By Topic

2017 IEEE 15th International Symposium on Applied Machine Intelligence and Informatics (SAMI)

26-28 Jan. 2017

Filter Results

Displaying Results 1 - 25 of 94
  • Author's index

    Publication Year: 2017, Page(s): 513
    Request permission for commercial reuse | PDF file iconPDF (62 KB)
    Freely Available from IEEE
  • Committees

    Publication Year: 2017, Page(s):4 - 5
    Request permission for commercial reuse | PDF file iconPDF (41 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2017, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (16 KB)
    Freely Available from IEEE
  • [Front cover]

    Publication Year: 2017, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (26 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2017, Page(s):6 - 10
    Request permission for commercial reuse | PDF file iconPDF (72 KB)
    Freely Available from IEEE
  • Foreword

    Publication Year: 2017, Page(s): 3
    Request permission for commercial reuse | PDF file iconPDF (29 KB)
    Freely Available from IEEE
  • Relaxed design conditions for Takagi-Sugeno unknown input observers

    Publication Year: 2017, Page(s):000061 - 000066
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (118 KB) | HTML iconHTML

    New design conditions for the Takagi-Sugeno fuzzy model based unknown input observer, is presented in the paper. By the proposed methods, the design problem is parameterized in terms of linear matrix inequalities in relaxed and enhanced structures. Related to the state decoupling and reconstruction in the given class nonlinear systems, the design steps are revealed in the example for attenuation o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The analysis of participatory computing in dynamic web environments

    Publication Year: 2017, Page(s):000067 - 000072
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (414 KB) | HTML iconHTML

    Participatory Computing is the concept of a group of computers contributing processing power and storage to form a larger, distributed computing system. Past experiences show that a system of this type can reach performance rivaling the fastest supercomputers in the world. In theory, any connected modern PC could participate and yet the prevalence of these systems is not comparable to their potent... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of small scale turbojet engine with variable exhaust nozzle

    Publication Year: 2017, Page(s):000073 - 000078
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (806 KB) | HTML iconHTML

    The main goal of the present paper is to identify the coefficients of the linear state space representation of a small scale turbojet engine with variable area convergent exhaust nozzle through measurements on a real gas turbine. The thermodynamics based mathematical model has been established previously; the further steps are to conduct measurements on the laboratory equipment at the authors' Dep... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Building environment analysis based on clustering methods from sensor data on top of the Hadoop platform

    Publication Year: 2017, Page(s):000079 - 000082
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (410 KB)

    Presented paper describes the use of clustering methods in building environment analysis task. The presented approach is based on modeling of the sensor data containing information about humidity and temperature. Such models are then used to describe the level of the comfort of particular environment. K-means clustering algorithm was used to create those models. The paper then presents and describ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Offline signature identification via HOG features and artificial neural networks

    Publication Year: 2017, Page(s):000083 - 000086
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (319 KB) | HTML iconHTML

    In this work, an offline signature identification system based on Histogram of Oriented Gradients (HOG) vector features is designed. Handwritten signature images are collected at Yildiz Technical University, from 15 people, 40 samples from each. Before the HOG feature extraction, size fixing and noise reduction processes are applied to all signature images. HOG features are extracted from the nois... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Anti-spoofing in face recognition with liveness detection using pupil tracking

    Publication Year: 2017, Page(s):000087 - 000092
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1050 KB) | HTML iconHTML

    In this work, we focused on liveness detection for facial recognition system's spoofing via fake face movement. We have developed a pupil direction observing system for anti-spoofing in face recognition systems using a basic hardware equipment. Firstly, eye area is being extracted from real time camera by using Haar-Cascade Classifier with specially trained classifier for eye region detection. Fea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach to support education of data mining algorithms

    Publication Year: 2017, Page(s):000093 - 000098
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (724 KB)

    The aim of this article is to describe the design, implementation and evaluation of the educational application to support learning of data mining algorithms. The role of the application is to help students to better understand the algorithms such as Naive Bayes classifier, decision trees and association rules. The application also includes a test area that allows students to generate and solve di... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Role of information content in multipurpose virtual engineering space

    Publication Year: 2017, Page(s):000099 - 000104
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (239 KB) | HTML iconHTML

    This paper is about extended application of virtual engineering principles, methodologies, and systems as a possible answer to urgent need for integrated industrial, research, and higher educational programs and processes. One of the motivations is the changed world of engineering which requires quick utilization of new findings as new context. At the same time, development of virtual engineering ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementing English speech interface to Jaguar robot for SWAT training

    Publication Year: 2017, Page(s):000105 - 000110
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (623 KB) | HTML iconHTML

