• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.104-107
• /
• 2004

In this study, using brain phantom for multi-modality imaging, we acquired CT, MR and PET images and performed registration of these anatomical images and nuclear medicine functional images. The algorithms and program applied for registration were Chamfer Matching and Mutual Information Maximization algorithm which have been using frequently in clinic and verified accuracy respectively. In result, both algorithms were useful methods for CT-MR, CT-PET and MR-PET. But Mutual Information Maximization was more effective algorithm for low resolution image as nuclear medicine functional image.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.5
• /
• pp.1527-1535
• /
• 2012

Selection of the most informative molecular descriptors from the original data set is a key step for development of quantitative structure activity/property relationship models. Recently, mutual information (MI) has gained increasing attention in feature selection problems. This paper presents an effective mutual information-based feature selection approach, named mutual information maximization by replacing collinear variables (MIMRCV), for nonlinear quantitative structure-property relationship models. The proposed variable selection method was applied to three different QSPR datasets, soil degradation half-life of 47 organophosphorus pesticides, GC-MS retention times of 85 volatile organic compounds, and water-to-micellar cetyltrimethylammonium bromide partition coefficients of 62 organic compounds.The obtained results revealed that using MIMRCV as feature selection method improves the predictive quality of the developed models compared to conventional MI based variable selection algorithms.

• 전자공학회논문지 IE
• /
• v.45 no.3
• /
• pp.20-26
• /
• 2008

Two independent component analysis(ICA) algorithms were applied for the recognition of speech signals corrupted by a car engine noise. Speech recognition was performed by hidden markov model(HMM) for the estimated signals and recognition rates were compared with those of orginal speech signals which are not corrupted. Two different ICA methods were applied for the estimation of speech signals, one of which is FastICA algorithm that maximizes negentropy, the other is information-maximization approach that maximizes the mutual information between inputs and outputs to give maximum independence among outputs. Word recognition rate for the Korean news sentences spoken by a male anchor is 87.85%, while there is 1.65% drop of performance on the average for the estimated speech signals by FastICA and 2.02% by information-maximization for the various signal to noise ratio(SNR). There is little difference between the methods.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.237-245
• /
• 2004

In general, Gaussian mixture model(GMM) is used to estimate the speaker model for speaker identification. The parameter estimates of the GMM are obtained by using the expectation-maximization (EM) algorithm for the maximum likelihood(ML) estimation. However, if the number of mixtures isn't defined well in the GMM, those parameters are obtained inappropriately. The problem to find the number of components is significant to estimate the optimal parameter in mixture model. In this paper, to estimate the optimal number of mixtures, we propose the method that starts from the sufficient mixtures, after, the number is reduced by investigating the mutual information between mixtures for GMM. In result, we can estimate the optimal number of mixtures. The effectiveness of the proposed method is shown by the experiment using artificial data. Also, we performed the speaker identification applying the proposed method comparing with other approaches.

• Progress in Medical Physics
• /
• v.13 no.4
• /
• pp.209-217
• /
• 2002

There have been many studies on the application of the reciprocal advantages of multimodality image to define accurate target volume in the Process of radiation treatment planning. For the proper use of the multimodality images, the registration works between different modality images should be performed in advance. In this study, we selected chamfer matching method and mutual information method as most popular methods in recent image registration studies considering the registration accuracy and clinical practicality. And the two registration methods were analyzed to deduce the optimal registration method according to the characteristics of images. Lung phantom of which multimodality images could be acquired was fabricated and CT, MRI and SPECT images of the phantom were used in this study. We developed the registration program which can perform the two registration methods properly and analyzed the registration results which were produced by the developed program in many different images' conditions. Although the overall accuracy of the registration in both chamfer matching method and mutual information method was acceptable, the registration errors in SPECT images which had lower resolution and in degraded images of which data were removed in some part were increased when chamfer matching method was applied. Especially in the case of degraded reference image, chamfer matching methods produce relatively large errors compared with mutual information method. Mutual information method can be estimated as more robust registration method than chamfer matching method in this study because it did not need the prerequisite works, the extraction of accurate contour points, and it produced more accurate registration results consistently regardless of the images' characteristics. The analysis of the registration methods in this study can be expected to provide useful information to the utilization of multimodality images in delineating target volume for radiation treatment planning and in many other clinical applications.

• Korean Business Review
• /
• v.16
• /
• pp.169-184
• /
• 2003

IR(Investor Relation) is an active management activity to provide well balanced information to investors which can reduce asymmetry of information between investors and management. This activity could contribute to the long-term development of corporation with increased mutual trust between investors and management. Consequently, in these days, ill is widely recognized as an effective measure of securing corporate transparency, maximization corporate value, and stock-holder oriented management. The purpose of this study is to examine the effect of corporate IR activity on investment behavior as well as stock price. It is assumed that if asymmetry of information between investors and management is cured by active ill activity from a corporation, with more transparent and reliable information of the firm at hand investors would more actively involved in trading. Statistically speaking, I assumed that the more information provided by ill activities, the higher value of a corporation at the stock trading.

• Journal of Yeungnam Medical Science
• /
• v.16 no.2
• /
• pp.237-243
• /
• 1999

We conducted this study to find the optimal correction factor(${\alpha}$) of Lassen's linearization algorithm which has been applied for correction of flow-limited uptake at a high flow range in $^{99m}Tc$ d,l-hexamethylpropy leneamine oxime(HMPAO) and $^{99m}Tc$ ethyl cysteinate dimer(ECD). Ten patients with chronic cerebral infarction were involved in this study. We obtained the corrected $^{99m}Tc$ HMPAO and $^{99m}Tc$-ECD brain SPECT(single photon emission computed tomography) using the algorithm with ${\alpha}$ values that varied from 0.1 to 10 and compared the results with regional cerebral blood flow determined by positron emission tomography (PET-rCBF). The multi-modal volume registration by maximization of mutual information was used for matching between PET-rCBF and SPECT images. The highest correlation coefficient between $^{99m}Tc$-HMPAO and $^{99m}Tc$-ECD brain uptake and PET-rCBF was revealed at ${\alpha}$ 1.4 and 2.1, respectively. We concluded that the ${\alpha}$ values of Lassen's linearization algorithm for $^{99m}Tc$-HMPAO and $^{99m}Tc$-ECD brain SPECT images were 1.4 and 2.1, respectively to indicate cerebral blood flow with comparison of PET-rCBF.