Chia-Ching Lin
Chang Jung Christian University

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

A Novel Approach to Multi-Task Prediction in IoT Environments Using Dynamic Heterogeneous Graph Neural Networks Chia-Ching Lin; Yih-Chang Chen
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 3 (2026): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i3.16044

Abstract

The rapid proliferation of Internet of Things (IoT) devices and digital services has created densely interconnected socio-technical networks that challenge conventional risk management. Traditional machine learning models struggle to capture multi-hop relational structure, temporal drift, and severe class imbalance, while static Graph Neural Networks (GNNs) ignore dynamic graph evolution and high-frequency IoT telemetry. This paper proposes an IoT-driven dynamic prediction framework that conceptualizes financial and social-protection infrastructures as assets requiring predictive maintenance. We introduce a multi-task dynamic heterogeneous GNN that jointly estimates credit risk in financial networks and early-warning scores for high-risk social-work cases over evolving graphs linking clients, accounts, devices, households, and practitioners. The architecture combines relation-aware message passing with a Gated Recurrent Unit (GRU) temporal encoder to integrate streaming IoT signals with longitudinal administrative data. We specify an evaluation protocol that compares the framework with logistic regression, gradient boosting, temporal sequence models, and static GCN/GraphSAGE using AUC-ROC, AUC-PR, Brier score, and operational metrics under time-based splits and rolling-window validation; future empirical studies should also employ appropriate significance tests, such as DeLong’s test and bootstrap confidence intervals. This work does not report new experiments on proprietary datasets; instead, it synthesizes recent findings in credit risk, anti-money laundering, IoT-based predictive maintenance, and child-protection analytics to argue that dynamic multi-task graph modeling can better support timely, ethically governed interventions in complex socio-technical systems.
Cybersecurity and Privacy Governance in IoT-Enabled Social Work: A Systematic Review and Risk Framework Yih-Chang Chen; Chia-Ching Lin
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14589

Abstract

Social work practice is rapidly integrating Internet of Things (IoT) technologies to expand service delivery, yet this integration introduces significant cybersecurity and privacy vulnerabilities that disproportionately threaten vulnerable populations. Existing literature predominantly emphasizes technical security solutions while neglecting the ethical considerations, protective needs of vulnerable groups, and governance frameworks specific to social work contexts. Research Contribution: This study develops the first systematic multidimensional framework integrating engineering and social science perspectives to evaluate IoT cybersecurity, privacy risks, and governance requirements in social work applications. Using a Systematic Literature Review following PRISMA guidelines, we searched five major databases from January 2020 to September 2024. We employed qualitative thematic analysis combined with an innovative quantitative assessment algorithm to score technologies, threats, and governance components across 55 primary studies. Key Findings: Mental health services and vulnerable population support face “very high” privacy risks (PRS > 8.0), primarily from systemic infrastructure weaknesses in consumer-grade devices rather than sophisticated cyberattacks. Homomorphic encryption achieves the highest security score (9.8/10) but exhibits the highest implementation complexity (9.0/10). Federated learning provides an optimal balance (security 8.5, complexity 8.0, cost 6.0). Ethical guidelines demonstrate the highest implementation difficulty (8.2/10), reflecting challenges in translating abstract principles into technical specifications. Quantitative gap analysis identifies vulnerable population protection as the highest research priority (gap score 3.7/10). This study offers an evidence-driven agenda for practitioners and policymakers, proposing context-specific technology selection criteria and adaptive governance models that prioritize interdisciplinary collaboration, ensuring IoT advancements effectively promote social welfare while protecting at-risk individuals.