Power-Aware Transport Mode Detection: A Comparative Analysis on Resource-Constrained Smartphones

Abstract

Understanding human mobility is crucial for applications like urban planning, traffic management, and personalized services. This paper presents a power-aware transport mode detection approach that leverages a limited set of smartphone sensors and machine learning algorithms to accurately classify various transportation modes while optimizing energy consumption. By focusing on a subset of essential sensors (accelerometers, gyroscopes, magnetometers, etc.) and implementing an optimized data preprocessing pipeline, our method reduces the energy drain associated with continuous data collection. Using the Sussex-Huawei Locomotion dataset, we evaluate seven classification models, namely, 1-Nearest Neighbor, Gaussian Naïve Bayes, Decision Tree, Random Forest, and two Convolutional Neural Networks and a ResNet model. We propose a preprocessing pipeline and a windowing strategy for temporal sensor data, and we demonstrate that Random Forest achieves high classification accuracy (95.05%). The study also discusses trade-offs between model performance, computational cost, and energy efficiency, highlighting the potential of well-designed lightweight models and sensor subsets for real-world deployment. Our findings suggest that traditional models, when properly optimized, can effectively support energy-efficient and privacy-conscious transport mode detection on smartphones.

Keywords

• Transport Mode Detection
• Deep Learning
• Smartphone Sensors
• Random Forest

Güç Tüketimine Duyarlı Ulaşım Yöntemi Tespiti: Kaynak Kısıtlı Akıllı Telefonlarda Karşılaştırmalı Bir Analiz

Abstract

İnsan hareketliliğinin anlaşılması; kentsel planlama, trafik yönetimi ve kişiselleştirilmiş hizmetler gibi pek çok uygulama açısından kritik bir öneme sahiptir. Bu çalışma, enerji tüketimini optimize ederken çeşitli ulaşım modlarını doğru bir şekilde sınıflandırmak için sınırlı sayıda akıllı telefon sensörü ve makine öğrenme algoritmasından yararlanan, enerjiye duyarlı bir ulaşım modu tespit yöntemi sunmaktadır. Sürekli veri toplamanın neden olduğu enerji kaybının azaltılması için temel algılayıcıların (ivmeölçer, jiroskop, manyetometre v.b.) belirli bir alt kümesine odaklanılmış ve optimize edilmiş bir veri ön işleme süreci kulanılmıştır. Sussex-Huawei Locomotion veri seti kullanılarak 1-En Yakın Komşu, Gauss Naive Bayes, Karar Ağacı, Rastgele Orman ve iki Evrişimsel Sinir Ağı ile bir ResNet modeli olmak üzere yedi sınıflandırma modelinin performansı değerlendirilmiştir. Zamansal algılayıcı verileri için bir ön işleme hattı ile pencereleme stratejisi önerilmiş; Rastgele Orman'ın %95,05 doğruluk oranı ile yüksek sınıflandırma başarısı elde ettiği ortaya konmuştur. Çalışmada ayrıca model performansı, hesaplama maliyeti ve enerji verimliliği arasındaki dengeler tartışılmakta; hafif ve iyi tasarlanmış modellerin gerçek dünya uygulamalarına uyarlanabilirliği vurgulanmaktadır. Bulgular, geleneksel modellerin uygun şekilde optimize edildiklerinde akıllı telefonlarda enerji verimli ve gizlilik odaklı ulaşım modu tespitini etkin biçimde destekleyebileceğini göstermektedir.

Keywords

• Ulaşım yöntemi tespiti
• Derin öğrenme
• Akıllı telefon algılayıcıları
• Rasgele Orman
• CNN

