score, and computing efficiency .Through a critical discussion, the article also contains a number of significant problems that have been touched upon: the explainability of the attacks, the existence of adversarial attacks, the data imbalance problem, and the limitations of real time processing. The investigation, however, brings up the possibility of using machine learning based on detection outcomes to improve cyber risk management by threat prioritization and thereby making informed decisions. The document is an essential resource for both researchers and field specialists interested in exploring the use of ML to significantly improve threat forecasting, speed incident handling, and strengthen risk management even in a more and more unfriendly domain of cyberattacks.
Authors - Md Tanzid, Md. Foridul Haque, Md. Ismail Hossain, Mohammad Golam Sarowar Abstract - The rice supply chain has been susceptible to quality deterioration, expiry, and a low level of transparency, which are risks to consumer health and food security. To overcome these challenges, the current research suggests a consortium-based blockchain and IoT-enabled smart contract framework to provide a holistic, traceable, and automated governance model. The framework facilitates a consortium of all key stakeholders in the rice supply chain from farmers to retailers as a blockchain network that is co-controlled and resistant to tampering. At key storage infrastructures, Internet of Things (IoT) sensors are deployed to provide the variable storage conditions (humidity and temperature) in real-time that are important in storing rice. The monitoring variables are sent to smart contracts that generate a two-tiered governance system. Upon data showing that a rice lot reached 90% of its shelf life, the intervening automated process will promulgate notifications. Upon expiration of the rice, monitoring will render a smart contract disables the ability to purchase or distribute in the supply chain. The automated process therefore notifies users of public health risks by preventing the introduction and sale of products deemed unsafe for consumption. The framework ensures the sustainable, validated, and tamper evident functionality for continuous monitoring and rule-based execution of perishable products on a public ledger to facilitate enhanced food governance, to lower food safety risks to consumer health, and to promote consumer trust in the rice supply chain.
Authors - Aksh Modi, Agrim Gairola, Suryansh Shah, Sahil Singh, Malvinder Singh Bali Abstract - The increasing degradation of global coral reef ecosystem heavily needs scalable, automated monitoring solution that are capable of operating in resource constrained underwater ecosystem. Though the ongoing State of the Art approaches, such as Vision Transformer and Efficient Net, achieve high classification accuracy, they heavily suffer from computational latency and power requirement that makes them unsuitable for Autonomous Underwater Vehicles (AUVs) or diver held devices. This paper presents a lightweight, real time detection model using the YOLOv8s-cls architecture, which is optimized for edge deployment. Our model achieves a Top 1 Accuracy of 89.84%, conquering the official NOAA Vision Transformer baseline (85.0%) and recent YOLOv8 benchmark at 88.0% accuracy when tested on NOAA-PIFSC-ESD dataset. Crucially, this performance is achieved with a fraction of the computational overhead, enabling high-frequency inference without reliance on cloud connectivity. These results demonstrate that lightweight Convolutional Neural Networks (CNNs) can outperform complex Transformerbased models in texture-centric underwater tasks, providing a viable pathway for immediate, in-situ bleaching assessment by low-power marine robotics.
Authors - Reepu Abstract - Wearable devices are gaining more importance in the present day as they offer various advantages to the users and thereby enabling in generating better outcomes. Wearable devices gained higher focus mainly in the healthcare sector as they support in tracing the critical signs of the patients on a real time basis, provide better support to them as and when needed. The application of wearable devices enables in addressing different health care concerns in an effective manner, the current context witnessed many advancements in the wearable device’s domain. With the integration with other techniques like AI, Internet of Things and other sophisticated tools it can undergo major shift in the health care domain in protecting the lives of the individuals, move from being reactive mode of providing treatment to the patients to more predictive method, enhance clinical skill and outcomes. The overall value of implementing these tools and technologies support in enhancing the life of the patients and supports the practitioners in making better progress in clinical advancements and other areas.
Authors - Shreya Shukla, Mishti Kukreja, Ruchika Katariya Abstract - Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder with a prevalence rate ranging between 5 to 7.2% among children and between 2.5 to 6.7% among adults worldwide. In spite of its high prevalence rate, its diagnosis still relies mostly on clinical ratings that have the tendency to show inter-rater differences and confusions with symptoms of other conditions associated with ADHD. Neuroimaging methods, particularly rs-fMRI and sMRI, offer an innovative approach towards providing objective measures for understanding the neurobiological underpinnings of ADHD. This paper offers a systematic narrative review of deep learning methods for ADHD classification using fMRI/sMRI data from 2012 to 2025, with a specific focus on the recent period from 2021 to 2025 characterized by architectural diversity. We classify the literature into three main streams according to the neural networks adopted: (1) Convolutional Neural Networks (CNNs), which involve 2D CNNs, 3D CNNs, residual CNNs, dense CNNs, attention-based CNNs, and graph-based CNNs; (2) Vision Transformers (ViTs), which encompass conventional ViTs, Swin transformers, self-supervised ViTs, multi-modal ViTs, and brain foundation model ViTs; and (3) hybrid CNN-ViT models, which combine both local and global context representations. This work highlights the problems of heterogeneity among multiple sites, inconsistent evaluations, fairness, efficient inference, and clinical deployment. Note: This review does not follow the guidelines for systematic reviews (PRISMA 2020). It is an organized narrative review. Numerical comparisons between different works should be considered approximate due to variations in training/testing sets and data preprocessing.
