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： Yi Zhang Yurong Song Guoping Jiang Bin Yu School of Computer Science Software and Network Space SecurityNanjing University of Posts and Telecommunications School of Automation Nanjing University of Posts and Telecommunications Jiangsu Engineering Lab for IOT Intelligent Robots(IOTRobot) Hengyang Key Laboratory of Information Secure and its application research

The supply chain network is a complex network with the risk of cascading *** study the cascading failure in it,an accurate supply chain network model needs to be *** this paper,we construct a layered supply chain network model according to the types of companies in real supply chain *** first define the similarity between companies in the same layer by studying real-world scenarios in supply chain ***,considering both the node degree and the similarity between nodes in the same layer,we propose preferential attachment probability formulas for the new nodes to join the exist ***,the evolution steps of the model are *** analyze the structural characteristics of the new *** results show that the new model has scale-free property and small-world property,which conform to the structural characteristics of the known supply chain *** with the other network models,it is found that the new model can better describe the actual supply chain network.

关键词： Supply Chain network Cascading Failure Similarity BA Model Structural Characteristics

来源：评论

学校读者我要写书评

暂无评论

ZSTAD: Zero-Shot Temporal Activity Detection

ZSTAD: Zero-Shot Temporal Activity Detection

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Lingling Zhang Xiaojun Chang Jun Liu Minnan Luo Sen Wang Zongyuan Ge Alexander Hauptmann School of Computer Science and Technology Xi'an Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xian China School of Information Technology and Electrical Engineering The University of Queensland Australia School of Computer Science Carnegie Mellon University USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS'14 and the Charades datasets show promising performance in terms of detecting unseen activities.

关键词： Semantics Proposals Training Task analysis Feature extraction Microsoft Windows Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

label Noise Robust Curriculum for Deep Paraphrase Identification

Label Noise Robust Curriculum for Deep Paraphrase Identifica...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Boxin Li Tingwen Liu Bin Wang Lihong Wang Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Xiaomi AI Lab Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In this paper, we study the effect of label noise on deep learning models for paraphrase identification. Curriculum learning, a learning paradigm that learns easy samples first and then gradually proceeds with hard ones, has shown excellent results in dealing with label noise for deep neural networks (DNNs). However, most previous studies focus on image classification, and design their curriculum only based on training losses of samples, ignoring domain-specific knowledge. In this paper, we propose a predefined curriculum learning based framework, incorporating both training losses of samples and domain-specific knowledge, to train robust deep models for paraphrase identification (PI) with label noise. Through extensive experiments on two popular PI benchmarks, we show that 1) the performance of the deep paraphrase identification model can drop sharply at the case of severe label noise; 2) our approach can significantly improve generalization performance of deep networks trained on corrupted data especially at extremely high levels of label noise; 3) our method can outperform several state-of-the-art label corruption robust methods.

关键词： Training Noise measurement Robustness Noise robustness Machine learning Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Investigating Bi-level optimization for learning and vision from a unified perspective: A survey and beyond

arXiv

引用

arXiv 2021年

作者： Liu, Risheng Gao, Jiaxin Zhang, Jin Meng, Deyu Lin, Zhouchen DUT-RU International School of Information Science & Engineering Dalian University of Technology Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian116024 China Department of Mathematics Southern University of Science and Technology National Center for Applied Mathematics Shenzhen China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an Shaanxi China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. © 2021, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ZSTAD: Zero-shot temporal activity detection

arXiv

引用

arXiv 2020年

作者： Zhang, Lingling Chang, Xiaojun Liu, Jun Luo, Minnan Wang, Sen Ge, Zongyuan Hauptmann, Alexander School of Computer Science and Technology Xian Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xian Jiaotong University Xian China School of Information Technology and Electrical Engineering University of Queensland Australia School of Computer Science Carnegie Mellon University United States

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

The Indoor Positioning System Using Fingerprint Method Based Deep Neural network 1

The Indoor Positioning System Using Fingerprint Method Based...

