Pub Date : 2024-09-05DOI: 10.1109/TITS.2024.3432995
Xinran Li;Xiangyang Xu;Hao Yang
Detecting road cracks is crucial for ensuring road traffic safety and stability. However, currently existing detection methods do not usually pay close attention to the global, local and multi-scale feature information of road crack images, resulting in poor detection effects. To overcome this limitation, we propose a road crack detection model that combines the global and local multi-scale attention network (GLMANet) and enhanced feature pyramid network (EFPN). The GLMANet can effectively extract useful global, local and multi-scale feature information of crack images through a novel global and local multi-scale attention mechanism. Meanwhile, EFPN utilizes global adaptive attention module and multi-receptive field feature enhancement module to mitigate information loss during feature map generation, enhancing the representation of advanced semantic features in the feature pyramid. Leveraging faster region-based convolutional neural networks (Faster R-CNN) as the object detection architecture, we conduct experimental evaluations on both publicly available crack datasets and a dataset we collected. The proposed model achieved optimal detection performance across all three datasets. In comparison experiments with the current state-of-the-art crack detection methods, the proposed model outperformed other models, with AP and AP50 increasing by up to 16% and 11%, respectively, validating its effectiveness and superiority. Additionally, the model achieved a good balance between complexity and detection performance with 79.2 GFLOPs and 72.60 million parameters.
{"title":"A Road Crack Detection Model Integrating GLMANet and EFPN","authors":"Xinran Li;Xiangyang Xu;Hao Yang","doi":"10.1109/TITS.2024.3432995","DOIUrl":"10.1109/TITS.2024.3432995","url":null,"abstract":"Detecting road cracks is crucial for ensuring road traffic safety and stability. However, currently existing detection methods do not usually pay close attention to the global, local and multi-scale feature information of road crack images, resulting in poor detection effects. To overcome this limitation, we propose a road crack detection model that combines the global and local multi-scale attention network (GLMANet) and enhanced feature pyramid network (EFPN). The GLMANet can effectively extract useful global, local and multi-scale feature information of crack images through a novel global and local multi-scale attention mechanism. Meanwhile, EFPN utilizes global adaptive attention module and multi-receptive field feature enhancement module to mitigate information loss during feature map generation, enhancing the representation of advanced semantic features in the feature pyramid. Leveraging faster region-based convolutional neural networks (Faster R-CNN) as the object detection architecture, we conduct experimental evaluations on both publicly available crack datasets and a dataset we collected. The proposed model achieved optimal detection performance across all three datasets. In comparison experiments with the current state-of-the-art crack detection methods, the proposed model outperformed other models, with AP and AP50 increasing by up to 16% and 11%, respectively, validating its effectiveness and superiority. Additionally, the model achieved a good balance between complexity and detection performance with 79.2 GFLOPs and 72.60 million parameters.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 11","pages":"18211-18223"},"PeriodicalIF":7.9,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/tits.2024.3445664
Jiajun Xian, Salim Rezvani, Dan Yang
{"title":"A New Decision Tree Based on Intuitionistic Fuzzy Twin Support Vector Machines","authors":"Jiajun Xian, Salim Rezvani, Dan Yang","doi":"10.1109/tits.2024.3445664","DOIUrl":"https://doi.org/10.1109/tits.2024.3445664","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"7 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/tits.2024.3449450
Heqing Tan, Anthony Chen, Xiangdong Xu
{"title":"Equilibria for Joint Congestion Game With Destination and Route Choices","authors":"Heqing Tan, Anthony Chen, Xiangdong Xu","doi":"10.1109/tits.2024.3449450","DOIUrl":"https://doi.org/10.1109/tits.2024.3449450","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"21 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/tits.2024.3449319
Mingqiang Wei, Baian Chen, Liangliang Nan, Haoran Xie, Lipeng Gu, Dening Lu, Fu Lee Wang, Qing Li
{"title":"SimLOG: Simultaneous Local-Global Feature Learning for 3D Object Detection in Indoor Point Clouds","authors":"Mingqiang Wei, Baian Chen, Liangliang Nan, Haoran Xie, Lipeng Gu, Dening Lu, Fu Lee Wang, Qing Li","doi":"10.1109/tits.2024.3449319","DOIUrl":"https://doi.org/10.1109/tits.2024.3449319","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"431 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/TITS.2024.3447282
Paul de Nailly;Etienne Côme;Latifa Oukhellou;Allou Samé;Jacques Ferrière;Yasmine Merad-Boudia
Forecasting counts data in transportation areas can enrich passenger information for public transport passengers, who may thus better plan their trips. Moreover, forecasting with uncertainty is particularly important in the transportation domain, where the risk of poorly managed high demand is to be avoided. In this paper, we propose a new probabilistic prediction model well-suited for multivariate, overdispersed, and possibly correlated count data. This model combines the strength of the deep learning framework with the modeling of counts data allowed by “sums and shares” distributions. Indeed, deep learning models can handle uncertainty by relying on an abstraction of contextual data and by assuming output distributions. Our model learns a latent representation of the input data with the help of a recurrent neural network and then translates it into multivariate count predictions with a “sums and shares” distribution, well suited to tackle multivariate overdispersed and correlated count data. An extensive benchmark of the proposed model is carried out. We compare this model with seven others from the state-of-the-art probabilistic forecasting models using five open-source data (bikes, taxis, railways, traffic, wikipedia) and a specific use case on pedestrian counts within a multimodal transport hub in the Paris Region. Our model outperforms other models in situations where the data present temporal regularities. The results also highlight the potential of our model in the specific use case. Moreover, this forecasting represents an interesting way to predict short-term pedestrian counts in response to different events, such as concerts or transport disruptions.
