Search results for: automatic speech recognition
1117 MarginDistillation: Distillation for Face Recognition Neural Networks with Margin-Based Softmax
Authors: Svitov David, Alyamkin Sergey
Abstract:
The usage of convolutional neural networks (CNNs) in conjunction with the margin-based softmax approach demonstrates the state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and face embeddings predicted by the teacher network.Keywords: ArcFace, distillation, face recognition, margin-based softmax.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6101116 Automatic Verification Technology of Virtual Machine Software Patch on IaaS Cloud
Authors: Yoji Yamato
Abstract:
In this paper, we propose an automatic verification technology of software patches for user virtual environments on IaaS Cloud to decrease verification costs of patches. In these days, IaaS services have been spread and many users can customize virtual machines on IaaS Cloud like their own private servers. Regarding to software patches of OS or middleware installed on virtual machines, users need to adopt and verify these patches by themselves. This task increases operation costs of users. Our proposed method replicates user virtual environments, extracts verification test cases for user virtual environments from test case DB, distributes patches to virtual machines on replicated environments and conducts those test cases automatically on replicated environments. We have implemented the proposed method on OpenStack using Jenkins and confirmed the feasibility. Using the implementation, we confirmed the effectiveness of test case creation efforts by our proposed idea of 2-tier abstraction of software functions and test cases. We also evaluated the automatic verification performance of environment replications, test cases extractions and test cases conductions.
Keywords: OpenStack, Cloud Computing, Automatic verification, Jenkins.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21581115 Generator Damage Recognition Based on Artificial Neural Network
Authors: Chang-Hung Hsu, Chun-Yao Lee, Guan-Lin Liao, Yung-Tsan Jou, Jin-Maun Ho, Yu-Hua Hsieh, Yi-Xing Shen
Abstract:
This article simulates the wind generator set which has two fault bearing collar rail destruction and the gear box oil leak fault. The electric current signal which produced by the generator, We use Empirical Mode Decomposition (EMD) as well as Fast Fourier Transform (FFT) obtains the frequency range-s signal figure and characteristic value. The last step is use a kind of Artificial Neural Network (ANN) classifies which determination fault signal's type and reason. The ANN purpose of the automatic identification wind generator set fault..Keywords: Wind-driven generator, Fast Fourier Transform, Neural network
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17481114 The Modified Eigenface Method using Two Thresholds
Authors: Yan Ma, ShunBao Li
Abstract:
A new approach is adopted in this paper based on Turk and Pentland-s eigenface method. It was found that the probability density function of the distance between the projection vector of the input face image and the average projection vector of the subject in the face database, follows Rayleigh distribution. In order to decrease the false acceptance rate and increase the recognition rate, the input face image has been recognized using two thresholds including the acceptance threshold and the rejection threshold. We also find out that the value of two thresholds will be close to each other as number of trials increases. During the training, in order to reduce the number of trials, the projection vectors for each subject has been averaged. The recognition experiments using the proposed algorithm show that the recognition rate achieves to 92.875% whilst the average number of judgment is only 2.56 times.Keywords: Eigenface, Face Recognition, Threshold, Rayleigh Distribution, Feature Extraction
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14791113 Influence of Loudness Compression on Hearing with Bone Anchored Hearing Implants
Authors: Anja Kurz, Marc Flynn, Tobias Good, Marco Caversaccio, Martin Kompis
Abstract:
Bone Anchored Hearing Implants (BAHI) are routinely used in patients with conductive or mixed hearing loss, e.g. if conventional air conduction hearing aids cannot be used. New sound processors and new fitting software now allow the adjustment of parameters such as loudness compression ratios or maximum power output separately. Today it is unclear, how the choice of these parameters influences aided speech understanding in BAHI users. In this prospective experimental study, the effect of varying the compression ratio and lowering the maximum power output in a BAHI were investigated. Twelve experienced adult subjects with a mixed hearing loss participated in this study. Four different compression ratios (1.0; 1.3; 1.6; 2.0) were tested along with two different maximum power output settings, resulting in a total of eight different programs. Each participant tested each program during two weeks. A blinded Latin square design was used to minimize bias. For each of the eight programs, speech understanding in quiet and in noise was assessed. For speech in quiet, the Freiburg number test and the Freiburg monosyllabic word test at 50, 65, and 80 dB SPL were used. For speech in noise, the Oldenburg sentence test was administered. Speech understanding in quiet and in noise was improved significantly in the aided condition in any program, when compared to the unaided condition. However, no significant differences were found between any of the eight programs. In contrast, on a subjective level there was a significant preference for medium compression ratios of 1.3 to 1.6 and higher maximum power output.
