• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• pp.862-869
• /
• 2020

This study attempted to analyze human brain responses toward visual content through EEG signals and intended to measure brain wave reactions of different age groups to determine the sexuality level of the media. The experimental stimuli consist of three different video footage (rated ages 12, 15, and 18) to analyze how subjects react in situations where they actually watch sexual content. For measuring and analyzing brain wave reactions, EEG equipment records alpha, beta, and gamma wave responses of the subjects' left and right frontal lobes, temporal lobes, and occipital lobes. The subjects of this study were 28 total and they are divided into two groups. The experiment configures a sexual content classification scale with age or gender as a discriminating variable and brain region-specific response frequencies (left/right, frontal/temporal/occipital, alpha/beta/gamma waves) as independent variables. The experimental results showed the possibility of distinguishing gender and age differences. The apparent differences in brain wave response areas and bands among high school girls, high school boys, and college students are found. Using these brain wave response data, this study explored the potential of developing algorithm for measurement of age-specific responses to sexual content and apply it as a film rating.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.110-116
• /
• 2023

Recently, as various examples of machine learning have been applied in the healthcare field, deep learning technology has been applied to various tasks, such as electrocardiogram examination and body composition analysis using wearable devices such as smart watches. To utilize deep learning, securing data is the most important procedure, where human intervention, such as data classification, is required. In this study, we propose a model that uses a clustering algorithm, namely, the K-means clustering, to label body fat according to gender and age considering body size aspects, such as chest circumference and waist circumference, and classifies body fat into five groups from high risk to low risk using a convolutional neural network (CNN). As a result of model validation, accuracy, precision, and recall results of more than 95% were obtained. Thus, rational decision making can be made in the field of healthcare or obesity analysis using the proposed method.

• 사상체질의학회지
• /
• 제22권3호
• /
• pp.87-97
• /
• 2010

1. Objectives: In SCM, a personal Sasang constitution must be determined accurately before any Sasang treatment. The purpose of this study is to develop an objective method for classification of Sasang constitution. 2. Methods: We collected samples from 5 centers where SCM is practiced, and applied two-stage decision tree analysis on these samples. We recruited samples from 5 centers. The collected data were from subjects whose response to herbal medicine was confirmed according to Sasang constitution. 3. Results: The two-stage decision tree model shows higher classification power than a simple decision tree model. This study also suggests that gender must be considered in the first stage to improve the accuracy of classification. 4. Conclusions: We identified important factors for classifying Sasang constitutions through two-stage decision tree analysis. The two-stage decision tree model shows higher classification power than a simple decision tree model.

• 한국콘텐츠학회논문지
• /
• 제21권9호
• /
• pp.105-116
• /
• 2021

하브루타 교육은 짝을 지어 대화하고 토론하고 논쟁하는 방식의 질문 중심 교육이며, 특히 명화 하브루타는 명화에 대한 질문과 답변을 통해 그림의 감상 능력을 증진하고 표현력을 풍부하게 하기 위한 목적으로 시행되고 있다. 본 연구에서는 동양화를 대상으로 한 명화 하브루타를 지원하기 위해, 최신 딥러닝 기술을 활용하여 동양화 등장인물의 성별 관점에서 질문을 자동으로 생성하는 방안을 제시한다. 구체적으로 본 연구에서는 사전학습모델인 VGG16을 바탕으로 동양화 인물 중심의 미세조정을 수행하여 동양화의 인물 분석을 효과적으로 수행할 수 있는 모델을 제안한다. 또한 질문의 유형을 명화 하브루타에서 사용되는 사실 질문, 상상 질문, 그리고 적용 질문의 3가지 유형으로 분류하고, 각 질문을 등장인물에 따라 세분화하여 총 9가지의 질문 패턴을 도출하였다. 제안 방법론의 활용 가능성을 확인하기 위해 실제 동양화의 등장인물 300건을 분석한 실험을 수행하였으며, 실험 결과 제안 방법론에 따른 성별 분류 모델이 기존 모델에 비해 높은 정확도를 나타냄을 확인하였다.