{"title":"Deep Probabilistic Forecasting of Multivariate Count Data With “Sums and Shares” Distributions: A Case Study on Pedestrian Counts in a Multimodal Transport Hub","authors":"Paul de Nailly;Etienne Côme;Latifa Oukhellou;Allou Samé;Jacques Ferrière;Yasmine Merad-Boudia","doi":"10.1109/TITS.2024.3447282","DOIUrl":"10.1109/TITS.2024.3447282","url":null,"abstract":"Forecasting counts data in transportation areas can enrich passenger information for public transport passengers, who may thus better plan their trips. Moreover, forecasting with uncertainty is particularly important in the transportation domain, where the risk of poorly managed high demand is to be avoided. In this paper, we propose a new probabilistic prediction model well-suited for multivariate, overdispersed, and possibly correlated count data. This model combines the strength of the deep learning framework with the modeling of counts data allowed by “sums and shares” distributions. Indeed, deep learning models can handle uncertainty by relying on an abstraction of contextual data and by assuming output distributions. Our model learns a latent representation of the input data with the help of a recurrent neural network and then translates it into multivariate count predictions with a “sums and shares” distribution, well suited to tackle multivariate overdispersed and correlated count data. An extensive benchmark of the proposed model is carried out. We compare this model with seven others from the state-of-the-art probabilistic forecasting models using five open-source data (bikes, taxis, railways, traffic, wikipedia) and a specific use case on pedestrian counts within a multimodal transport hub in the Paris Region. Our model outperforms other models in situations where the data present temporal regularities. The results also highlight the potential of our model in the specific use case. Moreover, this forecasting represents an interesting way to predict short-term pedestrian counts in response to different events, such as concerts or transport disruptions.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 11","pages":"15687-15701"},"PeriodicalIF":7.9,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Origin-Destination Matrix Prediction in Public Transport Networks: Incorporating Heterogeneous Direct and Transfer Trips","authors":"Tianli Tang, Jiannan Mao, Ronghui Liu, Zhiyuan Liu, Yiran Wang, Di Huang","doi":"10.1109/tits.2024.3447611","DOIUrl":"https://doi.org/10.1109/tits.2024.3447611","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"8 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/TITS.2024.3447161
Yinfeng Xiang;Chao Li;Shibo He;Jiming Chen
Despite the substantial progress in predicting human mobility, most existing methods fail to reveal the spatiotemporal patterns under significant interventions such as COVID-19, which disrupt the routine of human mobility. To fill this gap, this paper presents a unified framework for learning human mobility in both regular and intervened scenarios through explicit modeling of the intervention and the intervened system. To be concrete, we design a novel Deep State-Space Model (DSSM) called AGC-ODE: Adaptive Graph Controlled Neural Ordinary Differential Equation for human mobility prediction during COVID-19. The transition equation that describes continuous-time dynamics of human mobility is parameterized with a graph-controlled Neural ODE, and the latent control that guides the equation propagating is inferred through the multi-head gating filters. Additionally, an information capacity constraint is applied to foster the disentanglement of interventions. Lastly, AGC-ODE utilizes a data-driven initialization strategy to improve DSSM’s initial state estimation. We conduct extensive experiments and analysis on two real-world datasets of Beijing and the U.S. to demonstrate the superiority and interpretability of our model. Furthermore, we introduce a deployed system that is based on AGC-ODE and how it helps epidemic prevention during the COVID era and work resumption in the post-COVID era.