Authors - Madhumati Pol, Rutuja Chaudhari, Sai Jadhav, Sri Sai Preethi Munnaluri, Rudrani Sarangdhar Abstract - The necessity of developing adaptive, autonomous, and intelligent security systems has developed significantly over time because of the increased volume and complexity of cyber attacks. Therefore, this research project will present an AI-powered multi agent self-evolution cybersecurity intelligence system. The purpose of the system will be for the real-time identification, classification, and prediction of cyber threats. The system will consist of three working agents: Network Monitoring Agent, System-Metrics Surveillance Agent and Threat Intelligence Agent. These agents will be supported by interpretable machine learning classifiers and light-weight Python-based data collection tools. A universal dataset converter will enable it to operate on all types of cybersecurity datasets, and a self-evolving element will allow it to continually update itself with additional information regarding current threats. Dashboards will be provided through the use of Streamlit in order to provide real-time timelines of attacks, CVE intelligence, anomaly detection, and real-time visualization of threats. Results from experimental testing show that the system can improve the accuracy of its threat detection as time progresses and perform well across various datasets. Overall, this work provides a self-learning, scalable, modular, and dataset-agnostic architecture for use within modern enterprise-level cybersecurity environments.
Authors - Elmar B. Noche, Randy Joy M. Ventayen Abstract - Breast cancer remains one of the leading causes of mortality among women, highlighting the need for reliable survival prediction tools. This study applied big data analytics and Cox Proportional Hazards regression to the METABRIC dataset, which contains clinical, pathological, and genomic records from over 2,000 breast cancer patients. Hadoop HDFS was used for distributed storage, while PySpark supported preprocessing and data transformation. After feature selection, six significant predictors were identified: inferred menopausal state, Nottingham Prognostic Index, oncotree code, type of breast surgery, cohort classification, and tumor size. The findings show that combining Hadoop-based infrastructure with interpretable survival modeling can support patient risk stratification, treatment planning, and precision oncology.
Authors - Phat Ly Tan, My Nguyen Kieu, Phung Nguyen Thi Kim Abstract - This paper presents an automated approach for cardiac arrhythmia detection using ECG signals from the CPSC2018 database. The proposed pipeline includes band-pass filtering, normalization, and segmentation of raw ECG recordings, conversion of ECG segments into 2D grayscale images, and multi-label arrhythmia classification using CNN based on a DenseNet architecture. According to the official CPSC2018 labeling scheme, ECG segments are categorized into multiple clinically relevant rhythm types, including normal sinus rhythm and major arrhythmias such as first-degree atrioventricular block, atrial fibrillation, right bundle branch block, left bundle branch block, ventricular ectopic beat, premature atrial contraction, ST-segment elevation, and ST-segment depression. The DenseNet-based architecture combines an oversampling training strategy to alleviate class imbalance. Experimental results on the CPSC2018 database demonstrate the effectiveness of the proposed image-based ECG classification approach, highlighting its potential to assist clinicians in ECG interpretation and early diagnosis of cardiac disorders.
Authors - Renato E. Salcedo, Elmar B. Noche Abstract - The rapid proliferation of Artificial Intelligence (AI) in education has prompted growing scholarly and policy interest in how higher education institutions across the Asia-Pacific region are systematically incorporating AI into teaching, learning, research, and governance. This paper presents a systematic review of 68 peer-reviewed studies, institutional policy documents, and government reports published between 2018 and 2024, examining the extent to which AI is being institutionalized within Asia-Pacific higher education systems in alignment with Education for Sustainable Development (ESD) principles. Using the PRISMA framework and a content analysis methodology, this review identifies four dominant institutionalization pathways: curriculum integration, research infrastructure development, policy formalization, and faculty capacity-building. Findings indicate significant heterogeneity across countries, with East Asian economies particularly China, Japan, and South Korea exhibiting more advanced levels of AI policy coherence, while Southeast Asian and Pacific Island nations remain in nascent stages of formal AI institutionalization. Critical barriers include data governance deficits, algorithmic inequity risks, underfunded professional development pipelines, and insufficient alignment between national AI strategies and ESD frameworks. The review concludes with a set of evidence-based recommendations for regional policymakers, university administrators, and international development organizations to accelerate equitable, sustainable AI institutionalization across the Asia-Pacific higher education landscape.
Authors - Abstract - This research investigated the potential for improving the reliability of the Central Pangasinan Electric Cooperative (CENPELCO) San Carlos 20MVA Substation distribution system through optimized placement of Automatic Circuit Reclosers (ACRs). The study employed a Steady-State Genetic Algorithm (SSGA) implemented in MATLAB to identify optimal ACR locations that minimized SAIDI, SAIFI, and maximized EENS. The algorithm was validated using the IEEE 34-node test feeder, demonstrating its effectiveness in balancing competing objectives. The validated SSGA was then applied to the CENPELCO system, resulting in significant improvements in SAIDI values across all feeders. The research introduced a novel approach to using EENS to represent the number of connected customers at each node, refining the SAIDI calculation and providing a more accurate measure of the impact of outages on consumers. The optimized ACR placement strategy consistently brought SAIDI values below the NEA standard for on-grid electric cooperatives, indicating a substantial enhancement in the reliability of the CENPELCO distribution system. The study provides valuable insights for CENPELCO and other power system operators seeking to improve system reliability and minimize the impact of power outages.
