Pub Date : 2019-07-01DOI: 10.1109/ICTIS.2019.8883751
Fenglu Zhao, Ruishan Sun, Xiongbing Chen, Kai Zhang, Shunmei Han
In order to provide scientific advice for civil aviation safety management, this paper analyzes and forecasts the fluctuation rules of Chinese civil aviation incidents. For the said purpose, a research based on the time series of the monthly incidents per 10000 flight hours from 2006–2016 year was done by model of X–12 seasonal adjustment multiplication. And then the time series was decomposed into seasonal periodic components, trend components, and random components. On this basis, the Autoregressive Integrated Moving Average (ARIMA) model, the trend regression model and the mean value method were used to predict the sequence of each sequence respectively. The X–12 multiplication model was used to restore the fitting value and the prediction value of the frequency of the accident, and the actual data were used to verify the value. The results show that: the monthly incidents per 10000 flight hours from 2006–2016 year have obvious trends and seasonality. September and April each year are the most affected by the seasons, and December and January are the least affected by the seasons; in the long run, the 2006–2008 year trend is declining, the 2009–2016 year trend is fluctuating, and the other stages tend to be stable. The prediction results show that the accuracy is more reliable. In 2017, the highest monthly incidents per 10000 flight hours is in October and the second in June.
{"title":"Flight Incidents Prediction Based on Model of X-12 and ARIMA","authors":"Fenglu Zhao, Ruishan Sun, Xiongbing Chen, Kai Zhang, Shunmei Han","doi":"10.1109/ICTIS.2019.8883751","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883751","url":null,"abstract":"In order to provide scientific advice for civil aviation safety management, this paper analyzes and forecasts the fluctuation rules of Chinese civil aviation incidents. For the said purpose, a research based on the time series of the monthly incidents per 10000 flight hours from 2006–2016 year was done by model of X–12 seasonal adjustment multiplication. And then the time series was decomposed into seasonal periodic components, trend components, and random components. On this basis, the Autoregressive Integrated Moving Average (ARIMA) model, the trend regression model and the mean value method were used to predict the sequence of each sequence respectively. The X–12 multiplication model was used to restore the fitting value and the prediction value of the frequency of the accident, and the actual data were used to verify the value. The results show that: the monthly incidents per 10000 flight hours from 2006–2016 year have obvious trends and seasonality. September and April each year are the most affected by the seasons, and December and January are the least affected by the seasons; in the long run, the 2006–2008 year trend is declining, the 2009–2016 year trend is fluctuating, and the other stages tend to be stable. The prediction results show that the accuracy is more reliable. In 2017, the highest monthly incidents per 10000 flight hours is in October and the second in June.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132341908","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883821
Mingjian Lu, Xin-ping Yan, Jian Wang, Yuwei Sun, Zikang Gong
Printed circuit heat exchanger (PCHE) is a new type of millimeter–level channel heat exchanger. The working fluid in the PCHE precooler of the supercritical carbon dioxide (SCO2) Brayton cycle usually works near or cross the pseudo-critical point, where the thermophysical properties exhibit drastic nonlinear characteristics. This brings challenges to analysis the thermal hydraulic performance of the PCHE. In present paper, a straight channel PCHE precooler model is established by the segment method to accurately account for the change of thermophysical properties. The precooler is designed by adopting the Gnielinski empirical correlations. Local heat transfer and pressure drop characteristics of SCO2 along the length are analyzed. The results show that the designed length obtained by segment method is significantly larger than by logarithmic mean temperature difference (LMTD) method. Overall the local temperature difference decreases from the hot end to the cold end. The heat transfer coefficient on SCO2 side is more relevant to the Prandtl number than the Reynolds number. The research results are of great significance for the development of PCHE design methods.
