• Title/Summary/Keyword: i-vector

Search Result 1,075, Processing Time 0.024 seconds

A BORSUK-ULAM TYPE THEOREM OVER ITERATED SUSPENSIONS OF REAL PROJECTIVE SPACES

  • Tanaka, Ryuichi
    • Journal of the Korean Mathematical Society
    • /
    • v.49 no.2
    • /
    • pp.251-263
    • /
    • 2012
  • A CW complex B is said to be I-trivial if there does not exist a $\mathbb{Z}_2$-map from $S^{i-1}$ to S(${\alpha}$) for any vector bundle ${\alpha}$ over B a any integer i with i > dim ${\alpha}$. In this paper, we consider the question of determining whether $\Sigma^k\mathbb{R}P^n$ is I-trivial or not, and to this question we give complete answers when k $\neq$ 1, 3, 8 and partial answers when k = 1, 3, 8. A CW complex B is I-trivial if it is "W-trivial", that is, if for every vector bundle over B, all the Stiefel-Whitney classes vanish. We find, as a result, that $\Sigma^k\mathbb{R}P^n$ is a counterexample to the converse of th statement when k = 2, 4 or 8 and n $\geq$ 2k.

A Feature Vector Extraction Method For the Automatic Classification of Power Quality Disturbances (전력 외란 자동 식별을 위한 특징 벡터 추출 기법)

  • Lee, Chul-Ho;Lee, Jae-Sang;Cho, Kwan-Young;Chung, Ji-Hyun;Nam, Sang-Won
    • Proceedings of the KIEE Conference
    • /
    • 1996.11a
    • /
    • pp.404-406
    • /
    • 1996
  • The objective of this paper is to present a new feature-vector extraction method for the automatic detection and classification of power quality(PQ) disturbances, where FFT, DWT(Discrete Wavelet Transform), and data compression are utilized to extract an appropriate feature vector. In particular, the proposed classifier consists of three parts: i.e., (i) automatic detection of PQ disturbances, where the wavelet transform and signal power estimation method are utilized to detect each disturbance, (ii) feature vector extraction from the detected disturbance, and (iii) automatic classification, where Multi-Layer Perceptron(MLP) is used to classify each disturbance from the corresponding extracted feature vector. To demonstrate the performance and applicability of the proposed classification algorithm, some test results obtained by analyzing 7-class power quality disturbances generated by the EMTP are also provided.

  • PDF

FUNCTIONAL EQUATIONS ASSOCIATED WITH INNER PRODUCT SPACES

  • Park, Choonkil;Huh, Jae Sung;Min, Won June;Nam, Dong Hoon;Roh, Seung Hyeon
    • Journal of the Chungcheong Mathematical Society
    • /
    • v.21 no.4
    • /
    • pp.455-466
    • /
    • 2008
  • In, [7], Th.M. Rassias proved that the norm defined over a real vector space V is induced by an inner product if and only if for a fixed integer $n{\geq}2$ $$n{\left\|{\frac{1}{n}}{\sum\limits_{i=1}^{n}}x_i{\left\|^2+{\sum\limits_{i=1}^{n}}\right\|}{x_i-{\frac{1}{n}}{\sum\limits_{j=1}^{n}x_j}}\right\|^2}={\sum\limits_{i=1}^{n}}{\parallel}x_i{\parallel}^2$$ holds for all $x_1,{\cdots},x_{n}{\in}V$. Let V,W be real vector spaces. It is shown that if a mapping $f:V{\rightarrow}W$ satisfies $$(0.1){\hspace{10}}nf{\left({\frac{1}{n}}{\sum\limits_{i=1}^{n}}x_i \right)}+{\sum\limits_{i=1}^{n}}f{\left({x_i-{\frac{1}{n}}{\sum\limits_{j=1}^{n}}x_i}\right)}\\{\hspace{140}}={\sum\limits_{i=1}^{n}}f(x_i)$$ for all $x_1$, ${\dots}$, $x_{n}{\in}V$ $$(0.2){\hspace{10}}2f\(\frac{x+y}{2}\)+f\(\frac{x-y}{2} \)+f\(\frac{y}{2}-x\)\\{\hspace{185}}=f(x)+f(y)$$ for all $x,y{\in}V$. Furthermore, we prove the generalized Hyers-Ulam stability of the functional equation (0.2) in real Banach spaces.

