Tsunenori Mine received a B.E. degree in Computer Science and Computer Engineering in 1987 and a M.E. and a D.E. degree in Information Systems in 1989 and 1993, respectively, all from Kyushu University. He is an Associate Professor at the Department of Advanced Information Technology, Faculty of Information Science and Electrical Engineering, Kyushu University.
2018 7th International Congress on Advanced Applied Informatics (IIAI-AAI), 2018
Agent-based traffic simulation has become more and more attractive and important to develop new I... more Agent-based traffic simulation has become more and more attractive and important to develop new ITS (Intelligent Transport Systems) services. So far a variety of studies and developments that combine simulators and evaluate ITS services on the combined simulators have been conducted. In this paper, we introduce a simulation environment, called Agent-based USE (Agent-based Unified Simulation Environment), and some application examples for ITS services. The Agent-based USE provides an easy-to-build simulation environment for ITS-related services. In particular, by connecting simulators with ITS services, the Agent-based USE determines behaviors to be changed on the simulators using the data of the services such as recommendation results generated by the services, tells the decisions to simulators; the Agent-based USE then obtains the data representing the current situation on the simulators and sends the data to the services as feedback so as to enable the services to generate the next recommendation. In addition, by using the Agent-based USE, it is possible to construct a co-simulation environment where simulation is performed by synchronizing some kinds of simulators and services and by sharing each simulation information. In this paper, we introduce the overview and architecture of the Agent-based USE for traffic simulation, and discuss its usefulness through some application examples.
Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services, 2016
Government 2.0 activities have become very attractive and popular these days. Using platforms to ... more Government 2.0 activities have become very attractive and popular these days. Using platforms to support the activities such as FixMyStreet, SeeClickFix, or CitySourced, anyone can anytime report issues or complaints in a city with their photographs and geographical information on the Web, and share them with other people. On the other hand, unlike telephone calls, the concreteness of a report depends on its reporter; the actual status and demand to the status may not be described clearly or either one may be miss-described in the report. It may accordingly happen that officials in the city management section can not understand the actual status or a demand to the status from the report. To solve the problems, it is indispensable to complement missing information and estimate the actual status or the demand to the status from ambiguous information in the report. This paper proposes novel methods to detect segments related to an actual status and the demand to the status in a report. The methods combine empirical rules with several machine learning techniques that actively use dependency relation between words. Experimental results illustrate the validity of the proposed methods.
2017 6th IEEE International Conference on Advanced Logistics and Transport (ICALT), 2017
Prediction of bus travel times is of crucial importance for passengers in letting them know their... more Prediction of bus travel times is of crucial importance for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. To predict bus travel times, it is important to know whether the target routes are stable or not. In this paper, we propose a time series approach to predict the travel time over an interval between two adjacent bus stops. We build Artificial Neural Network (ANN) models to predict the travel time over the interval. To make accurate predictions, we divide a day into 8 time-periods in calculating travel time over the interval and classify unstable intervals into three types: weak, medium and strong unstable. We use bus probe data collected from November 21st to December 20th 2013 and provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively impr...
International Journal of Intelligent Transportation Systems Research, 2021
Understanding conditions and situations causing abnormal driving behaviors like sudden braking or... more Understanding conditions and situations causing abnormal driving behaviors like sudden braking or sudden acceleration is important for preventing traffic accidents. Previous studies have used probe vehicle data to detect risky situations where sudden braking frequently occurred. However, they have mainly focused on location and vehicle-related factors. In this paper, we build models which discriminate sudden braking using a machine learning method. The models use weather-related information as well as probe data. To investigate how weather-related factors help to determine sudden braking, we conducted extensive experiments using probe data obtained from dashboard cameras and two types of weather-related information obtained from meteorological observatories (MO) and AMeDAS. Experimental results illustrate that using weather-related information improves performance in determining sudden braking and that the temporally and spatially denser characteristics of weather-related factors from AMeDAS help to compensate for insufficiencies in the model with MO data.
