JAPONYA'DA SÜRDÜRÜLEBİLİR LOJİSTİK İÇİN MAKİNE ÖĞRENİMİ İLE YÜKSEK KAPASİTELİ ARAÇLARIN VERİ ANALİZİ

Öz

Son yıllarda, Japon lojistik endüstrisi yük taşımacılığı talebinde bir artış ve ciddi bir kamyon sürücüsü sıkıntısı ile karşı karşıyadır. İşgücü sorunlarını çözmek ve sürdürülebilir lojistik için verimliliği artırmak için, uzunluğu 21 metreden fazla olan çift römorklu kamyonlar tanıtıldı. Bunlara daha uzun ve ağır araçlar (LHV) veya yüksek kapasiteli araçlar (HCV) denir. Bu çalışmada makine öğrenimi ve coğrafi bilgi sisteminde k-ortalama kümeleme algoritması uygulanarak yüksek kapasiteli araçların sürüş özellikleri çalışılacaktır. Bu çalışmada kullanılan veriler, Kara, Altyapı, Ulaştırma ve Turizm Bakanlığı tarafından yürütülen Ekim 2017 ile Temmuz 2018 tarihleri arasındaki deneysel koşulardan elde edilmiştir. K- ortalama kümeleme algoritması uygulanmadan önce, en uygun küme sayısını bulmak için dirsek yöntemi uygulanır ve verilerin ne kadar iyi kümelendiğini gösteren kümelerin kalitesini değerlendirmek için siluet katsayısı hesaplanır. K-means kümeleme ile veriler farklı kümeler halinde gruplandırilir. Elde edilen kümeler coğrafi bilgi sisteminde görselleştirilir. Kümeler incelenir ve kamyonların sürüş özelliklerinin her kümede nasıl farklılık gösterir ve özelliklerin birbirleriyle nasıl ilişkili olduğu karşılaştırılır. Bu çalışma, yolculuk boyunca kalp atış hızlarına ve dalgalanmalara odaklanmıştır. Yüksek kalp atış hızlarının aykırı değerleri ve ilişkili özellikler, nasıl meydana geldiği ve sürücülerin hangi alanlarda strese maruz kalabileceği tespit edilir. Lojistik tesislerin yakınında kaydedilen sürücülerin kalp atış hızlarının karşılaştırılmasına vurgu yapılır. Anahtar kelimeler: yüksek kapasiteli araçlar, k-kümeleme, kalp atış hızı, kamyon hızı

Anahtar Kelimeler

• yüksek kapasiteli araçlar
• k-kümeleme
• kalp atış hızı
• kamyon hızı

DATA ANALYSIS OF HIGH CAPACITY VEHICLES BY MACHINE LEARNING FOR SUSTAINABLE LOGISTICS IN JAPAN

Öz

In recent years, the Japanese logistics industry has been facing an increase in freight transportation demand and a serious shortage of truck drivers. To address the labor problems and improve efficiency for sustainable logistics, trucks with double trailers whose length is over 21 meters were introduced. They are called longer and heavier vehicles (LHV) or high capacity vehicles (HCV). In this study, the driving characteristics of the high capacity vehicles will be studied by applying k-means clustering algorithm in machine learning and geographic information system. The data used in this study were obtained from the experimental runs between October 2017 and July 2018, conducted by the Ministry of Land, Infrastructure, Transport and Tourism. Before k-means clustering algorithm is applied, the elbow method is applied to find the optimal number of clusters and the silhouette coefficient is calculated to evaluate the quality of clusters which indicates how well the data are clustered. By k-means clustering, the data are grouped into different clusters. The resultant clusters are visualized in the geographic information system. The clusters are studied and compared how the driving characteristics of the trucks differ in each cluster and how the characteristics correlate to each other. This study is focused on the heart rates and the fluctuations throughout the trip. The outliers of high heart rates and the associated characteristics are identified how they occur and in which areas the drivers can suffer stress. The emphasis is given to the comparison of the drivers’ heart rates recorded near the logistics facilities.

Anahtar Kelimeler

• high capacity vehicles
• k-means clustering
• heart rate
• truck speed

Kaynakça

1. Bhardwaj, A. (2020). Silhouette Coefficient Validating clustering techniques. available at https://towardsdatascience.com/silhouette-coefficient-validating-clustering-techniques-e976bb81d10c# (accessed 30 May 2021).
2. Dabbura, I. (2018). K-means Clustering: Algorithm, Applications, Evaluation Methods, and Drawbacks. available at https://towardsdatascience.com/k-means-clustering-algorithm-applications-evaluation-methods-and-drawbacks-aa03e644b48a (accessed 27 May 2021).
3. Gupta, K. (2019). Data Science with Jupyter, BPB Publications, India.
4. International Transport Forum. (2017a). Data-Led Governance of Road Freight Transport: Improving Compliance, OECD Publishing, Paris.
5. International Transport Forum. (2017b). ITF Transport Outlook 2017, OECD Publishing, Paris. available at http://dx.doi.org/10.1787/9789282108000-en.
6. International Transport Forum. (2019a). High Capacity Transport: Towards Efficient, Safe and Sustainable Road Freight, International Transport Forum Policy Papers, No. 69, OECD Publishing, Paris.
7. International Transport Forum. (2019b). ITF Transport Outlook 2019, OECD Publishing, Paris.
8. Japan Automobile Manufacturer Association. (2020). Japanese Automobile Industry. available at https://www.jama.or.jp/industry/ [in Japanese] (accessed 2 June 2021) Ministry of Land, Infrastructure, Transport and Tourism (2018). Experiments of Double Connected Trucks. available at

9. https://www.mlit.go.jp/road/double_renketsu_truck/jiken.html [in Japanese] (accessed 5 June 2021).
10. Nemoto, T. (2021). An opportunity for industry reform with the corona disaster. Interview in The Future of Logistics in the Eyes of Robots, 29_c_1, Published 25 May 2021. available at https://www.magazine.mlit.go.jp/interview/vol29-c-1/ [in Japanese] (accessed 1 June 2021).
11. OECD (2011). Moving Freight with Better Trucks: Improving Safety, Productivity and Sustainability, OECD Publishing, Paris.
12. Prasad, A. (2020). K-Means Clustering Explained. available at https://medium.com/analytics-vidhya/k-means-clustering-explained-419ee66d095e (accessed 30 May 2021)
13. Soma, D. and Hyodo, T. (2020). A Study on The Driving Characteristics and The Driver Stress of Longer and Heavier Vehicle. Journal of Japan Society of Traffic Engineers, 6(2), A_23-A_30 [in Japanese].
14. Statistics Bureau. (2021). Japan Statistical Yearbook 2021. Ministry of Internal Affairs and Communications, Japan.
15. Watanabe, D. and Hyodo, T. (2021). Data Analysis on the Driving Characteristics of High Capacity Vehicles on Highway in Japan using Geographic Information System. Journal of Japan Logistics Society, 29 (in press) [in Japanese].
16. Watanabe, D., Kenmochi, T., Sasa, K. and Hyodo, T. (2021). Current Situations on High Capacity Transport And Truck Platooning in Japan, Proceedings of 16th International Symposium on Heavy Vehicle Transport & Technology (HVTT16), Qingdao, China, September, 2021 (accepted).