1. |
- Aslani, Mohammad, et al.
(författare)
-
Developing adaptive traffic signal control by actor-critic and direct exploration methods
- 2019
-
Ingår i: Proceedings of the Institution of Civil Engineers. - : Thomas Telford. - 0965-092X .- 1751-7710. ; 172:5, s. 289-298
-
Tidskriftsartikel (refereegranskat)abstract
- Designing efficient traffic signal controllers has always been an important concern in traffic engineering. This is owing to the complex and uncertain nature of traffic environments. Within such a context, reinforcement learning has been one of the most successful methods owing to its adaptability and its online learning ability. Reinforcement learning provides traffic signals with the ability automatically to determine the ideal behaviour for achieving their objective (alleviating traffic congestion). In fact, traffic signals based on reinforcement learning are able to learn and react flexibly to different traffic situations without the need of a predefined model of the environment. In this research, the actor-critic method is used for adaptive traffic signal control (ATSC-AC). Actor-critic has the advantages of both actor-only and critic-only methods. One of the most important issues in reinforcement learning is the trade-off between exploration of the traffic environment and exploitation of the knowledge already obtained. In order to tackle this challenge, two direct exploration methods are adapted to traffic signal control and compared with two indirect exploration methods. The results reveal that ATSC-ACs based on direct exploration methods have the best performance and they consistently outperform a fixed-time controller, reducing average travel time by 21%.
|
|
2. |
- Gáspár, Lászlo, et al.
(författare)
-
Recycling reclaimed road material in hydraulically bound layers
- 2015
-
Ingår i: Proceedings of the Institution of Civil Engineers. - : ICE Publishing. - 0965-092X .- 1751-7710. ; 168:3, s. 276-287
-
Tidskriftsartikel (refereegranskat)abstract
- The European Direct-mat project provided a significant contribution to increasing recycling reclaimed road wastes. Part of the project was dedicated to the recycling of various reclaimed road materials in new hydraulically bound layers. This paper summarises the results of the project and the activities of the eight contributing European countries. Several examples from countries outside the project are also provided to give a comprehensive overview. The paper highlights the main trends of relevant practice worldwide (particularly in Europe) and draws conclusions for practitioners.
|
|
3. |
- Moran, Carlos, et al.
(författare)
-
Reliability of congestion measures : Stockholm's case
- 2010
-
Ingår i: Proceedings of the Institution of Civil Engineers. - : Thomas Telford Ltd.. - 0965-092X .- 1751-7710. ; 163:2, s. 85-91
-
Tidskriftsartikel (refereegranskat)abstract
- The Stockholm congestion charging trial was implemented with the aim of satisfying a number of transport policy objectives related to reducing car use in the central area of Stockholm. However, the multifaceted nature of congestion that the charges aimed to alleviate was not technically defined. The traffic impact evaluation efforts were based on survey results for chosen links without any scientific review of the dynamic character of congestion or any investigation of the statistical characteristics of the chosen congestion indicator. Neither was there any analysis of area networks nor any calculation of an overall indicator. Based on a literature review, approaches for defining congestion and a number of alternative congestion performance measures were selected. Data from the trial 'before' and 'after' surveys were used to estimate congestion levels and the accuracy of the performance measures. Specific issues and lessons regarding the quality of the data collection are discussed. Accuracy rankings are presented for different cases, concluding that some performance measures showed better reliability in all situations whereas others proved to always be less reliable. These findings are used as a basis for recommendations regarding the implementations of the congestion indicators studied.
|
|
4. |
- Nadimi, Navid, et al.
(författare)
-
A method to find the optimum routes and stations for Bus Rapid Transit in urban areas
- 2024
-
Ingår i: Proceedings of the Institution of Civil Engineers: Transport. - : Thomas Telford Ltd.. - 0965-092X .- 1751-7710. ; 177:3, s. 162-175
-
Tidskriftsartikel (refereegranskat)abstract
- Public transportation (PT) is an essential system for cities to achieve sustainability. However, determination of proper locations for PT stations and finding suitable routes are critical decisions. This paper aims to propose a novel method to determine BRT stations and routes in the cities, using Fuzzy Inference System (FIS) and Binary Integer Programming (BIP). In the proposed method, first, a set of potential locations for BRT stations is selected based on engineering judgment. Then, by considering several variables and with the help of FIS, a weight is calculated for each location. Subsequently, the optimum corridors for BRT with BIP are identified. The objective function of the BIP model is to maximize the sum of stations’ weights (involving the most suitable locations for BRT stations), while ensuring that the maximum number of passengers can travel each route. Constraints related to technical, social, and economic considerations are also taken into account. To control the model efficiency, the outputs are compared with the stations and corridor suggested by experts. Based on the results, the most important features of the developed model are its simplicity, its ability to consider various factors, a short running time, and its high level of accuracy.
|
|
5. |
- Razouki, Sabah, et al.
(författare)
-
Predicting Long-term Soaked CBR of Gypsiferous Subgrade Soils
- 2006
-
Ingår i: Proceedings of the Institution of Civil Engineers. - 0965-092X .- 1751-7710. ; 159:3, s. 135-140
-
Tidskriftsartikel (refereegranskat)abstract
- Thirty-two laboratory California Bearing Ratio (CBR) tests were carried out on a CH gypsiferous subgrade soil with an initial gypsum content of 34%. The soil samples were prepared according to ASTM D 1883-99 at 95% of the maximum modified AASHTO dry density. For each 40 Ib (178 N) and 70 Ib (311-5 N) surcharge load, eight pairs of CBR samples were prepared, and soaked for periods of 0, 4, 7, 15, 30, 60, 120 and 180 days respectively. To develop a general empirical formula for predicting long-term soaked CBR from unsoaked CBR, use was made of available results on CH soil with a gypsum content of 15%, on granular gypsiferous soils of the SW-SM group with a gypsum content of 64%, and on SM soils with gypsum contents of 34% and 61%. The empirical equation developed in this paper enables the soaked CBR to be determined from the unsoaked CBR for all types of gypsiferous soil and for any surcharge load and soaking period. The equation's validity was examined using six different gypsiferous soils (eight case studies) including both granular and fine-grained soils. This paper also shows the invalidity of Fekpe's empirical equation in modelling the long-term behaviour of gypsiferous soils.
|
|