检索结果-内蒙古大学图书馆

10th International conference on Robotic, Vision, Signal processing and Power Applications, ROVISP 2018

ISBN: (纸本)9789811364464

The proceedings contain 81 papers. The special focus in this conference is on Robotic, Vision, Signal processing and Power Applications. The topics include: Breadfruit peel extract impact on hela cancer cell viability and proliferation;human sperm tracking using improved anti-collision mean shift tracking method;muscle oxygen saturation correlates with muscle mechanomyography during prolonged electrical stimulation-evoked wrist extension exercise;application of artocarpus altilis extract on cervical cancer cell via electroporation method;development of health monitoring system with support vector machine based machine learning;microfabrication and electrical characterization of non-spiral planar microcoils for biomedical applications;Embedded ethernet and controller area network (CAN) in real time control communication system;physical modelling of gallium nitride (gan) based double barrier quantum well device;bank division topology for existing hierarchical balancing control in a grid-scale battery energy storage system;A study of artificial neural network (ANN) in power system dynamic stability;cell balancing topologies in battery energy storage systems: A review;Model predictive control of off-board PEV charger;Grid-connected PV generator using three-phase VSC with model predictive control;four coil wireless power transfer system using magnetic resonance coupling;switching circuit and drive for cascaded multilevel inverter;place and route optimization for high coverage multi-corner multi-mode timing fix;8-bit hybrid DAC with rail-to-rail buffer amplifier;an investigation of reactive-active power control approach for grid-connected pv arrays in a low voltage distribution system;Power quality improvements in a novel 24-pulse line commutated converter HVDC transmission system;effect of distributed generation (dg) to earth fault.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An ERT-based Robotic Skin with Sparsely distributed Electrodes: Structure, Fabrication, and DNN-based Signal processing

An ERT-based Robotic Skin with Sparsely Distributed Electrod...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Kyungseo Park Hyunkyu Park Hyosang Lee Sungbin Park Jung Kim Korea Advanced Institute of Science and Technology Daejeon South Korea Max Planck Institute for Intelligent Systems Stuttgart Germany

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Electrical resistance tomography (ERT) has previously been utilized to develop a large-scale tactile sensor because this approach enables the estimation of the conductivity distribution among the electrodes based on a known physical model. Such a sensor made with a stretchable material can conform to a curved surface. However, this sensor cannot fully cover a cylindrical surface because in such a configuration, the edges of the sensor must meet each other. The electrode configuration becomes irregular in this edge region, which may degrade the sensor performance. In this paper, we introduce an ERT-based robotic skin with evenly and sparsely distributed electrodes. For implementation, we sprayed a carbon nanotube (CNT)-dispersed solution to form a conductive sensing domain on a cylindrical surface. The electrodes were firmly embedded in the surface so that the wires were not exposed to the outside. The sensor output images were estimated using a deep neural network (DNN), which was trained with noisy simulation data. An indentation experiment revealed that the localization error of the sensor was 5.2 ± 3.3 mm, which is remarkable performance with only 30 electrodes. A frame rate of up to 120 Hz could be achieved with a sensing domain area of 90 cm 2 . The proposed approach simplifies the fabrication of 3D-shaped sensors, allowing them to be easily applied to existing robot arms in a seamless and robust manner.

关键词： Robot sensing systems Electrodes Conductivity Image reconstruction Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Research on Project Knowledge Management Risk Early Warning Based on Bp neural network

引用

Journal of Physics: conference Series 2021年第3期1744卷

作者： Wei Li Shandong Vocational College of Science and Technology Weifang Shandong China 261053

On the premise of analyzing various evaluation methods and means and constructs the comprehensive evaluation model of external knowledge transfers risk of transformation enterprises. BP network has robustness and fault tolerance, it is distributed storage of information, local damage will be a certain degree of reduce the network performance, does not result in a catastrophic risk, tolerance with a larger error in the input value, and even individual errors exist, at the same time each activity unit has the independence of the information processing, which can realize the parallel computing, improve speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Line Loss Calculation in Power Distribution network Based on Power Measurement Data and BP neural network

Line Loss Calculation in Power Distribution Network Based on...

引用

International conference on Power System Technology (POWERCON)

作者： Su Chao Liu Zhensheng Hu Jinlei Kuang Zhenxing Wei Zheng Guangdong Power Grid Corp Qingyuan Power Supply Bur Qingyuan 511515 Guangdong Peoples R China Shanghai Qiyi Elect Technol Co Ltd Shanghai 200052 Peoples R China

ISBN: (纸本)9781538664612

The line loss in power distribution network is an important index that affects the economic benefit of power supply enterprise. In order to ensure the accuracy and stability of the line loss calculation based on large amount of power measurement data, the distributed parallel processing method is applied to the line loss computing service, and the line loss calculation model in power distribution network was obtained by the fitting of BP neural network. Furthermore, many examples are given to test the algorithm proposed in this paper, the results show that the method can guarantee the stability and the accuracy of calculation results in line loss calculation.

