• International Journal of Contents
• /
• 제8권1호
• /
• pp.23-29
• /
• 2012

Multiple expression levels of genes obtained using time series microarray experiments have been exploited effectively to enhance understanding of a wide range of biological phenomena. However, the unique nature of microarray data is usually in the form of large matrices of expression genes with high dimensions. Among the huge number of genes presented in microarrays, only a small number of genes are expected to be effective for performing a certain task. Hence, discounting the majority of unaffected genes is the crucial goal of gene selection to improve accuracy for disease diagnosis. In this paper, a non-Gaussian weight matrix obtained from an incremental model is proposed to extract useful features of multivariate time series microarrays. The proposed method can automatically identify a small number of significant features via discovering hidden variables from a huge number of features. An unsupervised hierarchical clustering representative is then taken to evaluate the effectiveness of the proposed methodology. The proposed method achieves promising results based on predictive accuracy of clustering compared to existing methods of analysis. Furthermore, the proposed method offers a robust approach with low memory and computation costs.

• 제어로봇시스템학회논문지
• /
• 제9권11호
• /
• pp.874-882
• /
• 2003

The condition assessment of engineering systems has increased in importance because the manpower needed to operate and supervise various plants has been reduced. Especially, induction motors are at the core of most engineering processes, and there is an indispensable need to monitor their health and performance. So detection and diagnosis of motor faults is a base to improve efficiency of the industrial plant. In this paper, a model-based fault detection system is developed for induction motors, using steady state vibration signals. Early various fault detection systems using vibration signals are a trivial method and those methods are prone to have missed fault or false alarms. The suggested motor fault detection system was developed using a model-based reference value. The stationary signal had been extracted from the non-stationary signal using a data segmentation method. The signal processing method applied in this research is FFT. A reference model with spectra signal is developed and then the residuals of the vibration signal are generated. The ratio of RMS values of vibration residuals is proposed as a fault indicator for detecting faults. The developed fault detection system is tested on 800 hp motor and it is shown to be effective for detecting faults in the air-gap eccentricities and broken rotor bars. The suggested system is shown to be effective for reducing missed faults and false alarms. Moreover, the suggested system has advantages in the automation of fault detection algorithms in a random signal system, and the reference model is not complicated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2333-2345
• /
• 2024

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

• 전자공학회논문지
• /
• 제51권1호
• /
• pp.185-194
• /
• 2014

한국에서 만성위염은 10명당 한 명 꼴로 발생하는 질병이다. 만성위염을 진단하기 위해서 일반적으로 내시경 검사를 하지만 이는 환자에게 고통을 주고 비용이 비싸다는 단점을 가지고 있다. 한편 비침습적이고 저비용인 전통한방의학의 맥진에 따르면, 오른쪽 손목의 '관' 위치에서 비위의 기능적 이상을 진단할 수 있다. 본 연구에서는, 전통한방의학의 견해에 따라 오른쪽 손목 '관' 부위의 맥파를 분석하여 만성위염 판별모델을 개발하였다. 모델의 판별률을 비교하기 위해, 피크-밸리 검출법과 가우시안 모델을 적용한 상이한 방법의 특징점 추출방법에 대해 선형판별분석 기법과 로지스틱 회귀분석법을 적용해 보았다. 그 결과, 판별모델과 특징점 추출 방법에 따라 77%~89%의 민감도와 72%~83%의 특이도를 보였고 각 모델의 평균 판별률은 약 80% 내외로 얻어졌다. 구체적으로, 가우시안 모델이 상대적으로 우수한 민감도(89.1%와 87.5%)를 보인 반면, 피크-밸리 검출법은 우수한 특이도(82.8%와 81.3%)를 보였고, 평균적인 판별률에 있어서는 가우시안 모델이 1.2% 정로 앞섰다(80.9% vs 79.7%). 결론적으로, 전통의학적 맥진원리에 기반한 요골동맥 맥파의 특성을 이용하여 유의미한 만성위염 판별모델을 얻을 수 있었고, 민감도에 있어서 가우시안 모델이 더 우수하였고, 특이도에 있어서 피크-밸리 검출법이 더 우수하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권5호
• /
• pp.1911-1915
• /
• 2012

