Search results for: Discriminant vectors
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 255

Search results for: Discriminant vectors

165 3D Model Retrieval based on Normal Vector Interpolation Method

Authors: Ami Kim, Oubong Gwun, Juwhan Song

Abstract:

In this paper, we proposed the distribution of mesh normal vector direction as a feature descriptor of a 3D model. A normal vector shows the entire shape of a model well. The distribution of normal vectors was sampled in proportion to each polygon's area so that the information on the surface with less surface area may be less reflected on composing a feature descriptor in order to enhance retrieval performance. At the analysis result of ANMRR, the enhancement of approx. 12.4%~34.7% compared to the existing method has also been indicated.

Keywords: Interpolated Normal Vector, Feature Descriptor, 3DModel Retrieval.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1440
164 An Evaluation of Algorithms for Single-Echo Biosonar Target Classification

Authors: Turgay Temel, John Hallam

Abstract:

A recent neurospiking coding scheme for feature extraction from biosonar echoes of various plants is examined with avariety of stochastic classifiers. Feature vectors derived are employedin well-known stochastic classifiers, including nearest-neighborhood,single Gaussian and a Gaussian mixture with EM optimization.Classifiers' performances are evaluated by using cross-validation and bootstrapping techniques. It is shown that the various classifers perform equivalently and that the modified preprocessing configuration yields considerably improved results.

Keywords: Classification, neuro-spike coding, non-parametricmodel, parametric model, Gaussian mixture, EM algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1623
163 Hybrid Color-Texture Space for Image Classification

Authors: Hassan El Maia, Ahmed Hammouch, Driss Aboutajdine

Abstract:

This work presents an approach for the construction of a hybrid color-texture space by using mutual information. Feature extraction is done by the Laws filter with SVM (Support Vectors Machine) as a classifier. The classification is applied on the VisTex database and a SPOT HRV (XS) image representing two forest areas in the region of Rabat in Morocco. The result of classification obtained in the hybrid space is compared with the one obtained in the RGB color space.

Keywords: Color, texture, laws filter, mutual information, SVM, hybrid space.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1779
162 Identification of Cardiac Arrhythmias using Natural Resonance Complex Frequencies

Authors: Moustafa A. Bani-Hasan, Yasser M. Kadah, Fatma M. El-Hefnawi

Abstract:

An electrocardiogram (ECG) feature extraction system based on the calculation of the complex resonance frequency employing Prony-s method is developed. Prony-s method is applied on five different classes of ECG signals- arrhythmia as a finite sum of exponentials depending on the signal-s poles and the resonant complex frequencies. Those poles and resonance frequencies of the ECG signals- arrhythmia are evaluated for a large number of each arrhythmia. The ECG signals of lead II (ML II) were taken from MIT-BIH database for five different types. These are the ventricular couplet (VC), ventricular tachycardia (VT), ventricular bigeminy (VB), and ventricular fibrillation (VF) and the normal (NR). This novel method can be extended to any number of arrhythmias. Different classification techniques were tried using neural networks (NN), K nearest neighbor (KNN), linear discriminant analysis (LDA) and multi-class support vector machine (MC-SVM).

Keywords: Arrhythmias analysis, electrocardiogram, featureextraction, statistical classifiers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2034
161 Developing Measurement Model of Interpersonal Skills of Youth

Authors: Mohd Yusri Ibrahim

Abstract:

Although it is known that interpersonal skills are essential for personal development, the debate however continues as to how to measure those skills, especially in youths. This study was conducted to develop a measurement model of interpersonal skills by suggesting three construct namely personal, skills and relationship; six function namely self, perception, listening, conversation, emotion and conflict management; and 30 behaviours as indicators. This cross-sectional survey by questionnaires was applied in east side of peninsula of Malaysia for 150 respondents, and analyzed by structural equation modelling (SEM) by AMOS. The suggested constructs, functions and indicators were consider accepted as measurement elements by observing on regression weight for standard loading, average variance extracted (AVE) for convergent validity, square root of AVE for discriminant validity, composite reliability (CR), and at least three fit indexes for model fitness. Finally, a measurement model of interpersonal skill for youth was successfully developed.

