A Synergetic Orchestration of Objects, Data, and Services to Enable Smart Cities

You, Linlin; Tunçer, Bige; Zhu, Rui; Xing, Hexu; Yuen, Chau

doi:10.1109/jiot.2019.2939496

Cited by 24 publications

(19 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the IoT, spatial data can appear in different formats. Mobile sensor applications store data related to trajectories (Laska, Herle, Klamma, & Blankenbach, 2018;Li et al, 2019;Limkar & Jha, 2019;Lwin, Takeuchi, Sekimoto, & Zettsu, 2019;Mello et al, 2019;Zhou, Li, & Tu, 2020), sensor location (Işikdağ, 2020), buildings (Yang et al, 2020) and mobile devices (Li et al, 2020;You, Tunçer, Zhu, Xing, & Yuen, 2019). Furthermore, locations related to abstract events can be stored, such as events (Finogeev et al, 2019) and social media content (Qader and Hristidis, 2017).…”

Section: Rq3 What Are the Main Data Formats Stored?mentioning

confidence: 99%

“…The papers in this group describe the creation of tools, models, architectures, frameworks, etc., that aid the design of IoT applications containing big data with some geospatial dimension. Some examples are Liu, Wu, Meng, Wang, and Wang (2021), with an accurate range query scheme for IoT location-based services data outsourced to cloud servers, which preserves data privacy and users' query privacy; Işikdağ (2020), who proposed an architecture for real-time integration of IoT geoinformation; Ding et al (2013), who proposed SeaCloudDM, a massive data management mechanism for heterogeneous sensors; and You et al (2019) and Alvarez et al (2019) who proposed architectures applicable in the creation of services in smart cities.…”

Section: G02 Artifacts To Support the Implementation Of Iot Applicati...mentioning

confidence: 99%

See 1 more Smart Citation

Applications of geospatial big data in the Internet of Things

Silva

Holanda

2021

Transactions in GIS

View full text Add to dashboard Cite

The Internet of Things (IoT) has emerged as a communication paradigm that allows the interconnection of devices that interact with the environment through sensors and actuators, collect data from it, and transmit these data over a network without requiring human interaction (Armstrong, Wang, & Zhang, 2019). IoT architectures can demand database management systems capable of handling high data generation and transmission rates, bringing the research on the IoT closer to the studies on big data (Ge,

show abstract

Section: Rq3 What Are the Main Data Formats Stored?mentioning

confidence: 99%

Section: G02 Artifacts To Support the Implementation Of Iot Applicati...mentioning

confidence: 99%

Applications of geospatial big data in the Internet of Things

Silva

Holanda

2021

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Therefore, optimizing the allocation of parking resources is a critical and urgent issue. There have been many solutions proposed to address this problem and parking occupancy prediction (POP) plays a vital role in most of them [3,4], examples including dynamic parking charges [5,6], parking guidance [7,8], and shared parking [9].…”

Section: Introductionmentioning

confidence: 99%

Adaptation and Learning to Learn (ALL): An Integrated Approach for Small-Sample Parking Occupancy Prediction

Liu

et al. 2022

Mathematics

View full text Add to dashboard Cite

Parking occupancy prediction (POP) plays a vital role in many parking-related smart services for better parking management. However, an issue hinders its mass deployment: many parking facilities cannot collect enough data to feed data-hungry machine learning models. To tackle the challenges in small-sample POP, we propose an approach named Adaptation and Learning to Learn (ALL) by adopting the capability of advanced deep learning and federated learning. ALL integrates two novel ideas: (1) Adaptation: by leveraging the Asynchronous Advantage Actor-Critic (A3C) reinforcement learning technique, an auto-selector module is implemented, which can group and select data-scarce parks automatically as supporting sources to enable the knowledge adaptation in model training; and (2) Learning to learn: by applying federated meta-learning on selected supporting sources, a meta-learner module is designed, which can train a high-performance local prediction model in a collaborative and privacy-preserving manner. Results of an evaluation with 42 parking lots in two Chinese cities (Shenzhen and Guangzhou) show that, compared to state-of-the-art baselines: (1) the auto-selector can reduce the model variance by about 17.8%; (2) the meta-learner can train a converged model 102x faster; and (3) finally, ALL can boost the forecasting performance by about 29.8%. Through the integration of advanced machine learning methods, i.e., reinforcement learning, meta-learning, and federated learning, the proposed approach ALL represents a significant step forward in solving small-sample issues in parking occupancy prediction.

show abstract

“…The SCs is a terminology given to urban areas that use information and communications technologies (ICTs), to support various domains and municipal services, e.g., in governance to create a collaborative process for city management, in mobility to provide personalized and on-demand mobility services, and an environment to solve pollution issues [3] [4] [5] [6]. The SCs, built on top of largescale Internet of Things (IoT) systems that are overgrowing worldwide, provide an excellent opportunity across many cross domain sectors [7]. IoT refers to the interconnection of heterogeneous objects or things on the Internet, capable of collecting and exchanging data [4].…”

Section: Introductionmentioning

confidence: 99%

Enabling Customizable Services for Multimodal Smart Mobility With City-Platforms

et al. 2021

View full text Add to dashboard Cite

In the last decades, the cities' capacity for generating digital information has grown exponentially. In this context, the successful implementation of smart cities' concept depends on the current possibility of handling the significant volumes of sensed data. This is particularly notorious in the case of urban mobility. Researchers in the field of urban planning have shown a great interest in urban mobility problems, proposing different route recommendation services towards making it easier and safer to move around the city. This paper addresses the development of an urban data platform and how to obtain and integrate information from sensors and other data sources to provide aggregated and intelligent views of raw data to support urban mobility. With the aim of evaluating the efficiency of the developed platform, we present an intelligent urban mobility solution, where the context-awareness, user preferences, and environmental factors play a significant role in the process of route planning. Finally, our work provides an experiment to assess different long-range wireless communication technologies to enable its implementation within an urban environment.

show abstract

A Synergetic Orchestration of Objects, Data, and Services to Enable Smart Cities

Cited by 24 publications

References 24 publications

Applications of geospatial big data in the Internet of Things

Applications of geospatial big data in the Internet of Things

Adaptation and Learning to Learn (ALL): An Integrated Approach for Small-Sample Parking Occupancy Prediction

Enabling Customizable Services for Multimodal Smart Mobility With City-Platforms

Contact Info

Product

Resources

About