Keywords: Bone Anchored Hearing Implant, Compression, Maximum Power Output, Speech understanding.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20451112 Vision Based Hand Gesture Recognition Using Generative and Discriminative Stochastic Models
Authors: Mahmoud Elmezain, Samar El-shinawy
Abstract:
Many approaches to pattern recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features. Generative and discriminative models have very different characteristics, as well as complementary strengths and weaknesses. In this paper, we study these models to recognize the patterns of alphabet characters (A-Z) and numbers (0-9). To handle isolated pattern, generative model as Hidden Markov Model (HMM) and discriminative models like Conditional Random Field (CRF), Hidden Conditional Random Field (HCRF) and Latent-Dynamic Conditional Random Field (LDCRF) with different number of window size are applied on extracted pattern features. The gesture recognition rate is improved initially as the window size increase, but degrades as window size increase further. Experimental results show that the LDCRF is the best in terms of results than CRF, HCRF and HMM at window size equal 4. Additionally, our results show that; an overall recognition rates are 91.52%, 95.28%, 96.94% and 98.05% for CRF, HCRF, HMM and LDCRF respectively.
Keywords: Statistical Pattern Recognition, Generative Model, Discriminative Model, Human Computer Interaction.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 29151111 Rapid Study on Feature Extraction and Classification Models in Healthcare Applications
Authors: S. Sowmyayani
Abstract:
The advancement of computer-aided design helps the medical force and security force. Some applications include biometric recognition, elderly fall detection, face recognition, cancer recognition, tumor recognition, etc. This paper deals with different machine learning algorithms that are more generically used for any health care system. The most focused problems are classification and regression. With the rise of big data, machine learning has become particularly important for solving problems. Machine learning uses two types of techniques: supervised learning and unsupervised learning. The former trains a model on known input and output data and predicts future outputs. Classification and regression are supervised learning techniques. Unsupervised learning finds hidden patterns in input data. Clustering is one such unsupervised learning technique. The above-mentioned models are discussed briefly in this paper.
Keywords: Supervised learning, unsupervised learning, regression, neural network.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3261110 Comparison of Fricative Vocal Tract Transfer Functions Derived using Two Different Segmentation Techniques
Authors: K. S. Subari, C. H. Shadle, A. Barney, R. I. Damper
Abstract:
The acoustic and articulatory properties of fricative speech sounds are being studied using magnetic resonance imaging (MRI) and acoustic recordings from a single subject. Area functions were derived from a complete set of axial and coronal MR slices using two different methods: the Mermelstein technique and the Blum transform. Area functions derived from the two techniques were shown to differ significantly in some cases. Such differences will lead to different acoustic predictions and it is important to know which is the more accurate. The vocal tract acoustic transfer function (VTTF) was derived from these area functions for each fricative and compared with measured speech signals for the same fricative and same subject. The VTTFs for /f/ in two vowel contexts and the corresponding acoustic spectra are derived here; the Blum transform appears to show a better match between prediction and measurement than the Mermelstein technique.
Keywords: Area functions, fricatives, vocal tract transferfunction, MRI, speech.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16421109 Kurtosis, Renyi's Entropy and Independent Component Scalp Maps for the Automatic Artifact Rejection from EEG Data
Authors: Antonino Greco, Nadia Mammone, Francesco Carlo Morabito, Mario Versaci
Abstract:
The goal of this work is to improve the efficiency and the reliability of the automatic artifact rejection, in particular from the Electroencephalographic (EEG) recordings. Artifact rejection is a key topic in signal processing. The artifacts are unwelcome signals that may occur during the signal acquisition and that may alter the analysis of the signals themselves. A technique for the automatic artifact rejection, based on the Independent Component Analysis (ICA) for the artifact extraction and on some high order statistics such as kurtosis and Shannon-s entropy, was proposed some years ago in literature. In this paper we enhance this technique introducing the Renyi-s entropy. The performance of our method was tested exploiting the Independent Component scalp maps and it was compared to the performance of the method in literature and it showed to outperform it.
