EEG Classification with BSA Spike Encoding Algorithm and Evolving Probabilistic Spiking Neural Network

Size: px
Start display at page:

Download "EEG Classification with BSA Spike Encoding Algorithm and Evolving Probabilistic Spiking Neural Network"

Transcription

1 EEG Classification with BSA Spike Encoding Algorithm and Evolving Probabilistic Spiking Neural Network Nuttapod Nuntalid 1, Kshitij Dhoble 1, and Nikola Kasabov 1,2, 1 Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Private Bag 92006, Auckland 1010, New Zealand {nnuntali, kdhoble, nkasabov}@aut.ac.nz 2 Institute for Neuroinformatics, University of Zurich and ETH Zurich Abstract.This study investigates the feasibility of Bens Spike Algorithm (BSA) to encode continuous EEG spatio-temporal data into input spike streams for a classification in a spiking neural network classifier. A novel evolving probabilistic spiking neural network reservoir (epsnnr) architecture is used for the purpose of learning and classifying the EEG signals after the BSA transformation. Experiments are conducted with EEG data measuring a cognitive state of a single individual under 4 different stimuli. A comparison is drawn between using traditional machine learning algorithms and using BSA plus epsnnr, when different probabilistic models of neurons are utilised. The comparison demonstrates that: (1) The BSA is a suitable transformation for EEG data into spike trains; (2) The performance of the epsnnr improves when a probabilistic model of a neuron is used, compared to the use of a deterministic LIF model of a neuron; (3) The classification accuracy of the EEG data in an epsnnr depends on the type of the probabilistic neuronal model used. The results suggest that an epsnnr can be optimised in terms of neuronal models used and parameters that would better match the noise and the dynamics of EEG data. Potential applications of the proposed method for BCI and medical studies are briefly discussed. Keywords: Spatio-Temporal Patterns, Electroencephalograms (EEG), Stochastic neuron models, evolving probabilistic spiking neural networks. 1 Introduction EEG refers to the recording of electrical brain signal activity that is acquired along the head scalp as a result of neuronal activity in brain. In clinical aspect, EEG have been used in clinical recording of the brain electrical activity over a period of time and usually employs 19 electrodes / channels that are placed over various locations on the scalp. In neurology, the main diagnostic application of EEG is in the case of epilepsy,

2 as epileptic seizure creates clear spike activities that can be measured in standard EEG equipment [1], [2]. A clinical application of EEG is to show the type and location of the activity in the brain during a seizure. It is also commonly used to evaluate people who are having problems related to brain functionality such as coma, tumours, long-term memory loss, or stroke. In computer science, there have been many studies that focus on EEG applications for Brain Computer Interfaces (BCI). EEG data analysis has been explored for a better understanding of the information processing capability of the mammalian brain. EEG can also be potentially used in biometric systems. Given that the brain-wave pattern of every individual is unique, EEG can be used for developing person identification or authentication systems [3], [4]. Having in mind the importance of the accurate analysis and study of EEG signals, we are aiming in this paper to propose a method for EEG data transformation into spike trains and their accurate classification. The rest of the paper is structured as follows: Section 2 describes related researches and motivations. Section 3 presents the proposed methodology that is been used in this experimentation. Section 4 contains comparative experimental results along with discussions. Finally, Section 5 summarizes the conclusion and future directions of our study. 2 Related Works Spiking neuron networks (SNN) have been used for EEG analysis in some researches, and have shown remarkable performance in comparison to other traditional methods for classification task. In [5], the authors have proposed a method for the creation of spiking neural networks for EEG classification of epilepsy data for the purpose of epileptic seizure detection. Their experiment used a simple 3-layer feed-forward architecture (having input layer, hidden layer, output layer) which resulted in an average classification accuracy of approximately 90.7%. In a recent study [6], the researchers analysed rat s EEG data using reservoir computing approach (echo state network) for epileptic seizure detection in real-time, based on a data from 4 EEG channels. It is a two class problem, where they had to classify the EEG signals for detection of seizure and tonic-seizure. The reservoir was made of 200 Leaky Integrate-and Fire (LIF) neurons, where 20% and 80% of the EEG data was used for training and testing respectively. The results of this study claimed that the performance was higher than the other four traditional methods in terms of detection time, which was around 85% accuracy in 0.5 seconds for seizure and 85% accuracy in 3 seconds for tonic-seizure. However, this study was done by using EEG data from a rat, acquired from only 4 channels and the frequency for detecting seizure/s was known in advance (8, 16 and 24 Hz). Hence, recent studies on SNN and reservoir computing for EEG application shows that many of them produced comparatively good results while utilizing a deterministic neuronal model. However, in one of our recent work [7], we have shown that replacing the deterministic with the probabilistic spiking neuron models yields better results.

3 In this study we aim to analyze the feasibility of BSA spike encoding scheme along with a SNN reservoir such as LSM using probabilistic spiking neuron models for complex spatio-temporal human EEG data, acquired from 64 channels. In the following we have described the design of our experiment and its setup. 3 Methodology The framework for classification of spatio-temporal data based on evolving probabilistic spiking neural network reservoir (epsnnr) paradigm is presented in Fig.1. At first, each channel of spatial-temporal data (EEG) is transformed into trains of spikes by the encoder module. Then the trains of spikes are distributed into spatiotemporal filter which employs the latest reservoir paradigm (i.e. LSM) that utilizes several stochastic neuron models as liquid generators [7]. Further, the filter generates liquid state for each time step. These states are fed into a readout function for training and testing the classification performance using a pre-defined type of a classifier. Fig. 1. Framework for EEG spatio-temporal pattern learning and classification based on epsnnr. 3.1 Spike Encoder In our methodology we have incorporated BSA spike encoding scheme. So far, this encoding scheme has only been used for encoding sound data. However, since EEG signals also fall under the frequency domain, we hypothesised that BSA encoding will be suitable to transform EEG signals into spike representation. The key benefit of using BSA is that the frequency and amplitude features are smoother in comparison to the HSA (Hough Spiker Algorithm) spike encoding scheme [8]. Moreover, due to the smoother threshold optimization curve, it is also less susceptible to changes in the filter and the threshold [8]. Studies have shown that this method offers an improvement of 10dB-15dB over the HSA spike encoding scheme. According to [8], the stimulus is estimated from the spike train by

4 where, t k represents the neurons firing time, h(t) denotes the linear filters impulse response and x(t) is the spike of the neuron that can be calculated as For this particular dataset, we have set the Finite Impulse Response (FIR) filter size to 20, and the BSA threshold to Fig. 2. The top figure shows the Actual one channel EEG signal for the duration of 20ms. The middle figure is the spike representation of the above figure obtained using BSA. The bottom figure shows the actual one channel EEG signal that has been superimposed with another signal (dashed lines) which represents the reconstructed EEG signal from the BSA encoded spikes. The similarity between the two signals is obvious that illustrates the applicability of the BSA transformation. However, when the spike train x(t) is applied with a discrete FIR filter, the Eq.2 can be represented as

