检索结果-内蒙古大学图书馆

Short Term Trend Forecast of On-Line Monitoring data of Dissolved Gas in Power Transformer

学校读者我要写书评

暂无评论

Short Term Trend Forecast of On-Line Monitoring Data of Diss...

Electrical Insulation Conference and Electrical Manufacturing & Coil Winding Conference

作者： Peng Zhang Bo Qi Qipeng Chen Zhihai Rong Chengrong Li State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing P.R. China Global Energy Interconnection Research Institute Co. Ltd Advanced Computing and Big Data Laboratory of SGCC Beijing China

ISBN: (纸本)9781538641798

As the transformation equipment of electrical energy, transformer is the key equipment in power system. When it comes to breakdown, there will be a great loss. Dissolved gas analysis (DGA) online testing is an important indicator of transformer health assessment which is widely used in insolation testing as it is sensitive to discharge defect. Nowadays, most of researches on DGA online testing analysis are aimed at the faults diagnosis. However, in some conditions, the fault may develop very rapidly. The operation and maintenance personnel don't have enough time to figure the problem out before the breakdown occur. This problem can be solved by forecasting the DGA on-line testing data effectively. With the reveal of deterioration trend, the serious failure will be avoided and the reliability of transformer will be improved. This paper proposes a short term trend forecast method based on online data optimization for dissolved gas in oil, which is a time series forecast. This method is made up of five parts: data optimization, related gases selection, the orders selection, model parameters estimation and model checking, multi-step forecast. With the field interference and DGA online testing device status error, the DGA online data's quality can't be assured. To improve the accuracy of forecast model, the transformer online testing data needs to be optimized in first step, including Pauta criterion removing for singular value and linear interpolation for missing data. The second step, select related gases, as different gases have strong relationship. The third step is to build forecaster model based on Auto-Regressive and Moving Average Model (ARMA), using Akaike information criterion (AIC) to select the model orders. The forth step, estimate the unknown parameters by least square method. After that, the model should be verified by residual error testing to make sure the effective information of the time series is fully extracted. The final step, use the forecast model

关键词： Predictive models Gases Oil insulation Time series analysis Mathematical model Monitoring data models

Adversarial binary coding for efficient person re-identification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Zheng Qin, Jie Li, Annan Wang, Yunhong van Gool, Luc Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Computer Vision Laboratory ETH Zürich Switzerland

Person re-identification (ReID) aims at matching persons across different views/scenes. In addition to accuracy, the matching efficiency has received more and more attention because of demanding applications using large-scale data. Several binary coding based methods have been proposed for efficient ReID, which either learn projections to map high-dimensional features to compact binary codes, or directly adopt deep neural networks by simply inserting an additional fully-connected layer with tanh-like activations. However, the former approach requires time-consuming hand-crafted feature extraction and complicated (discrete) optimizations;the latter lacks the necessary discriminative information greatly due to the straightforward activation functions. In this paper, we propose a simple yet effective framework for efficient ReID inspired by the recent advances in adversarial learning. Specifically, instead of learning explicit projections or adding fully-connected mapping layers, the proposed Adversarial Binary Coding (ABC) framework guides the extraction of binary codes implicitly and effectively. The discriminability of the extracted codes is further enhanced by equipping the ABC with a deep triplet network for the ReID task. More importantly, the ABC and triplet network are simultaneously optimized in an end-to-end manner. Extensive experiments on three large-scale ReID benchmarks demonstrate the superiority of our approach over the state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Efficiency

Word2Cluster: A New Multi-Label Text Clustering Algorithm with an Adaptive Clusters Number

学校读者我要写书评

暂无评论

Word2Cluster: A New Multi-Label Text Clustering Algorithm wi...

