检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Bau, David Zhu, Jun-Yan Strobelt, Hendrik Lapedriza, Agata Zhou, Bolei Torralba, Antonio Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States Adobe Research Adobe Inc. San JoseCA95110 United States Watson Artificial Intelligence Laboratory CambridgeMA02142 United States Media Lab Massachusetts Institute of Technology CambridgeMA02139 United States Estudis d’Informàtica Multimèdia i Telecomunicació Universitat Oberta de Catalunya Barcelona08018 Spain Department of Information Engineering Chinese University of Hong Kong Shatin Hong Kong

Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. We find evidence that the network has learned many object classes that play crucial roles in classifying scene classes. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes. By analyzing changes made when small sets of units are activated or deactivated, we find that objects can be added and removed from the output scenes while adapting to the context. Finally, we apply our analytic framework to understanding adversarial attacks and to semantic image *** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Probabilistic modelling of gait for robust passive monitoring in daily life

arXiv

引用

arXiv 2020年

作者： Raykov, Yordan P. Evers, Luc J.W. Badawy, Reham Bloem, Bastiaan Heskes, Tom M. Meinders, Marjan Claes, Kasper Little, Max A. Aston University School of Engineering and Applied Sciences Department of Mathematics Birmingham United Kingdom Radboud university medical center Donders Institute for Brain Cognition and Behaviour Department of Neurology Center of Expertise for Parkinson & Movement Disorders Nijmegen Netherlands Radboud University Institute for Computing and Information Sciences Nijmegen Netherlands University of Birmingham School of Computer Science Birmingham United Kingdom Nijmegen Netherlands UCB Biopharma Brussels Belgium Media Lab Massachusetts Institute of Technology CambridgeMA United States

Passive monitoring in daily life may provide invaluable insights about a person's health throughout the day. Wearable sensor devices are likely to play a key role in enabling such monitoring in a non-obtrusive fashion. However, sensor data collected in daily life reflects multiple health and behavior-related factors together. This creates the need for structured principled analysis to produce reliable and interpretable predictions that can be used to support clinical diagnosis and treatment. In this work we develop a principled modelling approach for free-living gait (walking) analysis. Gait is a promising target for non-obtrusive monitoring because it is common and indicative of various movement disorders such as Parkinson's disease (PD), yet its analysis has largely been limited to experimentally controlled lab settings. To locate and characterize stationary gait segments in free living using accelerometers, we present an unsupervised statistical framework designed to segment signals into differing gait and non-gait patterns. Our flexible probabilistic framework combines empirical assumptions about gait into a principled graphical model with all of its merits. We demonstrate the approach on a new video-referenced dataset including unscripted daily living activities of 25 PD patients and 25 controls, in and around their own houses. We evaluate our ability to detect gait and predict medication induced fluctuations in PD patients based on modelled gait. Our evaluation includes a comparison between sensors attached at multiple body locations including wrist, ankle, trouser pocket and lower back. Copyright © 2020, The Authors. All rights reserved.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Generalized distributed compressive sensing with security challenges for linearly correlated information sources

Generalized distributed compressive sensing with security ch...

引用

作者： Park, Jeonghun Hwang, Seunggye Yang, Janghoon Bae, Kitae Ko, Hoon Kim, Dong Ku Department of Electrical and Computer Engineering University of Texas AustinTX United States LG Electronics Anyang Korea Republic of Department of New media Seoul Media Institute of Technology Seoul Korea Republic of College of Information & Communication Engineering Sungkyunkwan University Suwon Korea Republic of School of Electrical and Electronics Engineering Yonsei University Seoul Korea Republic of

Distributed compressive sensing (DCS) usually improves the signal recovery performance of multi-signal ensembles by exploiting both intra- and inter-signal correlation and sparsity structure. However, the existing DCS had proposed for a very limited ensemble of signals that has only single common information. This paper proposes a generalized DCS (GDCS) framework which can improve sparse signal detection performance given arbitrary types of common information, which are classified into full common information and partial common information after overcoming against existing limitation. Specifically, the theoretical bound on the required number of measurements under the GDCS is obtained. We also develop a practical algorithm to obtain benefits using the GDCS. At the end of this paper, it simply summarizes the potential security issues when it gets all sensing information in a sensor network. Finally, numerical results verify that the proposed algorithm reduces the required number of measurements for correlated sparse signal detection compared to the DCS algorithm. This research lays down the basis for efficient distributed signal detection so that it can improve the detection performance or it can detect the signal reliably when the number of signal observations is limited. Copyright © 2017 John Wiley & Sons, Ltd.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning

arXiv

引用

arXiv 2021年

作者： Hering, Alessa Hansen, Lasse Mok, Tony C.W. Chung, Albert C.S. Siebert, Hanna Häger, Stephanie Lange, Annkristin Kuckertz, Sven Heldmann, Stefan Shao, Wei Vesal, Sulaiman Rusu, Mirabela Sonn, Geoffrey Estienne, Théo Vakalopoulou, Maria Han, Luyi Huang, Yunzhi Yap, Pew-Thian Brudfors, Mikael Balbastre, Yaël Joutard, Samuel Modat, Marc Lifshitz, Gal Raviv, Dan Lv, Jinxin Li, Qiang Jaouen, Vincent Visvikis, Dimitris Fourcade, Constance Rubeaux, Mathieu Pan, Wentao Xu, Zhe Jian, Bailiang De Benetti, Francesca Wodzinski, Marek Gunnarsson, Niklas Sjölund, Jens Grzech, Daniel Qiu, Huaqi Li, Zeju Thorley, Alexander Duan, Jinming Großbröhmer, Christoph Hoopes, Andrew Reinertsen, Ingerid Xiao, Yiming Landman, Bennett Huo, Yuankai Murphy, Keelin Lessmann, Nikolas van Ginneken, Bram Dalca, Adrian V. Heinrich, Mattias P. Institute of Medical Informatics Universität zu Lübeck Ratzeburger Allee 160 Lübeck23562 Germany Fraunhofer MEVIS Institute for Digital Medicine Lübeck23562 Germany Department of Radiology and Nuclear Medicine Radboud University Medical Center GA Nijmegen6525 Netherlands The Institute of Medical Informatics Universität zu Lübeck Lübeck23562 Germany The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The Fraunhofer MEVIS Institute for Digital Medicine Lübeck23562 Germany The Department of Radiology Stanford University StanfordCA94305 United States The Department of Urology Stanford University StanfordCA94305 United States The Université Paris-Saclay CentraleSupélec Mathématiques et Informatique pour la Complexité et les Systèmes Inria Saclay Gif-sur-Yvette 91190 France Université Paris-Saclay Institut Gustave Roussy Inserm Radiothérapie Moléculaire et Innovation Thérapeutique Villejuif94800 France The Université Paris-Saclay CentraleSupélec Mathématiques et Informatique pour la Complexité et les Systèmes Inria Saclay Gif-sur-Yvette91190 France The Department of Radiology and Nuclear Medicine Radboud University Medical Center Nijmegen6525 GA Netherlands The School of Automation Nanjing University of Information Science and Technology Nanjing210044 China The School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom The Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital United States Harvard Medical School Boston United States The King’s College London United Kingdom The Tel Aviv University The Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology Hubei Wuhan430074 China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical Engineering School of Engineering Sciences Huazhong University of Sci

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://***. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods. © 2021, CC BY.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Work in Progress – Establishing a Master Program in Cyber Physical Systems: Basic Findings and Future Perspectives

Work in Progress – Establishing a Master Program in Cyber P...

引用

International Conference on Promising Electronic Technologies (ICPET)

作者： Isam Ishaq Rashid Jayousi Salaheddin Odeh Ezzaldeen Edwan Asmaa Shaheen Mohamed Elnaggar Ahmed Elagha Samy Salamah Christian Weber Hasan Abu Rasheed Raimund Kirner Martina Doolan Hamidreza Ahmadian Roman Obermaisser Dhiah el Diehn I. Abou-Tair Ala Khalifeh Sahel Alouneh Zaid Alhalhouli Khalid Alemerien Faiez Gargouri Bassem Bouaziz Nadia Aloui Mohammad Saleh Computer Engineering and Science Departments Al-Quds University Jerusalem Palestine Engineering Program and Computer Department Palestine Technical College - Deir El-Balah Deir El-Balah Palestine Institute of Knowledge Based Systems & Knowledge Management University of Siegen Siegen Germany University of Siegen Siegen Germany School of Engineering and Computer Science University of Hertfordshire Hatfield UK Chair of Embedded Systems University of Siegen Siegen Germany German Jordanian University Amman Jordan School of Electrical Engineering and Information Technology German Jordanian University Amman Jordan Computer and Information Technology Department Tafila Technical University Tafila Jordan Higher Institute of Computer Science and Multimedia University of Sfax Sfax Tunisia Higher Institute of Applied Sciences and Technology of Mateur University of Carthage Mateure Tunisia KTH Royal Institute of Technology Stockholm Sweden

