Classification of Mental Task for Brain Computer Interface Using Artificial Neural Network
|
|
- Evelyn King
- 5 years ago
- Views:
Transcription
1 Classification of Mental Task for Brain Computer Interface Using Artificial Neural Network Mohammad Naushad 1, Mohammad Waseem Khanooni 2, Nicky Ballani 3 1,2,3 Department of Electronics and Telecommunication Engineering,S. B Jain Institute of Technology Management & Research, Katol Road, Nagpur, India Abstract: This paper deals with classification of mental task using PSD and ANN. In this work feature is extracted by using different PSD methods such as periodogram method, Welch method etc. After extracting the features signal is given to Neural Network for classification. In this work Back Propagation Algorithm has been used to train the Neural Network. The two task left hand and right hand real movement and left hand and right hand imaginary movement have been classified, and the comparison between real and imaginary movement has been discussed. The EEG signal is recorded using B-Alert system and also EEG data have been taken from BCI data base (BCI competition III data set V). Keywords: Power Spectral Density (PSD), Artificial Neural Network (ANN) Electroencephalogram (EEG), Brain Computer Interface (BCI). I. INTRODUCTION A BCI is a computer-based system that acquires brain signals, analyzes them, and translates them into commands that are relayed to an output device to carry out a desired action. In recent years mental tasks have been studied by many researchers and their study shows that BCI is useful for physically challenged individual. Such individuals who have lost their entire voluntary actions can only rely on their cognitive actions to interact with others BCI is useful for them [1]. An electroencephalogram (EEG) is the basic building block for Brain-Computer Interfaces. The Electroencephalogram (EEG) is used to measure the brain signals pertaining to various activities like imagining hand movements leg movement etc. The EEG recognition procedure mainly involves feature extraction from EEG signal and classification of mental task. The useful EEG signals contain huge data of brain signals. Numerous methods have been used to extract feature vectors from the EEG signals. The different PSD methods have used to extract the feature. The Fourier presented his famous method for representing signals in the frequency domain; life scientists have employed his transform in order to determine cyclical events in nature. The PSD is a powerful method for the identification of repetitive and correlated events, and was first refined by Schuster in the late 1800s, in order to accurately quantify natural phenomena for lunar and sunspot-induced earthquake predictions. Known as the periodogram, the resulting PSD is formed by averaging many Fourier spectra in order to improve signal to noise, and preserve frequency resolution. Since that time, signal processing has blossomed in the field of communications and biometric measurements. Non-parametric estimation methods involve simple averaging techniques of multiple spectra, which is well within the capabilities of even modest computing equipment. In addition to the basic periodogram, methods by Bartlett and Welch offer more advanced forms involving pre-filtering, and data windowing. Recent approaches involve developing parameterized models, whereby the PSD is represented by a high-order mathematical equation, instead of a simple running average. The extracted feature vectors are then classified using machine learning techniques like neural networks, linear discriminate analysis, support vector machines (SVM), common spatial pattern, etc. DOI : /IJRTER XDMNO 145
2 II. METHODOLOGY The classification of mental task involves, EEG recording or EEG data from data base then the feature extraction and finally classification. 2.1 Design Flow The EEG signals have been used for mental task classification, however the EEG signals are often corrupted by power line interference noise and EMC induced noise. These artifacts strongly influence the utility of recorded EEGs and need to be removed for better classification of mental task. Therefore the signals were preprocessed and then used to extract the feature. The EEG signals are obtained from B-Alert experimental setup for two subjects and also from BCI data base (BCI Competition III data set V for three subjects). Then the different PSD methods have been employed for feature extraction. The final step involves classification of mental task which has been done by using neural network based on Back Propagation Algorithm. Figure 1: Design Flow 2.2 Experimental paradigm BCI Data set This dataset contains data from 3 normal subjects during 4 non-feedback sessions. The subjects sat in a normal chair, relaxed arms resting on their legs. There are 3 tasks: Imagination of repetitive self-paced left hand movements, (left, class 2), Imagination of repetitive self-paced right hand movements, (right, class 3), All 4 sessions of a given subject were acquired on the same day, each lasting 4 minutes with 5-10 minutes breaks in between them. The subject performed a given task for about 15 seconds and then switched randomly to another task at the operator's request. EEG data is not splitted in trials since the subjects are continuously performing any of the mental tasks. The algorithm should provide an output every 0.5 seconds using the last second of data (see clarification in the paragraph 'Requirements and Evaluation'.). Data are provided in two ways: Raw EEG signals. Sampling rate was 512 Hz. Precomputed features. The raw EEG potentials were first spatially filtered by means of a surface Laplacian. Then, every 62.5 ms --i.e., 16 times per second-- the power spectral density (PSD) in the band 8-30 Hz was estimated over the last second of data with a frequency resolution of 2 Hz for the 8 centro-parietal channels C3, Cz, C4, CP1, CP2, P3, Pz, and P4. As a result, an EEG sample is a 96dimensional vector (8 channels times 12 frequency All Rights Reserved 146