{"title":"Thermal Hydraulic Performance Analysis of PCHE Precooler for Supercritical CO2 Brayton Cycle","authors":"Mingjian Lu, Xin-ping Yan, Jian Wang, Yuwei Sun, Zikang Gong","doi":"10.1109/ICTIS.2019.8883821","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883821","url":null,"abstract":"Printed circuit heat exchanger (PCHE) is a new type of millimeter–level channel heat exchanger. The working fluid in the PCHE precooler of the supercritical carbon dioxide (SCO2) Brayton cycle usually works near or cross the pseudo-critical point, where the thermophysical properties exhibit drastic nonlinear characteristics. This brings challenges to analysis the thermal hydraulic performance of the PCHE. In present paper, a straight channel PCHE precooler model is established by the segment method to accurately account for the change of thermophysical properties. The precooler is designed by adopting the Gnielinski empirical correlations. Local heat transfer and pressure drop characteristics of SCO2 along the length are analyzed. The results show that the designed length obtained by segment method is significantly larger than by logarithmic mean temperature difference (LMTD) method. Overall the local temperature difference decreases from the hot end to the cold end. The heat transfer coefficient on SCO2 side is more relevant to the Prandtl number than the Reynolds number. The research results are of great significance for the development of PCHE design methods.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114453306","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883707
Huaizhong Zhu, Xiaoguang Yang, Yizhe Wang, N. Zhang
Car-following models are the core component of microscopic traffic simulation. Most of the deterministic models take fixed parameter values for different drivers. However, considerable behavioral differences exist between individual drivers. Simulating car-following behaviors of different drivers thus poses a challenge for microscopic traffic simulation. In this study, three approaches to calibrating car-following models for a group of heterogeneous drivers (calibrating an ‘average’ driver, calibrating at an individual-driver level, calibrating based on clustered drivers’ data) were tested with real-world driving data. Specifically, twenty randomly selected drivers’ car-following trajectories extracted from the Safety Pilot Model Deployment (SPMD) project were used to calibrate the intelligent driver model (IDM) with the abovementioned three calibration approaches. The errors of replicating drivers’ behavior in the validation datasets were used to evaluate the performances of the three calibration approaches.Results show that 1) calibrating at the individual level (i.e., each driver has its own model parameters) has the best performance in replicating a group of drivers’ car-following behavior; 2) calibrating an ‘average’ driver based on all drivers’ data performs worst; 3) calibrating at the cluster level achieves intermediate performance; and 4) simply averaging calibrated individual drivers’ parameters is not a good way to simulate a group of heterogeneous drivers’ car-following behavior. The results suggest that inter-driver heterogeneity in car-following should not be neglected in microscopic traffic simulation, and also that there is a need to develop archetypes of a variety of drivers to build a traffic mix in simulation.
{"title":"Simulating Car-following Behavior for Heteregeneous Drivers: the Need for Driver Specific Model Parameters","authors":"Huaizhong Zhu, Xiaoguang Yang, Yizhe Wang, N. Zhang","doi":"10.1109/ICTIS.2019.8883707","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883707","url":null,"abstract":"Car-following models are the core component of microscopic traffic simulation. Most of the deterministic models take fixed parameter values for different drivers. However, considerable behavioral differences exist between individual drivers. Simulating car-following behaviors of different drivers thus poses a challenge for microscopic traffic simulation. In this study, three approaches to calibrating car-following models for a group of heterogeneous drivers (calibrating an ‘average’ driver, calibrating at an individual-driver level, calibrating based on clustered drivers’ data) were tested with real-world driving data. Specifically, twenty randomly selected drivers’ car-following trajectories extracted from the Safety Pilot Model Deployment (SPMD) project were used to calibrate the intelligent driver model (IDM) with the abovementioned three calibration approaches. The errors of replicating drivers’ behavior in the validation datasets were used to evaluate the performances of the three calibration approaches.Results show that 1) calibrating at the individual level (i.e., each driver has its own model parameters) has the best performance in replicating a group of drivers’ car-following behavior; 2) calibrating an ‘average’ driver based on all drivers’ data performs worst; 3) calibrating at the cluster level achieves intermediate performance; and 4) simply averaging calibrated individual drivers’ parameters is not a good way to simulate a group of heterogeneous drivers’ car-following behavior. The results suggest that inter-driver heterogeneity in car-following should not be neglected in microscopic traffic simulation, and also that there is a need to develop archetypes of a variety of drivers to build a traffic mix in simulation.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125656242","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883442
Zibo Zhu, Chunfang Feng, Yangyang Zhao, Jian Lu
Separate dual-left turn lane is a new type of inlet channelization, which has been tentatively set in many cities. Through the actual measurement and analysis, it is found that the separate dual-left turn traffic flow has obvious interference at the exit position of the intersection, the traffic efficiency is significantly lower than the entrance position. According to the analysis of vehicle mutual interference based on separate dual-left turn traffic flow at exit position and quantization model of force and relative position, this paper gives the range of safety distance between the left-turning vehicles driven in inner and outer lanes. It analyzed the turning angles of vehicles driven in both inner and outer lanes by the exit position. Based on all the researches this paper brings out a guide line setting method for vehicle flow release in the case of separate dual-left turn lane setting is proposed. This research fulfills the blank of the existed traffic guide line setting specification GB5768.2, which makes a significant theoretical support for the signalized intersection traffic guide line setting work.
