检索结果-内蒙古大学图书馆

38th Chinese Control conference (CCC)

作者： Hou, Yuqing Jin, Feng Zhao, Baicheng Zhang, Wei Beijing Inst Technol Acad Automat Beijing 100081 Peoples R China

ISBN: (纸本)9789881563972

In many information retrieval and natural language processing tasks, it is common to use pertained word embedding to alleviate training difficulty. This motivate us to learn low-dimension representations for all domains on the Internet. There are hundreds of millions of domains on the Internet, majority of the domains attribute to only one or two specific field. Representing these property of domains in a low-dimensional and interpretable space attribute to many tasks, such as domain recommendation, domain classification, web search and et al. In this paper, we propose a novel algorithm named domain embedding, an unsupervised model which learns a fixed length representation for each domain. Experimental results show the superior performance of the proposed method.

关键词： Domain Embedding neural network Domain Classification

来源：评论

学校读者我要写书评

暂无评论

Construction of Big Data Monitoring Platform for Teaching Quality under Intelligent Education

Construction of Big Data Monitoring Platform for Teaching Qu...

引用

International Wireless Communications and Mobile Computing conference, IWCMC

作者： Fang Qin Weijia Zeng Lin Li Rong Zhao School of Digital Technology Dalian University of Science and Technology Dalian China

ISBN: (数字)9781728131290

ISBN: (纸本)9781728131306

To a great extent, the quality of teaching determines the level of trained talents. Now it has entered the era of intelligent education, coupled with the rapid development of the Internet, has produced a large number of teaching data, which also makes the monitoring and evaluation of teaching quality become particularly difficult. In view of the above problems, this paper proposes the construction of big data monitoring platform for teaching quality under intelligent education. In this paper, the OPC UA unified architecture is used for communication between devices, and the information configuration is based on the spring boot framework to achieve data collection. Then, data processing is based on GRU neural network, and spark distributed computing framework is used to improve the efficiency of data operation. Finally, the monitoring effect is realized by constructing the evaluation system.

关键词： Education Big Data Monitoring Sparks distributed computing Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Deepfakes Detection with Automatic Face Weighting

Deepfakes Detection with Automatic Face Weighting

引用

IEEE Computer Society conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Daniel Mas Montserrat Hanxiang Hao S. K. Yarlagadda Sriram Baireddy Ruiting Shao János Horváth Emily Bartusiak Justin Yang David Güera Fengqing Zhu Edward J. Delp Video and Image Processing Laboratory (VIPER) School of Electrical Engineering Purdue University West Lafayette Indiana USA

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Altered and manipulated multimedia is increasingly present and widely distributed via social media platforms. Advanced video manipulation tools enable the generation of highly realistic-looking altered multimedia. While many methods have been presented to detect manipulations, most of them fail when evaluated with data outside of the datasets used in research environments. In order to address this problem, the Deepfake Detection Challenge (DFDC) provides a large dataset of videos containing realistic manipulations and an evaluation system that ensures that methods work quickly and accurately, even when faced with challenging data. In this paper, we introduce a method based on convolutional neural networks (CNNs) and recurrent neural networks (RNNs) that extracts visual and temporal features from faces present in videos to accurately detect manipulations. The method is evaluated with the DFDC dataset, providing competitive results compared to other techniques.

关键词： Face Feature extraction Streaming media Recurrent neural networks Training Tools Social network services

来源：评论

学校读者我要写书评

暂无评论

Islanding detection using bi-directional energy meter in a DFIG based active distribution network

Islanding detection using bi-directional energy meter in a D...

引用

2019 International conference on Computer, Electrical and Communication Engineering, ICCECE 2019

作者： Verma, Shailesh Dutta, Soham Sadhu, Pradip Kumar Bharata Reddy, M. Jaya Mohanta, Dusmanta Kumar Department of Electrical Engineering Dhanbad Jharkhand India National Institute of Technology Department of Electrical and Electronics Engineering Tiruchirappalli Tamilnadu India Birla Institute of Technology Department of Electrical and Electronics Engineering Mesra Jharkhand India

ISBN: (纸本)9781538666470

With the deregulation of the electrical power market, the distribution architecture has now heavily integrated distributed generation (DG) technologies. The presence of DGs has reformed power grid management leading to concepts such as micro-grid technology. Despite its huge advantages like smoothing power grid operations, improving power quality and managing capricious demand, DGs have limitations like unplanned islanding. Prolonged accidental islanding can seriously damage utility resources and compromise the safety and serviceability. Thus, it's critical to have a protection scheme which enables quick and reliable islanding detection. Though many techniques have been developed recently, they lack either consistency or swiftness. The proposed methodology is based on voltage measurement directly from a bi-directional energy meter and processing of these signals with constant-Q transform (CQT). This technique determines, if the abnormity in a micro-grid is because of any fault or an island operation by using artificial neural network (ANN). The proposed algorithm and its efficiency is demonstrated and justified with MATLAB simulations. Various islanding events as well as non-islanding events in a wind based DG micro-grid is considered for the proposed method. © 2019 IEEE.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

From Orthography to Semantics: a Study of Morphological processing through Deep Learning neural networks

From Orthography to Semantics: a Study of Morphological Proc...