Keywords: Interpersonal communication, interpersonal skill, youth.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1222
160 A Multimodal Approach for Biometric Authentication with Multiple Classifiers

Authors: Sorin Soviany, Cristina Soviany, Mariana Jurian

Abstract:

The paper presents a multimodal approach for biometric authentication, based on multiple classifiers. The proposed solution uses a post-classification biometric fusion method in which the biometric data classifiers outputs are combined in order to improve the overall biometric system performance by decreasing the classification error rates. The paper shows also the biometric recognition task improvement by means of a carefully feature selection, as much as not all of the feature vectors components support the accuracy improvement.

Keywords: biometric fusion, multiple classifiers

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2042
159 A Hybrid GMM/SVM System for Text Independent Speaker Identification

Authors: Rafik Djemili, Mouldi Bedda, Hocine Bourouba

Abstract:

This paper proposes a novel approach that combines statistical models and support vector machines. A hybrid scheme which appropriately incorporates the advantages of both the generative and discriminant model paradigms is described and evaluated. Support vector machines (SVMs) are trained to divide the whole speakers' space into small subsets of speakers within a hierarchical tree structure. During testing a speech token is assigned to its corresponding group and evaluation using gaussian mixture models (GMMs) is then processed. Experimental results show that the proposed method can significantly improve the performance of text independent speaker identification task. We report improvements of up to 50% reduction in identification error rate compared to the baseline statistical model.

Keywords: Speaker identification, Gaussian mixture model (GMM), support vector machine (SVM), hybrid GMM/SVM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2186
158 Analysis of Combined Use of NN and MFCC for Speech Recognition

Authors: Safdar Tanweer, Abdul Mobin, Afshar Alam

Abstract:

The performance and analysis of speech recognition system is illustrated in this paper. An approach to recognize the English word corresponding to digit (0-9) spoken by 2 different speakers is captured in noise free environment. For feature extraction, speech Mel frequency cepstral coefficients (MFCC) has been used which gives a set of feature vectors from recorded speech samples. Neural network model is used to enhance the recognition performance. Feed forward neural network with back propagation algorithm model is used. However other speech recognition techniques such as HMM, DTW exist. All experiments are carried out on Matlab.

Keywords: Speech Recognition, MFCC, Neural Network, classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3224
157 Octonionic Reformulation of Vector Analysis

Authors: Bhupendra C. S. Chauhan, P. S. Bisht, O. P. S. Negi

Abstract:

According to celebrated Hurwitz theorem, there exists four division algebras consisting of R (real numbers), C (complex numbers), H (quaternions) and O (octonions). Keeping in view the utility of octonion variable we have tried to extend the three dimensional vector analysis to seven dimensional one. Starting with the scalar and vector product in seven dimensions, we have redefined the gradient, divergence and curl in seven dimension. It is shown that the identity n(n - 1)(n - 3)(n - 7) = 0 is satisfied only for 0, 1, 3 and 7 dimensional vectors. We have tried to write all the vector inequalities and formulas in terms of seven dimensions and it is shown that same formulas loose their meaning in seven dimensions due to non-associativity of octonions. The vector formulas are retained only if we put certain restrictions on octonions and split octonions.

Keywords: Octonions, Vector Space and seven dimensions

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1158
156 A Virtual Simulation Environment for a Design and Verification of a GPGPU

Authors: Kwang Y. Lee, Tae R. Park, Jae C. Kwak, Yong S. Koo

Abstract:

When a small H/W IP is designed, we can develop an appropriate verification environment by observing the simulated signal waves, or using the serial test vectors for the fixed output. In the case of design and verification of a massive parallel processor with multiple IPs, it-s difficult to make a verification system with existing common verification environment, and to verify each partial IP. A TestDrive verification environment can build easy and reliable verification system that can produce highly intuitive results by applying Modelsim and SystemVerilog-s DPI. It shows many advantages, for example a high-level design of a GPGPU processor design can be migrate to FPGA board immediately.