{"title":"Research on Setting Method of Guide Line of Separate Dual-Left Turn Lanes","authors":"Zibo Zhu, Chunfang Feng, Yangyang Zhao, Jian Lu","doi":"10.1109/ICTIS.2019.8883442","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883442","url":null,"abstract":"Separate dual-left turn lane is a new type of inlet channelization, which has been tentatively set in many cities. Through the actual measurement and analysis, it is found that the separate dual-left turn traffic flow has obvious interference at the exit position of the intersection, the traffic efficiency is significantly lower than the entrance position. According to the analysis of vehicle mutual interference based on separate dual-left turn traffic flow at exit position and quantization model of force and relative position, this paper gives the range of safety distance between the left-turning vehicles driven in inner and outer lanes. It analyzed the turning angles of vehicles driven in both inner and outer lanes by the exit position. Based on all the researches this paper brings out a guide line setting method for vehicle flow release in the case of separate dual-left turn lane setting is proposed. This research fulfills the blank of the existed traffic guide line setting specification GB5768.2, which makes a significant theoretical support for the signalized intersection traffic guide line setting work.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132109599","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883703
Jinyan Zhu, Wanqing Zhang, Han Luo, Hongheng Liu, Rongchun Shi
In many cities, the asphalt beside the rail at intersection often cracks under traffic load after tramcar running for several months. The main reason is that the rail flexible material is not strength enough to provide brace for asphalt. The strength of rail flexible material is closely related to its structure. In this article, several parameters such as wall thickness, interval distance of ribbed slabs and so on are chosen to change the structure of the rail flexible material. The deformations under traffic loads of different structures are calculated through building finite element models. At last, reasonable structure parameters of the rail flexible material are recommended.
{"title":"Structure Design of Rail Flexible Material Based on Mechanical Calculation","authors":"Jinyan Zhu, Wanqing Zhang, Han Luo, Hongheng Liu, Rongchun Shi","doi":"10.1109/ICTIS.2019.8883703","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883703","url":null,"abstract":"In many cities, the asphalt beside the rail at intersection often cracks under traffic load after tramcar running for several months. The main reason is that the rail flexible material is not strength enough to provide brace for asphalt. The strength of rail flexible material is closely related to its structure. In this article, several parameters such as wall thickness, interval distance of ribbed slabs and so on are chosen to change the structure of the rail flexible material. The deformations under traffic loads of different structures are calculated through building finite element models. At last, reasonable structure parameters of the rail flexible material are recommended.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134430319","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883588
Yong Zeng, Jin-fen Zhang, Mingyang Zhang, Liu Tingwen
Collision between ships is one of the most common types of accident in most navigable waters. A fast and effective anti-collision decision making procedure is significant for the safety of the navigating ships. The ships have to adhere to the International Regulations for Preventing Collisions at Sea (COLREGs) during navigating, which is subjective to a large degree. The paper presents a mathematical model to compute the distance to closest point of approach (DCPA) and calculated the derivative of own ship’s course and velocity, based on which the effectiveness of avoiding collision by course alteration and speed change are evaluated in a quantitative way under different encounter situations. The simulation results indicate that in most cases course alteration performs better than changing velocity for the encounter situations with large crossing angle while changing velocity performs better under some encounter situations with small crossing angle. Two case studies are conducted to evaluate the proposed approach.