引用

International Joint conference on neural networks (IJCNN)

作者： Davila, Jaime Morris, Joanna Hampshire Coll Sch Cognit Sci Amherst MA 01002 USA

ISBN: (纸本)9781509060146

This paper presents results of using deep learning neural network techniques to map words, represented at the levels of letters, into semantic, distributed vector representations. We study and compare algorithms that have been proposed as models for human orthographic and morphological processing, such as the two layers symbolic network (AKA Naive Discriminatory Learning network) proposed by Baayen et al [1], and the dual-route approach presented by Grainger and Ziegler [2]. In addition, we study the effect of representing letters as one-hot vectors or via distributed vector representations, much like the natural language processing field has done for words. Experiment results show a better performance for the dual-route algorithm using distributed letter representations, both in terms of accuracy and speed. Our results are obtained with training sets in the tens of thousands of words, as opposed to the hundreds of thousands of words used elsewhere in the literature. These results point to the feasibility of taking advantage of morpho-orthographic patterns in order to assist with word processing in natural language processing tasks.

关键词： Semantics neural networks Training network topology Topology Task analysis Linguistics

来源：评论

学校读者我要写书评

暂无评论

Real-time Crop Classification Using Edge Computing and Deep Learning

Real-time Crop Classification Using Edge Computing and Deep ...

引用

Consumer Communications and networking conference, CCNC IEEE

作者： Ming Der Yang Hsin Hung Tseng Yu Chun Hsu Wei Chen Tseng National Chung Hsing University Pervasive AI Research (PAIR) Labs Taichung Taiwan National Chung Hsing University Taichung Taiwan

ISBN: (数字)9781728138930

ISBN: (纸本)9781728138947

In recent years, edge computing and deep learning have been successfully performed processing and classification tasks in a variety of fields including agriculture. Therefore, this research aims to use unmanned aerial vehicle (UAV) for agriculture applications with integrating edge computing and deep learning techniques. This research experiment was carried out in the NCHU Experimental Farm. The DJI Matrice 100 drone with ASUS Tinker Board S embedded system, which connects a Logitech C925e webcam to capture images are used in this study. The ASUS Tinker Board S runs a folder monitoring program and sends images over the 4G LTE network to the backend server whenever new images are captured and stored. The backend server runs a pre-trained image semantic segmentation model and provides image inference service. The image inference results with the associated segmented image will be sent to the mobile device of the drone controller, and a dynamic flight control action can be triggered. The image semantic segmentation model adopts SegNet network architecture. For a comparison purpose, another network architecture, FCN-AlexNet, was also trained and validated. The preliminary results show SegNet outperformed FCN-AlexNet in image semantic segmentation tasks in terms of the evaluation between training and validation. The average inference speed of the semantic image segmentation model is 0.7s with segmentation identification accuracy is 89%. The promising results shed light on many agriculture applications, such as crop growth condition assessment, fertilizer management, and yield prediction. Additionally, this research provides possible solutions for the labor shortage issue of agriculture which is a common challenge in an aging community like Taiwan and many countries worldwide.

关键词： 4G mobile communication autonomous aerial vehicles control engineering computing convolutional neural nets crops distributed processing image capture image classification image segmentation learning (artificial intelligence) Long Term Evolution 4G mobile communication control engineering computing Long Term Evolution image segmentation image capture distributed processing Image classification images crops drone honey bees agriculture Image Imagery (Psychotherapy) Semantics

来源：评论

学校读者我要写书评

暂无评论

distributed Active Learning Strategies on Edge Computing 6

Distributed Active Learning Strategies on Edge Computing

引用

6th IEEE International conference on Cyber Security and Cloud Computing (IEEE CSCloud) / 5th IEEE International conference on Edge Computing and Scalable Cloud (IEEE EdgeCom)

作者： Qian, Jia Hansen, Lars Kai Gochhayat, Sarada Prasad Tech Univ Denmark Dept Appl Math & Comp Sci Lyngby Denmark Old Dominion Univ Virginia Modeling Anal & Simulat Ctr Norfolk VA USA

ISBN: (纸本)9781728116617

Fog platform brings the computing power from the remote cloud-side closer to the edge devices to reduce latency, as the unprecedented generation of data causes ineligible latency to process the data in a centralized fashion at the Cloud. In this new setting, edge devices with distributed computing capability, such as sensors, surveillance camera, can communicate with fog nodes with less latency. Furthermore, local computing (at edge side) may improve privacy and trust. In this paper, we present a new method, in which, we decompose the data processing, by dividing them between edge devices and fog nodes, intelligently. We apply active learning on edge devices;and federated learning on the fog node which significantly reduces the data samples to train the model as well as the communication cost. To show the effectiveness of the proposed method, we implemented and evaluated its performance on a benchmark images data set.