Keywords: Virtual Simulation, Verification, IP Design, GPGPU

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1621
155 Analysis of Fertilizer Effect in the Tilapia Growth of Mozambique (Oreochromis mossambicus)

Authors: Sérgio Afonso Mulema, Andrés Carrión García, Vicente Ernesto

Abstract:

This paper analyses the effect of fertilizer (organic and inorganic) in the growth of tilapia. An experiment was implemented in the Aquapesca Company of Mozambique; there were considered four different treatments. Each type of fertilizer was applied in two of these treatments; a feed was supplied to the third treatment, and the fourth was taken as control. The weight and length of the tilapia were used as the growth parameters, and to measure the water quality, the physical-chemical parameters were registered. The results show that the weight and length were different for tilapias cultivated in different treatments. These differences were evidenced mainly by organic and feed treatments, where there was the largest and smallest value of these parameters, respectively. In order to prove that these differences were caused only by applied treatment without interference for the aquatic environment, a Fisher discriminant analysis was applied, which confirmed that the treatments were exposed to the same environment condition.

Keywords: Fertilizer, tilapia, growth, statistical methods.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 859
154 Automatic Intelligent Analysis of Malware Behaviour

Authors: H. Dornhackl, K. Kadletz, R. Luh, P. Tavolato

Abstract:

In this paper, we describe the use of formal methods to model malware behaviour. The modelling of harmful behaviour rests upon syntactic structures that represent malicious procedures inside malware. The malicious activities are modelled by a formal grammar, where API calls’ components are the terminals and the set of API calls used in combination to achieve a goal are designated non-terminals. The combination of different non-terminals in various ways and tiers make up the attack vectors that are used by harmful software. Based on these syntactic structures a parser can be generated which takes execution traces as input for pattern recognition.

Keywords: Malware behaviour, modelling, parsing, search, pattern matching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1430
153 Power System Security Assessment using Binary SVM Based Pattern Recognition

Authors: S Kalyani, K Shanti Swarup

Abstract:

Power System Security is a major concern in real time operation. Conventional method of security evaluation consists of performing continuous load flow and transient stability studies by simulation program. This is highly time consuming and infeasible for on-line application. Pattern Recognition (PR) is a promising tool for on-line security evaluation. This paper proposes a Support Vector Machine (SVM) based binary classification for static and transient security evaluation. The proposed SVM based PR approach is implemented on New England 39 Bus and IEEE 57 Bus systems. The simulation results of SVM classifier is compared with the other classifier algorithms like Method of Least Squares (MLS), Multi- Layer Perceptron (MLP) and Linear Discriminant Analysis (LDA) classifiers.

Keywords: Static Security, Transient Security, Pattern Recognition, Classifier, Support Vector Machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1824
152 Ranking - Convex Risk Minimization

Authors: Wojciech Rejchel

Abstract:

The problem of ranking (rank regression) has become popular in the machine learning community. This theory relates to problems, in which one has to predict (guess) the order between objects on the basis of vectors describing their observed features. In many ranking algorithms a convex loss function is used instead of the 0-1 loss. It makes these procedures computationally efficient. Hence, convex risk minimizers and their statistical properties are investigated in this paper. Fast rates of convergence are obtained under conditions, that look similarly to the ones from the classification theory. Methods used in this paper come from the theory of U-processes as well as empirical processes.

Keywords: Convex loss function, empirical risk minimization, empirical process, U-process, boosting, euclidean family.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1372
151 A Double Referenced Contrast for Blind Source Separation

Authors: Atman Jbari, Abdellah Adib, Driss Aboutajdine

Abstract:

This paper addresses the problem of blind source separation (BSS). To recover original signals, from linear instantaneous mixtures, we propose a new contrast function based on the use of a double referenced system. Our approach assumes statistical independence sources. The reference vectors will be incrusted in the cumulant to evaluate the independence. The estimation of the separating matrix will be performed in two steps: whitening observations and joint diagonalization of a set of referenced cumulant matrices. Computer simulations are presented to demonstrate the effectiveness of the suggested approach.

