Search scope:
排序: Display mode:
Forecasting traffic flows in irregular regions with multi-graph convolutional network and gated recurrent unit Research Articles
Dewen Seng, Fanshun Lv, Ziyi Liang, Xiaoying Shi, Qiming Fang,sengdw@hdu.edu.cn,172050041@hdu.edu.cn,liangziyi2020@163.com,shixiaoying@hdu.edu.cn,fangqiming@hdu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 9, Pages 1179-1193 doi: 10.1631/FITEE.2000243
Keywords: 交通流量预测;多图卷积网络;门控循环单元;不规则区域
Interpreting the vulnerability of power systems in cascading failures using multi-graph convolutional networks Research Article
Supaporn LONAPALAWONG, Changsheng CHEN, Can WANG, Wei CHEN
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 12, Pages 1848-1861 doi: 10.1631/FITEE.2200035
Keywords: Power systems Vulnerability Cascading failures Multi-graph convolutional networks Weighted line graph
Video summarization with a graph convolutional attention network Research Articles
Ping Li, Chao Tang, Xianghua Xu,patriclouis.lee@gmail.com
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 6, Pages 902-913 doi: 10.1631/FITEE.2000429
Keywords: 时序学习;自注意力机制;图卷积网络;上下文融合;视频摘要
Cell-Zone Method: An Engineering Approach to Predict Smoke Movement in Large Scale Building Fire
Hu Longhua,Huo Ran,Liy Uanzhou,Wang Haobo
Strategic Study of CAE 2003, Volume 5, Issue 8, Pages 59-63
In large scale building fire, it is improper to predict smoke descending using traditional simple two-layer zone model, which divides the total space of the building into upper hot smoke layer and lower cool air layer. In this paper, an improved method, named Cell-Zone Method, is used to solve this problem, which first divides the total space into some small subspaces and then uses traditional two-layer zone model in each subspace. Comparison is carried out between these two methods in fire smoke development simulation in typical large space buildings by CFAST4.02 software package. Results show that Cell-Zone Method demonstrates more applicability than traditional simple two-layer zone model in large scale building, especially in buildings having large scale in one direction.
Keywords: large scale building smoke movement cell-zone method zone-model
A distributed EEMDN-SABiGRU model on Spark for passenger hotspot prediction
夏大文,耿建,黄瑞曦,申冰琪,胡杨,李艳涛,李华青
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9, Pages 1316-1331 doi: 10.1631/FITEE.2200621
Keywords: Passenger hotspot prediction Ensemble empirical mode decomposition (EEMD) Spatial attention mechanism Bi-directional gated recurrent unit (BiGRU) GPS trajectory Spark
Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images Research Article
Xiaolong CHEN, Xiaoqian MU, Jian GUAN, Ningbo LIU, Wei ZHOU,cxlcxl1209@163.com,guanjian_68@163.com
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 4, Pages 630-643 doi: 10.1631/FITEE.2000611
Keywords: Marine target detection Navigation radar Plane position indicator (PPI) images Convolutional neural network (CNN) Faster R-CNN (region convolutional neural network) method
Study on realtime method of traffic flow guidance system
Cui Jianming,Ye Huaizhen
Strategic Study of CAE 2008, Volume 10, Issue 10, Pages 64-66
Real-time guidance system of traffic flow is information reconstruct in unit time. If events occut in short periodic time, these events will inflict the normal traffic guidance. In this paper, a new and simple solution scheme is proposed by analyzing status traffic situation. In this plan, systematic revision for read-time guidance in burst event is added to deduce reaction time. This scheme is imporved technology built on the current guidance system, therefore, this conclusion can be widly applied to traffic flow guidance system.
