检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Lujuan Zhang Jun Li Tao Huang Zhenyuan Ma Zhiyong Lin Mukesh Prasad School of Mathematics and System Sciences Guangdong Polytechnic Normal University Guangzhou China School of Software and Center for Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia School of Computer Science Guangdong Polytechnic Normal University Guangzhou China

This paper proposes an information completion technique, GAN2C, by imposing dual consistency constraints (2C) to a closed loop encoder-decoder architecture based on the generative adversarial nets (GAN). When adopting deep neural networks as function approximators, GAN2C enables highly effective multi-modality image conversion with sparse observation in the target modes. For empirical demonstration and model evaluation, we show that trained deep neural networks in GAN2C can infer colors for grayscale images, as well as estimate rich 3D information of a scene by densely predicting the depths. The results of the experiments show that in both tasks GAN2C as a generic framework has been comparable to or advanced the state-of-the-art performance which are achieved by highly specialized systems. Code is available at https://***/AdalinZhang/GAN2C.

关键词： Image color analysis Gallium nitride Task analysis Neural networks Gray-scale Generative adversarial networks Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Ensemble soft-margin softmax loss for image classification

arXiv

引用

arXiv 2018年

作者： Wang, Xiaobo Zhang, Shifeng Lei, Zhen Liu, Si Guo, Xiaojie Li, Stan Z. CBSRandNLPR Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University School of Computer Software Tianjin University Tianjin China Faculty of Information Technology Macau University of Science and Technology Macau China

Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrimination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a strong one, inspired by the recognition that the diversity among weak classifiers is critical to a good ensemble. To achieve the diversity, we adopt the Hilbert-Schmidt Independence Criterion (HSIC). Considering these two aspects in one framework, we design a novel loss, named as Ensemble soft-Margin Softmax (EM-Softmax). Extensive experiments on benchmark datasets are conducted to show the superiority of our design over the baseline softmax loss and several state-of-the-art alternatives. Copyright © 2018, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Label-Free Detection of DNA Hybridization Utilizing Dual S-Tapered Thin-Core Fiber Interferometer”

引用

Journal of Lightwave Technology 2019年第19期37卷 5158-5158页

作者： Xu Zhang Bo Liu Hao Zhang Binbin Song Jixuan Wu Shaoxiang Duan Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology College of Electronic Information and Optical Engineering Nankai University Tianjin China Key Laboratory of Computer Vision and Systems Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin China College of Electronic and Information Engineering Tianjin Polytechnic University Tianjin China

Presents corrections to above named paper.

关键词： Biosensors DNA Optical fiber sensors Molecular biophysics Microsensors

来源：评论

学校读者我要写书评

暂无评论

New Big Data Collecting Method Based on Compressive Sensing in WSN

New Big Data Collecting Method Based on Compressive Sensing ...

引用

International Conference on computer Communications and Networks (ICCCN)

作者： De-gan Zhang Xiao-hua Liu Yu-ya Cui Hong-tao Peng School of Computer Science &Engineering Tianjin University of Technology Tianjin China Computing & Novel software Technology Tianjin Key Lab of Intelligent Tianjin China Ministry of Education Key Laboratory of Computer Vision and System(TJUT) Tianjin China National Petroleum Corporation (CNPC) Managers Training Institute Beijing China

Considered the wireless sensor network clustering structure, a new big data collecting method based on compressive sensing is proposed. The collection process is as follows: in the cluster, the sink node sets the corresponding seed vector based on the distribution of network, and then sends it to each cluster head. Cluster head can generate corresponding own random spacing sparse matrix based on its received seed vector, and collect data through compressive sensing technology; Among clusters, clusters forward measurement values to sink node along multi-hop routing tree which we built before. Performance analyzing and comparison of results show that this method is superior to other methods regardless of in a cluster or inter-cluster.

关键词： Wireless sensor networks Compressed sensing Sparse matrices Big Data Routing Energy consumption Training

来源：评论

学校读者我要写书评

暂无评论

Auto-contouring FDG-PET/MR images for cervical cancer radiation therapy: An intelligent sequential approach using focally trained, shallow U-Nets

引用

Intelligence-Based Medicine 2021年 5卷 100026-100026页

作者： Atallah Baydoun Ke Xu Latoya A. Bethell Feifei Zhou Jin Uk Heo Kaifa Zhao Elisha T. Fredman Rodney J. Ellis Pengjiang Qian Raymond F. Muzic Bryan J. Traughber Department of Radiation Oncology University Hospitals Cleveland Medical Center Cleveland OH USA School of Artificial Intelligence and Computer Science Jiangnan University Wuxi Jiangsu 214122 China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi Jiangsu 214122 China Department of Radiology School of Medicine Case Western Reserve University Cleveland OH 44106 USA Department of Biomedical Engineering Case Western Reserve University Cleveland OH 44106 USA Department of Computing Hong Kong Polytechnic University Hung Hom 999077 Hong Kong Department of Radiation Oncology Penn State Cancer Institute Hershey PA 17033 USA

