检索结果-内蒙古大学图书馆

3rd International Conference on Cognitive Computing and Information processing, CCIP 2017

作者： Bhavanishankar, K. Sudhamani, M.v. RNS Institute of Technology Bengaluru India

ISBN: (纸本)9789811090585

Cancer is considered to be one of the threat causing disease to human health. Amongst the various types of cancers, the one which originates in lung is most fatal. Lung cancer appears in the form of nodules and is caused by anomalous growth of cells in the lung organ. Though detecting and diagnosing lung cancer at the early stages can enhance the survival rate, there are still numerous challenges. Computer Aided Diagnosis (CAD) systems which makes use of various imaging modalities like Computed Tomography (CT) and several image processing techniques, assists the domain experts in the process of prognosis and treatment. A novel technique to detect the candidate lung nodule in 3D CT imagery is presented in this paper which employs minimum area filters and layer based filters designed to eliminate the irregularities, blood vessels and other nodules like lung artifacts. Finally the spherical and spiculated structures are retained by considering the diameter of components under observation. The algorithms are tested against 15 cases each having an average of 250 slices, obtained from LIDC. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Artificial vision in Embedded System for Rigid Parts Recognition

Artificial Vision in Embedded System for Rigid Parts Recogni...

引用

CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)

作者： Mario Peña-Cabrera L. Amezquita v.Lomas-Barrié R. Osorio I. López J Gastón Lefranc IIMAS Universidad Nacional Autónoma de México CDMX Posgrado I.Eléctrica Universidad Nacional Autónoma de México CDMX Pontificia Universidad Católica de Valparaiso Chile CINVESTAV Saltillo México

Since the first robot manipulator for industrial applications was installed for General Motors, the planning and execution of its movements has been an important part in the development of robotic systems involving researchers from different specialties. The planning and guidance of the movement in the robots has been increasingly complex due to the wide variety of applications in which they are used, from repetitive tasks in the traditional assembly lines to the assistance in the movements of very precise surgical operations which require real-time movement guidance, this has established an area of research and technological development known as “Robotics hardware and software driving”. The article shows the implementation of the methodology called “Boundary Object Function BOF” [Peña 2005], algorithm for recognition and location of rigid forms, in an embedded electronic device of the RaspBerry Pi type 3. In the method used, the electronic system acquires and condition the image, to be converted to a binary image used by the BOF algorithm. Experimental results within a manufacturing cell were performed with the implementation of the method. The result of the integration of recognition algorithms and location of rigid manufacturing parts in embedded electronic systems, shows the possibility of using them in manufacturing applications with processing high speed requirements and concurrent processes, in this way, a robot learns online and identify objects that are familiar to the performed tasks. The technological proposal presented for the invariant recognition of objects based on the BOF algorithm implemented in an electronic embedded system calculates the contour of rigid pieces very quickly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Identification with Convolutional Neural Networks 16

Network Traffic Identification with Convolutional Neural Net...

引用

16th IEEE Int Conf on Dependable, Autonom and Secure Comp/16th IEEE Int Conf on Pervas Intelligence and Comp/4th IEEE Int Conf on Big Data Intelligence and Comp/3rd IEEE Cyber Sci and Technol Congress (DASC/PiCom/DataCom/CyberSciTech)

作者： Jain, Akshit v. Rochester Inst Technol Rochester NY 14623 USA

ISBN: (纸本)9781538675182

Network traffic identification plays a major role in modern-day network monitoring systems. Most network systems identify traffic based on features such as, flow statistics, static signatures and port numbers. Identifying network traffic is essential, because plenty of information regarding a network flow can be learned by knowing the application protocol associated with it. However, the challenge for traffic classification is to identify features in the network flow data. This paper explores the issue of network traffic identification with neural network and deep learning. A convolutional neural network (CNN) with different optimization algorithms is trained to identify application protocols based on network flow data. The image and text processing hypothesis of the CNN model is extended to naturally fit to the curated dataset. Protocol labels with a high frequency distribution are easily detected by the model, and the results show that the CNN model works equally well on network flow data. A discussion on the performance of different optimization algorithms used with the CNN model is presented.

关键词： deep learning convolutional neural network network protocol classification network flow data network traffic

来源：评论

学校读者我要写书评

暂无评论

vehicle Classification Based on Deep Convolutional Neural Networks Model for Traffic Surveillance systems 15

Vehicle Classification Based on Deep Convolutional Neural Ne...

引用

15th International Computer Conference on Wavelet Active Media Technology and Information processing, ICCWAMTIP 2018

作者： Zakria Cai, Jingye Deng, Jianhua Khokhar, Muhammad Saddam Umar Aftab, Muhammad School of Information and Software Engineering University of Electronic Science and Technology of China China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China

ISBN: (纸本)9781728115351

Due to growth of vehicles in urban cities, such problems are increases traffic control systems, security and crime investigation, intelligent parking and electronic toll collection. Moreover, Logistics access management system (LMS)is also a big problem in urban cities and all the issues are challenging and demands to develop effective and efficient approach for vehicle classification. Mostly, traditional vehicle classification uses hand craft feature extraction method like SIFT, Surf, HoG etc. However, these approaches are not efficient in results. This paper presents the efficient framework for vehicle classification by using Inception-v3 model for image vector features extraction that is most advance deep learning neural network, and this model is not used before for vehicle classification. After that, different classification algorithms are implemented on the feature vector. The classification conducted on three vehicle datasets and results demonstration is helpful for researchers to choose dataset with algorithm performance. © 2018 IEEE.

