This page has only limited features, please log in for full access.

Ms. Sohani Liyanage
Phd candidate - Swinburne University of Technology

Basic Info


Research Keywords & Expertise

0 Artificial Intelligence
0 Transportation Engineering
0 artificial neural network
0 Intelligent transport system
0 smart mobility

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 13 May 2021 in IEEE Transactions on Intelligent Transportation Systems
Reads 0
Downloads 0

Autonomous Mobility-on-Demand (AMoD) systems hold potential promise for addressing urban mobility challenges. Their key principle is to utilize fleets of shared self-driving vehicles to respond to customer demand on flexible routes in real-time. This research investigates station-based AMoD car-sharing systems and uses scenario analyses to identify plausible future paths for their deployment. A traffic simulation model which implements real-time rebalancing of idle vehicles is developed to evaluate their performance under uncertain travel demands. Unlike other literature which assumed homogeneous demand and resulted in low increases in vehicle kilometers travelled (VKT), this study relied on realistic heterogeneous demand and showed a significant increase in VKT. A case study for Melbourne demonstrated the impacts and showed that while AMoD can meet the demand for travel using only 16% of the current vehicle fleet, they would produce 77% increase in VKT. This would significantly increase congestion in any real-world scenario and goes against the hype of AMoD being the answer to congestion problems.

ACS Style

Farid Javanshour; Hussein Dia; Gordon Duncan; Rusul Abduljabbar; Sohani Liyanage. Performance Evaluation of Station-Based Autonomous On-Demand Car-Sharing Systems. IEEE Transactions on Intelligent Transportation Systems 2021, PP, 1 -12.

AMA Style

Farid Javanshour, Hussein Dia, Gordon Duncan, Rusul Abduljabbar, Sohani Liyanage. Performance Evaluation of Station-Based Autonomous On-Demand Car-Sharing Systems. IEEE Transactions on Intelligent Transportation Systems. 2021; PP (99):1-12.

Chicago/Turabian Style

Farid Javanshour; Hussein Dia; Gordon Duncan; Rusul Abduljabbar; Sohani Liyanage. 2021. "Performance Evaluation of Station-Based Autonomous On-Demand Car-Sharing Systems." IEEE Transactions on Intelligent Transportation Systems PP, no. 99: 1-12.

Journal article
Published: 30 March 2021 in Future Transportation
Reads 0
Downloads 0

Traffic forecasting remains an active area of research in the transport and data science fields. Decision-makers rely on traffic forecasting models for both policy-making and operational management of transport facilities. The wealth of spatial and temporal real-time data increasingly available from traffic sensors on roads provides a valuable source of information for policymakers. This paper adopts the Long Short-Term Memory (LSTM) recurrent neural network to predict speed by considering both the spatial and temporal characteristics of real-time sensor data. A total of 288,653 real-life traffic measurements were collected from detector stations on the Eastern Freeway in Melbourne/Australia. A comparative performance analysis among different models such as the Recurrent Neural Network (RNN) that has an internal memory that is able to remember its inputs and Deep Learning Backpropagation (DLBP) neural network approaches are also reported. The LSTM results showed average accuracies in the outbound direction ranging between 88 and 99 percent over prediction horizons between 5 and 60 min, and average accuracies between 96 and 98 percent in the inbound direction. The models also showed resilience in accuracies as the prediction horizons increased spatially for distances up to 15 km, providing a remarkable performance compared to other models tested. These results demonstrate the superior performance of LSTM models in capturing the spatial and temporal traffic dynamics, providing decision-makers with robust models to plan and manage transport facilities more effectively.

ACS Style

Rusul Abduljabbar; Hussein Dia; Pei-Wei Tsai; Sohani Liyanage. Short-Term Traffic Forecasting: An LSTM Network for Spatial-Temporal Speed Prediction. Future Transportation 2021, 1, 21 -37.

AMA Style

Rusul Abduljabbar, Hussein Dia, Pei-Wei Tsai, Sohani Liyanage. Short-Term Traffic Forecasting: An LSTM Network for Spatial-Temporal Speed Prediction. Future Transportation. 2021; 1 (1):21-37.

Chicago/Turabian Style

Rusul Abduljabbar; Hussein Dia; Pei-Wei Tsai; Sohani Liyanage. 2021. "Short-Term Traffic Forecasting: An LSTM Network for Spatial-Temporal Speed Prediction." Future Transportation 1, no. 1: 21-37.

