Senior Lecturer attached to the University of Moratuwa with the field of specialization in Transportation Engineer, Transport Modeling, Demand forecast, Road Safety.
Identification and tracking of vehicles are essential for control and surveillance of transport s... more Identification and tracking of vehicles are essential for control and surveillance of transport systems. It is important not only for traffic control but also to estimate vehicle storage within a cordon of city.
2022 International Conference on Data Analytics for Business and Industry (ICDABI)
Locations that act as prominent attractors for humans can be defined as the Point of Interests (P... more Locations that act as prominent attractors for humans can be defined as the Point of Interests (POIs). Restaurants, schools, and transit terminals are some excellent examples of it. Historically, these have been added to the maps utilizing symbols and labels by cartographers, and the increasing digitization assisted the institution of digital maps and the POIs. Contemporarily, POI data are provided by several Location Based Services (LBSs), comprising comparative advantages and disadvantages. However, all these sources provide the data for the users through the different requests attached to their Application Programming Interfaces (APIs). In this context, APIs limit the data extraction to balance the distribution of its resources and its pricing strategies which halt the users from achieving their highest potential in different applications accompanied by POI data. To this end, this study proposes a methodology to collect the POI data for a defined land area in large and store it locally for further analytical utilizations. This approach performs the iteration of API calls that can be used for a defined land area efficiently and cost-effectively. It was tested for an area of 49km 2 in a country in the South Asian region and could extract 50,207 POIs with an average API calling time of 3 seconds. In future, application users of POI data are beneficial through this approach in conducting their tasks without bounding to the typical limitations. The implementation of the proposed methodology has been made publicly available at http://github.com/dineth33/Extracting-large-scale-POI-data
2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)
Activity-based modeling has become the backbone behind transportation planning, and trip purposes... more Activity-based modeling has become the backbone behind transportation planning, and trip purposes inferred from large GPS datasets are paving the path to augmenting its accuracy. Since trip purpose inference models are often accompanied by Point of Interest (POI) data, the quality of POI data is highly influential in obtaining outcomes. However, only a few studies attempted to enhance the POI data to achieve higher accurate purpose inference results. Hence, this study focuses on overcoming two common limitations that emerge with POI data in purpose inference utilizing machine learning techniques: (1) Improving the POI categorization with text classification and (2) Identifying the possible entrances for POIs with large land areas from cluster analysis. Support Vector Machines (SVM) predicts the category type of POIs with the highest accuracy from compared classifiers, and 1,656 entrances were identified from the designed methodology to identify entrances. These were tested with a probabilistic trip purpose inference model and evaluated using large-scale taxi GPS data. The experimental evaluation shows that the proposed methods effectively enhance the trip purpose inference compared to its output with the trip purpose proportions of passengers obtained from a travel survey in the study area (i.e. for "Shopping" trips it enhanced from 16.1% to 23.6% which is comparable to 25.2%)
Even-though Public Transport (PT) was the most common (60%) mode of transport in Sri Lanka, peopl... more Even-though Public Transport (PT) was the most common (60%) mode of transport in Sri Lanka, people are shifting from PT to private vehicles during last few years. That has created a significant traffic congestion on roads which is one of the critical issues in urban roads in Sri Lanka. Improving PT service quality and promoting PT among people would be one solution. The existing service quality of PT should be identified first and expected improvements should be captured. Many researchers have identified “Level of Service (LOS)” as an efficient tool to measure PT service quality [1]. Transit Capacity and Quality of Service Manual highlights the importance of user’s perception for determining level of service [2]. This research attempt to quantify the existing LOS of PT based on bus passengers’ opinion gathered through a questionnaire survey from route between Galle to Colombo. From the literature review, the study identified around 15 factors which affect the LOS of PT and incorpora...
A technological revolution has emerged in the context of mobility surveys with the widescale usab... more A technological revolution has emerged in the context of mobility surveys with the widescale usability of wearable and onboard global positioning system (GPS) devices. Sri Lanka is also at the edge of utilizing these, in replacing the traditional methods. The earnestness' for this transition is supported by the deficiencies such as higher cost, higher nonresponses rates, over and under-reporting, and small sample sizes of traditional surveys. The activity that a passenger performs after a trip, or the purpose of a trip is a vital concern in transportation research as it is the reason behind the generation of travel demands. Hence, trip purpose inference from GPS data has become an important study area in this context [1]. Gong et al. [2] reviewing the existing trip purpose inference studies categorized the methodologies that had been used into three as rule-based, probabilistic, and machine learning-based. In this study, we utilized the GPS records of taxi trips from a popular s...