5 where, M refers to the number of filter taps. A more detailed explanation is given in [8]. 3.2 Evolving probabilistic spiking neuron network reservoir (epsnnr) In epsnnr, we have replaced the deterministic LIF neurons of a traditional LSM with probabilistic neural models that have been comprehensively described in [7]. The probabilistic approach has been inspired by biological neurons that exhibit substantial stochastic characteristics. Therefore, incorporation of non-deterministic elements into the neural model may provide us with advantage due to the brain-like information processing system. In our reservoir we have used the standard Leaky Integrate and Fire (LIF) neuron model as well as probabilistic models such as Noisy Reset (NR), Step-wise Noisy Threshold (ST) and Continuous Noisy Threshold (CT) (see fig.3. for an illustration of the difference between the three stochastic neuronal models). The advantage of stochastic neural models has been demonstrated in a previous study [7]. Table 1. The following table provides the parameter setting that has been used in our experimental setup for the epsnnr. 3.3 Dataset RIKEN EEG Dataset was collected in the RIKEN Brain Science Institute in Japan. It includes 4 stimulus conditions (4 classes): Class1 - Auditory stimulus; Class2 -Visual stimulus; Class3 - Mixed auditory and visual stimuli; Class4 -No stimulus. The EEG data were acquired using a 64 electrode EEG system that was filtered using a 0.05Hz to 500 Hz band- pass filter and sampled at 2KHz. According to the sample rate, the dataset is instable. In this preliminary proof of concept investigation we collected a small number of data points: 11 epochs from 50 epochs ( samples/epoch/50ms) of each class (4 classes are 44 epochs) which have closer rate as possible. We used 80% (9 epochs) and 20% (2 epochs) for training and testing respectively.

6 Fig. 3. Evolution of the post-synaptic potential u(t) and the firing threshold over time (blue (dark) and yellow (light) curves respectively recorded from a single neuron of each of the three stochastic neural models used in this paper vs the standard LIF model. The input stimulus for each neuron is shown at the top of the diagram. The output spikes of each neuron are shown as thick vertical lines above the corresponding threshold curve (from [7]) 4 Experiments and Discussions The experimental setup of this study is presented in Fig.1. All networks have the same network topology and the same connection weight matrix. A detailed description of the network generation and parameterisation is given in Table 1. We construct a reservoir having a small-world interconnectivity pattern as described in [9]. In order to make a standard comparison in our further investigation, the recurrent SNN is generated by using Brain[10] whose grid alignment is similar to the CSIM s (A neural Circuit Simulation) default LSM setting having 135 neurons in a three-dimensional grid of size In this grid, two neurons A and B are connected with a connection probability The sample rate of the EEG dataset is extremely higher than usual EEG datasets, where each epoch belonging to a class (having samples/epoch) was encoded into 50ms spike trains which are then transformed to 500ms, in order to normalise the parameters and simulation time steps. The liquid responses from the network, which are shown in fig.4, were mapped into 25ms time-bins (20 time bins/epoch). This particular setting resulted in an optimal accuracy for this experimental setup. There are two readout functions in this investigation. The first is none-adaptive Naivebayes whose Numeric estimator precision values are chosen based on analysis of the training data. The Second is Multi-Layered Perceptron(MLP) which utilizes 139 sigmoid nodes for hidden layer (number of input attributes plus 4 stimuli), 0.3 for learning rate, 0.2 for momentum, 500 training iterations, and validate threshold was set to 20.

7 In conventional method, parameters of Naivebayes and MLP were setup in the same way as the proposed method but MLP included only 68 sigmoid nodes for hidden layer (64 input plus 4 stimuli). The state time-bins from 1 st to 9 th epoch were used for training set (equivalent to 80%) and 10 th to 11 th epoch were used as test set. From table 2, it can be seen that the traditional classifiers do not perform optimally on the raw EEG data. However, when the raw EEG is applied with BSA spike encoder and is passed through epsnnr with various stochastic models and classifiers such as Naivebayes and MLP, they perform especially well. For our experiment we had considered various other classifiers but they were found to be inappropriate due to their inability to handle complex spatiotemporal EEG data. The accuracy obtained from epsnnr that utilizes Naivebayes have the same result for all the neuronal models, however the root mean squared error (RMSE) values (see Fig.5.) shows significant difference particularly for the ST model with Naivebayes, which is found to be the lowest, signifying the highest performance and stability in comparison with deterministic and other probabilistic models for this experiment. Our main results prove that transforming EEG signals into spike trains using the BSA spike encoding scheme results is significantly higher classification accuracy. A second result is that using a stochastic neuronal model in the epsnnr (e.g. the ST model) may lead to an improved accuracy (see the classification results for the MLP classifier from Table 2 and the root mean square error results from Fig.5). 5 Conclusion and Future Works In this study, we have shown that BSA spike encoding scheme is suitable for encoding EEG data stream. Moreover, we have also addressed the question whether probabilistic neural models are principally suitable liquids in the context of LSM. We have experimentally shown that, the performance of the epsnnr improves when a probabilistic model of a neuron is used, compared to the use of a deterministic LIF model of a neuron, and the classification performance of the EEG data in an epsnnr depends on the type of the probabilistic neuronal model used. The results suggest that an epsnnr can be optimised in terms of neuronal models used and parameters that would better match the noise and the dynamics of EEG data. Moreover, previous researches have had never incorporated 64 EEG channels. Our results have indicated potential advantages of using epsnnr along with the viability of BSA encoding scheme for EEG data streams that are spatio-temporal in nature which may contribute to BCI and medical studies. However, noise reduction and/or feature extraction methods, and optimization algorithm could also be employed possibly for both local and global optimization in our future study, since various parameters in the framework need to be adjusted. However, further study on the behavior of the epsnnr architecture under different conditions is needed and more experiments are required to be carried out on EEG datasets.