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Kaili Mao Jianwei Niu Xuefeng Liu Shui Yu Longbo Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Hangzhou Innovation Research Institute Beihang University School of Computer Science and Cyber Engineering Guangzhou University Guangdong China China aerospace science and industry corporation China

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Text clustering has been widely used in many Natural Language Processing (NLP) applications such as text summarization and news recommendation. However, most of the current algorithms need to predefine a clustering number, which is difficult to obtain. Moreover, the mutli-label clustering is useful in multiple clustering tasks in many applications, but related works are rarely available. Although several studies have attempted to solve above two problems, there is a need for methods that can solve the two issues simultaneously. Therefore, we propose a new text clustering algorithm called Word2Cluster. Word2Cluster can automatically generate an adaptive number of clusters and support multi-label clustering. To test the performance of Wrod2Cluster, we build a Chinese text dataset, Hotline, according to real world applications. To evaluate the clustering results better, we propose an improved evaluation method based on basic accuracy, precision and recall for multi-label text clustering. Experimental results on a Chinese text dataset (Hotline) and a public English text dataset (Reuters) demonstrate that our algorithm can achieve better F1-measure and runs faster than the state-of- the-art baselines.

关键词： Clustering algorithms Biological system modeling Merging Task analysis Computer science Technological innovation Natural language processing

Oscillatory evolution of collective behavior in evolutionary games played with reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Si-Ping Zhang, Ji-Qiang Chen, Li Liu, Xu-Dong Key Laboratory of Biomedical Information Engineering Ministry of Education Key Laboratory of Neuro-informatics & Rehabilitation Engineering Ministry of Civil Affairs Institute of Health and Rehabilitation Science School of Life Science and Technology Xi'an Jiaotong University Xi'an710049 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Physics and Information Technology Shaanxi Normal University Xi'an710062 China

Large-scale cooperation underpins the evolution of ecosystems and the human society, and the collective behaviors by self-organization of multi-agent systems are the key for understanding. As artificial intelligence (AI) prevails in almost all branches of science, it would be of great interest to see what new insights of collective behavior could be obtained from a multi-agent AI system. Here, we introduce a typical reinforcement learning (RL) algorithm - Q learning into evolutionary game dynamics, where agents pursue optimal action on the basis of the introspectiveness rather than the birth-death or imitation processes in the traditional evolutionary game (EG). We investigate the cooperation prevalence numerically for a general 2 × 2 game setting. We find that the cooperation prevalence in the multi-agent AI is amazingly of equal level as in the traditional EG in most cases. However, in the snowdrift games with RL we also reveal that explosive cooperation appears in the form of periodic oscillation, and we study the impact of the payoff structure on its emergence. Finally, we show that the periodic oscillation can also be observed in some other EGs with the RL algorithm, such as the rock-paper-scissors game. Our results offer a reference point to understand emergence of cooperation and oscillatory behaviors in nature and society from AI's perspective. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

Aggregating multiple types of complex data in stock market prediction: A model-independent framework

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wang, Huiwen Lu, Shan Zhao, Jichang School of Economics and Management Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations

The increasing richness in volume, and especially types of data in the financial domain provides unprecedented opportunities to understand the stock market more comprehensively and makes the price prediction more accurate than before. However, they also bring challenges to classic statistic approaches since those models might be constrained to a certain type of data. Aiming at aggregating differently sourced information and offering type-free capability to existing models, a framework for predicting stock market of scenarios with mixed data, including scalar data, compositional data (pie-like) and functional data (curve-like), is established. The presented framework is model-independent, as it serves like an interface to multiple types of data and can be combined with various prediction models. And it is proved to be effective through numerical simulations. Regarding to price prediction, we incorporate the trading volume (scalar data), intraday return series (functional data), and investors’ emotions from social media (compositional data) through the framework to competently forecast whether the market goes up or down at opening in the next day. The strong explanatory power of the framework is further demonstrated. Specifically, it is found that the intraday returns impact the following opening prices differently between bearish market and bullish market. And it is not at the beginning of the bearish market but the subsequent period in which the investors’ "fear" comes to be indicative. The framework would help extend existing prediction models easily to scenarios with multiple types of data and shed light on a more systemic understanding of the stock market. Copyright © 2018, The Authors. All rights reserved.

