By Topic

Neural Network Applications in Electrical Engineering (NEUREL), 2010 10th Symposium on

Date 23-25 Sept. 2010

Filter Results

Displaying Results 1 - 25 of 86
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (495 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (36 KB)  
    Freely Available from IEEE
  • Foreword

    Page(s): 1 - 3
    Save to Project icon | Request Permissions | PDF file iconPDF (1528 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (36 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): 1 - 4
    Save to Project icon | Request Permissions | PDF file iconPDF (52 KB)  
    Freely Available from IEEE
  • Tutorial lecture 1: Nucleotide genomic signal methodology

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (14 KB)  
    Freely Available from IEEE
  • Nucleotide genomic signal methodology

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (99 KB)  

    The nucleotide genomic signal (NuGS) methodology is based on the conversion of symbolic nucleotide sequences into digital genomic signals. There have been several attempts to represent nucleotide sequences as digital signals, most using some specific property of the nitrogeneous bases, e.g., the electronion interaction (EII) potential. Unfortunately, the resulting representation tends to be biased, being adequate primarily for the study of those phenomena in which the chosen property plays a key role, but less for others. The representation presented and discussed in this tutorial is unbiased, i.e., it is adequate for a large range of problems related to nucleotide sequence analysis, having been used for both the analysis of global features of genomic sequences, maintained over distances of 106-108 base pairs, as well as for the local study of nucleotide sequences. The large scale approach reveals hidden symmetries and regularities of current and ancestral nucleotide sequences, while the local approach can be used in the analysis of pathogen variability, important in the context of the development of pathogen resistance to treatment. This aspect is especially important for the fast diagnosis and early assessment of drug efficiency, allowing a simple and systematic use of the recent advances in molecular medicine to help clinical decisions. The striking regularities of the digital genomic signals reveal surprising restrictions in the distribution of nucleotides and pairs of nucleotides along DNA sequences, in both prokaryotes and eukaryotes. In what concerns its statistical structural symmetry, a chromosome appears to be more than a plain text, as it also satisfies restrictions evoking the rhythm and rhyme in poems. These regularities can be used to "predict" individual nucleotides in nucleotide sequences, by using a methodology similar to time series prediction and allow to analyze the potential for molecular scale self-repair in processes such- - as replication, transcription or crossover. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Special session 1: Data processing and neural networks for rehabilitation of sensory-motor systems

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (15 KB)  
    Freely Available from IEEE
  • Classification of walking patterns in Parkinson's disease patients based on inertial sensor data

    Page(s): 3 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (311 KB) |  | HTML iconHTML  

    The gait disturbances in Parkinson's disease (PD) patients occur occasionally and intermittently, appearing in a random, inexplicable manner. These disturbances include festinations, shuffling, and complete freezing of gait (FOG). Alternation of walking pattern decreases the quality of life and may result in falls. In order to recognize disturbances during walking in PD patients, we recorded gait kinematics with wireless inertial measurement system and designed an algorithm for automatic recognition and classification of walking patterns. The algorithm combines a perceptron neural network with simple signal processing and rule-based classification. In parallel, gait was recorded with video camera. Medical experts identified FOG episodes from videos and their results were used for comparison and validation of this method. The summary result shows that the error in recognition and classification of walking patterns is up to 16%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mapping of sensory representation of walking and EMG of prime joint movers: Control of functional electrical stimulation

    Page(s): 7 - 10
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (225 KB) |  | HTML iconHTML  

    This paper presents machine learning (ML) techniques for development of a control scheme to be used in functional electrical stimulation (FES) of hemiplegic walking. The goal is to make an electrical stimulation pattern by mapping the sensors signals acquired during walking (input) to activities of muscles (output) acting around knee and ankle joints. Two machine learning techniques with ability of time series prediction were analyzed: a nonlinear autoregressive neural network (NARX) and an adaptive-network-based fuzzy inference system (ANFIS). Networks were compared in terms of minimum number of sensors needed for accurate prediction, timing errors, false detections and generalization ability. ANFIS network predicted more accurately, while NARX network needed less sensors, had less false detections and better generalization. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification of muscle twitch response using ANN: Application in multi-pad electrode optimization

