• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.163-166
• /
• 2005

We propose a speech emotion recognition method for natural human-robot interface. In the proposed method, emotion is classified into 6 classes: Angry, bored, happy, neutral, sad and surprised. Features for an input utterance are extracted from statistics of phonetic and prosodic information. Phonetic information includes log energy, shimmer, formant frequencies, and Teager energy; Prosodic information includes pitch, jitter, duration, and rate of speech. Finally a patten classifier based on Gaussian support vector machines decides the emotion class of the utterance. We record speech commands and dialogs uttered at 2m away from microphones in 5different directions. Experimental results show that the proposed method yields 59% classification accuracy while human classifiers give about 50%accuracy, which confirms that the proposed method achieves performance comparable to a human.

• Agribusiness and Information Management
• /
• 제12권2호
• /
• pp.24-39
• /
• 2021

As the number of fields adopting ICT (Information and Communication Technology) increased, it was necessary to diagnose the information service status of corporations and present improvement plans in agriculture. Therefore, we designed and conducted various surveys to understand the information service status of domestic agricultural company corporations.The research included ways to utilize information technology, establishing infrastructure related to information technology, current status of information technology application and impact on performance. Specifically, the main purpose of this study was to subdivide related corporations by industry and sales level and provide differentiated management implications for each sector. This is because the type of information service and information technology support that each corporation needs varies greatly depending on the industry and sales level. We provide customized management and policy proposals based on descriptive statistics and regression techniques.

• Communications for Statistical Applications and Methods
• /
• 제26권1호
• /
• pp.69-78
• /
• 2019

A structured model with both single-index and varying coefficients is a powerful tool in modeling high dimensional data. It has been widely used because the single-index can overcome the curse of dimensionality and varying coefficients can allow nonlinear interaction effects in the model. For high dimensional index vectors, variable selection becomes an important question in the model building process. In this paper, we propose an efficient estimation and a variable selection method based on a smoothing spline approach in a partially linear single-index-coefficient regression model. We also propose an efficient algorithm for simultaneously estimating the coefficient functions in a data-adaptive lower-dimensional approximation space and selecting significant variables in the index with the adaptive LASSO penalty. The empirical performance of the proposed method is illustrated with simulated and real data examples.

• 근관절건강학회지
• /
• 제28권1호
• /
• pp.70-78
• /
• 2021

Purpose: Flipped learning is a novel teaching strategy for encouraging students to engage in the learning process. This study aimed to redesign the public health nursing course and examine the implications of flipped learning on learning outcomes, self-efficacy, and self-leadership in undergraduate programs. Methods: A one-group, pretest-posttest design was used. A total of 80 students participated in this study. The flipped learning method was employed between April 14 and June 5, 2016. The data were analyzed using descriptive statistics and an independent t-test. Results: The self-efficacy of the lower 25% group based on academic performance was significantly increased; however, self-leadership did not show any change after utilizing flipped learning. Overall, 65.4% of the students were satisfied with their class. Conclusion: Flipped learning was an effective strategy for students with low achievement. Despite these advantages, it was considered to reduce the burden of studying.

• Nonlinear Functional Analysis and Applications
• /
• 제26권2호
• /
• pp.347-371
• /
• 2021

A plethora of applications from mathematical programmings, such as minimax, mathematical programming, penalization and fixed point problems can be framed as variational inequality problems. Most of the methods that used to solve such problems involve iterative methods, that is why, in this paper, we introduce a new extragradient-like method to solve pseudomonotone variational inequalities in a real Hilbert space. The proposed method has the advantage of a variable step size rule that is updated for each iteration based on previous iterations. The main advantage of this method is that it operates without the previous knowledge of the Lipschitz constants of an operator. A strong convergence theorem for the proposed method is proved by letting the mild conditions on an operator 𝒢. Numerical experiments have been studied in order to validate the numerical performance of the proposed method and to compare it with existing methods.

• Genomics & Informatics
• /
• 제19권4호
• /
• pp.36.1-36.11
• /
• 2021

Predicting individual traits and diseases from genetic variants is critical to fulfilling the promise of personalized medicine. The genetic variants from genome-wide association studies (GWAS), including variants well below GWAS significance, can be aggregated into highly significant predictions across a wide range of complex traits and diseases. The recent arrival of large-sample public biobanks enables highly accurate polygenic predictions based on genetic variants across the whole genome. Various statistical methodologies and diverse computational tools have been introduced and developed to computed the polygenic risk score (PRS) more accurately. However, many researchers utilize PRS tools without a thorough understanding of the underlying model and how to specify the parameters for the best performance. It is advantageous to study the statistical models implemented in computational tools for PRS estimation and the formulas of parameters to be specified. Here, we review a variety of recent statistical methodologies and computational tools for PRS computation.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 춘계학술발표대회
• /
• pp.1045-1046
• /
• 2009