Advances in Intelligent Systems and Computing, 2019
Crime is one of the most important social problems for administrative region. Ascertaining the de... more Crime is one of the most important social problems for administrative region. Ascertaining the detailed characteristics of crime and preparing countermeasures are important to keep community life safe and secure. A lot of studies using crime data and geographical data have been carried out with a view to crime prevention. These studies include analyzing geographical features of crime, mapping crime-related information and crime hotspots on the map, predicting crime rate and so on. In addition, police stations have recently begun emailing notifications regarding crime to citizens to help them avoid crime. The e-mail messages include rich information about regional crime; they are actively used by services providing guidance to people in how to avoid crime. These services map the messages onto regional maps using the location information in the messages and show the relations between the locations and crime on the map. In addition, some services send alarms to their users when the GPS information of the users indicates that they are passing by the places where crime has occurred. However, these services only use the location and crime information extracted from the messages. Thus, we cannot say the messages have been fully used to clarify characteristics of regional crime. Therefore, in this paper, we investigate whether or not the crime messages sent by e-mail can be further exploited as a valid source for analyzing the criminal characteristics of a region, i.e., whether or not they include the characteristics of regional crime. To this end, in this research, we conducted experiments to make clear whether or not the crime messages sent by e-mail can help to distinguish regions. Experimental results illustrate that the contents of e-mail crime messages helped to distinguish regions having greater than or equal to 100 reports, with an average F-measure of about 90.3%, while only using the names of the areas where crime has occurred cannot match that F-measure.
2018 IEEE/ACM 5th International Conference on Big Data Computing Applications and Technologies (BDCAT), 2018
Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan ... more Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan their journey, e.g., when they should leave from the origin bus stop, what they will do after arriving at the destination bus stop, and so on. Many studies have tackled this task using probe data and/or the real time data provided by automatic vehicle location (AVL) systems. Most of them only targeted a small number of routes, short time periods, e.g. less than one week, and used few machine learning models to evaluate their methods. However, different routes generally show different characteristics. In fact, there are big differences between urban routes and rural routes. Furthermore, the performance of machine learning models also varies according to the data dealt with by the models. In this paper, we propose prediction models for bus delay over all intervals between pairs of adjacent bus stops. To build the models, we use one month of bus probe data, which includes more than 80 routes, and apply several machine learning models: linear regression (LR), artificial neural network (ANN), support vector regression (SVR), random forest (RF), and gradient boosting decision tree (GBDT). Experimental results demonstrate the superiority of the GBDT-based prediction model and the effects of considering travel time over prior intervals.
Communications in Computer and Information Science, 2011
Some of Internet services require users to provide their sensitive information such as credit car... more Some of Internet services require users to provide their sensitive information such as credit card number, and an ID-password pair. In these services, the manner in which the provided information is used is solely determined by the service providers. As a result, even when ...
Public transportation guidance services, which are widely used nowadays, support our daily lives.... more Public transportation guidance services, which are widely used nowadays, support our daily lives. However they have not fully been personalized yet. Regarding personalized services, an adaptive user interface plays a crucial role. This paper presents an Adaptive User Interface (AUI) agent of our personalized transportation recommendation system called PATRASH. To design and implement the agent, first, we collected and analyzed public transportation usage histories of 10 subjects so as to confirm the possibilities and effectiveness of the personalized route recommendation function. Then we propose a method to deal with user histories and evaluate the effectiveness of the proposed method based on click costs, comparing with two major transportation guidance systems in Japan. We also propose a decision-tree-based route recommendation method. The experimental results illustrate the effectiveness of the proposed method.
Abstract. Due to the problem of information overload, locating relevant Web portals precisely bas... more Abstract. Due to the problem of information overload, locating relevant Web portals precisely based on user requirements is quite an essential task. As the need for application-to-application communication and in-teroperability grows, providing Web portal services that satisfy ...
2012 IIAI International Conference on Advanced Applied Informatics, 2012
Balance is very important in all areas from art down to the details of our daily life. There is n... more Balance is very important in all areas from art down to the details of our daily life. There is no exception in research work especially when we want to develop an application which will be used in the real world. Currently more and more semantic Web applications are emerging. Although there are some researches on the evaluation and benchmarking of semantic Web applications, they mainly focused on the semantic Web technology itself or specific types of applications. The evaluation of general features of Semantic Web applications is not sufficient. In this paper, we will focus on the evaluation of one of the general characteristics -- balance of semantic Web applications. An analysis of current semantic Web applications will be given first in order to summarize their statistical features and get some hints for identifying the aspects that are critical for balance evaluation. Then we summarize the main aspects of balance evaluation, and present the key factors for each balance evaluation aspect. Finally, suggestions for future semantic Web application development and evaluation will be made based on the analysis of semantic Web applications and the summarizing of balance evaluation aspects.
