• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.653-668
• /
• 2012

In this study, an improved HMM based recognition model is proposed for online English and Korean handwritten characters. The pattern elements of the handwriting model are sub character strokes and ligatures. To deal with the problem of handwriting style variations, a modified Hierarchical Clustering approach is introduced to partition different writing styles into several classes. For each of the English letters and each primitive grapheme in Korean characters, one HMM that models the temporal and spatial variability of the handwriting is constructed based on each class. Then the HMMs of Korean graphemes are concatenated to form the Korean character models. The recognition of handwritten characters is implemented by a modified level building algorithm, which incorporates the Korean character combination rules within the efficient network search procedure. Due to the limitation of the HMM based method, a post-processing procedure that takes the global and structural features into account is proposed. Experiments showed that the proposed recognition system achieved a high writer independent recognition rate on unconstrained samples of both English and Korean characters. The comparison with other schemes of HMM-based recognition was also performed to evaluate the system.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2003

In this paper, assuming that the score of speech utterance is the product of HMM log likelihood and HMM weight, we propose a new method that HMM weights are adapted iteratively like the general MCE training. The proposed method adjusts HMM weights for better performance using delta coefficient defined in terms of misclassification measure. Therefore, the parameter estimation and the Viterbi algorithms of conventional 1:.um can be easily applied to the proposed model by constraining the sum of HMM weights to the number of HMMs in an HMM set. Comparing with the general segmental MCE training approach, computing time decreases by reducing the number of parameters to estimate and avoiding gradient calculation through the optimal state sequence. To evaluate the performance of HMM-based speech recognizer by weighting HMM likelihood, we perform Korean isolated digit recognition experiments. The experimental results show better performance than the MCE algorithm with state weighting.

• Journal of Life Science
• /
• v.19 no.4
• /
• pp.449-456
• /
• 2009

Murine Neuro-2a (N2a) cells have been widely used for the investigation of neuronal differentiation, trophic interaction and neurotoxic effects of various compounds and their associated mechanisms. N2a cells have many genomic variations such as gains or losses in DNA copy number, similar to other neuroblastoma cells, and no systematic or high-resolution studies of their genome-wide chromosomal aberrations have been reported. Presently, we conducted a systematic genome-wide determination of chromosomal aberrations in N2a cells using a high-throughput, oligonucleotide array-based comparative genomic hybridization (oaCGH) technique. A hidden Markov Model was employed to assign each genomic oligonucleotide to a DNA copy number state: double loss, single loss, normal, gain, double gain and amplification. Unlike most neuroblastoma cells, Mycn amplification was not observed in N2a cells. In addition, these cells showed gain only in the neuron-derived neurotrophic factor (NF), while other neurotrophic factors such as glial line-derived NF and brain-derived NF presented normal copy numbers. Chromosomes 4, 8, 10, 11 and 15 displayed more than 1000 aberrational oligonucleotides, while chromosomes 3, 17, 18 and 19 displayed less than 20. The largest region of gain was located on chromosome 8 and its size was no less than 26.7 Mb (Chr8:8427841-35162415), while chromosome 4 had the longest region of single deletion, with a size of 15.1 Mb (Chr4:73265785-88374165).

• Korean Journal of Microbiology
• /
• v.39 no.4
• /
• pp.207-215
• /
• 2003

Gene structure prediction, which is to predict protein coding regions in a given nucleotide sequence, is the most important process in annotating genes and greatly affects gene analysis and genome annotation. As eukaryotic genes have more complicated stuructures in DNA sequences than those of prokaryotic genes, analysis programs for eukaryotic gene structure prediction have more diverse and more complicated computational models. We have developed EGSP, a eukaryotic gene structure program, using duration hidden markov model. The program consists of two major processes, one of which is a training process to produce parameter values from training data sets and the other of which is to predict protein coding regions based on the parameter values. The program predicts multiple genes rather than a single gene from a DNA sequence. A few computational models were implemented to detect signal pattern and their scanning efficiency was tested. Prediction performance was calculated and was compared with those of a few commonly used programs, GenScan, GeneID and Morgan based on a few criteria. The results show that the program can be practically used as a stand-alone program and a module in a system. For gene prediction of eukaryotic microbial genomes, training and prediction analysis was done with Saccharomyces chromosomes and the result shows the program is currently practically applicable to real eukaryotic microbial genomes.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.8
• /
• pp.498-504
• /
• 2005

We introduce a Korean speech recognition platform (ECHOS) developed for education and research Purposes. ECHOS lowers the entry barrier to speech recognition research and can be used as a reference engine by providing elementary speech recognition modules. It has an easy simple object-oriented architecture, implemented in the C++ language with the standard template library. The input of the ECHOS is digital speech data sampled at 8 or 16 kHz. Its output is the 1-best recognition result. N-best recognition results, and a word graph. The recognition engine is composed of MFCC/PLP feature extraction, HMM-based acoustic modeling, n-gram language modeling, finite state network (FSN)- and lexical tree-based search algorithms. It can handle various tasks from isolated word recognition to large vocabulary continuous speech recognition. We compare the performance of ECHOS and hidden Markov model toolkit (HTK) for validation. In an FSN-based task. ECHOS shows similar word accuracy while the recognition time is doubled because of object-oriented implementation. For a 8000-word continuous speech recognition task, using the lexical tree search algorithm different from the algorithm used in HTK, it increases the word error rate by $40\%$ relatively but reduces the recognition time to half.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.375-382
• /
• 2003

