Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Seoul National University  

The purpose of this study is to enhance the resilience of restoration scheduling for road networks. Optimal scheduling for resource allocation plays an important role on early restoration. However, circumstances in the post-seismic period are more likely to change due to various factors such as secondary disaster. Furthermore, it is necessary to prepare for unexpected damages. This study examines a method to reduce changes of restoration plan with keeping the adaptability against uncertainties in the post-seismic period. Specifically, an attempt is made to clarify factors strongly related to the delay of restoration in the flexible scheduling which is based on allocation priorities of restoration groups proposed by the existing studies. In this study, numerical simulations are presented to investigate the influence of the change of schedule on early restoration. And then, this paper discussed a method to keep initial restoration plan and to enhance adaptability to circumstances' changes.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publisher：一般社団法人 経営情報学会  

In this research, we analyzed the relationship between gaze duration and the selection of items by using eye-tracking data acquired at a supermarket. We construct a model that shows the relationship between gaze duration and purchase result. We consider the influence of gaze duration on purchase result depending on product categories.

researchmap

Language：Japanese   Publisher：一般社団法人 経営情報学会  

The purpose of this study is to reduce the difficulty of survey experiment on human behavior. In real world, there are many constraints on a survey experiment. In a case of supermarket, the survey experiment must be performed with keeping the sales of store. Thus, researchers cannot examine consumer behaviors on sales reduction in field experiment. We apply a virtual reality headset with eye-tracking to collect data. This device can observe participant's eye movements and position in a virtual space. In this paper, the availability of our proposition for a survey experiment is discussed by constructing a prototype system for data collection.

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

The purpose of this study is to clarify the applicability of data-driven approach in accounting area. As the first stage, focusing on the model comparison, this paper shows the effectiveness of model selection with data mining technique for the development of earnings prediction model based on financial statement data. In accounting area, researchers have not considered the characteristic of financial statement data and a suitable method for that enough. In this study, several methods are applied to develop prediction models. From the comparison with obtained results, we discuss the characteristic of financial statement data and show the possibility of data mining technique for the improvement of prediction accuracy.

DOI： 10.1109/SMC.2017.8122582

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

The purpose of this study is to develop a model to predict the number of vehicles owned in consideration of recent circumstances of emerging countries. In the previous studies, prediction models have been developed from different viewpoints such as energy issue. However, recent growth of the number of vehicles owned in the emerging countries has been more rapid than the predictions. On the other hand, big city in those emerging countries introduced the traffic restriction to prevent aerial pollution from the latter half of 2000s. In this paper, an attempt is made to develop a prediction model based on GDP, income gap and historical transition. Using statistical data of 47 countries from 1952 to 2014, the applicability of the proposed model is verified.

DOI： 10.1109/APWC-on-CSE.2016.037

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

The worldwide market for luxury and fashion goods is dominated today by a handful of multinational corporations (MNCs). The way MNCs access foreign markets and organize distribution, however, remains unclear. In this paper, based on an analysis of foreign trade statistics, we take the example of watches and provide a model to highlight the most important flows as well as regional hubs in this global distribution system. By using this matrix data about watch distribution as a network consisting of countries ( nodes) and trades (links), a network analysis is applied to extract hub nodes playing an important role. The network is visualized to represent the distribution system while focusing on heavily weighted links. As a result, the analysis has demonstrated that the flow of watches does not run always directly from the country of production to end consumers. Intermediaries play a key role, especially in regional markets like Asia, Europe and North America.

DOI： 10.1109/ICDMW.2017.86

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

Prior research identifies that «visit» and «stay» relate positively to individual's purchase outcome. However, the mechanism that how do these two factors affect sales outcomes at an aggregated level is still unclear. This study posits that shop area visit ratio leads to sales outcomes through the effects on stay time, and the influence paths of shop area visit ratio and stay time on sales outcomes differ across products. To further clarify the mechanism, we propose a mediation model, to study how shop area visit ratio and stay time affect purchasers ratio and purchase volume. The data in our study are used from ratio frequency identification (RFID) technology, and matched with point-of-sale (POS) data. The major result suggests that for «selected products», the two sales outcomes (i.e., purchasers ratio and purchase volume) are mainly determined by stay time, while for «planned products», which depends more on shop area visit ratio than stay time. This finding can help retailers to visualize the process of customers' in-store shopping, and to better understand the importance of shop area visit ratio and stay time.