Authors - Phway Phway Aung, Tin Zar Thaw Abstract - Multi-object tracking (MOT) is widely applied in surveillance, traffic monitoring, and autonomous systems. Most MOT systems are created by combining DeepSORT and YOLO series. The original DeepSORT relies on IoU as-sociation-based matching and a fixed age threshold deletion algorithm which of-ten leads to incorrect associations, premature track removal, and frequent ID switches under occlusion or fast motion. To address these limitations, YOLOv9-Based Multi-Object Tracking System is proposed by using GIoU for more reliable geometric association and the enhanced filtering algorithm that are integrated class validation, motion uncertainty estimation with consign similarity, and a Re-Identification (ReID) memory buffer for reducing ID switching. To analyze the performance of the proposed MOT system we compare two cases: IoU and GIoU on Original DeepSORT and the improved DeepSORT and original DeepSORT based on MOT16 videos’ sequences. Experimental evaluation demonstrates that the proposed YOLOv9-Based Multi-Object Tracking System achieves more sta-ble and accurate tracking performance compared to the original DeepSORT system in two cases.
Authors - Mainford Mutandavari, D. Hemavathi Abstract - Maize (Zea mays L.) is an essential staple produce for smallholder farmers in developing nations, yet Northern Corn Leaf Blight (NLB), Grey Leaf Spot (GLS), and Common Rust foliar diseases cause yield losses of 30–70%. Infection detection is done at advanced stages due to labor intensity resulting from the conventional disease monitoring methods. A Low-Cost Drone-Mounted Multispectral Imaging (LCDMI) framework for resource-constrained smallholder systems is presented in this paper, pairing a consumer-grade UAV with a five-band multispectral sensor. The vegetation-index features are fused with multispectral band data using a Spectral-Spatial Attention Vision Transformer (SSAViT) classifier and a Spectral-Constrained Synthetic Data Generation (SC-SDG) module addresses training-data scarcity. A hardware cost of USD1,940 is projected for field evaluations across twelve plots in Zimbabwe over two growing seasons yielding 95.8% detection accuracy, identifying diseases 7–12 days before visible symptom onset. A multi-label extension enables simultaneous classification of co-occurring infections. Georeferenced disease maps are delivered within 6.3 min/ha. With perhectare costs as low as USD2.10 on a scale, the economic analysis projects ROI within two seasons for cooperatives managing 50+ hectares.
Authors - IGN Oka Ariwangsa, Komang Widhya Sedana Putra P, Wayan Sri Maitri Abstract - The rapid adoption of artificial intelligence (AI) in higher education has transformed how students access information and engage in academic activities. While AI-powered technologies enhance efficiency and provide personalised support, their uncritical use may weaken independent reasoning and reduce meaningful social-academic participation. This raises concerns in digitally mediated environments where individuals must interpret complex information, evaluate uncertainty, and make informed judgments. Despite growing attention, most studies emphasise functional outcomes such as academic performance, overlooking the mechanisms through which AI-integrated teaching can foster deeper, more sustainable learning. This study examines how AI-aware pedagogy—defined as the intentional and reflective integration of AI in instructional design—enhances critical thinking through social-academic engagement. A quantitative approach was employed, involving 200 undergraduate students in Indonesia. Data were collected via structured questionnaires and analysed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings reveal that AI-aware pedagogy has no significant direct effect on critical thinking. However, it significantly influences critical thinking indirectly through social-academic engagement. This indicates that higher-order thinking develops not merely through technological integration, but through socially embedded learning processes that encourage interaction, reflection, and evaluation. Theoretically, this study links digital pedagogy with cognitive and social learning processes. Practically, it highlights the need for AIsupported environments that foster critical evaluation and responsible decisionmaking under conditions of uncertainty. Future research should explore its applicability across contexts and its long-term cognitive implications.
Authors - Mary Diana C. Yamzon, Janelli M. Mendez Abstract - This study provides a data-driven analysis of the academic performance of Bachelor of Science in Office Administration (BSOAD) students at Tagbilaran City College from Academic Year 2021 to 2024, employing data mining clustering techniques to ascertain the five most challenging subjects. The study specifically aimed to: (1) construct and preprocess a dataset of pertinent academic attributes; (2) employ K-Means, K-Medoids, and Agglomerative Hierarchical Clustering algorithms to discern groupings of subject difficulty; (3) validate clustering results utilizing the Davies-Bouldin Index (DBI); and (4) develop evidence-based recommendations for curriculum enhancement and academic assistance. The analysis involved a dataset of 26,965 valid student grade records across 68 subjects, all of which were processed using RapidMiner Studio. The research utilized the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework within the context of Educational Data Mining (EDM). The DBI for K-Means (DBI = 0.461; Excellent) and K-Medoids (DBI = 0.9145) were used to check the clusters, and the visual dendrogram was used to check the Agglomerative Hierarchical Clustering. All three algorithms consistently recognized OA113 Advanced Shorthand and OA111 Foundations of Shorthand as the two most challenging subjects in the program. The results offer statistically substantiated, evidence-based insights to facilitate curriculum evaluation, instructional enhancement, and the formulation of specialized academic intervention programs for BSOAD students.