본 논문에서는 이산 이벤트 시뮬레이터인 SMPL을 이용하여 노변 네트워크에서의 데이터 처리에 따르는 데이터 캐쉬 성능분석기를 구현한다. 구현된 성능분석기는 SMPL의 요청 도착과 서비스 사건 처리를 기본 골격으로 하여 실제 차량의 궤적 데이터에 기반한 데이터 요청 생성부와 큐잉 정책과 캐쉬 정책을 선택할 수 있는 정책 처리부 등으로 구성된다. 이 분석기는 서비스율, 해당 정책, 캐쉬의 크기 등의 수행인자를 설정하여 이에 따르는 큐 길이의 분포, 캐쉬의 히트율, 요청 처리시간의 분포 등을 측정할 수 있도록 한다. 추정된 성능 요소를 기반으로 노변 네트워크에 기반한 차량 텔레매틱스 시스템에서 RSU(RoadSide Unit)의 배치, 성능 요구사항 분석, 새로운 큐잉 정책과 캐쉬 정책의 설계 등 다양한 응용이 가능하다.

• Journal of Preventive Medicine and Public Health
• /
• 제32권4호
• /
• pp.538-545
• /
• 1999

Objective : To compare the predictive power of International Classification of Diseases 10th Edition(ICD-10) based International Classification of Diseases based Injury Severity Score(ICISS) with Trauma and Injury Severity Score(TRISS) and International Classification of Diseases 9th Edition Clinical Modification(ICD-9CM) based ICISS in the injury severity measure. Methods : ICD-10 version of Survival Risk Ratios(SRRs) was derived from 47,750 trauma patients from 35 Emergency Centers for 1 year. The predictive power of TRISS, the ICD-9CM based ICISS and ICD-10 based ICISS were compared in a group of 367 severely injured patients admitted to two university hospitals. The predictive power was compared by using the measures of discrimination(disparity, sensitivity, specificity, misclassification rates, and ROC curve analysis) and calibration(Hosmer-Lemeshow goodness-of-fit statistics), all calculated by logistic regression procedure. Results : ICD-10 based ICISS showed a lower performance than TRISS and ICD-9CM based ICISS. When age and Revised Trauma Score(RTS) were incorporated into the survival probability model, however, ICD-10 based ICISS full model showed a similar predictive power compared with TRISS and ICD-9CM based ICISS full model. ICD-10 based ICISS had some disadvantages in predicting outcomes among patients with intracranial injuries. However, such weakness was largely compensated by incorporating age and RTS in the model. Conclusions : The ICISS methodology can be extended to ICD-10 horizon as a standard injury severity measure in the place of TRISS, especially when age and RTS were incorporated in the model. In patients with intracranial injuries, the predictive power of ICD-10 based ICISS was relatively low because of differences in the classifying system between ICD-10 and ICD-9CM.

• 기본간호학회지
• /
• 제14권3호
• /
• pp.288-296
• /
• 2007

Purpose: This study was conducted to investigate the effects of self-efficacy promoting program on self-efficacy, self-care behavior and psychosocial adaptation in patients with a colostomy. Method: A non-equivalent control group pre test post test design was used. The self efficacy promoting programs was composed of a CD image program based on varicaious experience, education and telephone coaching program based on verbal persuasion, and Stoma care practice, and Self care performance based on performance accomplishment. This study was carried out from July 2, 2005 to April 20, 2006 and 21 patients with a colostomy at one of 2 hospitals participated. Descriptive statistics, ${\chi}^2-test$, and Mann-whitney U test were used to analyze the data. Results: There were significantly different for specific self efficacy, self care and psychosocial adaptation between the experimental group and control group. Conclusion: The self efficacy promoting program for patients with stomas was effective in improving degree of specific self efficacy, self care and psychosocial adaptation.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제12권5호
• /
• pp.275-285
• /
• 2006

본 논문에서는 그리드 컴퓨팅의 기존 자원 거래망 모델들의 문제점을 분석하고, 해결하기 위한 새로운 자원 거래 모델을 제안한다. 이 모델은 사용자와 자원 공급자 사이의 거래 가격을 예측하고 합리적인 거래 가격을 제시한다. 합리적인 가격 제안을 통해, 사용자와 자원 공급자 사이의 더 많은 자원 거래를 발생시키고, 사용자는 더 짧은 시간에 자원을 공급받게 된다. 본 논문에서 사용자의 자원 요구량 예측 정확도를 향상시키기 위하여 통계학의 예측 모델을 도입하였고 합리적인 가격 제안을 위해 미시 경제학의 가격 결정 이론을 도입하였다. 본 모델의 성능 평가를 위하여 사용자의 자원 요구량 예측 정확도, 자원 거래를 위한 응답시간, 자원 거래 횟수 그리고 사용자의 자원 활용률을 측정하였다. 실험의 결과로는 자원 예측 정확도는 87.45%의 신뢰성 있는 결과를 얻었고, 기존 모델들에 비해 응답시간은 72.39% 단축 되었다. 또한, 자원 거래 횟수는 162.56% 증가 하였다. 본 논문에서 제안하는 모델의 평균 자원 활용률은 90%에 근접했으며 기존 모델들과 비교해서는 230%이상 자원 활용률이 증가 하였다.