DOI： 10.1109/APWCCSE.2015.7476231

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ELSEVIER SCIENCE BV  

The purpose of this study is to verify the effectiveness of a data-driven approach for financial statement analysis. In the area of accounting, variable selection for construction of models to predict firm's earnings based on financial statement data has been addressed from perspectives of corporate valuation theory, etc., but there has not been enough verification based on data mining techniques. In this paper, an attempt was made to verify the applicability of variable selection for the construction of an earnings prediction model by using recent data mining techniques. From analysis results, a method that considers the interaction among variables and the redundancy of model could be effective for financial statement data. (C) 2016 The Authors. Published by Elsevier B.V.

DOI： 10.1016/j.procs.2016.08.216

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ELSEVIER SCIENCE BV  

The purpose of this article is to verify the effect of previous purchases on later purchases, using shopping path data. We focus on the effect of vice category products bought before. In existing research, the effect of the prior purchase of virtue category products (which are relative necessities) on later purchases, is explained as licensing effect. Based on earlier studies, the purchase of vice category products is also expected to impact later purchase behavior. For example, prior vice category products purchased may impel customers to purchase virtue category products. But the verification result clearly indicated that prior purchase of vice category products did not impel customers to buy virtue category products, rather it indirectly led to a tendency to refrain from further purchases of products. (C) 2015 The Authors. Published by Elsevier B.V.

DOI： 10.1016/j.procs.2015.08.288

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：International Association for Bridge and Structural Engineering (IABSE)  

The purpose of this study is to minimize life cycle cost (LCC) for bridge asset management. This study attempts to develop an optimization method for bridge maintenance planning. It is realistically difficult to keep the safety level of all bridges within a limited budget. Furthermore, a local government needs to manage a large number of bridges. These cause the difficulty of optimization such as the increase of the number of bridges and strict constraint conditions. However, an optimization of maintenance plan for multiple bridges is significant to decrease an annual total cost. Hence, this paper proposes a new method to formulate a maintenance plan, which has the flexibility against uncertainties that involve the change of schedule, by multi-stage optimization that consider an appropriate budget allocation based on each bridge's importance. Several numerical examples are presented to demonstrate the effectiveness for the planning of LCC minimized maintenance.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：International Association for Bridge and Structural Engineering (IABSE)  

In this study, an attempt is made to propose a method for flexible bridge maintenance plans against the modification of deterioration curve by using the multi-stage optimization. Both the minimization of cost and the maximization of structural soundness are important for the maintenance planning. Numerical experiments with 10 bridges were presented to demonstrate that solutions obtained by the proposed method were effective against the uncertainties involved in the financial circumstances and the deterioration prediction.

Scopus

researchmap

Language：Japanese   Publisher：公益社団法人 日本材料学会  

The purpose of this paper is to propose a method effective for the structural reliability assessment based on the multimodal analysis. A structure should be evaluated from various perspectives in order to improve the safety against unpredictable crises. Factors related to failure modes and elements contributing to the capability are estimated based on each criterion. Thus, by considering these criteria as modes, the multimodal analysis can extract information effective to the improvement of reliability and the rational preparedness. However, because this analysis requires enormous samples in practical problems, it is difficult to apply sampling methods like Monte Carlo simulation. In this paper, an attempt is made to propose a search method of samples feasible to the multimodal analysis by using Cellular Automaton Particle Swarm Optimization. A numerical example with a single-bay and single-story rigid frame structure is presented to demonstrate the applicability of the proposed method.

DOI： 10.2472/jsms.64.190

CiNii Books

researchmap

Language：Japanese  

本研究の目的は現実問題の最適化に対する実用的な手法を開発することである．応用における使いやすさと拡張性は最適化手法の実用性を高めるために重要である．本論文は，粒子群最適化（Particle Swarm Optimization: PSO）に対して，解探索における収束性能の問題点を解決し，実問題に対するメタヒューリスティクスとしての有効性を高めるために，セルオートマトン（Cellular Automaton: CA）の考え方を導入したセルオートマトンPSOの提案を試みる．提案手法は，各粒子を群全体で制御せず，近接最適性原理に基づく行動ルールで自律的に行動させ，近傍との相互作用を促すことで解探索を行う．このようにして，提案手法は，探索中の最良位置に対する過度な収束を防ぎ，大規模，かつ複雑な設計空間において効果的な解探索を行うことができると考えられる．本論文では，連続関数を用いた数値実験により，実問題への適用を想定した手法の枠組みとしての提案手法の有効性を示す．The purpose of this study is to develop a practical method for optimizations of real-world problems. The usability and extensibility of the optimization methods are important to improve the applicability for practical use. This paper attempts to overcome the problem of the search of Particle Swarm Optimization (PSO) and improve the effectiveness of PSO for the optimization of practical problems. The proposed method, named Cellular Automaton Particle Swarm Optimization (CAPSO), introduces the concept of Cellular Automaton (CA). Instead of the control of swarm in the conventional PSO, the proposed method searches solutions by promoting the interaction of each particle. Thus, in this method, each particle autonomously moves to improve its state through the reference of neighbors, following the action rule based on Proximate Optimality Principle. In this way, CAPSO prevents the solution search from falling into a local solution and performs an effective search in a problem including the large-scale and complicated design space. In this paper, numerical experiments applying several continuous functions are presented to demonstrate the effectiveness of the proposed method as the methodological framework for practical problems.

