检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data Analysis (ICBDA)

作者： Wanting Wen Qiudan Li Junfeng Li Xu Zhang Daniel Zeng The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China National Internet Emergency Center CNCERT/CC Beijing China

ISBN: (数字)9781728141114

ISBN: (纸本)9781728141121

In this paper, we study the problem of authorship identification in online news data. Most of the existing approaches predict authorship via feature engineering, which cannot focus on important attributes. We designed an authorship identification method named Authorship Embeddings Space model (AES) to predict the online news authorship between online news and authors. First, we propose an authorship space to represent the deep semantic relationship of news content. Second, we use an embedding learning method to perform the relationship between authors and news. Finally, we formulated an authorship prediction algorithm to identify the news authors based on the authorship embeddings. Experimental results on the online news dataset reveal that the AES model outperforms the baseline models.

关键词： Organizations Stock markets Training Semantics Writing Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Faster gradient-based NAS pipeline combining broad scalable architecture with confident learning rate

arXiv

引用

arXiv 2020年

作者： Ding, Zixiang Chen, Yaran Li, Nannan Zhao, Dongbin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

In order to further improve the search efficiency of Neural Architecture Search (NAS), we propose B-DARTS, a novel pipeline combining broad scalable architecture with Confident Learning Rate (CLR). In B-DARTS, Broad Convolutional Neural Network (BCNN) is employed as the scalable architecture for DARTS, a popular differentiable NAS approach. On one hand, BCNN is a broad scalable architecture whose topology achieves two advantages compared with the deep one, mainly including faster single-step training speed and higher memory efficiency (i.e. larger batch size for architecture search), which are all contributed to the search efficiency improvement of NAS. On the other hand, DARTS discovers the optimal architecture by gradient-based optimization algorithm, which benefits from two superiorities of BCNN simultaneously. Similar to vanilla DARTS, B-DARTS also suffers from the performance collapse issue, where those weight-free operations are prone to be selected by the search strategy. Therefore, we propose CLR, that considers the confidence of gradient for architecture weights update increasing with the training time of over-parameterized model, to mitigate the above issue. Experimental results on CIFAR-10 and ImageNet show that 1) B-DARTS delivers state-of-the-art efficiency of 0.09 GPU day using first order approximation on CIFAR-10;2) the learned architecture by B-DARTS achieves competitive performance using state-of-the-art composite multiply-accumulate operations and parameters on ImageNet;and 3) the proposed CLR is effective for performance collapse issue alleviation of both B-DARTS and DARTS. Copyright © 2020, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Inferring users' usage patterns for drug abuse surveillance 17

Inferring users' usage patterns for drug abuse surveillance

引用

17th IEEE International Conference on Intelligence and Security Informatics, ISI 2019

作者： Liu, Ruoran Li, Qiudan Dajun Zeng, Daniel State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Institute of Automation Beijing 100190 China University of Chinese Academy of Sciences Beijing China China

ISBN: (纸本)9781728125046

Inferring drug usage patterns includes age of drug abuse and intention of rehabilitation, which is of much importance for drug abuse surveillance. The challenges are how to mine patterns from posts and interaction relationships between users. In this paper, we propose a novel drug usage pattern inference method, which improves the inference accuracy by integrating the semantic features and interaction relationships effectively. Experimental results on a real-world dataset demonstrate the efficacy of the proposed method. © 2019 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Short Term Traffic Flow Forecast Based on CM-GRU Networks

Short Term Traffic Flow Forecast Based on CM-GRU Networks

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Guo, Zhongzheng Zhong, Weifeng Zhu, Fenghua Li, Xiaoshuang Wang, Fei-Yue Xiong, Gang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Automation Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781728128535

Intelligent transportation systems (ITS) have developed for a long time. The rise of deep learning has brought new vitality of the ITS. However, traffic flow data is usually time-correlated and highly randomized. The data distribution will also change dynamically. To actualize the forecasting of traffic flow accurately, we use the historical traffic information to predict the messages of the traffic flow at any time interval. This paper proposes an efficient traffic flow forecast architecture based on deep learning. The method combines the gated recurrent unit (GRU, a type of recurrent neural network) layers and one-dimension convolution layers. Since the performance of these models has a strong dependence on hyper-parameters, this paper conducts a large-scale search of the hyper-parameter space. At the same time, experiments on flow data show that the method proposed in this paper can achieve a better prediction accuracy. Experiments also show lower test errors compared with the existing approaches. © 2019 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Evolution and Neural Representation of Mammalian Cooperative Behavior

SSRN

引用

SSRN 2021年

作者： Jiang, Mengping Wang, Miaoyaoxin Shi, Qianqian Wei, Lei Lin, Yongqin Wu, Dingcheng Liu, Boyi Nie, Xiupeng Qiao, Hong Xu, Lin Yang, Tianming Wang, Zuoren Institute of Neuroscience State Key Laboratory of Neuroscience CAS Center for Excellence in Brain Science &Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Key Laboratory of Animal Models and Human Disease Mechanisms and Laboratory of Learning and Memory Kunming Institute of Zoology Chinese Academy of Sciences KunmingYunnan650223 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Cooperation is common in nature and has been pivotal to the development of human society. However, the details of how and why cooperation evolved remain poorly understood. Cross-species investigation of cooperation may help to elucidate the evolution of cooperative strategies. Thus, we designed a novel cooperative behavioral paradigm and quantitatively examined the cooperative abilities and strategies of mice, rats, and tree shrews. We found that social communication played a key role in the establishment of new cooperation, and that increased cooperative ability and a more efficient cooperative strategy emerged as a function of the evolutionary hierarchy of the tested species. We also found neural representations of distinct aspects of cooperation in the brains of rats through in vivo electrophysiological recording. Cooperation-preferential signals were identified in addition to material reward-preferential signals, each of which may represent internal drives for cooperation. © 2021, The Authors. All rights reserved.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

arXiv

引用

arXiv 2022年

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China The College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology China Qingdao Academy of Intelligent Industries Qingdao266109 China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://***/bridgeqiqi/DREAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Internet of Mind with General Intelligent Dispatch in Electrical Industrial: The Concept, Framework, Technology, and Future

