# Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing

^{*}

^{†}

## Abstract

**:**

## 1. Introduction

## 2. Related Work

## 3. Hierarchical Agglomerative Clustering Based on Ultra-Light Edge Computing Algorithm

#### 3.1. IoSB Architecture

#### 3.2. Problem Statement

#### 3.3. Ultra-Light Edge Computing Algorithm

- $-1$:
- indicates a negative net arrival, i.e., the number of bicycles that have been returned is lower than the number of bicycles that have been picked up; in this case, the docking station is empting;
- $\phantom{+}0$:
- indicates that the number of deposits compensate the number of withdrawals, thus resulting in a constant occupancy value during time interval t;
- $+1$:
- indicates a positive net arrival, i.e., the number of bicycles that have been returned is higher than the number of bicycles that have been picked up; in this case, the docking station is filling up.

#### 3.4. Hierarchical Agglomerative Clustering

## 4. Results

#### 4.1. Dataset

- Time stamp: it showed the moment when the bicycle was picked up; every time stamp was set with 1 hour definition for privacy and anonymity issues.
- User’s identifier: it was an encrypted identifier which was unique per user and day in order to preserve the privacy of the user.
- Type of user: annual, eventual, staff.
- User’s range of age: it provided six age intervals [0,16], [17,18], [19–26], [27–40], [41–65], [66,∞), and unknown.
- Identifier of the origin docking station.
- Identifier of the destination docking station.
- Travel time: time elapsed between the withdrawal and deposit of the bicycle.
- Track: sequence of geographical coordinates travelled by the bicycle, updated every minute (this information was not always available).