  • PDF

SVG Based Realtime Drawing Using NXT Robot (NXT 로봇을 이용한 SVG 기반 실시간 드로잉)

  • Jang, ho-yeon;Ryoo, seung-taek;Park, jin-wan
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2009.05a
    • /
    • pp.146-151
    • /
    • 2009
  • A reward of the work which used physical computing in fields artistic modern installation is becoming large. But the example that used a robot cannot try to easily look it up on a tool of the drawing which isn't robot use for interaction. I will mention it about a user and a drawing system design and the developmental process which I can communicate with at these papers. I used a Mindstorm NXT system to have been said in Lego companies in the robot which composed working environment, and I classified it to virtual environments that I forecasted environmental actual drawing this, and I did simulate. I used an Icommand library to control a NXT system, and drawing used a processing library in actual environments for the purpose of in order to to express to virtual environment. I got image information, and I expressed to a vector method SVG file to bases for line drawing. This system can have already made it according to demand of a user as real-time communication is possible by bluetooth working together. These figures can work to one performance not being stopping to the results of already in processes doing drawing.

  • PDF

Type I projection sum of squares by weighted least squares (가중최소제곱법에 의한 제1종 사영제곱합)

  • Choi, Jaesung
    • Journal of the Korean Data and Information Science Society
    • /
    • v.25 no.2
    • /
    • pp.423-429
    • /
    • 2014
  • This paper discusses a method for getting Type I sums of squares by projections under a two-way fixed-effects model when variances of errors are not equal. The method of weighted least squares is used to estimate the parameters of the assumed model. The model is fitted to the data in a sequential manner by using the model comparison technique. The vector space generated by the model matrix can be composed of orthogonal vector subspaces spanned by submatrices consisting of column vectors related to the parameters. It is discussed how to get the Type I sums of squares by using the projections into the orthogonal vector subspaces.

Speaker Adaptation Using i-Vector Based Clustering

  • Kim, Minsoo;Jang, Gil-Jin;Kim, Ji-Hwan;Lee, Minho
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.14 no.7
    • /
    • pp.2785-2799
    • /
    • 2020
  • We propose a novel speaker adaptation method using acoustic model clustering. The similarity of different speakers is defined by the cosine distance between their i-vectors (intermediate vectors), and various efficient clustering algorithms are applied to obtain a number of speaker subsets with different characteristics. The speaker-independent model is then retrained with the training data of the individual speaker subsets grouped by the clustering results, and an unknown speech is recognized by the retrained model of the closest cluster. The proposed method is applied to a large-scale speech recognition system implemented by a hybrid hidden Markov model and deep neural network framework. An experiment was conducted to evaluate the word error rates using Resource Management database. When the proposed speaker adaptation method using i-vector based clustering was applied, the performance, as compared to that of the conventional speaker-independent speech recognition model, was improved relatively by as much as 12.2% for the conventional fully neural network, and by as much as 10.5% for the bidirectional long short-term memory.

Test Pattern Generation for Combinational Circuits using Inherited Values (전수받은 값을 이용한 조합회로에 대한 검사 패턴 발생)

  • Song, Sang-Hun
    • The Transactions of the Korea Information Processing Society
    • /
    • v.4 no.2
    • /
    • pp.606-615
    • /
    • 1997
  • This paper proposes an dffcient method for test pattern generation.Current test pattern genration systems generate a test vester for fault $F_{i+l}$ independently of the computation previously done for faults F1,F2...,Fi The proposed algorithm generates a test vector for fault $F_{i+l}$ by inheriting the test vector for fault Fi. A new test vector is grnerated from inherited values by gradually changing the inhderited values .The inherited values may partially activate a fauog and propagate the fault signal,Normally,this reduses the number of decision steps and backtracks in the second search.Experimental results for well-Known benchmark circuts show that the proposed algorithm is very efficient with small backtrack kimit;in combination eith other algorithms,it is very efficient for arbitrary backtrack limits.