Lip-reading technique based on bimodal is to enhance speech recognition rate in noisy environment. It is most important to detect the correct lip-image. But it is hard to estimate stable performance in dynamic environment, because of many factors to deteriorate Lip-reading's performance. There are illumination change, speaker's pronunciation habit, versatility of lips shape and rotation or size change of lips etc. In this paper, we propose the IIR filtering in time-domain for the stable performance. It is very proper to remove the noise of speech, to enhance performance of recognition by digital filtering in time domain. While the lip-reading technique in whole lip image makes data massive, the Principal Component Analysis of pre-process allows to reduce the data quantify by detection of feature without loss of image information. For the observation performance of speech recognition using only image information, we made an experiment on recognition after choosing 22 words in available car service. We used Hidden Markov Model by speech recognition algorithm to compare this words' recognition performance. As a result, while the recognition rate of lip-reading using PCA is 64%, Time-domain filter applied to lip-reading enhances recognition rate of 72.4%.

• Molecules and Cells
• /
• v.28 no.3
• /
• pp.195-200
• /
• 2009

Protein tyrosine kinases (PTKs) play a central role in the modulation of a wide variety of cellular events such as differentiation, proliferation and metabolism, and their unregulated activation can lead to various diseases including cancer and diabetes. PTKs represent a diverse family of proteins including both receptor tyrosine kinases (RTKs) and non-receptor tyrosine kinases (NRTKs). Due to the diversity and important cellular roles of PTKs, accurate classification methods are required to better understand and differentiate different PTKs. In addition, PTKs have become important targets for drugs, providing a further need to develop novel methods to accurately classify this set of important biological molecules. Here, we introduce a novel statistical model for the classification of PTKs that is based on their structural features. The approach allows for both the recognition of PTKs and the classification of RTKs into their subfamilies. This novel approach had an overall accuracy of 98.5% for the identification of PTKs, and 99.3% for the classification of RTKs.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.3-6
• /
• 2007

사람들이 어떠한 행동을 할 때는 특정 의도를 가지고 있기 때문에 상황에 맞는 적합한 서비스를 제공하기 위해서는 사용자가 현재 하고 있는 행동에 대한 의도를 파악해야한다. 이를 위해 의도와 행동사이의 연관성을 이용하여 사용자의 의도에 따른 행동의 모델을 만든다. 일상생활에서 사람들이 하는 행동은 작은 단위 행동들의 연속(sequence)으로 이루어지므로, 사용자의 단위행동의 순서를 분석한다면 의도에 따른 행동 모델을 만들기가 용이해진다. 하지만, 이런 단위 행동 분석 방법의 문제점은 같은 의도를 가진 행동이 완벽하게 동일한 단위 행동의 순서로 일어나지는 않는다는 점이다. 시스템은 동일한 동작 순서로 일어나지 않는 행동들을 서로 다른 의도를 가진 행동으로 이해하게 된다. 따라서 이 문제점을 해결할 수 있는 사용자 의도 파악 기법이 필요하다. 본 논문에서는 과거의 사용자의 행동 정보를 기반으로 행동들의 유사성을 판별하였고, 그 결과를 이용하여 행동의 의도를 파악하는 방법을 사용한다. 이를 위해, 과거 사용자가 한 행동들을 단위 시간 별로 나누어 단위 행동의 순서로 만들고, 이를 K-평균 군집화 방법(K-means)으로 군집들의 순서로 나타내었다. 이 변경된 사용자 행동 정보를 사용하여 은닉 마코프 모델을 학습 시키고, 이렇게 만들어진 은닉 마코프 모델은 현재 사용자가 행한 행동이 어떤 행동인지를 예측하여 사용자의 의도를 파악한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.175-182
• /
• 2004

There is a growing interest in speaker verification, which verifies someone by his/her voices. There are many speaker vitrification algorithms such as HMM and DTW. However, it is impossible to apply these algorithms to memory limited applications because of large number of feature vectors to register or verify users. In this paper we introduces a speaker verification system using SVM, which needs a little memory usage and computation time. Also we proposed hardware architecture for SVM. Experiments were conducted with Korean database which consists of four-digit strings. Although the error rate of SVM is slightly higher than that of HMM, SVM required much less computation time and small model size.

• The Korean Journal of Applied Statistics
• /
• v.22 no.1
• /
• pp.115-127
• /
• 2009

The purpose of statistical analyses of array-CGH experiment data is to divide the whole genome into regions of equal copy number, to quantify the copy number in each region and finally to evaluate its significance of being different from two. Several statistical procedures have been proposed which include the circular binary segmentation, and a Gaussian based local regression for detecting break points (GLAD) by estimating a piecewise constant function. We propose in this note a penalized spline regression and its simultaneous confidence band(SCB) approach to evaluate the statistical significance of regions of genetic gain/loss. The region of which the simultaneous confidence band stays above 0 or below 0 can be considered as a region of genetic gain or loss. We compare the performance of the SCB procedure with GLAD and hidden Markov model approaches through a simulation study in which the data were generated from AR(1) and AR(2) models to reflect spatial dependence of the array-CGH data in addition to the independence model. We found that the SCB method is more sensitive in detecting the low level copy number alterations.