Embedded Files
I have been working with a number of organisations in local and international industry and research institutes on various collaborative projects.
Some on-going and recent projects include:
Intelligent traffic control with use of IoT technologies
Intelligent traffic control with use of IoT technologies
This is a STF-funded project with Hong Kong Transport Department in which we aim to develop an intelligent traffic control framework that can fully incorporate the capability of the emerging IoT-based sensing, computing, and control technologies. Transport Department will suggest sites for case study and provide most of the data required, and outline the requirements from a user’s perspective with which the deliverables should be developed. Our industrial collaborators will advise the input layer (sensors and data collection), processor (simulation and optimisation algorithm), and output layer (control devices) for maximising the impact of the proposed project, and the prospect for future development and commercialisation of the deliverables.
This is a STF-funded project with Hong Kong Transport Department in which we aim to develop an intelligent traffic control framework that can fully incorporate the capability of the emerging IoT-based sensing, computing, and control technologies. Transport Department will suggest sites for case study and provide most of the data required, and outline the requirements from a user’s perspective with which the deliverables should be developed. Our industrial collaborators will advise the input layer (sensors and data collection), processor (simulation and optimisation algorithm), and output layer (control devices) for maximising the impact of the proposed project, and the prospect for future development and commercialisation of the deliverables.
Patent:
Chow, A.H.F.*, Lu, Z., Yang, C. (2023) Intelligent traffic control method based on IoT and reinforcement learning technologies. US Provisional Patent (Priority No. 63/504,440).
Project sponsor:
Hong Kong Transport Department (Smart Traffic Fund (STF))
Modelling and optimisation of urban rail transit network
Modelling and optimisation of urban rail transit network
This is an ITF-funded collaborative project with Hong Kong MTR Corporation in which we develop a set of tools for assessing and improving level of service of urban rail transit network. Control algorithms are developed based on reinforcement learning (RL) techniques for improving customer satisfaction and system energy consumption. The methodologies are tested using scenario data collected from the Hong Kong MTR metro and Light Rail Transit (LRT) networks.
This is an ITF-funded collaborative project with Hong Kong MTR Corporation in which we develop a set of tools for assessing and improving level of service of urban rail transit network. Control algorithms are developed based on reinforcement learning (RL) techniques for improving customer satisfaction and system energy consumption. The methodologies are tested using scenario data collected from the Hong Kong MTR metro and Light Rail Transit (LRT) networks.
Selected publication (*-corresponding author):
Nguyen, H., Chow, A.H.F.*, Ying, C. (2021) Pareto routing and scheduling dynamic urban rail transit services with multi-objective cross entropy method. Transportation Research Part E, 156, 102544. doi.org/10.1016/j.tre.2021.102544.
Project sponsor:
Hong Kong Innovation and Technology Commission (Innovation and Technology Fund (ITF)); MTR Corporation
Road network assessment and optimisation with air pollution performance measures
Road network assessment and optimisation with air pollution performance measures
This is a ECF-funded research project on assessing and improving Hong Kong road network performance with consideration of environmental measures. The methodologies are tested using scenario data collected from the Hong Kong Cross Harbour Tunnel network with open data sources made available by Hong Kong Transport Department and Environmental Protection Department.
This is a ECF-funded research project on assessing and improving Hong Kong road network performance with consideration of environmental measures. The methodologies are tested using scenario data collected from the Hong Kong Cross Harbour Tunnel network with open data sources made available by Hong Kong Transport Department and Environmental Protection Department.
Selected publication (*-corresponding author):
Lu, Z., Chow, A.H.F.*, Leung, Y., Kwok, H., Cheung, S. (2021) Empirical assessment and modelling of traffic-induced pollution. Transportation Research Record, 2675(11), 1043-1053. doi.org/10.1177/03611981211023769.
Project sponsor:
Hong Kong Environmental Protection Department (Environment and Conservation Fund (ECF))
My previous and current industrial partners include:
AECOM (London, UK)
Arup (London, UK)
Department for Transport (UK)
High Speed Two (HS2) Limited (UK)
Network Rail (UK)
Transport for London (UK)
Transport Research Laboratory (UK)
NEC Europe Ltd (Germany)
Arup (Toronto, Canada)
Berkeley Transportation Systems (CA, USA)
California Department of Transportation (CA, USA)
Federal Highways Administration (USA)
Sensys Networks (CA, USA)
Australian Road Research Board (ARRB, Australia)
Data61 (formerly NICTA, Australia)
Arup (Hong Kong)
Autotoll Ltd (Hong Kong)
Hong Kong Transport Department (Hong Kong)
MTR Corporation (Hong Kong)
PTV Asia Pacific (Hong Kong; Singapore)
QTC Traffic Technology Limited (Hong Kong)
Page updated
Google Sites
Report abuse