Authors - Hussein P. El Sayed Ahmed, Ardee Joy T. Ocampo Abstract - Youth participation in local governance remains a persistent challenge despite institutional mechanisms designed to promote engagement. In the Philippines, the Sangguniang Kabataan (SK) serves as a formal platform for youth involvement in local decisionmaking; however, many SK programs continue to experience low participation, limited feedback integration, and repetitive activity design. This study presents EmpowerSK, a data-driven framework that leverages data mining techniques to enhance youth engagement in SK programs. Using structured survey data from 1,055 youth respondents aged 18–25 across the nine barangays of Alilem, Ilocos Sur, the study applies the Knowledge Discovery in Databases (KDD) framework, K-Means clustering, and sentiment analysis to transform raw feedback into governance intelligence. K-Means clustering (k=3) identified three statistically validated engagement profiles: Highly Active (61.6%), Moderately Involved (17.0%), and Disengaged (21.3%). Sentiment analysis of open-ended responses revealed appreciation (77.8% positive), diagnosis (73.2% negative), and aspiration (85.5% neutral-aspirational) as a coherent three-phase youth governance narrative. An overall weighted mean of 3.75 ("Very Good") across eleven Likert-scale items confirmed a critical institutional gap: Digital Engagement (4.14) significantly outpaced SK Support Initiatives (3.52), with SK Training recording the lowest item score (3.44). A five-pillar data-driven action plan—Awareness and Inclusion, Program Diversification, Digital Transformation, Capacity Building, and Monitoring and Evaluation—was developed, validated by SK officials, and aligned with SDG 4, 11, and 16. The findings demonstrate that freely available data mining tools can transform rural youth governance into an annually replicable, evidence-based participatory system.
Authors - Reynaldo F. Agunod, Janelli M. Mendez Abstract - Higher education institutions collect large volumes of student data but these are underutilized for institutional planning. This study applies the CRISP-DM framework to enrolment records of a freshman cohort of 1,916 students across four academic years (2021-2025) across 28 academic programs from a private higher education institution in Central Visayas, Philippines, to forecast institutional progression metrics using predictive analytics. Descriptive analytics and three predictive models were applied based on their suitability for the dataset with 3-4 data points, namely: Linear Regression, Holt-Winters Exponential Smoothing, and ARIMA. Six institutional performance metrics were analyzed: enrolment, retention, persistence, attrition, program shifts, and graduation. Key findings reveal a continuous 29.6% enrolment decline within the cohort, an im-proving retention and persistence profile, a program-shift surge largely due to migrations from Accountancy to Finance, and a rapidly increasing graduation rate. Linear Regression (OLS) was identified as the most effective forecasting model for the study’s single-cohort dataset.
Authors - Edimar J. Rato, Janelli M. Mendez Abstract - Student dropout has remained a major problem in all higher education institutions globally, including in the Philippines, where the total college dropout rate in the country was recorded at about 35.15% in the Academic Year 2023–2024. This study aimed to develop a predictive analytics model that identifies dropout and retention patterns among students of Tagbilaran City College to support evidence-based intervention strategies. offered by the school from Academic Year 2021-2024. The algorithms implemented for the supervised learning process include Random Forest and Gradient Boosting, while the algorithm for the unsupervised learning process is K-Means Clustering implemented using the RapidMiner Studio tool. Results revealed that both supervised models had a poor performance due to class imbalance issues as well as a small feature set; the Random Forest model had an accuracy of 59.59%, while it had an AUC of 0.575. The Gradient Boosting model had an accuracy of 60.51%, while it had an AUC of 0.508. The K-Means Clustering model had a good performance since it resulted in three interpretable student risk clusters: a moderate-risk group with a dropout rate of 27.3%, a highest-risk group with a dropout rate of 44.7%, and a lower-risk but larger group with a dropout rate of 41.9%. The Davies-Bouldin Index of 0.967 confirmed adequate cluster separation. The K-Means model demonstrated the most practical utility as an early-warning risk stratification tool applicable at the start of each academic year, forming the foundation of an evidence-based intervention plan to improve student retention at Tagbilaran City College.
Authors - Ni Made Prasiwi Bestari, Jonathan Jacob Paul Latupeirissa, Suryanto Nugroho, Iwan Adinugroho, Melati Budi Srikandi, Ayu Made Bianca Juarez Abstract - The Fourth Industrial Revolution has been transforming the global tourism industry, shifting toward a dynamic Tourism 4.0 ecosystem. Given that the adoption of AI is expected to increase the revenue of the tourism industry, it is necessary to conduct a Systematic Literature Review to fill the gap in empirical research on the relationship between technological innovation and long-term sustainability. Most studies on smart tourism from different perspectives, including tourist behavior, tourist service quality, innovation, and sustainability, focus on the "hardware construction" at the macro level and its implementation based on related policies, ignoring the psychological mechanisms affecting tourists' experiences at the micro level. This study aims to identify the key technological drivers, including AI, IoT, and computer vision, and their influence on operational innovation and Sustainable Development Goals. A total of 23 core manuscripts from 2020 to 2025 gathered from Scopus database were synthesized and analyzed based on PRISMA guidelines. The results showed that smart tourism technologies can greatly improve efficiency and enhance hyper-personalization. However, most current applications of smart tourism technologies do not take adequate account of social and environmental metrics. Also, many digital tourism strategies prioritize revenue over social inclusion. For the future of smart tourism destinations, frameworks such as Society 5.0 that integrate high-tech with the human touch of hospitality and tourism are needed. Destinations should also seek governance models that ensure long-term resilience by moving the focus away from infrastructure and toward "Smart People" initiatives and the development of standardized real-time sustainability metrics.