This paper reports on the basic findings and future perspectives of a capacity building project funded by the European Union. The International Master of Science on Cyber Physical Systems (MS@CPS) is a collaborative project that aims to establish a master program in cyber physical systems (CPS). A consortium composed of nine partners proposed the project. Three partners are European and from Germany, UK and Sweden; while the other six partners are from the South Mediterranean region and include: Palestine, Jordan and Tunisia. The consortium is led by the University of Siegen in Germany who also manages the implementation of the work packages. CPS is an emerging engineering subject with significant economic and societal implications, which motivated the consortium to propose the establishment of a master program to offer educational and training opportunities at graduate level in the fields of CPS. In this paper, CPS as a field of study is presented with an emphasis on its importance, especially with regard to meeting local needs. A brief description of the project is presented in conjunction with the methodology for developing the courses and their learning outcomes.

关键词： computer science Internet of Things Industries Knowledge engineering Embedded systems Europe Collaboration

来源：评论

学校读者我要写书评

暂无评论

A smart service model in greenhouse environment using event-based security based on wireless sensor network

A smart service model in greenhouse environment using event-...

引用

作者： Sivamani, Saraswathi Choi, Jongsun Bae, Kitae Ko, Hoon Cho, Yongyun Department of Information and Communication Engineering Sunchon National University 413 Jungangno SuncheonJeonnam57922 Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of New Media Business Seoul Media Institute of Technology 99 Hwagok-ro 61-gil Gangseo-du Seoul07590 Korea Republic of College of Information and Communication Engineering Sunkyunkwan Univeristy Suwon Korea Republic of

In the smart agricultural environment such as greenhouse or vertical farm, the automation process is performed using the environment sensors to maintain the growth of the crops. Currently, the system rely on the defined rule to perform automation, but the situation can turn catastrophic. With the interruption in the communication, data forging, or eavesdropping, the crops will be rotten and destroyed. Therefore, to maintain the automation without failure, the connection needs to be secure and tampering has to be avoided. In this paper, we discuss the security solution for the wireless sensor networks in the automated agricultural environment without any human intervention. The sink node that collects the sensor values organizes the data and transfer the data to the server, along with the XML encryption and private key mechanism for the communication. The secure protocol is used to make connection using the private key, XML ecryption prevents the system from eavesdropping, and forging. Some of the events discussed in the papers are EVNData, SENSORError, DDoSAttack, and ConnThreat. With the help of the event and the tag information, the data security and confidentiality is increased, for the better automation and crop growth. Copyright © 2017 John Wiley & Sons, Ltd.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

User sensitive data identification method based on constraint gaussian mixture-probability hypothesis density filter

引用

International Journal of Circuits, Systems and Signal Processing 2018年 12卷 367-371页

作者： Lu, Zhengqiu Xue, Shengjun Zhou, Chunliang Hua, Quanping Hu, Defa Jiang, Weijin Department of Information & Media Zhejiang Fashion Institute of Technology NingboZhejiang315175 China Department of Computer & Software Nanjing University of Information Science & Technology NanjingJiangsu210044 China Department of Information & Engineering Dahongying University NingboZhejiang315175 China Computer and Information Engineering Hunan University of Commerce ChangshaHunan410205 China

In order to identify the sensitive data of users in Internet, a sensitive data identification method is proposed by weight constraint Gaussian Mixture-Probability Hypothesis Density (GM-PHD) filter and Restricted Boltzmann Machines (RBM) in this thesis. At first, the data is normalized with weight constraint in this method, and the random network is formed by the definition of the collected characteristic simulation energy function of RBM. Then, the sensitive feature weight of sensitive data is generated in GM-PHD filter. Finally, the simulation experiments are conducted to study this method performance compared with GM-PGD filter, Gaussian filter by MATLAB, including filtering and tracking performance, relevancy degree, sensitive words weight, cluster mapping and high frequency approximation. The results show that, compared with other methods, this method has better performance. © 2018, North Atlantic University Union. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms-based Object Detection and Localization Revisited