2021 International Conference on Data Analytics for Business and Industry (ICDABI), 2021
Semantic enrichment of the taxi trajectories with trip purposes has been a moderately discussed s... more Semantic enrichment of the taxi trajectories with trip purposes has been a moderately discussed subject area in travel behavior analysis. Two data sources, (a) Point of Interest (POI) and (b) GPS records of taxi trips, are often combined in predicting the trip purposes of taxi passengers. Three methods (rule-based, probabilistic, and machine learning) have been emerged to infer the trip purpose using these two data sources. However, choosing a model has become a challenge. As rule-based and probabilistic methods are the most widely used in this context, this study considered (1) closest assignment, (2) gravity model, and (3) Bayes theorem-based model accordingly. This study aims to compare and identify the best-performing model among those three models. POI data from Google Places API and GPS records from a taxi service provider in Colombo District, Sri Lanka is utilized for this evaluation. Comparing all these three models it is concluded that Bayes theorem-based model produces more consistent results. The possibility to use crowdsourced user reviews to measure the attractiveness of POIs in probabilistic models is also assessed. Finally, the limitations of the evaluated models and the possibilities of machine learning-based models to overcome those are presented.
Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared para... more Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared paratransit modes. Applicability of ridesharing is studied in a selected corridor by examining the attitude of the passengers and drivers. The undergraduates of University of Moratuwa (passengers) were selected as the population and one of the access road (between Katubedda junction and university) was selected as the study area with Three-Wheel (3W) mode as common para-transit mode in Sri Lanka. Structured questionnaire was used to gather users (3W passengers) preference and drivers willingness along with road side survey on 3W movements to study the existing situation in the study area. The study focused on effects of ridesharing on three aspects while identifying barriers for ridesharing implementation; (1) demand for 3W, (2) monetary benefit for 3W operators and (3) Environment. It is found that implementing ridesharing with pool of three passengers and with fare of LKR (Sri Lankan currency-Rupees) 20 (less than ⅓ of the current fare, LKR 70) per head; (1) increases 3W ridership by 42%, (2) increases daily profit of the drivers by 13.3% compared to the existing (average vehicle occupancy=1.4) operating cost and (3) Reduces emission cost per user by 50% per passenger. Barriers to ridesharing from users are reluctant to share rides with unknown passengers (stranger-danger) and also with opposite gender while that of from operators is the fear from peer operators like other 3W drivers and bus operators. Implementing ridesharing is certainly a win-win case for both users and operators.
Journal of the Eastern Asia Society for Transportation Studies, 2007
Developing countries are nowadays considering exclusive or semi-exclusive transit system implemen... more Developing countries are nowadays considering exclusive or semi-exclusive transit system implementation. Such systems need to be planned well; attractive to car-owners and affordable to the transit captive users. Therefore, survey becomes essential to grasp preference from all segments of potential users. However, in developing countries, their response for questionnaire survey using hypothetical questions is less reliable because of users' lack of knowledge about such transit systems and trading-off in hypothetical questions. This study aims to propose a systematic approach for questionnaire design in the contest of developing countries. Two different surveys with hypothesis system (BRT for Sri Lanka) were conducted: (1) System explanation ways of with and without pictures in questionnaire; and, (2) Level of complexity of the hypothetical questions. This study concludes that, in developing countries, questionnaires need to be attentive in questionnaires design. Even if questionnaires are conceptually same, few structural changes affect users' response considerably.