Professor, National Institute of Technology Raipur, India.
Narendra D. Londhe is presently working as Associate Professor in the Department of Electrical Engineering of National Institute of Technology Raipur, Chhattisgarh INDIA. He completed his B.E. from Amravati University in 2000 followed by M.Tech and Ph.D. from Indian Institute of Technology... Read More →
Authors - Max Angelo D. Perin, Lenie B. Maligmat, Darrel A. Cardana, Renante S. Digamon, Joan Mae G. Lagumbay, Cecilia T. Gumanoy Abstract - The Quality Assurance Office of a Philippine state university campus conducts 7S evaluations across all offices each semester, producing numeric scores and written evaluator comments. Consolidating the narrative comments has depended on manual review, which is time-consuming across more than a hundred offices per cycle. This paper describes a two-phase AI-assisted analytics pipeline. Phase 1 retrieves audit records from a MySQL database via a stored procedure, formats them with a Python ETL script, and submits them to Grok (xAI) to draft scorecards and action items; evaluators then review the drafts be-fore consolidation into the official PDF report. Phase 2 parses the validated PDF with Python to extract structured fields and compute descriptive statistics, office rankings, a priority index, and TF-IDF text clustering. Applied to the November 2025–January 2026 cycle (112 offices; 107 scored, 5 with no submission), most units cluster in the moderate-to-great compliance range while a meaningful minority fall below threshold. Among the top 25 priority offices, Standardize (20/25) and Safety (19/25) are the most frequently flagged dimensions. The pipe-line shows that AI assistance structured around human review can accelerate QA consolidation while preserving evaluator accountability.
Authors - Nur Fajrina, Felina C. Young, Rosita Widya Putri Abstract - This study investigates the relationships among Stakeholder Integration (STI), Digital Transformation Capability (DTC), Absorptive Capacity (AEC), and Sustainable Supply Performance (SSP) within a knowledge-intensive supply chain context. Employing a quantitative methodology alongside Partial Least Squares Structural Equation Modeling (PLS-SEM), data were collected from 262 respondents involved in strategic and operational functions. The results reveal that stakeholder integration significantly enhances digital transformation capability, thereby strengthening absorptive capacity. Both digital transformation capability and absorptive capacity have direct positive effects on sustainable sup-ply performance. However, stakeholder integration does not directly influence sustainable supply performance. Instead, its effect becomes significant only when mediated by absorptive capacity, indicating that internal knowledge assimilation and utilization mechanisms are essential for translating collaborative efforts into sustainability outcomes. The results highlight the critical role of dynamic capabilities in accomplishing sustainable supply performance, particularly in environments characterized by digital transformation and stakeholder complexity. The study contributes theoretically by integrating stakeholder theory and dynamic capability perspectives, emphasizing absorptive capacity as a key mediating mechanism. The results suggest that firms should complement external stakeholder collaboration with investments in digital infrastructure and organizational learning systems to enhance long-term sustainability performance.
Authors - Ayush Ghumare, Reena S. Satpute Abstract - Mobile application development has evolved rapidly with the emergence of advanced technologies such as 5G connectivity, Artificial Intelligence (AI), Machine Learning (ML), and Mobile Edge Computing (MEC). These technologies are transforming the mobile ecosystem by enabling the development of intelligent, data-driven applications and accelerating development cycles. Mod-ern mobile applications are expected to provide real-time services, personalized user experiences, and seamless connectivity, which has significantly increased the complexity of mobile application design and implementation. It is resulting into many challenges. One of the major challenges in mobile application development is the inherent limitation of mobile devices, including restricted pro-cessing power, limited memory capacity, and battery constraints. Developers must optimize application performance while ensuring energy efficiency to pre-vent excessive battery consumption and degraded user experience. Additionally, the increasing reliance on third-party libraries and analytics tools may introduce security vulnerabilities, creating potential security gaps within applications. These risks are often intensified by the lack of specialized security expertise within development teams, raising concerns related to data privacy, application security, and software supply chain vulnerabilities. Another challenge is platform fragmentation, particularly within the Android ecosystem, where diverse devices, operating system versions, and hardware configurations complicate compatibility and performance optimization. This diversity increases testing complexity and development costs. Furthermore, integrating AI and ML models into mobile ap-plications requires careful decisions regarding cloud-based versus on-device pro-cessing. Therefore, developers must balance scalability, performance, security, and energy efficiency when designing modern mobile applications. This study presents systematic literature evaluation methodology, comparative analysis of native and cross-platform paradigms, software supply chain security frameworks, measurable energy optimization strategies, and practical industry case studies from healthcare, fintech, and mobile commerce sectors.
