• 대한산업공학회지
• /
• 제24권2호
• /
• pp.199-209
• /
• 1998

Consumers turn away their face from a vehicle that doesn't satisfy their sensibility and is designed without consideration of driver's performance. In terms of driver's performance, the manual motor processor carries out the primary interactions between driver and vehicle. Therefore, in this paper, time prediction model is studied that is an important part when drivers manipulate the manual control during driving. Experiments were executed for 20 subjects using two kinds of vehicles and regressed to Fitts' Law. The noise filtering method was suggested for the performance times of manipulating the manual control. Especially, it was shown that Fitts' Law derived by an approximation of Shannon's theorem can predict drivers performance time more appropriately than other methods.

• 전기학회논문지
• /
• 제67권11호
• /
• pp.1506-1511
• /
• 2018

This study presents a human sensibility evaluation method using neural network and multiple-template method on electroencephalogram(EEG). We used a multi-layer perceptron type neural network as the sensibility classifier using EEG signal. For our research objective, 10-channel EEG signals are collected from the healthy subjects. After the necessary preprocessing is performed on the acquired signals, the various EEG parameters are estimated and their discriminating performance is evaluated in terms of pattern classification capability. In our study, Linear Prediction(LP) coefficients are utilized as the feature parameters extracting the characteristics of EEG signal, and a multi-layer neural network is used for indicating the degree of human sensibility. Also, the estimation for human comfortableness is performed by varying temperature and humidity environment factors and our results showed that the proposed scheme achieved good performances for evaluation of human sensibility.

• 지능정보연구
• /
• 제21권4호
• /
• pp.37-51
• /
• 2015

인터넷 기술의 발전과 인터넷 상 데이터의 급속한 증가로 인해 데이터의 활용 목적에 적합한 분석방안 연구들이 활발히 진행되고 있다. 최근에는 텍스트 마이닝 기법의 활용에 대한 연구들이 이루어지고 있으며, 특히 문서 내 텍스트를 기반으로 문장이나 어휘의 긍정, 부정과 같은 극성 분포에 따라 의견을 스코어링(scoring)하는 감성분석과 관련된 연구들도 다수 이루어지고 있다. 이러한 연구의 연장선상에서, 본 연구는 인터넷 상의 특정 기업에 대한 뉴스 데이터를 수집하여 이들의 감성분석을 실시함으로써 주가의 등락에 대한 예측을 시도하였다. 개별 기업의 뉴스 정보는 해당 기업의 주가에 영향을 미치는 요인으로, 적절한 데이터 분석을 통해 주가 변동 예측에 유용하게 활용될 수 있을 것으로 기대된다. 따라서 본 연구에서는 개별 기업의 온라인 뉴스 데이터에 대한 감성분석을 바탕으로 개별 기업의 주가 변화 예측을 꾀하였다. 이를 위해, KOSPI200의 상위 종목들을 분석 대상으로 선정하여 국내 대표적 검색 포털 서비스인 네이버에서 약 2년간 발생된 개별 기업의 뉴스 데이터를 수집 분석하였다. 기업별 경영 활동 영역에 따라 기업 온라인 뉴스에 나타나는 어휘의 상이함을 고려하여 각 개별 기업의 어휘사전을 구축하여 분석에 활용함으로써 감성분석의 성능 향상을 도모하였다. 분석결과, 기업별 일간 주가 등락여부에 대한 예측 정확도는 상이했으며 평균적으로 약 56%의 예측률을 보였다. 산업 구분에 따른 주가 예측 정확도를 통하여 '에너지/화학', '생활소비재', '경기소비재'의 산업군이 상대적으로 높은 주가 예측 정확도를 보임을 확인하였으며, '정보기술'과 '조선/운송' 산업군은 주가 예측 정확도가 낮은 것으로 확인되었다. 본 논문은 온라인 뉴스 정보를 활용한 기업의 어휘사전 구축을 통해 개별 기업의 주가 등락 예측에 대한 분석을 수행하였으며, 향후 감성사전 구축 시 불필요한 어휘가 추가되는 문제점을 보완한 연구 수행을 통하여 주가 예측 정확도를 높이는 방안을 모색할 수 있을 것이다.

• 전기학회논문지
• /
• 제59권4호
• /
• pp.823-830
• /
• 2010

This study was designed to examine the morphological measurement and characteristics of trabecullae based on femoral radiographic image for prediction of osteoporosis. Study subjects were 34 females (average age of 62.1 years) and 6 males (average age of 60.1 years), they were categorized into normal group and osteoporosis group in accordance with the T-score value. Measurement of the bone density of femoral bone was measured with DEXA(Dual Energy X-ray absorptiometry). ROI(Region of interests) was selected on femoral neck and trochanter. Characteristics of trabecullae was analyzed by using the skeletonization analysis of trabecular image. Morphological measurement was analyzed through femoral radiographic image in order to examine the correlation with osteoporosis. The result demonstrated statistically significant correlation between neck cortical thickness, shaft width, shaft cortical thickness, periphery, mean gray level and trabeculae area with BMD average (T-score) of femoral part. The results show that morphological measurement and characteristics of trabecullae based on femoral radiographic images for osteoporosis prediction could be effective.