3 2.2.2 B-Alert Experimental Setup. The S.B. Jain Institute of Technology Management and Research has got grand from Research Promotion Scheme (RPS) of AICET for BCI research work, under this scheme college has provided us the two EEG recording system RMS EEG machine and B-Alert X10-Standard system. Here we have discussed about B-Alert system. B-Alert X10-Standard system is a wireless EEG data acquisition system. The data has been recorded using B-Alert X10-Standard system. The experiment was done on two subjects. The subjects were given to perform two different tasks left hand and right hand real and imaginary movement. For left hand and right hand real movement data was recorded for around 3 minutes where as for left hand and right hand imaginary movement recording was done for 2 minutes with sampling frequency of 256 Hz. X10-Standard system is a ten channels system the ten channels are ECG, F3, Fz, F4, C3, CZ, C4, P3, POz and P4. In this 8 channels have been considered which are F3, Fz, F4, C3, CZ, C4, P3 and POz. 2.3 Feature extraction: The EEG signals are used to classify the mental tasks; the feature is first extracted before classification. The different PSD methods are used here to extract the features PSD Using FFT method: Power spectral density (PSD) is computed by performing Fast Fourier Transform (FFT) on a segment of data that is of interest, and calculating the amplitudes of the sinusoidal components for designated frequency bins. Input variables to this transformation are an EEG segment for which PSD is to be computed, and its length; output variables include PSD amplitudes. Frequency domain variables are based on the power spectral density derived after application of a 50 overlapping window, and a FFT with and without application of a Kaiser window is calculated from 8Hz to 30 Hz for each EEG channel that are logged to obtain a Gaussian distribution. The 8 channels are (Poz, Fz, Cz, C3, C4, F3, F4, F3 and F3) used to calculate the PSD. The 12 components are calculated for each channel in 8Hz to 30 Hz band there by providing 96 components for 8 channels. Both sets of PSD output files apply a 50 overlapping window which averages the PSD across three x one-second overlays to smooth the data. The illustration below shows that overlays 0, 1, and 2 are averaged (each overlay containing 256 data points with 128 data points being shared for each overlay) to provide the PSD values for epoch n: Figure 2: Overlap All Rights Reserved 147
4 Figure 3: Plot for PSD estimated using FFT Method Figure 4: Plot for PSD estimated using FFT Method with Kaiser Window Periodogram Method. The well-know known form of the PSD is called periodogram. It was originally introduced by Schuster (1898) to detect and measure hidden periodicities in data. The periodogram is given as. [30] The periodogram Pxx(f) can be computed by use of DFT, which in turn in efficiently computed by an FFT algorithm. If we have N data points, we compute as a minimum the Npoint DFT. For example, the computation yields samples of the periodogram k= 0, 1, 2 N-1. at the frequencies f = k/n Samples of the periodogram at fk = k=n, k =0, 1, : : :,N 1 can be computed efficiently with the use of the fast Fourier transform (FFT) algorithm while values at the other frequencies are evaluated by either zero padding or All Rights Reserved 148
5 xx N Where id is the starting point for the ith sequence. If D = M, the segment do not overlap and the L of data sequence is identical to the data segment of Bartlett method. The second change in Welch method is to window the data segments prior to computing the periodogram. In this work Power spectral density (PSD) is computed by calculating periodogram without and with hamming window for segment of data that is of interest. The periodogram is calculated till the last epoch where each epoch consists of sequence of 256 samples. Figure 5: Plot for PSD estimated using periodogram Welch Method. Power Spectral Estimate (PSE) is most important application area in Digital Signal Welch method have two basic modifications to the Bartlett method. These are allowed the data length to overlap. The data segment can be represented as Where U is a normalization factor for the power The Welch power spectrum estimate is the average of modified periodgram, All Rights Reserved 149
6 Mean value of Welch estimate International Journal of Recent Trends in Engineering & Research (IJRTER) The resolution of estimated power estimation is determine by the spectral resolution of each segment which is of length L. it is window dependent. Welch allows the data segments to overlap and window the data segments prior to computing preiodogram. Here the 256 point sequence is subdivided into 8 overlapping segments with 50 overlap; each segment is windowed by hamming window. The again the PSD is calculated in same frequency band 8 Hz to 30 Hz, 12 PSD components are calculated for each channel. Therefore for 8 channels 96 PSD components will be obtained. Plot for PSD estimated using Welch Method 2.4 Classifier. In this work two task left hand and right hand real and imaginary movement has been classified using Artificial Neural Network with different number of hidden layers and neurons. The back propagation algorithm is used to train the neural network. III. RESULT In this work two task left hand and right hand real and imaginary movement has been classified using Back propagation neural network with different number of hidden layers and neurons, where as the feature is extracted using FFT method, Periodogram method, and Welch Method. The different result i.e. classification accuracy has been obtained as shown in table below. Sr. No. Table1. Comparative results for real hand movement for B-Alert data No. of hidde n Neurons in each layers layer PSD Method Periodogram Periodogram Periodogram with Hamming 74 All Rights Reserved 150
7 Periodogram with Hamming window FFT method FFT method FFT method with Kaiser FFT method 66 with Kaiser Welch method Welch method 86 Table2. Comparative results for Imaginary hand movement for B-Alert data Sr. No. of hidden Neurons in No. layers each PSD Method layer Periodogram Periodogram Periodogram with Hamming window Periodogram with Hamming window FFT method FFT method FFT method with Kaiser FFT method with 63 Kaiser Welch method Welch method 62 Sr. No. Table3. Comparative results for Imaginary hand movement for BCI data No. of hidden layers Neurons in each layer PSD Method Periodogram Periodogram Periodogram with 74 Hamming window Periodogram with 72 Hamming All Rights Reserved 151