Keywords: Artifact, EEG, Renyi's entropy, independent component analysis, kurtosis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 24171108 BIP-Based Alarm Declaration and Clearing in SONET Networks Employing Automatic Protection Switching
Authors: Vitalice K. Oduol, C. Ardil
Abstract:
The paper examines the performance of bit-interleaved parity (BIP) methods in error rate monitoring, and in declaration and clearing of alarms in those transport networks that employ automatic protection switching (APS). The BIP-based error rate monitoring is attractive for its simplicity and ease of implementation. The BIP-based results are compared with exact results and are found to declare the alarms too late, and to clear the alarms too early. It is concluded that the standards development and systems implementation should take into account the fact of early clearing and late declaration of alarms. The window parameters defining the detection and clearing thresholds should be set so as to build sufficient hysteresis into the system to ensure that BIP-based implementations yield acceptable performance results.
Keywords: Automatic protection switching, bit interleaved parity, excessive bit error rate
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18841107 Integration of Acceleration Feedback Control with Automatic Generation Control in Intelligent Load Frequency Control
Authors: H. Zainuddin, F. Hanafi, M. H. Hairi, A. Aman, M.H.N. Talib
Abstract:
This paper investigates the effects of knowledge-based acceleration feedback control integrated with Automatic Generation Control (AGC) to enhance the quality of frequency control of governing system. The Intelligent Acceleration Feedback Controller (IAFC) is proposed to counter the over and under frequency occurrences due to major load change in power system network. Therefore, generator tripping and load shedding operations can be reduced. Meanwhile, the integration of IAFC with AGC, a well known Load-Frequency Control (LFC) is essential to ensure the system frequency is restored to the nominal value. Computer simulations of frequency response of governing system are used to optimize the parameters of IAFC. As a result, there is substantial improvement on the LFC of governing system that employing the proposed control strategy.
Keywords: Knowledge-based Supplementary Control, Acceleration Feedback, Load Frequency Control, Automatic Generation Control.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16901106 On-line Lao Handwritten Recognition with Proportional Invariant Feature
Authors: Khampheth Bounnady, Boontee Kruatrachue, Somkiat Wangsiripitak
Abstract:
This paper proposed high level feature for online Lao handwritten recognition. This feature must be high level enough so that the feature is not change when characters are written by different persons at different speed and different proportion (shorter or longer stroke, head, tail, loop, curve). In this high level feature, a character is divided in to sequence of curve segments where a segment start where curve reverse rotation (counter clockwise and clockwise). In each segment, following features are gathered cumulative change in direction of curve (- for clockwise), cumulative curve length, cumulative length of left to right, right to left, top to bottom and bottom to top ( cumulative change in X and Y axis of segment). This feature is simple yet robust for high accuracy recognition. The feature can be gather from parsing the original time sampling sequence X, Y point of the pen location without re-sampling. We also experiment on other segmentation point such as the maximum curvature point which was widely used by other researcher. Experiments results show that the recognition rates are at 94.62% in comparing to using maximum curvature point 75.07%. This is due to a lot of variations of turning points in handwritten.
Keywords: Handwritten feature, chain code, Lao handwritten recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20231105 Control Chart Pattern Recognition Using Wavelet Based Neural Networks
Authors: Jun Seok Kim, Cheong-Sool Park, Jun-Geol Baek, Sung-Shick Kim
Abstract:
Control chart pattern recognition is one of the most important tools to identify the process state in statistical process control. The abnormal process state could be classified by the recognition of unnatural patterns that arise from assignable causes. In this study, a wavelet based neural network approach is proposed for the recognition of control chart patterns that have various characteristics. The procedure of proposed control chart pattern recognizer comprises three stages. First, multi-resolution wavelet analysis is used to generate time-shape and time-frequency coefficients that have detail information about the patterns. Second, distance based features are extracted by a bi-directional Kohonen network to make reduced and robust information. Third, a back-propagation network classifier is trained by these features. The accuracy of the proposed method is shown by the performance evaluation with numerical results.