8 Fig. 4. The reservoir using ST Model response of one epoch of auditory stimulus is shown, where x axis represents time in 500ms and y axis is neurons. Table 2. The following table provides Classification Accuracy (%), for various methods. Several methods will be investigated for the improvement of the epsnnr: Using dynamic selection of the chunk of input data entered into the epsnnr; A new algorithm for an evolving (adaptive) learning in the epsnnr will be developed so that the reservoir learns to discriminate better states that represent different class data. Using more complex probabilistic spiking neuron models, such as [11], would require dynamic optimization of its probabilistic parameters. We intend to use a gene regulatory network (GRN) model to represent the dynamics of these parameters in relation to the dynamics of the spiking activity of the epsnnr as suggested in [12]. Each of the probability parameter, the decay parameter, the threshold and other parameters of the neurons, will be represented as a function of particular genes for a set of genes related to the epsnn model, all genes being linked together in a dynamic GRN model. Furthermore, various parameters such as the connection probability, size and shape of the network topology shall also be tested. In this respect the soft winnertake-all topology will be investigated [13]. For applications that require on line training we intend to use evolving SNN classifier [14], [15]. Finally, implementation

9 of the developed models on existing SNN hardware [16], [17] will be studied especially for on-line learning and object recognition applications such as intelligent mobile robots [18]. Fig. 5. This figure shows the Root Mean Squared Error (RMSE) for various stochastic neuron models when applied to Naivebayes and MLP classifiers. Acknowledgment The EEG data used in the experiments were collected in the RIKEN Brain Science Institute, Tokyo by a team lead by Case van Leuven and Andrjei Chihotsky. We developed a software simulator using the software environment Brian [18]. The work on this paper has been supported by the Knowledge Engineering and Discovery Research Institute (KEDRI, Auckland University of Technology. N.K. has been supported by a one year Marie Curie International Incoming Fellowship within the 7 th European Framework Programme under the project EvoSpike, hosted by the Institute for Neuroinformatics at the University of Zurich and ETH Zurich. References 1. Tatum, W.: Handbook of EEG interpretation. Demos Medical Publishing (2007) 2. Niedermeyer, E., Da Silva, F.: Electroencephalography: basic principles, clinical applications, and related fields. Lippincott Williams & Wilkins (2005) 3. Marcel, S., Mill an, J.: Person authentication using brainwaves (EEG) and maximum a posteriori model adaptation. IEEE transactions on pattern analysis and machine intelligence (2007) 4. Palaniappan, R., Mandic, D.: EEG based biometric framework for automatic identity verification. The Journal of VLSI Signal Processing 49(2) (2007)

10 5. Ghosh-Dastidar, S., Adeli, H.: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural networks 22(10) (2009) 6. Buteneers, P., Schrauwen, B., Verstraeten, D., Stroobandt, D.: Real-time epileptic seizure detection on intra-cranial rat data using reservoir computing. Advances in Neuro- Information Processing (2009) 7. Schliebs, S., Nuntalid, N., Kasabov, N.: Towards spatio-temporal pattern recognition using evolving spiking neural networks. Proceedings of the 17th international conference on Neural information processing: theory and algorithms-volume Part I, Springer-Verlag (2010) 8. Schrauwen, B., Van Campenhout, J.: BSA, a fast and accurate spike train encoding scheme. Proceedings of the International Joint Conference on Neural Networks. Volume 4., IEEE (2003) 9. Maass, W., Natschl ager, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural computation14(11) (2002) 10. Goodman, D., Brette, R.: The Brian simulator. Frontiers in Neuroscience 3(2) 192 (2009) 11. Kasabov, N.: To spike or not to spike: A probabilistic spiking neuron model. Neural Networks 23(1) (2010) 12. Kasabov,N. and R.Schliebs and H.Kojima : Probabilistic Computational Neurogenetic Framework: From Modelling Cognitive Systems to Alzheimer s Disease. IEEE Transactions on Autonomous Mental Development (2011) 13. Rutishauser, U., Douglas, R., Slotine, J.: Collective Stability of Networks of Winner- Take-All Circuits. Neural Computation 1 39 (2011) 14. Kasabov, N.: Evolving connectionist systems: the knowledge engineering approach. Springer-Verlag New York Inc (2007) 15. Schliebs, S., Kasabov, N., Defoin-Platel, M.: On the Probabilistic Optimization of Spiking Neural Networks. International Journal of Neural Systems 20(6) (2010) 16. Indiveri, G., Stefanini, F., Chicca, E.: Spike-based learning with a generalized integrate and fire silicon neuron. Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE (2010) 17. Indiveri, G., Chicca, E., Douglas, R.: Artificial cognitive systems: From vlsi networks of spiking neurons to neuromorphic cognition. Cognitive Computation 1(2) (2009) 18. Bellas, F., Duro, R., Faina, A., Souto, D.: Multilevel Darwinist Brain (MDB): Artificial Evolution in a Cognitive Architecture for Real Robots. IEEE Transactions on Autonomous Mental Development 2(4) (2010)

Nuttapod Nuntalid. A thesis submitted to. Auckland University of Technology. in fulfilment of the requirements for the degree of

Nuttapod Nuntalid. A thesis submitted to. Auckland University of Technology. in fulfilment of the requirements for the degree of Evolving Probabilistic Spiking Neural Networks for Modelling and Pattern Recognition of Spatio-temporal Data on the Case Study of Electroencephalography (EEG) Brain Data Nuttapod Nuntalid A thesis submitted

More information

Dynamic 3D Clustering of Spatio-Temporal Brain Data in the NeuCube Spiking Neural Network Architecture on a Case Study of fmri Data

Dynamic 3D Clustering of Spatio-Temporal Brain Data in the NeuCube Spiking Neural Network Architecture on a Case Study of fmri Data Dynamic 3D Clustering of Spatio-Temporal Brain Data in the NeuCube Spiking Neural Network Architecture on a Case Study of fmri Data Maryam Gholami Doborjeh (B) and Nikola Kasabov Knowledge Engineering

More information

arxiv: v1 [eess.sp] 27 Apr 2018

arxiv: v1 [eess.sp] 27 Apr 2018 CLASSIFICATION OF AUDITORY STIMULI FROM EEG SIGNALS WITH A REGULATED RECURRENT NEURAL NETWORK RESERVOIR Marc-Antoine Moinnereau 1,2, Thomas Brienne 1, Simon Brodeur 1, Jean Rouat 1, Kevin Whittingstall

More information

Spiking Inputs to a Winner-take-all Network

Spiking Inputs to a Winner-take-all Network Spiking Inputs to a Winner-take-all Network Matthias Oster and Shih-Chii Liu Institute of Neuroinformatics University of Zurich and ETH Zurich Winterthurerstrasse 9 CH-857 Zurich, Switzerland {mao,shih}@ini.phys.ethz.ch

More information

Recognition of English Characters Using Spiking Neural Networks

Recognition of English Characters Using Spiking Neural Networks Recognition of English Characters Using Spiking Neural Networks Amjad J. Humaidi #1, Thaer M. Kadhim *2 Control and System Engineering, University of Technology, Iraq, Baghdad 1 601116@uotechnology.edu.iq

