Pub Date : 2016-07-10DOI: 10.1109/FISTS.2016.7552317
Yun Dong, Yuan Yuan, Guoqiang Wang
Differential evolution (DE) is a very simple and effective stochastic search algorithm, which obtains various performances with different parameter and searching strategy configurations. DE with an individual-dependent mechanism (IDE) is a recently proposed DE variant, which includes an individual-dependent parameter (IDP) setting method and an individual-dependent mutation (IDM) strategy. In this paper, to validate the ability of IDE on solving real-world optimization problem, we first modify it by intruding Cauchy distribution to generate random control parameters and simplifying the proportion function and threshold functions. Subsequently, we test the performance of new IDE via CEC 2014 benchmark suite of single objective real-parameter numerical optimization. In addition, we apply it to solve a ship stowage planning problem in which the objective function is minimizing the stability deviation of the ship. The numerical results demonstrate the good performance of new IDE on solve these two kinds of optimization problems.
{"title":"Apply differential evolution with individual-dependent mechanism to solve the ship stowage planning problem of coils in the steel industry","authors":"Yun Dong, Yuan Yuan, Guoqiang Wang","doi":"10.1109/FISTS.2016.7552317","DOIUrl":"https://doi.org/10.1109/FISTS.2016.7552317","url":null,"abstract":"Differential evolution (DE) is a very simple and effective stochastic search algorithm, which obtains various performances with different parameter and searching strategy configurations. DE with an individual-dependent mechanism (IDE) is a recently proposed DE variant, which includes an individual-dependent parameter (IDP) setting method and an individual-dependent mutation (IDM) strategy. In this paper, to validate the ability of IDE on solving real-world optimization problem, we first modify it by intruding Cauchy distribution to generate random control parameters and simplifying the proportion function and threshold functions. Subsequently, we test the performance of new IDE via CEC 2014 benchmark suite of single objective real-parameter numerical optimization. In addition, we apply it to solve a ship stowage planning problem in which the objective function is minimizing the stability deviation of the ship. The numerical results demonstrate the good performance of new IDE on solve these two kinds of optimization problems.","PeriodicalId":179987,"journal":{"name":"2016 IEEE Forum on Integrated and Sustainable Transportation Systems (FISTS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115396781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-07-10DOI: 10.1109/FISTS.2016.7552320
W. C. Ku, G. Jagadeesh, Alok Prakash, T. Srikanthan
The problem of missing samples in road traffic data undermines the performance of intelligent transportation applications. This paper proposes a data-driven imputation method that exploits the spatial and temporal relationships existing between the traffic flows of multiple road segments that are correlated with each other. The K-means clustering technique is used to group together road segments with similar traffic flow patterns. Next, a deep-learning model based on stacked denoising autoencoders is constructed for each group of road segments to extract their spatial-temporal relationships and use them for imputing the missing data points. Experiments conducted with real traffic data demonstrate that the imputation accuracy of the proposed method is robust under different missing data rates.
{"title":"A clustering-based approach for data-driven imputation of missing traffic data","authors":"W. C. Ku, G. Jagadeesh, Alok Prakash, T. Srikanthan","doi":"10.1109/FISTS.2016.7552320","DOIUrl":"https://doi.org/10.1109/FISTS.2016.7552320","url":null,"abstract":"The problem of missing samples in road traffic data undermines the performance of intelligent transportation applications. This paper proposes a data-driven imputation method that exploits the spatial and temporal relationships existing between the traffic flows of multiple road segments that are correlated with each other. The K-means clustering technique is used to group together road segments with similar traffic flow patterns. Next, a deep-learning model based on stacked denoising autoencoders is constructed for each group of road segments to extract their spatial-temporal relationships and use them for imputing the missing data points. Experiments conducted with real traffic data demonstrate that the imputation accuracy of the proposed method is robust under different missing data rates.","PeriodicalId":179987,"journal":{"name":"2016 IEEE Forum on Integrated and Sustainable Transportation Systems (FISTS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121960272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-07-10DOI: 10.1109/FISTS.2016.7552318
Shulian Wu
Public-private Partnership (PPP) is widely used to provide public infrastructure and services around the world. Chinese central government has also promoted this model since 2013 and it is estimated that there would be more and more PPP projects to be implemented in China. The foreign experiences that renegotiation has been more and more with PPP projects development. However, few studies have been conducted to identify critical PPP renegotiation risks for private sectors in transportation projects in China and therefore the effective strategies to respond to such risks are lack. Based on the identified critical PPP renegotiation risks for private sectors, effective strategies are provided for references. The strategies can facilitate the private sectors better manage renegotiation risks during implementation, which can also promote healthy development of PPP transportation projects in China.
