ELEKTRİKLİ SCOOTER (E-SCOOTER) SÜRÜCÜLERİNİN SÜRÜŞ SÜRESİNİN MAKİNE ÖĞRENMESİ İLE TAHMİNİ

Öz

Bu çalışma, elektrikli scooter araçlarını tercih eden sürücülerin sürüş sürelerinin tahmin edilmesini amaçlamaktadır. E-scooter'lar genel olarak daha küçük boyutları ve manevra kabiliyetleri sayesinde şehir içi yolculuklarda hızlı ilerleme sağlayabildikleri için trafik sıkışıklığından kaynaklanan zaman kaybını azaltmaktadır. E-scooter'lar daha kompakt yapıları sayesinde park yeri bulma ve kolay park etme konusunda da avantaj sağlıyor. Bu çalışmada e-scooter araçlarını tercih eden sürücülerin sürüş sürelerinin tahmin edilmesi amacıyla ML algoritmaları kullanılmıştır. AB modeli, düşük Ortalama Kareler Hata (MSE) değeriyle (0,005) iyi performans gösterdi. Ortalama Karekök Hata (RMSE) ve Ortalama Mutlak Hata (MAE) değerleri de nispeten düşüktür (sırasıyla 0,069 ve 0,039), bu da modelin tahminlerinin gerçek değerlere yakın olduğunu göstermektedir.Ayrıca R-kare Belirleme Katsayısı (R2) değerinin (0,947) yüksek olması, bu modelin verileri oldukça iyi açıkladığını ve tahminlerinin gerçek değerlere yüksek doğrulukla yaklaştığını göstermektedir.Öte yandan GB algoritması, yüksek hata payı ve düşük doğruluk oranıyla farklı algoritmalara göre zayıf performans gösterdi. Bu sonuçlar, sürücünün e-scooter ile yapacağı yolculuk süresini tahmin ederek zaman yönetiminde avantaj sağlıyor. Sonuç olarak e-scooter'lar sürücülere zamandan tasarruf etme ve günlük hareketliliklerini daha etkin yönetme fırsatı sunarak bu araçları ulaşım açısından cazip hale getiriyor.

Anahtar Kelimeler

• E-scooter
• zaman yönetimi
• makine öğrenimi
• tahmin

PREDICTION OF DRIVING TIME OF ELECTRIC SCOOTER (E-SCOOTER) DRIVERS BY MACHINE LEARNING

Öz

This study aims to estimate the driving times of drivers who prefer electric scooter vehicles. In general, e-scooters reduce the loss of time caused by traffic jams because, thanks to their smaller size and maneuverability, these vehicles provide rapid progress in urban journeys. E-scooters also offer an advantage in finding a parking space and easy parking thanks to their more compact structure. In this study, ML algorithms were used to predict the driving times of drivers who prefer e-scooter vehicles. The AB model has performed well with a low Mean Square Error (MSE) value (0.005). The Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values are also relatively low (0.069 and 0.039, respectively), indicating that the model's predictions are close to the actual values. Also, the high R-squared-Coefficient of Determination (R2) value (0.947) suggests that this model explains the data quite well, and its predictions approach the actual values with high accuracy. On the other hand, the GB algorithm performed poorly compared to different algorithms, with its high margin of error and low accuracy rate. These results provide an advantage in time management by estimating the travel time a driver will make with the e-scooter. As a result, e-scooters offer drivers the opportunity to save time and manage their daily mobility more effectively, driving these vehicles attractive for transportation.

Anahtar Kelimeler

• E-scooter
• time management
• machine learning
• prediction

Kaynakça

1. Akter, S., Michael, K., Uddin, M. R., McCarthy, G., & Rahman, M. (2022). Transforming business using digital innovations: The application of AI, blockchain, cloud and data analytics. Annals of Operations Research, 1-33.
2. Arslan, E., & Uyulan, Ç. (2023). Analysis of an e-scooter and rider system dynamic response to curb traversing through physics-informed machine learning methods. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 237(7), 1555-1571.
3. Atalan, A. (2023, May). Neural network and random forest algorithms for estimation of the waiting times based on the DES in ED. In International Conference on Contemporary Academic Research,1(1), 14-20.
4. Atalan, A. (2023). Forecasting drinking milk price based on economic, social, and environmental factors using machine learning algorithms. Agribusiness, 39(1), 214-241.
5. Atalan, A., & Atalan, Y. A. (2022). Analysis of the impact of air transportation on the spread of the covid-19 pandemic. In Challenges and Opportunities for Transportation Services in the Post-COVID-19 Era (pp. 68-87). IGI Global.
6. Atalan, A., Dönmez, C. Ç., & Atalan, Y. A. (2018). Yüksek-eğitimli uzman hemşire istihdamı ile acil servis kalitesinin yükseltilmesi için simülasyon uygulaması: Türkiye sağlık sistemi. Marmara Fen Bilimleri Dergisi, 30(4), 318-338.
7. Atalan, A., Şahin, H., & Atalan, Y. A. (2022, September). Integration of machine learning algorithms and discrete-event simulation for the cost of healthcare resources. In Healthcare (Vol. 10, No. 10, p. 1920). MDPI.
8. Ayözen, Y. E., İnaç, H., Atalan, A., & Dönmez, C. Ç. (2022). E-Scooter micro-mobility application for postal service: the case of turkey for energy, environment, and economy perspectives. Energies, 15(20), 7587.