#### 4.2. Dendograms

#### 4.3. Analysis with Two Clusters

#### 4.4. Analysis with 11 Clusters

## 5. Conclusions and Future Research

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Xu, T.; Han, G.; Qi, X.; Du, J.; Lin, C.; Shu, L. A Hybrid Machine Learning Model for Demand Prediction of Edge-Computing based Bike Sharing System Using Internet of Things. IEEE Internet Things J.
**2020**, in press. [Google Scholar] [CrossRef] - Krizek, K.J.; Sharmeen, F.; Martens, K. JTLU special issue editorial: Bicycling in changing urban regions. J. Transp. Land Use
**2018**, 11, 805–810. [Google Scholar] [CrossRef][Green Version] - Frade, I.; Ribeiro, A. Bike-sharing stations: A maximal covering location approach. Transp. Res. Part. A Policy Pract.
**2015**, 82, 216–227. [Google Scholar] [CrossRef] - Lin, J.R.; Yang, T.H.; Chang, Y.C. A hub location inventory model for bicycle sharing system design: Formulation and solution. Comput. Ind. Eng.
**2013**, 65, 77–86. [Google Scholar] [CrossRef] - Dell’Amico, M.; Hadjicostantinou, E.; Iori, M.; Novellani, S. The bike sharing rebalancing problem: Mathematical formulations and benchmark instances. Omega
**2014**, 45, 7–19. [Google Scholar] [CrossRef] - Winslow, J.; Mont, O. Bicycle Sharing Sustainable Value Creation and Institutionalisation Strategies in Barcelona. Sustainability
**2019**, 11, 728. [Google Scholar] [CrossRef][Green Version] - Elen, B.; Peters, J.; Van Poppel, M.; Bleux, N.; Theunis, J.; Reggente, M.; Standaert, A. The Aeroflex: A Bicycle for Mobile Air Quality Measurements. Sensors
**2013**, 13, 221–240. [Google Scholar] [CrossRef] - Guo, H.; Liu, J.; Zhang, J.; Sun, W.; Kato, N. Mobile-Edge Computation Offloading for Ultradense IoT Networks. IEEE Internet Things J.
**2018**, 5, 4977–4988. [Google Scholar] [CrossRef] - Del-Valle-Soto, C.; Mex-Perera, C.; Nolazco-Flores, J.A.; Velázquez, R.; Rossa-Sierra, A. Wireless Sensor Network Energy Model and Its Use in the Optimization of Routing Protocols. Energies
**2020**, 13, 728. [Google Scholar] [CrossRef][Green Version] - Gharghan, S.; Nordin, R.; Ismail, M. Energy-Efficient ZigBee-Based Wireless Sensor Network for Track Bicycle Performance Monitoring. Sensors
**2014**, 14, 15573–15592. [Google Scholar] [CrossRef] - De la Iglesia, D.H.; Villarrubia, G.; Paz, J.D.; Bajo, J. Multi-Sensor Information Fusion for Optimizing Electric Bicycle Routes Using a Swarm Intelligence Algorithm. Sensors
**2017**, 17, 2501. [Google Scholar] [CrossRef] [PubMed][Green Version] - Shen, S.; Wei, Z.Q.; Sun, L.J.; Su, Y.Q.; Wang, R.C.; Jiang, H.M. The Shared Bicycle and Its Network—Internet of Shared Bicycle (IoSB): A Review and Survey. Sensors
**2018**, 18, 2581. [Google Scholar] [CrossRef] [PubMed][Green Version] - Zhang, Y.; Ma, X.; Zhang, J.; Hossain, M.S.; Muhammad, G.; Amin, S.U. Edge Intelligence in the Cognitive Internet of Things: Improving Sensitivity and Interactivity. IEEE Network
**2019**, 33, 58–64. [Google Scholar] [CrossRef] - Chiariotti, F.; Pielli, C.; Zanella, A.; Zorzi, M. A Dynamic Approach to Rebalancing Bike-Sharing Systems. Sensors
**2018**, 18, 512. [Google Scholar] [CrossRef][Green Version] - Mellou, K.; Jaillet, P. Dynamic Resource Redistribution and Demand Estimation: An Application to Bike Sharing Systems. SSRN Electron. J.
**2019**, 1–58. [Google Scholar] [CrossRef][Green Version] - Forma, I.A.; Raviv, T.; Tzur, M. A 3-step math heuristic for the static repositioning problem in bike-sharing systems. Transp. Res. Part B: Methodological
**2015**, 71, 230–247. [Google Scholar] [CrossRef] - Li, Y.; Zheng, Y. Citywide Bike Usage Prediction in a Bike-Sharing System. IEEE Trans. Knowl. Data Eng.
**2020**, 32, 1079–1091. [Google Scholar] [CrossRef] - Vogel, P.; Greiser, T.; Mattfeld, D.C. Understanding Bike-Sharing Systems using Data Mining: Exploring Activity Patterns. Procedia-Soc. Behav. Sci.
**2011**, 20, 514–523. [Google Scholar] [CrossRef][Green Version] - Froehlich, J.; Neumann, J.; Oliver, N. Measuring the pulse of the city through Shared Bicycle Programs. In Proceedings of the InternationalWorkshop on Urban, Community, and Social Applications of Networked Sensing Systems, Raleigh, NC, USA, 4 November 2008; pp. 16–20. [Google Scholar]
- Etienne, C.; Latifa, O. Model-based count series clustering for Bike Sharing System usage mining: A case study with the Vélib’ system of Paris. ACM Trans. Intell. Syst. Technol.
**2014**, 5, 1–21. [Google Scholar] [CrossRef] - Feng, S.; Chen, H.; Du, C.; Li, J.; Jing, N. A Hierarchical Demand Prediction Method with Station Clustering for Bike Sharing System. In Proceedings of the 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), Guangzhou, China, 18–21 June 2018; pp. 829–836. [Google Scholar]
- Almannaa, M.H.; Elhenawy, M.; Rakha, H.A. A novel supervised clustering algorithm for transportation system applications. IEEE Trans. Intell. Transp. Syst.
**2020**, 21, 222–232. [Google Scholar] [CrossRef] - Lin, L.; He, Z.; Peeta, S. Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach. Transp. Res. Part C: Emerg. Technol.
**2018**, 97, 258–276. [Google Scholar] [CrossRef][Green Version] - Ghosh, S.; Varakantham, P.; Adulyasak, Y.; Jaillet, P. Dynamic repositioning to reduce lost demand in Bike Sharing Systems. J. Artif. Intell. Res.
**2017**, 58, 387–430. [Google Scholar] [CrossRef] - Scherrer, L.; Tomko, M.; Ranacher, P.; Weibel, R. Travelers or locals? Identifying meaningful sub-populations from human movement data in the absence of ground truth. EPJ Data Sci.
**2018**, 7, 19. [Google Scholar] [CrossRef] - Médard de Chardon, C.; Caruso, G.; Thomas, I. Bicycle sharing system ‘success’ determinants. Transp. Res. Part A Policy Pract.
**2017**, 100, 202–214. [Google Scholar]

**Figure 1.**Dendrogram (binary tree). Groups numbered from left to right: g#1 (dark blue), 28 stations; g#2 (red), 5 stations; g#3 (orange), 19 stations; g#4 (purple), 26 stations; g#5 (dark green), 3 stations; g#6 (light blue), 7 stations; g#7 (garnet), 16 stations; g#8 (light pink), 33 stations; g#9 (gold yellow), 22 stations; g#10 (light green), 6 stations; g#11 (dark pink), 4 stations.

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Vinagre Díaz, J.J.; Fernández Pozo, R.; Rodríguez González, A.B.; Wilby, M.R.; Sánchez Ávila, C. Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing. *Sensors* **2020**, *20*, 3550.
https://doi.org/10.3390/s20123550

**AMA Style**

Vinagre Díaz JJ, Fernández Pozo R, Rodríguez González AB, Wilby MR, Sánchez Ávila C. Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing. *Sensors*. 2020; 20(12):3550.
https://doi.org/10.3390/s20123550

**Chicago/Turabian Style**

Vinagre Díaz, Juan José, Rubén Fernández Pozo, Ana Belén Rodríguez González, Mark R. Wilby, and Carmen Sánchez Ávila. 2020. "Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing" *Sensors* 20, no. 12: 3550.
https://doi.org/10.3390/s20123550