References

1. [1] G. Lan, W. Xu, D. Ma, S. Khalifa, M. Hassan and W. Hu, "EnTrans: Leveraging Kinetic Energy Harvesting Signal for Transportation Mode Detection," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 7, pp. 2816-2827, July 2020, DOI: 10.1109/TITS.2019.2918642
2. [2] P. -C. Aubin-Frankowski and N. Petit, "Data-driven approximation of differential inclusions and application to detection of transportation modes," 2020 European Control Conference (ECC), St. Petersburg, Russia, 2020, pp. 1358-1364, DOI: 10.23919/ECC51009.2020.9143694
3. [3] R.A. Hasan, H. Irshaid, F. Alhomaidat, et al. Transportation Mode Detection by Using Smartphones and Smartwatches with Machine Learning. KSCE J Civ Eng 26, pp. 3578–3589, 2022, DOI:10.1007/s12205-022-1281-0
4. [4] “Geolife project webpage,” [Online]. Available : https://www.microsoft.com/en-us/research/project/geolife-building-social-networks-using-human-location-history/downloads, accessed: 2025-01-13.
5. [5] M.-C. Yu, T. Yu, S.-C. Wang, C.-J. Lin, and E. Y. Chang, “Big data small footprint: the design of a low-power classifier for detecting transportation modes,” Proceedings of the VLDB Endowment 7, no. 13, pp. 1429-1440, Aug. 2014. DOI: 10.14778/2733004.2733015
6. [6] L. Wang, H. Gjoreski, M. Ciliberto, S. Mekki, S. Valentin, and D. Roggen, “Enabling reproducible research in sensor-based transportation mode recognition with the sussex-huawei dataset,” IEEE Access, vol. 7, pp. 10870–10891, 2019, DOI: 10.1109/ACCESS.2019.2890793
7. [7] C. Carpineti, V. Lomonaco, L. Bedogni, M. D. Felice and L. Bononi, "Custom Dual Transportation Mode Detection By Smartphone Devices Exploiting Sensor Diversity," 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Athens, Greece, 2018, pp. 367-372, DOI: 10.1109/PERCOMW.2018.8480119
8. [8] Z. Li, G. Xiong, Z. Wei, Y. Lv, N. Anwar and F. -Y. Wang, "A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices," in IEEE Internet of Things Journal, vol. 9, no. 10, pp. 7842-7852, 15 May15, 2022, DOI: 10.1109/JIOT.2021.3115239

