Authors - Thaw Thaw May Oo, Khaing Khaing Wai Abstract - Modern maritime industry depends largely on digital communications and access control systems for their operation and security maintenance. On the other hand, digital communication and access control systems make maritime industry more vulnerable to cybersecurity attacks, such as unauthorized access, data leaks, and insiders' malicious actions. Centralized security measures become inefficient against modern and advanced cyber threats. In that regard, this paper presents a Smart Digital Lock System using Zero Trust Architecture and AES Encryption. The suggested approach assumes the implementation of zero trust policy in terms of continuous user identity validation requiring tight access control, including strict user authentication and monitoring. Multifactor authentication and real-time monitoring are the key characteristics of the suggested system, especially considering such potential high-risk zones as ships and ports. Communication of authorized parties will be performed using the AES encryption to protect the information's privacy and integrity. As a result, the presented system will be assessed from three perspectives: authentication accuracy, data protection effectiveness, and response latency.
Authors - Ei Marlar Win, Amy Tun, Khant Kyawt Kyawt Theint Abstract - Electrocardiogram (ECG) signal analysis plays an important role in the early detection and diagnosis of cardiovascular diseases. Manual interpretation of ECG recordings is time-consuming and highly dependent on clinical expertise, creating a need for automated and accurate classification systems. This study presents an automated ECG classification model using signal preprocessing, heartbeat segmentation, wavelet, feature extraction, and deep learning. ECG signals are preprocessed to remove noise using filtering and normalization methods. Features are extracted heartbeat segments-based windows around each R peak and classified into five different arrhythmias N (Normal), V (Ventricular), S (Supraventricular), F (Fusion) and Q (Unknown/noisy /unclassified) using wavelet Convolutional Neural Network (CNN) Self Attention model. Experiments on MIT-BIH ECG dataset and analyze the model performance evaluation across a single-lead ECG, multi lead ECG, lead fusion and feature fusion techniques by wavelet attention. The results indicate that the proposed approach yields high classification performance and effectively distinguishes heartbeats abnormalities. Class weighting techniques were applied to address the issue of imbalanced class labels in the ECG dataset. The lead fusion approach achieved classification accuracies of 0.98. Single lead, multi lead and feature fusion experimental approaches were evaluated, resulting in classification accuracies of 0.97, 0.98, and 0.97, respectively. The class-weighting method combined with lead fusion feature extraction obtained an accuracy of 0.95. Furthermore, class weight additional techniques achieved accuracies of 0.91, 0.92 and 0.92, demonstrating variations in model performance across different methodologies. This automated system can support clinicians to assist in the early diagnosis of heart abnormalities and improve healthcare efficiency.
Authors - Caroline Sutiono, Ronald Gunawan, Silvina Chandra, Maria Pia Adiati Abstract - Online to Offline applications (O2O) have transformed a service style to a new level, since consumers increasingly rely on digital technology to access daily food and beverage products and services based on their needs and preferences. Prior to their arrival, the customer browses the menu, place the order and finish the payment and afterwards the product will be collected at the store. The application required to provide details menu information, options and preference as well as payment details. To use of O2O applications requires customers to have sufficient digital literacy to navigate the ap-plication, place orders, and complete upfront payments. Meanwhile, outlet staff must be able to accurately interpret and process each order specification to ensure service accuracy. Therefore, this study is examining the relationship between O2O application usage, service efficiency, and customer experience in F&B retail businesses. This research uses a quantitative research method, with a survey approach with 160 eligible respondents and analyzed thru SEM PLS. This result emphasizes the importance of user experience and service design into interaction in O2O application usage experience, where customers prioritize applications that are intuitive, convenient, and aligned with their needs. Therefore, the effectiveness of O2O applications is influenced not only by operational efficiency but also by how well the technology supports user-friendly and meaningful user experiences.