CiNii Books

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：日本材料学会  

The reliability analysis is necessary to maintain the safety of structure. In order to evaluate the soundness of structure quantitatively, the calculation of failure probability is one of useful measures. In the reliability analysis for large-scale structures, the enhancement of calculation accuracy and the estimation of factors for the failure require the failure probability calculated by considering the various failure modes. However, the sampling method like Monte Carlo simulation is difficult to calculate the failure probability and estimate multiple failure modes efficiently. This is because the search of various failure modes increases the calculation cost significantly. Therefore, in order to overcome the trade-off, this paper attempts to propose an efficient method by applying Metaheuristic methods. Metaheuristic methods are characterized by the high search ability with keeping the diversity among solution candidates. Firstly, the search of failure modes is formulated as the combinatorial optimization. In this optimization, the metaheuristic method searches failure modes in consideration of the occurrence probability of minimal cut set. In this way, various failure modes that have high occurrence probability are obtained efficiently. Secondly, Probabilistic Network Evaluation Techniques (PNET) is applied to calculate the failure probability of network in consideration of the correlation among obtained failure modes. Through these processes, the proposed method can calculate the accurate failure probability efficiently. Several numerical experiments are presented to demonstrate the applicability of the proposed method for the reliability analysis of large-scale networks.©2014 The Society of Materials Science Japan.

DOI： 10.2472/jsms.63.143

Scopus

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

 This study attempts to evaluate the effectiveness of earthquake preparedness to the improvement of regional resilience by analyzing the reliability of road network based on the safety of human life. This reliability analysis extracts vulnerable points to the reachability of fire truck and ambulance and the evacuation of residents. By comparing the reinforcement of extracted elements with the ongoing plan, this paper demonstrates that the proposed preparedness based on the regional resilience more improves the safety of residents with the enhancement of the continuity of road network. The assessment of earthquake preparedness from various viewpoints is necessary to predict and minimize the seismic crisis. In this paper, it was implied that the evaluation that put a priority on the human life could be a criterion for the improvement of regional resilience.

DOI： 10.2208/jscejsp.70.I_73

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：American Society of Civil Engineers (ASCE)  

In the maintenance planning,life cycle cost (LCC) can be reduced by treating multiple bridges simultaneously. However, it is difficult for a practical case to establish an optimal plan that reduces LCC because there is a large number of bridges to be maintained. In this study, an attempt is made to propose an optimal planning method for a large number of bridges in two stages by using a genetic algorithm (GA). In the first stage, the proposed method optimizes a maintenance plan for a single bridge with considering for preventive maintenance. Here, this optimal plan involves some periods in which maintenance works can be postponed without increasing LCC under the same safety condition. Then, in the second stage, the proposed method minimizes the total LCC of a large number of bridges by using each maintenance plan obtained for a single bridge, modifying it using such flexible periods involved in the maintenance plan, and calculating the total LCC by summing up the LCC for single bridge. Furthermore, the effects of budget constraints on LCC minimization are discussed. Numerical examples are presented to demonstrate the applicability of the proposed method.

DOI： 10.1061/9780784413357.200

Scopus

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

The purpose of this study is to develop an optimization method of maintenance planning of bridges for the asset management. It is realistically difficult to keep the safety of all bridges within a limited budget. Furthermore, the increase of the number of bridges treated in an optimization significantly increases the number of combination of solution candidates and the difficulty of optimization. Because an optimization of maintenance planning for multiple bridges is effective to decrease an annual cost, it is necessary to overcome this problem. In this paper, an attempt is made to propose a method making optimal plans in response to various objectives such as the cost saving, the improvement of safety and the adaptation to uncertainties. This method improves the flexibility of plan against the change of schedule by basing on the preventive maintenance. In the proposed method, various candidates of plan for each bridge are created in consideration of the preventive maintenance. Then, a combination of candidates corresponding to the purpose of planning is searched. A numerical experiment was presented to demonstrate that the proposed method could develop an optimal plan based on a safety level different from bridge to bridge.