• 사상체질의학회지
• /
• 제33권4호
• /
• pp.1-9
• /
• 2021

Objectives The purpose of this study was to check whether the classification of the individual's Body Mass Index (BMI) could be predicted by analyzing the voice data constructed at the Korean medicine data center (KDC) using machine learning. Methods In this study, we proposed a convolutional neural network (CNN)-based BMI classification model. The subjects of this study were Korean adults who had completed voice recording and BMI measurement in 2006-2015 among the data established at the Korean Medicine Data Center. Among them, 2,825 data were used for training to build the model, and 566 data were used to assess the performance of the model. As an input feature of CNN, Mel-frequency cepstral coefficient (MFCC) extracted from vowel utterances was used. A model was constructed to predict a total of four groups according to gender and BMI criteria: overweight male, normal male, overweight female, and normal female. Results & Conclusions Performance evaluation was conducted using F1-score and Accuracy. As a result of the prediction for four groups, The average accuracy was 0.6016, and the average F1-score was 0.5922. Although it showed good performance in gender discrimination, it is judged that performance improvement through follow-up studies is necessary for distinguishing BMI within gender. As research on deep learning is active, performance improvement is expected through future research.

• 패션비즈니스
• /
• 제14권5호
• /
• pp.78-92
• /
• 2010

The culture phenomenon, which the desire of self expression is noticeable and the diversity of gender identity is widely accepted, simply makes a difference in the lifestyle of one human being rather than the dichotomous classification of male and female. Now, the delicate and aesthetic sensitivity classified as the feminine characteristics is no longer the exclusive property of female and this refers to substituting it as a social gender from the concept of biological sex. This phenomenon has influenced on the male culture and is creating various codes according to the cultural gender extended from the gender as a social role. Also, the transition into the western lifestyle has extended the aesthetic emotion to accommodate new codes from the diversification and globalization of lifestyle. The mansumer power, which does not care too much about the money for the emotionally attached items, has enabled various fashion styles. After analyzing the diversified clothing behavior conducted by these people in connection with the social phenomenon, First, this shows the phenomenon of emotional value pursuit that finds pleasure over the clothing as the item of augmented reality is added to the concept of play, in which the real space referred to as garment and virtual space of playing the rock, paper and scissors game meet together within the augmented reality. Second, the convergence concept has enabled the coordination of new style by obscuring the area of design concept and this refers to the changes in design from the development of new items and transformation into double-style details. Third, the divergence that intensively provides specific use/convenience and specialized value shows a change in the fashion market from the phenomenon that admits various gene rations of culture and specifically, takes differently about the recognition of middle-aged males. Fourth, the variety seeking tendency receives attention as the value of future design together with the phenomenon of discriminative value pursuit. In the male fashion, it is linked to the collaboration with the design area and this tells that the fashion with the narcissistic cross-dressing and motto of neutral gender without being sided to male/female is rising.

• 한국정보기술학회논문지
• /
• 제16권11호
• /
• pp.11-21
• /
• 2018

본 논문에서는 사람을 대신하여 분류, 예측 하는 딥러닝 기술을 활용하여 목소리를 통해 남녀노소를 분류하는 연구를 수행한다. 연구과정은 기존 신경망 기반의 사운드 분류 연구를 살펴보고 목소리 분류를 위한 개선된 신경망을 제안한다. 기존 연구에서는 도시 데이터를 이용해 사운드를 분류하는 연구를 진행하였으나, 얕은 신경망으로 인한 성능 저하가 나타났으며 다른 소리 데이터에 대해서도 좋은 성능을 보이지 못했다. 이에 본 논문에서는 목소리 데이터를 전처리하여 특징값을 추출한 뒤 추출된 특징값을 기존 사운드 분류 신경망과 제안하는 신경망에 입력하여 목소리를 분류하고 두 신경망의 분류 성능을 비교 평가한다. 본 논문의 신경망은 망을 더 깊고 넓게 구성함으로써 보다 개선된 딥러닝 학습이 이루어지도록 하였다. 성능 결과로는 기존 연구와 본 연구의 신경망에서 각각 84.8%, 91.4%로 제안하는 신경망에서 약 6% 더 높은 정확도를 보였다.