More information

Realization of Visual Representation Task on a Humanoid Robot

Realization of Visual Representation Task on a Humanoid Robot Istanbul Technical University, Robot Intelligence Course Realization of Visual Representation Task on a Humanoid Robot Emeç Erçelik May 31, 2016 1 Introduction It is thought that human brain uses a distributed

More information

Applying Data Mining for Epileptic Seizure Detection

Applying Data Mining for Epileptic Seizure Detection Applying Data Mining for Epileptic Seizure Detection Ying-Fang Lai 1 and Hsiu-Sen Chiang 2* 1 Department of Industrial Education, National Taiwan Normal University 162, Heping East Road Sec 1, Taipei,

More information

Preparing More Effective Liquid State Machines Using Hebbian Learning

Preparing More Effective Liquid State Machines Using Hebbian Learning 2006 International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada July 16-21, 2006 Preparing More Effective Liquid State Machines Using Hebbian Learning

More information

Biceps Activity EMG Pattern Recognition Using Neural Networks

Biceps Activity EMG Pattern Recognition Using Neural Networks Biceps Activity EMG Pattern Recognition Using eural etworks K. Sundaraj University Malaysia Perlis (UniMAP) School of Mechatronic Engineering 0600 Jejawi - Perlis MALAYSIA kenneth@unimap.edu.my Abstract:

More information

Recurrent lateral inhibitory spiking networks for speech enhancement

Recurrent lateral inhibitory spiking networks for speech enhancement Recurrent lateral inhibitory spiking networks for speech enhancement Julie Wall University of East London j.wall@uel.ac.uk Cornelius Glackin neil.glackin@intelligentvoice.com Nigel Cannings nigel.cannings@intelligentvoice.com

More information

CHAPTER 6 INTERFERENCE CANCELLATION IN EEG SIGNAL

CHAPTER 6 INTERFERENCE CANCELLATION IN EEG SIGNAL 116 CHAPTER 6 INTERFERENCE CANCELLATION IN EEG SIGNAL 6.1 INTRODUCTION Electrical impulses generated by nerve firings in the brain pass through the head and represent the electroencephalogram (EEG). Electrical

More information

Detection and Plotting Real Time Brain Waves

Detection and Plotting Real Time Brain Waves Detection and Plotting Real Time Brain Waves Prof. M. M. PAL ME (ESC(CS) Department Of Computer Engineering Suresh Deshmukh College Of Engineering, Wardha Abstract - The human brain, either is in the state

More information

Noise Cancellation using Adaptive Filters Algorithms

Noise Cancellation using Adaptive Filters Algorithms Noise Cancellation using Adaptive Filters Algorithms Suman, Poonam Beniwal Department of ECE, OITM, Hisar, bhariasuman13@gmail.com Abstract Active Noise Control (ANC) involves an electro acoustic or electromechanical

More information

A Computational Biological Network for Wood Defect Classification

A Computational Biological Network for Wood Defect Classification A Computational Biological Network for Wood Defect Classification S. Shahnorbanun, S.A.Siti Nurul Huda, A. Haslina, O. Nazlia and H. Rosilah, Member IAENG Abstract Spiking Learning vector quantization

More information

Artificial Neural Networks in Cardiology - ECG Wave Analysis and Diagnosis Using Backpropagation Neural Networks

Artificial Neural Networks in Cardiology - ECG Wave Analysis and Diagnosis Using Backpropagation Neural Networks Artificial Neural Networks in Cardiology - ECG Wave Analysis and Diagnosis Using Backpropagation Neural Networks 1.Syed Khursheed ul Hasnain C Eng MIEE National University of Sciences & Technology, Pakistan

More information

Automatic Detection of Epileptic Seizures in EEG Using Machine Learning Methods

Automatic Detection of Epileptic Seizures in EEG Using Machine Learning Methods Automatic Detection of Epileptic Seizures in EEG Using Machine Learning Methods Ying-Fang Lai 1 and Hsiu-Sen Chiang 2* 1 Department of Industrial Education, National Taiwan Normal University 162, Heping

More information

Novel single trial movement classification based on temporal dynamics of EEG

Novel single trial movement classification based on temporal dynamics of EEG Novel single trial movement classification based on temporal dynamics of EEG Conference or Workshop Item Accepted Version Wairagkar, M., Daly, I., Hayashi, Y. and Nasuto, S. (2014) Novel single trial movement

More information

EEG signal classification using Bayes and Naïve Bayes Classifiers and extracted features of Continuous Wavelet Transform

EEG signal classification using Bayes and Naïve Bayes Classifiers and extracted features of Continuous Wavelet Transform EEG signal classification using Bayes and Naïve Bayes Classifiers and extracted features of Continuous Wavelet Transform Reza Yaghoobi Karimoi*, Mohammad Ali Khalilzadeh, Ali Akbar Hossinezadeh, Azra Yaghoobi

More information

arxiv: v1 [cs.lg] 4 Feb 2019

arxiv: v1 [cs.lg] 4 Feb 2019 Machine Learning for Seizure Type Classification: Setting the benchmark Subhrajit Roy [000 0002 6072 5500], Umar Asif [0000 0001 5209 7084], Jianbin Tang [0000 0001 5440 0796], and Stefan Harrer [0000

More information

Rolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press.

Rolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press. Digital Signal Processing and the Brain Is the brain a digital signal processor? Digital vs continuous signals Digital signals involve streams of binary encoded numbers The brain uses digital, all or none,

More information

Real-time inference in a VLSI spiking neural network

Real-time inference in a VLSI spiking neural network Real-time inference in a VLSI spiking neural network Dane Corneil, Daniel Sonnleithner, Emre Neftci, Elisabetta Chicca, Matthew Cook, Giacomo Indiveri, Rodney Douglas Institute of Neuroinformatics University

More information

Evolving, Dynamic Clustering of Spatio/Spectro-Temporal Data in 3D Spiking Neural Network Models and a Case Study on EEG Data

Evolving, Dynamic Clustering of Spatio/Spectro-Temporal Data in 3D Spiking Neural Network Models and a Case Study on EEG Data < Evolving Systems Journal > Evolving, Dynamic Clustering of Spatio/Spectro-Temporal Data in 3D Spiking Neural Network Models and a Case Study on EEG Data Maryam Gholami Doborjeh*, Nikola Kasabov, Zohreh

More information

Restoring Communication and Mobility

Restoring Communication and Mobility Restoring Communication and Mobility What are they? Artificial devices connected to the body that substitute, restore or supplement a sensory, cognitive, or motive function of the nervous system that has

More information

Error Detection based on neural signals

Error Detection based on neural signals Error Detection based on neural signals Nir Even- Chen and Igor Berman, Electrical Engineering, Stanford Introduction Brain computer interface (BCI) is a direct communication pathway between the brain

More information

Classification of People using Eye-Blink Based EOG Peak Analysis.