Authors - Murali Mohan Reddy Seelam, VyshnaviThanneeru, Ajay Kumar Reddy Vemireddy, Srilatha Kudumula Abstract - This paper shows a new approach to implement the Agentforce-NS framework to provide zero touch salesforce deployment pipelines by integrating it with the Neuro Symbolic AI Agents. Even though the complete salesforce deployment pipelines have been automated end to end, it has been very difficult to achieve zero touch deployments due to its nature of the handling of metadata due to the interdependency of the components within the salesforce. The regular pipeline processes still heavily depend on the manual intervention to resolve the merge conflicts, resolve the dependency errors, working on the roll back deployments and following the compliances. The architecture we are proposing will solve all these problems by integrating the adaptive and predictive capabilities of the neural networks with rule based, transparent precision of the symbolic reasoning. The proposed Agentforce architecture will have five agents that will collaborate and will execute the deployments without any human intervention. These five agents are used to learn the deployment strategies, roll back planning, analyzing the metadata, autonomous execution and verification of the governance. After many tests in the enterprise level environments, we see that it is resolving so many blockers, issues and increasing the deployment success rate, improving the governance, and reducing the meantime to recover. By covering the technical gap between logical interface and the deep learning, the Agentforce-NS represents a break through advancement to have the fully automated, autonomous and auditable salesforce devops pipelines.
Authors - Shreya S. Partake, Reena S. Satpute Abstract - Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing, achieving human-level performance on many semantic and syntactic benchmarks. However, their competence in pragmatics—the study of how context shapes meaning—remains a critical and underexamined frontier. This paper presents a unified analysis of the “pragmatic gap” in LLMs, arguing that it stems from a fundamental distinction between the co-textual statistical patterns LLMs are trained on and the contextual world knowledge humans use for inference. We first establish a theoretical baseline by reviewing foundational linguistic concepts, including Grice’s maxims, implicature, presupposition, speech acts, and deixis. We then systematically evaluate LLM performance, contrasting successes in pattern-rich tasks like coreference resolution with systemic failures in tasks requiring novel inference, such as non-conventionalized indirect speech acts and irony. We analyze the development of new evaluation tools, particularly the Pragmatics Understanding Benchmark (PUB), which quantifies the persistent gap between model and human performance. Subsequently, we synthesize emerging technical solutions, including “thought-based” fine-tuning and the injection of Gricean principles into Retrieval-Augmented Generation (RAG) frameworks. Finally, we dissect the profound cognitive and philosophical implications of this gap, critically examining the debates on the Symbol Grounding Problem and Theory of Mind (ToM). We conclude that while LLMs can pass “literal” ToM tests, they fail “functional” ToM, revealing them to be sophisticated co-text manipulators rather than context-aware agents. We propose that future progress lies in developing a “machine pragmatics” based on probabilistic models rather than flawed anthropomorphic imitation.
Authors - Ayushi Chapate, Reena S. Satpute Abstract - Natural language helps us to interact with the computer through human language. This article investigates how Natural Language Processing (NLP) can enhance our understanding of social media changes. To its audience, social media provides a large - arguably unlimited - and otherwise untapped linguistic re-source, revealing information about government behavior, civic participation, in-dividual mental well-being, and consumption behavior, among many other things. Using machine learning analytical methods such as sentiment analysis, topic modeling, stance detection, and misinformation tracking, researchers can begin to study the social, psychological, and economic implications of web-based inter-action. In terms of civic and political implications, to analyze user-generated con-tent, discourse networks, and hashtags using NLP applications can produced new insights into online mobilization and collective action. For example, researchers studying the political movement’s #MeToo and #BlackLivesMatter, based on analysis of Twitter data, have employed topic modeling techniques to reveal their influence and significance in innovative ways. From a psychological perspective, NLP methods make it possible to examine prevalent mental health indicators across separated populations, through the analysis of emotional tone, pronoun use, and distress markers. In studies conducted between 2020–2025, the application of BERT based embedding models were found to detect online indicators of depression, anxiety, and social comparison leverage's based on word meaning. Further, understanding the depth of these psychological consequences remains nebulous and limited to a range of social categories in the digital landscape, similar to previous notions of 'self-checking' across the digital commons exploring citizen engagement.
Authors - Jes Maries M. Mendez, Max Angelo D. Perin, Joan Mae G. Lagumbay, Mae S. Dagupan, Elizabeth A. Orapa, Marcelina S. Butlig Abstract - Educational tours are widely used in higher education to connect class-room learning with real settings, yet evaluations often stop at overall ratings that do not explain why students endorse a tour or which delivery issues weaken the experience. This study applies a student experience intelligence workflow that integrates survey analytics with offline text mining to produce planning-relevant evidence. A survey of 156 students captured demographics, three 10-item Likert constructs—motivation, perceived effectiveness, and problems encountered (4-point scale)—a recommendation rating, and open-ended comments. Responses were cleaned through category standardization and rule-based numeric conversion. Internal consistency was good for motivation (α = 0.877) and excellent for effectiveness (α = 0.960) and problems (α = 0.958). Learning beyond classroom instruction (M = 3.71) and interest in tour inclusions (M = 3.68) led motivation; creative learning (M = 3.67), resourcefulness (M = 3.66), and social skills (M = 3.65) led effectiveness; tour expense (M = 3.21) and short time per attraction (M = 2.60) led problems. 73.1% gave the top recommendation. Recommendation correlated positively with motivation (ρ = 0.317, p < 0.001) and effectiveness (ρ = 0.328, p < 0.001); a binary logistic model showed perceived effectiveness as the strongest predictor of the top recommendation category. Open-ended comments (171 entries) were summarized through TF–IDF with K-Means clustering (k = 6) and complemented with a VADER polarity pass on 155 meaningful entries (68.4% positive, 21.9% neutral, 9.7% negative; mean compound = +0.365). The combined evidence points to improvements that preserve educational value while addressing cost and pacing, and shows that the workflow is portable to other programs and experiential learning activities.