Keywords: Blind source separation, Referenced Cumulant, Contrast, Joint Diagonalization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 972
150 On the Determination of a Time-like Dual Curve in Dual Lorentzian Space

Authors: Emin Özyılmaz

Abstract:

In this work, position vector of a time-like dual curve according to standard frame of D31 is investigated. First, it is proven that position vector of a time-like dual curve satisfies a dual vector differential equation of fourth order. The general solution of this dual vector differential equation has not yet been found. Due to this, in terms of special solutions, position vectors of some special time-like dual curves with respect to standard frame of D31 are presented.

Keywords: Classical Differential Geometry, Dual Numbers, DualFrenet Equations, Time-like Dual Curve, Position Vector, DualLorentzian Space.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1436
149 Determining the Principles Affecting Perceptions of Strategic Quality Management Implementation: A Study of the Turkish Large Scale Firms

Authors: Gül Tekin Temur, Tolga Kaya, Serpil Öktem, Sıtkı Gözlü

Abstract:

The purpose of this study is to reveal the principles, which have the highest impact on determining the Strategic Quality Management (SQM) implementation perceptions of managers. In order to accomplish this goal, first of all, a factor analysis is conducted on the attitudes of managers at 80 large-scale firms in Turkey for SQM principles. Secondly, utilizing t tests and discriminant analysis, the most effective items are determined. The results show that “process improvement" and “assessment of competitiveness" are the management principles, which have the highest impact on determining the SQM implementation perceptions of Turkish managers.

Keywords: Assessment of Competitiveness, Process Improvement, Strategic Quality Management.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1492
148 Distinguishing Innocent Murmurs from Murmurs caused by Aortic Stenosis by Recurrence Quantification Analysis

Authors: Christer Ahlstrom, Katja Höglund, Peter Hult, Jens Häggström, Clarence Kvart, Per Ask

Abstract:

It is sometimes difficult to differentiate between innocent murmurs and pathological murmurs during auscultation. In these difficult cases, an intelligent stethoscope with decision support abilities would be of great value. In this study, using a dog model, phonocardiographic recordings were obtained from 27 boxer dogs with various degrees of aortic stenosis (AS) severity. As a reference for severity assessment, continuous wave Doppler was used. The data were analyzed with recurrence quantification analysis (RQA) with the aim to find features able to distinguish innocent murmurs from murmurs caused by AS. Four out of eight investigated RQA features showed significant differences between innocent murmurs and pathological murmurs. Using a plain linear discriminant analysis classifier, the best pair of features (recurrence rate and entropy) resulted in a sensitivity of 90% and a specificity of 88%. In conclusion, RQA provide valid features which can be used for differentiation between innocent murmurs and murmurs caused by AS.

Keywords: Bioacoustics, murmur, phonocardiographic signal, recurrence quantification analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1963
147 Anaplasmosis among Camels in Iran and Observation of Abnormalities in Infected Blood Films

Authors: Khosro Ghazvinian, Touba Khodaiean

Abstract:

Anaplasma organisms are obligatory intracellular bacteria belonging to the order Rickettsiales, family Anaplasmataceae. This disease is distributed around the globe and infected ticks are the most important vectors in anaplasmosis transmission. There is a little information about anaplasmosis in camels. This research investigated the blood films of 35 (20 male, 15 female) camels randomly selected from a flock of 150 camels. Samples were stained with Giemsa and Anaplasma sp. organisms were observed in six out of 35 (17.14 %) blood films. There were also some changes in Diff-Quick and morphology of leukocytes. No significant difference between male and female camels was observed (P>0.05). According to the results anaplasmosis is presented among camels in Iran.

