检索结果-内蒙古大学图书馆

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Transportation Systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

Pre-training Everywhere: Parameter-Efficient Fine-Tuning for Medical Image analysis via Target Parameter Pre-training

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lei, Xingliang Ye, Yiwen Chen, Ziyang Shu, Minglei Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University China China Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Parameter-efficient fine-tuning (PEFT) techniques have emerged to address issues of overfitting and high computational costs associated with fully fine-tuning in the paradigm of self-supervised learning. Mainstream methods based on PEFT involve adding a few trainable parameters while keeping the pre-trained parameters of the backbone fixed. These methods achieve comparative, and often superior, performance to fully fine-tuning, demonstrating the powerful representation ability of the pre-trained backbone. Despite its success, these methods typically ignore the initialization of the new parameters, often relying solely on random initialization. We argue that if pre-training is significantly beneficial, it should be applied to all parameters requiring representational capacity. Motivated by this insight, we propose a simple yet effective fine-tuning framework based on Target Parameter Pre-training (TPP). The target parameters refer to the new parameters introduced during fine-tuning. TPP includes an additional stage before PEFT to pre-train these target parameters. During this stage, the pre-trained backbone parameters are frozen, and only the target parameters are trainable. A defined pre-text task is used to encourage the target parameters to learn specific representations of downstream data. When PEFT is subsequently employed, the pre-trained target parameters are loaded to enhance fine-tuning efficiency. The proposed TPP framework is versatile, allowing for the integration of various pretext tasks for pre-training and supporting different PEFT methods as backbones. We evaluated the fine-tining performance of our method using five public datasets, including three modalities and two task types. The results demonstrate that the proposed TPP can be easily integrated into existing PEFT methods, significantly improving performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Freight Transportation Structure Adjustment Control with Priority in Energy Consumption in China

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zuo, Dajie Liang, Qichen Zhan, Shuguang Huang, Wencheng Yang, Shenglan Wang, Mengyun School of Transportation and Logistics Southwest Jiaotong University Chengdu611756 China National and Local Joint Engineering Laboratory of Comprehensive Intelligent Transportation Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Key Laboratory of Comprehensive Transportation of Sichuan Province Southwest Jiaotong University Chengdu611756 China

China has set the goal of controlling the total energy consumption to 6 billion tonnes of standard coal by 2030 in an attempt to avoid an energy crisis. Generally, freight transportation is an energy-intensive industry. Controlling the energy consumption of freight transportation is crucial for achieving energy-saving goals in China. In this study, we establish the annual control model for freight transportation structure adjustment from the perspectives of the target year prediction and the intermediate year controlling to control energy consumption in the freight industry. We solve the model and obtain the annual control plan of freight transportation structure adjustment in China (2021-2030). As per the plan, energy consumption will reach its peak in 2029, with 145 million tonnes of standard coal. Lastly, we proposed a series of reasonable policy recommendations. This study will provide a reference for the sustainable development of transportation in China. © 2022, The Authors. All rights reserved.

关键词： Energy utilization

XCrossNet: Feature structure-oriented learning for click-through rate prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Runlong Ye, Yuyang Liu, Qi Wang, Zihan Yang, Chunfeng Hu, Yucheng Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China Management Science and Information Systems Rutgers Business School Rutgers University Newark United States MOE Key Laboratory of Computational Linguistics School of Electronics Engineering and Computer Science Peking University Beijing China Tencent Inc Shenzhen China

Click-Through Rate (CTR) prediction is a core task in nowadays commercial recommender systems. Feature crossing, as the mainline of research on CTR prediction, has shown a promising way to enhance predictive performance. Even though various models are able to learn feature interactions without manual feature engineering, they rarely attempt to individually learn representations for different feature structures. In particular, they mainly focus on the modeling of cross sparse features but neglect to specifically represent cross dense features. Motivated by this, we propose a novel Extreme Cross Network, abbreviated XCrossNet, which aims at learning dense and sparse feature interactions in an explicit manner. XCrossNet as a feature structure-oriented model leads to a more expressive representation and a more precise CTR prediction, which is not only explicit and interpretable, but also time-efficient and easy to implement. Experimental studies on Criteo Kaggle dataset show significant improvement of XCrossNet over state-of-the-art models on both effectiveness and efficiency. © 2021, CC BY.

关键词： Forecasting

Perceptive self-supervised learning network for noisy image watermark removal

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. Comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

Group Multi-View Transformer for 3D Shape analysis with Spatial Encoding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Lixiang Cui, Qingzhe Hong, Richang Xu, Wei Chen, Enhong Yuan, Xin Li, Chenglong Tang, Yuanyan The College of Artificial Intelligence and Big Data Hefei University Hefei230027 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China The School of Electrical and Mechanical Engineering The University of Adelaide AdelaideSA5005 Australia The School of Artificial Intelligence Anhui University Hefei230601 China The Zhuhai UM Science and Technology Research Institute FST University of Macau China