8 FFT method FFT method FFT method with Kaiser FFT method with Kaiser Welch method Welch method 66 From above tables it can be seen that the accuracy of neural network increases as increase the number of hidden layers but the complexity and computation time is also increased. The table below shows the comparative results with different PSD techniques in term of maximum accuracy obtained. Table4. Comparative results for real hand movement for B-Alert data Sr. No. PSD Method 1 Periodogram 62 2 Periodogram with Hamming window 74 3 FFT method 88 4 FFT method with Kaiser 92 5 Welch method Table5. Comparative results for Imaginary hand movement for B-Alert data Sr. No. PSD Method 1 Periodogram 50 2 Periodogram with Hamming window FFT method 70 4 FFT method with Kaiser 70 5 Welch method 71 For BCI competition III data set V, for subject 1 the two trials has been taken to calculate classification accuracy the average classification accuracy is shown in table below. Table6. Comparative results for Imaginary hand movement for BCI data base. Sr. No. with with Averag e PSD Method Trail1 Trail2 accurac y 1 Periodogram Periodogram with Hamming window 3 FFT method FFT method with Kaiser 5 Welch method All Rights Reserved 152
9 IV. CONCLUSION In this work the two task left hand and right real and imaginary movement have been classified for which the EEG data has been recorded using B-Alert X10 standard wireless system on two subjects. The comparative results for real hand movement for B-Alert data is given in table 4 and the comparative results for imaginary hand movement for BAlert data is given in table 5. It is found that the classification accuracy is found to be better in case of real hand movement. The classification is also done for BCI competition III data set V, the classification accuracy for two trials is shown in table 6. In which the accuracy with FFT method is found to be 100. The classification accuracy has also been calculated with different number of layers in neural network and different number of neurons in each layer the as shown in table 1, table 2 and table 3. It can be seen from table 1, table 2 and table 3 that the on an average the classification accuracy increases as we increase the number of layer and neuron in the neural network. REFERENCES 1. Padmanabh Mahesh Lanke, Prof. R. K. Shastri, Prof. S. D. Biradar EEG Signal Processing Techniques for Mental Task Classification, International Journal of Advanced Computing and Electronics Technology (IJACET), ISSN(PRINT): , (ONLINE): ,VOLUME-2,ISSUE-1, Yang Zong-chang, Establishing Structure for Neural Networks Based-on Fractal. Journal of Theoretical and Applied Information Technology 10th March Vol. 49 No.1, ISSN: , E-ISSN: p. 342_ H. C. So, Y. T. Chan Comparison of Various Periodograms for Sinusoid Detection and Frequency Estimation, IEEE Transactions on Aerospace and Electronic system VOL. 35, NO. 3 pp JULY Soosan Beheshti Mean-Square Error in Periodogram Approaches with Adaptive Windowing IEEE Transaction on signal processing VOL. 59, NO. 3.pp , March Sem a Arslan, Gulay T ezel, and Ha kan Islk, EEG Signals Classification Using a Hybrid Structure of ANN and PSO, International Journal of Future Computer and Communication, Vol. 1, No. 2, August Hansa Rani Gupta, Rajesh Mehra, Power Spectrum Estimation using Welch Method for various Window Techniques, International Journal of Scientific Research Engineering & Technology (IJSRET) Volume 2 Issue 6 pp September 2013, ISSN Mythra H V, Veenakumari H M, Sanjeev Kubakaddi., Multi-Class EEG Classification for Brain Computer Interface, International Journal of Scientific & Engineering Research, Volume 4, Issue 9, September-2013 p Shaik.Jakeer Husain and K.Srinivasa.Rao Epileptic Seizures Classification from EEG Signals using Neural Networks, 2012 International Conference on Information and Network Technology (ICINT 2012) IPCSIT vol. 37 p (2012) (2012) IACSIT Press, All Rights Reserved 153
OPTIMAL FEATURE SELECTION BY GENETIC ALGORITHM FOR CLASSIFICATION USING NEURAL NETWORK
OPTIMAL FEATURE SELECTION BY GENETIC ALGORITHM FOR CLASSIFICATION USING NEURAL NETWORK Swati N.Moon 1, Dr. Narendra Bawane 2 1 Student, Department of Electronics Engineering, S.B. Jain Institute of Technology
More informationModified Welch Power Spectral Density Computation with Fast Fourier Transform
Modified Welch Power Spectral Density Computation with Fast Fourier Transform Sreelekha S 1, Sabi S 2 1 Department of Electronics and Communication, Sree Budha College of Engineering, Kerala, India 2 Professor,
More informationEstimating Noise and Dimensionality in BCI Data Sets: Towards Illiteracy Comprehension
Estimating Noise and Dimensionality in BCI Data Sets: Towards Illiteracy Comprehension Claudia Sannelli, Mikio Braun, Michael Tangermann, Klaus-Robert Müller, Machine Learning Laboratory, Dept. Computer
More informationLouis Fourrier Fabien Gaie Thomas Rolf
CS 229 Stay Alert! The Ford Challenge Louis Fourrier Fabien Gaie Thomas Rolf Louis Fourrier Fabien Gaie Thomas Rolf 1. Problem description a. Goal Our final project is a recent Kaggle competition submitted
More informationOptimizing Number of Hidden Nodes for Artificial Neural Network using Competitive Learning Approach
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 5, May 2015, pg.358
More informationIris recognition using SVM and BP algorithms
International Journal of Engineering Research and Advanced Technology (IJERAT) DOI: http://dx.doi.org/10.31695/ijerat.2018.3262 E-ISSN : 2454-6135 Volume.4, Issue 5 May -2018 Iris recognition using SVM
More informationBackground: Bioengineering - Electronics - Signal processing. Biometry - Person Identification from brain wave detection University of «Roma TRE»
Background: Bioengineering - Electronics - Signal processing Neuroscience - Source imaging - Brain functional connectivity University of Rome «Sapienza» BCI - Feature extraction from P300 brain potential
More informationSimulation of Back Propagation Neural Network for Iris Flower Classification
American Journal of Engineering Research (AJER) e-issn: 2320-0847 p-issn : 2320-0936 Volume-6, Issue-1, pp-200-205 www.ajer.org Research Paper Open Access Simulation of Back Propagation Neural Network
More informationA Survey on Image Segmentation Using Clustering Techniques
A Survey on Image Segmentation Using Clustering Techniques Preeti 1, Assistant Professor Kompal Ahuja 2 1,2 DCRUST, Murthal, Haryana (INDIA) Abstract: Image is information which has to be processed effectively.
More informationTHREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM
THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM M. Sivakumar 1 and R. M. S. Parvathi 2 1 Anna University, Tamilnadu, India 2 Sengunthar College of Engineering, Tamilnadu,
More informationEEG Imaginary Body Kinematics Regression. Justin Kilmarx, David Saffo, and Lucien Ng
EEG Imaginary Body Kinematics Regression Justin Kilmarx, David Saffo, and Lucien Ng Introduction Brain-Computer Interface (BCI) Applications: Manipulation of external devices (e.g. wheelchairs) For communication
More informationLeaf Image Recognition Based on Wavelet and Fractal Dimension
Journal of Computational Information Systems 11: 1 (2015) 141 148 Available at http://www.jofcis.com Leaf Image Recognition Based on Wavelet and Fractal Dimension Haiyan ZHANG, Xingke TAO School of Information,
More informationi-eeg: A Software Tool for EEG Feature Extraction, Feature Selection and Classification
i-eeg: A Software Tool for EEG Feature Extraction, Feature Selection and Classification Baha ŞEN Computer Engineering Department, Yıldırım Beyazıt University, Ulus, Ankara, TURKEY Musa PEKER Computer Engineering
More informationA Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation
A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation * A. H. M. Al-Helali, * W. A. Mahmmoud, and * H. A. Ali * Al- Isra Private University Email: adnan_hadi@yahoo.com Abstract:
More informationReview on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,
More informationCHAPTER 3. Preprocessing and Feature Extraction. Techniques
CHAPTER 3 Preprocessing and Feature Extraction Techniques CHAPTER 3 Preprocessing and Feature Extraction Techniques 3.1 Need for Preprocessing and Feature Extraction schemes for Pattern Recognition and
More informationGender Classification Technique Based on Facial Features using Neural Network
Gender Classification Technique Based on Facial Features using Neural Network Anushri Jaswante Dr. Asif Ullah Khan Dr. Bhupesh Gour Computer Science & Engineering, Rajiv Gandhi Proudyogiki Vishwavidyalaya,
More informationA Framework of Hyperspectral Image Compression using Neural Networks
A Framework of Hyperspectral Image Compression using Neural Networks Yahya M. Masalmah, Ph.D 1, Christian Martínez-Nieves 1, Rafael Rivera-Soto 1, Carlos Velez 1, and Jenipher Gonzalez 1 1 Universidad
More informationArgha Roy* Dept. of CSE Netaji Subhash Engg. College West Bengal, India.
Volume 3, Issue 3, March 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Training Artificial
More informationPerformance Analysis of SVM, k-nn and BPNN Classifiers for Motor Imagery
Performance Analysis of SVM, k-nn and BPNN Classifiers for Motor Imagery Indu Dokare #1, Naveeta Kant *2 #1 Assistant Professor, *2 Associate Professor #1, *2 Department of Electronics & Telecommunication
More informationAn Optimum Adaptive Parameterized Mask NHA Based Image Denoising
An Optimum Adaptive Parameterized Mask NHA Based Image Denoising K.INDUPRIYA *1, Dr. G. P. RAMESH KUMAR 2 *1 Research Scholar, Department of Computer Science, SNR Sons College, Tamilnadu, India, * 1 indupriya1406@gmail.com
More informationNeural Network Classifier for Isolated Character Recognition
Neural Network Classifier for Isolated Character Recognition 1 Ruby Mehta, 2 Ravneet Kaur 1 M.Tech (CSE), Guru Nanak Dev University, Amritsar (Punjab), India 2 M.Tech Scholar, Computer Science & Engineering
More informationFEATURE EVALUATION FOR EMG-BASED LOAD CLASSIFICATION
FEATURE EVALUATION FOR EMG-BASED LOAD CLASSIFICATION Anne Gu Department of Mechanical Engineering, University of Michigan Ann Arbor, Michigan, USA ABSTRACT Human-machine interfaces (HMIs) often have pattern
More informationAnalyze EEG Signals with Convolutional Neural Network Based on Power Spectrum Feature Selection
Analyze EEG Signals with Convolutional Neural Network Based on Power Spectrum Feature Selection 1 Brain Cognitive Computing Lab, School of Information Engineering, Minzu University of China Beijing, 100081,
More informationCursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network
Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Utkarsh Dwivedi 1, Pranjal Rajput 2, Manish Kumar Sharma 3 1UG Scholar, Dept. of CSE, GCET, Greater Noida,
More informationImage Enhancement Techniques for Fingerprint Identification
March 2013 1 Image Enhancement Techniques for Fingerprint Identification Pankaj Deshmukh, Siraj Pathan, Riyaz Pathan Abstract The aim of this paper is to propose a new method in fingerprint enhancement
More informationInternational Journal of Scientific Research & Engineering Trends Volume 4, Issue 6, Nov-Dec-2018, ISSN (Online): X
Analysis about Classification Techniques on Categorical Data in Data Mining Assistant Professor P. Meena Department of Computer Science Adhiyaman Arts and Science College for Women Uthangarai, Krishnagiri,
More informationLatency [ms] Nose RVF LVF. Fpz Fp2. Fp1 AF7 AF3 AF8 AF4. AFz F7 F5 F3. Fz F2 F4. FT7 FC5 FC3 FC1 FCz FT8 FC6 FC4 FC2. Cz C2 C4 C6 T8.