• Nutrition Research and Practice
• /
• 제15권1호
• /
• pp.95-105
• /
• 2021

BACKGROUND/OBJECTIVES: The measurement of body composition, including muscle and fat mass, remains challenging in large epidemiological studies due to time constraint and cost when using accurate modalities. Therefore, this study aimed to develop and validate prediction equations according to sex to measure lean body mass (LBM), appendicular skeletal muscle mass (ASM), and body fat mass (BFM) using anthropometric measurement, serum creatinine level, and lifestyle factors as independent variables and dual-energy X-ray absorptiometry as the reference method. SUBJECTS/METHODS: A sample of the Korean general adult population (men: 7,599; women: 10,009) from the Korean National Health and Nutrition Examination Survey 2008-2011 was included in this study. The participants were divided into the derivation and validation groups via a random number generator (with a ratio of 70:30). The prediction equations were developed using a series of multivariable linear regressions and validated using the Bland-Altman plot and intraclass correlation coefficient (ICC). RESULTS: The initial and practical equations that included age, height, weight, and waist circumference had a different predictive ability for LBM (men: R2 = 0.85, standard error of estimate [SEE] = 2.7 kg; women: R2 = 0.78, SEE = 2.2 kg), ASM (men: R2 = 0.81, SEE = 1.6 kg; women: R2 = 0.71, SEE = 1.2 kg), and BFM (men: R2 = 0.74, SEE = 2.7 kg; women: R2 = 0.83, SEE = 2.2 kg) according to sex. Compared with the first prediction equation, the addition of other factors, including serum creatinine level, physical activity, smoking status, and alcohol use, resulted in an R2 that is higher by 0.01 and SEE that is lower by 0.1. CONCLUSIONS: All equations had low bias, moderate agreement based on the Bland-Altman plot, and high ICC, and this result showed that these equations can be further applied to other epidemiologic studies.

• 모자간호학회지
• /
• 제1권
• /
• pp.34-44
• /
• 1991

The purposes of this study were to predict newborn birthweight by use of gestational period and fundal height and to identify growth curve of fundal height according to gestational period and growth curve of newborn birthweight according to fundal height. The subjects for the study were 802 women who delivered the normal newborn babies at Seoul National University Hospital from Sep. 1, 1981 to Aug.31, 1986. The data were collected bit chart review and analyzed nth SPSS program. The results of study were as follows : 1. The multiple regression equation ($R^2$=0.416) used for the prediction of newborn birthweight was y=(newborn birthweight, kg)=-4.421+0.075$x_1$(fundal height, cm)+0.053$x_2$(gestational period, weeks)+0.016$x_3$(abdominal girth, cm)+0.010$x_4$(maternal height, cm) 2. The growth curve of fundal height according to gestational period was obtained by polynomial regression. The regression equation was Y(fundal height, cm)=-36.78+18.58$log_ex$(gestational period, weeks) The growth curve of newborn birth weight according to fundal height was obtained by polynomial regression. The regression equation was Y(newborn birthweight, kg)=-8.09+3.27$log_ex$ (Fundal Height, cm) 3. In the following subgroups no significant difference was found in fundal height : engaged vs. nonengaged presentation, and nulliparous vs. multiparous women.

• 대한의용생체공학회:의공학회지
• /
• 제30권1호
• /
• pp.94-102
• /
• 2009

In this paper, we propose a hearing impairment simulator considering reduced frequency selectivity of the hearing impaired, and verify it's performance through experiments. The reduced frequency selectivity was embodied by spectral smearing using linear prediction coding(LPC). The experiments are composed of 4 kinds of tests; pure tone test, speech reception threshold(SRT) test, and word recognition score(WRS) test without spectral smearing and with spectral smearing. The experiments of the hearing impairment simulator were performed with 9 subjects who have normal hearing. The amount of spectral smearing was controlled by LPC order. The percentile score of WRS test without smearing is $89.78{\pm}2.420%$. The scores of WRS with 24th LPC order and with 8th LPC order are $88.00{\pm}3.556%$ and $83.78{\pm}2.123%$ respectively. It is verified that WRS score is lowered by decreasing LPC order. This is a reasonable result considering that spectral smearing is getting heavier according to decreasing LPC order. It is confirmed that spectral smearing using LPC simulates the reduced frequency selectivity of the hearing impaired and affects the clearness of speech reception.