Classification of People using Eye-Blink Based EOG Peak Analysis. Classification of People using Eye-Blink Based EOG Peak Analysis. Andrews Samraj, Thomas Abraham and Nikos Mastorakis Faculty of Computer Science and Engineering, VIT University, Chennai- 48, India. Technical

More information

An Edge-Device for Accurate Seizure Detection in the IoT

An Edge-Device for Accurate Seizure Detection in the IoT An Edge-Device for Accurate Seizure Detection in the IoT M. A. Sayeed 1, S. P. Mohanty 2, E. Kougianos 3, and H. Zaveri 4 University of North Texas, Denton, TX, USA. 1,2,3 Yale University, New Haven, CT,

More information

Introduction to Computational Neuroscience

Introduction to Computational Neuroscience Introduction to Computational Neuroscience Lecture 5: Data analysis II Lesson Title 1 Introduction 2 Structure and Function of the NS 3 Windows to the Brain 4 Data analysis 5 Data analysis II 6 Single

More information

Introduction to Computational Neuroscience

Introduction to Computational Neuroscience Introduction to Computational Neuroscience Lecture 7: Network models Lesson Title 1 Introduction 2 Structure and Function of the NS 3 Windows to the Brain 4 Data analysis 5 Data analysis II 6 Single neuron

More information

A micropower support vector machine based seizure detection architecture for embedded medical devices

A micropower support vector machine based seizure detection architecture for embedded medical devices A micropower support vector machine based seizure detection architecture for embedded medical devices The MIT Faculty has made this article openly available. Please share how this access benefits you.

More information

EPILEPTIC SEIZURE DETECTION USING WAVELET TRANSFORM

EPILEPTIC SEIZURE DETECTION USING WAVELET TRANSFORM EPILEPTIC SEIZURE DETECTION USING WAVELET TRANSFORM Sneha R. Rathod 1, Chaitra B. 2, Dr. H.P.Rajani 3, Dr. Rajashri khanai 4 1 MTech VLSI Design and Embedded systems,dept of ECE, KLE Dr.MSSCET, Belagavi,

More information

A Brain Computer Interface System For Auto Piloting Wheelchair

A Brain Computer Interface System For Auto Piloting Wheelchair A Brain Computer Interface System For Auto Piloting Wheelchair Reshmi G, N. Kumaravel & M. Sasikala Centre for Medical Electronics, Dept. of Electronics and Communication Engineering, College of Engineering,

More information

OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION

OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION V. Shah, M. Golmohammadi, S. Ziyabari, E. Von Weltin, I. Obeid and J. Picone Neural Engineering Data Consortium, Temple University, Philadelphia, Pennsylvania,

More information

EEG-Based Classification of Upper-Limb ADL Using SNN for Active Robotic Rehabilitation*

EEG-Based Classification of Upper-Limb ADL Using SNN for Active Robotic Rehabilitation* 214 5th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) August 12-15, 214. São Paulo, Brazil EEG-Based Classification of Upper-Limb ADL Using SNN for Active

More information

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Longhao Yuan and Jianting Cao ( ) Graduate School of Engineering, Saitama Institute of Technology, Fusaiji 1690, Fukaya-shi,

More information

A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $

A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $ Neurocomputing 69 (26) 1327 1331 www.elsevier.com/locate/neucom A model to explain the emergence of reward expectancy neurons using reinforcement learning and neural network $ Shinya Ishii a,1, Munetaka

More information

Event Related Potentials: Significant Lobe Areas and Wave Forms for Picture Visual Stimulus

Event Related Potentials: Significant Lobe Areas and Wave Forms for Picture Visual Stimulus Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 6.017 IJCSMC,

More information

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence To understand the network paradigm also requires examining the history

More information

Introduction to Computational Neuroscience

Introduction to Computational Neuroscience Introduction to Computational Neuroscience Lecture 10: Brain-Computer Interfaces Ilya Kuzovkin So Far Stimulus So Far So Far Stimulus What are the neuroimaging techniques you know about? Stimulus So Far

More information

Selection of Feature for Epilepsy Seizer Detection Using EEG

Selection of Feature for Epilepsy Seizer Detection Using EEG International Journal of Neurosurgery 2018; 2(1): 1-7 http://www.sciencepublishinggroup.com/j/ijn doi: 10.11648/j.ijn.20180201.11 Selection of Feature for Epilepsy Seizer Detection Using EEG Manisha Chandani

More information

Reactive agents and perceptual ambiguity

Reactive agents and perceptual ambiguity Major theme: Robotic and computational models of interaction and cognition Reactive agents and perceptual ambiguity Michel van Dartel and Eric Postma IKAT, Universiteit Maastricht Abstract Situated and

More information

A general error-based spike-timing dependent learning rule for the Neural Engineering Framework

A general error-based spike-timing dependent learning rule for the Neural Engineering Framework A general error-based spike-timing dependent learning rule for the Neural Engineering Framework Trevor Bekolay Monday, May 17, 2010 Abstract Previous attempts at integrating spike-timing dependent plasticity

More information

Visual Motion Perception using Critical Branching Neural Computation

Visual Motion Perception using Critical Branching Neural Computation Visual Motion Perception using Critical Branching Neural Computation Janelle K. Szary (jszary@ucmerced.edu) Christopher T. Kello (ckello@ucmerced.edu) Cognitive and Information Science, 5200 North Lake

More information

Development of 2-Channel Eeg Device And Analysis Of Brain Wave For Depressed Persons

Development of 2-Channel Eeg Device And Analysis Of Brain Wave For Depressed Persons Development of 2-Channel Eeg Device And Analysis Of Brain Wave For Depressed Persons P.Amsaleka*, Dr.S.Mythili ** * PG Scholar, Applied Electronics, Department of Electronics and Communication, PSNA College

More information

A COMPETITIVE NETWORK OF SPIKING VLSI NEURONS

A COMPETITIVE NETWORK OF SPIKING VLSI NEURONS A COMPETITIVE NETWORK OF SPIKING VLSI NEURONS Indiveri G., Horiuchi T., Niebur, E., and Douglas, R. Institute of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland Computational Sensorimotor

More information

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience. Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing

More information

Genetic Algorithm based Feature Extraction for ECG Signal Classification using Neural Network

Genetic Algorithm based Feature Extraction for ECG Signal Classification using Neural Network Genetic Algorithm based Feature Extraction for ECG Signal Classification using Neural Network 1 R. Sathya, 2 K. Akilandeswari 1,2 Research Scholar 1 Department of Computer Science 1 Govt. Arts College,

More information

Epileptic seizure detection using EEG signals by means of stationary wavelet transforms

Epileptic seizure detection using EEG signals by means of stationary wavelet transforms I J C T A, 9(4), 2016, pp. 2065-2070 International Science Press Epileptic seizure detection using EEG signals by means of stationary wavelet transforms P. Grace Kanmani Prince 1, R. Rani Hemamalini 2,

More information

EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks

EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks Pari Jahankhani, Vassilis Kodogiannis and Kenneth Revett AbstractDecision Support Systems have been utilised since 196, providing

More information

Wavelet Neural Network for Classification of Bundle Branch Blocks

Wavelet Neural Network for Classification of Bundle Branch Blocks , July 6-8, 2011, London, U.K. Wavelet Neural Network for Classification of Bundle Branch Blocks Rahime Ceylan, Yüksel Özbay Abstract Bundle branch blocks are very important for the heart treatment immediately.