{"title":"Strategies for private sector to treat PPP renegotiation risks in transportation projects in china","authors":"Shulian Wu","doi":"10.1109/FISTS.2016.7552318","DOIUrl":"https://doi.org/10.1109/FISTS.2016.7552318","url":null,"abstract":"Public-private Partnership (PPP) is widely used to provide public infrastructure and services around the world. Chinese central government has also promoted this model since 2013 and it is estimated that there would be more and more PPP projects to be implemented in China. The foreign experiences that renegotiation has been more and more with PPP projects development. However, few studies have been conducted to identify critical PPP renegotiation risks for private sectors in transportation projects in China and therefore the effective strategies to respond to such risks are lack. Based on the identified critical PPP renegotiation risks for private sectors, effective strategies are provided for references. The strategies can facilitate the private sectors better manage renegotiation risks during implementation, which can also promote healthy development of PPP transportation projects in China.","PeriodicalId":179987,"journal":{"name":"2016 IEEE Forum on Integrated and Sustainable Transportation Systems (FISTS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132741572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-07-10DOI: 10.1109/FISTS.2016.7552319
Rui Zhang, Yulin Ma, Xiaofeng Liu
This paper proposes a successive approximation algorithm (SAA) for intelligent vehicle speed adaption (IVSA) based on energy dissipation. As vehicle dynamical system resembles a series of mass/spring/damper systems that are dissipative, i.e., the energy of the system decays to zero eventually, the problem of IVSA is transformed into dissipative control design based on energy storage function. In order to satisfy the γ-performance with respect to the quadratic supply rate, the storage function is developed by using a backstepping based Lyapunov method based on a step-by-step improvement of performance bounds. A dissipative control law is designed by a SAA with a step-by-step reduction of the value of γ. The IVSA simulations are given under variable acceleration condition, whose performances are verified by the comparison of both longitudinal and lateral tracking errors and energy-consuming in different values of γ.
{"title":"Energy dissipation based successive approximation algorithm for intelligent vehicle speed adaption*","authors":"Rui Zhang, Yulin Ma, Xiaofeng Liu","doi":"10.1109/FISTS.2016.7552319","DOIUrl":"https://doi.org/10.1109/FISTS.2016.7552319","url":null,"abstract":"This paper proposes a successive approximation algorithm (SAA) for intelligent vehicle speed adaption (IVSA) based on energy dissipation. As vehicle dynamical system resembles a series of mass/spring/damper systems that are dissipative, i.e., the energy of the system decays to zero eventually, the problem of IVSA is transformed into dissipative control design based on energy storage function. In order to satisfy the γ-performance with respect to the quadratic supply rate, the storage function is developed by using a backstepping based Lyapunov method based on a step-by-step improvement of performance bounds. A dissipative control law is designed by a SAA with a step-by-step reduction of the value of γ. The IVSA simulations are given under variable acceleration condition, whose performances are verified by the comparison of both longitudinal and lateral tracking errors and energy-consuming in different values of γ.","PeriodicalId":179987,"journal":{"name":"2016 IEEE Forum on Integrated and Sustainable Transportation Systems (FISTS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115646337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：