    Page(s): 11 - 13
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (618 KB) |  | HTML iconHTML  

    In this paper we present a method for optimization of spatial selectivity of multi-pad electrode during transcutaneous Functional Electrical Stimulation (FES). The presented method is based on measurement of individual muscle twitches using Micro-Electro-Mechanical Systems (MEMS) accelerometers positioned on hand, while stimulating with low frequency electrical stimulation via pads within multi-pad electrode. When elicited, wrist or fingers flexion/extension produce different, characteristic wave shapes of acceleration, by using trained Artificial Neural Network (ANN) we can detect these characteristic signals and detect correlation of each pad and activated muscle beneath. Results presented in this paper show high degree of accurate classification of the elicited movement in inter-subject testing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Blank page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (11 KB)  
    Freely Available from IEEE
  • An EMG system for studying motor control strategies and fatigue

    Page(s): 15 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (380 KB) |  | HTML iconHTML  

    We present a system for polymyographic analysis which addresses detection of muscle fatigue and strategies assumed by the central nervous system to deal with it. The system consists of EMG amplifiers, force transducers, A/D converter, portable computer and software running in the LabView environment that allows real-time and detailed offline processing of EMG signals in time and frequency domains. We demonstrate the features of the system by using the example of analyzing the strategy to generate 80% percent of the maximum force for prolonged period of time. Force sensor was used to detect muscle fatigue (fall of the force bellow the selected threshold), and EMG recordings were used for the analysis which of the quantitative measures of EMG is correlated with this. We tested the following four methods of EMG measures: 1) median frequency, 2) short-time mean frequency, 3) mean frequency of scalogram and 4) fractal dimension. We show that the system is capable of providing reproducible results and could be used for diagnostics and basic research in motor control. The analysis shows that the median frequency used often is not the best predictor of fatigues, and the measure needs to be selected based on the relative activity of the muscle compared to its maximal activity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Independent Component Analysis (ICA) methods for neonatal EEG artifact extraction: Sensitivity to variation of artifact properties

    Page(s): 19 - 21
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (158 KB) |  | HTML iconHTML  

    Independent Component Analysis (ICA) is becoming an accepted technique for artifact removal. Nevertheless, there is no consensus about appropriate methods for different applications. This study presents a comparison of common ICA methods: RobustICA, SOBI, JADE, and BSS-CCA, for extraction of ECG artifacts from EEG signal. Algorithms were applied to the data created by superimposing artifact free real-life neonatal EEG and synthetic ECG. Their sensitivity to variation of noise property was compared: we examined variability of Spearman correlation coefficients (SCC) for various Heart Rates (HR) in each of ICA methods. Results show that SOBI and BSS-CCA methods were less sensitive than RobustICA and JADE to artifact alterations (mean SCCs were 0.85 and 0.85 compared to 0.80 and 0.73, respectively) being quite successful in source signal extraction. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Blank page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (11 KB)  
    Freely Available from IEEE
  • Action representation for Wii bowling: Classification

    Page(s): 23 - 26
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (769 KB) |  | HTML iconHTML  

    We present the method for classifying kinematical data required for control of a rehabilitation robot for upper extremities. The classification to two cases (success, no-success) was analyzed by two methods: Bayes estimation and artificial neural network (ANN). The results are presented for an example being envisioned for rehabilitation: playing the Wii bowling with the specially constructed pantograph. The pantograph transforms the pointing-like movement into the appropriate motion of the WiiMote (hand held controller for Wii game); thereby, the user is playing Wii bowling with greatly simplified movement of the hand (range and speed) compared with normal play. The data analysis reduced the information to two key parameters for distinction of success vs. no-success: 1) maximal acceleration of WiiMote and 2) the acceleration of the WiiMote at the ball release time. The Bayes estimation resulted with 82% of correct classification, while the ANN reached the level of 90%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A closed-loop neural prosthesis for vestibular disorders