Keywords: Control chart pattern recognition, Multi-resolution wavelet analysis, Bi-directional Kohonen network, Back-propagation network, Feature extraction.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 24661104 Local Spectrum Feature Extraction for Face Recognition
Authors: Muhammad Imran Ahmad, Ruzelita Ngadiran, Mohd Nazrin Md Isa, Nor Ashidi Mat Isa, Mohd Zaizu Ilyas, Raja Abdullah Raja Ahmad, Said Amirul Anwar Ab Hamid, Muzammil Jusoh
Abstract:
This paper presents two techniques, local feature extraction using image spectrum and low frequency spectrum modelling using GMM to capture the underlying statistical information to improve the performance of face recognition system. Local spectrum features are extracted using overlap sub block window that are mapped on the face image. For each of this block, spatial domain is transformed to frequency domain using DFT. A low frequency coefficient is preserved by discarding high frequency coefficients by applying rectangular mask on the spectrum of the facial image. Low frequency information is non- Gaussian in the feature space and by using combination of several Gaussian functions that has different statistical properties, the best feature representation can be modelled using probability density function. The recognition process is performed using maximum likelihood value computed using pre-calculated GMM components. The method is tested using FERET datasets and is able to achieved 92% recognition rates.
Keywords: Local features modelling, face recognition system, Gaussian mixture models.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22391103 A Simple Adaptive Atomic Decomposition Voice Activity Detector Implemented by Matching Pursuit
Authors: Thomas Bryan, Veton Kepuska, Ivica Kostanic
Abstract:
A simple adaptive voice activity detector (VAD) is implemented using Gabor and gammatone atomic decomposition of speech for high Gaussian noise environments. Matching pursuit is used for atomic decomposition, and is shown to achieve optimal speech detection capability at high data compression rates for low signal to noise ratios. The most active dictionary elements found by matching pursuit are used for the signal reconstruction so that the algorithm adapts to the individual speakers dominant time-frequency characteristics. Speech has a high peak to average ratio enabling matching pursuit greedy heuristic of highest inner products to isolate high energy speech components in high noise environments. Gabor and gammatone atoms are both investigated with identical logarithmically spaced center frequencies, and similar bandwidths. The algorithm performs equally well for both Gabor and gammatone atoms with no significant statistical differences. The algorithm achieves 70% accuracy at a 0 dB SNR, 90% accuracy at a 5 dB SNR and 98% accuracy at a 20dB SNR using 30d B SNR as a reference for voice activity.Keywords: Atomic Decomposition, Gabor, Gammatone, Matching Pursuit, Voice Activity Detection.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17811102 Hybrid Method Using Wavelets and Predictive Method for Compression of Speech Signal
Authors: Karima Siham Aoubid, Mohamed Boulemden
Abstract:
The development of the signal compression algorithms is having compressive progress. These algorithms are continuously improved by new tools and aim to reduce, an average, the number of bits necessary to the signal representation by means of minimizing the reconstruction error. The following article proposes the compression of Arabic speech signal by a hybrid method combining the wavelet transform and the linear prediction. The adopted approach rests, on one hand, on the original signal decomposition by ways of analysis filters, which is followed by the compression stage, and on the other hand, on the application of the order 5, as well as, the compression signal coefficients. The aim of this approach is the estimation of the predicted error, which will be coded and transmitted. The decoding operation is then used to reconstitute the original signal. Thus, the adequate choice of the bench of filters is useful to the transform in necessary to increase the compression rate and induce an impercevable distortion from an auditive point of view.Keywords: Compression, linear prediction analysis, multiresolution analysis, speech signal.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13231101 Harmonic Parameters with HHT and Wavelet Transform for Automatic Sleep Stages Scoring
Authors: Wei-Chih Tang, Shih-Wei Lu, Chih-Mong Tsai, Cheng-Yan Kao, Hsiu-Hui Lee
Abstract:
Previously, harmonic parameters (HPs) have been selected as features extracted from EEG signals for automatic sleep scoring. However, in previous studies, only one HP parameter was used, which were directly extracted from the whole epoch of EEG signal. In this study, two different transformations were applied to extract HPs from EEG signals: Hilbert-Huang transform (HHT) and wavelet transform (WT). EEG signals are decomposed by the two transformations; and features were extracted from different components. Twelve parameters (four sets of HPs) were extracted. Some of the parameters are highly diverse among different stages. Afterward, HPs from two transformations were used to building a rough sleep stages scoring model using the classifier SVM. The performance of this model is about 78% using the features obtained by our proposed extractions. Our results suggest that these features may be useful for automatic sleep stages scoring.Keywords: EEG, harmonic parameter, Hilbert-Huang transform, sleep stages, wavelet transform.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18741100 Simulation and Analysis of the Shift Process for an Automatic Transmission
Authors: Kei-Lin Kuo
Abstract:
The automatic transmission (AT) is one of the most important components of many automobile transmission systems. The shift quality has a significant influence on the ride comfort of the vehicle. During the AT shift process, the joint elements such as the clutch and bands engage or disengage, linking sets of gears to create a fixed gear ratio. Since these ratios differ between gears in a fixed gear ratio transmission, the motion of the vehicle could change suddenly during the shift process if the joint elements are engaged or disengaged inappropriately, additionally impacting the entire transmission system and increasing the temperature of connect elements.The objective was to establish a system model for an AT powertrain using Matlab/Simulink. This paper further analyses the effect of varying hydraulic pressure and the associated impact on shift quality during both engagment and disengagement of the joint elements, proving that shift quality improvements could be achieved with appropriate hydraulic pressure control.Keywords: Automatic transmission, Simulation and analysis, Shift quality.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 44881099 Ottoman Script Recognition Using Hidden Markov Model
Authors: Ayşe Onat, Ferruh Yildiz, Mesut Gündüz
Abstract:
In this study, an OCR system for segmentation, feature extraction and recognition of Ottoman Scripts has been developed using handwritten characters. Detection of handwritten characters written by humans is a difficult process. Segmentation and feature extraction stages are based on geometrical feature analysis, followed by the chain code transformation of the main strokes of each character. The output of segmentation is well-defined segments that can be fed into any classification approach. The classes of main strokes are identified through left-right Hidden Markov Model (HMM).Keywords: Chain Code, HMM, Ottoman Script Recognition, OCR
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23001098 Automatic Staging and Subtype Determination for Non-Small Cell Lung Carcinoma Using PET Image Texture Analysis
Authors: Seyhan Karaçavuş, Bülent Yılmaz, Ömer Kayaaltı, Semra İçer, Arzu Taşdemir, Oğuzhan Ayyıldız, Kübra Eset, Eser Kaya
Abstract:
In this study, our goal was to perform tumor staging and subtype determination automatically using different texture analysis approaches for a very common cancer type, i.e., non-small cell lung carcinoma (NSCLC). Especially, we introduced a texture analysis approach, called Law’s texture filter, to be used in this context for the first time. The 18F-FDG PET images of 42 patients with NSCLC were evaluated. The number of patients for each tumor stage, i.e., I-II, III or IV, was 14. The patients had ~45% adenocarcinoma (ADC) and ~55% squamous cell carcinoma (SqCCs). MATLAB technical computing language was employed in the extraction of 51 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and Laws’ texture filters. The feature selection method employed was the sequential forward selection (SFS). Selected textural features were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). In the automatic classification of tumor stage, the accuracy was approximately 59.5% with k-NN classifier (k=3) and 69% with SVM (with one versus one paradigm), using 5 features. In the automatic classification of tumor subtype, the accuracy was around 92.7% with SVM one vs. one. Texture analysis of FDG-PET images might be used, in addition to metabolic parameters as an objective tool to assess tumor histopathological characteristics and in automatic classification of tumor stage and subtype.Keywords: Cancer stage, cancer cell type, non-small cell lung carcinoma, PET, texture analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9661097 Handwritten Character Recognition Using Multiscale Neural Network Training Technique
Authors: Velappa Ganapathy, Kok Leong Liew
Abstract:
Advancement in Artificial Intelligence has lead to the developments of various “smart" devices. Character recognition device is one of such smart devices that acquire partial human intelligence with the ability to capture and recognize various characters in different languages. Firstly multiscale neural training with modifications in the input training vectors is adopted in this paper to acquire its advantage in training higher resolution character images. Secondly selective thresholding using minimum distance technique is proposed to be used to increase the level of accuracy of character recognition. A simulator program (a GUI) is designed in such a way that the characters can be located on any spot on the blank paper in which the characters are written. The results show that such methods with moderate level of training epochs can produce accuracies of at least 85% and more for handwritten upper case English characters and numerals.Keywords: Character recognition, multiscale, backpropagation, neural network, minimum distance technique.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19091096 Contour Estimation in Synthetic and Real Weld Defect Images based on Maximum Likelihood
Authors: M. Tridi, N. Nacereddine, N. Oucief
Abstract:
This paper describes a novel method for automatic estimation of the contours of weld defect in radiography images. Generally, the contour detection is the first operation which we apply in the visual recognition system. Our approach can be described as a region based maximum likelihood formulation of parametric deformable contours. This formulation provides robustness against the poor image quality, and allows simultaneous estimation of the contour parameters together with other parameters of the model. Implementation is performed by a deterministic iterative algorithm with minimal user intervention. Results testify for the very good performance of the approach especially in synthetic weld defect images.Keywords: Contour, gaussian, likelihood, rayleigh.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16501095 Validation Testing for Temporal Neural Networks for RBF Recognition
Authors: Khaled E. A. Negm
Abstract:
A neuron can emit spikes in an irregular time basis and by averaging over a certain time window one would ignore a lot of information. It is known that in the context of fast information processing there is no sufficient time to sample an average firing rate of the spiking neurons. The present work shows that the spiking neurons are capable of computing the radial basis functions by storing the relevant information in the neurons' delays. One of the fundamental findings of the this research also is that when using overlapping receptive fields to encode the data patterns it increases the network-s clustering capacity. The clustering algorithm that is discussed here is interesting from computer science and neuroscience point of view as well as from a perspective.