Background Manual contouring for radiation therapy planning remains the most laborious and time consuming part in the radiation therapy workflow. Particularly for cervical cancer, this task is complicated by the complex female pelvic anatomy and the concomitant dependence on 18 F-labeled Fluorodeoxyglucose (FDG) positron emission tomography (PET) and magnetic resonance (MR) images. Using deep learning, we propose a new auto-contouring method for FDG-PET/MR based cervical cancer radiation therapy by combining the high level anatomical topography and radiological properties, to the low-level pixel wise deep-learning based semantic segmentation. Materials/methods The proposed method: 1) takes advantage of PET data and left/right anatomical symmetry, creating sub-volumes that are centered on the structures to be contoured. 2) Uses a 3D shallow U-Net (sU-Net) model with an encoder depth of 2.3) Applies the successive training of 3 consecutive sU-Nets in a feed forward strategy. 4) Employs, instead of the usual generalized dice loss function (GDL), a patch dice loss function (PDL) that takes into account the Dice similarity index (DSI) at the level of each training patch. Experimental analysis was conducted on a set of 13 PET/MR images was using a leave-one-out strategy. Results Despite the limited data availability, 5 anatomical structures - the gross tumor volume, bladder, anorectum, and bilateral femurs - were accurately (DSI = 0.78), rapidly (1.9 s/structure), and automatically delineated by our algorithm. Overall, PDL achieved a better performance than GDL and DSI was higher for organs at risk (OARs) with solid tissue (e.g. femurs) than for OARs with air-filled soft tissues (e.g. anorectum). Conclusion The presented workflow successfully addresses the challenge of auto-contouring in FDG-PET/MR based cervical cancer. It is expected to expedite the cervical cancer radiation therapy workflow in both, conventional and adaptive radiation therapy settings.

关键词： Cervical cancer Deep learning Image segmentation PET/MR Based radiation therapy U-net

来源：评论

学校读者我要写书评

暂无评论

Simultaneous fidelity and regularization learning for image restoration

arXiv

引用

arXiv 2018年

作者： Ren, Dongwei Zuo, Wangmeng Zhang, David Zhang, Lei Yang, Ming-Hsuan College of Intelligence and Computing Tianjin University Tianjin300350 China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China School of Science and Engineering Chinese University of Hong Kong Shenzhen China School of Engineering University of California MercedCA95344

Most existing non-blind restoration methods are based on the assumption that a precise degradation model is known. As the degradation process can only be partially known or inaccurately modeled, images may not be well restored. Rain streak removal and image deconvolution with inaccurate blur kernels are two representative examples of such tasks. For rain streak removal, although an input image can be decomposed into a scene layer and a rain streak layer, there exists no explicit formulation for modeling rain streaks and the composition with scene layer. For blind deconvolution, as estimation error of blur kernel is usually introduced, the subsequent non-blind deconvolution process does not restore the latent image well. In this paper, we propose a principled algorithm within the maximum a posterior framework to tackle image restoration with a partially known or inaccurate degradation model. Specifically, the residual caused by a partially known or inaccurate degradation model is spatially dependent and complexly distributed. With a training set of degraded and ground-truth image pairs, we parameterize and learn the fidelity term for a degradation model in a task-driven manner. Furthermore, the regularization term can also be learned along with the fidelity term, thereby forming a simultaneous fidelity and regularization learning model. Extensive experimental results demonstrate the effectiveness of the proposed model for image deconvolution with inaccurate blur kernels, deconvolution with multiple degradations and rain streak removal. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A K self-adaptive SDN controller placement for wide area networks

引用

Frontiers of Information Technology & Electronic engineering 2016年第7期17卷 620-633页

作者： Peng XIAO Zhi-yang LI Song GUO Heng QI Wen-yu QU Hai-sheng YU School of Information Science and Technology Dalian Maritime University School of Information Science and Engineering Dalian Polytechnic University School of Computer Science and Engineering The University of Aizu School of Computer Science and Technology Dalian University of Technology School of Computer Software Tianjin University

As a novel architecture,software-defined networking(SDN) is viewed as the key technology of future *** core idea of SDN is to decouple the control plane and the data plane,enabling centralized,flexible,and programmable network *** local area networks like data center networks have benefited from SDN,it is still a problem to deploy SDN in wide area networks(WANs) or large-scale *** works show that multiple controllers are required in WANs with each covering one small SDN ***,the problems of SDN domain partition and controller placement should be further ***,we propose the spectral clustering based partition and placement algorithms,by which we can partition a large network into several small SDN domains efficiently and *** our algorithms,the matrix perturbation theory and eigengap are used to discover the stability of SDN domains and decide the optimal number of SDN domains *** evaluate our algorithms,we develop a new experimental framework with the Internet2 topology and other available WAN *** results show the effectiveness of our algorithm for the SDN domain partition and controller placement problems.