DOI： 10.2208/jscejam.70.I_959

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

The purpose of this study is to demonstrate the applicability of Cellular Automaton Particle Swarm Optimization (CAPSO) for constrained problems. CAPSO is a method that can efficiently search solutions with an autonomic action of each particle adapted to the applied problem. In the optimization for practical problems, a solution search requires the applicability to a design space including constraint conditions, various evaluation criteria and uncertainties. In past researches, search methods for certain problem such as the multi-objective optimization have been proposed. However, the improvement of those methods for application problems tends to become difficult due to the complication of their algorithm. On the other hand, CAPSO can treat the algorithm of search solution and the description of particle's action in response to a problem separately. By this feature, CAPSO has the extensibility for practical problems. In this paper, an attempt is made to propose an action rule of particle suitable for constrained optimization problems in consideration of the extensibility of method. Numerical examples in the function optimization are presented to demonstrate the applicability of proposed method.

DOI： 10.14864/fss.30.0_412

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

The purpose of this study is to support an independent life of person with the acquired visual impairment. In this study, an attempt is made to develop a walking support system comfortable for acquired visually impaired users. Support systems for a person who has the congenital visual impairment have been developed by various researchers. In existing researches, walking support systems have been used by combining with the Braille and the white cane. However, the acquired impaired feels stress against the use of these systems. This is because the life with the visual impairment is extremely-different from the past custom. In addition, the treatment as the visually impaired injures that person's pride. Therefore, it is necessary to develop a support system that considers a person with the acquired visual impairment. In the proposed system, an attempt is made to support a walking with a small wearable camera in consideration of the comfort of user. In this paper, several experiments are presented to demonstrate that the proposed system can detect a person who has possibilities to collide with a user.

DOI： 10.14864/fss.30.0_700

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

Scopus

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

In the maintenance planning, the maintenance cost is reduced by working for multiple bridges simultaneously. However, it is difficult to establish an optimal plan that reduces the maintenance cost by this work because there are a large number of bridges that requires the management. In this study, an attempt is made to propose the planning method for a large number of bridges in two stages by using Genetic Algorithm. In the first stage, the proposed method optimizes a maintenance plan for single bridge with considering the preventive maintenance. Here, this optimal plan involves the period in which the work can be postponed without losing the safety. Therefore, in the second stage, the proposed method minimizes the maintenance cost by considering the year of works in the postponable period of multiple bridges.

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

Recently, it has become difficult to keep the skill level of bridge maintenance engineers due to the retirement of experienced engineers. Hence, the daily inspection for bridges cannot be performed accurately and efficiently in order to detect damages early and take appropriate measures. This study attempts to develop a support system for decision making of the damage assessment of bridges based on the pattern recognition considering the exception extraction. In this system, the exception extraction with one-class SVM removes some data that may cause the decrease of generalization capability of pattern recognition from the database. Therefore, it is guessed that the accuracy and confidence of recognized result are improved. Numerical examples applying digital images of RC slab of bridges with cracks are presented to demonstrate the practical utility of the approach of this study.

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.3850/978-981-07-2219-7_P206

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In pattern recognition, feature selection is a quite important process for constructing practical systems. However, because there are many features as candidates to recognize object, it is difficult to select appropriate features for pattern recognition systematically. The previous research proposed a pattern recognition method using the ensemble system based on fuzzy classifier for multiple feature selection. However, this method can not apply for the problems with many input vectors because it takes a lot of time for learning when the number of the input vector increases. In this study, an attempt is made to overcome the problem by introducing ID3 (Iterative Dichotomizer 3) with classifiers consisting of many feature vectors. ID3 constructs a decision tree for multiple feature selection with the results obtained from classifiers based on each feature. Therefore, it is possible to select appropriate features applied many input vectors. Several benchmark problems are presented to demonstrate the efficiency and applicability of the proposed method.

DOI： 10.1109/ICGEC.2012.111

Web of Science

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

In pattern recognition, feature selection is a quite important process for constructing practical systems. However, because there are many features as candidates to recognize object, it is difficult to select appropriate features for pattern recognition systematically. The previous research proposed a pattern recognition method using the ensemble system based on fuzzy classifier for multiple feature selection. However, this method can not apply for the problems with many input vectors because it takes a lot of time for learning when the number of the input vector increases. In this study, an attempt is made to overcome the problem by introducing ID3 (Iterative Dichotomizer 3) with classifiers consisting of many feature vectors. ID3 constructs the decision tree for multiple feature selection with the results obtained from classifiers based on each feature. Therefore, it is possible to select appropriate features applied many input vectors. Several benchmark problems are presented to demonstrate the efficiency and applicability of the proposed method.