Keywords: traffic flow guidance system simulation emergent events real-time guidance
Amultimodal dense convolution network for blind image quality assessment Research Article
Nandhini CHOCKALINGAM, Brindha MURUGAN
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1601-1615 doi: 10.1631/FITEE.2200534
Keywords: No-reference image quality assessment (NR-IQA) Blind image quality assessment Multimodal dense convolution network (MDSC-Net) Deep learning Visual quality Perceptual quality
Multi-focus image fusion based on fully convolutional networks Research Articles
Rui Guo, Xuan-jing Shen, Xiao-yu Dong, Xiao-li Zhang,zhangxiaoli@jlu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7, Pages 963-1118 doi: 10.1631/FITEE.1900336
Keywords: 多焦距图像融合;全卷积网络;跳层;性能评估
Shi Shiliang,Wu Aiyou
Strategic Study of CAE 2009, Volume 11, Issue 9, Pages 91-96
The coal and gas outburst is a dynamic pheaomenon in the underground exploitation of coal mine,and the strong dynamic effect can result in damage of belongs and death of workers of coal mine. Therefore,it is very important to advance coal industry healthy and continual in forecast the area of coal and gas outburst reasonablely.This paper aimed at the defect that neural network is easy to fall into some extremely local smallness and cause the unreasonable distribution of the weight value of the forecast indexes,ade the area forecast model of the coal and gas outburst was established based on coupling of the neural network and the genetic algorithm according to the natural conditions and the characteristics of the geologic structure. The coupling forecast model was validated with the practical example.The study results has proved the validity of the model, and laid the foundation of the area forecast of the coal and gas outburst based on coupling of the neural network and genetic algorithm.
Keywords: coal and gas outburst area forecast neural network genetic algorithm isoneph of outburst
A highly efficient reconfigurable rotation unit based on an inverse butterfly network Article
Chao MA, Zi-bin DAI, Wei LI, Hai-juan ZANG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 11, Pages 1784-1794 doi: 10.1631/FITEE.1601265
Keywords: Rotation operations Self-routing Control-bit generation algorithm Inverse butterfly network
Integrated Network Design and Demand Forecast for On-Demand Urban Air Mobility Article
Zhiqiang Wu, Yu Zhang
Engineering 2021, Volume 7, Issue 4, Pages 473-487 doi: 10.1016/j.eng.2020.11.007
Urban air mobility (UAM) is an emerging concept proposed in recent years that uses electric vertical take-off and landing vehicles (eVTOLs). UAM is expected to offer an alternative way of transporting passengers and goods in urban areas with significantly improved mobility by making use of low-altitude airspace. In addition to other essential elements, ground infrastructure of vertiports is needed to transition UAM from concept to operation. This study examines the network design of UAM on-demand service, with a particular focus on the use of integer programming and a solution algorithm to determine the optimal locations of vertiports, user allocation to vertiports, and vertiport access- and egress-mode choices while considering the interactions between vertiport locations and potential UAM travel demand. A case study based on simulated disaggregate travel demand data of the Tampa Bay area in Florida, USA was conducted to demonstrate the effectiveness of the proposed model. Candidate vertiport locations were obtained by analyzing a three-dimensional (3D) geographic information system (GIS) map developed from lidar data of Florida and physical and regulation constraints of eVTOL operations at vertiports. Optimal locations of vertiports were determined to achieve the minimal total generalized cost; however, the modeling structure allows each user to select a better mode between ground transportation and UAM in terms of generalized cost. The outcomes of the case study reveal that although the percentage of trips that switched from ground mode to multimodal UAM was small, users choosing the UAM service benefited from significant time saving. In addition, the impact of different parameter settings on the demand for UAM service was explored from the supply side, and different pricing strategies were tested that might influence potential demand and revenue generation for UAM operators. The combined effects of the number of vertiports and pricing strategies were also analyzed. The findings from this study offer in-depth planning and managerial insights for municipal decision-makers and UAM operators. The conclusion of this paper discusses caveats to the study, ongoing efforts by the authors, and future directions in UAM research.