Authors - Su Thet Oo, Ah Nge Htwe, Nilar Aye Abstract - The automatic detection of AI-generated art images is essential for distinguishing authentic human creations from artificial ones. This process is critical for authenticity verification, provenance control, misinformation management, and digital forensics. With the rapid evolution of deep learning content generation, the existing detection approaches within artistic imagery remain an underexplored domain characterized by artworks that differ widely in style and often contain non-standard, complex, or distorted visual patterns. The proposed model is an empirical study of a fine-tuned CNN-based generative art detection to classify real and human-created art accurately by learning discriminative visual features such as texture, structure, and statistical patterns, adapting a pre-trained CNN model and also finetuning architecture layers and defining the spatial dimension, which is used to determine the level of detail captured in feature extraction and classification. In our system, utilizing a balanced dataset consisting of real and AI-generated art images, the system was trained and evaluated, where a base VGG16 net in traditional architecture and this architecture of pre-trained and fine-tuned VGG16 with hyperparameter tuning of task-specific input representation and data augmentation, layer optimization strategies using the same balanced dataset, with results benchmarked against a strong baseline.
Authors - Ferdinand V. Dalisay, Gerli Ryza DS. Reyes Abstract - On-the-Job Training (OJT) in Philippine higher education institutions (HEIs) stands at a decisive inflection point. Historically constrained by misaligned curricula, weak industry-academe partnerships, and inadequate quality assurance mechanisms, the OJT system is now confronted simultaneously with the disruptive potential of artificial intelligence (AI), the transformative power of data analytics, and the imperatives of broader digital transformation. This systematic literature review synthesizes 35 peer-reviewed studies and policy documents published between 2020 and 2026 to examine how these three technological forces are reshaping and should further reshape the design, implementation, supervision, and evaluation of OJT programs across Philippine colleges and universities. Guided by the TIBS 2026 conference tracks on AI and Intelligent Systems, Data Analytics and Business Intelligence, and Digital Transformation and Technology Strategy, the review constructs a crosscutting analytical framework that interrogates the current state of Philippine OJT against the backdrop of these technological paradigms. Four thematic clusters are identified: (1) AI-mediated supervision, mentoring, and competency scaffolding; (2) data-driven OJT quality assurance and outcome analytics; (3) digital platform ecosystems and virtual work-integrated learning; and (4) strategic alignment between OJT curricula and the emerging digital economy. Findings reveal that while Philippine HEIs have begun to engage with digital tools in OJT administration, deep integration of AI and analytics into OJT pedagogy and governance remains nascent. The review concludes with a multi-stakeholder digital transformation roadmap for the Philippine OJT system, offering implications for CHED policymakers, HEI administrators, industry partners, and technology developers.
Authors - Janssen Emmanuel Jahja, Anderes Gui Abstract - The rapid development of e-commerce also raises the need for new innovations such as Virtual Try-On (VTO) to address the physical limitations of online product evaluation. Nevertheless, the interaction of functional and psychological factors of VTO is poorly understood as influencing its adoption, while their influence on purchase decisions also remains limited. This study investigates these factors with respect to online purchasing intentions. Incorporating an extended Technology Acceptance Model (TAM) with consumer behavior theories, the conceptual model assesses Perceived Ease of Use, Perceived Usefulness, Perceived Enjoyment, Attitude, Personal Innovativeness in IT, and Self-Efficacy. Using a quantitative approach, information was gathered from consumers who shop on e-commerce sites and analyzed using Structural Equation Modeling (SEM). The results show that the hypotheses suggested are well supported. This study contributes theoretically by extending digital retail literature and offers managerial implications for designing VTO features that not only improve the shopping experience but also yield higher sales conversions.
Authors - Jayanthi J, Krishna Kanwar, Divansh Tarun Mittal, Akash Kumar, Srikanta Pradhan, Arun Kumar K Abstract - The problem of financial distress faced by the sandwich generation-who are held responsible for both the elderly parents and dependent children simultaneously, but not accommodated by available tools-motivates this research. In this work, we developed a portfolio intelligence system named WealthBridge that leverages an AI framework, which includes Random Forest model for risk profiling and an LSTM network for market regime detection. While the model accurately classify investors (with 95% accuracy) and market regimes, it forecasts market trends using time series of various features. A fusion engine then provides recommendation for allocation to different portfolio asset classes and investment in particular stock. It is accessible through the deployment of a Streamlit dashboard, making it an efficient tool for data-driven financial planning. The accuracy was assessed with robust performance of models that caters to financial services of the Indian middle income sandwich generation.
