检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： Zhexin Shi Jianglong Yu Jiahong Wei Xiwang Dong 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

The cooperative guidance design and analysis issues for multiple robots system are investigated. First, a cooperative guidance structure is constructed by leader layer robots and follower layer robots. Then, for the leader robot layer, the cooperative detection guidance law is designed to achieve the coordination of the detection field of view（FOV）, while providing the reference trajectories. Third, for the follower robot layer, the time-varying line of sight（LOS） angle formation tracking guidance law is proposed based on the leader robots’ LOS angle trajectories convex combination. In addition, the design process is given ***, a cooperative guidance platform consisting of two leaders, three followers, and a target is constructed. The theoretical results are verified by numerical simulation examples, and experimental results are presented on the platform.

关键词： Paper Instruction Chinese Control Conference

来源：评论

学校读者我要写书评

暂无评论

A deep learning based known-plaintext attack method for chaotic cryptosystem

arXiv

引用

arXiv 2021年

作者： Wang, Fusen Sang, Jun Liu, Qi Huang, Chunlin Tan, Jinghan Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing400044 China School of Big Data & Software Engineering Chongqing University Chongqing401331 China

In this paper, we propose a known-plaintext attack (KPA) method based on deep learning for traditional chaotic encryption scheme. We employ the convolutional neural network to learn the operation mechanism of chaotic cryptosystem, and accept the trained network as the final decryption system. To evaluate the attack performance of different networks against different chaotic cryptosystem, we adopt two neural networks to perform known-plaintext attacks on two distinct chaotic encryption schemes. The experimental results demonstrate the potential of deep learning-based method for known-plaintext attack against chaotic cryptosystem. Different from the previous known-plaintext attack methods, which were usually limited to specific chaotic cryptosystems, a neural network can be applied to the cryptanalysis of various chaotic cryptosystems with deep learning-based approach, while several different networks can be designed for the cryptanalysis of chaotic cryptosystems. This paper provides a new idea for the cryptanalysis of chaotic image encryption algorithm. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Adversarial Active Learning With Model Uncertainty For Image Classification

Deep Adversarial Active Learning With Model Uncertainty For ...

引用

IEEE International Conference on Image Processing

作者： Zheng Zhu Hongxing Wang Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Active learning aims at selecting and labeling as few samples as possible to train a good task model. Most existing methods rely on various heuristics to iteratively select a single sample in each active learning loop, thus cannot tackle large datasets efficiently. In this paper, we propose a new batch-mode active learning method, which can plug model prediction uncertainty into adversarial batch selection to ensure the selected samples are representative in unlabeled data, complementary to labeled data, and beneficial for model training. Experiments on four benchmark image datasets validate the effectiveness and efficiency of the proposed method for active image classification in comparison with the state-of-the-art methods.

关键词： Task analysis Uncertainty Training Predictive models Data models Labeling Loss measurement

来源：评论

学校读者我要写书评

暂无评论

Full Black-Box Retrievable And Accountable Identity-Based Encryption

SSRN

引用

SSRN 2023年

作者： Zhao, Zhen Susilo, Willy Guo, Fuchun Lai, Jianchang Wang, Baocang State Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong Wollongong2522 Australia School of Cyber Science and Engineering Southeast University Nanjing211189 China

Accountable identity-based encryption (A-IBE) was proposed to relieve the key escrow problem caused by the fully trustworthy private-key generator (PKG) in the IBE system, where the true generator of private keys or decoder boxes can be traced back to the PKG or related users. Retrievable A-IBE (RA-IBE) enhances the security of A-IBE by providing retrievability to the master secret key of the PKG when more than one private key of the same user are released. RA-IBE strengthens the deterrent effect of A-IBE against the PKG since disclosure of the master secret key could lead to the breakdown of the entire IBE system. However, current RA-IBE schemes only provide retrievability in a white-box model, which limits the ability to support traceability and retrievability on well-formed private keys only. This overlooks the fact that a malicious PKG can easily conceal a private key within a decoder box, making the inserted private key inaccessible. To overcome this limitation, we propose a full black-box RA-IBE scheme, where traceability and retrievability of decoder boxes are provided while the malicious PKG is allowed to access the decryption oracle in the security model simultaneously. We first give the formal definition and security models of full black-box RA-IBE and then present a concrete construction. In our construction, a user interacts with the PKG to obtain its private key and an additional commitment tuple with which the user can retrieve the master secret key of the PKG using a related decoder box generated by the PKG. Finally, we show that the proposed full black-box RA-IBE scheme is secure in the random oracle model. © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Predictive and Contrastive: Dual-Auxiliary Learning for Recommendation

arXiv

引用

arXiv 2022年

作者： Tao, Yinghui Gao, Min Yu, Junliang Wang, Zongwei Xiong, Qingyu Wang, Xu The Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education School of Big Data and Software Engineering Chongqing401331 China The School of Information Technology and Electrical Engineering The University of Queensland Queensland4072 Australia The College of Mechanical and Vehicle Engineering Chongqing University Chongqing400044 China