Journal article
Published: 09 February 2021 in Transportation Research Part D: Transport and Environment
Reads 0
Downloads 0

Micro-mobility is increasingly recognised as a promising mode of urban transport, particularly for its potential to reduce private vehicle use for short-distance travel. Despite valuable research contributions that represent fundamental knowledge on this topic, today’s body of research appears quite fragmented in relation to the role of micro-mobility as a transformative solution for meeting sustainability outcomes in urban environments. This paper consolidates knowledge on the topic, analyses past and on-going research developments, and provides future research directions by using a rigorous and auditable systematic literature review methodology. To achieve these objectives, the paper analysed 328 journal publications from the Scopus database covering the period between 2000 and 2020. A bibliographic analysis was used to identify relevant publications and explore the changing landscape of micro-mobility research. The study constructed and visualised the literature’s bibliometric networks through citations and co-citations analyses for authors, articles, journals and countries. The findings showed a consistent spike in recent research outputs covering the sustainability aspects of micro-mobility reflecting its importance as a low-carbon and transformative mode of urban transport. The co-citation analysis, in particular, helped to categorise the literature into four main research themes that address benefits, technology, policy and behavioural mode-choice categories where the majority of research has been focused during the analysis period. For each cluster, inductive reasoning is used to discuss the emerging trends, barriers as well as pathways to overcome challenges to wide-scale deployment. This article provides a balanced and objective summary of research evidence on the topic and serves as a reference point for further research on micro-mobility for sustainable cities.

ACS Style

Rusul L. Abduljabbar; Sohani Liyanage; Hussein Dia. The role of micro-mobility in shaping sustainable cities: A systematic literature review. Transportation Research Part D: Transport and Environment 2021, 92, 102734 .

AMA Style

Rusul L. Abduljabbar, Sohani Liyanage, Hussein Dia. The role of micro-mobility in shaping sustainable cities: A systematic literature review. Transportation Research Part D: Transport and Environment. 2021; 92 ():102734.

Chicago/Turabian Style

Rusul L. Abduljabbar; Sohani Liyanage; Hussein Dia. 2021. "The role of micro-mobility in shaping sustainable cities: A systematic literature review." Transportation Research Part D: Transport and Environment 92, no. : 102734.

Journal article
Published: 18 May 2020 in Sustainability
Reads 0
Downloads 0

On-demand multi-passenger shared transport options are increasingly being promoted as an influential strategy to reduce traffic congestion and emissions and improve the convenience and travel experience for passengers. These services, often referred to as on-demand public transport, are aimed at meeting personal travel demands through the use of shared vehicles that run on flexible routes using advanced tools for dynamic scheduling. This paper presents an agent-based traffic simulation model that was developed to evaluate the performance of on-demand public transport and compare it with existing scheduled bus services using a case study of the inner city of Melbourne in Australia. The key performance measures used in the comparative evaluation included quality of service and passenger experience in terms of waiting times, the efficiency of service and operations in terms of hourly vehicle utilization, and system efficiency in terms of trip completion rates, passenger kilometers travelled and total passenger trip times. The results showed significant benefits for passengers who use on-demand bus services compared to scheduled bus services. The on-demand bus service was found to reduce average total passenger waiting times by 89% during the Morning Peak; by 78% during the Mid-Day period; by 81% during the Afternoon Peak; and by more than 95% during other periods of the day. From an operator’s perspective, the on-demand services were found to achieve around 70% vehicle utilization rates during peak hours compared to a utilization rate not exceeding 16% for the scheduled bus services. Even during off-peak periods, the occupancies for on-demand services were almost twice the vehicle occupancies for scheduled bus services. In terms of system efficiency, the on-demand services achieved a trip completion rate of 85% compared to a trip completion rate of 67% for the scheduled bus services. The total passenger-kilometers travelled was similar for both scheduled and on-demand bus services, which refutes claims that on-demand bus services induce more kilometers of travel. The trip completion times were around 55% shorter for on-demand bus services compared to scheduled services, which represents a significant saving in travel time for users. Finally, the paper presents average emissions per completed trip for both types of services and shows a significant reduction in emissions for on-demand services compared to conventional bus services. These include, on average, a 48% reduction in CO2 emissions per trip; 82% reduction in NO emissions per trip; and 41% reduction in p.m.10 emissions per trip. These findings clearly demonstrate the superior benefits of on-demand bus services compared to scheduled bus services.

ACS Style

Sohani Liyanage; Hussein Dia. An Agent-Based Simulation Approach for Evaluating the Performance of On-Demand Bus Services. Sustainability 2020, 12, 4117 .

AMA Style

Sohani Liyanage, Hussein Dia. An Agent-Based Simulation Approach for Evaluating the Performance of On-Demand Bus Services. Sustainability. 2020; 12 (10):4117.

Chicago/Turabian Style

Sohani Liyanage; Hussein Dia. 2020. "An Agent-Based Simulation Approach for Evaluating the Performance of On-Demand Bus Services." Sustainability 12, no. 10: 4117.