Keywords: Temporal Neurons, RBF Recognition, Perturbation, On Line Recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14821094 Reducing the False Rejection Rate of Iris Recognition Using Textural and Topological Features
Authors: M. Vatsa, R. Singh, A. Noore
Abstract:
This paper presents a novel iris recognition system using 1D log polar Gabor wavelet and Euler numbers. 1D log polar Gabor wavelet is used to extract the textural features, and Euler numbers are used to extract topological features of the iris. The proposed decision strategy uses these features to authenticate an individual-s identity while maintaining a low false rejection rate. The algorithm was tested on CASIA iris image database and found to perform better than existing approaches with an overall accuracy of 99.93%.Keywords: Iris recognition, textural features, topological features.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19331093 Face Recognition using Features Combination and a New Non-linear Kernel
Authors: Essam Al Daoud
Abstract:
To improve the classification rate of the face recognition, features combination and a novel non-linear kernel are proposed. The feature vector concatenates three different radius of local binary patterns and Gabor wavelet features. Gabor features are the mean, standard deviation and the skew of each scaling and orientation parameter. The aim of the new kernel is to incorporate the power of the kernel methods with the optimal balance between the features. To verify the effectiveness of the proposed method, numerous methods are tested by using four datasets, which are consisting of various emotions, orientations, configuration, expressions and lighting conditions. Empirical results show the superiority of the proposed technique when compared to other methods.Keywords: Face recognition, Gabor wavelet, LBP, Non-linearkerner
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15281092 Classification Algorithms in Human Activity Recognition using Smartphones
Authors: Mohd Fikri Azli bin Abdullah, Ali Fahmi Perwira Negara, Md. Shohel Sayeed, Deok-Jai Choi, Kalaiarasi Sonai Muthu
Abstract:
Rapid advancement in computing technology brings computers and humans to be seamlessly integrated in future. The emergence of smartphone has driven computing era towards ubiquitous and pervasive computing. Recognizing human activity has garnered a lot of interest and has raised significant researches- concerns in identifying contextual information useful to human activity recognition. Not only unobtrusive to users in daily life, smartphone has embedded built-in sensors that capable to sense contextual information of its users supported with wide range capability of network connections. In this paper, we will discuss the classification algorithms used in smartphone-based human activity. Existing technologies pertaining to smartphone-based researches in human activity recognition will be highlighted and discussed. Our paper will also present our findings and opinions to formulate improvement ideas in current researches- trends. Understanding research trends will enable researchers to have clearer research direction and common vision on latest smartphone-based human activity recognition area.Keywords: Classification algorithms, Human Activity Recognition (HAR), Smartphones
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 62891091 Recognition of Tifinagh Characters with Missing Parts Using Neural Network
Authors: El Mahdi Barrah, Said Safi, Abdessamad Malaoui
Abstract:
In this paper, we present an algorithm for reconstruction from incomplete 2D scans for tifinagh characters. This algorithm is based on using correlation between the lost block and its neighbors. This system proposed contains three main parts: pre-processing, features extraction and recognition. In the first step, we construct a database of tifinagh characters. In the second step, we will apply “shape analysis algorithm”. In classification part, we will use Neural Network. The simulation results demonstrate that the proposed method give good results.