{"title":"Anti-collision Decision Making by Course Alteration and Speed Change under COLREGs","authors":"Yong Zeng, Jin-fen Zhang, Mingyang Zhang, Liu Tingwen","doi":"10.1109/ICTIS.2019.8883588","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883588","url":null,"abstract":"Collision between ships is one of the most common types of accident in most navigable waters. A fast and effective anti-collision decision making procedure is significant for the safety of the navigating ships. The ships have to adhere to the International Regulations for Preventing Collisions at Sea (COLREGs) during navigating, which is subjective to a large degree. The paper presents a mathematical model to compute the distance to closest point of approach (DCPA) and calculated the derivative of own ship’s course and velocity, based on which the effectiveness of avoiding collision by course alteration and speed change are evaluated in a quantitative way under different encounter situations. The simulation results indicate that in most cases course alteration performs better than changing velocity for the encounter situations with large crossing angle while changing velocity performs better under some encounter situations with small crossing angle. Two case studies are conducted to evaluate the proposed approach.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133195072","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883731
Hongtai Yang, Xiuqin Liang, Zhaolin Zhang, Xu Zhang, Malik Muneeb Abid, Yugang Liu
Traveling Salesman Problem (TSP) plays an important role in research and has many applications in the field of transportation and logistics. Most studies focus on developing algorithms to find the shortest path while some studies explore the average length of the shortest paths. However, the quartiles and variance of the shortest paths have not been studied so far. The quartiles and variance of the shortest paths are important because they can give information about the travel/delivery time reliability and the best and worst travel/delivery time scenario, when the tour can be regarded as TSP. This study performs experiments to find the shortest path connecting n customers, which are generated randomly in a specified service area, using genetic algorithm. The service areas considered include equilateral triangle, rectangle with ratio of length and width ranging from 1 to 8, regular hexagon, and circle. The number of customers considered range from 10 to 100 with an interval of 10. In each experiment, the customers are generated randomly for 500 times. The first, second and third quartiles as well as the variance of the 500 shortest paths have been recorded. Subsequently, regression models have been developed to estimate quartiles and variance using number of customers and parameters of service area. R squares of the developed models are all above 0.96, indicating very good fit. The constructed models can be used to estimate the travel time variance and reliability.
{"title":"Modeling Quartiles and Variance of Optimal Traveling Salesman Tour Lengths","authors":"Hongtai Yang, Xiuqin Liang, Zhaolin Zhang, Xu Zhang, Malik Muneeb Abid, Yugang Liu","doi":"10.1109/ICTIS.2019.8883731","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883731","url":null,"abstract":"Traveling Salesman Problem (TSP) plays an important role in research and has many applications in the field of transportation and logistics. Most studies focus on developing algorithms to find the shortest path while some studies explore the average length of the shortest paths. However, the quartiles and variance of the shortest paths have not been studied so far. The quartiles and variance of the shortest paths are important because they can give information about the travel/delivery time reliability and the best and worst travel/delivery time scenario, when the tour can be regarded as TSP. This study performs experiments to find the shortest path connecting n customers, which are generated randomly in a specified service area, using genetic algorithm. The service areas considered include equilateral triangle, rectangle with ratio of length and width ranging from 1 to 8, regular hexagon, and circle. The number of customers considered range from 10 to 100 with an interval of 10. In each experiment, the customers are generated randomly for 500 times. The first, second and third quartiles as well as the variance of the 500 shortest paths have been recorded. Subsequently, regression models have been developed to estimate quartiles and variance using number of customers and parameters of service area. R squares of the developed models are all above 0.96, indicating very good fit. The constructed models can be used to estimate the travel time variance and reliability.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"931 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133383768","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883755
Min Tu, Qingming Zou, Zhuo Chen
Urban road structure is an important factor affecting the distribution of urban logistics industry. As the core carrier and organization subject of logistics space, logistics nodes and logistics enterprises have important significance for optimizing the spatial layout of urban logistics and rational allocation of logistics resources. Based on the Baidu Point of Interest (POI) platform, this paper collect massive data of logistics nodes, logistics enterprises and logistics facilities in Wuhan, study the spatial accessibility and logistics of road networks and the agglomeration characteristics of logistics industry by using spatial syntax model and GIS nuclear density method, and the relationship between them is illustrated by bivariate analysis. The results show that: 1 The overall distribution of the logistics industry is characterized by a spatial pattern of Chinese character “North”-shaped distribution along the banks of the Yangtze River, and different types of POIs are presented in different layouts and hierarchical levels. Among them, the logistics nodes are concentrated in the city center, the logistics facilities are around City ring line, and logistics enterprises match the industrial layout. 2 The roads in the central city, the urban ring road and the external traffic circle have good permeability, and can quickly realize the space connection, so it corresponds to the area where the logistics industry is highly concentrated.