Keywords: Anaplasma, camel, anaplasmosis, Iran.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 986
146 Topology Preservation in SOM

Authors: E. Arsuaga Uriarte, F. Díaz Martín

Abstract:

The SOM has several beneficial features which make it a useful method for data mining. One of the most important features is the ability to preserve the topology in the projection. There are several measures that can be used to quantify the goodness of the map in order to obtain the optimal projection, including the average quantization error and many topological errors. Many researches have studied how the topology preservation should be measured. One option consists of using the topographic error which considers the ratio of data vectors for which the first and second best BMUs are not adjacent. In this work we present a study of the behaviour of the topographic error in different kinds of maps. We have found that this error devaluates the rectangular maps and we have studied the reasons why this happens. Finally, we suggest a new topological error to improve the deficiency of the topographic error.

Keywords: Map lattice, Self-Organizing Map, topographic error, topology preservation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2940
145 Study on Crater Detection Using FLDA

Authors: Yoshiaki Takeda, Norifumi Aoyama, Takahiro Tanaami, Syouhei Honda, Kenta Tabata, Hiroyuki Kamata

Abstract:

In this paper, we validate crater detection in moon surface image using FLDA. This proposal assumes that it is applied to SLIM (Smart Lander for Investigating Moon) project aiming at the pin-point landing to the moon surface. The point where the lander should land is judged by the position relations of the craters obtained via camera, so the real-time image processing becomes important element. Besides, in the SLIM project, 400kg-class lander is assumed, therefore, high-performance computers for image processing cannot be equipped. We are studying various crater detection methods such as Haar-Like features, LBP, and PCA. And we think these methods are appropriate to the project, however, to identify the unlearned images obtained by actual is insufficient. In this paper, we examine the crater detection using FLDA, and compare with the conventional methods.

Keywords: Crater Detection, Fisher Linear Discriminant Analysis , Haar-Like Feature, Image Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1688
144 Design of Variable Fractional-Delay FIR Differentiators

Authors: Jong-Jy Shyu, Soo-Chang Pei, Min-Han Chang

Abstract:

In this paper, the least-squares design of variable fractional-delay (VFD) finite impulse response (FIR) digital differentiators is proposed. The used transfer function is formulated so that Farrow structure can be applied to realize the designed system. Also, the symmetric characteristics of filter coefficients are derived, which leads to the complexity reduction by saving almost a half of the number of coefficients. Moreover, all the elements of related vectors or matrices for the optimal process can be represented in closed forms, which make the design easier. Design example is also presented to illustrate the effectiveness of the proposed method.

Keywords: Differentiator, variable fractional-delay filter, FIR filter, least-squares method, Farrow structure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1371
143 Contributions to Differential Geometry of Pseudo Null Curves in Semi-Euclidean Space

Authors: Melih Turgut, Süha Yılmaz

Abstract:

In this paper, first, a characterization of spherical Pseudo null curves in Semi-Euclidean space is given. Then, to investigate position vector of a pseudo null curve, a system of differential equation whose solution gives the components of the position vector of a pseudo null curve on the Frenet axis is established by means of Frenet equations. Additionally, in view of some special solutions of mentioned system, characterizations of some special pseudo null curves are presented.

Keywords: Semi-Euclidean Space, Pseudo Null Curves, Position Vectors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1298
142 Performance Enhancement of Motion Estimation Using SSE2 Technology

Authors: Trung Hieu Tran, Hyo-Moon Cho, Sang-Bock Cho

Abstract:

Motion estimation is the most computationally intensive part in video processing. Many fast motion estimation algorithms have been proposed to decrease the computational complexity by reducing the number of candidate motion vectors. However, these studies are for fast search algorithms themselves while almost image and video compressions are operated with software based. Therefore, the timing constraints for running these motion estimation algorithms not only challenge for the video codec but also overwhelm for some of processors. In this paper, the performance of motion estimation is enhanced by using Intel's Streaming SIMD Extension 2 (SSE2) technology with Intel Pentium 4 processor.