引用

1st International Conference on Smart City Innovation, ICSCI 2018

作者： Malik, R.F. Gustifa, R. Farissi, A. Stiawan, D. Ubaya, H. Ahmad, M.R. Khirbeet, A.S. Communication Network and Information Security Research Lab Faculty of Computer Science Universitas Sriwijaya Jalan Srijaya Negara Bukit Besar Bukit Lama Ilir Bar. I Sumatera Selatan Palembang30128 Indonesia Faculty of Electronics and Computer Engineering Universiti Teknikal Malaysia Melaka Jalan Hang Tuah Jaya Durian Tunggal Melaka76100 Malaysia

Highly dynamic indoor environments being one of the challenge in the Indoor Positioning System (IPS). Collecting the Received Signal Strength (RSS) value from every WiFi access point known fingerprint method is presented by previous researchers. They proposed with different techniques in fingerprint methods to compete similar existing technology such as GPS in term of accuracy. The drawback using fingerprint is the IPS cannot maintain the high performance constantly. In this research, we propose the Deep Neural network (DNN) algorithm for improving the fingerprint method in the IPS. Basically, the fingerprint method consists of two phases, Online and Offline phases. In the off-line, RSS values will be collected from several coordinates as known reference points and stored in the database. The online phase has different step which the current position will be compared to RSS values stored in the database. The DNN method was used to calculate the closest position estimation probability. The IPS using DNN was successfully applied using 5 layers consisting of a 1 input layer, 3 hidden layers and 1 output layer. The input and hidden layer have 28 nodes for each layers and output layer has 2 nodes. The simulation results from RSS data set has achieved 2 meters accuracy. It concluded that DNN performance depends on the number of hidden layers and the number of nodes in each hidden layer. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

WLAN Based Position Estimation System Using Classification Fuzzy K-Nearest Neighbor (FK-NN) 1

WLAN Based Position Estimation System Using Classification F...

引用

1st International Conference on Smart City Innovation, ICSCI 2018

作者： Malik, R.F. Mardiah Farissi, A. Stiawan, D. Zulfahmi, R. Ahmad, M.R. Khirbeet, A.S. Communication Network and Information Security Research Lab Faculty of Computer Science Universitas Sriwijaya Jalan Srijaya Negara Bukit Besar Bukit Lama Ilir Bar. I Kota Palembang Sumatera Selatan30128 Indonesia Faculty of Electronics and Computer Engineering Universiti Teknikal Malaysia Melaka Jalan Hang Tuah Jaya Durian Tunggal Melaka76100 Malaysia

Increasing the number of public hotspots using Wi-Fi technology is one of opportunity to gain advantage for proposing many new technologies. One of emerging technology is an estimation system to locate the object/person position using Wi-Fi. The object estimation position is the technology to estimate object position accuracy, using signal Received Signal Strength (RSS) from Wi-Fi Access Point. The RSS is an information about the strength of the signal indicates the distance between the access point device. Through the Indoor Positioning System (IPS), RSS value information from multiple access points are processed in order to provide position information. In this study, the IPS using Fuzzy K-Nearest Neighbour (FK-NN) classification method which is a combination of Fuzzy algorithm and K-NN to increase the accuracy of the object estimation position based on the learning data as reference point. Through hybridization from the algorithm is expected to calculate the position estimation more effectively and accurately and minimize errors in estimation. The results show that the algorithm FK-NN obtain the average location error of 2.4 meters with an accuracy percentage of 76%. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

Triple-view Learning for Predicting Antibiotic Resistance Genes

Triple-view Learning for Predicting Antibiotic Resistance Ge...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shujie Luo Haifang Wu Weizhong Zhao Xingpeng Jiang Tingting He Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal University Wuhan PR China School of Computer Central China Normal University Wuhan PR China National Language Resources Monitoring & Research Center for Network Media Central China Normal University Wuhan PR China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin PR China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin PR China