{"title":"Research on Location Characteristics of Logistics Industry in Wuhan Based on Spatial Syntax and POI","authors":"Min Tu, Qingming Zou, Zhuo Chen","doi":"10.1109/ICTIS.2019.8883755","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883755","url":null,"abstract":"Urban road structure is an important factor affecting the distribution of urban logistics industry. As the core carrier and organization subject of logistics space, logistics nodes and logistics enterprises have important significance for optimizing the spatial layout of urban logistics and rational allocation of logistics resources. Based on the Baidu Point of Interest (POI) platform, this paper collect massive data of logistics nodes, logistics enterprises and logistics facilities in Wuhan, study the spatial accessibility and logistics of road networks and the agglomeration characteristics of logistics industry by using spatial syntax model and GIS nuclear density method, and the relationship between them is illustrated by bivariate analysis. The results show that: 1 The overall distribution of the logistics industry is characterized by a spatial pattern of Chinese character “North”-shaped distribution along the banks of the Yangtze River, and different types of POIs are presented in different layouts and hierarchical levels. Among them, the logistics nodes are concentrated in the city center, the logistics facilities are around City ring line, and logistics enterprises match the industrial layout. 2 The roads in the central city, the urban ring road and the external traffic circle have good permeability, and can quickly realize the space connection, so it corresponds to the area where the logistics industry is highly concentrated.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116981398","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883692
Huaizhong Zhu, Xiaoguang Yang, Yizhe Wang, N. Zhang
Accurate prediction of multimodal public transportation sharing rate is of great significance in coordinating traffic management, increasing public transport efficiency and allocating resources properly. The daily number of trips by subway, bus and ferry of pubic transport is calculated through data reduction and data mining, and the data of main factors affecting the fluctuation of public transportation sharing rate, i.e. holidays (or not), weather and air temperature, is collected in this paper based on big data on swiping public transportation IC cards in Shanghai. In addition, the sharing rates of subway, bus and ferry are predicted by using deep learning model based on historical data on daily number of trips and main influence factors, setting characteristic data and label data, and selecting activation function, loss function and gradient descent algorithm. The results show that the prediction error is less than 2.9%.
{"title":"The Prediction of Multimodal Public Transportation Sharing Rate Based on Data","authors":"Huaizhong Zhu, Xiaoguang Yang, Yizhe Wang, N. Zhang","doi":"10.1109/ICTIS.2019.8883692","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883692","url":null,"abstract":"Accurate prediction of multimodal public transportation sharing rate is of great significance in coordinating traffic management, increasing public transport efficiency and allocating resources properly. The daily number of trips by subway, bus and ferry of pubic transport is calculated through data reduction and data mining, and the data of main factors affecting the fluctuation of public transportation sharing rate, i.e. holidays (or not), weather and air temperature, is collected in this paper based on big data on swiping public transportation IC cards in Shanghai. In addition, the sharing rates of subway, bus and ferry are predicted by using deep learning model based on historical data on daily number of trips and main influence factors, setting characteristic data and label data, and selecting activation function, loss function and gradient descent algorithm. The results show that the prediction error is less than 2.9%.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114776273","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 : 2019-07-01DOI: 10.1109/ICTIS.2019.8883718
Tianqi Zha, Lei Xie, Jiliang Chang
In recent years, the scale of offshore wind farms is increasing because of the high efficiency and pollution-free wind power resources. However, the introduction of many facilities in the corresponding wind farm sea area has led to the increasing difficulty of ship navigation. Therefore, it is very important to plan safe and efficient driving path according to the corresponding starting and ending points for the navigation of ships in the increasing wind farm area. In this paper, a path planning algorithm based on the hybrid method of A* algorithm and reinforcement learning is proposed, which can plan an effective collision avoidance path for the sea area of wind farm. Then the method is used to simulate the ship’s path planning in a wind farm, which proves the feasibility of the method. Finally, it shows that the method has universal reference significance for ship navigation in the wind farm waters.
{"title":"Wind farm water area path planning algorithm based on A* and reinforcement learning","authors":"Tianqi Zha, Lei Xie, Jiliang Chang","doi":"10.1109/ICTIS.2019.8883718","DOIUrl":"https://doi.org/10.1109/ICTIS.2019.8883718","url":null,"abstract":"In recent years, the scale of offshore wind farms is increasing because of the high efficiency and pollution-free wind power resources. However, the introduction of many facilities in the corresponding wind farm sea area has led to the increasing difficulty of ship navigation. Therefore, it is very important to plan safe and efficient driving path according to the corresponding starting and ending points for the navigation of ships in the increasing wind farm area. In this paper, a path planning algorithm based on the hybrid method of A* algorithm and reinforcement learning is proposed, which can plan an effective collision avoidance path for the sea area of wind farm. Then the method is used to simulate the ship’s path planning in a wind farm, which proves the feasibility of the method. Finally, it shows that the method has universal reference significance for ship navigation in the wind farm waters.","PeriodicalId":325712,"journal":{"name":"2019 5th International Conference on Transportation Information and Safety (ICTIS)","volume":"601 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116311198","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：