Keywords: Motion Estimation, Full Search, Three StepSearch, MMX/SSE/SSE2 Technologies, SIMD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2049
141 Human Action Recognition System Based on Silhouette

Authors: S. Maheswari, P. Arockia Jansi Rani

Abstract:

Human action is recognized directly from the video sequences. The objective of this work is to recognize various human actions like run, jump, walk etc. Human action recognition requires some prior knowledge about actions namely, the motion estimation, foreground and background estimation. Region of interest (ROI) is extracted to identify the human in the frame. Then, optical flow technique is used to extract the motion vectors. Using the extracted features similarity measure based classification is done to recognize the action. From experimentations upon the Weizmann database, it is found that the proposed method offers a high accuracy.

Keywords: Background subtraction, human silhouette, optical flow, classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 953
140 Investigation of Some Technical Indexes inStock Forecasting Using Neural Networks

Authors: Myungsook Klassen

Abstract:

Training neural networks to capture an intrinsic property of a large volume of high dimensional data is a difficult task, as the training process is computationally expensive. Input attributes should be carefully selected to keep the dimensionality of input vectors relatively small. Technical indexes commonly used for stock market prediction using neural networks are investigated to determine its effectiveness as inputs. The feed forward neural network of Levenberg-Marquardt algorithm is applied to perform one step ahead forecasting of NASDAQ and Dow stock prices.

Keywords: Stock Market Prediction, Neural Networks, Levenberg-Marquadt Algorithm, Technical Indexes

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1901
139 Support Vector Machines For Understanding Lane Color and Sidewalks

Authors: Hoon Lee, Soonyoung Park, Kyoungho Choi

Abstract:

Understanding road features such as lanes, the color of lanes, and sidewalks in a live video captured from a moving vehicle is essential to build video-based navigation systems. In this paper, we present a novel idea to understand the road features using support vector machines. Various feature vectors including color components of road markings and the difference between two regions, i.e., chosen AOIs, and so on are fed into SVM, deciding colors of lanes and sidewalks robustly. Experimental results are provided to show the robustness of the proposed idea.

Keywords: video-based navigation system, lane detection, SVMs, autonomous vehicles

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1792
138 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 1800
137 Automatic Classification of the Stand-to-Sit Phase in the TUG Test Using Machine Learning

Authors: Y. A. Adla, R. Soubra, M. Kasab, M. O. Diab, A. Chkeir

Abstract:

Over the past several years, researchers have shown a great interest in assessing the mobility of elderly people to measure their functional status. Usually, such an assessment is done by conducting tests that require the subject to walk a certain distance, turn around, and finally sit back down. Consequently, this study aims to provide an at home monitoring system to assess the patient’s status continuously. Thus, we proposed a technique to automatically detect when a subject sits down while walking at home. In this study, we utilized a Doppler radar system to capture the motion of the subjects. More than 20 features were extracted from the radar signals out of which 11 were chosen based on their Intraclass Correlation Coefficient (ICC > 0.75). Accordingly, the sequential floating forward selection wrapper was applied to further narrow down the final feature vector. Finally, five features were introduced to the Linear Discriminant Analysis classifier and an accuracy of 93.75% was achieved as well as a precision and recall of 95% and 90% respectively.

Keywords: Doppler radar system, stand-to-sit phase, TUG test, machine learning, classification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 379
136 Eclectic Rule-Extraction from Support Vector Machines

Authors: Nahla Barakat, Joachim Diederich

Abstract:

Support vector machines (SVMs) have shown superior performance compared to other machine learning techniques, especially in classification problems. Yet one limitation of SVMs is the lack of an explanation capability which is crucial in some applications, e.g. in the medical and security domains. In this paper, a novel approach for eclectic rule-extraction from support vector machines is presented. This approach utilizes the knowledge acquired by the SVM and represented in its support vectors as well as the parameters associated with them. The approach includes three stages; training, propositional rule-extraction and rule quality evaluation. Results from four different experiments have demonstrated the value of the approach for extracting comprehensible rules of high accuracy and fidelity.

Keywords: Data mining, hybrid rule-extraction algorithms, medical diagnosis, SVMs

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1657