DOI： 10.14864/fss.28.0_755

CiNii Books

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

Recently, it has become more and more important to establish a rational maintenance program for infrastructures. In bridge structures, concrete slabs are suffering from damage, because they directly resist applied loads. In this study, an attempt is made to develop a new damage detection method for concrete slabs with cracks, by using pattern recognition techniques. In the pattern recognition, the feature extraction is a quite important process, because the recognition rate depends on the characteristic of the recognition object. The previous research proposed the method which can select efficient features among various features. However, the method can't apply the problems with many input values. The proposed method can deal in those problems by introducing ID3 with classifiers consisting of many feature vectors. Numerical examples are presented to demonstrate the efficiency and applicability of the proposed method.

DOI： 10.11532/structcivil.58A.756

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In recent years, many researchers focus on metha-heuristics as a method to large-scale and complicated optimization problems. In these problems, an optimization method requires versatility and applicability to a characteristic of design space by combining appropriate global and local searches. Multi-Agent Optimization (MAO) is a method based on Multi-Agent System, and it has been proposed to satisfy these requirements. In this method, agents which represent solution candidates evolve by their autonomous actions and interaction with each other. Through these features, it is expected that MAO can perform global search with whole agents and local search with each agent efficiently. However, it is not clear what parameters are more effective to the evolution of MAO. In this paper, an attempt is made to verify the applicability of MAO to optimization problems by clarifying effects of its parameters with numerical experiments.

DOI： 10.1109/ICGEC.2012.59

Web of Science

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

In the structural reliability analysis of large and complex systems, it is necessary to develop a calculation method of failure probability with efficiency and accuracy in order to quantitatively evaluate the safety. So far, Monte Carlo simulation has been used because of its simplicity and easiness of calculation. For large and complex structures, many improved Monte Carlo simulation methods have been proposed, which can efficiently obtain various failure samples. In this study, an attempt is made to develop an effective sampling method for large-scale structures with multiple failure modes by using Multi-Agent Optimization (MAO) which is one of meta-heuristic optimization techniques. The proposed method is first applied to a one-bay one-story simple rigid frame structure with a limit number of failure mechanism so as to investigate the applicability of the proposed method. From the numerical results, it is obtained that the original MAO can obtain a few failure samples with high occurrence probability, but can not find other lower probability samples necessary for the reliability assessment of complex systems. Therefore, a new method called Resampling MAO is proposed in this study, which successively estimates appropriate searching spaces according to the occurrence probabilities of failure samples. Failure samples are searched in descending order of failure probability. Therefore, it is expected that the proposed method is useful to analyze important members or elements of structures or systems and improve the efficiency of Importance Sampling.

DOI： 10.14864/fss.28.0_330

CiNii Books

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

Recently, the development of the communications networks for mobile phones has led to the services to provide sightseeing information via mobile phone at tourist sites. However, existing tourist guide information provided by website and guide books is not enough or useful, especially in inactive sightseeing regions, because such information is not interactive. In this study, an attempt is made to develop a mobile application system for sightseeing guidance to solve these problems. With this application system, users can post sightseeing information and share it by using mobile phones. This will enable them to provide more vivid and latest information to improve the quality and efficiency of sightseeing information. Furthermore, the proposed application system uses augmented reality. Augmented reality is a technology which enhances a real environment with virtual objects. Therefore, at the sight spot, the application system can be used as a sightseeing guidance system that superimposes annotations on a real world. Eventually, the proposed application system presents virtual tour guides and route so as to be able to assist their tour. In this study, an experiment in Takatsuki city is conducted to demonstrate the applicability of the proposed application system.

DOI： 10.14864/fss.28.0_398

CiNii Books

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

The purpose of this study is to solve problems of using educational contents in E-learning. In recent years, in E-learning, many educational contents such as audio and video are available with the developments in ICT. However, it is not easy to get effect of them by simply introducing. In order to provide contents which consider learning effect and usability to learners, it is necessary to spend huge cost and labor. Therefore, an attempt is made to develop the support system to learners for watching and utilizing video contents. It is expected that the proposed system can support learners by automatically creating chapters of provided video. In this study, chapters are created from the result of automatic summarization of text data extracted from a video by speech recognition. The experiment for verification is presented to demonstrate the applicability of the proposed system to the automatic creation of chapters.

DOI： 10.14864/fss.28.0_643

CiNii Books

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Recently, it has been widely recognized that bridge maintenance is one of emergent and important issues. However, it is not easy to keep the existing bridges in satisfactory conditions because of the lack of enough budget, sufficient data, and experienced inspectors and maintenance engineers. Many experienced bridge engineers have retired and the number of engineers has been reduced. It is, then, urgent how to inherit their knowledge and experience. The purpose of this study is to propose E-learning system in the field of civil engineering. In this study, it is proposed system that E-learning system to apply the SNS in order to improve the effective and efficient education effect. The applicability of the proposed system is verified in the field of civil engineering.