关键词： software-defined networking(SDN) Controller placement K self-adaptive method

来源：评论

学校读者我要写书评

暂无评论

Cost-effective object detection: Active sample mining with switchable selection criteria

arXiv

引用

arXiv 2018年

作者： Wang, Keze Lin, Liang Yan, Xiaopeng Chen, Ziliang Zhang, Dongyu Zhang, Lei School of Data and Computer Science Sun Yat-sen University Guangzhou China Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education China Department of Computing Hong Kong Polytechnic University Hong Kong

Though quite challenging, leveraging large-scale unlabeled or partially labeled data in learning systems (e.g., model / classifier training) has attracted increasing attentions due to its fundamental importance. To address this problem, many active learning (AL) methods have been proposed that employ up-to-date detectors to retrieve representative minority samples according to predefined confidence or uncertainty thresholds. However, these AL methods cause the detectors to ignore the remaining majority samples (i.e., those with low uncertainty or high prediction confidence). In this work, by developing a principled active sample mining (ASM) framework, we demonstrate that cost-effectively mining samples from these unlabeled majority data is key to training more powerful object detectors while minimizing user effort. Specifically, our ASM framework involves a switchable sample selection mechanism for determining whether an unlabeled sample should be manually annotated via AL or automatically pseudo-labeled via a novel self-learning process. The proposed process can be compatible with mini-batch based training (i.e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection. In this process, the detector, such as a deep neural network, is first applied to the unlabeled samples (i.e., object proposals) to estimate their labels and output the corresponding prediction confidences. Then, our ASM framework is used to select a number of samples and assign pseudo-labels to them. These labels are specific to each learning batch, based on the confidence levels and additional constraints introduced by the AL process, and will be discarded afterward. Then, these temporarily labeled samples are employed for network fine-tuning. In addition, a few samples with low-confidence predictions are selected and annotated via AL. Notably, our method is suitable for object categories that are not seen in the unlabeled data during the learning process. Ex

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Cache Optimization Method to Reduce Network Traffic in Communication Systems

Cache Optimization Method to Reduce Network Traffic in Commu...

引用

International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)

作者： Ruey-Shun Chen Yu-Xi Hu Xiaopeng Fan Yeh-Cheng Chen Shi-Jinn Horng T.-C. Wang Naixue Xiong Department of computer engineering Dongguan Polytechnic Dongguan P.R. China Department of computer science University of California Davis CA USA The School of Software and Microelectronic Northwestern Polytechnical University Xian P.R. China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen P.R. China Institute of Information Management National Chiao Tung University School of Computer Science and Technology Tianjin University Tianjin P. R. China

ISBN: (纸本)9781538694046;9781538694039

Using the cloud technology with Smart Protect Network (SPN) to do file virus scanning. The overwhelming increase of population will lead to an increase network traffic usage. In most products, local cache mechanism is implemented for the purpose of reducing the network traffics. However, the database designed to store cache is limited, lot of times, cache will get purged when there are lots of queries sent and replaced by other newest queries. It is not an efficient by using traditional methodology to build or forming cache. In order to reduce the network traffic usage, the paper propose a solution, which utilize data mining technique with clustering concept, by gathering the current feedback data we have from our SPN, we are able to form these data in groups with similarity, and by deploying these data to client side, to achieve the reduction of traffic usage. In prototyping, this design for military communications can really reduce network traffic more than 20%. And the speed of file scanning time can faster more than 12%.

关键词： Parallel architectures Programming Data mining Optimization Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Design of contactless electromagnetic levitation and electrostatic driven rotation control system for a micro mirror

Design of contactless electromagnetic levitation and electro...

引用

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Qijun Xiao Kraft Michael Zhonghui Luo Jianping Chen Jianbin Wang School of electronic and electrical engineering Zhaoqing University Zhaoqing PRC ESAT department Catholic University of Leuven Leuven Belgium Faculty of Mechanical and Electronic Guangdong Polytechnic Normal University Guangzhou PRC School of Computer Science and Software Zhaoqing University Zhaoqing PRC

It is proposed in this paper the design of a contactless electromagnetic levitation and electrostatic driven rotation control system for a micro mirror. The design can levitate an aluminum micro rotor with 3.3mm diameter and 8 μm thickness. Using electromagnetic force and electrostatic force, the rotor can be levitated to 100μm height with 20MHz frequency and 0.5A p-p input current and driven to rotate around the vertical axis within the range of ±180°. The control system design is presented using detection and control circuit, and the levitation and rotation figures are also presented. The square wave response experiment is carried out to show its feasibility.

关键词： Rotors Electrodes Levitation Voltage control Electromagnetics Control systems Electrostatics

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：