Keywords: Tifinagh character recognition, Neural networks, Local cost computation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12741090 Speaker Identification by Joint Statistical Characterization in the Log Gabor Wavelet Domain
Authors: Suman Senapati, Goutam Saha
Abstract:
Real world Speaker Identification (SI) application differs from ideal or laboratory conditions causing perturbations that leads to a mismatch between the training and testing environment and degrade the performance drastically. Many strategies have been adopted to cope with acoustical degradation; wavelet based Bayesian marginal model is one of them. But Bayesian marginal models cannot model the inter-scale statistical dependencies of different wavelet scales. Simple nonlinear estimators for wavelet based denoising assume that the wavelet coefficients in different scales are independent in nature. However wavelet coefficients have significant inter-scale dependency. This paper enhances this inter-scale dependency property by a Circularly Symmetric Probability Density Function (CS-PDF) related to the family of Spherically Invariant Random Processes (SIRPs) in Log Gabor Wavelet (LGW) domain and corresponding joint shrinkage estimator is derived by Maximum a Posteriori (MAP) estimator. A framework is proposed based on these to denoise speech signal for automatic speaker identification problems. The robustness of the proposed framework is tested for Text Independent Speaker Identification application on 100 speakers of POLYCOST and 100 speakers of YOHO speech database in three different noise environments. Experimental results show that the proposed estimator yields a higher improvement in identification accuracy compared to other estimators on popular Gaussian Mixture Model (GMM) based speaker model and Mel-Frequency Cepstral Coefficient (MFCC) features.Keywords: Speaker Identification, Log Gabor Wavelet, Bayesian Bivariate Estimator, Circularly Symmetric Probability Density Function, SIRP.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16431089 Behavioral and EEG Reactions in Native Turkic-Speaking Inhabitants of Siberia and Siberian Russians during Recognition of Syntactic Errors in Sentences in Native and Foreign Languages
Authors: Tatiana N. Astakhova, Alexander E. Saprygin, Tatiana A. Golovko, Alexander N. Savostyanov, Mikhail S. Vlasov, Natalia V. Borisova, Alexandera G. Karpova, Urana N. Kavai-ool, Elena Mokur-ool, Nikolay A. Kolchano, Lyubomir I. Aftanas
Abstract:
The aim of the study is to compare behavioral and EEG reactions in Turkic-speaking inhabitants of Siberia (Tuvinians and Yakuts) and Russians during the recognition of syntax errors in native and foreign languages. Sixty-three healthy aboriginals of the Tyva Republic, 29 inhabitants of the Sakha (Yakutia) Republic, and 55 Russians from Novosibirsk participated in the study. EEG were recorded during execution of error-recognition task in Russian and English language (in all participants) and in native languages (Tuvinian or Yakut Turkic-speaking inhabitants). Reaction time (RT) and quality of task execution were chosen as behavioral measures. Amplitude and cortical distribution of P300 and P600 peaks of ERP were used as a measure of speech-related brain activity. In Tuvinians, there were no differences in the P300 and P600 amplitudes as well as in cortical topology for Russian and Tuvinian languages, but there was a difference for English. In Yakuts, the P300 and P600 amplitudes and topology of ERP for Russian language were the same as Russians had for native language. In Yakuts, brain reactions during Yakut and English language comprehension had no difference, while the Russian language comprehension was differed from both Yakut and English. We found out that the Tuvinians recognized both Russian and Tuvinian as native languages, and English as a foreign language. The Yakuts recognized both English and Yakut as foreign languages, but Russian as a native language. According to the inquirer, both Tuvinians and Yakuts use the national language as a spoken language, whereas they do not use it for writing. It can well be a reason that Yakuts perceive the Yakut writing language as a foreign language while writing Russian as their native.Keywords: EEG, brain activity, syntactic analysis, native and foreign language.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20541088 Improvement of MLLR Speaker Adaptation Using a Novel Method
Authors: Ing-Jr Ding
Abstract:
This paper presents a technical speaker adaptation method called WMLLR, which is based on maximum likelihood linear regression (MLLR). In MLLR, a linear regression-based transform which adapted the HMM mean vectors was calculated to maximize the likelihood of adaptation data. In this paper, the prior knowledge of the initial model is adequately incorporated into the adaptation. A series of speaker adaptation experiments are carried out at a 30 famous city names database to investigate the efficiency of the proposed method. Experimental results show that the WMLLR method outperforms the conventional MLLR method, especially when only few utterances from a new speaker are available for adaptation.Keywords: hidden Markov model, maximum likelihood linearregression, speech recognition, speaker adaptation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1835