• 한국전자거래학회지
• /
• 제21권1호
• /
• pp.147-163
• /
• 2016

스마트 기기 사용자의 성별 정보는 성공적인 개인화 서비스를 위해 중요하며, 스마트 기기로부터 수집된 멀티 모달 로그 데이터는 사용자의 성별 예측에 중요한 근거가 된다. 하지만 각 멀티 모달 데이터의 특성에 따라 다른 방식으로 성별 예측을 수행해야 한다. 따라서 본 연구에서는 스마트 기기로부터 발생한 로그 데이터 중 텍스트, 어플리케이션, 가속도 데이터에 기반한 각기 다른 분류기의 예측 결과를 다수결 방식으로 앙상블하여 최종 성별을 예측하는 기법을 제안한다. 텍스트 데이터를 이용한 분류기는 데이터 유출에 의한 사생활 침해 문제를 최소화하기 위해 웹 문서로부터 각 성별의 특징적 단어 집합을 도출하고 이를 기기로 전송하여 사용자의 기기 내에서 성별 분류를 수행한다. 어플리케이션 데이터에 기반한 분류기는 사용자가 실행한 어플리케이션들에 성별을 부여하고 높은 비율을 차지하는 성별로 사용자의 성별을 예측한다. 가속도 기반 분류기는 성별에 따른 사용자의 가속도 데이터 인스턴스를 학습한 SVM 모델을 사용하여 주어진 성별을 분류한다. 자체 제작한 안드로이드 어플리케이션을 통해 수집된 실제 스마트 기기 로그 데이터를 사용하여 제안하는 기법을 평가하였으며 그 결과 높은 예측 성능을 보였다.

• 대한한의학회지
• /
• 제40권4호
• /
• pp.29-40
• /
• 2019

Objectives: To analyze the prescription frequency of various herbs as either individual or major herbs (in terms of dosage) and their usage patterns in the treatment of different diseases for standardization of traditional Korean medicine. Methods: We analyzed the prescription database of patients at the Pusan National University Korean Medicine Hospital from the date of establishment of the hospital to February 2013. The complete prescription data were extracted from the electronic medical records of patients, and the prescription frequencies of individual herbs, particularly, of major herbs, were analyzed in terms of gender, age, and international classification of diseases (ICD) code. Results: The prescription frequency of individual herbs based on age and gender showed a similar pattern. Herbal mixtures were also distributed in a similar manner. The use of some herbs differed according to age and gender (Table 1.). The herbs that were used at high frequencies for a given ICD code had similar usage patterns in different categories. However, some major herbs in the "Jun (King)" category were used uniquely for a given ICD code (Table 2.). There was significant difference between male and female on ICD code E and N, but the other ICD codes had small differences. The ratio of herbal medicine by gender showed different usage patterns in each gender. Conclusions: The findings of our study provide fundamental data that reflect the real clinical conditions in South Korea, and therefore, can contribute to the standardization of TKM.

• 여성건강간호학회지
• /
• 제15권4호
• /
• pp.312-319
• /
• 2009

Purpose: The purpose of this study was to determine the discriminant factors of attitude pattern toward sexual violence of college women. Methods: A cross-sectional research design with non-probability samples was conducted. A total of 292 college women participated. The instruments were Attitude Pattern toward Sexual Violence, Self-Esteem Scale, Gender Role Scale, and Attitude toward Sexuality. Dependent variable is Attitude Pattern toward Sexual Violence, which is composed of two groups; cases either harmer blame or sufferer blame. Independent variables were self-esteem, attitude toward gender role, and attitude toward sexuality. Data were analyzed by SPSS WIN program and descriptive analysis, $x^2$-test, and discriminant analysis. Results: To assess the adequacy of classification, the overall hit ratio was 68.5%, and the significant predictor variable was attitude toward sexuality. Conclusion: Replication of the study needs to be considered to further enrich the specific knowledge base regarding attitude toward sexual violence among college women.