Traffic Surveys are crucial for different transport studies like Origin-Destination studies, Traf... more Traffic Surveys are crucial for different transport studies like Origin-Destination studies, Traffic Volume estimations, Vehicle Flow characteristics Determinations, Speed and Delay Studies, Turning Movement analysis, Parking Analysis etc. Currently, Sri Lankan researchers are using mostly human-based manual surveys and semi-automated methods for Traffic Surveys. However, there is an issue in cost, effort, the value of time, and the accuracy of data gathering in the above methods. Therefore, under Accelerating Higher Education Expansion and Development (AHEAD) grant, we are researching the possibility of doing surveys using videography and Artificial Intelligence technologies for continuous and accurate data collection to reduce the burden that is currently facing. Using CCTV video cameras, we have done surveys in different locations in Western Province to check
Traffic-related analyses are essential to implementing traffic management approaches to create mo... more Traffic-related analyses are essential to implementing traffic management approaches to create mobility more convenient. In this context, Passenger Car Unit (PCU) values as a uniform measure of vehicles are instrumental in analysis such as traffic capacity estimation, traffic flow model development, level of service determination, etc. These studies always demand a recently calculated set of PCU values since the traffic conditions in arterials often change. PCU values for expressway and three-lane (one-way) road types have not been calculated in the Sri Lankan context, and the available set of values has become somewhat outdated. Hence, this study used Chandra's method to assess the PCU values of ten vehicle categories for four different mid-block road sections in the Colombo district, Sri Lanka. The data relating to the two main variables of this method, categorical speed, and area of vehicles, were collected from field surveys. The results of four-lane arterials were aggregate...
2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)
Emergency vehicles are equipped with audio and visual warning devices, which are meant to help th... more Emergency vehicles are equipped with audio and visual warning devices, which are meant to help them navigate through traffic by demanding manoeuvring space from other vehicles. Notable deaths happen due to the delay in reaching their destinations by ambulance and fire engine vehicles. Depending on local legislation, vehicles on the road may be compelled to cede the right of way to emergency responders utilizing their warning devices. Emergency vehicles happen to wait at signalized intersections with fixed cycle timing. Though there are DL-based vehicle classification techniques that support intelligent traffic light systems, this study discusses the Emergency vehicle sound detection model based on Deep Learning techniques as additional prop data to improve the accuracy of existing vehicle detection. The Convolutional Neural Network (CNN) model was trained based on short audio signals. The sound was processed using the Mel-frequency Cepstral Coefficients (MFCC) feature extraction technique to transform into an image. The model successfully reached 93% accuracy.
In mitigating urban transportation problems and providing a sustainable transit system, rail-base... more In mitigating urban transportation problems and providing a sustainable transit system, rail-based systems have become popular. While rail-based systems are welcome in many developed countries, it is impractical for cities in developing countries due to the high cost of system building and operation. Thus, a staged or incremental adjustment towards fixed guide way transit implementation of greater interest to many agencies today, and these days it has started developing in terms of Bus Rapid Transit (BRT). As it is very new to developing cities, it is a challenge to get the users to understand the system and to grasp their attitude. Besides, there are many other general issues like literacy, lack of a sample frame etc. Survey design needs to be tuned carefully for these cities to obtain a resonant output. Concerning all these problems, a hypothetical questionnaire survey such as Stated Preference (SP) has become popular. This study conducted a survey on BRT implementation with SP as a hypothetical tool at a selected corridor in Colombo, the capital of Sri Lanka. The main objectives were to identify questionnaire design(media) effects, literacy of users, segmental variation, and the important variable(s). In this survey design, system explanation has been set in two slightly different ways (media: TEXT ∼ IMAGE) for comparison and it was found that even a slight difference on design affected the users' response considerably. Income level could not be predicted directly, but car ownership was found to be a good predictor, it was found to be an important variable and it showed a correlation with literacy.
Journal of the Eastern Asia Society for Transportation Studies, 2007
Developing countries are nowadays considering exclusive or semi-exclusive transit system implemen... more Developing countries are nowadays considering exclusive or semi-exclusive transit system implementation. Such systems need to be planned well; attractive to car-owners and affordable to the transit captive users. Therefore, survey becomes essential to grasp preference from all segments of potential users. However, in developing countries, their response for questionnaire survey using hypothetical questions is less reliable because of users' lack of knowledge about such transit systems and trading-off in hypothetical questions. This study aims to propose a systematic approach for questionnaire design in the contest of developing countries. Two different surveys with hypothesis system (BRT for Sri Lanka) were conducted: (1) System explanation ways of with and without pictures in questionnaire; and, (2) Level of complexity of the hypothetical questions. This study concludes that, in developing countries, questionnaires need to be attentive in questionnaires design. Even if questionnaires are conceptually same, few structural changes affect users' response considerably.
Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared para... more Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared paratransit modes. Applicability of ridesharing is studied in a selected corridor by examining the attitude of the passengers and drivers. The undergraduates of University of Moratuwa (passengers) were selected as the population and one of the access road (between Katubedda junction and university) was selected as the study area with Three-Wheel (3W) mode as common para-transit mode in Sri Lanka. Structured questionnaire was used to gather users (3W passengers) preference and drivers willingness along with road side survey on 3W movements to study the existing situation in the study area. The study focused on effects of ridesharing on three aspects while identifying barriers for ridesharing implementation; (1) demand for 3W, (2) monetary benefit for 3W operators and (3) Environment. It is found that implementing ridesharing with pool of three passengers and with fare of LKR (Sri Lankan currency-Rupees) 20 (less than ⅓ of the current fare, LKR 70) per head; (1) increases 3W ridership by 42%, (2) increases daily profit of the drivers by 13.3% compared to the existing (average vehicle occupancy=1.4) operating cost and (3) Reduces emission cost per user by 50% per passenger. Barriers to ridesharing from users are reluctant to share rides with unknown passengers (stranger-danger) and also with opposite gender while that of from operators is the fear from peer operators like other 3W drivers and bus operators. Implementing ridesharing is certainly a win-win case for both users and operators.
Proceedings of the Eastern Asia Society for Transportation Studies, Vol.12, 2019, 2019
The extent of congestion in Colombo Municipal Council area, Sri Lanka during morning peak time br... more The extent of congestion in Colombo Municipal Council area, Sri Lanka during morning peak time brought the average travel speed to less than 20km/hr. Congestion charging is one among the other many initiatives taken by the government like Bus priority lane, Area Traffic Control System, etc. This study developed a systematic approach to identify an appropriate congestion charging strategy in terms of 'time of the day' and 'mode type' considering the exiting traffic volume via traffic surveying. In comparison with some existing congestion charging examples from other countries, opinion of the general public was obtained to validate the proposed congestion charging for Colombo. The study identified the most effective congestion charging time-window for Colombo Municipal Council area is from 0600 to 1800 using traffic flow and service flow rate. Congestion charging value was calculated as 250LKR though the preferred range of congestion charging value by users is 150~200LKR.
Identification and tracking of vehicles are essential for control and surveillance of transport s... more Identification and tracking of vehicles are essential for control and surveillance of transport systems. It is important not only for traffic control but also to estimate vehicle storage within a cordon of city.
2022 International Conference on Data Analytics for Business and Industry (ICDABI)
Locations that act as prominent attractors for humans can be defined as the Point of Interests (P... more Locations that act as prominent attractors for humans can be defined as the Point of Interests (POIs). Restaurants, schools, and transit terminals are some excellent examples of it. Historically, these have been added to the maps utilizing symbols and labels by cartographers, and the increasing digitization assisted the institution of digital maps and the POIs. Contemporarily, POI data are provided by several Location Based Services (LBSs), comprising comparative advantages and disadvantages. However, all these sources provide the data for the users through the different requests attached to their Application Programming Interfaces (APIs). In this context, APIs limit the data extraction to balance the distribution of its resources and its pricing strategies which halt the users from achieving their highest potential in different applications accompanied by POI data. To this end, this study proposes a methodology to collect the POI data for a defined land area in large and store it locally for further analytical utilizations. This approach performs the iteration of API calls that can be used for a defined land area efficiently and cost-effectively. It was tested for an area of 49km 2 in a country in the South Asian region and could extract 50,207 POIs with an average API calling time of 3 seconds. In future, application users of POI data are beneficial through this approach in conducting their tasks without bounding to the typical limitations. The implementation of the proposed methodology has been made publicly available at http://github.com/dineth33/Extracting-large-scale-POI-data
2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)
Activity-based modeling has become the backbone behind transportation planning, and trip purposes... more Activity-based modeling has become the backbone behind transportation planning, and trip purposes inferred from large GPS datasets are paving the path to augmenting its accuracy. Since trip purpose inference models are often accompanied by Point of Interest (POI) data, the quality of POI data is highly influential in obtaining outcomes. However, only a few studies attempted to enhance the POI data to achieve higher accurate purpose inference results. Hence, this study focuses on overcoming two common limitations that emerge with POI data in purpose inference utilizing machine learning techniques: (1) Improving the POI categorization with text classification and (2) Identifying the possible entrances for POIs with large land areas from cluster analysis. Support Vector Machines (SVM) predicts the category type of POIs with the highest accuracy from compared classifiers, and 1,656 entrances were identified from the designed methodology to identify entrances. These were tested with a probabilistic trip purpose inference model and evaluated using large-scale taxi GPS data. The experimental evaluation shows that the proposed methods effectively enhance the trip purpose inference compared to its output with the trip purpose proportions of passengers obtained from a travel survey in the study area (i.e. for "Shopping" trips it enhanced from 16.1% to 23.6% which is comparable to 25.2%)