Self-supervised learning (SSL) recently has achieved outstanding success on recommendation. By setting up an auxiliary task (either predictive or contrastive), SSL can discover supervisory signals from the raw data without human annotation, which greatly mitigates the problem of sparse user-item interactions. However, most SSL-based recommendation models rely on general-purpose auxiliary tasks, e.g., maximizing correspondence between node representations learned from the original and perturbed interaction graphs, which are explicitly irrelevant to the recommendation task. Accordingly, the rich semantics reflected by social relationships and item categories, which lie in the recommendation data-based heterogeneous graphs, are not fully exploited. To explore recommendation-specific auxiliary tasks, we first quantitatively analyze the heterogeneous interaction data and find a strong positive correlation between the interactions and the number of user-item paths induced by meta-paths. Based on the finding, we design two auxiliary tasks that are tightly coupled with the target task (one is predictive and the other one is contrastive) towards connecting recommendation with the self-supervision signals hiding in the positive correlation. Finally, a model-agnostic DUal-Auxiliary Learning (DUAL) framework which unifies the SSL and recommendation tasks is developed. The extensive experiments conducted on three real-world datasets demonstrate that DUAL can significantly improve recommendation, reaching the state-of-the-art performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

RASTE: A Relation-Guided Joint Method for Aspect Sentiment Triplet Extraction

RASTE: A Relation-Guided Joint Method for Aspect Sentiment T...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Linyang Zhong Jiaxing Shang Linjiang Zheng Fei Hao Weiwei Cao Hong Sun Key Laboratory of Dependable Service Computing in Cyber Physical Society College of Computer Science Chongqing University Chongqing China School of Computer Science Shaanxi Normal University Xian China Key Laboratory of Flight Techniques and Flight Safety Civil Aviation Flight University of China Guanghan China Flight Technology and Flight Safety Research Base Civil Aviation Flight University of China Guanghan China

Aspect Sentiment Triplet Extraction (ASTE) is an important subtask of aspect-based sentiment analysis. It aims to extract aspect terms, corresponding sentiment polarities and related opinion terms from a sentence. The most advanced research efforts solve this problem in an end-to-end manner. However, they usually use one classifier to handle both relation detection and sentiment polarity classification tasks for aspectopinion pairs, which affects the prediction performance of the classifier. Moreover, the previous works treat subtasks equally, ignoring the differences between subtasks. In this paper, we propose a relation-guided method that models the relation detection and sentiment polarity classification subtasks differently to extract aspect sentiment triplets more effectively. Further, we capture the corresponding contextual features for each subtask separately to improve the overall performance of the model. We conducted experiments on two group benchmark datasets. Our model turns out to be one of the state-of-the-art models with effectiveness and superiority according to the experimental results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Fatigue Driving Based on Steering Operation Using Wearable Smart Watch 1

引用

9th International Conference on Green Intelligent Transportation Systems and Safety, 2018

作者： Sun, Dihua Huang, Yong Zhao, Min Chen, Dong Han, Weijian Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing400044 China College of Automation Chongqing University Chongqing400044 China College of Automotive Engineering Chongqing University Chongqing400044 China

ISBN: (数字)9789811506444

ISBN: (纸本)9789811506437

Given the growing popularity of wearable smart watch with the capability to detect human hand movements, this paper studies the potential to recognize fatigue driving based on steering operation by using a wearable smart watch. The sensor data used includes acceleration and angular velocity data related to drivers’ operation behavior. We analyze the sensors’ data features of smart watch under drivers’ fatigue and normal states, and select 13 principal characteristic parameters by using the method of principal component analysis (PCA). Then the recognition model of fatigue driving based on support vector machine (SVM) is established. The results show that the proposed method recognizes the drivers’ fatigue or normal state more effectively than other methods and its accuracy can reach 83.29%. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Patch Label Inference Networks for Efficient Pavement Distress Detection and Recognition in the Wild

arXiv

引用

arXiv 2022年

作者： Huang, Sheng Tang, Wenhao Huang, Guixin Huangfu, Luwen Yang, Dan Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing400044 China The School of Big Data and Software Engineering Chongqing University Chonqqing 400044 China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA92182 United States

Automatic image-based pavement distress detection and recognition are vital for pavement maintenance and management. However, existing deep learning-based methods largely omit the specific characteristics of pavement images, such as high image resolution and low distress area ratio, and are not end-to-end trainable. In this paper, we present a series of simple yet effective end-to-end deep learning approaches named Weakly Supervised Patch Label Inference Networks (WSPLIN) for efficiently addressing these tasks under various application settings. WSPLIN transforms the fully supervised pavement image classification problem into a weakly supervised pavement patch classification problem for solutions. Specifically, WSPLIN first divides the pavement image under different scales into patches with different collection strategies and then employs a Patch Label Inference Network (PLIN) to infer the labels of these patches to fully exploit the resolution and scale information. Notably, we design a patch label sparsity constraint based on the prior knowledge of distress distribution and leverage the Comprehensive Decision Network (CDN) to guide the training of PLIN in a weakly supervised way. Therefore, the patch labels produced by PLIN provide interpretable intermediate information, such as the rough location and the type of distress. We evaluate our method on a large-scale bituminous pavement distress dataset named CQU-BPDD and the augmented Crack500 (Crack500-PDD) dataset, which is a newly constructed pavement distress detection dataset augmented from the Crack500. Extensive results demonstrate the superiority of our method over baselines in both performance and efficiency. The source codes of WSPLIN are released on https://***/DearCaat/wsplin. © 2022, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

RFID E-Plate Data based Bus Travel Time Prediction Considering Traffic Flow Diversion Rate

RFID E-Plate Data based Bus Travel Time Prediction Consideri...

引用

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

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：