Internet of Mind with General Intelligent Dispatch in Electr...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Tianlu Gao Xiaoyan Gong Shiqian Ma Weichen Wang Xiaojing Yang Jian Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China Power Dispatching and Control center State Grid Tianjin Electric Power Company Tianjin China

ISBN: (数字)9781728176840

ISBN: (纸本)9781728176857

This paper proposes the concept of general intelligent dispatch, which is a novel framework of electrical power dispatch based on modern artificial intelligence (AI). The general intelligent dispatch system is based on knowledge automation, parallel system, ACP method, and fully integrated with cutting-edge technologies such as parallel deep learning, parallel dynamics programming. The general intelligent dispatch system is devised to be a comprehensive framework that can support the applications of various modern AI technologies in electrical power dispatch. General intelligent dispatch can accommodate the rapid development of the future smart grid, especially the extensive implementation of distributed energy resources and renewable energy. General intelligent dispatch also provides the practical technical path and framework for the future smart power dispatch services to achieve a higher level of automation and intelligence. Based on the general intelligent dispatch concept, this paper addresses power grid situational awareness, which provides an example for the applications of general intelligent dispatch.

关键词： Automation Optimal scheduling Real-time systems Dispatching Smart grids Artificial intelligence Business

来源：评论

学校读者我要写书评

暂无评论

The Application of Artificial Intelligence in Energy Internet

The Application of Artificial Intelligence in Energy Interne...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Zhigang Huang Tianlu Gao Xiaoyan Gong Qian Li Wenzhong Gao Power Dispatching and Control Center State Grid Tianjin Electric Power Company Tianjin China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China

ISBN: (数字)9781728176840

ISBN: (纸本)9781728176857

The energy internet is a cyber-physical system (CPS) to connect directly and indirectly the devices of information, communication, control, and protection to effectively generate, transmit, use, and store various energy by merging new technologies such as artificial intelligence (AI), cloud computing, and blockchain, etc. Recently, AI technology has become increasingly popular in many research and industrial fields because it can perform tasks well. However, applying AI technologies to energy internet is relatively less. Therefore, in this paper, the potential applications of AI technologies in the energy internet will be reviewed and discussed. In section II and section III, the operating and monitoring of power systems are the main parts to discuss. Firstly, applying AI technologies to the operation of control, optimization, and decision-making in power systems will be detailed in section II from three aspects such as existing problems, potential demands, and valuable improvement. Secondly, in section III, detecting faults and analyzing stability by energy internet monitoring is mainly discussed. Finally, in section IV, it shows an example using the neural network to analyze the power flow of a standard IEEE 39 nodes power system compared with traditional Newton-Raphson method.

关键词： Decision making Power system stability Stability analysis Power grids Artificial intelligence Monitoring Optimization

来源：评论

学校读者我要写书评

暂无评论

Semi-autonomous greenhouse environment control by combining expert knowledge and machine learning

Semi-autonomous greenhouse environment control by combining ...

引用

Chinese Automation Congress (CAC)

作者： Mengzhen Kang Yuchen Weng Haitong Pang Liangde Li Xing-Rong Fan Jing Hua Fangle Chang Xiujuan Wang Longhua Ma The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Ningbo Institute of Technology Zhejiang University Ningbo China The School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao AgriTech Co. Ltd Qingdao Qingdao China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The concept of "autonomous greenhouse" hints the automatic setting of control target, and giving orders on facilities to reach these targets (set point). Information and communication technologies are widely used, but how to integrate common sense or knowledge in decision-making is still challenging. Semi-autonomous greenhouse control is to set rules with joint advantages of experienced grower and powerful machinery, with the support of knowledge graph and semantic analysis. The contribution of each side is dependent on the intelligence level of computers, the availability of data, etc. In this work, the hybrid system between human and machinery is shown with the temperature control in greenhouse. The target is set mainly by expert knowledge, while the temperature controlled by vent opening is decided by an algorithm. Result shows that the target is better reached compared to that of the experience-based approach. This example shows the feasibility of human-machine hybrid intelligence system for greenhouse environment control. Although this approach is tested for temperature control, it can be extended to control multiple factors simultaneously (temperature, light intensity, humidity, etc.) by driving multiple facilities (heating, lightening, venting, etc.).

关键词： Green products Temperature measurement Monitoring Temperature sensors Vents Agriculture Temperature distribution

来源：评论

学校读者我要写书评

暂无评论

Correction: Deep learning radiomics of multimodal ultrasound for classifying metastatic cervical lymphadenopathy into primary cancer sites: a feasibility study

引用

Ultraschall in der Medizin - European Journal of Ultrasound 2024年第3期45卷 e2-e2页

作者： Yangyang Zhu Zheling Meng Hao Wu Xiao Fan Wenhao lv Jie Tian Kun Wang Fang Nie Medical Center of Ultrasound Lanzhou University Second Hospital Lanzhou China CAS Key Laboratory of Molecular Imaging The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of the Chinese Academy of Sciences School Beijing China Gansu Province Medical Engineering Research Center for Intelligence Ultrasound Lanzhou China

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：