检索结果-内蒙古大学图书馆

International Workshop/Symposium on Distributed Simulation and Real-Time Applications (DS-RT)

作者： Agnieszka Chodorek Robert R. Chodorek Krzysztof Wajda Faculty of Electrical Engineering Automatic Control and Computer Science Kielce University of Technology Kielce Poland Department of Telecommunications The AGH University of Science and Technology Kraków Poland

In this paper we propose a flying IoT system designed to monitor parking lot. The system is composed of a flying mobile station and a terrestrial station. The mobile station consists of visual monitoring camera associated with air quality monitoring sensors, mounted on a Turnigy SK450 quad copter controlled with Pixhawk autopilot hardware. Data gathered from the monitoring system are transmitted to an IoT broker running on a Raspberry Pi 3+ microcontroller, also mounted on a drone, that aggregates data into a common flow and retransmits them to the terrestrial station. The transmission system was build according to WebRTC architecture. In order to assure separation of the production network (for transmission of application data) and the management network (for management and control purposes), two different transmission channels are used: one for the WebRTC transmission and the other for controlling the drone. The paper includes a description of the system and the results of field trials carried out on the parking lot of the AGH University of technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The hierarchical learning algorithm for deep neural networks 27

The hierarchical learning algorithm for deep neural networks

引用

27th International Workshop on Concurrency, Specification and Programming, CS and P 2018

作者： Placzek, Stanislaw Placzek, Aleksander University of Business Wroclaw Poland Silesian University of Technology Faculty of Automatic Control Electronic and Computer Science WASKO Gliwice Poland

In the article, the emphasis is put on the modern artificial neural network (ANN) structure, which in the literature is known as a deep neural network. A network includes more than one hidden layer and comprises many standard modules with ReLu nonlinear activation function. A learning algorithm includes two standard steps, forward and backward, and its effectiveness depends on the way the learning error is transported back through all the layers to the first layer. Taking into account all the dimensionalities of matrixes and the nonlinear characteristics of ReLu activation function, the problem is very challenging. In practice tasks, a neural networks internal layer matrixes with ReLu activations function, include a lot of null value of weight coefficients. This phenomenon has a negative impact on the effectiveness of the learning algorithm's convergence. Analyzing and describing an ANN structure, one usually finds that the first parameter is the number of ANNs layers "L". By implementing the hierarchical structure to the learning algorithm, an ANN structure is divided into sub-networks. Every sub-network is responsible for finding the optimal value of its weight coefficients using a local target function to minimize the learning error. The second coordination level of the learning algorithm is responsible for coordinating the local solutions and finding the minimum of the global target function. In each iteration the coordinator has to send coordination parameters into the first level of subnetworks. By using the input and the teaching vectors, the local procedures are working and finding their weight coefficients. At the same step the feedback error is calculated and sent to the coordinator. The process is being repeated until the minimum of all the target functions is achieved. © Copyright 2018 for the individual papers by the papers' authors.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

On noise-to-state stability of stochastic discrete-time systems via finite-step Lyapunov functions

On noise-to-state stability of stochastic discrete-time syst...

引用

IEEE Annual Conference on Decision and control

作者： Navid Noroozi Roxanne Jackson Daniel E. Quevedo Fabian R. Wirth Rolf Findeisen Laboratory for Systems Theory and Automatic Control Ottovon-Guericke University Magdeburg Magdeburg Germany Faculty of Computer Science and Mathematics University of Passau Passau Germany Faculty of Computer Science Electrical Engineering and Mathematics University of Paderborn Paderborn Germany

ISBN: (数字)9781728113982

ISBN: (纸本)9781728113999

In this paper, we introduce a notion of so-called finite-step simulation functions for discrete-time control systems. In contrast to the existing notions of simulation functions, a finite-step simulation function does not need decay at each time step but after some finite numbers of steps. We show that the existence of such a function guarantees that the mismatch between output trajectories of the concrete and abstract systems lies within an appropriate bound. Using this relaxation, we develop a new type of small-gain conditions which are less conservative than those previously used for compositional construction of approximate abstractions of interconnected control systems. In particular, using finite-step simulation functions, it is possible to construct approximate abstractions, where stabilizability of each subsystem is not necessarily required. The effectiveness of our results is verified by an illustrative example.