    Page(s): 27 - 30
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (379 KB) |  | HTML iconHTML  

    Vestibular disorders can cause severe problems including nausea, inability to concentrate, and visual deficits. The CLONS project is developing a closed-loop sensory neural prosthesis to alleviate these symptoms. Conceptually, the prosthesis restores vestibular information by stimulating the semicircular canals according to measurements from inertial sensors rigidly affixed to the user. Here we present a project overview and brief update of our progress in animal models and selected human volunteers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Session 2: Neural networks in power engineering

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (14 KB)  
    Freely Available from IEEE
  • An enhanced ANN wind power forecast model based on a fuzzy representation of wind direction

    Page(s): 31 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (966 KB) |  | HTML iconHTML  

    Due to high penetration of wind generation in modern power systems, the influence of wind power production over the efficient operation of the power system is increasingly complex. Hence, an increasing interest is shown by different actors in the wind energy market to develop and enhance existent forecasting methods for power generated by wind farms. This paper presents the experience with wind power prediction of a small size wind power producer in Romania. The model was designed using components from Artificial Neural Networks and Fuzzy System theory. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A class of neural adaptive FIR filters for complex-valued load prediction

    Page(s): 37 - 39
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (188 KB) |  | HTML iconHTML  

    Load prediction is a necessity in a deregulated electrical energy sector. It is important financially and technically. In order to cope with nonlinear and non stationary character of a load signal, an efficient adaptive predictor should be employed. Also, power utilities manage load information as a complex-valued signal. To this cause, performance of a class of complex-valued gradient descent (GD) neural adaptive finite impulse response (FIR) filters is analyzed. It is shown that fully complex nonlinear GD algorithms have the best performance in a load prediction task. To support the analysis, experiments are carried out on the test load signal, metered on a medium voltage feeder. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Blank page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (11 KB)  
    Freely Available from IEEE
  • Design of artificial neural network models for the prediction of the Hellenic energy consumption

    Page(s): 41 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (140 KB) |  | HTML iconHTML  

    Energy consumption predictions are essential and are required in the studies of capacity expansion, energy supply strategy, capital investment, revenue analysis and market research management. In the recent years artificial neural networks (ANN) have attracted much attention and many interesting ANN applications have been reported in power system areas, due to their computational speed, their ability to handle complex non-linear functions, robustness and great efficiency, even in cases where full information for the studied problem is absent. In this paper, several ANN models were addressed to identify the future energy consumption. Each model has been constructed using different structures, learning algorithms and transfer functions in order the best generalizing ability to be achieved. Actual input and output data were used in the training, validation and testing process. A comparison among the developed neural network models was performed in order the most suitable model to be selected. Finally the selected ANN model has been used for the prediction of the Hellenic energy consumption in the years ahead. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Early fault detection and isolation in coal mills based on self-organizing maps

    Page(s): 45 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (428 KB) |  | HTML iconHTML  

    Classical approaches to the fault detection and isolation usually require extensive plant-modeling and statistical analysis of the measured signals and their residuals versus the developed model. In this paper, alternative simple model-free approach is proposed. Real-time data are preprocessed and self-organizing map is trained and used for the reliable isolation of the most frequent mill fault - output fuel-mixture drop due to the coal-stuck in the input bunker. Proposed approach is successfully verified on the real-time data-sets from the coal mills in thermal power plant “Nikola Tesla B”, Serbia. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Artificial neural networks broken rotor bars induction motor fault detection

    Page(s): 49 - 53
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (370 KB) |  | HTML iconHTML  

    Paper deals with application of online rotor broken bar fault detection via artificial neural networks. Fault can be detected by monitoring abnormalities of the spectrum amplitudes at certain frequencies in the motor current spectrum. These discriminative features are used for training of feed-forward backpropagation artificial neural network. Trained network is capable to successfully classify induction motor rotor condition. Results are presented in tables and figures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Blank page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (11 KB)  
    Freely Available from IEEE