关键词： line loss calculation distributed parallel processing power measurement data BP neural network

来源：评论

学校读者我要写书评

暂无评论

OCC: A Smart Reply System for Efficient In-App Communications 19

OCC: A Smart Reply System for Efficient In-App Communication...

引用

25th ACM SIGKDD International conference on Knowledge Discovery & Data Mining (KDD)

作者： Weng, Yue Zheng, Huaixiu Bell, Franziska Tur, Gokhan Uber AI San Francisco CA 94103 USA

ISBN: (纸本)9781450362016

Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber's smart reply system: one-click-chat (OCC), which is a key enhanced feature on top of the Uber in-app chat system. It enables driver-partners to quickly respond to rider messages using smart replies. The smart replies are dynamically selected according to conversation content using machine learning algorithms. Our system consists of two major components: intent detection and reply retrieval, which are very different from standard smart reply systems where the task is to directly predict a reply. It is designed specifically for mobile applications with short and non-canonical messages. Reply retrieval utilizes pairings between intent and reply based on their popularity in chat messages as derived from historical data. For intent detection, a set of embedding and classification techniques are experimented with, and we choose to deploy a solution using unsupervised distributed embedding and nearest-neighbor classifier. It has the advantage of only requiring a small amount of labeled training data, simplicity in developing and deploying to production, and fast inference during serving and hence highly scalable. At the same time, it performs comparably with deep learning architectures such as word-level convolutional neural network. Overall, the system achieves a high accuracy of 76% on intent detection. Currently, the system is deployed in production for English-speaking countries and 71% of in-app communications between riders and driver-partners adopted the smart replies to speedup the communication process.

关键词： smart reply machine learning natural language processing intent detection unsupervised learning distributed embedding neural networks

来源：评论

学校读者我要写书评

暂无评论

Combining Parallel Genetic Algorithms and Machine Learning to improve the research of optimal vaccination protocols 26

Combining Parallel Genetic Algorithms and Machine Learning t...

引用

26th Euromicro International conference on Parallel, distributed, and network-Based processing (PDP)

作者： Pennisi, Marzio Russo, Giulia Pappalardo, Francesco Univ Catania Dept Math & Comp Sci Catania Italy Univ Catania Dept Biomed Sci Catania Italy Univ Catania Dept Drug Sci Catania Italy

ISBN: (纸本)9781538649756

The developing of novel prophylactic and therapeutic vaccine candidates in the field of cancer immunology brought to very promising results against tumors, entitling full protection with reduced amount of the typical side effects of the actual conventional treatments. However, such treatments required a constant, life-long, administration procedure to keep protection. As both the period of protection and the relative number of administrations grow, the problem of finding the best administration protocol, in time and dosage, becomes more and more complex. Such a problem cannot be usually solved in in vivo experiments, as the costs in terms of time, money, and people would be prohibitive. We propose a hybrid approach that integrates machine learning and parallel genetic algorithms to enhance the research in silico of optimal administration protocols for a cancer vaccine. A neural network is used to improve both crossover and mutation operators. Preliminary results suggest that the use of such could bring to better administration protocols using a similar computational effort.

关键词： Genetic algorithms machine learning neural networks agent based models optimal vaccine protocol cancer

来源：评论

学校读者我要写书评

暂无评论

Deep Face Recognition with Weighted Center Loss 10

Deep Face Recognition with Weighted Center Loss

引用

10th International conference on Graphics and Image processing (ICGIP)

作者： Wu, Fuzhang Kong, Yan Wu, Yanjun Chinese Acad Sci Inst Software Beijing Peoples R China State Key Lab Comp Sci Beijing Peoples R China Tencent Youtu Lab Shanghai Peoples R China

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

ID face photos are widely used for identity verification in many real-world applications. In these cases, the face from ID photo is expected to compare with the face obtained from the daily life image. To improve the ID/life face verification performance, the datasets containing various ID face photos and daily life face images are always needed to train an available CNN model for feature extraction. However, it's really hard to get uniform distributed data for both the ID photos and daily life images. In most face datasets, each subject only contains one ID photo (for example, obtained from the identity card) while contains varies of life images. This imbalanced distribution causes the difficulty of learning a general deep feature representation for both the ID and life faces, since the daily life images tend to have a higher impact on the feature learning than the ID photos. To address this challenge, we propose a weighted center loss which aims to learn a center of deep features for each class and penalizes the distance between the image features and their corresponding class centers with different weights. By emphasizing the ID photo features in the loss computation, our weighted center loss can train a general CNN which obviously narrows the distance between the ID and life faces. Final experiments demonstrate that with the joint supervision of softmax and weighted center loss, our proposed framework can minimize the intra-class variations caused by the imbalanced ID/life data distribution and significantly improve the ID face based verification accuracy.

