• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.131-134
• /
• 2004

본 논문에서는 GMM(Gaussian Mixture Model)을 이용한 문맥독립 화자 검증 시스템을 구현한 후, arctan 함수를 이용한 정규화 방법을 사용하여 화자검증실험을 수행하였다. 특징파라미터로서는 선형예측방법을 이용한 켑스트럼 계수와 회귀계수를 사용하고 화자의 발성 변이를 고려하여 CMN(Cepstral Mean Normalization)을 적용하였다. 화자모델 생성을 위한 학습단에서는 화자발성의 음향학적 특징을 잘 표현할 수 있는 GMM(Gaussian Mixture Model)을 이용하였고 화자 검증단에서는 ML(Maximum Likelihood)을 이용하여 유사도를 계산하고 기존의 정규화 방법과 arctan 함수를 이용한 방법에 의해 정규화된 점수(score)와 미리 정해진 문턱값과 비교하여 검증하였다. 화자 검증 실험결과, arctan 함수를 부가한 방법이 기존의 방법보다 항상 향상된 EER을 나타냄을 확인할 수 있었다.

• The Korean Journal of Physiology and Pharmacology
• /
• v.9 no.3
• /
• pp.159-164
• /
• 2005

Effects of antioxidants on the established nephropathy were investigated. The experimental nephropathy was induced in rats by intravenous injection of adriamycin (2 mg/kg). Six weeks later, when proteinuria was apparent, the rats were supplemented with N-acetylcysteine (NAC, 1 g/kg/day) in drinking water for additional 6 weeks. Glomerulosclerosis score and tubulointerstitial injury index were determined by light microscopy. Expression of transforming growth factor (TGF) ${\beta}1$ and laminin ${\beta}1$ was determined in the renal cortex by reverse transcription-polymerase chain reaction, Western blotting, immunohistochemistry, and immunogold electron microscopy. The adriamycin-induced proteinuria as well as the glomerulosclerosis and tubulointerstitial injury was ameliorated by the treatment with NAC. Adriamycin increased the expression of TGF ${\beta}1$ mRNA and protein, which was ameliorated by NAC. Although the expression of laminin ${\beta}1$ mRNA was increased, adriamycin did not significantly alter that of its protein. These results indicate that antioxidants ameliorate the established nephropathy in association with normalization of overexpressed TGF ${\beta}1$.

• Journal of Korea Game Society
• /
• v.8 no.3
• /
• pp.23-30
• /
• 2008

To strengthen the competitiveness of the game industry, one needs to develope a tool for evaluation of the satisfaction level of the game users, which leads to the improvement of the quality of games and increment of the amount of game trade. In this study, we developed factors to measure the satisfaction level and estimate their distributional properties. For the purpose, using a survey data for RPG games, we discussed several aspects for normalization of score distribution for satisfaction factors and estimated their density function by use of parametric density estimation of SAS/INSIGHT. We believe that the proposed results help us to predict or estimate the satisfaction level of newly developed games as well as the current popular games.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.11-19
• /
• 1994

The matching probability P(ο/$\lambda$), of the signal sequence(ο) observed for a finite time interval with a HMM (Hidden Markov Model $\lambda$) indicates the probability that signal comes from the given model. By utilizing the fact that the probability represents matching score of the observed signal with the model we can recognize an unknown signal pattern by comparing the magnitudes of the matching probabilities with respect to the known models. Because the algorithm however uses floating point variables during the computing process hardware implementation of the algorithm requires floating point units. This paper proposes an integer algorithm which uses positive integer numbers rather than float point ones to compute the matching probability so that we can economically realize the algorithm into hardware. The algorithm makes the model parameters integer numbers by multiplying positive constants and prevents from divergence of data through the normalization of variables at each step. The final equation of matching probability is composed of constant terms and a variable term which contains logarithm operations. A scheme to make the log conversion table smaller is also presented. To analyze the qualitive characteristics of the proposed algorithm we attatch simulation result performed on two groups of 10 hypothetic models respectively and inspect the statistical properties with repect to the model order the magnitude of scaling constants and the effect of the observation length.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.383-387
• /
• 2003

This paper deals with the method of speaker verification based on the conventional cohort of fixed size. In particular, a new cohort of variable size, which makes use of the distance between speaker models, is proposed: The density of neighboring speaker models within the fixed distance from each speaker is taken into account in the proposed method. The high density leads to the increase of cohort size, thus improving the speaker verification rate. On the other hand, the low density leads to its decrease, thus reducing the amount of computations. The simulation results show that the proposed method outperforms the conventional one, achieving a reduction in the EER.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.27 no.6
• /
• pp.311-320
• /
• 2023