More information

Gender Based Emotion Recognition using Speech Signals: A Review

Gender Based Emotion Recognition using Speech Signals: A Review 50 Gender Based Emotion Recognition using Speech Signals: A Review Parvinder Kaur 1, Mandeep Kaur 2 1 Department of Electronics and Communication Engineering, Punjabi University, Patiala, India 2 Department

More information

Keywords: Adaptive Neuro-Fuzzy Interface System (ANFIS), Electrocardiogram (ECG), Fuzzy logic, MIT-BHI database.

Keywords: Adaptive Neuro-Fuzzy Interface System (ANFIS), Electrocardiogram (ECG), Fuzzy logic, MIT-BHI database. Volume 3, Issue 11, November 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Detection

More information

A Study of Smartphone Game Users through EEG Signal Feature Analysis

A Study of Smartphone Game Users through EEG Signal Feature Analysis , pp. 409-418 http://dx.doi.org/10.14257/ijmue.2014.9.11.39 A Study of Smartphone Game Users through EEG Signal Feature Analysis Jung-Yoon Kim Graduate School of Advanced Imaging Science, Multimedia &

More information

ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network

ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network International Journal of Electronics Engineering, 3 (1), 2011, pp. 55 58 ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network Amitabh Sharma 1, and Tanushree Sharma 2

More information

Simultaneous Real-Time Detection of Motor Imagery and Error-Related Potentials for Improved BCI Accuracy

Simultaneous Real-Time Detection of Motor Imagery and Error-Related Potentials for Improved BCI Accuracy Simultaneous Real-Time Detection of Motor Imagery and Error-Related Potentials for Improved BCI Accuracy P. W. Ferrez 1,2 and J. del R. Millán 1,2 1 IDIAP Research Institute, Martigny, Switzerland 2 Ecole

More information

CLASSIFICATION OF BRAIN TUMOUR IN MRI USING PROBABILISTIC NEURAL NETWORK

CLASSIFICATION OF BRAIN TUMOUR IN MRI USING PROBABILISTIC NEURAL NETWORK CLASSIFICATION OF BRAIN TUMOUR IN MRI USING PROBABILISTIC NEURAL NETWORK PRIMI JOSEPH (PG Scholar) Dr.Pauls Engineering College Er.D.Jagadiswary Dr.Pauls Engineering College Abstract: Brain tumor is an

More information

Classification of EEG signals in an Object Recognition task

Classification of EEG signals in an Object Recognition task Classification of EEG signals in an Object Recognition task Iacob D. Rus, Paul Marc, Mihaela Dinsoreanu, Rodica Potolea Technical University of Cluj-Napoca Cluj-Napoca, Romania 1 rus_iacob23@yahoo.com,

More information

Mike Davies Director, Neuromorphic Computing Lab Intel Labs

Mike Davies Director, Neuromorphic Computing Lab Intel Labs Mike Davies Director, Neuromorphic Computing Lab Intel Labs Loihi at a Glance Key Properties Integrated Memory + Compute Neuromorphic Architecture 128 neuromorphic cores supporting up to 128k neurons and

More information

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical

More information

Recursive Least Squares for Echo State Network Damage Compensation

Recursive Least Squares for Echo State Network Damage Compensation Recursive Least Squares for Echo State Network Damage Compensation Daniel Dean d.p.dean@pgr.reading.ac.uk Prof. Slawomir Nasuto s.j.nasuto@reading.ac.uk School of Systems Engineering, University Of Reading,

More information

PCA Enhanced Kalman Filter for ECG Denoising

PCA Enhanced Kalman Filter for ECG Denoising IOSR Journal of Electronics & Communication Engineering (IOSR-JECE) ISSN(e) : 2278-1684 ISSN(p) : 2320-334X, PP 06-13 www.iosrjournals.org PCA Enhanced Kalman Filter for ECG Denoising Febina Ikbal 1, Prof.M.Mathurakani

More information

Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks

Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks Priyadarshini Panda, Gopalakrishnan Srinivasan and Kaushik Roy School of Electrical and Computer Engineering,

More information

HST 583 fmri DATA ANALYSIS AND ACQUISITION

HST 583 fmri DATA ANALYSIS AND ACQUISITION HST 583 fmri DATA ANALYSIS AND ACQUISITION Neural Signal Processing for Functional Neuroimaging Neuroscience Statistics Research Laboratory Massachusetts General Hospital Harvard Medical School/MIT Division

More information

Minimum Feature Selection for Epileptic Seizure Classification using Wavelet-based Feature Extraction and a Fuzzy Neural Network

Minimum Feature Selection for Epileptic Seizure Classification using Wavelet-based Feature Extraction and a Fuzzy Neural Network Appl. Math. Inf. Sci. 8, No. 3, 129-1300 (201) 129 Applied Mathematics & Information Sciences An International Journal http://dx.doi.org/10.1278/amis/0803 Minimum Feature Selection for Epileptic Seizure

More information

Analysis of in-vivo extracellular recordings. Ryan Morrill Bootcamp 9/10/2014

Analysis of in-vivo extracellular recordings. Ryan Morrill Bootcamp 9/10/2014 Analysis of in-vivo extracellular recordings Ryan Morrill Bootcamp 9/10/2014 Goals for the lecture Be able to: Conceptually understand some of the analysis and jargon encountered in a typical (sensory)

More information

Optimal preictal period in seizure prediction

Optimal preictal period in seizure prediction Optimal preictal period in seizure prediction Mojtaba Bandarabadi, Jalil Rasekhi, Cesar A. Teixeira, António Dourado CISUC/DEI, Center for Informatics and Systems of the University of Coimbra, Department

More information

Modeling of Hippocampal Behavior

Modeling of Hippocampal Behavior Modeling of Hippocampal Behavior Diana Ponce-Morado, Venmathi Gunasekaran and Varsha Vijayan Abstract The hippocampus is identified as an important structure in the cerebral cortex of mammals for forming