ISBN: (纸本)9781665429825

With the increasing resistance of bacteria to antibiotics, the problem of antibiotic resistance has become a major challenge in healthcare. Therefore, the accurate identification of antibiotic resistance genes (ARGs) in bacteria is particularly urgent and important. Although culture-based methods can accurately identify ARGs, they are limited by domain knowledge and are time-consuming. With the availability of whole genome sequence data, most existing methods rely on sequence alignment to calculate sequence similarity to predict ARGs. However, for ARGs that has low sequence identity with known sequences, the existing methods do not identify them well. To address the challenges, we propose a multiple view learning based framework for ARGs. Experimental results demonstrate that the proposed approach performs better than the selected representative baselines on the real-world dataset.

关键词： Deep learning Microorganisms Antibiotics Semantics Genomics Medical services Predictive models

来源：评论

学校读者我要写书评

暂无评论

Optimizing network resource allocation with graph pointer neural network in large-scale AI systems

引用

Digital Communications and networks 2024年

作者： Peiying Zhang Yilin Li Athanasios V. Vasilakos Konstantin Igorevich Kostromitin Jianyong Zhang Mohsen Guizani Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China State Key Laboratory of Integrated Services Networks Xidian University Xi'an 710071 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250013 China Department of Networks and Communications College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam 31441 Saudi Arabia Department of Physics of Nanoscale Systems South Ural State University Chelyabinsk 454080 the Russian Federation Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Key Lab of All Optical Network and Advanced Telecommunication of EMC Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi 999041 United Arab Emirates

For increasingly complex communication demands of large-scale AI communication systems, the Space-Air-Ground Integrated network (SAGIN) better caters to demands but also raises concerns about resource scarcity and diversity. This paper innovatively combines Graph Pointer Neural networks (GPNN) and Reinforcement Learning (RL) to enhance resource allocation efficiency. The method leverages the advantages of GPNN in handling graph data and RL in optimizing decisions in dynamic environments. It also targets the optimization goal of maximizing resource allocation while minimizing deployment latency. This paper begins by modeling SAGIN and elucidating the SAGIN logical architecture based on Software-defined networking (SDN). Subsequently, it introduces an SFC deployment algorithm aimed at joint optimization of resource allocation and latency. The algorithm leverages GPNN and RL to deploy virtual nodes and links, with the goal of optimizing resource allocation and deployment latency. Experiment findings conclusively demonstrate that the efficacy of proposed algorithm in effectively weighing limited heterogeneous resources and minimum mapping delay. Notably, when compared to three other SFC mapping algorithms MLRL, NFVdeep, and RL, the proposed algorithm consistently outperforms them, with an average improvement of 10.17% in long-term average reward/cost, 11.21% in link resource utilization ratio, 15.34% in node resource utilization ratio, and 16.38% in acceptance ratio.

关键词： Space-air-ground integrated network Topological structure Reinforcement learning Service function chain Graph pointer neural network

来源：评论

学校读者我要写书评

暂无评论

An improved RL-based framework for multiple biomedical event extraction via self-supervised learning

An improved RL-based framework for multiple biomedical event...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yao Zhao Weizhong Zhao Xingpeng Jiang Tingting He Bianping Su Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal University Wuhan Hubei PR China School of Computer Central China Normal University Wuhan Hubei PR China National Language Resources Monitoring & Research Center for Network Media Central China Normal University Wuhan Hubei PR China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin PR China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin PR China Xi’an University of Architecture and Technology Xi’an Shanxi PR China

ISBN: (纸本)9781665429825

The main goal of biomedical event extraction is to structurally extract biomedical events from texts, however, the specificity of the domain makes both text modeling and data annotation very difficult. We propose a self-supervised learning-based data augmentation method in this paper and design specific augmentation strategies for biomedical entities and event triggers in biomedical texts, which solves the problem of sparse annotation data to some extent. In addition we improve the reinforcement learning-based event extraction method to improve the training efficiency of the model. The experiments on two datasets demonstrate the effectiveness of our method.

关键词： Training Annotations Conferences Biological system modeling Data models Data mining Bioinformatics

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：