• 한국생활과학회지
• /
• 제18권6호
• /
• pp.1267-1276
• /
• 2009

The purpose of this study is to classify breast types and to inquire about characteristics depending on breast types of women subjects in their twenties. We researched size items affecting breast volume and regression equations for the prediction of breast volume, and thereby, we will be able to provide some basic data, useful to the development of the brassiere depending on breast types. As a result of categorizing the types of three breast types, "type 1" was characterized by big and greatest protrusion of the breast with large breast volume and a large bust, while "type 2" was characterized by flat breasts with the least breast volume and least bust, and "type 3" was characterized by breast location apart from the center front line. Breast volume is significant in establishment of the brassiere cup depending on breast type. Five items such as, the circumference of the breast, the length of the upper breast, the depth of the breast point, the length of the shoulder point-breast point, and the length of the inferior breast were extracted through regression equations for breast volume.

• The Korean Journal of Physiology
• /
• 제4권2호
• /
• pp.37-44
• /
• 1970

Human body volumes were calculated from the measurments of body height and body weight. Equations Suited to express the relations of height, weight, and surface area to show the body volume were derived from the body volume measurements by means of underwater. weighing method. Underwater body weights were corrected for the residual volume of long obtained by the Rahn's three breath method. Underwater weighing was performed on 173 male subjects aged between 13 and 51 years. Subjects were divided into 4 age groups, namely, 13-16 years group of 47 subjects, 16-19 years group of 46 subjects, adult group aged between 22 and 38 years comprising 45 subjects, and middle-aged group (40-51 years) of 35 subjects. The group division was made on .the basis of physical growth and development. The following results were obtained. 1. Body height (H, cm), body weight (W, kg), body surface area $S,\; m^{2})$, and body volume (V, liter.) interrelated closely. V/S showed a high correlation with W/H and the coefficient of correlation was r=0.97 irrespective of age group differences of the subjects. The coefficients of correlation between V/S and W/H in the total mate subjects as a single group was r=1.983. Subsequently the following regression equation was obtained. V = S X (54.84 W/H + 14.08) The agreement of body volume values obtained by the calculation and underwater weighing in the total subject group was better than that of the separate age group division. 2. The calculated values of body volume were: 40.4 l (euiqvalent to the body density value of 1.0562 kg/1) in 13-16 years group; 52.0 l (equivalent to density value of 1.0723 kg/l) in 16-19 years group; 55.3 l (equivalent to density value of 1.0570 kg/l) In the adult group; and 54. 0 l (equivalent to density value of 1.074 kg/l) in the middle-age group. The mean deviation of calculated from the measured volume value ranged between ${\pm}0.55$ and ${\pm}0.81$ liters. 3. The correlation between V/S and mean skinfold thickness of 4 sites (arm, back, iliac and chest) was high, namely, the coefficient of correlation was r=0.656. The coefficients of correlation between V./S and the $R\"{o}hrer$ index ranged between r=0.668 and r=0.810 affected by the difference in group age of the subject. The body volume (V) alone correlated poorly than V/S with mean skinfold thickness (r=0.606) and the $R\"{o}hrer$ index (r ranged between 0.274 and 0.588).

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권11호
• /
• pp.837-850
• /
• 2002

본 논문에서는 인지적 긍정/부정 선택 과제의 수행 시 뇌파를 이용하여 피험자의 반응시간 RT(response time)를 예측하는 방법에 관하여 기술한다. 실험 task에서 피험자는 시각적 자극에 대한 반응, 문제의 해석, 손 움직임의 조절, 손동작 등과 관련된 뇌활동을 한다. 이와 같은 피험자의 정신상태의 변화를 CT(cut time), ST(selection time), RP(repeated period) 등을 정의하여 모델링하고, 선택시간 ST를 감지하여 피험자의 반응시간 RT를 예측한다. ST를 감지하기 위하여 측정한 뇌파로부터 $\alpha$, $\beta$, ${\gamma}$파를 분리하고, 공간적인 관계를 고려하여 설정한 4쌍의 전극들로부터 3가지의 특징들을 추출한다. 추출한 특징들을 분석하여 각 피험자별로 나타나는 상세 규칙(specific rule)과 공통적인 특징들로 구성된 일반 규칙(meta rule)들을 설정한다. 8명의 피험자를 대상으로 설정한 규칙들을 적용하여 평균 83%의 ST 감지 성공률을 보이고, ST 감지 이후 약 0.73초에서 RT가 나타나는 것을 보인다. 설정한 규칙들의 타당성을 검증하기 위하여 8명 중 2명의 피험자에 대해서 재실험을 하고, 이들 데이타에 적용한 결과를 보인다. 본 논문에서 제안한 방법을 기존의 인지적인 정신상태 판별을 위한 방법들이나 왼손/오른손 동작구분 방법들과 결합하여 사용할 경우 BCI를 위한 기반 기술로 활용될 것으로 기대한다.