HikeSmart: A Personalized AI Assistant for Multi-Facet Hiking Preparation and Risk
DOI:
https://doi.org/10.64849/ssi.v3i1.92Keywords:
Recommendation Systems, Mountain Hiking, Personalization, Risk Mitigation, Human-Computer Interaction (HCI)Abstract
Mountain hiking’s growing popularity was paralleled by persistent safety risks, often stemming from inadequate preparation and the limitations of one-size-fits-all planning tools. Existing solutions typically failed to provide guidance tailored to a user’s specific experience level and the dynamic context of an expedition. To address this gap, this paper proposed and evaluated HikeSmart, a personalized AI assistant for hiking preparation. The system’s core technical contribution was an integrated decision-support engine governed by a multi-persona framework (novice, experienced, group leader). This engine combined a heuristic scoring algorithm for personalized route recommendation with a rule-based inference engine for generating dynamic, context-aware logistics checklists. A usability study with 15 participants yielded a high mean System Usability Scale (SUS) score of 85.5, placing it in the ‘excellent’ usability category. Qualitative feedback confirmed that this personalized and integrated approach improved user confidence during the planning phase.
References
W. S. Widodo, “Indonesia Punya 400-an Gunung, Potensi Wisatanya Besar Sekali,” detikTravel. Accessed: Jun. 23, 2025. [Online]. Available: https://travel.detik.com/travel-news/d-6953185/indonesia-punya-400-an-gunung-potensi-wisatanya-besar-sekali
GoodStats, “Jumlah Kecelakaan Pendakian di Berbagai Gunung Indonesia 2013-2024,” GoodStats. Accessed: Jun. 23, 2025. [Online]. Available: https://goodstats.id/article/jumlah-kecelakaan-pendakian-di-berbagai-gunung-indonesia-2013-2024-moVFb
B. Smyth, “Recommender Systems: A Healthy Obsession,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, Art. no. 01, Jul. 2019, doi: 10.1609/aaai.v33i01.33019790.
A. Felfernig, M. Wundara, T. N. T. Tran, V.-M. Le, S. Lubos, and S. Polat-Erdeniz, “Sports Recommender Systems: Overview and Research Issues,” Dec. 11, 2023, Research Square. doi: 10.21203/rs.3.rs-3710874/v1.
Z. Zheng and Y. Liu, “Design of Cloud Storage‐Oriented Sports Physical Fitness Monitoring System”, doi: 10.1155/2022/1889381.
H. Lei, X. Shan, and L. Jiang, “Personalized Item Recommendation Algorithm for Outdoor Sports”, doi: 10.1155/2022/8282257.
SHARMA, Durgansh and SHARMA, Vaibhava, “Machine Learning-Based Model for Injury-Free Sports Training,” ijcih, vol. 3, no. 1, 2023, doi: 10.55487/ijcih.v3i1.97.
B. N. Iduh, M. N. Umeh, O. I. Anusiuba, and F. A. Egba, “Development of a Predictive Modeling Framework for Athlete Injury Risk Assessment and Prevention: A Machine Learning Approach,” ejtas, vol. 2, no. 4, pp. 894–906, Jul. 2024, doi: 10.59324/ejtas.2024.2(4).73.
H. Van Eetvelde, L. D. Mendonça, C. Ley, R. Seil, and T. Tischer, “Machine learning methods in sport injury prediction and prevention: a systematic review,” J EXP ORTOP, vol. 8, no. 1, p. 27, Dec. 2021, doi: 10.1186/s40634-021-00346-x.
L. Xiong et al., “Risk Reduction Behaviors Regarding PM2.5 Exposure among Outdoor Exercisers in the Nanjing Metropolitan Area, China,” IJERPH, vol. 15, no. 8, p. 1728, Aug. 2018, doi: 10.3390/ijerph15081728.
R. Licker, K. Dahl, and J. T. Abatzoglou, “Quantifying the impact of future extreme heat on the outdoor work sector in the United States,” Elementa: Science of the Anthropocene, vol. 10, no. 1, p. 00048, Jan. 2022, doi: 10.1525/elementa.2021.00048.
S. Swain and R. Niyogi, “Service Composition in a Context-Aware Setting with Functionally Equivalent Services,” in Computational Science and Its Applications – ICCSA 2020, vol. 12253, O. Gervasi, B. Murgante, S. Misra, C. Garau, I. Blečić, D. Taniar, B. O. Apduhan, A. M. A. C. Rocha, E. Tarantino, C. M. Torre, and Y. Karaca, Eds., in Lecture Notes in Computer Science, vol. 12253. , Cham: Springer International Publishing, 2020, pp. 106–119. doi: 10.1007/978-3-030-58814-4_8.
J. Zhong and E. Negre, “Towards Better Representation of Context Into Recommender Systems:,” International Journal of Knowledge-Based Organizations, vol. 12, no. 2, pp. 1–12, Apr. 2022, doi: 10.4018/IJKBO.295080.
P. T. Moore and H. V. Pham, “Personalization and rule strategies in data-intensive intelligent context-aware systems,” The Knowledge Engineering Review, vol. 30, no. 2, pp. 140–156, Mar. 2015, doi: 10.1017/S0269888914000265.
M. Kosrane and M. Gharzouli, “Toward a Context-Aware Course-Planning Model in Pervasive Learning Environments,” Int. J. Emerg. Technol. Learn., vol. 18, no. 15, pp. 36–51, Aug. 2023, doi: 10.3991/ijet.v18i15.40601.
S. Belhadi and R. Merzougui, “Design and implementation of a Context-Aware Health Service Platform (CAHS),” IJECE, vol. 9, no. 6, p. 4993, Dec. 2019, doi: 10.11591/ijece.v9i6.pp4993-5005.
john Brooke, “SUS: A ‘Quick and Dirty’ Usability Scale,” in Usability Evaluation In Industry, CRC Press, 1996.
V. Braun and V. Clarke, “Using thematic analysis in psychology,” Qualitative Research in Psychology, vol. 3, no. 2, pp. 77–101, Jan. 2006, doi: 10.1191/1478088706qp063oa.
A. Bangor, P. T. Kortum, and J. T. Miller, “An Empirical Evaluation of the System Usability Scale,” International Journal of Human–Computer Interaction, vol. 24, no. 6, pp. 574–594, Jul. 2008, doi: 10.1080/10447310802205776.
I. Orue-Saiz, M. Rico-González, J. Pino-Ortega, and A. Méndez-Zorrilla, “Improving diet through a recommendation system using physical activity data and healthy diet indexes of female futsal players,” Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology, vol. 239, no. 1, pp. 39–52, Mar. 2025, doi: 10.1177/17543371241241847.
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Sustainability and Social Impact
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