Review
Published: 27 February 2019 in Sustainability
Reads 0
Downloads 0

On-demand shared mobility is increasingly being promoted as an influential strategy to address urban transport challenges in large and fast-growing cities. The appeal of this form of transport is largely attributed to its convenience, ease of use, and affordability made possible through digital platforms and innovations. The convergence of the shared economy with a number of established and emerging technologies—such as artificial intelligence (AI), Internet of Things (IoT), and Cloud and Fog computing—is helping to expedite their deployment as a new form of public transport. Recently, this has manifested itself in the form of Flexible Mobility on Demand (FMoD) solutions, aimed at meeting personal travel demands through flexible routing and scheduling. Increasingly, these shared mobility solutions are blurring the boundaries with existing forms of public transport, particularly bus operations. This paper presents an environmental scan and analysis of the technological, social, and economic impacts surrounding disruptive technology-driven shared mobility trends. Specifically, the paper includes an examination of current and anticipated external factors that are of direct relevance to collaborative and low carbon mobility. The paper also outlines how these trends are likely to influence the mobility industries now and into the future. The paper collates information from a wide body of literature and reports on findings from actual ‘use cases’ that exist today which have used these disruptive mobility solutions to deliver substantial benefits to travellers around the world. Finally, the paper provides stakeholders with insight into identifying and responding to the likely needs and impacts of FMoD and informs their policy and strategy positions on the implementation of smart mobility systems in their cities and jurisdictions.

ACS Style

Sohani Liyanage; Hussein Dia; Rusul Abduljabbar; Saeed Bagloee. Flexible Mobility On-Demand: An Environmental Scan. Sustainability 2019, 11, 1262 .

AMA Style

Sohani Liyanage, Hussein Dia, Rusul Abduljabbar, Saeed Bagloee. Flexible Mobility On-Demand: An Environmental Scan. Sustainability. 2019; 11 (5):1262.

Chicago/Turabian Style

Sohani Liyanage; Hussein Dia; Rusul Abduljabbar; Saeed Bagloee. 2019. "Flexible Mobility On-Demand: An Environmental Scan." Sustainability 11, no. 5: 1262.

Review
Published: 02 January 2019 in Sustainability
Reads 0
Downloads 0

The rapid pace of developments in Artificial Intelligence (AI) is providing unprecedented opportunities to enhance the performance of different industries and businesses, including the transport sector. The innovations introduced by AI include highly advanced computational methods that mimic the way the human brain works. The application of AI in the transport field is aimed at overcoming the challenges of an increasing travel demand, CO2 emissions, safety concerns, and environmental degradation. In light of the availability of a huge amount of quantitative and qualitative data and AI in this digital age, addressing these concerns in a more efficient and effective fashion has become more plausible. Examples of AI methods that are finding their way to the transport field include Artificial Neural Networks (ANN), Genetic algorithms (GA), Simulated Annealing (SA), Artificial Immune system (AIS), Ant Colony Optimiser (ACO) and Bee Colony Optimization (BCO) and Fuzzy Logic Model (FLM) The successful application of AI requires a good understanding of the relationships between AI and data on one hand, and transportation system characteristics and variables on the other hand. Moreover, it is promising for transport authorities to determine the way to use these technologies to create a rapid improvement in relieving congestion, making travel time more reliable to their customers and improve the economics and productivity of their vital assets. This paper provides an overview of the AI techniques applied worldwide to address transportation problems mainly in traffic management, traffic safety, public transportation, and urban mobility. The overview concludes by addressing the challenges and limitations of AI applications in transport.

ACS Style

Rusul Abduljabbar; Hussein Dia; Sohani Liyanage; Saeed Asadi Bagloee. Applications of Artificial Intelligence in Transport: An Overview. Sustainability 2019, 11, 189 .

AMA Style

Rusul Abduljabbar, Hussein Dia, Sohani Liyanage, Saeed Asadi Bagloee. Applications of Artificial Intelligence in Transport: An Overview. Sustainability. 2019; 11 (1):189.

Chicago/Turabian Style

Rusul Abduljabbar; Hussein Dia; Sohani Liyanage; Saeed Asadi Bagloee. 2019. "Applications of Artificial Intelligence in Transport: An Overview." Sustainability 11, no. 1: 189.

Journal article
Published: 31 December 2018 in Engineer: Journal of the Institution of Engineers, Sri Lanka
Reads 0
Downloads 0
ACS Style

S. P. Liyanage; S. Pravinvongvuth. Obtaining the Optimum Block Length of the Chet Network: An At-Grade Transportation Network without Signalized Intersections, Roundabouts, or Stop Signs. Engineer: Journal of the Institution of Engineers, Sri Lanka 2018, 51, 37 .

AMA Style

S. P. Liyanage, S. Pravinvongvuth. Obtaining the Optimum Block Length of the Chet Network: An At-Grade Transportation Network without Signalized Intersections, Roundabouts, or Stop Signs. Engineer: Journal of the Institution of Engineers, Sri Lanka. 2018; 51 (4):37.

Chicago/Turabian Style

S. P. Liyanage; S. Pravinvongvuth. 2018. "Obtaining the Optimum Block Length of the Chet Network: An At-Grade Transportation Network without Signalized Intersections, Roundabouts, or Stop Signs." Engineer: Journal of the Institution of Engineers, Sri Lanka 51, no. 4: 37.