In recent years, the results of view-based 3D shape recognition methods have saturated, and models with excellent performance cannot be deployed on memory-limited devices due to their huge size of parameters. To address this problem, we introduce a compression method based on knowledge distillation for this field, which largely reduces the number of parameters while preserving model performance as much as possible. Specifically, to enhance the capabilities of smaller models, we design a high-performing large model called Group Multi-view Vision Transformer (GMViT). In GMViT, the view-level ViT first establishes relationships between view-level features. Additionally, to capture deeper features, we employ the grouping module to enhance view-level features into group-level features. Finally, the group-level ViT aggregates group-level features into complete, well-formed 3D shape descriptors. Notably, in both ViTs, we introduce spatial encoding of camera coordinates as innovative position embeddings. Furthermore, we propose two compressed versions based on GMViT, namely GMViT-simple and GMViT-mini. To enhance the training effectiveness of the small models, we introduce a knowledge distillation method throughout the GMViT process, where the key outputs of each GMViT component serve as distillation targets. Extensive experiments demonstrate the efficacy of the proposed method. The large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB. The smaller models, GMViT-simple and GMViT-mini, reduce the parameter size by 8 and 17.6 times, respectively, and improve shape recognition speed by 1.5 times on average, while preserving at least 90% of the classification and retrieval performance. The code is available at https://***/bigdatagraph/*** Codes 68 Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

A Wavelet-CNN-LSTM Model for Tailings Pond Risk Prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Jun Li, Qing Sun, Yixuan Wang, Wei Li, Linchao Wang, Xuwei Jia, Shengyao Tong, Renyuan National and Local Joint Engineering research center for Disaster Monitoring Technologies and Instruments China Jiliang University Hangzhou310051 China Zhejiang Provincial Key Laboratory of Intelligent Manufacturing Quality Big Data Traceability Analysis and Application China Jiliang University Hangzhou310051 China Zhejiang PeckerAI Technology. Ltd Hangzhou310018 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China

Tailings ponds are places for storing industrial waste. The saturation line is the key factor of quantifying the safety of tailings pond. Existing saturation line time-series prediction methods are mainly based on statistical models or shallow machine learning models. Although these models aim to capture the time dependence of the sequence data, the channel and temporal are even unavailable in principle. In this paper, we presents a two-stage forecasting method, which embeds the channel and temporal attention into a hybrid CNN-LSTM model to predict the saturation line. In the first stage, the discrete wavelet transform (DWT) is applied to capture the refined sequence information. In the second stage, the CNN-LSTM model is utilized to learn the basic spatial and temporal features in the time series. Furthermore, the channel and temporal attention model are embedded into CNN-LSTM model to enhance the feature extracting ability in channel and temporal dimension. Consequently, our proposed model is shown to outperform classic models on five real-world datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Modelling the Bus Fleet Automation Transition Problem

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Tang, Chunyan Liu, Yang Zhang, Jiyu Liu, Tao College of Transportation Engineering Dalian Maritime University Liaoning Province Dalian116026 China College of Transportation Engineering Chang’an University Shaanxi Xi’an China National Engineering Laboratory of Integrated Transportation Big Data Application Technology School of Transportation and Logistics Southwest Jiaotong University Chengdu611756 China National United Engineering Laboratory of Integrated and Intelligent Transportation School of Transportation and Logistics Southwest Jiaotong University Chengdu611756 China

Autonomous bus is known as a potential contributor in improving the service level and reducing vehicle operational cost due to without drivers. For this reason, replacing existing human driving buses with autonomous buses in the public transport sector has become a highly active research area in recent years. Unlike the human driving bus fleet replacement problem that only considers the fleet replacement cost of the operator, replacing the bus fleet with autonomous buses needs to consider both costs of passengers and operator due to the change of service level. To fill the gap in the literature, this paper solves a bus fleet automation transition problem, where both passenger and operator costs during the planning horizon and their mitigation cost of the end-of-horizon are considered. The proposed new model simultaneously determines the service frequencies of human driving buses and autonomous buses, vehicle purchase plan, and vehicle retirement plan over the planning horizon. The model is applied into a real-world case study in the Dandong city, China. The experimental results show that the fleet composition including 80% autonomous buses and 20% human driving buses achieves the lowest total fleet replacement cost. © 2024, The Authors. All rights reserved.

关键词： Life cycle

Transformer-Based Hierarchical Dynamic Decoders for Salient Object Detection

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zheng, Qingping Zheng, Ling Deng, Jiankang Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northewestern Polytechnical University Shaanxi Xi’an710129 China Fuzhou Institute of Data Technology Fujian350200 China Department of Computing Imperial College London LondonSW7 2AZ United Kingdom

HighlightsTransformer-Based Hierarchical Dynamic Decoders for Salient Object DetectionQingping Zheng, Ling Zheng, Jiankang Deng, Ying Li, Changjing Shang, Qiang Shen• T-HDDNet employs dynamic upsampling and fusion for data-driven salient object detection.• T-HDDNet uses a spatially sensitive loss to learn salient object structures, yielding a high-resolution map.• Our method exceeds benchmarks at 22.19G MACs and 27M Params, reducing costs compared to the top model. © 2023, The Authors. All rights reserved.

关键词： Object detection