DOI： 10.1109/SCIS-ISIS.2012.6505290

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Recently, the development of the communications networks for mobile phones has led to the services to provide sightseeing information via mobile phone at tourist sites. However, existing tourist information guide contents such as web and guide books provide information in one direction especially in non-activated sightseeing. In this study, an attempt is made to develop a mobile application system for sightseeing guidance to solve these problems. With this application system, users can post sightseeing information and share it by using mobile phones. This will enable them to improve the sightseeing information. Furthermore, the proposed application system uses augmented reality. Augmented reality is a technology which enhances a real environment with virtual objects. Therefore, at the sight spot, the application system can be used as a sightseeing guidance system that superimposes annotations on a real world. Especially, the proposed application system presents virtual tour guides and route so as to be able to assist their tour. In this study, an experiment in Takatsuki city is presented to demonstrate the validity of the proposed application.

DOI： 10.1109/SCIS-ISIS.2012.6505308

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publisher：日本知能情報ファジィ学会  

Recently, the bridge management is required for keeping the safety of daily life. On the other hand, it is difficult to sustain the management in the future due to the short of engineers and the budget cut. The long term planning for management is attempted to reduce the cost for maintenance and improve the safety. However, this planning has some problems due to uncertainties and the equalization of cost. The uncertainty in the prediction of degradation may cause the change of plan. The purpose of this paper is to develop the decision support system for long term planning. In the long term planning, it is undesirable to increase the maintenance cost due to the change of plan. Therefore, in this paper, an attempt is made to propose the dealing method against uncertainties. The proposed method estimates the flexible term for maintenance year without increasing the cost. In the proposed method, a plan considering the preventive maintenance is searched by Genetic Algorithm (GA). In this step, the obtained plan is expected to be able to change the maintenance year without increasing the cost because the search of GA has the fuzziness in a problem which has various suboptimal solutions. The estimation of the flexible term for the obtained plan is attempted by applying the numerical simulation. Therefore, the plan obtained by the proposed method is expected to improve the safety against uncertainties without increase the cost by following the flexible term. Numerical examples are presented to demonstrate the applicability of the proposed method.

DOI： 10.3156/jsoft.23.469

CiNii Books

researchmap

DOI： 10.2208/jscejam.67.I_825

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

 The purpose of this paper is the realization of quick restoration of the lifeline system after earthquake disaster. It is intended to determine the optimal allocation of restoring teams and optimal scheduling of restoring process. In previous researches, optimal restoration scheduling system, uncertainties like the secondary disaster were considered. And some numerical example showed that the system was effective. However, the system proposed in previous researches has not considered the practical situation where optimal schedule is used. In order to support the decision making for an early restoration, it is necessary to fulfill the following conditions: a) available after disaster, b) disclosure of information about restoration. In this paper, the system for optimal restoration scheduling is realized under Web system. An attempt is made to improve the practicality of restoration scheduling system by developing the proposed system under the technologies of Cloud Computing.

DOI： 10.2208/jscejsp.67.I_77

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

The purpose of this research is to establish an appropriate program for the long/middle term planning of public works. This planning needs to satisfy various constraints such as the order relations among construction projects and annual budget. Therefore, in order to solve this planning problem as a combinatorial optimization, it is necessary to search for solutions in very complicated solution space. In this optimization, Genetic Algorithm (GA) is more likely to be trapped by a local optimum due to the lack of diversity among individuals. In this study, an attempt is made to develop a decision support system for the optimal planning by using Improved GA. The proposed method adopts a local search which aims at satisfying constraint of the order relations. This local search can prevent that the search of GA tends to converge to a local optimum. Numerical examples are presented to demonstrate the applicability of the proposed method through the comparison with Simple GA computation. Copyright © ASCE 2011.

DOI： 10.1061/41170(400)37

Scopus

researchmap

Publisher：公益社団法人 土木学会  

The purpose of this research is to propose an early restoration for lifeline systems after earthquake disasters. Here, two issues are focused on, the first of which is such an allocation problem that which groups will restore which disaster places, and the second is such a scheduling problem what order is the best for the restoration. In order to solve the two problems simultaneously, Genetic Algorithm (GA) is applied. However, road networks after earthquake disasters have an uncertain environment. In this study, the priority of an allocation that which groups will restore which disaster places is optimized under uncertain environments. So, the restoration schedules adapting to various situations can be made by using this priority. An attempt is made to develop a decision support system of the optimal restoration scheduling by using the proposed method.