Authors - Kent Cyryl A. Campit, Christian Kelvin Gonzales Abstract - This study explored a data-driven approach to evaluating citizen feedback within the Provincial Government of La Union (PGLU) by integrating quantitative and qualitative analytical techniques. Traditional feedback systems in government offices often rely on averages and summary reports, limiting the ability to capture deeper citizen experiences and concerns. To address this gap, the research transformed paper-based feedback forms into a structured digital dataset covering responses from 34 frontline offices and service units from July 2025 to January 2026. The study applied Customer Satisfaction Score (CSAT), Weighted Mean, and Range of Interval to measure and classify service performance levels. For qualitative analysis, Latent Dirichlet Allocation (LDA) was used to identify recurring themes in open-ended responses, while a dual-model sentiment analysis approach combining VADER and RoBERTa classified citizen feedback into positive, neutral, and negative sentiments. The analytical pro-cesses were implemented using Microsoft Excel, Google Sheets, and Python through Google Colaboratory. Findings revealed consistently high satisfaction ratings across offices, while qualitative analysis uncovered recurring themes related to service efficiency, staff assistance, facility conditions, and operational concerns. RoBERTa demonstrated better contextual understanding and achieved higher performance metrics compared to VADER. The study further developed an Observed Satisfaction Classification Framework to support evidence-based decision-making and service improvement. Ultimately, the re-search demonstrated how citizen feedback can be transformed into actionable governance insights that promote transparency, accountability, and continuous improvement in public service delivery, aligned with Sustainable Development Goal 16.
Professor, National Institute of Technology Raipur, India.
Narendra D. Londhe is presently working as Associate Professor in the Department of Electrical Engineering of National Institute of Technology Raipur, Chhattisgarh INDIA. He completed his B.E. from Amravati University in 2000 followed by M.Tech and Ph.D. from Indian Institute of Technology... Read More →
Authors - Kalva Yamini, Kapilesh C, Hari Kishore R, Giri Karthick S Abstract - Phishing attacks remain among the most prevalent cybersecurity threats, exploiting deceptive URLs that imitate legitimate domains. Traditional blacklist and heuristic-based methods fail to detect zero-day phishing URLs, leaving users exposed to novel attack vectors. This paper presents 3P-VAD (Three-Phase Verification and Detection), an AI-powered system for real-time URL classification integrating three complementary layers: (i) threat intelligence dataset lookup against live feeds, (ii) multi-engine verification via the VirusTotal API aggregating results from 70+ security vendors, and (iii) a Convolutional Neural Network (CNN)-based zero-day detection model operating exclusively on URL character sequences. A selection-based scanning mechanism enables on-demand URL verification, enhancing user privacy by preventing inadvertent submission of sensitive internal URLs to third-party services. Evaluated on 2 million URLs, the framework achieved 95.0% accuracy, 94.5% precision, 86.0% recall, and 90.0% F1-score on the CNN zero-day component, with 100% combined detection rate across all three phases. Ablation experiments confirm non-redundant, complementary coverage.
Authors - Farai C. Jonha, Arthur Ndlovu, Mainford Mutandavari Abstract - This study presents a systematic review on the use of deep learning and density-based techniques for explainable segmentation of banking customers. We analyze 71 peer-reviewed papers published between 2015 and 2025 to investigate their methodological trends, validation approaches, and the degree of incorporation of interpretability into proposed models. Our findings suggest that autoencoders and variational autoencoders provide better separation of clusters than models using raw data. In terms of clustering methods, density-based clustering algorithms perform better than clustering algorithms based on centroids since banking data exhibit highly skewed and non-Gaussian patterns. We also observe a common deficiency in explainability, with less than 26% of the re-viewed papers considering approaches such as SHAP or LIME. Furthermore, considerations of external validity, operational governance, regulation, and scalability of implementation are rare. We therefore propose an explainable customer segmentation (XCS) framework based on deep representation learning, density-based clustering, post-hoc explainability, and an operationally ready pipeline that is suitable for use in regulated banking environments
Authors - Mohammed Sulaiman I, Shreevatsa DS, Kavitha Sooda, Revanth L, Dhanush M Abstract - The unintentional release of API keys, tokens, and any other credentials in the source code is an obvious security threat to contemporary software development. Old rule-based scanners produce too many false positives and cannot scan through obfuscated secrets or secrets that are unknown. This paper introduces AV-SHIELD (Automated Vulnerability Scanning Hybrid, Implementing integrated Leakage Detection) which is a hybrid framework that brings together pattern matching and machine learning to identify credential leaks in real time. The system serves to monitor development spaces in event-driven fashion and scan repositories in GitHub up to size limitations. One uses a Random Forest type of classifier, which is trained on entropy based features to combatSecret vs Benign strings and a risk scoring engine which gives priority to create alerts. Records of the identified exposures are archived in a fingerprint-tracked vault, batch-processed into mail notifications, and include professionally-formatted PDF records. A trade analysis using an interactive Streamlit dashboard allows viewing trends of exposure, provider profiles, and risk allocations. The synthetic data generated has demonstrated a high precision and recall rate that is much lower than the explanation of the uses of regex alone, tested through experimental evaluation. The framework was implemented as a systemd service, which shows its applicability to the enterprise DevSecOps pipelines.