Even-though Public Transport (PT) was the most common (60%) mode of transport in Sri Lanka, peopl... more Even-though Public Transport (PT) was the most common (60%) mode of transport in Sri Lanka, people are shifting from PT to private vehicles during last few years. That has created a significant traffic congestion on roads which is one of the critical issues in urban roads in Sri Lanka. Improving PT service quality and promoting PT among people would be one solution. The existing service quality of PT should be identified first and expected improvements should be captured. Many researchers have identified “Level of Service (LOS)” as an efficient tool to measure PT service quality [1]. Transit Capacity and Quality of Service Manual highlights the importance of user’s perception for determining level of service [2]. This research attempt to quantify the existing LOS of PT based on bus passengers’ opinion gathered through a questionnaire survey from route between Galle to Colombo. From the literature review, the study identified around 15 factors which affect the LOS of PT and incorpora...
A technological revolution has emerged in the context of mobility surveys with the widescale usab... more A technological revolution has emerged in the context of mobility surveys with the widescale usability of wearable and onboard global positioning system (GPS) devices. Sri Lanka is also at the edge of utilizing these, in replacing the traditional methods. The earnestness' for this transition is supported by the deficiencies such as higher cost, higher nonresponses rates, over and under-reporting, and small sample sizes of traditional surveys. The activity that a passenger performs after a trip, or the purpose of a trip is a vital concern in transportation research as it is the reason behind the generation of travel demands. Hence, trip purpose inference from GPS data has become an important study area in this context [1]. Gong et al. [2] reviewing the existing trip purpose inference studies categorized the methodologies that had been used into three as rule-based, probabilistic, and machine learning-based. In this study, we utilized the GPS records of taxi trips from a popular s...
2021 International Conference on Data Analytics for Business and Industry (ICDABI), 2021
Semantic enrichment of the taxi trajectories with trip purposes has been a moderately discussed s... more Semantic enrichment of the taxi trajectories with trip purposes has been a moderately discussed subject area in travel behavior analysis. Two data sources, (a) Point of Interest (POI) and (b) GPS records of taxi trips, are often combined in predicting the trip purposes of taxi passengers. Three methods (rule-based, probabilistic, and machine learning) have been emerged to infer the trip purpose using these two data sources. However, choosing a model has become a challenge. As rule-based and probabilistic methods are the most widely used in this context, this study considered (1) closest assignment, (2) gravity model, and (3) Bayes theorem-based model accordingly. This study aims to compare and identify the best-performing model among those three models. POI data from Google Places API and GPS records from a taxi service provider in Colombo District, Sri Lanka is utilized for this evaluation. Comparing all these three models it is concluded that Bayes theorem-based model produces more consistent results. The possibility to use crowdsourced user reviews to measure the attractiveness of POIs in probabilistic models is also assessed. Finally, the limitations of the evaluated models and the possibilities of machine learning-based models to overcome those are presented.
Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared para... more Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared paratransit modes. Applicability of ridesharing is studied in a selected corridor by examining the attitude of the passengers and drivers. The undergraduates of University of Moratuwa (passengers) were selected as the population and one of the access road (between Katubedda junction and university) was selected as the study area with Three-Wheel (3W) mode as common para-transit mode in Sri Lanka. Structured questionnaire was used to gather users (3W passengers) preference and drivers willingness along with road side survey on 3W movements to study the existing situation in the study area. The study focused on effects of ridesharing on three aspects while identifying barriers for ridesharing implementation; (1) demand for 3W, (2) monetary benefit for 3W operators and (3) Environment. It is found that implementing ridesharing with pool of three passengers and with fare of LKR (Sri Lankan currency-Rupees) 20 (less than ⅓ of the current fare, LKR 70) per head; (1) increases 3W ridership by 42%, (2) increases daily profit of the drivers by 13.3% compared to the existing (average vehicle occupancy=1.4) operating cost and (3) Reduces emission cost per user by 50% per passenger. Barriers to ridesharing from users are reluctant to share rides with unknown passengers (stranger-danger) and also with opposite gender while that of from operators is the fear from peer operators like other 3W drivers and bus operators. Implementing ridesharing is certainly a win-win case for both users and operators.