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery  

In order to establish a rational bridge maintenance program, it is inevitable to determine the deterioration curves of various components of bridges. However, it is difficult to identify appropriate deterioration curves because of various uncertainties involved in the prediction process and environment evaluation. Furthermore, it is necessary to take into account the effects of natural hazards. Under the situation, although the existing bridges should be kept in a safety condition through inspection and maintenanceworks, it is not easy to maintain them in a satisfactory level, due to the financial constraints. In this study, an attempt is made to develop an optimal maintenance planning method that can account for the effects of various uncertainties. In the proposed method, an optimal maintenance schedule is obtained with the aid of genetic algorithms, in which the deterioration curve can be treated as a random function. A numerical example is presented to demonstrate the applicability and efficiency of the proposed method. © 2010 Taylor &amp
Francis Group, London.

DOI： 10.1201/b10497-11

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

The purpose of this research is to propose an early restoration for lifeline systems after earthquake disasters. The previous researches show that the optimization of the restoration schedule by using genetic algorithm (GA) is powerful. However, those are not considering the uncertain environment after earthquake disasters. The circumstances of the damage at devastated areas are very changeable due to the aftershock, fire disaster and bad weather. In addition, the restoring works may delay by unexpected accidents. Therefore, it is necessary to obtain the restoration schedule which has robustness, because the actual restoring works could not progress smoothly under the uncertain environment. GA considering uncertainty (GACU) can treat various uncertainties involved, but it is difficult to obtain the robust schedule. In this study, an attempt is made to develop a decision support system of the optimal restoration scheduling by using the improved GACU. © 2008 Tsinghua University Press.

DOI： 10.1016/S1007-0214(08)70181-0

Scopus

researchmap

Language：Japanese   Publisher：公益社団法人 土木学会  

The purpose of this research is to propose an early restoration for lifeline systems after earthquake disasters. Here, two issues are focused on, the first of which is such an allocation problem that which groups will restore which disaster places, and the second is such a scheduling problem what order is the best for the restoration. In order to solve the two problems simultaneously, Genetic Algorithm (GA) is applied, because it has been proven to be very powerful in solving combinatorial problems. However, road networks after earthquake disasters have an uncertain environment, that is, the restoring works are not progressing on schedule. The actual restoring process should be performed by considering various uncertainties simultaneously. In addition, the restoring works should be performed by not single group but multiple group in order to make the progress more effective. In this study, an attempt is made to develop a decision support system of the optimal restoration scheduling by using the improved GA to consider uncertainty.

researchmap

Language：Japanese   Publisher：大阪城南女子短期大学  

CiNii Books

researchmap

Language：Japanese  

researchmap

Language：Japanese   Publisher：関西大学先端科学技術推進機構  

CiNii Books

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：関西大学先端科学技術推進機構  

CiNii Books

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：日本材料学会  

CiNii Books

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Publisher：Japan Society of Civil Engineers  

The purpose of this research is to establish an appropriate program for the long/middle term planning of public activities. This planning should account for various constraints. The previous research attempted to obtain an appropriate solution by applying Genetic Algorithm (GA). However, in the method, the solution obtained may not be optimal due to the lack of diversity among individuals. In this study, an attempt is made to develop a decision support system of the optimal long/middle term planning by using Memetic Algorithm (MA). MA can obtain the solutions which satisfy all constraints by adopting the repair of gene. Numerical examples are presented to demonstrate the applicability of the proposed method through the comparison with GA computation.

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：Japan Society for Fuzzy Theory and Intelligent Informatics  

In order to establish a rational bridge maintenance program, it is inevitable to determine the deterioration curves of various components of bridges. However, it is difficult to identify appropriate deterioration curves because of various uncertainties involved in the prediction process and environment evaluation. Furthermore, it is necessary to take into account the effects of natural hazards. Under the situation, although the existing bridges should be kept in a safety condition through inspection and maintenance works, it is not easy to maintain them in a satisfactory level, because of the financial constraints. In this study, an attempt is made to develop an optimal maintenance planning system. In the proposed system, an optimal maintenance scheduling is obtained with Genetic Algorithm and Monte Carlo Simulation, in which the deterioration curve can be updated by using the data given from the structural health monitoring or periodical inspection. Several numerical examples are presented to demonstrate the applicability and efficiency of the proposed method.