关键词： Stability analysis Lyapunov methods Asymptotic stability Stochastic systems Nonlinear systems Covariance matrices Discrete-time systems

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Heterogeneity Investigation: Multiple k-Means Clustering Approach

Breast Cancer Heterogeneity Investigation: Multiple k-Means ...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Joanna Tobiasz Christos Hatzis Joanna Polanska Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Medicine Yale School of Medicine New Haven USA

ISBN: (纸本)9781728146188

Breast cancer, a frequent cause of mortality among women, is a heterogeneous disease with multiple subtypes, which identification has a great impact on the prognosis and the choice of therapy. Various attempts are being made worldwide to classify breast tumors and to discover differences between subtypes. The purpose of this study is to divide a diverse group of patients with a multiple k-means clustering approach in order to investigate the complex structure of the dataset. Primary tumor samples collected from 859 females within The Cancer Genome Atlas Breast Invasive Carcinoma project served as the material for an RNA-Seq experiment. Expression levels measured with the RNA-Seq procedure were downloaded from the Genomic Data Commons Data Portal and used for this study. The proposed multilevel clustering algorithm is based on the idea of treating each resulting cluster as an input for a new k-means clustering as long as a given cluster is not too small or integrated. Each clustering is preceded with feature filtration and selection, which are based on the Gaussian Mixture Model decomposition of gene expression level amplitude or variance, respectively. The gap statistic is used for the selection of the optimal number of clusters as well as for deciding whether a group should be divided. Results were compared to the subtype labels either obtained from the PAM50 classifier or based on the HER2 and hormone-receptor markers. The performed multilevel clustering produced a large number of small clusters. During the first division five clusters were obtained, three of them containing almost only hormone-receptor positive (HR+) tumors. One cluster consisted of similar numbers of HER2-enriched, triple-negative breast cancer (TNBC), and HR+ cases. Obtained results confirm a great heterogeneity of breast cancer. However, they also suggest that commonly used breast tumor classification corresponding to the receptor markers may not entirely reflect the complexity of subtypes of

关键词： Breast cancer Clustering algorithms Tumors Filtration Gene expression Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Multi-person remote heart-rate measurement from human faces - a CNN based approach

Multi-person remote heart-rate measurement from human faces ...

引用

IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin)

作者： Thomas Pursche Marcel Walz Roland Clauß Robert Roth Bernd Tibken Reinhard Möller School of Electrical Information and Media Engineering Automatic Control University of Wuppertal Wuppertal Germany Faculty of Electrical Information and Media Engineering Automatic Control University of Wuppertal Wuppertal Germany Faculty of Electrical Information and Media Engineering Automation/Computer Science University of Wuppertal Wuppertal Germany

The conventional heart rate measurement techniques using electrocardiogram, wrist belts and so on, are attached with some disadvantages like discomfort, irritation of the skin and even more. From this starting point various video based heart rate measurement techniques were developed in the last years. All of these techniques use video data of the human faces to extract information to estimate the heart rate of the person in front of the camera. Most of them work with the detection of minimal changes in the color spectrum of the recorded video data. With these extracted information and multiple concluding steps, they are able to estimate the heart rate of the person sitting in front of the camera. All of these approaches have some big disadvantages, they are only able to measure the heart rate of one person - and in a small number of cases up to three persons. So the main objective of this work is to adapt and enhance existing research approaches of processing visual biological signals. The focus is set on the design and deployment of a new system, which is able to process visual data as well as detect and localize human faces by using artificial neural networks and calculate each individuals heart rate from the processed data's information. For the first time in this research area, different scenarios with more than three observed participants are being analyzed to calculate the heart rate for each of them separately. It will be shown that by using the applied technical architecture and technologies, it is possible to deploy a comparable and qualitatively competitive system. In addition, the implemented system proves the feasibility of processing various faces' signals and calculating the respective heart rates simultaneously within an acceptable range of tolerance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Colour histogram analysis for skin lesions discrimination 19

Colour histogram analysis for skin lesions discrimination

引用

19th International Multidisciplinary Scientific Geoconference, SGEM 2019

作者： Damian, Felicia Anisoara Moldovanu, Simona Moraru, Luminita Faculty of Sciences and Environment Dunarea de Jos University of Galati Galati Romania Department of Computer Science and Information Technology Technical College Dumitru Motoc Galati Galati Romania Faculty of Automatic Control Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania Modelling and Simulation Laboratory Dunarea de Jos University of Galati Galati Romania

One of the risk factors in skin cancer is unprotected exposure to UV radiation. Melanoma is the deadliest form of skin cancer but also curable if it is diagnosed in the early stages. This study uses a histogram analysis technique to investigate and classify two common skin lesions, nevi and melanoma. The colour feature investigated is the optimal threshold values in RGB space. Also, a boundary limit of the skin lesions is performed using a colour histogram analysis and the optimal threshold determination. A statistical analysis of the relevant threshold values for R, G and B histograms to establish a sound colour separation between benign and malignant lesions is performed. Monochromatic channel threshold values are clustered using K-means and the validity of clustering is assessed by silhouette method. The proposed method technique is evaluated using 120 colour digital images (60 melanomas and 60 nevi) from the Digital Archive of the Department of Dermatology of the University Medical Center in Groningen (UMCG)1. The reported results suggest red as the lesion representative colour in dermoscopic images. The pixel values for red channel are strongly related to the skin lesion type. © SGEM 2019.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Using grey-scale hit-or-miss transform for detection of isolated foreground pixels in cerebral rmn datasets 19

Using grey-scale hit-or-miss transform for detection of isol...