NR HEOG VEOG Fpz AF7 AF3 AFz AF4 AF8 F7 F5 F3 F1 Fz F2 F4 F6 F8 FT9 FT10 F FC5 FC3 FC1 FCz FC2 FC4 FC6 F C5 C3 C1 Cz C2 C4 C6 T CP5 CP3 CP1 CPz CP2 CP4 CP6 T TP9 TP10 P5 P3 P1 Pz P2 P4 P6 PO7 PO3 POz PO4
More informationPerforming real-time BCI experiments
Performing real-time BCI experiments g.tec medical engineering GmbH Herbersteinstr. 60 8020 Graz, Austria www.gtec.at guger@gtec.at g.usbamp is a biosignal acquisition system for EEG, ECG, EMG, EOG and
More informationResearch on Applications of Data Mining in Electronic Commerce. Xiuping YANG 1, a
International Conference on Education Technology, Management and Humanities Science (ETMHS 2015) Research on Applications of Data Mining in Electronic Commerce Xiuping YANG 1, a 1 Computer Science Department,
More informationDesign of classification methods for Brain Computer Interfaces: An application using the OpenViBE software
Informatics Engineering Degree Software Engineering Degree s Final Project Design of classification methods for Brain Computer Interfaces: An application using the OpenViBE software Author Ibai Díez Oronoz
More informationGlobal Journal of Engineering Science and Research Management
A NOVEL HYBRID APPROACH FOR PREDICTION OF MISSING VALUES IN NUMERIC DATASET V.B.Kamble* 1, S.N.Deshmukh 2 * 1 Department of Computer Science and Engineering, P.E.S. College of Engineering, Aurangabad.
More informationLocalized Anomaly Detection via Hierarchical Integrated Activity Discovery
Localized Anomaly Detection via Hierarchical Integrated Activity Discovery Master s Thesis Defense Thiyagarajan Chockalingam Advisors: Dr. Chuck Anderson, Dr. Sanjay Rajopadhye 12/06/2013 Outline Parameter
More informationEdge Detection for Dental X-ray Image Segmentation using Neural Network approach
Volume 1, No. 7, September 2012 ISSN 2278-1080 The International Journal of Computer Science & Applications (TIJCSA) RESEARCH PAPER Available Online at http://www.journalofcomputerscience.com/ Edge Detection
More informationClassifying Twitter Data in Multiple Classes Based On Sentiment Class Labels
Classifying Twitter Data in Multiple Classes Based On Sentiment Class Labels Richa Jain 1, Namrata Sharma 2 1M.Tech Scholar, Department of CSE, Sushila Devi Bansal College of Engineering, Indore (M.P.),
More informationTraffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers
Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane
More informationLiquefaction Analysis in 3D based on Neural Network Algorithm
Liquefaction Analysis in 3D based on Neural Network Algorithm M. Tolon Istanbul Technical University, Turkey D. Ural Istanbul Technical University, Turkey SUMMARY: Simplified techniques based on in situ
More informationA Combined Method for On-Line Signature Verification
BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 14, No 2 Sofia 2014 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.2478/cait-2014-0022 A Combined Method for On-Line
More informationResearch Article International Journals of Advanced Research in Computer Science and Software Engineering ISSN: X (Volume-7, Issue-6)
International Journals of Advanced Research in Computer Science and Software Engineering Research Article June 17 Artificial Neural Network in Classification A Comparison Dr. J. Jegathesh Amalraj * Assistant
More informationNeural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani
Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer
More informationBrain enabled mechanized speech synthesizer using Brain Mobile Interface
Brain enabled mechanized speech synthesizer using Brain Mobile Interface G.N.Jayabhavani, N.R.Raajan School of Electrical and Electronics Engineering, SASTRA University, Thanjavur, TamilNadu, India Email:
More informationDepartment of Electronics and Telecommunication Engineering 1 PG Student, JSPM s Imperial College of Engineering and Research, Pune (M.H.