When an earthquake occurs, the severity of damage is determined by natural factors such as the magnitude of the earthquake, the epicenter distance, soil properties, and type of the structures in the affected area, as well as the socio-economic factors such as the population, disaster prevention measures, and economic power of the community. This study evaluated the direct economic loss due to building damage and the community's recovery ability. Building damage was estimated using fragility functions due to the design earthquake by the seismic design code. The usage of the building was determined from the information in the building registrar. Direct economic loss was evaluated using the standard unit price and estimated building damage. The standard unit price was obtained from the Korean Real Estate Board. The community's recovery capacity was calculated using nine indicators selected from regional statistical data. After appropriate normalization and factor analysis, the recovery ability score was calculated through relative evaluation with neighboring cities.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.290-297
• /
• 2024

We investigate the efficacy of ensemble learning methods, specifically the soft voting technique, for enhancing heart disease prediction accuracy. Our study uniquely combines Logistic Regression, SVM with RBF Kernel, and Random Forest models in a soft voting ensemble to improve predictive performance. We demonstrate that this approach outperforms individual models in diagnosing heart disease. Our research contributes to the field by applying a well-curated dataset with normalization and optimization techniques, conducting a comprehensive comparative analysis of different machine learning models, and showcasing the superior performance of the soft voting ensemble in medical diagnosis. This multifaceted approach allows us to provide a thorough evaluation of the soft voting ensemble's effectiveness in the context of heart disease prediction. We evaluate our models based on accuracy, precision, recall, F1 score, and Area Under the ROC Curve (AUC). Our results indicate that the soft voting ensemble technique achieves higher accuracy and robustness in heart disease prediction compared to individual classifiers. This study advances the application of machine learning in medical diagnostics, offering a novel approach to improve heart disease prediction. Our findings have significant implications for early detection and management of heart disease, potentially contributing to better patient outcomes and more efficient healthcare resource allocation.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.41-51
• /
• 2024

In this paper, we explore the enhancement of target detection accuracy in the guided weapon using deep learning object detection on infrared (IR) images. Due to the characteristics of IR images being influenced by factors such as time and temperature, it's crucial to ensure a consistent representation of object features in various environments when training the model. A simple way to address this is by emphasizing the features of target objects and reducing noise within the infrared images through appropriate pre-processing techniques. However, in previous studies, there has not been sufficient discussion on pre-processing methods in learning deep learning models based on infrared images. In this paper, we aim to investigate the impact of image pre-processing techniques on infrared image-based training for object detection. To achieve this, we analyze the pre-processing results on infrared images that utilized global or local information from the video and the image. In addition, in order to confirm the impact of images converted by each pre-processing technique on object detector training, we learn the YOLOX target detector for images processed by various pre-processing methods and analyze them. In particular, the results of the experiments using the CLAHE (Contrast Limited Adaptive Histogram Equalization) shows the highest detection accuracy with a mean average precision (mAP) of 81.9%.

• Journal of Advanced Navigation Technology
• /
• v.5 no.1
• /
• pp.1-10
• /
• 2001

Speech has a good characteristics of which car drivers busy to concern with miscellaneous operation can make use in convenient handling and manipulating of devices. By utilizing this, this works proposes a speaker verification method for protecting cars from being stolen and identifying a person trying to access critical on-line services. In this, continuant phonemes recognition which uses language information of speech and MLP(mult-layer perceptron) which has some advantages against previous stochastic methods are adopted. The recognition method, though, involves huge computation amount for learning, so it is somewhat difficult to adopt this in speaker verification application in which speakers should enroll themselves at real time. To relieve this problem, this works presents a solution that introduces speaker cohort models from speaker verification score normalization technique established before, dividing background speakers into small cohorts in advance. As a result, this enables computation burden to be reduced through classifying the enrolling speaker into one of those cohorts and going through enrollment for only that cohort.

• Journal of Korean Neurosurgical Society
• /
• v.50 no.4
• /
• pp.357-362
• /
• 2011

Objective : To report our experience with pyogenic spondylitis treated with anterior radical debridement and insertion of a titanium mesh cage and to demonstrate the effectiveness and safety of the use of a titanium mesh cage in the surgical management of pyogenic spondylitis. Methods : We retrospectively analyzed the clinical characteristics of 19 patients who underwent surgical treatment in our department between January 2004 and December 2008. The average follow-up period was 11.16 months (range, 6-64 months). We evaluated risk factors, cultured organisms, lab data, clinical outcomes, and radiographic results. Surgical techniques for patients with pyogenic spondylitis were anterior radical debridement and reconstruction with titanium mesh cage insertion and screw fixation. All patients received intravenous antibiotics for at least 6 weeks postoperatively, and some patients received oral antibiotics. Results : The infections resolved in all of the patients as noted by normalization of their erythrocyte sedimentation rates and C-reactive protein levels. The mean pain score on a Visual Analog Scale was 7.8 (range, 4-10) before surgery and 2.4 (range, 1-5) after surgery. The Frankel grade was improved by one grade in seven patients. After surgery, the average difference of the angle was improved about $6.96^{\circ}$ in all patients. At the last follow-up, the mean loss of correction was $4.86^{\circ}$. Conclusion : Anterior radical debridement followed by the placement of instrumentation with a titanium mesh cage may be a safe and effective treatment for selected patients with pyogenic spondylitis. This surgical therapy does not lead to recurrent pyogenic spondylitis.