More information

TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING

TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING 134 TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING H.F.S.M.Fonseka 1, J.T.Jonathan 2, P.Sabeshan 3 and M.B.Dissanayaka 4 1 Department of Electrical And Electronic Engineering, Faculty

More information

Sound Quality Evaluation of Hermetic Compressors Using Artificial Neural Networks

Sound Quality Evaluation of Hermetic Compressors Using Artificial Neural Networks Purdue University Purdue e-pubs International Compressor Engineering Conference School of Mechanical Engineering 2006 Sound Quality Evaluation of Hermetic Compressors Using Artificial Neural Networks Claudio

More information

FIR filter bank design for Audiogram Matching

FIR filter bank design for Audiogram Matching FIR filter bank design for Audiogram Matching Shobhit Kumar Nema, Mr. Amit Pathak,Professor M.Tech, Digital communication,srist,jabalpur,india, shobhit.nema@gmail.com Dept.of Electronics & communication,srist,jabalpur,india,

More information

International Journal of Advanced Computer Technology (IJACT)

International Journal of Advanced Computer Technology (IJACT) Abstract An Introduction to Third Generation of Neural Networks for Edge Detection Being inspired by the structure and behavior of the human visual system the spiking neural networks for edge detection

More information

Neuromorphic computing

Neuromorphic computing Neuromorphic computing Robotics M.Sc. programme in Computer Science lorenzo.vannucci@santannapisa.it April 19th, 2018 Outline 1. Introduction 2. Fundamentals of neuroscience 3. Simulating the brain 4.

More information

VALIDATION OF AN AUTOMATED SEIZURE DETECTION SYSTEM ON HEALTHY BABIES Histogram-based Energy Normalization for Montage Mismatch Compensation

VALIDATION OF AN AUTOMATED SEIZURE DETECTION SYSTEM ON HEALTHY BABIES Histogram-based Energy Normalization for Montage Mismatch Compensation VALIDATION OF AN AUTOMATED SEIZURE DETECTION SYSTEM ON HEALTHY BABIES Histogram-based Energy Normalization for Montage Mismatch Compensation A. Temko 1, I. Korotchikova 2, W. Marnane 1, G. Lightbody 1

More information

Automatic Detection of Heart Disease Using Discreet Wavelet Transform and Artificial Neural Network

Automatic Detection of Heart Disease Using Discreet Wavelet Transform and Artificial Neural Network e-issn: 2349-9745 p-issn: 2393-8161 Scientific Journal Impact Factor (SJIF): 1.711 International Journal of Modern Trends in Engineering and Research www.ijmter.com Automatic Detection of Heart Disease

More information

Spontaneous Cortical Activity Reveals Hallmarks of an Optimal Internal Model of the Environment. Berkes, Orban, Lengyel, Fiser.

Spontaneous Cortical Activity Reveals Hallmarks of an Optimal Internal Model of the Environment. Berkes, Orban, Lengyel, Fiser. Statistically optimal perception and learning: from behavior to neural representations. Fiser, Berkes, Orban & Lengyel Trends in Cognitive Sciences (2010) Spontaneous Cortical Activity Reveals Hallmarks

More information

Task 1: Machine Learning with Spike-Timing-Dependent Plasticity (STDP)

Task 1: Machine Learning with Spike-Timing-Dependent Plasticity (STDP) DARPA Report Task1 for Year 1 (Q1-Q4) Task 1: Machine Learning with Spike-Timing-Dependent Plasticity (STDP) 1. Shortcomings of the deep learning approach to artificial intelligence It has been established

More information

NIH Public Access Author Manuscript Conf Proc IEEE Eng Med Biol Soc. Author manuscript; available in PMC 2010 January 1.

NIH Public Access Author Manuscript Conf Proc IEEE Eng Med Biol Soc. Author manuscript; available in PMC 2010 January 1. NIH Public Access Author Manuscript Published in final edited form as: Conf Proc IEEE Eng Med Biol Soc. 2009 ; 1: 4719 4722. doi:10.1109/iembs.2009.5334195. Estimation of Brain State Changes Associated

More information

Using stigmergy to incorporate the time into artificial neural networks

Using stigmergy to incorporate the time into artificial neural networks Using stigmergy to incorporate the time into artificial neural networks Federico A. Galatolo, Mario G.C.A. Cimino, and Gigliola Vaglini Department of Information Engineering, University of Pisa, 56122

More information

Energy of Brain Potentials Evoked During Visual Stimulus: A New Biometric?

Energy of Brain Potentials Evoked During Visual Stimulus: A New Biometric? Energy of Brain Potentials Evoked During Visual Stimulus: A New Biometric? Ramaswamy Palaniappan 1 and Danilo P. Mandic 2 1 Department of Computer Science, University of Essex, Colchester, United Kingdom

More information

Adaptive Treatment of Epilepsy via Batch Mode Reinforcement Learning

Adaptive Treatment of Epilepsy via Batch Mode Reinforcement Learning Adaptive Treatment of Epilepsy via Batch Mode Reinforcement Learning Arthur Guez, Robert D. Vincent and Joelle Pineau School of Computer Science, McGill University Massimo Avoli Montreal Neurological Institute

More information

A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery

A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery RESEARCH ARTICLE A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery Ewan S. Nurse 1,2 *, Philippa J. Karoly 1,2,3, David B. Grayden 1,2, Dean R. Freestone 1,2,3,4

More information

Evolving, Probabilistic Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition

Evolving, Probabilistic Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition Regular Paper Evolving, Probabilistic Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition Nikola Kasabov, FIEEE, FRSNZ Knowledge Engineering

More information

ANALYSIS AND CLASSIFICATION OF EEG SIGNALS. A Dissertation Submitted by. Siuly. Doctor of Philosophy

ANALYSIS AND CLASSIFICATION OF EEG SIGNALS. A Dissertation Submitted by. Siuly. Doctor of Philosophy UNIVERSITY OF SOUTHERN QUEENSLAND, AUSTRALIA ANALYSIS AND CLASSIFICATION OF EEG SIGNALS A Dissertation Submitted by Siuly For the Award of Doctor of Philosophy July, 2012 Abstract Electroencephalography

More information

Prediction of Diabetes by using Artificial Neural Network

Prediction of Diabetes by using Artificial Neural Network 2011 International Conference on Circuits, System and Simulation IPCSIT vol.7 (2011) (2011) IACSIT Press, Singapore Prediction of Diabetes by using Artificial Neural Network Muhammad Akmal Sapon 1, Khadijah

More information

LIE DETECTION SYSTEM USING INPUT VOICE SIGNAL K.Meena 1, K.Veena 2 (Corresponding Author: K.Veena) 1 Associate Professor, 2 Research Scholar,