Volume 5, Issue 4, 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Introduction to Probabilistic
More informationCHAPTER 5 RANDOM VIBRATION TESTS ON DIP-PCB ASSEMBLY
117 CHAPTER 5 RANDOM VIBRATION TESTS ON DIP-PCB ASSEMBLY 5.1 INTRODUCTION Random vibration tests are usually specified as acceptance, screening and qualification tests by commercial, industrial, and military
More informationNeural networks for variable star classification
Neural networks for variable star classification Vasily Belokurov, IoA, Cambridge Supervised classification Multi-Layer Perceptron (MLP) Neural Networks for Pattern Recognition by C. Bishop Unsupervised
More informationImplementing Machine Learning in Earthquake Engineering
CS9 MACHINE LEARNING, DECEMBER 6 Implementing Machine Learning in Earthquake Engineering Cristian Acevedo Civil and Environmental Engineering Stanford University, Stanford, CA 9435, USA Abstract The use
More informationA Simple Generative Model for Single-Trial EEG Classification
A Simple Generative Model for Single-Trial EEG Classification Jens Kohlmorgen and Benjamin Blankertz Fraunhofer FIRST.IDA Kekuléstr. 7, 12489 Berlin, Germany {jek, blanker}@first.fraunhofer.de http://ida.first.fraunhofer.de
More informationFingerprint Image Enhancement Algorithm and Performance Evaluation
Fingerprint Image Enhancement Algorithm and Performance Evaluation Naja M I, Rajesh R M Tech Student, College of Engineering, Perumon, Perinad, Kerala, India Project Manager, NEST GROUP, Techno Park, TVM,
More information- Graphical editing of user montages for convenient data review - Import of user-defined file formats using generic reader
Data review and processing Source montages and 3D whole-head mapping Onset of epileptic seizure with 3D whole-head maps and hemispheric comparison of density spectral arrays (DSA) Graphical display of
More informationFACE DETECTION AND RECOGNITION USING BACK PROPAGATION NEURAL NETWORK AND FOURIER GABOR FILTERS
FACE DETECTION AND RECOGNITION USING BACK PROPAGATION NEURAL NETWORK AND FOURIER GABOR FILTERS Anissa Bouzalmat 1, Naouar Belghini, Arsalane Zarghili 3 and Jamal Kharroubi 4 1 Department of Computer Sciences,
More informationCLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS
CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of
More informationA Data Classification Algorithm of Internet of Things Based on Neural Network
A Data Classification Algorithm of Internet of Things Based on Neural Network https://doi.org/10.3991/ijoe.v13i09.7587 Zhenjun Li Hunan Radio and TV University, Hunan, China 278060389@qq.com Abstract To
More informationArtificial Neural Network and Multi-Response Optimization in Reliability Measurement Approximation and Redundancy Allocation Problem
International Journal of Mathematics and Statistics Invention (IJMSI) E-ISSN: 2321 4767 P-ISSN: 2321-4759 Volume 4 Issue 10 December. 2016 PP-29-34 Artificial Neural Network and Multi-Response Optimization
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationAdaptive Fingerprint Image Enhancement Techniques and Performance Evaluations
Adaptive Fingerprint Image Enhancement Techniques and Performance Evaluations Kanpariya Nilam [1], Rahul Joshi [2] [1] PG Student, PIET, WAGHODIYA [2] Assistant Professor, PIET WAGHODIYA ABSTRACT: Image
More informationFace Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
IJCSES International Journal of Computer Sciences and Engineering Systems, Vol., No. 3, July 2011 CSES International 2011 ISSN 0973-06 Face Detection Using Radial Basis Function Neural Networks with Fixed
More informationAMOL MUKUND LONDHE, DR.CHELPA LINGAM
International Journal of Advances in Applied Science and Engineering (IJAEAS) ISSN (P): 2348-1811; ISSN (E): 2348-182X Vol. 2, Issue 4, Dec 2015, 53-58 IIST COMPARATIVE ANALYSIS OF ANN WITH TRADITIONAL
More informationInternational Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS)
International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) International Journal of Emerging Technologies in Computational
More informationTransactions on Information and Communications Technologies vol 19, 1997 WIT Press, ISSN
Gap Repair in Water Level Measurement Data Using Neural Networks P. van der Veer, J. Cser, O. Schleider & E. Kerckhoffs Delft University of Technology, Faculties of Civil Engineering and Informatics, Postbus
More informationDigital Image Processing
Digital Image Processing Third Edition Rafael C. Gonzalez University of Tennessee Richard E. Woods MedData Interactive PEARSON Prentice Hall Pearson Education International Contents Preface xv Acknowledgments
More informationRough Set Approach to Unsupervised Neural Network based Pattern Classifier
Rough Set Approach to Unsupervised Neural based Pattern Classifier Ashwin Kothari, Member IAENG, Avinash Keskar, Shreesha Srinath, and Rakesh Chalsani Abstract Early Convergence, input feature space with
More informationTexture Image Segmentation using FCM
Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Texture Image Segmentation using FCM Kanchan S. Deshmukh + M.G.M
More informationModeling Body Motion Posture Recognition Using 2D-Skeleton Angle Feature
2012 International Conference on Image, Vision and Computing (ICIVC 2012) IPCSIT vol. 50 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V50.1 Modeling Body Motion Posture Recognition Using
More informationFace Detection Using Radial Basis Function Neural Networks With Fixed Spread Value
Detection Using Radial Basis Function Neural Networks With Fixed Value Khairul Azha A. Aziz Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka, Ayer Keroh, Melaka, Malaysia.
More informationRecognition of finger movements using EEG signals for control of upper limb prosthesis using logistic regression.
