检索结果-内蒙古大学图书馆

第32届中国控制与决策会议

作者： Zhizong Liu Shuai Huang Siyuan Zhong Rui Chen Dihua Sun School of Automation Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education

The conventional bus travel time prediction(bus-TTP) generally utilizes the Global Position System(GPS),video detection,***,they are vulnerable to ambient,weather,illuminance,electromagnetic interferences or other additional *** improve the performance of TTP,we study the Radio Frequency Identification(RFID) electronic license plate(E-Plate) data based bus-TTP and proposed an improved Kalman filter(i.e.,the Adaptive Extended Kalman Filter,AEKF) algorithm considering traffic flow diversion rate(TFDR).Firstly,the RFID readers mounted on road gantry read the critical information from the electronic tag deployed on ***,the received traffic information is modulated and demodulated as the available ***,the proposed bus-TTP algorithm is used to predict bus travel time,which makes the predicted bus travel time better approach the actual *** experimental results show that the AEKF algorithm Considering TFDR improves the dynamic performance of the filtering and better inhibits the filtering divergence process in the case of bus travel time changing abruptly during rush hours.

关键词： Bus travel time prediction RFID Traffic flow diversion rate Adaptive Extended Kalman Filter

来源：评论

学校读者我要写书评

暂无评论

Prompt Learning for Multi-modal COVID-19 Diagnosis

Prompt Learning for Multi-modal COVID-19 Diagnosis

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yang Yu Lu Rong Mengyao Wang Min Huang Yazhou Zhang Yijie Ding Software Engineering College Zhengzhou University of Light Industry Zhengzhou China Human Resources Office Zhengzhou University of Light Industry Zhengzhou China Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing China Yangtze Delta Region Institute (Quzhou) University of Electronic Science and Technology of China Quzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

The outbreak of COVID-19 pandemic has spread rapidly and severely affected all aspects of human lives. Recent researches has shown artificial intelligence and deep learning based approaches have achieved successful results in detecting diseases. How to accurately and quickly detect COVID-19 has always been the core topic of research. In this paper, we propose a novel approach based on prompt learning for COVID-19 diagnosis. Different from the traditional “pre-training, fine-tuning” paradigm, we propose the prompt-based method that redefine the COVID-19 diagnosis as a masked predict task. Specifically, we adopt an attention mechanism to learn the multi-modal representation of medical image and text, and manually construct a cloze prompt template and a label word set. Selecting the label word corresponding to the maximum probability by pre-training language model. Finally, mapping the prediction results to the disease categories. Experimental results show that our proposed method obtains obvious improvement of 1.2% in terms of Mi-F1 score compared with the state-of-the-art methods.

关键词： COVID-19 Representation learning Learning systems Deep learning Pandemics Feature extraction Task analysis

来源：评论

学校读者我要写书评

暂无评论

Time-varying group formation-tracking control for heterogeneous multi-agent systems with switching topologies and time-varying delays

Time-varying group formation-tracking control for heterogene...

引用

第40届中国控制会议

作者： Shiyu Zhou Xiaobao Wei Xiwang Dong Yongzhao Hua Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control LaboratoryBeihang University Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education of ChinaChongqing University Institute of Artificial Intelligence Beihang University

Group formation-tracking problem for heterogeneous multi-agent systems（HMASs） with both switching networks and communication delays is investigated in this paper. In order to achieve different tasks, the agents are classified into various groups. The followers are allowed to realize the formation and track the trajectory of the leader in each group. Firstly, by utilizing the consensus control, an observer is proposed to estimate the state of the leader. Then, an observer-based control protocol is put forward to solve the group formation-tracking problem with both communication delays and switching networks. Moreover, an algorithm to determine the gain feedbacks is demonstrated, in the meantime, the observer’s error systems as well as the group formation-tracking error systems are proved to be convergent. Finally, an example in the simulation prat is presented to verify the theoretical results.

关键词： Group formation-tracking problem general linear multi-agent systems time-varying delays switching topologies

来源：评论

学校读者我要写书评

暂无评论

QDL: Quantitative Dynamic Latency Model in Permissioned Blockchain System

QDL: Quantitative Dynamic Latency Model in Permissioned Bloc...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Jiacheng Wei Qingmei Wang Zheng Wang School of Artificial Intelligence Beihang University Beijing Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing National Center for Materials Service Safety University of Science and Technology Beijing Beijing Institute of Cyber Science and Technology Shanghai Jiao Tong University Shanghai Key Laboratory of Integrated Administration Technologies for Information Security

