Design and Implementation of A Real-Time Log-Based AI Personalized Voice Coaching and Dynamic Safe Route Recommendation System

With the rapid advancement of wearable devices and location-based services, personalized fitness tracking has gained significant attention. However, conventional running applications often fail to provide real-time adaptive feedback and dynamic route optimization based on runners' immediate physiological states and environmental hazards. To address these limitations, this paper proposes a real-time, log-based AI personalized voice coaching and dynamic safe route recommendation system. The proposed architecture systematically collects multi-modal telemetry logs—including biometric data and spatial coordinates—to analyze runners' performance profiles in real time. By leveraging advanced machine learning models, the system delivers context-aware voice coaching tailored to individual fitness levels and fatigue metrics. Furthermore, it incorporates a dynamic routing algorithm that evaluates environmental safety factors to recommend secure and optimal running paths. Experimental results demonstrate that the proposed system enhances user safety, improves workout efficiency, and delivers an optimized personalized running experience.

Intelligent Healthcare, AI Voice Cloning, Spatial Database, Dijkstra Algorithm, Real-time Data Processing, Personalized Support System

1. T. Shi and F. Gao, “Utilizing Multi-Source Geospatial Big Data to Examine How Environmental Factors Attract Outdoor Jogging Activities,” Remote Sensing, 2024. [Google Scholar] [Crossref]

2. W. Yang, J. Fei, Y. Li, H. Chen, and Y. Liu, “Unraveling nonlinear and interaction effects of multilevel built environment features on outdoor jogging with explainable machine learning,” Cities, 2024. [Google Scholar] [Crossref]

3. H. Issa, A. Guirguis, S. Beshara, S. Agne, and A. Dengel, “Preference based Filtering and Recommendations for Running Routes,” SciTePress, 2016. [Google Scholar] [Crossref]

4. A. Fitro, S. Suryono, and R. Kusumaningrum, “Shortest Route at Dynamic Location with Node Combination-Dijkstra Algorithm,” EECSI, 2018. [Google Scholar] [Crossref]

5. J. Zheng, Z. Zhang, B. Ciepłuch, A. C. Winstanley, P. Mooney, and R. Jacob, “A PostGIS-based pedestrian way finding module using OpenStreetMap data,” Geoinformatics, 2013. [Google Scholar] [Crossref]

6. R. O. Obe and L. S. Hsu, “pgRouting: A Practical Guide,” Locate Press, 2018. [Google Scholar] [Crossref]

7. W. Li, Y. Wang, D. Li, and X. Xu, “MCM: A Robust Map Matching Method by Tracking Multiple Road Candidates,” AAIM, 2022. [Google Scholar] [Crossref]

8. Y. Geng, J. Xu, Z. Liang, J. Yang, X. Shi, and X. Shen, “Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai,” ACL, 2025. [Google Scholar] [Crossref]

9. H. Zhou, X. Wu, and L. Yu, “The comforting companion: using AI to bring loved one’s voices to newborns, infants, and unconscious patients in ICU,” Critical Care, 2023. [Google Scholar] [Crossref]

10. Y. Jiang, T. Wang, H. Wang, C. Gong, Q. Liu, Z. Huang, L. Wang, and J. Dang, “Expressive Text-to-Speech with Contextual Background for ICAGC 2024,” ISCSLP, 2024. [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study