Biomedical Research 2017; 28 (17): 7361-7369 ISSN 0970-938X www.biomedres.info Recognition of finger movements using EEG signals for control of upper limb prosthesis using logistic regression. Amna Javed,
More informationProcessing of Iris Video frames to Detect Blink and Blurred frames
Processing of Iris Video frames to Detect Blink and Blurred frames Asha latha.bandi Computer Science & Engineering S.R.K Institute of Technology Vijayawada, 521 108,Andhrapradesh India Latha009asha@gmail.com
More informationAn Improved CBIR Method Using Color and Texture Properties with Relevance Feedback
An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback MS. R. Janani 1, Sebhakumar.P 2 Assistant Professor, Department of CSE, Park College of Engineering and Technology, Coimbatore-
More informationPreprocessing of Stream Data using Attribute Selection based on Survival of the Fittest
Preprocessing of Stream Data using Attribute Selection based on Survival of the Fittest Bhakti V. Gavali 1, Prof. Vivekanand Reddy 2 1 Department of Computer Science and Engineering, Visvesvaraya Technological
More informationHANDWRITTEN GURMUKHI CHARACTER RECOGNITION USING WAVELET TRANSFORMS
International Journal of Electronics, Communication & Instrumentation Engineering Research and Development (IJECIERD) ISSN 2249-684X Vol.2, Issue 3 Sep 2012 27-37 TJPRC Pvt. Ltd., HANDWRITTEN GURMUKHI
More informationELEC Dr Reji Mathew Electrical Engineering UNSW
ELEC 4622 Dr Reji Mathew Electrical Engineering UNSW Review of Motion Modelling and Estimation Introduction to Motion Modelling & Estimation Forward Motion Backward Motion Block Motion Estimation Motion
More informationIsolated Curved Gurmukhi Character Recognition Using Projection of Gradient
International Journal of Computational Intelligence Research ISSN 0973-1873 Volume 13, Number 6 (2017), pp. 1387-1396 Research India Publications http://www.ripublication.com Isolated Curved Gurmukhi Character
More informationADJUST: An Automatic EEG artifact Detector based on the Joint Use of Spatial and Temporal features
ADJUST: An Automatic EEG artifact Detector based on the Joint Use of Spatial and Temporal features A Tutorial. Marco Buiatti 1 and Andrea Mognon 2 1 INSERM U992 Cognitive Neuroimaging Unit, Gif sur Yvette,
More informationColour Image Segmentation Using K-Means, Fuzzy C-Means and Density Based Clustering
Colour Image Segmentation Using K-Means, Fuzzy C-Means and Density Based Clustering Preeti1, Assistant Professor Kompal Ahuja2 1,2 DCRUST, Murthal, Haryana (INDIA) DITM, Gannaur, Haryana (INDIA) Abstract:
More informationInternational Journal of Advance Engineering and Research Development. Iris Recognition and Automated Eye Tracking
International Journal of Advance Engineering and Research Development Scientific Journal of Impact Factor (SJIF): 4.72 Special Issue SIEICON-2017,April -2017 e-issn : 2348-4470 p-issn : 2348-6406 Iris
More informationA Comparative Study of Conventional and Neural Network Classification of Multispectral Data
A Comparative Study of Conventional and Neural Network Classification of Multispectral Data B.Solaiman & M.C.Mouchot Ecole Nationale Supérieure des Télécommunications de Bretagne B.P. 832, 29285 BREST
More informationHand Written Digit Recognition Using Tensorflow and Python
Hand Written Digit Recognition Using Tensorflow and Python Shekhar Shiroor Department of Computer Science College of Engineering and Computer Science California State University-Sacramento Sacramento,
More informationRadial Basis Function (RBF) Neural Networks Based on the Triple Modular Redundancy Technology (TMR)
Radial Basis Function (RBF) Neural Networks Based on the Triple Modular Redundancy Technology (TMR) Yaobin Qin qinxx143@umn.edu Supervisor: Pro.lilja Department of Electrical and Computer Engineering Abstract
More informationRefined Measurement of Digital Image Texture Loss Peter D. Burns Burns Digital Imaging Fairport, NY USA
Copyright 3 SPIE Refined Measurement of Digital Image Texture Loss Peter D. Burns Burns Digital Imaging Fairport, NY USA ABSTRACT Image texture is the term given to the information-bearing fluctuations
More informationA Cloud Based Intrusion Detection System Using BPN Classifier
A Cloud Based Intrusion Detection System Using BPN Classifier Priyanka Alekar Department of Computer Science & Engineering SKSITS, Rajiv Gandhi Proudyogiki Vishwavidyalaya Indore, Madhya Pradesh, India
More informationA Survey on Feature Extraction Techniques for Palmprint Identification
International Journal Of Computational Engineering Research (ijceronline.com) Vol. 03 Issue. 12 A Survey on Feature Extraction Techniques for Palmprint Identification Sincy John 1, Kumudha Raimond 2 1
More informationResearch on the New Image De-Noising Methodology Based on Neural Network and HMM-Hidden Markov Models
Research on the New Image De-Noising Methodology Based on Neural Network and HMM-Hidden Markov Models Wenzhun Huang 1, a and Xinxin Xie 1, b 1 School of Information Engineering, Xijing University, Xi an
More informationPATTERN RECOGNITION USING NEURAL NETWORKS
PATTERN RECOGNITION USING NEURAL NETWORKS Santaji Ghorpade 1, Jayshree Ghorpade 2 and Shamla Mantri 3 1 Department of Information Technology Engineering, Pune University, India santaji_11jan@yahoo.co.in,