    This paper describes the development of a specialized application for voice command recognition for the Jaguar V4 robot in conjunction with the Starkville, MS, USA Special Weapons and Tactics (SWAT) team during training. This training took place at The Center for Advanced Vehicular Systems (CAVS), which provides a specialized environment for police SWAT training. This reconfigurable space, setup d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of using the LBC format for compressing medical images

    Publication Year: 2017, Page(s):000111 - 000116
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (278 KB) | HTML iconHTML

    The article performs a comparative study between the image compression technique Local Binary Compressed format (LBC) proposed by the authors [11] and the standard image compression techniques used today (BMP, JPEG, PNG and GIF). The study is carried out for large medical images that need to be stored for longer periods of time. In the study, the most common types of medical images used are: X-ray... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantics as the basis of truly cognitive computing

    Publication Year: 2017, Page(s):000011 - 000014
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (403 KB)

    At the 2014 AAAI, Pat Langley, one of the founders of machine learning and, recently, of its detractors, publicly lamented the current abandonment of the "big issues" in AI. Indeed, from emulating human intelligence in the process of learning more about it, AI is often confused with non-intelligent emulation of human intelligent activities. Both in the States and Europe, cognitive computing has em... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applications of remote controlled robotics in the intelligent space

    Publication Year: 2017, Page(s):000117 - 000122
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (397 KB) | HTML iconHTML

    As the concept of the Internet of Things (IoT) permeates the industry and our lives it becomes more and more advantageous to use its emerging services and capabilities. In this paper we explore the possibility of combining the data and services provided by the emerging IoT with remotely controlled robots using a concept of the so-called Intelligent Space (IS). We also provide an overview of infras... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evaluation of biometrie identification approach on low-frequency eye tracking data

    Publication Year: 2017, Page(s):000123 - 000128
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (324 KB) | HTML iconHTML

    During the last decade many information systems started applying various biometric identification modules. This type of identification is secure and provides a real possibility to protect a system from an unapproved access. The paper presents a newly developed biometric identification approach that is suitable for many biometric signals. This work describes an evaluation of the approach on low-fre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Frequency spectrum allocation in an agent-based model of real-time spectrum secondary market

    Publication Year: 2017, Page(s):000129 - 000136
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (480 KB) | HTML iconHTML

    A significant increase in wireless communication has been observed in the last decade. Traditional fixed spectrum allocation presents limitations to better spectrum utilization. Real-time secondary spectrum market seems to be appropriate approach to eliminating the problem of spectrum scarcity. Economic aspects of the new approach are still only partially investigated. Besides the conventional who... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evaluation of biometrie identification approach on low-frequency ECG signal

    Publication Year: 2017, Page(s):000137 - 000142
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (297 KB) | HTML iconHTML

    In order to provide high security level, different identification and verification methods are being used in information systems. A development of the new highly accurate methods are of great interest nowadays. Those methods that analyze biometric signals are becoming more widespread as biometric data can provide hardly forged information about a person. This paper presents the developed biometric... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Static person detection and localization with estimation of person's breathing rate using single multistatic UWB radar

    Publication Year: 2017, Page(s):000143 - 000148
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1025 KB) | HTML iconHTML

    In the past period, great efforts have been made to develop the methods for the detection of human beings based on a monitoring their respiratory motion. For that purpose, ultra-wideband sensors (radars) operating in the frequency band DC-5GHz can be used with advantage. The basic principle of respiratory motion detection consists in the identification of sensor signal components possessing a sign... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vocabulary matching for information extraction language

    Publication Year: 2017, Page(s):000149 - 000152
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (186 KB) | HTML iconHTML

    In the previous paper, we have described specification of the domain-specific declarative language for natural language processing and information extraction tasks. This paper extends the previous specification of the language with the extensions, which allow to specify sequences of words and corresponding meta-data annotations in the vocabulary. The paper describes syntax extensions and internal ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simple understandable analysis of medical data to support the diagnostic process

    Publication Year: 2017, Page(s):000153 - 000158
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (341 KB) | HTML iconHTML

    Medical diagnostic is a complex process consisting of many input variables, which the general practitioner (GP) or specialist should take into account before confirm the expected diagnosis. In the case of electronic records, they have an opportunity to support this process within simple understandable results of the correctly applied suitable methods from machine learning or statistics. We used a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Artificial neural network based IDS

    Publication Year: 2017, Page(s):000159 - 000164
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (693 KB) | HTML iconHTML

    The Network Intrusion Detection Systems (NIDS) are either signature based or anomaly based. In this paper presented NIDS system belongs to anomaly based Neural Network Intrusion Detection System (NNIDS). The proposed NNIDS is able to successfully recognize learned malicious activities in a network environment. It was tested for the SYN flood attack, UDP flood attack, nMap scanning attack, and also... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.