Keywords: Advanced air mobility Skyport Travel mode choice Low-altitude airspace Unmanned systems
Petros Ioannou: Autopilot Connectivity and Traffic Flow Control (2019-9-18)
12 Aug 2021
Keywords: 交通
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Engineering 2021, Volume 7, Issue 12, Pages 1751-1765 doi: 10.1016/j.eng.2020.10.023
Dissolved oxygen (DO) is an important indicator of aquaculture, and its accurate forecasting can effectively improve the quality of aquatic products. In this paper, a new DO hybrid forecasting model is proposed that includes three stages: multi-factor analysis, adaptive decomposition, and an optimization-based ensemble. First, considering the complex factors affecting DO, the grey relational (GR) degree method is used to screen out the environmental factors most closely related to DO. The consideration of multiple factors makes model fusion more effective. Second, the series of DO, water temperature, salinity, and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform (EWT) method. Then, five benchmark models are utilized to forecast the sub-series of EWT decomposition. The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm (PSOGSA). Finally, a multi-factor ensemble model for DO is obtained by weighted allocation. The performance of the proposed model is verified by time-series data collected by the pacific islands ocean observing system (PacIOOS) from the WQB04 station at Hilo. The evaluation indicators involved in the experiment include the nash-sutcliffe efficiency (NSE), kling-gupta efficiency (KGE), mean absolute percent error (MAPE), standard deviation of error (SDE), and coefficient of determination (R2). Example analysis demonstrates that: ① the proposed model can obtain excellent DO forecasting results; ② the proposed model is superior to other comparison models; and ③ the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.
Keywords: Dissolved oxygen concentrations forecasting Time-series multi-step forecasting Multi-factor analysis Empirical wavelet transform decomposition Multi-model optimization ensemble
A many-objective evolutionary algorithm based on decomposition with dynamic resource allocation for irregular optimization Research Articles
Ming-gang Dong, Bao Liu, Chao Jing,jingchao@glut.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 8, Pages 1119-1266 doi: 10.1631/FITEE.1900321
Keywords: Many-objective optimization problems Irregular Pareto front External archive Dynamic resource allocation Shift-based density estimation Tchebycheff approach
Title Author Date Type Operation
Forecasting traffic flows in irregular regions with multi-graph convolutional network and gated recurrent unit
Dewen Seng, Fanshun Lv, Ziyi Liang, Xiaoying Shi, Qiming Fang,sengdw@hdu.edu.cn,172050041@hdu.edu.cn,liangziyi2020@163.com,shixiaoying@hdu.edu.cn,fangqiming@hdu.edu.cn
Journal Article
Interpreting the vulnerability of power systems in cascading failures using multi-graph convolutional networks
Supaporn LONAPALAWONG, Changsheng CHEN, Can WANG, Wei CHEN
Journal Article
Video summarization with a graph convolutional attention network
Ping Li, Chao Tang, Xianghua Xu,patriclouis.lee@gmail.com
Journal Article
Cell-Zone Method: An Engineering Approach to Predict Smoke Movement in Large Scale Building Fire
Hu Longhua,Huo Ran,Liy Uanzhou,Wang Haobo
Journal Article
A distributed EEMDN-SABiGRU model on Spark for passenger hotspot prediction
夏大文,耿建,黄瑞曦,申冰琪,胡杨,李艳涛,李华青
Journal Article
Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images
Xiaolong CHEN, Xiaoqian MU, Jian GUAN, Ningbo LIU, Wei ZHOU,cxlcxl1209@163.com,guanjian_68@163.com
Journal Article
Amultimodal dense convolution network for blind image quality assessment
Nandhini CHOCKALINGAM, Brindha MURUGAN
Journal Article
Multi-focus image fusion based on fully convolutional networks
Rui Guo, Xuan-jing Shen, Xiao-yu Dong, Xiao-li Zhang,zhangxiaoli@jlu.edu.cn
Journal Article
Study on area forecast of coal and gas outburst based on coupling of neural network and genetic algorithm
Shi Shiliang,Wu Aiyou
Journal Article
A highly efficient reconfigurable rotation unit based on an inverse butterfly network
Chao MA, Zi-bin DAI, Wei LI, Hai-juan ZANG
Journal Article
Integrated Network Design and Demand Forecast for On-Demand Urban Air Mobility
Zhiqiang Wu, Yu Zhang
Journal Article
Petros Ioannou: Autopilot Connectivity and Traffic Flow Control (2019-9-18)
12 Aug 2021
Conference Videos
A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Journal Article