关键词： vehicles

来源：评论

学校读者我要写书评

暂无评论

Segmentation of the hippocampus by transferring algorithmic knowledge for large cohort processing

引用

MEDICAL image ANALYSIS 2018年 43卷 214-228页

作者： Thyreau, Benjamin Sato, Kazunori Fukuda, Hiroshi Taki, Yasuyuki Tohoku Univ Tohoku Med Megabank Org Sendai Miyagi Japan Tohoku Univ Inst Dev Aging & Canc Sendai Miyagi Japan Tohoku Pharmaceut Univ Sendai Miyagi Japan

The hippocampus is a particularly interesting target for neuroscience research studies due to its essential role within the human brain. In large human cohort studies, bilateral hippocampal structures are frequently identified and measured to gain insight into human behaviour or genomic variability in neuropsychiatric disorders of interest. Automatic segmentation is performed using various algorithms, with FreeSurfer being a popular option. In this manuscript, we present a method to segment the bilateral hippocampus using a deep-learned appearance model. Deep convolutional neural networks (ConvNets) have shown great success in recent years, due to their ability to learn meaningful features from a mass of training data. Our method relies on the following key novelties: (i) we use a wide and variable training set coming from multiple cohorts (ii) our training labels come in part from the output of the FreeSurfer algorithm, and (iii) we include synthetic data and use a powerful data augmentation scheme. Our method proves to be robust, and it has fast inference (<30s total per subject), with trained model available online (https://***/bthyreau/hippodeep). We depict illustrative results and show extensive qualitative and quantitative cohort-wide comparisons with FreeSurfer. Our work demonstrates that deep neural network methods can easily encode, and even improve, existing anatomical knowledge, even when this knowledge exists in algorithmic form. (C) 2017 Elsevier B.v. All rights reserved.

关键词： knowledge Hippocampus Human behavior synthetic data Epistemology

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-Based Detection of Lung Abnormalities Using Single Shot Detection Convolutional Neural Networks

Ultrasound-Based Detection of Lung Abnormalities Using Singl...

引用

Int Workshop on Point-of-Care Ultrasound / Int Workshop on Bio-Imaging and visualizat for Patient-Customized Simulat / Int Workshop on Correct of Brainshift with Intra-Operat Ultrasound / Int Workshop on Computat Precis Med

作者： Kulhare, Sourabh Zheng, Xinliang Mehanian, Courosh Gregory, Cynthia Zhu, Meihua Gregory, Kenton Xie, Hua Jones, James McAndrew Wilson, Benjamin Intellectual Ventures Lab Bellevue WA 98007 USA Oregon Hlth & Sci Univ Portland OR 97239 USA

ISBN: (纸本)9783030010454;9783030010447

Ultrasound imaging can be used to identify a variety of lung pathologies, including pneumonia, pneumothorax, pleural effusion, and acute respiratory distress syndrome (ARDS). Ultrasound lung images of sufficient quality are relatively easy to acquire, but can be difficult to interpret as the relevant features are mostly non-structural and require expert interpretation. In this work, we developed a convolutional neural network (CNN) algorithm to identify five key lung features linked to pathological lung conditions: B-lines, merged B-lines, lack of lung sliding, consolidation and pleural effusion. The algorithm was trained using short ultrasound videos of in vivo swine models with carefully controlled lung conditions. Key lung features were annotated by expert radiologists and snonographers. Pneumothorax (absence of lung sliding) was detected with an Inception v3 CNN using simulated M-mode images. A single shot detection (SSD) framework was used to detect the remaining features. Our results indicate that deep learning algorithms can successfully detect lung abnormalities in ultrasound imagery. Computer-assisted ultrasound interpretation can place expert-level diagnostic accuracy in the hands of low-resource health care providers.

关键词： Lung ultrasound Deep learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

9th International Conference on Wireless and Satellite systems, WiSATS 2017

9th International Conference on Wireless and Satellite Syste...