关键词： Forecasting

PSGAN: A generative adversarial network for remote sensing image pan-sharpening

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Xiangyu Wang, Yunhong Liu, Qingjie Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China

Remote sensing image fusion (also known as pan-sharpening) aims to generate a high resolution multi-spectral image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral (MS) image. In this paper, we propose PSGAN, a generative adversarial network (GAN) for remote sensing image pan-sharpening. To the best of our knowledge, this is the first attempt at producing high quality pan-sharpened images with GANs. The PSGAN consists of two parts. Firstly, a two-stream fusion architecture is designed to generate the desired high resolution multi-spectral images, then a fully convolutional network serving as a discriminator is applied to distinct "real" or "pan-sharpened" MS images. Experiments on images acquired by Quickbird and GaoFen-1 satellites demonstrate that the proposed PSGAN can fuse PAN and MS images effectively and significantly improve the results over the state of the art traditional and CNN based pan-sharpening methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

MIXGAN: Learning concepts from different domains for mixture generation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Hao, Guang-Yuan Yu, Hong-Xing Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Collaborative Innovation Center of High Performance Computing NUDT China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

In this work, we present an interesting attempt on mixture generation: absorbing different image concepts (e.g., content and style) from different domains and thus generating a new domain with learned concepts. In particular, we propose a mixture generative adversarial network (MIXGAN). MIXGAN learns concepts of content and style from two domains respectively, and thus can join them for mixture generation in a new domain, i.e., generating images with content from one domain and style from another. MIXGAN overcomes the limitation of current GAN-based models which either generate new images in the same domain as they observed in training stage, or require off-theshelf content templates for transferring or translation. Extensive experimental results demonstrate the effectiveness of MIXGAN as compared to related state-of-the-art GAN-based models. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

HIERARCHICAL ATTENTION AND CONTEXT MODELING FOR GROUP ACTIVITY RECOGNITION

学校读者我要写书评

暂无评论

HIERARCHICAL ATTENTION AND CONTEXT MODELING FOR GROUP ACTIVI...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Longteng Kong Jie Qin Di Huang Yunhong Wang Luc Van Gool Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing 100191 China Computer Vision Laboratory ETH Zürich CH-8092 Zürich Switzerland

ISBN: (纸本)9781538646595

Group activity recognition in videos is a challenging task, with two major issues, i.e. attending to those persons and their body parts that contribute significantly to the activity, and modeling contextual person structures in the group. Most previous approaches fail to provide a practical solution to jointly address both issues, however. In this paper, we propose to simultaneously deal with both issues via a hierarchical attention and context modeling framework based on Long Short-Term Memory (LSTM) networks. For the former, we propose 'Hierarchical Attention Networks' applied at the part/person level, capable of attending distinctively to different persons and their body parts. For the latter, we build 'Hierarchical Context Networks' that take the attentively pooled person-level features as input and recurrently model intra/inter-group contextual structures. The attentive and contextual representations are concatenated and fed into another LSTM to generate high-level discriminative temporal representations for group activity recognition. Extensive experiments on two widely-used group activity datasets demonstrate the effectiveness and superiority of the proposed framework.

关键词： Group Activity Recognition Visual Attention Context Modeling LSTM Networks Context modeling Visual Attention Body Parts Persons Modeling Videotapes

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Jia Fu, Kui Zhao, Shengwei Ge, Shiming State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security at University of Chinese Academy of Sciences Beijing100095 China

—The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model. The knowledge of spatial and temporal saliency is first separately transferred from the two complex and redundant teachers to their simple and compact students, and the input scenes are also degraded from high-resolution to low-resolution to remove the probable data redundancy so as to greatly speed up the feature extraction process. After that, the desired spatiotemporal model is further trained by distilling and encoding the spatial and temporal saliency knowledge of two students into a unified network. In this manner, the inter-model redundancy can be further removed for the effective estimation of dynamic saliency on aerial videos. Experimental results show that the proposed approach outperforms ten state-of-the-art models in estimating visual saliency on aerial videos, while its speed reaches up to 28,738 FPS on the GPU platform. Copyright © 2019, The Authors. All rights reserved.

关键词： Students