关键词： Fog Computing Edge Computing Active Learning Federated Learning Bayesian neural network

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural networks for solving problems of signal processing from segmental distributed fiber optic measuring networks

引用

Journal of Physics: conference Series 2021年第1期1864卷

作者： Yu. N. Kulchin A.Yu. Kim Academician of RAS Doctor of Physical and Mathematical Sciences Professor Scientific director of the institute IACP FEB RAS Vladivostok Russia Candidate of Technical Sciences Junior Research Officer IACP FEB RAS Vladivostok Russia

The work is devoted to the problem of critical situations recognition in real-time and localization of increased acoustic vibration in critical objects, based on the signals from segmental distributed fiber-optic measuring networks (DFOMN). To solve the problem, an architecture is proposed, and a model of a situational approach to using the Convolutional neural network as an effective classification method for processing large data arrays of the DFOMN is developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative evaluation of performance and scalability of convolutional neural network implementations on a multisystem HPC architecture

引用

Journal of Physics: conference Series 2021年第1期2062卷

作者： Sunil Pandey Naresh Kumar Nagwani Shrish Verma Research Scholar Dept of Computer Science and Engineering NIT Raipur India Associate Professor Dept of Computer Science and Engineering NIT Raipur India Professor Dept of Electronics and Communications Engineering NIT Raipur India

The convolutional neural network training algorithm has been implemented for a central processing unit based high performance multisystem architecture machine. The multisystem or the multicomputer is a parallel machine model which is essentially an abstraction of distributed memory parallel machines. In actual practice, this model corresponds to high performance computing clusters. The proposed implementation of the convolutional neural network training algorithm is based on modeling the convolutional neural network as a computational pipeline. The various functions or tasks of the convolutional neural network pipeline have been mapped onto the multiple nodes of a central processing unit based high performance computing cluster for task parallelism. The pipeline implementation provides a first level performance gain through pipeline parallelism. Further performance gains are obtained by distributing the convolutional neural network training onto the different nodes of the compute cluster. The two gains are multiplicative. In this work, the authors have carried out a comparative evaluation of the computational performance and scalability of this pipeline implementation of the convolutional neural network training with a distributed neural network software program which is based on conventional multi-model training and makes use of a centralized server. The dataset considered for this work is the North Eastern University's hot rolled steel strip surface defects imaging dataset. In both the cases, the convolutional neural networks have been trained to classify the different defects on hot rolled steel strips on the basis of the input image. One hundred images corresponding to each class of defects have been used for the training in order to keep the training times manageable. The hyperparameters of both the convolutional neural networks were kept identical and the programs were run on the same computational cluster to enable fair comparison. Both the convolutional neur

关键词：

来源：评论

学校读者我要写书评

暂无评论

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized neural Scene Representations

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quan...

引用

IEEE Computer Society conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Mihir Prabhudesai Shamit Lal Hsiao-Yu Fish Tung Adam W. Harley Shubhankar Potdar Katerina Fragkiadaki Carnegie Mellon University

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Concept learning lies at the very heart of intelligence, providing organizing principles with which to comprehend the world (6). Most computer vision models learn concept classifiers or detectors using labelled examples of object boxes, poses and categories. Self-supervised or unsupervised approaches mostly focus on (pre)training CNNs on auxiliary pretext tasks to lessen the need for human labels for a downstream recognition task. The visual "concepts" learnt from pretext tasks are implicit and represented as distributed neural CNN activations (7). We see the following limitations with representing concepts (solely) as neural activations across multiple layers of a deep network: i) visual memory and computation are not separated (3), which means that computation increases exponentially with the number of visual concepts learnt, ii) concepts are not stored somewhere and cannot be referred to or retrieved on demand, iii) the number of concepts cannot increase automatically based on new visual experiences, rather it is determined by the processing architecture; this misaligns with the idea that animals are capable of spontaneous concept instantiation in novel scenes (2), iv) concepts cannot be mentally manipulated by imagining variations, transformations or mental simulations (8), v) concepts do not have any spatial dimension and are hard to use for spatial reasoning.

关键词： Three-dimensional displays Prototypes Visualization Two dimensional displays Solid modeling Feature extraction Detectors

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：