Aim: New technologies for the early detection of pancreatic cancer (PC) are urgently needed. The aim of the present study was to screen for the potential protein biomarkers in serum using proteomic fingerprint technology. Methods: Magnetic beads combined with surface-enhanced laser desorption/ionization (SELDI) TOF MS were used to profile and compare the protein spectra of serum samples from 85 patients with pancreatic cancer, 50 patients with acute-on-chronic pancreatitis and 98 healthy blood donors. Proteomic patterns associated with pancreatic cancer were identified with Biomarker Patterns Software. Results: A total of 37 differential m/z peaks were identified that were related to PC (P < 0.01). A tree model of biomarkers was constructed with the software based on the three biomarkers (7762 Da, 8560 Da, 11654 Da), this showing excellent separation between pancreatic cancer and non-cancer., with a sensitivity of 93.3% and a specificity of 95.6%. Blind test data showed a sensitivity of 88% and a specificity of 91.4%. Conclusions: The results suggested that serum biomarkers for pancreatic cancer can be detected using SELDI-TOF-MS combined with magnetic beads. Application of combined biomarkers may provide a powerful and reliable diagnostic method for pancreatic cancer with a high sensitivity and specificity.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권6호
• /
• pp.393-402
• /
• 2015

조직을 구성하는 인적자원은 조직의 중요한 구성요소 중 하나다. 특히 통제된 조직일수록 인적자원의 가치는 조직의 목표 달성을 위해 더욱 중요하다. 현재까지의 조직 구성원 진단은 과거 병력과 같은 외연적인 개인의 특성 및 인성검사와 같은 자발적 진단결과를 통해서 이루어지고 있다. 그러나 구성원 개인단위에 대한 진단방법은 설문 내용이 방대하고 본인의 응답에 전적으로 의존하는 것이어서 거짓 응답 및 은폐 등의 단점이 있으며 소요되는 시간 또한 길다. 이러한 단점을 극복할 수 있는 객관적 진단방법으로 구성원 상호간 진단방법이 있으나, 사람과 사람사이의 눈에 보이지 않는 관계를 표현하고 분석하기 어렵다는 제한사항이 있다. 본 논문에서는 구성원 상호간 진단방법을 통한 조직 진단 모델인 다면평가 모델을 제안한다. 이 모델은 10분 내외의 설문으로 조직의 사회 연결망을 구성한 후 소셜 네트워크 분석 기법을 이용한 제안된 알고리즘을 통해 조직을 진단한다. 실험결과 표본 집단에서 특별 관리하는 인원과 비교하여 Weighted Precision 0.62를 보였으며, 기존 방법으로 식별되지 않는 인원들을 식별할 수 있었다. 본 연구에서 제안하는 모델을 기반으로 조직 진단 시각화 시스템을 구성한다면 인적자원을 관리하는 모든 조직 관리자에게 유용한 시스템이 될 것이다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권19호
• /
• pp.8371-8376
• /
• 2014

Background: The use of statistical methods has become an imperative tool in breast cancer survival data analysis. The purpose of this study was to develop the best statistical probability model using the Bayesian method to predict future survival times for the black non-Hispanic female breast cancer patients diagnosed during 1973-2009 in the U.S. Materials and Methods: We used a stratified random sample of black non-Hispanic female breast cancer patient data from the Surveillance Epidemiology and End Results (SEER) database. Survival analysis was performed using Kaplan-Meier and Cox proportional regression methods. Four advanced types of statistical models, Exponentiated Exponential (EE), Beta Generalized Exponential (BGE), Exponentiated Weibull (EW), and Beta Inverse Weibull (BIW) were utilized for data analysis. The statistical model building criteria, Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC) were used to measure the goodness of fit tests. Furthermore, we used the Bayesian approach to obtain the predictive survival inferences from the best-fit data based on the exponentiated Weibull model. Results: We identified the highest number of black non-Hispanic female breast cancer patients in Michigan and the lowest in Hawaii. The mean (SD), of age at diagnosis (years) was 58.3 (14.43). The mean (SD), of survival time (months) for black non-Hispanic females was 66.8 (30.20). Non-Hispanic blacks had a significantly increased risk of death compared to Black Hispanics (Hazard ratio: 1.96, 95%CI: 1.51-2.54). Compared to other statistical probability models, we found that the exponentiated Weibull model better fits for the survival times. By making use of the Bayesian method predictive inferences for future survival times were obtained. Conclusions: These findings will be of great significance in determining appropriate treatment plans and health-care cost allocation. Furthermore, the same approach should contribute to build future predictive models for any health related diseases.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권10호
• /
• pp.606-610
• /
• 2003