{"title":"AGC-ODE: Adaptive Graph Controlled Neural ODE for Human Mobility Prediction","authors":"Yinfeng Xiang;Chao Li;Shibo He;Jiming Chen","doi":"10.1109/TITS.2024.3447161","DOIUrl":"10.1109/TITS.2024.3447161","url":null,"abstract":"Despite the substantial progress in predicting human mobility, most existing methods fail to reveal the spatiotemporal patterns under significant interventions such as COVID-19, which disrupt the routine of human mobility. To fill this gap, this paper presents a unified framework for learning human mobility in both regular and intervened scenarios through explicit modeling of the intervention and the intervened system. To be concrete, we design a novel Deep State-Space Model (DSSM) called AGC-ODE: Adaptive Graph Controlled Neural Ordinary Differential Equation for human mobility prediction during COVID-19. The transition equation that describes continuous-time dynamics of human mobility is parameterized with a graph-controlled Neural ODE, and the latent control that guides the equation propagating is inferred through the multi-head gating filters. Additionally, an information capacity constraint is applied to foster the disentanglement of interventions. Lastly, AGC-ODE utilizes a data-driven initialization strategy to improve DSSM’s initial state estimation. We conduct extensive experiments and analysis on two real-world datasets of Beijing and the U.S. to demonstrate the superiority and interpretability of our model. Furthermore, we introduce a deployed system that is based on AGC-ODE and how it helps epidemic prevention during the COVID era and work resumption in the post-COVID era.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 11","pages":"18449-18460"},"PeriodicalIF":7.9,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-02DOI: 10.1109/TITS.2024.3442249
Venkata Phanikrishna Balam
Drowsiness is characterized by reduced attentiveness, commonly experienced during the transition from wakefulness to sleepiness. It can decrease an individual’s alertness, thereby increasing the risk of accidents during activities such as driving, crane operation, working in mining areas, and industrial machinery operation. The detection of drowsiness plays an important role in preventing such accidents. Numerous methods exist for drowsiness detection, including Subjective, Vehicle, Behavioral, and Physiological approaches. Among these, Physiological methods, particularly those utilizing Electroencephalogram (EEG) data combined with artificial intelligence, have proven effective in detecting drowsiness. These methods excel in capturing physiological changes in the body during drowsiness and the potential for gathering information from the human brain during this state. EEG data-based Brain-Computer interface (BCI) systems have been popular for detecting drowsiness. Single-channel EEG signal analysis BCIs have been highly preferred for their ease and convenient usage in real-time applications. While some progress has been made in the single-channel EEG BCI, substantial progress is still needed. This paper provides a state-of-the-art analysis of recent developments in the single-channel EEG-based drowsiness detection methods. Ultimately, this review study explores potential avenues for the future development of single-channel EEG-based drowsiness detection.
{"title":"Systematic Review of Single-Channel EEG-Based Drowsiness Detection Methods","authors":"Venkata Phanikrishna Balam","doi":"10.1109/TITS.2024.3442249","DOIUrl":"10.1109/TITS.2024.3442249","url":null,"abstract":"Drowsiness is characterized by reduced attentiveness, commonly experienced during the transition from wakefulness to sleepiness. It can decrease an individual’s alertness, thereby increasing the risk of accidents during activities such as driving, crane operation, working in mining areas, and industrial machinery operation. The detection of drowsiness plays an important role in preventing such accidents. Numerous methods exist for drowsiness detection, including Subjective, Vehicle, Behavioral, and Physiological approaches. Among these, Physiological methods, particularly those utilizing Electroencephalogram (EEG) data combined with artificial intelligence, have proven effective in detecting drowsiness. These methods excel in capturing physiological changes in the body during drowsiness and the potential for gathering information from the human brain during this state. EEG data-based Brain-Computer interface (BCI) systems have been popular for detecting drowsiness. Single-channel EEG signal analysis BCIs have been highly preferred for their ease and convenient usage in real-time applications. While some progress has been made in the single-channel EEG BCI, substantial progress is still needed. This paper provides a state-of-the-art analysis of recent developments in the single-channel EEG-based drowsiness detection methods. Ultimately, this review study explores potential avenues for the future development of single-channel EEG-based drowsiness detection.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 11","pages":"15210-15228"},"PeriodicalIF":7.9,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","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：