关键词： face recognition convolutional neural network weighted center loss

来源：评论

学校读者我要写书评

暂无评论

Real Time Classification Analysis in distributed Acoustic Sensing Systems 26

Real Time Classification Analysis in Distributed Acoustic Se...

引用

26th IEEE Signal processing and Communications Applications conference (SIU)

作者： Maral, Hakan Akgun, Toygar Aktas, Metin ASELSAN Ulasim Guvenl Enerji & Otomasyon Sistemle Sekt Baskanligi Ankara Turkey TOBB Ekon & Teknol Univ Sogutozu MahSogutozu Cd 43 TR-06510 Ankara Turkey

ISBN: (纸本)9781538615010

In this paper, we present a real time treat classification approach to be used in a distributed acoustic sensing system that is developed for monitoring linear assets with a maximum length of 50 kms. The Convolutional Neuaral network (CNN) based deep learning approach is used for treat classification. The classification accuracies and execution times for neural networks with different architecture and complexity are measured. The proposed approach for classifying all the detected treats without decreasing the detection accuracy is introduced. The maximum allowable execution time for the network structure that is appropriate for the proposed approach is analyzed for the worst case scenario. Hence, the most appropriate network architecture selection can be performed based on classification accuracy and also applicability in real-time criterion.

关键词： distributed acoustic sensing phase-OTDR deep learning convolutional neural networks CNN threat detection threat classification real-time processing

来源：评论

学校读者我要写书评

暂无评论

Image Preprocessing Algorithm Based on K-Means

Image Preprocessing Algorithm Based on K-Means

引用

IEEE International conference on Parallel and distributed Computing, Applications and Technologies (PDCAT)

作者： Xiaofan Zhao Manchun Cai Yuan Ren Fan Yang School of Information Technology University of China Beijing China

ISBN: (数字)9781728126166

ISBN: (纸本)9781728126173

With the development of image acquisition and storage technology, the image data is greatly increased. How to process the increasing image data quickly has become the main problem of image processing. In this paper, the image data are processed by K-means algorithm in Python language environment, and the original image and the image processed by K-means algorithm are classified and trained in convolution neural network. The experimental results show that the time consumed by the image processed by K-means algorithm is 20 s to 30 s less than that of the original image in convolution neural network. It can effectively improve the efficiency of image processing.

关键词： Clustering algorithms Classification algorithms Training Convolution neural networks Partitioning algorithms Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Using Long Short-Term Memory network for Recognizing Motor Imagery Tasks 24

Using Long Short-Term Memory Network for Recognizing Motor I...

引用

24th IEEE International conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)

作者： Xu, Xiaoyan Xu, Fangzhou Shu, Minglei Zhang, Yingchun Yuan, Qi Zheng, Yuanjie Qilu Univ Technol Shandong Acad Sci Sch Elect Engn & Automat Jinan Peoples R China Qilu Univ Technol Shandong Acad Sci Sch Elect & Informat Engn Dept Phys Jinan Peoples R China Natl Supercomp Ctr Jinan Shandong Comp Sci Ctr Jinan Peoples R China Key Lab Med Artificial Intelligence Jinan Peoples R China Qilu Univ Technol Shandong Acad Sci Jinan Peoples R China Qilu Univ Technol Shandong Acad Sci Engn Training Ctr Jinan Peoples R China Shandong Normal Univ Sch Phys & Elect Jinan Peoples R China Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Univ Shandong Key Lab Intelligent Comp & Informat Secur Jinan Peoples R China Shandong Prov Key Lab Novel Distributed Comp Soft Jinan Peoples R China Shandong Normal Univ Inst Biomed Sci Jinan Peoples R China

ISBN: (纸本)9781538683446

Classifying the electrocorticogram (ECoG) signals based on motor imagery (MI) is one of the important issues of the BCI systems. Deep learning approaches have been most popularly applied to learn representations and classify different types of data. However, the number of studies that modeling cognitive events from ECoG signals are very limited. In this paper, we propose a deep learning method to use long short-term memory (LSTM) recurrent neural networks for learning representations from ECoG and gradient boosting (GB) for classifying MI ECoG, and demonstrate its advantages. First, we transform multichannel ECoG time-series into the LSTM-GB model including sequential information. After that, we train an LSTM neural network to learn robust spatial-temporal representations. The subtle temporal dependencies of ECoG data streams can be extracted from LSTM with unique information processing mechanism. The LSTM features coupled with the GB classifier can yield the satisfactory accuracy of 100% on publicly available ECoG dataset. Experiments demonstrate that the proposed method can effectively recognize different MI tasks. Empirical evaluation on the MI classification tasks demonstrates significant improvements in classification accuracy over current state-of-the-art approaches in MI-based BCI field.

关键词： electrocorticogram motor imagery long short-term memory gradient boosting

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：