Journal of the Eastern Asia Society for Transportation Studies, 2007
Developing countries are nowadays considering exclusive or semi-exclusive transit system implemen... more Developing countries are nowadays considering exclusive or semi-exclusive transit system implementation. Such systems need to be planned well; attractive to car-owners and affordable to the transit captive users. Therefore, survey becomes essential to grasp preference from all segments of potential users. However, in developing countries, their response for questionnaire survey using hypothetical questions is less reliable because of users' lack of knowledge about such transit systems and trading-off in hypothetical questions. This study aims to propose a systematic approach for questionnaire design in the contest of developing countries. Two different surveys with hypothesis system (BRT for Sri Lanka) were conducted: (1) System explanation ways of with and without pictures in questionnaire; and, (2) Level of complexity of the hypothetical questions. This study concludes that, in developing countries, questionnaires need to be attentive in questionnaires design. Even if questionnaires are conceptually same, few structural changes affect users' response considerably.
Traffic Surveys are crucial for different transport studies like Origin-Destination studies, Traf... more Traffic Surveys are crucial for different transport studies like Origin-Destination studies, Traffic Volume estimations, Vehicle Flow characteristics Determinations, Speed and Delay Studies, Turning Movement analysis, Parking Analysis etc. Currently, Sri Lankan researchers are using mostly human-based manual surveys and semi-automated methods for Traffic Surveys. However, there is an issue in cost, effort, the value of time, and the accuracy of data gathering in the above methods. Therefore, under Accelerating Higher Education Expansion and Development (AHEAD) grant, we are researching the possibility of doing surveys using videography and Artificial Intelligence technologies for continuous and accurate data collection to reduce the burden that is currently facing. Using CCTV video cameras, we have done surveys in different locations in Western Province to check
Traffic-related analyses are essential to implementing traffic management approaches to create mo... more Traffic-related analyses are essential to implementing traffic management approaches to create mobility more convenient. In this context, Passenger Car Unit (PCU) values as a uniform measure of vehicles are instrumental in analysis such as traffic capacity estimation, traffic flow model development, level of service determination, etc. These studies always demand a recently calculated set of PCU values since the traffic conditions in arterials often change. PCU values for expressway and three-lane (one-way) road types have not been calculated in the Sri Lankan context, and the available set of values has become somewhat outdated. Hence, this study used Chandra's method to assess the PCU values of ten vehicle categories for four different mid-block road sections in the Colombo district, Sri Lanka. The data relating to the two main variables of this method, categorical speed, and area of vehicles, were collected from field surveys. The results of four-lane arterials were aggregate...
2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)
Emergency vehicles are equipped with audio and visual warning devices, which are meant to help th... more Emergency vehicles are equipped with audio and visual warning devices, which are meant to help them navigate through traffic by demanding manoeuvring space from other vehicles. Notable deaths happen due to the delay in reaching their destinations by ambulance and fire engine vehicles. Depending on local legislation, vehicles on the road may be compelled to cede the right of way to emergency responders utilizing their warning devices. Emergency vehicles happen to wait at signalized intersections with fixed cycle timing. Though there are DL-based vehicle classification techniques that support intelligent traffic light systems, this study discusses the Emergency vehicle sound detection model based on Deep Learning techniques as additional prop data to improve the accuracy of existing vehicle detection. The Convolutional Neural Network (CNN) model was trained based on short audio signals. The sound was processed using the Mel-frequency Cepstral Coefficients (MFCC) feature extraction technique to transform into an image. The model successfully reached 93% accuracy.