引用

9th International Conference on Wireless and Satellitesystems, WiSATS 2017

ISBN: (纸本)9783319765709

The proceedings contain 19 papers. The special focus in this conference is on Wireless and Satellite systems. The topics include: How to Support the Machine Learning Take-Off: Challenges and Hints for Achieving Intelligent UAvs;UAvs and UAv Swarms for Civilian Applications: Communications and image processing in the SCIADRO Project;a Comparative Assessment of Embedded Energy Storage and Electric vehicle Integration in a Community virtual Power Plant;investigating the Impact of Cyber-Attack on Load Profile of Home Energy Management System;propagation Elements for the Link Budget of Broadband Satellite systems in Ka and Q/v Band;Monthly and Seasonal CFLOS Statistics for Optical GEO Feeder Links Design;Large Scale Site Diversity Experimental Campaign Between Greece and UK Using ALPHASAT: First Results;architectural Design of the Q/v Band Site Diversity Experiment Between Austria and Hungary;flexible Capacity Allocation in Smart Gateway Diversity Satellite systems Using Matching Theory;doS Attack Impact Assessment on Software Defined Networks;analysis of the Suitability of Satellite Communication for Time-Critical IoT Applications in Smart Grid and Medical Grade Networks;Making H-ARQ Suitable for a Mobile TCP Receiver over LEO Satellite Constellations;Joint Beam Hopping and Precoding in HTS systems;link Adaptation algorithms for Dual Polarization Mobile Satellite systems;Bandwidth Management Using MPLS Model for Future Mobile Wireless Networks;A Survey on Network Architectures and Applications for Nanosat and UAv Swarms;Command and Control of UAv Swarms via Satellite.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polynomial feature engineering for classification of textural images 4

Polynomial feature engineering for classification of textura...

引用

4th International Conference on Information Technology and Nanotechnology, ITNT 2018

作者： Gaidel, A.v. Samara National Research University Moskovskoe Shosse 34 Samara443086 Russia Image Processing Systems Institute Branch of the Federal Scientific Research Centre Crystallography and Photonics Russian Academy of Sciences Molodogvardeyskaya str. 151 Samara443001 Russia

I consider a number of methods of automatic quadratic features adjustment for digital textural images of biological tissues in order to improve the quality of classification. The proposed approaches are based on optimization procedures that use various quality criteria of a feature space as target functions. I investigate the methods based on random search, genetic algorithm, simulation of annealing, as well as the original hybrid algorithm. I presented results of experimental studies of the proposed algorithms on sets of real X-ray images of bone tissue and the lung CT images. We show that the hybrid algorithm provides more stable results regardless of the chosen quality criterion of the feature space, which is expressed in decreasing of the average percentage of incorrectly recognized images in comparison with the use of the specific optimization methods individually. © 2018 Institute of Physics Publishing. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Compiling algorithms for Heterogeneous systems

引用

Synthesis Lectures on Computer Architecture 2018年第1期13卷 1-105页

作者： Bell, Steven Pu, Jing Hegarty, James Horowitz, Mark Stanford University United States Google United States Oculus United States

ISBN: (纸本)9781681730011

Most emerging applications in imaging and machine learning must perform immense amounts of computation while holding to strict limits on energy and power. To meet these goals, architects are building increasingly specialized compute engines tailored for these specific tasks. The resulting computer systems are heterogeneous, containing multiple processing cores with wildly different execution models. Unfortunately, the cost of producing this specialized hardware - and the software to control it - is astronomical. Moreover, the task of porting algorithms to these heterogeneous machines typically requires that the algorithm be partitioned across the machine and rewritten for each specific architecture, which is time consuming and prone to error. Over the last several years, the authors have approached this problem using domain-specific languages (DSLs): high-level programming languages customized for specific domains, such as database manipulation, machine learning, or image processing. By giving up generality, these languages are able to provide high-level abstractions to the developer while producing high-performance output. The purpose of this book is to spur the adoption and the creation of domain-specific languages, especially for the task of creating hardware designs. In the first chapter, a short historical journey explains the forces driving computer architecture today. Chapter 2 describes the various methods for producing designs for accelerators, outlining the push for more abstraction and the tools that enable designers to work at a higher conceptual level. From there, Chapter 3 provides a brief introduction to image processing algorithms and hardware design patterns for implementing them. Chapters 4 and 5 describe and compare Darkroom and Halide, two domain-specific languages created for image processing that produce high-performance designs for both FPGAs and CPUs from the same source code, enabling rapid design cycles and quick porting of algorithms. The

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

DEEPAGENT: AN ALGORITHM INTEGRATION APPROACH FOR PERSON RE-IDENTIFICATION

DEEPAGENT: AN ALGORITHM INTEGRATION APPROACH FOR PERSON RE-I...

引用

IEEE International Conference on image processing

作者： Fulong Jiao Bir Bhanu Center for Research in Intelligent Systems University of California Riverside Riverside CA USA

Person re-identification (RE-ID) has played a significant role in the fields of image processing and computer vision because of its potential value in practical applications. Researchers are striving to design new algorithms to improve the performance of RE-ID but ignore the advantages of existing approaches. In this paper, motivated by deep reinforcement learning, we propose a Deep Agent which can integrate existing algorithms and enable them to complement each other. Two Deep Agents are designed to integrate algorithms for data augmentation and feature extraction parts separately for RE-ID. Experiment results demonstrate that the integrated algorithms can achieve a better accuracy than using each one of them alone.

关键词： Probes Feature extraction Training Cameras Learning (artificial intelligence) Neural networks Testing

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：