LIE DETECTION SYSTEM USING INPUT VOICE SIGNAL K.Meena 1, K.Veena 2 (Corresponding Author: K.Veena) 1 Associate Professor, 2 Research Scholar, International Journal of Pure and Applied Mathematics Volume 117 No. 8 2017, 121-125 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu doi: 10.12732/ijpam.v117i8.25

More information

The 29th Fuzzy System Symposium (Osaka, September 9-, 3) Color Feature Maps (BY, RG) Color Saliency Map Input Image (I) Linear Filtering and Gaussian

The 29th Fuzzy System Symposium (Osaka, September 9-, 3) Color Feature Maps (BY, RG) Color Saliency Map Input Image (I) Linear Filtering and Gaussian The 29th Fuzzy System Symposium (Osaka, September 9-, 3) A Fuzzy Inference Method Based on Saliency Map for Prediction Mao Wang, Yoichiro Maeda 2, Yasutake Takahashi Graduate School of Engineering, University

More information

Information Processing During Transient Responses in the Crayfish Visual System

Information Processing During Transient Responses in the Crayfish Visual System Information Processing During Transient Responses in the Crayfish Visual System Christopher J. Rozell, Don. H. Johnson and Raymon M. Glantz Department of Electrical & Computer Engineering Department of

More information

DISCRETE WAVELET PACKET TRANSFORM FOR ELECTROENCEPHALOGRAM- BASED EMOTION RECOGNITION IN THE VALENCE-AROUSAL SPACE

DISCRETE WAVELET PACKET TRANSFORM FOR ELECTROENCEPHALOGRAM- BASED EMOTION RECOGNITION IN THE VALENCE-AROUSAL SPACE DISCRETE WAVELET PACKET TRANSFORM FOR ELECTROENCEPHALOGRAM- BASED EMOTION RECOGNITION IN THE VALENCE-AROUSAL SPACE Farzana Kabir Ahmad*and Oyenuga Wasiu Olakunle Computational Intelligence Research Cluster,

More information

University of California Postprints

University of California Postprints University of California Postprints Year 2006 Paper 2444 Analysis of early hypoxia EEG based on a novel chaotic neural network M Hu G Li J J. Li Walter J. Freeman University of California, Berkeley M Hu,

More information

Temporal Adaptation. In a Silicon Auditory Nerve. John Lazzaro. CS Division UC Berkeley 571 Evans Hall Berkeley, CA

Temporal Adaptation. In a Silicon Auditory Nerve. John Lazzaro. CS Division UC Berkeley 571 Evans Hall Berkeley, CA Temporal Adaptation In a Silicon Auditory Nerve John Lazzaro CS Division UC Berkeley 571 Evans Hall Berkeley, CA 94720 Abstract Many auditory theorists consider the temporal adaptation of the auditory

More information

Automatic Definition of Planning Target Volume in Computer-Assisted Radiotherapy

Automatic Definition of Planning Target Volume in Computer-Assisted Radiotherapy Automatic Definition of Planning Target Volume in Computer-Assisted Radiotherapy Angelo Zizzari Department of Cybernetics, School of Systems Engineering The University of Reading, Whiteknights, PO Box

More information

Heterogeneous networks of spiking neurons: self-sustained activity and excitability

Heterogeneous networks of spiking neurons: self-sustained activity and excitability Heterogeneous networks of spiking neurons: self-sustained activity and excitability Cristina Savin 1,2, Iosif Ignat 1, Raul C. Mureşan 2,3 1 Technical University of Cluj Napoca, Faculty of Automation and

More information

Supplementary materials for: Executive control processes underlying multi- item working memory

Supplementary materials for: Executive control processes underlying multi- item working memory Supplementary materials for: Executive control processes underlying multi- item working memory Antonio H. Lara & Jonathan D. Wallis Supplementary Figure 1 Supplementary Figure 1. Behavioral measures of

More information

SOLUTIONS Homework #3. Introduction to Engineering in Medicine and Biology ECEN 1001 Due Tues. 9/30/03

SOLUTIONS Homework #3. Introduction to Engineering in Medicine and Biology ECEN 1001 Due Tues. 9/30/03 SOLUTIONS Homework #3 Introduction to Engineering in Medicine and Biology ECEN 1001 Due Tues. 9/30/03 Problem 1: a) Where in the cochlea would you say the process of "fourier decomposition" of the incoming

More information

Automated System for Detecting Neonatal Brain Injuries

Automated System for Detecting Neonatal Brain Injuries Snapshots of Postgraduate Research at University College Cork 2016 Automated System for Detecting Neonatal Brain Injuries Rehan Ahmed Dept. of Electrical and Electronics Engineering,, UCC The most dangerous

More information

A Deep Learning Approach to Identify Diabetes

A Deep Learning Approach to Identify Diabetes , pp.44-49 http://dx.doi.org/10.14257/astl.2017.145.09 A Deep Learning Approach to Identify Diabetes Sushant Ramesh, Ronnie D. Caytiles* and N.Ch.S.N Iyengar** School of Computer Science and Engineering

More information

Local Image Structures and Optic Flow Estimation

Local Image Structures and Optic Flow Estimation Local Image Structures and Optic Flow Estimation Sinan KALKAN 1, Dirk Calow 2, Florentin Wörgötter 1, Markus Lappe 2 and Norbert Krüger 3 1 Computational Neuroscience, Uni. of Stirling, Scotland; {sinan,worgott}@cn.stir.ac.uk

More information

Seizure Prediction Through Clustering and Temporal Analysis of Micro Electrocorticographic Data

Seizure Prediction Through Clustering and Temporal Analysis of Micro Electrocorticographic Data Seizure Prediction Through Clustering and Temporal Analysis of Micro Electrocorticographic Data Yilin Song 1, Jonathan Viventi 2, and Yao Wang 1 1 Department of Electrical and Computer Engineering, New

More information

Spatiotemporal clustering of synchronized bursting events in neuronal networks

Spatiotemporal clustering of synchronized bursting events in neuronal networks Spatiotemporal clustering of synchronized bursting events in neuronal networks Uri Barkan a David Horn a,1 a School of Physics and Astronomy, Tel Aviv University, Tel Aviv 69978, Israel Abstract in vitro

More information

Evidence-Based Filters for Signal Detection: Application to Evoked Brain Responses

Evidence-Based Filters for Signal Detection: Application to Evoked Brain Responses Evidence-Based Filters for Signal Detection: Application to Evoked Brain Responses M. Asim Mubeen a, Kevin H. Knuth a,b,c a Knuth Cyberphysics Lab, Department of Physics, University at Albany, Albany NY,

More information