In mitigating urban transportation problems and providing a sustainable transit system, rail-base... more In mitigating urban transportation problems and providing a sustainable transit system, rail-based systems have become popular. While rail-based systems are welcome in many developed countries, it is impractical for cities in developing countries due to the high cost of system building and operation. Thus, a staged or incremental adjustment towards fixed guide way transit implementation of greater interest to many agencies today, and these days it has started developing in terms of Bus Rapid Transit (BRT). As it is very new to developing cities, it is a challenge to get the users to understand the system and to grasp their attitude. Besides, there are many other general issues like literacy, lack of a sample frame etc. Survey design needs to be tuned carefully for these cities to obtain a resonant output. Concerning all these problems, a hypothetical questionnaire survey such as Stated Preference (SP) has become popular. This study conducted a survey on BRT implementation with SP as a hypothetical tool at a selected corridor in Colombo, the capital of Sri Lanka. The main objectives were to identify questionnaire design(media) effects, literacy of users, segmental variation, and the important variable(s). In this survey design, system explanation has been set in two slightly different ways (media: TEXT ∼ IMAGE) for comparison and it was found that even a slight difference on design affected the users' response considerably. Income level could not be predicted directly, but car ownership was found to be a good predictor, it was found to be an important variable and it showed a correlation with literacy.
Journal of the Eastern Asia Society for Transportation Studies, 2007
Developing countries are nowadays considering exclusive or semi-exclusive transit system implemen... more Developing countries are nowadays considering exclusive or semi-exclusive transit system implementation. Such systems need to be planned well; attractive to car-owners and affordable to the transit captive users. Therefore, survey becomes essential to grasp preference from all segments of potential users. However, in developing countries, their response for questionnaire survey using hypothetical questions is less reliable because of users' lack of knowledge about such transit systems and trading-off in hypothetical questions. This study aims to propose a systematic approach for questionnaire design in the contest of developing countries. Two different surveys with hypothesis system (BRT for Sri Lanka) were conducted: (1) System explanation ways of with and without pictures in questionnaire; and, (2) Level of complexity of the hypothetical questions. This study concludes that, in developing countries, questionnaires need to be attentive in questionnaires design. Even if questionnaires are conceptually same, few structural changes affect users' response considerably.
Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared para... more Recent increase in number of singly hired para-transit usage in Sri Lanka favors ride shared paratransit modes. Applicability of ridesharing is studied in a selected corridor by examining the attitude of the passengers and drivers. The undergraduates of University of Moratuwa (passengers) were selected as the population and one of the access road (between Katubedda junction and university) was selected as the study area with Three-Wheel (3W) mode as common para-transit mode in Sri Lanka. Structured questionnaire was used to gather users (3W passengers) preference and drivers willingness along with road side survey on 3W movements to study the existing situation in the study area. The study focused on effects of ridesharing on three aspects while identifying barriers for ridesharing implementation; (1) demand for 3W, (2) monetary benefit for 3W operators and (3) Environment. It is found that implementing ridesharing with pool of three passengers and with fare of LKR (Sri Lankan currency-Rupees) 20 (less than ⅓ of the current fare, LKR 70) per head; (1) increases 3W ridership by 42%, (2) increases daily profit of the drivers by 13.3% compared to the existing (average vehicle occupancy=1.4) operating cost and (3) Reduces emission cost per user by 50% per passenger. Barriers to ridesharing from users are reluctant to share rides with unknown passengers (stranger-danger) and also with opposite gender while that of from operators is the fear from peer operators like other 3W drivers and bus operators. Implementing ridesharing is certainly a win-win case for both users and operators.
Proceedings of the Eastern Asia Society for Transportation Studies, Vol.12, 2019, 2019
The extent of congestion in Colombo Municipal Council area, Sri Lanka during morning peak time br... more The extent of congestion in Colombo Municipal Council area, Sri Lanka during morning peak time brought the average travel speed to less than 20km/hr. Congestion charging is one among the other many initiatives taken by the government like Bus priority lane, Area Traffic Control System, etc. This study developed a systematic approach to identify an appropriate congestion charging strategy in terms of 'time of the day' and 'mode type' considering the exiting traffic volume via traffic surveying. In comparison with some existing congestion charging examples from other countries, opinion of the general public was obtained to validate the proposed congestion charging for Colombo. The study identified the most effective congestion charging time-window for Colombo Municipal Council area is from 0600 to 1800 using traffic flow and service flow rate. Congestion charging value was calculated as 250LKR though the preferred range of congestion charging value by users is 150~200LKR.
Uploads
Papers by Thillaiampalam SIVAKUMAR