Authors - Alfred ADINSI, Pelagie HOUNGUE Abstract - This systematic review evaluates AI-based techniques for rice dis-ease detection with a focus that existing surveys have not adopted: their deploy-ability in West African smallholder conditions, using Benin as the reference case. Based on 220 studies selected from 390 Scopus publications (2019–2025) via PRISMA, it goes beyond performance benchmarking to assess what actually works under resource constraints. Rice blast (70.9% of studies), brown spot (60.9%), and bacterial blight (44.5%) dominate the literature. Deep Learning accounts for 64.5% of approaches, hybrid methods for 21.8%, and classical Machine Learning for 13.6%. Mean accuracy reaches 94.2% for pure Deep Learning and 95.8% for hybrid architectures. Res-Net+ViT (96.4% ± 2.1%) and CNN+SVM (94.1% ± 4.1%) are the strongest per-formers, but performance alone is not the right metric for Benin. While 85% of studies apply to tropical climates, only 30.5% propose solutions running on limited hardware. Three approaches clear both bars: MobileNet+SVM (89.4%), optimized YOLOv8 (89.2%), and ResNet-based Transfer Learning (91–94% after fine-tuning). That AI can detect rice diseases accurately is no longer in question. The harder problem is which systems beninese farmers and extension agents can actually use. This review provides an answer.
Authors - I Gusti Ayu Agung Dewi Sucitawathi Pinatih, Jonathan Jacob Paul Latupeirissa Abstract - The objective of this study is to examine and analyze the integration of technology, governance, and sustainability in the context of e-government and public services, with a particular focus on the implementation of these three dimensions at the global and local levels, specifically in the Province of Bali. This study employs a Systematic Literature Review (SLR), beginning with the identification of relevant keywords such as “e-government,” “public service,” and “sustainabil-ity,” which were validated using WordCloud. Next, strict inclusion and exclusion criteria were used to select articles. These criteria included relevance to the topic, year of publication (2016-2026), and the journal’s peer-review status. Initial identification, screening of titles and abstracts, and in-depth reading of articles were part of the article selection process. The research findings indicate that in the digital transformation of the public sector, technology, governance, and sustainability are interrelated, and Bali serves as an example of how the integration of these three dimensions is reinforced by local values such as Tri Hita Karana and the subak system. These findings underscore that the digitization of public services in Bali will succeed if the principle of sustainability is applied in tandem with technology, governance, and local culture.
Authors - Aymane Chekira, Aziz Hmioui Abstract - The rapid expansion of digital technology in recent years has significantly changed the way international supply chains (SCs) are structured, operated, and how well they perform. Among these transformations, blockchain has grown to be a major enabler for addressing continuous concerns with transparency, traceability, collaboration, and trust throughout supply chain networks. As companies seek more and more to raise supply chain performance and sustainability, scholarly investigations of blockchain-based supply chain management have grown dramatically. Descriptive and content analysis of co-occurrence key-words using Biblioshiny and VOSviewer software revealed the main research subjects and their linkages across 145 peer-reviewed Scopus-indexed publications spanning 2019–2026. Scientometrically speaking, this study examines this expanding body of research. The results point to two primary research directions: (i) how blockchain uptake influences organizational performance and supply chains, and (ii) how transparency, traceability, decision-making, and sustainable development enabled by blockchain are present in supply chains. The data analysis reveals that blockchain technology is a key and unifying feature that connects performance improvement with the goals of governance and sustainability. It emphasizes new ways for more investigation in blockchain-enabled supply chain performance and offers a systematic overview of the intellectual environment of blockchain research in supply chain management, as well as comprehensible in-sights on its thematic evolution.
Authors - Putu Putri Prawitasari, Shefali Saluja, Jonathan Jacob Paul Latupeirissa Abstract - Financial statements are vital for conveying a company's performance and financial health, yet fraudulent financial reporting remains a significant concern, especially involving fraud hexagon schemes. This study investigates the integration of advanced technologies to combat fraud hexagon schemes and improve auditing effectiveness in the digital era. Through a comprehensive literature review of academic sources from the Scopus database, this research identifies the limitations of traditional auditing in detecting complex fraud patterns. Findings reveal that the adoption of technology-based tools such as data analytics, artificial intelligence, machine learning, and blockchain enhances auditors’ ability to detect anomalies and suspicious activities more efficiently and accurately. Furthermore, combining these technologies with robust corporate governance and auditor expertise strengthens fraud prevention mechanisms. The study concludes that leveraging digital innovations within a holistic fraud detection framework significantly advances audit quality and fraud mitigation strategies in contemporary financial environments.