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Latency, as a critical attribute influencing scalability and consistency in blockchain systems, has attracted significant research attention. This paper addresses the issue of latency evaluation by presenting a novel framework. We thoroughly analyze the factors affecting latency in blockchain system, including concurrency, consistency, and contention. To accurately model the correlation between latency and the quantity of nodes in permissioned blockchain setup, we introduce the Latency Regression Loss (LRL) function. By utilizing Newton’s interpolation and least squares methods, we determine the hyperparameters. Subsequently, we devise the framework for the Quantitative Dynamic Latency (QDL) evaluation model, which accounts for both the growth rate and magnitude of latency. Utilizing the parameters derived from the LRL function facilitated the calculation of latency growth rate, allowing for a comprehensive evaluation of latency. Finally, we validated the accuracy of the LRL function through extensive experiments and simulated the adaptability of the QDL model in latency assessment.

关键词： Concurrent computing Adaptation models Interpolation Distributed processing Protocols Scalability Evaluation models Mathematical models Blockchains Least mean squares methods

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Attention-Based Model for Code Search with Textual and Structural Features

Two-Stage Attention-Based Model for Code Search with Textual...

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Ling Xu Huanhuan Yang Chao Liu Jianhang Shuai Meng Yan Yan Lei Zhou Xu Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science and Technology Zhejiang University Hangzhou China

Searching and reusing existing code from a large scale codebase can largely improve developers' programming efficiency. To support code reuse, early code search models leverage information retrieval (IR) techniques to index a large-scale code corpus and return relevant code according to developers' search query. However, IR-based models fail to capture the semantics in code and query. To tackle this issue, developers applied deep learning (DL) techniques to code search models. However, these models either are too complex to determine an effective method efficiently or learning for semantic correlation between code and query *** bridge the semantic gap between code and query effectively and efficiently, we propose a code search model TabCS (Two-stage Attention-Based model for Code Search) in this study. TabCS extracts code and query information from the code textual features (i.e., method name, API sequence, and tokens), the code structural feature (i.e., abstract syntax tree), and the query feature (i.e., tokens). TabCS performs a two-stage attention net-work structure. The first stage leverages attention mechanisms to extract semantics from code and query considering their semantic gap. The second stage leverages a co-attention mechanism to capture their semantic correlation and learn better code/query representation. We evaluate the performance of TabCS on two existing large-scale datasets with 485k and 542k code snippets, respectively. Experimental results show that TabCS achieves an MRR of 0.57 on Hu et al.'s dataset, outperforming three state-of-the-art models CARLCS-CNN, DeepCS, and UNIF by 18%, 70%, 12%, respectively. Meanwhile, TabCS gains an MRR of 0.54 on Husain et al.'s, outperforming CARLCS-CNN, DeepCS, and UNIF by 32%, 76%, 29%, respectively.

关键词： Deep learning Correlation Semantics Syntactics Programming Feature extraction Information retrieval

来源：评论

学校读者我要写书评

暂无评论

The 3D McMaster Algorithm for Traffic Congestion Detection

The 3D McMaster Algorithm for Traffic Congestion Detection

引用

第32届中国控制与决策会议

作者： Tingrang Liu Min Zhao College of Automation Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University

Traffic congestion detection is a key issue in the research of intelligent transportation system（ITS）.Mc Master Algorithm,one of the most classical single-station congestion detection algorithms,has been widely used in ***,it doesn’t consider the effect of speed on volume and occupancy,and requires manual calibration of parameters,which results in a lower detection *** solve these problems,a three-dimensional McMaster algorithm is proposed in this *** on the analysis of the spatial distribution characteristics of congestion and non-congestion data,3 D McMaster algorithm extend McMaster algorithm from 2 D parameter space to 3 D parameter space for *** position of the lower boundary surface of uncongested data（LSUD） in 3 D parameter space is obtained by statistical method,and then the surface is fitted by a Bayesian regularization back propagation neural network to improve the detection *** proposed algorithm is validated with the real data from Shuijie expressway in *** experimental results show that 3 D McMaster algorithm has higher detection rate and lower false alarm rate.

关键词： Traffic Congestion Detection Intelligent Transportation System 3D McMaster Algorithm Bayesian Regularization Back Propagation Neural Network

来源：评论

学校读者我要写书评

暂无评论

PicT: A SlimWeakly Supervised Vision Transformer for Pavement Distress Classification

arXiv

引用

arXiv 2022年

作者： Tang, Wenhao Huang, Sheng Zhang, Xiaoxian Huangfu, Luwen School of Big Data & Software Engineering Chongqing University Chongqing China School of Big Data & Software Engineering Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA United States

Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and infers the patch labels for addressing these issues from the perspective of multi-instance learning. However, these methods neglect the correlation between patches and suffer from a low efficiency in the model optimization and inference. As a representative approach of vision Transformer, Swin Transformer is able to address both of these issues. It first provides a succinct and efficient framework for encoding the divided patches as visual tokens, then employs self-attention to model their relations. Built upon Swin Transformer, we present a novel vision Transformer named Pavement Image Classification Transformer (PicT) for pavement distress classification. In order to better exploit the discriminative information of pavement images at the patch level, the Patch Labeling Teacher is proposed to leverage a teacher model to dynamically generate pseudo labels of patches from image labels during each iteration, and guides the model to learn the discriminative features of patches via patch label inference in a weakly supervised manner. The broad classification head of Swin Transformer may dilute the discriminative features of distressed patches in the feature aggregation step due to the small distressed area ratio of the pavement image. To overcome this drawback, we present a Patch Refiner to cluster patches into different groups and only select the highest distress-risk group to yield a slim head for the final image classification. We evaluate our method on a large-scale bituminous pavement distress dataset named CQU-BPDD. Extensive results demonstrate the superiority of our method over baselines and also show that PicT outperforms the second-best performed model by a large margin of +2.4% in P@R on detection task, +3.9% in F 1 on recogni

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Accepted Influence Maximization under Linear Threshold Model on Large-Scale Social Networks

Accepted Influence Maximization under Linear Threshold Model...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Xiaojuan Yang Jiaxing Shang Linjiang Zheng Dajiang Liu Shu Fu Baohua Qiang Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing China School of Microelectronics and Communication Engineering Chongqing University Chongqing China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781665416597

The influence maximization (IM) problem, which aims to find $k$ most influential individuals from a social network to maximize the influence spread, has been extensively studied. Existing works all rely on the assumption that influenced individuals will definitely try to propagate the information to their neighbors through social trust. However, in real-world this assumption can be over-simplistic since trust-levels among different individuals usually exhibit high diversity. As a result, an influenced individual may choose not to further propagate the information to his neighbors. Motivated by the observation, in this paper we propose a new accepted influence maximization (AIM) problem where the influenced individuals are further divided into two subgroups, i.e., accepted and active, where only active individuals will continue to propagate the information. We prove this problem is NP-hard and the objective function is submodular, based on which a greedy algorithm is proposed with ( $1-1/e-\epsilon$ ) approximation guarantee. Considering the low computational efficiency of the greedy algorithm, we further propose a scalable path-based algorithm ALDAG. We conduct experiments on real datasets and the results demonstrate the effectiveness and efficiency of our method.

关键词： Greedy algorithms Data privacy Social networking (online) Computational modeling Heuristic algorithms Linear programming Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Vehicle Detection and Tracking Method in Highway Scene

Multi-Scale Vehicle Detection and Tracking Method in Highway...

引用

第32届中国控制与决策会议

作者： Tingming Zhang Min Zhao College of Automation Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University

Based on tracking-by-detection strategy,this paper proposes a detection and tracking method for multi-scale vehicle *** method consists of object detection and trajectory *** at object detection,an improved SNIPER sampling strategy was proposed,which combined with Faster R-CNN deep learning model to achieve variable scale vehicle *** the trajectory correlation,motion features,apparent features and trajectory features are matched to achieve the matching between the detection target and the vehicle *** experimental results show that the method in this paper has made significant improvements over previous methods,both in accuracy and speed,and can detect and track multi-scale vehicle targets in highway scenes in real time.

关键词： Highway Scene Vehicle Detection Multi-target Tracking Trajectory Matching

来源：评论

学校读者我要写书评

暂无评论

Battlefield Situation Deduction and Maneuver Decision Using Deep Q-Learning

Battlefield Situation Deduction and Maneuver Decision Using ...

引用

第40届中国控制会议

作者： Minghui Shi Xiwang Dong Liang Han Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education of ChinaChongqing University School of Sino-French Engineer Beihang University

As the pace and complexity of modern warfare accelerates, it is of great significance to apply intelligent technology to defense decision-making. Due to the high dynamics and randomness of the aircraft, traditional methods are difficult to solve the optimal control strategy. The characteristics of reinforcement learning match the difficulty of the problem. In this paper, the situation of hypersonic aircraft is deduced, and the deep reinforcement learning method is used to make autonomous penetration decisions in the reentry phase. The model of aircraft and environment is established, and the maneuvering decision-making model is established based on deep Q-learning and its optimization algorithm. Through a large number of simulation training,this method can effectively give the real-time decision output of the agent and make a good prediction of the situation. It has the ability of short-range accurate operation and long-term planning and prediction. This method can improve the probability of successful penetration, and can be used as the decision-making basis of glider penetration.

关键词： Hypersonic aircraft situational deduction maneuver decision-making reinforcement learning deep Q-learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：