引用

19th International Multidisciplinary Scientific Geoconference, SGEM 2019

作者： Pana, Lenuta Moldovanu, Simona Moraru, Luminita Faculty of Sciences and Environment University Dunarea de Jos of Galati Galati Romania Department of Computer Science and Information Technology Technical College Dumitru Motoc Galati Galati Romania Faculty of Automatic Control Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati Galati Romania Modelling and Simulation Laboratory University Dunarea de Jos of Galati Galati Romania

MRI images contain a lot of subtle information related to various lesions which are difficult to be picked up by radiologists. computer aided diagnosis CAD is a valuable tool to improve the ability of an average radiologist to diagnose the subtle lesions. This study uses the isolated foreground pixels in MRI images as a feature able to discern a stroke patient by a healthy one. Brain MRI image was divided into eight equal sectors. The isolated foreground pixels (i.e. pixels satisfying a neighborhood configuration that corresponds to an isolated foreground pixel) were extracted using hit-or-miss and skeleton transformations. We have tested the proposed algorithms using two cerebral image datasets (healthy and acute stroke patients). The mean SD values of isolated foreground pixels for stroke patients systematically exceed the corresponding values for healthy patients. The higher numbers of isolated foreground pixel determined using hit-or-miss transform indicate this method as a promising approach for a simple and quick evaluation of stroke. © SGEM 2019.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Trajectory control of an Autonomous Systemdedicated to Assisted Living

Trajectory Control of an Autonomous Systemdedicated to Assis...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Max Nicolae Stefan Mocanu Mihai Craciunescu Radu Dobrescu Faculty of Automatic Control and Computer Science UPB

In this paper a method of controlling a wheelchair using the video stream from two cameras is proposed. The cameras are placed on the side of the wheelchair having as main purpose to detect the edge between the floor and the wall. The images obtained are processed, thus obtaining an inclination angular error and a lateral errorfrom the desired trajectory, which is considered at the middle of the distance between the two lateral references. With the combined information from the camera and from the sensors conveniently placed on the system, the navigation inside a building with corridors delimited either by walls, by lines or by transitions is achieved.

关键词： Wheelchairs Sensors Cameras Trajectory Navigation Image edge detection computer architecture

来源：评论

学校读者我要写书评

暂无评论

Deep learning based switching filter for impulsive noise removal in color images

arXiv

引用

arXiv 2019年

作者： Radlak, Krystian Malinski, Lukasz Smolka, Bogdan Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44100 Faculty of Materials Engineering and Metallurgy Silesian University of Technology Krasinskiego 8 Katowice40-019

Noise reduction is one the most important and still active research topic in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we can observe a substantial increase of interest in the application of deep learning algorithms in many computer vision problems due to its impressive capability of automatic feature extraction and classification. These methods have been also successfully applied in image denoising, significantly improving the performance, but most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering design intended for impulsive noise removal using deep learning. In the proposed method, the impulses are identified using a novel deep neural network architecture and noisy pixels are restored using the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in digital color images. Copyright © 2019, The Authors. 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

Intact industrial internet of things communication solution

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2018年第3期80卷 17-30页

作者： Trancǎ, Dumitru-Cristian Buzilǎ, Eugen Rosner, Daniel Pǎtru, George Cristian Rughiniş, Rãzvan Victor Faculty of Automatic Control and Computer Science University POLITEHNICA of Bucharest Romania

In the past decades, the internet revolution has expanded in numerous application areas and has redefined both B2C (business-to-consumer) and B2B (business-to-business) industries, with the industrial environment adapting to the fast-changing technologies. IIoT (Industrial Internet of Things) based solutions are increasingly employed to address several limitations of previous generations of technologies, with multiple applications in areas such as energy, agriculture, industrial facilities. One specific area of high impact for IIoT is communication equipment interconnection in industrial scenarios. Most industries rely on wired interconnections - with several benefits, but also specific limitations and costs. This article proposes a wireless communication solution for this specific area, based on the LoRaWAN protocol, complete with a solution for centralizing information and offering a high-level overview of active infrastructure. We proposed a general module, that can be attached to any industrial equipment, collecting and transferring data through LoRaWAN protocol, introducing new opportunities but also new risks related to data security and integrity. © 2018 Politechnica University of *** Rights Reserved.

关键词： Internet of things

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：