  • PDF

QUADRATIC MAPPINGS ASSOCIATED WITH INNER PRODUCT SPACES

  • Lee, Sung Jin
    • Korean Journal of Mathematics
    • /
    • v.19 no.1
    • /
    • pp.77-85
    • /
    • 2011
  • In [7], Th.M. Rassias proved that the norm defined over a real vector space V is induced by an inner product if and only if for a fixed integer $n{\geq}2$ $${\sum_{i=1}^{n}}\left\|x_i-{\frac{1}{n}}{\sum_{j=1}^{n}}x_j \right\|^2={\sum_{i=1}^{n}}{\parallel}x_i{\parallel}^2-n\left\|{\frac{1}{n}}{\sum_{i=1}^{n}}x_i \right\|^2$$ holds for all $x_1$, ${\cdots}$, $x_n{\in}V$. Let V, W be real vector spaces. It is shown that if an even mapping $f:V{\rightarrow}W$ satisfies $$(0.1)\;{\sum_{i=1}^{2n}f}\(x_i-{\frac{1}{2n}}{\sum_{j=1}^{2n}}x_j\)={\sum_{i=1}^{2n}}f(x_i)-2nf\({\frac{1}{2n}}{\sum_{i=1}^{2n}}x_i\)$$ for all $x_1$, ${\cdots}$, $x_{2n}{\in}V$, then the even mapping $f:V{\rightarrow}W$ is quadratic. Furthermore, we prove the generalized Hyers-Ulam stability of the quadratic functional equation (0.1) in Banach spaces.

Optimal Weights for a Vector of Independent Poisson Random Variables

  • Kim, Joo-Hwan
    • Communications for Statistical Applications and Methods
    • /
    • v.9 no.3
    • /
    • pp.765-774
    • /
    • 2002
  • Suppose one is given a vector X of a finite set of quantities $X_i$ which are independent Poisson random variables. A null hypothesis $H_0$ about E(X) is to be tested against an alternative hypothesis $H_1$. A quantity $\sum\limits_{i}w_ix_i$ is to be computed and used for the test. The optimal values of $W_i$ are calculated for three cases: (1) signal to noise ratio is used in the test, (2) normal approximations with unequal variances to the Poisson distributions are used in the test, and (3) the Poisson distribution itself is used. The above three cases are considered to the situations that are without background noise and with background noise. A comparison is made of the optimal values of $W_i$ in the three cases for both situations.

Small-Sample Inference in the Errors-in-Variables Model (소표본 errors-in-vairalbes 모형에서의 통계 추론)

  • 소병수
    • Journal of Korean Society for Quality Management
    • /
    • v.25 no.1
    • /
    • pp.69-79
    • /
    • 1997
  • We consider the semiparametric linear errors-in-variables model: yi=(${\alpha}+{\beta}ui+{\varepsilon}i$, xi=ui+${\varepsilon}i$ i=1, …, n where (xi, yi) stands for an observation vector, (ui) denotes a set of incidental nuisance parameters, (${\alpha}$ , ${\beta}$) is a vector of regression parameters and (${\varepsilon}i$, ${\delta}i$) are mutually uncorrelated measurement errors with zero mean and finite variances but otherwise unknown distributions. On the basis of a simple small-sample low-noise a, pp.oximation, we propose a new method of comparing the mean squared errors(MSE) of the various competing estimators of the true regression parameters ((${\alpha}$ , ${\beta}$). Then we show that a class of estimators including the classical least squares estimator and the maximum likelihood estimator are consistent and first-order efficient within the class of all regular consistent estimators irrespective of type of measurement errors.

  • PDF