9. Boukerche, A., & Wang, J. (2020). Machine learning-based traffic prediction models for intelligent transportation systems. Computer Networks, 181, 107530.
10. Bretones, A., Marquet, O., Daher, C., Hidalgo, L., Nieuwenhuijsen, M., Miralles-Guasch, C., & Mueller, N. (2023). Public health-led insights on electric micro-mobility adoption and use: a scoping review. Journal of Urban Health, 1-15.
11. Capetillo, A., & Ibarra, F. (2017). Multiphase injector modelling for automotive SCR systems: A full factorial design of experiment and optimization. Computers & Mathematics with Applications, 74(1), 188-200.Flores, P.
12. J., & Jansson, J. (2021). The role of consumer innovativeness and green perceptions on green innovation use: The case of shared e‐bikes and e‐scooters. Journal of Consumer Behaviour, 20(6), 1466-1479.
13. Chen, X. M., Zahiri, M., & Zhang, S. (2017). Understanding ridesplitting behavior of on-demand ride services: An ensemble learning approach. Transportation Research Part C: Emerging Technologies, 76, 51–70.
14. Das, S., Hossain, A., Rahman, M. A., Sheykhfard, A., & Kutela, B. (2023). Case study on the traffic collision patterns of e-scooter riders. Transportation Research Record, 03611981231185770.
15. Dönmez, C. Ç., & Atalan, A. (2019). Developing statistical optimization models for urban competitiveness index: under the boundaries of econophysics approach. Complexity, 2019, 1-11.
16. Fietz, L. E. (2020). Predicting hourly shared e-scooter use in chicago: a machine learning approach (Doctoral dissertation, University of Oregon).
17. Fishman, E., & Cherry, C. (2016). E-bikes in the Mainstream: Reviewing a Decade of Research. Transport reviews, 36(1), 72-91.
18. Fuentes, S., Gonzalez Viejo, C., Cullen, B., Tongson, E., Chauhan, S. S., & Dunshea, F. R. (2020). Artificial intelligence applied to a robotic dairy farm to model milk productivity and quality based on cow data and daily environmental parameters. Sensors, 20(10), 2975.
19. Gössling, S. (2020). Integrating e-scooters in urban transportation: Problems, policies, and the prospect of system change. Transportation Research Part D: Transport and Environment, 79, 102230.
20. Haworth, N., Schramm, A., & Twisk, D. (2021). Comparing the risky behaviors of shared and private e-scooter and bicycle riders in downtown Brisbane, Australia. Accident Analysis & Prevention, 152, 105981.
21. Horton, J. J., & Zeckhauser, R. J. (2016). Owning, using and renting: some simple economics of the" sharing economy". National Bureau of Economic Research. (No. w22029).
22. Ignaccolo, M., Inturri, G., Cocuzza, E., Giuffrida, N., Le Pira, M., & Torrisi, V. (2022). Developing micromobility in urban areas: network planning criteria for e-scooters and electric micromobility devices. Transportation research procedia, 60, 448-455.
23. İnaç, H. (2023). Micro-mobility sharing system accident case analysis by statistical machine learning algorithms. Sustainability, 15(3), 2097.
24. İnaç, H., Ayözen, Y. E., Atalan, A., & Dönmez, C. Ç. (2022). Estimation of postal service delivery time and energy cost with e-scooter by machine learning algorithms. Applied Sciences, 12(23), 12266.
25. Inglesi-Lotz, R. (2016). The impact of renewable energy consumption to economic growth: A panel data application. Energy economics, 53, 58-63.
26. James, O., Swiderski, J. I., Hicks, J., Teoman, D., & Buehler, R. (2019). Pedestrians and e-scooters: An initial look at e-scooter parking and perceptions by riders and non-riders. Sustainability, 11(20), 5591.
27. Khan, P. W., Byun, Y. C., Lee, S. J., Kang, D. H., Kang, J. Y., & Park, H. S. (2020). Machine learning-based approach to predict energy consumption of renewable and nonrenewable power sources. Energies, 13(18), 4870.
28. Li, K., Zhou, G., Zhai, J., Li, F., & Shao, M. (2019). Improved PSO_AdaBoost ensemble algorithm for imbalanced data. Sensors, 19(6), 1476.
29. Li, Y., Zou, C., Berecibar, M., Nanini-Maury, E., Chan, J. C. W., Van den Bossche, P., ... & Omar, N. (2018). Random forest regression for online capacity estimation of lithium-ion batteries. Applied energy, 232, 197-210.
30. Moosavi, S. M. H., Ma, Z., Armaghani, D. J., Aghaabbasi, M., Ganggayah, M. D., Wah, Y. C., & Ulrikh, D. V. (2022). Understanding and predicting the usage of shared electric scooter services on university campuses. Applied Sciences, 12(18), 9392.
31. Nakagawa, S., & Cuthill, I. C. (2007). Effect size, confidence interval and statistical significance: a practical guide for biologists. Biological Reviews, 82(4), 591–605. https://doi.org/10.1111/j.1469-185X.2007.00027.