Noise subtraction using reference channel data has been used to improve signal-to-noise ratio in magnetoencephalography. In this paper, an adaptive noise subtraction model is proposed and parameters for the model are optimized. A criterion to determine an optimal update period for the filter coefficients is proposed based on the ratio of peak amplitude of evoked field (N100m) divided by the output standard deviation. Experiments are carried out using a 40 channel MEG system. From the experiments, the proposed noise subtraction method shows superior performances over existing non-adaptive methods. Two-dimensional topographic map is shown for a diagnosis with a cubic spline interpolation.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권21호
• /
• pp.9453-9458
• /
• 2014

Background: Breast cancer is the second leading cause of cancer death for women in the United States. Differences in survival of breast cancer have been noted among racial and ethnic groups, but the reasons for these disparities remain unclear. This study presents the characteristics and the survival curve of two racial and ethnic groups and evaluates the effects of race on survival times by measuring the lifetime data-based half-normal model. Materials and Methods: The distributions among racial and ethnic groups are compared using female breast cancer patients from nine states in the country all taken from the National Cancer Institute's Surveillance, Epidemiology, and End Results cancer registry. The main end points observed are: age at diagnosis, survival time in months, and marital status. The right skewed half-normal statistical probability model is used to show the differences in the survival times between black Hispanic (BH) and black non-Hispanic (BNH) female breast cancer patients. The Kaplan-Meier and Cox proportional hazard ratio are used to estimate and compare the relative risk of death in two minority groups, BH and BNH. Results: A probability random sample method was used to select representative samples from BNH and BH female breast cancer patients, who were diagnosed during the years of 1973-2009 in the United States. The sample contained 1,000 BNH and 298 BH female breast cancer patients. The median age at diagnosis was 57.75 years among BNH and 54.11 years among BH. The results of the half-normal model showed that the survival times formed positive skewed models with higher variability in BNH compared with BH. The Kaplan-Meir estimate was used to plot the survival curves for cancer patients; this test was positively skewed. The Kaplan-Meier and Cox proportional hazard ratio for survival analysis showed that BNH had a significantly longer survival time as compared to BH which is consistent with the results of the half-normal model. Conclusions: The findings with the proposed model strategy will assist in the healthcare field to measure future outcomes for BH and BNH, given their past history and conditions. These findings may provide an enhanced and improved outlook for the diagnosis and treatment of breast cancer patients in the United States.

• 융합신호처리학회논문지
• /
• 제20권4호
• /
• pp.226-231
• /
• 2019

한방 설진에서 WTCI(Winkel Tongue Coating Index) 설태 평가는 환자의 설태량 측정을 위한 중요한 객관적인 지표 중의 하나이다. 그러나 이전의 WTCI 설태 평가는 혀영상으로부터 설태 부분을 추출하여 전체 혀 영역에서 추출된 설태 영역의 비율을 정량적으로 측정하는 방법이 대부분으로 혀영상의 촬영 조건이나 설태 인식 성능에 의해서 비객관적 측정의 문제점이 있었다. 따라서 본 논문에서는 빅데이터를 기반으로 하는 인공지능의 딥러닝 방법을 적용하여 설태량을 분류하여 평가하는 딥러닝 기반의 WTCI 평가 방법을 제안하고 검증한다. 설태 평가 방법에 있어서 딥러닝의 유효성 검증을 위해서는 CNN을 학습 모델로 사용하여 소태, 박태, 후태의 3가지 유형의 설태량을 분류한다. 설태 샘플 영상을 학습 및 검증 데이터로 구축하여 CNN 기반의 딥러닝 모델로 학습한 결과 96.7%의 설태량 분류 정확성을 보였다.