researchmap

Language：Japanese   Publisher：日本材料学会  

CiNii Books

researchmap

Event date： 2021.5

Language：Japanese   Presentation type：Poster presentation  

researchmap

Event date： 2021.2

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Event date： 2020.6

Language：English   Presentation type：Oral presentation (general)  

researchmap

Event date： 2020.5

Presentation type：Poster presentation  

researchmap

Event date： 2017.12

Language：Japanese  

researchmap

Event date： 2016

Language：Japanese  

researchmap

Event date： 2014

Language：Japanese  

The purpose of this study is to demonstrate the applicability of Cellular Automaton Particle Swarm Optimization (CAPSO) for constrained problems. CAPSO is a method that can efficiently search solutions with an autonomic action of each particle adapted to the applied problem. In the optimization for practical problems, a solution search requires the applicability to a design space including constraint conditions, various evaluation criteria and uncertainties. In past researches, search methods for certain problem such as the multi-objective optimization have been proposed. However, the improvement of those methods for application problems tends to become difficult due to the complication of their algorithm. On the other hand, CAPSO can treat the algorithm of search solution and the description of particle's action in response to a problem separately. By this feature, CAPSO has the extensibility for practical problems. In this paper, an attempt is made to propose an action rule of particle suitable for constrained optimization problems in consideration of the extensibility of method. Numerical examples in the function optimization are presented to demonstrate the applicability of proposed method.

researchmap

Event date： 2014

Language：Japanese  

researchmap

Event date： 2013.11

Language：English  

researchmap

Event date： 2013

Language：Japanese  

researchmap

Event date： 2012.10

Language：English  

researchmap

Event date： 2012.5

Language：Japanese  

researchmap

Event date： 2012

Language：Japanese  

researchmap

Event date： 2012

Language：Japanese  

In the structural reliability analysis of large and complex systems, it is necessary to develop a calculation method of failure probability with efficiency and accuracy in order to quantitatively evaluate the safety. So far, Monte Carlo simulation has been used because of its simplicity and easiness of calculation. For large and complex structures, many improved Monte Carlo simulation methods have been proposed, which can efficiently obtain various failure samples. In this study, an attempt is made to develop an effective sampling method for large-scale structures with multiple failure modes by using Multi-Agent Optimization (MAO) which is one of meta-heuristic optimization techniques. The proposed method is first applied to a one-bay one-story simple rigid frame structure with a limit number of failure mechanism so as to investigate the applicability of the proposed method. From the numerical results, it is obtained that the original MAO can obtain a few failure samples with high occurrence probability, but can not find other lower probability samples necessary for the reliability assessment of complex systems. Therefore, a new method called Resampling MAO is proposed in this study, which successively estimates appropriate searching spaces according to the occurrence probabilities of failure samples. Failure samples are searched in descending order of failure probability. Therefore, it is expected that the proposed method is useful to analyze important members or elements of structures or systems and improve the efficiency of Importance Sampling.

researchmap

Event date： 2012

Language：Japanese  

Recently, the development of the communications networks for mobile phones has led to the services to provide sightseeing information via mobile phone at tourist sites. However, existing tourist guide information provided by website and guide books is not enough or useful, especially in inactive sightseeing regions, because such information is not interactive. In this study, an attempt is made to develop a mobile application system for sightseeing guidance to solve these problems. With this application system, users can post sightseeing information and share it by using mobile phones. This will enable them to provide more vivid and latest information to improve the quality and efficiency of sightseeing information. Furthermore, the proposed application system uses augmented reality. Augmented reality is a technology which enhances a real environment with virtual objects. Therefore, at the sight spot, the application system can be used as a sightseeing guidance system that superimposes annotations on a real world. Eventually, the proposed application system presents virtual tour guides and route so as to be able to assist their tour. In this study, an experiment in Takatsuki city is conducted to demonstrate the applicability of the proposed application system.

researchmap

Event date： 2012

Language：Japanese  

The purpose of this study is to solve problems of using educational contents in E-learning. In recent years, in E-learning, many educational contents such as audio and video are available with the developments in ICT. However, it is not easy to get effect of them by simply introducing. In order to provide contents which consider learning effect and usability to learners, it is necessary to spend huge cost and labor. Therefore, an attempt is made to develop the support system to learners for watching and utilizing video contents. It is expected that the proposed system can support learners by automatically creating chapters of provided video. In this study, chapters are created from the result of automatic summarization of text data extracted from a video by speech recognition. The experiment for verification is presented to demonstrate the applicability of the proposed system to the automatic creation of chapters.

researchmap

Event date： 2012

Language：Japanese  

researchmap

Event date： 2012

Language：Japanese  

researchmap

Event date： 2010

Language：Japanese  

researchmap

Language：Japanese   Presentation type：Poster presentation  

researchmap

Language：Japanese   Presentation type：Oral presentation (general)  

researchmap

Language：Japanese   Presentation type：Oral presentation (general)  

researchmap

Language：Japanese   Presentation type：Oral presentation (general)  

researchmap