9. [9] P. Wang and Y. Jiang, “Transportation mode detection using temporal convolutional networks based on sensors integrated into smartphones,” Sensors, vol. 22, 2022, DOI: 10.3390/s22176712
10. [10] Y. Tian, D. Hettiarachchi, and S. Kamijo, “Transportation mode detection combining cnn and vision transformer with sensors recalibration using smartphone built-in sensors,” Sensors, vol. 22, no. 17, pp. 6453, 2022, DOI: 10.3390/s22176453
11. [11] X. Liu, “Glmlp-trans: A transportation mode detection model using lightweight sensors integrated in smartphones,” Computer Communications, vol. 194, pp. 156–166, 2022, DOI: 10.1016/j.comcom.2022.07.006
12. [12] Q. Tang, K. Jahan, and M. Roth, “Deep cnn-bilstm model for transportation mode detection using smartphone accelerometer and magnetometer,” in 2022 IEEE Intelligent Vehicles Symposium (IV), 2022, pp. 772–778, DOI : 10.1109/IV51971.2022.9827275
13. [13] P. Nirmal, I. Disanayaka, D. Haputhanthri and A. Wijayasiri, "Transportation Mode Detection Using Crowdsourced Smartphone Data," 2021 28th Conference of Open Innovations Association (FRUCT), Moscow, Russia, 2021, pp. 341-349, DOI: 10.23919/FRUCT50888.2021.9347625
14. [14] I. Drosouli, A. Voulodimos, G. Miaoulis, P. Mastorocostas, and D. Ghazanfarpour, "Transportation Mode Detection Using an Optimized Long Short-Term Memory Model on Multimodal Sensor Data" Entropy vol. 23, no. 11, pp. 1457, DOI: 10.3390/e23111457 [15] E. F. d. S. Soares, C. A. d. M. S. Quintella and C. A. V. Campos, "Smartphone-Based Real-Time Travel Mode Detection for Intelligent Transportation Systems," in IEEE Transactions on Vehicular Technology, vol. 70, no. 2, pp. 1179-1189, Feb. 2021, DOI: 10.1109/TVT.2021.3055413
15. [16] A. D. Antar, M. Ahmed, and M. A. R. Ahad, “Recognition of human locomotion on various transportations fusing smartphone sensors,” Pattern Recognition Letters, vol. 148, pp. 146–153, 2021, DOI:10.1016/j.patrec.2021.04.015
16. [17] S. Roy, Y. P. Singh, U. Biswas, D. S. Gurjar and T. Goel, "Machine Learning in Smart Transportation Systems for Mode Detection," 2021 IEEE 18th India Council International Conference (INDICON), Guwahati, India, 2021, pp. 1-6, DOI:10.1109/INDICON52576.2021.9691616
17. [18] J. Iskanderov and M. A. Guvensan, "Breaking the Limits of Transportation Mode Detection: Applying Deep Learning Approach With Knowledge-Based Features," in IEEE Sensors Journal, vol. 20, no. 21, pp. 12871-12884, 1 Nov.1, 2020, DOI: 10.1109/JSEN.2020.3001803
18. [19] X. Liang, Y. Zhang, G. Wang and S. Xu, "A Deep Learning Model for Transportation Mode Detection Based on Smartphone Sensing Data," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 12, pp. 5223-5235, Dec. 2020, DOI: 10.1109/TITS.2019.2951165
19. [20] O. Lorintiu and A. Vassilev, "Transportation mode recognition based on smartphone embedded sensors for carbon footprint estimation," 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 2016, pp. 1976-1981, DOI: 10.1109/ITSC.2016.7795875
20. [21] S. Taherinavid, S. V. Moravvej, Y. -L. Chen, J. Yang, C. S. Ku and P. L. Yee, "Automatic Transportation Mode Classification Using a Deep Reinforcement Learning Approach With Smartphone Sensors," in IEEE Access, vol. 12, pp. 514-533, 2024, DOI:10.1109/ACCESS.2023.3346875
21. [22] Q. Tang, H. Cheng, “Feature pyramid biLSTM: Using smartphone sensors for transportation mode detection,” Transportation Research Interdisciplinary Perspectives, vol. 26, pp. 101181, 2024, DOI:10.1016/j.trip.2024.101181.
22. [23] T. Fourez, N. Verstaevel, F. Migeon, F. Schettini, F. Amblard,“Transport Mode Detection on GNSS and accelerometer data: a temporality based workflow,” Transportation Research Procedia, Vol. 82, pp. 3454-3471, 2025, DOI:10.1016/j.trpro.2024.12.083.
23. [24] M. Merikhipour, S. Khanmohammadidoustani, M. Abbasi, “Transportation mode detection through spatial attention-based transductive long short-term memory and off-policy feature selection,” Expert Systems with Applications, vol. 267, pp. 126196, 2025, DOI:10.1016/j.eswa.2024.126196.
24. [25] G. C. Ibañez, L. J. de la Cruz Llopis, A. C. Diaconeasa, A. B. Guillén and M. Aguilar Igartua, "MobilitApp: A Deep Learning-Based Tool for Transport Mode Detection to Support Sustainable Urban Mobility," IEEE Access, vol. 13, pp. 68439-68461, 2025, DOI: 10.1109/ACCESS.2025.3561238.
25. [26] A. Karite and C. Gentner, "Real-Time Detection of Transport Modes and Movement States via Smartphone Data," 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS), Salt Lake City, UT, USA, 2025, pp. 1087-1094, DOI: 10.1109/PLANS61210.2025.11028195
26. [27] R. Li, X. Song, Y. Wu, X. Yu and H. Huang, "AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection," IEEE Access, vol. 13, pp. 63690-63702, 2025, DOI:10.1109/ACCESS.2025.3559417.
27. [28] P. Sadeghian, J. Hakansson, and X. Zhao, “Review and evaluation of methods in transport mode detection 25based on gps tracking data,” Journal of Traffic and Transportation Engineering, vol. 8, no. 4, pp. 467–482, 2021, DOI: 10.1016/j.jtte.2021.04.004
28. [29] P. Sadeghian, X. Zhao, A. Golshan, and J. H˚akansson, “A stepwise methodology for transport mode detection in gps tracking data,” Travel Behaviour and Society, vol. 26, pp. 159–167, 2022, DOI: 10.1016/j.tbs.2021.10.004
29. [30] I. Drosouli, A. Voulodimos, and G. Miaoulis, “Transportation mode detection using machine learning techniques on mobile phone sensor data,” in 2020 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments (PETRA), 2020, pp. 1–8., DOI: 10.1145/3389189.3397996
30. [31] A. Efthymiou, E. N. Barmpounakis, D. Efthymiou, and E. I. Vlahogianni, “Transportation mode detection from low-power smartphone sensors using tree-based ensembles,” Journal of Big Data Analytics in Transportation, vol. 1, no. 1, pp. 57–69, Jun 2019, DOI: 10.1007/s42421-019-00004-w
31. [32] P. Wang and Y. Jiang, “Transportation mode detection using temporal convolutional networks based on sensors integrated into smartphones,” Sensors, vol. 22, no. 17, pp. 6712, 2022, DOI: 10.3390/s22176712
32. [33] N. Hnoohom, N. Maitrichit, S. Mekruksavanich and A. Jitpattanakul, "A Deep Residual Network for Recognizing Transportation Vehicles using Smartphone Sensors," 2022 IEEE 13th International Conference on Software Engineering and Service Science (ICSESS), Beijing, China, 2022, pp. 209-213, DOI: 10.1109/ICSESS54813.2022.9930314
33. [34] E. Aslan, Y. Özüpak, F. Alpsalaz and Z. M. S. Elbarbary, "A Hybrid Machine Learning Approach for Predicting Power Transformer Failures Using Internet of Things-Based Monitoring and Explainable Artificial Intelligence," in IEEE Access, vol. 13, pp. 113618-113633, 2025, DOI: 10.1109/ACCESS.2025.3583773