More informationBCI++: an object-oriented BCI Prototyping Framework
BCI++: an object-oriented BCI Prototyping Framework Luca Maggi 1, Sergio Parini 2, Paolo Perego 1 and Giuseppe Andreoni 1 Sensibilab, Politecnico di Milano 1 Indaco Dept., Politecnico di Milano, ITALY
More informationApproach to Increase Accuracy of Multimodal Biometric System for Feature Level Fusion
Approach to Increase Accuracy of Multimodal Biometric System for Feature Level Fusion Er. Munish Kumar, Er. Prabhjit Singh M-Tech(Scholar) Global Institute of Management and Emerging Technology Assistant
More information19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007
19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007 SUBJECTIVE AND OBJECTIVE QUALITY EVALUATION FOR AUDIO WATERMARKING BASED ON SINUSOIDAL AMPLITUDE MODULATION PACS: 43.10.Pr, 43.60.Ek
More informationMore on Learning. Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization
More on Learning Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization Neural Net Learning Motivated by studies of the brain. A network of artificial
More informationClustering Analysis based on Data Mining Applications Xuedong Fan
Applied Mechanics and Materials Online: 203-02-3 ISSN: 662-7482, Vols. 303-306, pp 026-029 doi:0.4028/www.scientific.net/amm.303-306.026 203 Trans Tech Publications, Switzerland Clustering Analysis based
More informationRobust Pose Estimation using the SwissRanger SR-3000 Camera
Robust Pose Estimation using the SwissRanger SR- Camera Sigurjón Árni Guðmundsson, Rasmus Larsen and Bjarne K. Ersbøll Technical University of Denmark, Informatics and Mathematical Modelling. Building,
More informationExtending reservoir computing with random static projections: a hybrid between extreme learning and RC
Extending reservoir computing with random static projections: a hybrid between extreme learning and RC John Butcher 1, David Verstraeten 2, Benjamin Schrauwen 2,CharlesDay 1 and Peter Haycock 1 1- Institute
More informationTumor Detection and classification of Medical MRI UsingAdvance ROIPropANN Algorithm
International Journal of Engineering Research and Advanced Technology (IJERAT) DOI:http://dx.doi.org/10.31695/IJERAT.2018.3273 E-ISSN : 2454-6135 Volume.4, Issue 6 June -2018 Tumor Detection and classification
More informationA Image Comparative Study using DCT, Fast Fourier, Wavelet Transforms and Huffman Algorithm
International Journal of Engineering Research and General Science Volume 3, Issue 4, July-August, 15 ISSN 91-2730 A Image Comparative Study using DCT, Fast Fourier, Wavelet Transforms and Huffman Algorithm
More informationStatistical Analysis of Neuroimaging Data. Phebe Kemmer BIOS 516 Sept 24, 2015
Statistical Analysis of Neuroimaging Data Phebe Kemmer BIOS 516 Sept 24, 2015 Review from last time Structural Imaging modalities MRI, CAT, DTI (diffusion tensor imaging) Functional Imaging modalities
More informationUpdate ASA 4.8. Expand your research potential with ASA 4.8. Highly advanced 3D display of single channel coherence
Update ASA 4.8 Expand your research potential with ASA 4.8. The ASA 4.8 software has everything needed for a complete analysis of EEG / ERP and MEG data. From features like (pre)processing of data, co-registration
More informationA Matlab based Face Recognition GUI system Using Principal Component Analysis and Artificial Neural Network
A Matlab based Face Recognition GUI system Using Principal Component Analysis and Artificial Neural Network Achala Khandelwal 1 and Jaya Sharma 2 1,2 Asst Prof Department of Electrical Engineering, Shri
More informationKeywords - DWT, Lifting Scheme, DWT Processor.
Lifting Based 2D DWT Processor for Image Compression A. F. Mulla, Dr.R. S. Patil aieshamulla@yahoo.com Abstract - Digital images play an important role both in daily life applications as well as in areas
More informationESTIMATING THE COST OF ENERGY USAGE IN SPORT CENTRES: A COMPARATIVE MODELLING APPROACH
ESTIMATING THE COST OF ENERGY USAGE IN SPORT CENTRES: A COMPARATIVE MODELLING APPROACH A.H. Boussabaine, R.J. Kirkham and R.G. Grew Construction Cost Engineering Research Group, School of Architecture
More informationFFT and Spectrum Analyzer
Objective: FFT and Spectrum Analyzer Understand the frequency domain and some of it's uses Understand the Discrete Fourier Transform Preparation: (i) PC and data acquisition system (ii)fft software Background:
More informationVoice Command Based Computer Application Control Using MFCC
Voice Command Based Computer Application Control Using MFCC Abinayaa B., Arun D., Darshini B., Nataraj C Department of Embedded Systems Technologies, Sri Ramakrishna College of Engineering, Coimbatore,
More informationCorrelation Based Feature Selection with Irrelevant Feature Removal
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 4, April 2014,
More informationShort Survey on Static Hand Gesture Recognition
Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of
More informationNeuro-fuzzy, GA-Fuzzy, Neural-Fuzzy-GA: A Data Mining Technique for Optimization
International Journal of Computer Science and Software Engineering Volume 3, Number 1 (2017), pp. 1-9 International Research Publication House http://www.irphouse.com Neuro-fuzzy, GA-Fuzzy, Neural-Fuzzy-GA:
More information