引用

Journal of Physics: Conference Series 2021年第1期1892卷

作者： Safa Riyadh Waheed Norhaida Mohd Suaib Mohd Shafry Mohd Rahim Myasar Mundher Adnan A. A. Salim Big Data Center & Faculty of Engineering School of Computing Universiti Teknologi Malaysia 81310 Johor Bahru Malaysia Computer Techniques Engineering Department Faculty of Information Technology Imam Jaafar Al-Sadiq University Baghdad Iraq UTM-IRDA Digital Media Institute of Human-Centred Engineering Universiti Teknologi Malaysia 81310 Johor Bahru Malaysia Islamic University Najaf Iraq Laser Center & Physics Department Faculty of Science Universiti Teknologi Malaysia 81310 Johor Bahru Malaysia

The computer vision (CV) is an emerging area with sundry promises. This communication encompasses the past development, recent trends and future directions of the CV in the context of deep learning (DL) algorithms-based object detections and localizations techniques. To identify the object location inside an image and recognize it by a computer program as fast as the human brain the machine learning and DL techniques have been evolved. However, the main limitations of the machine are related to the prolonged time consumption to handle vast amount of data to perform the same task as the human brain. To overcome these shortcomings, the convolution neural networks (NNs)-based deep NN has been developed, which detects and classifies the object with high precision. To train the deep NNs, massive amount of data (in the form of images and videos) and time is needed, making the computational cost of the CV very high. Thus, transfer learning techniques have been proposed wherein a model trained on one task can be reused on another linked task, thereby producing excellent outcomes. In this spirit, diverse DL-based algorithms have been introduced to detect and classify the object. These algorithms include the region-based convolutional NN (R-CNN), fast R-CNN, Faster R-CNN, mask E-CNN and You Only Look Once. A comparative evaluation among these techniques has been made to reveal their merits and demerits in the CV.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Lung cancer prediction using higher-order recurrent neural network based on glowworm swarm optimization

引用

Neural Computing and Applications 2018年第9期32卷 4373-4386页

作者： Selvanambi, Ramani Natarajan, Jaisankar Karuppiah, Marimuthu Islam, SK Hafizul Hassan, Mohammad Mehedi Fortino, Giancarlo School of Computing Science and Engineering Vellore Institute of Technology (VIT) Vellore India Department of Computer Science and Engineering Indian Institute of Information Technology Kalyani Kalyani India Chair of Smart Cities Technology College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Department of Informatics Modeling Electronics and Systems University of Calabria Rende Italy

Therapeutic issues are commonly found in every single person. Tumor is a standout among the most unsafe sicknesses a human can ever had. It is exceptionally hard to distinguish it in its beginning times as its side effects seem just in the progressed stages. Subsequently, the early forecast of lung growth is compulsory for the analysis procedure, and it gives the higher possibilities for fruitful treatment. It is the most difficult approach to upgrade a patient’s possibility for survival. Henceforth, a higher-order neural network system called recurrent neural network with Levenberg–Marquardt model with the help of glowworm swarm optimization algorithm is proposed for managing multimodal disease information. The execution of the proposed strategies is tried with information and the benchmark dataset, and the outcomes demonstrate that the higher-order recurrent neural systems with glowworm swarm optimization give better accuracy of 98% in comparison with customary optimized neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Differential Privacy Random Forest Method of Privacy Protection in Cloud

A Differential Privacy Random Forest Method of Privacy Prote...

引用

IEEE International Conference on Computational Science and engineering, CSE

作者： Chaoxian Lv Qianmu Li Huaqiu Long Yumei Ren Fei Ling School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Intelligent Manufacturing Department Wuyi University Jiangmen China Jiangsu Women's Federation New Media and Network Information Communication Center (Jiangsu “Mo Chou” magazine) Nanjing China Jiangsu Postgraduate Workstation Nanjing Liancheng Technology Development Co. Ltd. Nanjing China

This paper proposes a new random forest classification algorithm based on differential privacy protection. In order to reduce the impact of differential privacy protection on the accuracy of random forest classification, a hybrid decision tree algorithm is proposed in this paper. The hybrid decision tree algorithm is applied to the construction of random forest, which balances the privacy and classification accuracy of the random forest algorithm based on differential privacy. Experiment results show that the random forest algorithm based on differential privacy can provide high privacy protection while ensuring high classification performance, achieving a balance between privacy and classification accuracy, and has practical application value.

关键词： Classification algorithms Decision trees Privacy Forestry Prediction algorithms

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：