A Hybrid Machine Learning Model for Demand Prediction of Edge-Computing-Based Bike-Sharing System Using Internet of Things

Xu, Tiantian; Han, Guangjie; Qi, Xingyue; Du, Jian Hua; Lin, Chuan; Shu, Lei

doi:10.1109/jiot.2020.2983089

Cited by 52 publications

(26 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Under our perspective, a docking station is represented as an object into the IoSB hierarchy [ 12 ], with functionalities within the perception and physical layers, which uses the communication layer to transmit the relevant information to the upper processing levels. This approach also matches the edge-computing architecture proposed in [ 1 ], where the BSS is decomposed into site, BSS Server, and BSS cloud center.…”

Section: Hierarchical Agglomerative Clustering Based On Ultra-lighmentioning

confidence: 73%

“…This way, we could move this calculation to the edge, alleviating the data load on the communications channel to the central or cloud server. Following this approach, the authors in [ 1 ] designed an IoSB architecture for a BSS system, which includes three basic layers: the site, the BSS server, and the BSS cloud centre. They proposed a clustering algorithm based on self-organizing regression to be performed in the edge (site).…”

Section: Related Workmentioning

confidence: 99%

“…Its cooperative nature adds a novelty factor that follows the new economy paradigm that many cities worldwide are establishing in every domain, transport included. At present, we can find more than 500 BSSs around the world [ 1 ]. This evident success has also extended to the academic field, where the number of scientific papers has rapidly increased in the past 5 years [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Díaz

Pozo

González

et al. 2020

Sensors

View full text Add to dashboard Cite

Bicycle sharing systems (BSSs) have established a new shared-economy mobility model. After a rapid growth they are evolving into a fully-functional mobile sensor platform for cities. The viability of BSSs is floored by their operational costs, mainly due to rebalancing operations. Rebalancing implies transporting bicycles to and from docking stations in order to guarantee the service. Rebalancing performs clustering to group docking stations by behaviour and proximity. In this paper we propose a Hierarchical Agglomerative Clustering based on an Ultra-Light Edge Computing Algorithm (HAC-ULECA). We eliminate the proximity and let Hierarchical Agglomerative Clustering (HAC) focus on behaviour. Behaviour is represented by ULECA as an activity profile based on the net flow of arrivals and departures in a docking station. This drastically reduces the computing requirements which allows ULECA to run as an edge computing functionality embedded into the physical layer of the Internet of Shared Bikes (IoSB) architecture. We have applied HAC-ULECA to real data from BiciMAD, the public BSS in Madrid (Spain). Our results, presented as dendograms, graphs, geographical maps, and colour maps, show that HAC-ULECA is capable of separating behaviour profiles related to business and residential areas and extracting meaningful spatio-temporal information about the BSS and the city’s mobility.

show abstract

Section: Hierarchical Agglomerative Clustering Based On Ultra-lighmentioning

confidence: 73%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Díaz

Pozo

González

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Para garantir o bom funcionamento de um Sistema de Compartilhamento de Bicicletas é essencial redistribuir as bicicletas, repor o número de bicicletas em determinadas estação de acordo com a demanda [Liu et al, 2016]. No entanto, a demanda de bicicletas em cada estação de aluguel muda com frequência e esse é um problema desafiador [Xu et al, 2020]. Abordagens baseadas somente no monitoramento em tempo real podem não ser eficientes, já que leva tempo redistribuir as bicicletas quando ocorre um desequilíbrio.…”

Section: As Informações Coletadas Pelos Sistemas De Bicicletas Compartilhadasunclassified

Modelos De Aprendizagem De Máquina Para a Gestão Estratégica De Bicicletas Compartilhadas / Machine Learning Models for Shared Bicycle Strategic Management