32. Nawaro, Ł. (2021). E-scooters: competition with shared bicycles and relationship to public transport. International Journal of Urban Sustainable Development, 13(3), 614-630.
33. Nocerino, R., Colorni, A., Lia, F., & Lue, A. (2016). E-bikes and E-scooters for smart logistics: environmental and economic sustainability in pro-E-bike Italian pilots. Transportation research procedia, 14, 2362-2371.
34. Park, J. G., Jun, H. B., & Heo, T. Y. (2021). Retraining prior state performances of anaerobic digestion improves prediction accuracy of methane yield in various machine learning models. Applied Energy, 298, 117250.
35. Pazzini, M., Cameli, L., Lantieri, C., Vignali, V., Dondi, G., & Jonsson, T. (2022). New micromobility means of transport: An analysis of e-scooter users’ behaviour in Trondheim. International journal of environmental research and public health, 19(12), 7374.
36. Peng, H., Nishiyama, Y., & Sezaki, K. (2022). Assessing environmental benefits from shared micromobility systems using machine learning algorithms and Monte Carlo simulation. Sustainable Cities and Society, 87, 104207.
37. Prabu, A., Shen, D., Tian, R., Chien, S., Li, L., Chen, Y., & Sherony, R. (2022). A wearable data collection system for studying micro-level e-scooter behavior in naturalistic road environment. arXiv preprint arXiv:2212.11979. Sagi, O., & Rokach, L. (2018). Ensemble learning: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), e1249.
38. Schwendicke, F. A., Samek, W., & Krois, J. (2020). Artificial intelligence in dentistry: chances and challenges. Journal of dental research, 99(7), 769-774.
39. Sharma, N., Sharma, R., & Jindal, N. (2021). Machine learning and deep learning applications-a vision. Global Transitions Proceedings, 2(1), 24-28.
40. Sun, B., Garikapati, V., Wilson, A., & Duvall, A. (2021). Estimating energy bounds for adoption of shared micromobility. Transportation Research Part D: Transport and Environment, 100, 103012.
41. Teusch, J., Gremmel, J. N., Koetsier, C., Johora, F. T., Sester, M., Woisetschläger, D. M., & Müller, J. P. (2023). A Systematic Literature Review on Machine Learning in Shared Mobility. IEEE Open Journal of Intelligent Transportation Systems, 4, 870–899.
42. Thackeray, M. M., Wolverton, C., & Isaacs, E. D. (2012). Electrical energy storage for transportation—approaching the limits of, and going beyond, lithium-ion batteries. Energy & Environmental Science, 5(7), 7854-7863.
43. Tuncer, S., & Brown, B. (2020, April). E-scooters on the ground: Lessons for redesigning urban micro-mobility. In Proceedings of the 2020 CHI conference on human factors in computing systems (pp. 1-14).
44. Turoń, K., & Czech, P. (2020). The concept of rules and recommendations for riding shared and private e-scooters in the road network in the light of global problems. In Modern Traffic Engineering in the System Approach to the Development of Traffic Networks: 16th Scientific and Technical Conference" Transport Systems. Theory and Practice 2019" Selected Papers 16 (pp. 275-284). Springer International Publishing.
45. Vinagre Díaz, J. J., Fernández Pozo, R., Rodríguez González, A. B., Wilby, M. R., & Anvari, B. (2023). Blind classification of e-scooter trips according to their relationship with public transport. Transportation, 1-22.
46. Wan, S., & Yang, H. (2013, July). Comparison among methods of ensemble learning. In 2013 International Symposium on Biometrics and Security Technologies (pp. 286-290). IEEE.
47. Zhang, C., Zhang, Y., Shi, X., Almpanidis, G., Fan, G., & Shen, X. (2019). On incremental learning for gradient boosting decision trees. Neural Processing Letters, 50, 957-987.
48. Zhao, P., Li, A., Pilesjö, P., & Mansourian, A. (2022). A machine learning based approach for predicting usage efficiency of shared e-scooters using vehicle availability data. AGILE: GIScience Series, 3, 20.
49. Zhong, S., Zhang, K., Bagheri, M., Burken, J. G., Gu, A., Li, B., ... & Zhang, H. (2021). Machine learning: new ideas and tools in environmental science and engineering. Environmental Science & Technology, 55(19), 12741-12754.
50. Zhou, X., Tian, S., An, J., Yang, J., Zhou, Y., Yan, D., ... & Jin, X. (2021). Comparison of different machine learning algorithms for predicting air-conditioning operating behavior in open-plan offices. Energy and Buildings, 251, 111347.
51. Zuniga-Garcia, N., Tec, M., Scott, J. G., & Machemehl, R. B. (2022). Evaluation of e-scooters as transit last-mile solution. Transportation research part C: emerging technologies, 139, 103660.