2018 7th International Congress on Advanced Applied Informatics (IIAI-AAI), 2018
Agent-based traffic simulation has become more and more attractive and important to develop new I... more Agent-based traffic simulation has become more and more attractive and important to develop new ITS (Intelligent Transport Systems) services. So far a variety of studies and developments that combine simulators and evaluate ITS services on the combined simulators have been conducted. In this paper, we introduce a simulation environment, called Agent-based USE (Agent-based Unified Simulation Environment), and some application examples for ITS services. The Agent-based USE provides an easy-to-build simulation environment for ITS-related services. In particular, by connecting simulators with ITS services, the Agent-based USE determines behaviors to be changed on the simulators using the data of the services such as recommendation results generated by the services, tells the decisions to simulators; the Agent-based USE then obtains the data representing the current situation on the simulators and sends the data to the services as feedback so as to enable the services to generate the next recommendation. In addition, by using the Agent-based USE, it is possible to construct a co-simulation environment where simulation is performed by synchronizing some kinds of simulators and services and by sharing each simulation information. In this paper, we introduce the overview and architecture of the Agent-based USE for traffic simulation, and discuss its usefulness through some application examples.
Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services, 2016
Government 2.0 activities have become very attractive and popular these days. Using platforms to ... more Government 2.0 activities have become very attractive and popular these days. Using platforms to support the activities such as FixMyStreet, SeeClickFix, or CitySourced, anyone can anytime report issues or complaints in a city with their photographs and geographical information on the Web, and share them with other people. On the other hand, unlike telephone calls, the concreteness of a report depends on its reporter; the actual status and demand to the status may not be described clearly or either one may be miss-described in the report. It may accordingly happen that officials in the city management section can not understand the actual status or a demand to the status from the report. To solve the problems, it is indispensable to complement missing information and estimate the actual status or the demand to the status from ambiguous information in the report. This paper proposes novel methods to detect segments related to an actual status and the demand to the status in a report. The methods combine empirical rules with several machine learning techniques that actively use dependency relation between words. Experimental results illustrate the validity of the proposed methods.
2017 6th IEEE International Conference on Advanced Logistics and Transport (ICALT), 2017
Prediction of bus travel times is of crucial importance for passengers in letting them know their... more Prediction of bus travel times is of crucial importance for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. To predict bus travel times, it is important to know whether the target routes are stable or not. In this paper, we propose a time series approach to predict the travel time over an interval between two adjacent bus stops. We build Artificial Neural Network (ANN) models to predict the travel time over the interval. To make accurate predictions, we divide a day into 8 time-periods in calculating travel time over the interval and classify unstable intervals into three types: weak, medium and strong unstable. We use bus probe data collected from November 21st to December 20th 2013 and provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively impr...
International Journal of Intelligent Transportation Systems Research, 2021
Understanding conditions and situations causing abnormal driving behaviors like sudden braking or... more Understanding conditions and situations causing abnormal driving behaviors like sudden braking or sudden acceleration is important for preventing traffic accidents. Previous studies have used probe vehicle data to detect risky situations where sudden braking frequently occurred. However, they have mainly focused on location and vehicle-related factors. In this paper, we build models which discriminate sudden braking using a machine learning method. The models use weather-related information as well as probe data. To investigate how weather-related factors help to determine sudden braking, we conducted extensive experiments using probe data obtained from dashboard cameras and two types of weather-related information obtained from meteorological observatories (MO) and AMeDAS. Experimental results illustrate that using weather-related information improves performance in determining sudden braking and that the temporally and spatially denser characteristics of weather-related factors from AMeDAS help to compensate for insufficiencies in the model with MO data.