Viana

Gurgel

Silva

et al. 2021

BJD

View full text Add to dashboard Cite

RESUMOOs Sistemas de Bicicletas Compartilhadas são cada vez mais comuns nas cidades, evidenciando a relevância de abordagens que auxiliem na tomada de decisão e gestão estratégica das empresas responsáveis por esses sistemas. Neste trabalho, é apresentado uma versão estendida de um estudo de caso no sistema Capital BikeShare (Washington, D.C.) com o objetivo de realizar uma análise estatística para identificar a relação entre o clima e o serviço de aluguel de bicicletas, além de aplicar algoritmos de aprendizagem de máquina para classificar a quantidade de aluguéis. Como adicional desta versão, apresenta-se uma abordagem de agrupamentos das estações de aluguéis, que resultou em uma acurácia de 94,7%, maior do que a obtida anteriormente. Os resultados apresentados evidenciam que o agrupamento das estações, além de aumentar a acurácia dos modelos preditivos, também facilitam a aplicação desses modelos preditivos na prática. Dessa forma, os modelos preditivos apresentados são mecanismos eficientes que permitem gerenciar esses sistemas, adotando estratégias de negócios baseadas na previsão do tempo e nas estações do ano.

show abstract

“…Accordingly, it is difficult to plan urban complexities through interventions. Moreover, despite the recent advances in urban simulation models (e.g., Dazhou et al, 2020;Estiri, 2017;Gianni, D'Ambrogio, & Tolk, 2014;Grinberger, Lichter, & Felsenstein, 2017;Khan & Gulliver, 2018;Landis, 2012;Lu et al, 2021;Qin & Nishii, 2015;Sarkar, Chawla, Ahmad, et al, 2017;Wang, Xu, & Chen, 2019;Xu et al, 2020) and Bibri Computational Urban Science (2021) 1:8 multilevel integrated modelling based on big data analytics, the bulk of work tends to focus largely on smart cities, leaving important questions involving the potential role of these advanced technologies in enhancing the planning and design of sustainable cities. Data-driven smart sustainable cities pose enormous challenges for both the conventional approaches to planning as well as the conventional forms of simulation models due to the kind of wicked problems and complexities they inherently embody.…”

Section: Introductionmentioning

confidence: 99%

Data-driven smart sustainable cities of the future: urban computing and intelligence for strategic, short-term, and joined-up planning

Bibri

2021

Comput.Urban Sci.

View full text Add to dashboard Cite

Sustainable cities are quintessential complex systems—dynamically changing environments and developed through a multitude of individual and collective decisions from the bottom up to the top down. As such, they are full of contestations, conflicts, and contingencies that are not easily captured, steered, and predicted respectively. In short, they are characterized by wicked problems. Therefore, they are increasingly embracing and leveraging what smart cities have to offer as to big data technologies and their novel applications in a bid to effectively tackle the complexities they inherently embody and to monitor, evaluate, and improve their performance with respect to sustainability—under what has been termed “data-driven smart sustainable cities.” This paper analyzes and discusses the enabling role and innovative potential of urban computing and intelligence in the strategic, short-term, and joined-up planning of data-driven smart sustainable cities of the future. Further, it devises an innovative framework for urban intelligence and planning functions as an advanced form of decision support. This study expands on prior work done to develop a novel model for data-driven smart sustainable cities of the future. I argue that the fast-flowing torrent of urban data, coupled with its analytical power, is of crucial importance to the effective planning and efficient design of this integrated model of urbanism. This is enabled by the kind of data-driven and model-driven decision support systems associated with urban computing and intelligence. The novelty of the proposed framework lies in its essential technological and scientific components and the way in which these are coordinated and integrated given their clear synergies to enable urban intelligence and planning functions. These utilize, integrate, and harness complexity science, urban complexity theories, sustainability science, urban sustainability theories, urban science, data science, and data-intensive science in order to fashion powerful new forms of simulation models and optimization methods. These in turn generate optimal designs and solutions that improve sustainability, efficiency, resilience, equity, and life quality. This study contributes to understanding and highlighting the value of big data in regard to the planning and design of sustainable cities of the future.

show abstract

A Hybrid Machine Learning Model for Demand Prediction of Edge-Computing-Based Bike-Sharing System Using Internet of Things

Cited by 52 publications

References 32 publications

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

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

Modelos De Aprendizagem De Máquina Para a Gestão Estratégica De Bicicletas Compartilhadas / Machine Learning Models for Shared Bicycle Strategic Management

Data-driven smart sustainable cities of the future: urban computing and intelligence for strategic, short-term, and joined-up planning

Contact Info

Product

Resources

About