Impact in Computics – Volume 2 (2026)
A Multimodal Artificial Intelligence Framework for Intelligent Mortgage Risk Assessment Using Underwriting and Loan-Performance Information
Mortgage risk models often rely solely on underwriting variables, with unclear targets and evaluation protocols. This study proposes a multimodal artificial intelligence framework using separate encoders for financial and loan-performance features from the ...
Development and Preliminary Usability Evaluation of a Mobile Health Platform for Post-Discharge Monitoring of Diabetic Foot Ulcer Patients
Diabetic foot ulcer (DFU) management requires continued monitoring after hospital discharge to support continuity of care and timely clinical follow-up. This study presents a mobile health platform developed to support remote post-discharge monitoring of pa...
Explainability and Feature Fusion for Colon CT Image Classification
Accurate classification of colon computed tomography (CT) images using deep learning has shown promising results. However, the contribution of handcrafted features, reliability of explainability methods, and potential influence of data leakage remain import...
Automated Image-Based Detection and Measurement of Wheal Responses in Skin Prick Test Images
Allergic disorders are common conditions caused by immune responses to otherwise harmless substances. The Skin Prick Test (SPT) is commonly employed to evaluate sensitivity to particular allergens, with the development of wheals acting as a significant visi...
A Conv-Attention Seasonal Aggregation Network (CASA-Net) for PM2.5 Concentration Forecasting Using US EPA Monitoring Data
The prediction of fine particulate matter, or fine particulate (PM₂.₅), is very important for air quality management and protecting human health. Current deep-learning approaches, however, cannot capture the local time-specific interactions and spatiotempor...
Systematic Review of Machine Learning and Deep Learning Approaches for Spam Detection in Online Social Networks
Malicious activities such as phishing, disinformation, and bot attacks for spamming in online social networks (OSNs) have become an increasing problem, and online spam detection is an ongoing challenge to keep users safe and OSNs healthy. However, classical...
AI-Based Tutoring Systems for Deaf and Hard-of-Hearing Learners: A Systematic Review of Computational Architectures, Adaptive Mechanisms, and Meta-Analysis of Learning Outcomes
Children who are Deaf or hard of hearing (DHH) often experience educational challenges that may affect their academic achievement. Artificial intelligence (AI)-based tutoring systems have been proposed to address some of these challenges, but evidence regar...
An AI-Driven Game Analytics Framework for Intelligent Player Profiling in a Unity-Based Roll Ball Environment
Modern digital games generate extensive gameplay telemetry that can reveal patterns of player behavior and performance. This study proposes an AI-enabled game analytics framework for intelligent player profiling using gameplay data collected from a Unity-ba...
Towards Green AI: A Lightweight Experimental Study on Carbon-Aware Neural Network Training
Industry 5.0 places emphasis on human-centered innovation, aligning digital transformation with sustainability, resilience, and societal well-being. Smart cities serve as practical environments where advanced technologies must balance operational efficiency...