Advances in Intelligent Systems and Computing, 2019
Crime is one of the most important social problems for administrative region. Ascertaining the de... more Crime is one of the most important social problems for administrative region. Ascertaining the detailed characteristics of crime and preparing countermeasures are important to keep community life safe and secure. A lot of studies using crime data and geographical data have been carried out with a view to crime prevention. These studies include analyzing geographical features of crime, mapping crime-related information and crime hotspots on the map, predicting crime rate and so on. In addition, police stations have recently begun emailing notifications regarding crime to citizens to help them avoid crime. The e-mail messages include rich information about regional crime; they are actively used by services providing guidance to people in how to avoid crime. These services map the messages onto regional maps using the location information in the messages and show the relations between the locations and crime on the map. In addition, some services send alarms to their users when the GPS information of the users indicates that they are passing by the places where crime has occurred. However, these services only use the location and crime information extracted from the messages. Thus, we cannot say the messages have been fully used to clarify characteristics of regional crime. Therefore, in this paper, we investigate whether or not the crime messages sent by e-mail can be further exploited as a valid source for analyzing the criminal characteristics of a region, i.e., whether or not they include the characteristics of regional crime. To this end, in this research, we conducted experiments to make clear whether or not the crime messages sent by e-mail can help to distinguish regions. Experimental results illustrate that the contents of e-mail crime messages helped to distinguish regions having greater than or equal to 100 reports, with an average F-measure of about 90.3%, while only using the names of the areas where crime has occurred cannot match that F-measure.
2018 IEEE/ACM 5th International Conference on Big Data Computing Applications and Technologies (BDCAT), 2018
Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan ... more Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan their journey, e.g., when they should leave from the origin bus stop, what they will do after arriving at the destination bus stop, and so on. Many studies have tackled this task using probe data and/or the real time data provided by automatic vehicle location (AVL) systems. Most of them only targeted a small number of routes, short time periods, e.g. less than one week, and used few machine learning models to evaluate their methods. However, different routes generally show different characteristics. In fact, there are big differences between urban routes and rural routes. Furthermore, the performance of machine learning models also varies according to the data dealt with by the models. In this paper, we propose prediction models for bus delay over all intervals between pairs of adjacent bus stops. To build the models, we use one month of bus probe data, which includes more than 80 routes, and apply several machine learning models: linear regression (LR), artificial neural network (ANN), support vector regression (SVR), random forest (RF), and gradient boosting decision tree (GBDT). Experimental results demonstrate the superiority of the GBDT-based prediction model and the effects of considering travel time over prior intervals.
Communications in Computer and Information Science, 2011
Some of Internet services require users to provide their sensitive information such as credit car... more Some of Internet services require users to provide their sensitive information such as credit card number, and an ID-password pair. In these services, the manner in which the provided information is used is solely determined by the service providers. As a result, even when ...
Public transportation guidance services, which are widely used nowadays, support our daily lives.... more Public transportation guidance services, which are widely used nowadays, support our daily lives. However they have not fully been personalized yet. Regarding personalized services, an adaptive user interface plays a crucial role. This paper presents an Adaptive User Interface (AUI) agent of our personalized transportation recommendation system called PATRASH. To design and implement the agent, first, we collected and analyzed public transportation usage histories of 10 subjects so as to confirm the possibilities and effectiveness of the personalized route recommendation function. Then we propose a method to deal with user histories and evaluate the effectiveness of the proposed method based on click costs, comparing with two major transportation guidance systems in Japan. We also propose a decision-tree-based route recommendation method. The experimental results illustrate the effectiveness of the proposed method.
Abstract. Due to the problem of information overload, locating relevant Web portals precisely bas... more Abstract. Due to the problem of information overload, locating relevant Web portals precisely based on user requirements is quite an essential task. As the need for application-to-application communication and in-teroperability grows, providing Web portal services that satisfy ...
2012 IIAI International Conference on Advanced Applied Informatics, 2012
Balance is very important in all areas from art down to the details of our daily life. There is n... more Balance is very important in all areas from art down to the details of our daily life. There is no exception in research work especially when we want to develop an application which will be used in the real world. Currently more and more semantic Web applications are emerging. Although there are some researches on the evaluation and benchmarking of semantic Web applications, they mainly focused on the semantic Web technology itself or specific types of applications. The evaluation of general features of Semantic Web applications is not sufficient. In this paper, we will focus on the evaluation of one of the general characteristics -- balance of semantic Web applications. An analysis of current semantic Web applications will be given first in order to summarize their statistical features and get some hints for identifying the aspects that are critical for balance evaluation. Then we summarize the main aspects of balance evaluation, and present the key factors for each balance evaluation aspect. Finally, suggestions for future semantic Web application development and evaluation will be made based on the analysis of semantic Web applications and the summarizing of balance evaluation aspects.
Uploads
Papers by Tsunenori Mine