• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.809-819
• /
• 2020

Gender prediction accuracy increases as convolutional neural network (CNN) architecture evolves. This paper compares voting and ensemble schemes to utilize the already trained five CNN models to further improve gender prediction accuracy. The majority voting usually requires odd-numbered models while the proposed softmax-based voting can utilize any number of models to improve accuracy. The ensemble of CNN models combined with one more fully-connected layer requires further tuning or training of the models combined. With experiments, it is observed that the voting or ensemble of CNN models leads to further improvement of gender prediction accuracy and that especially softmax-based voters always show better gender prediction accuracy than majority voters. Also, compared with softmax-based voters, ensemble models show a slightly better or similar accuracy with added training of the combined CNN models. Softmax-based voting can be a fast and efficient way to get better accuracy without further training since the selection of the top accuracy models among available CNN pre-trained models usually leads to similar accuracy to that of the corresponding ensemble models.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권11호
• /
• pp.733-738
• /
• 2015

사용자의 인구통계학적 정보는 추천 시스템과 같은 개인화 서비스 발달에 도움이 되며, 모바일 사용 데이터는 사용자의 인구통계학적 정보 예측에 활용될 수 있다. 특히 텍스트 데이터는 성별 예측에 효과적인 것으로 알려져 있지만, 모바일 텍스트 데이터는 프라이버시 이슈가 존재하여 그 활용이 제한되고 있다. 본 연구에서는 디바이스 내 예측 방법론을 제안하여 모바일 텍스트 데이터를 사용하면서 프라이버시 이슈를 최소화는 동시에 사용자의 성별을 효과적으로 예측하고자 한다. 우선, 성별에 따른 특징이 반영된 웹문서를 수집하여 각 성별에 따른 특징적 단어 집합과 특징적 이모티콘 집합을 구성한다. 단어 집합과 이모티콘 집합을 디바이스 내에서 사용자의 모바일 데이터와 비교하여 성별을 각각 예측하고, 두 예측 결과를 앙상블하여 최종적인 성별 예측 결과를 도출한다. 피실험자들의 모바일 텍스트 데이터를 사용하여 성별 예측 실험을 수행하였으며 제안 방법론의 우수한 성능을 확인하였다.

• 대한간호학회지
• /
• 제42권6호
• /
• pp.810-818
• /
• 2012

Purpose: This study was done to explore factors relating to number of falls among community-dwelling elders, based on gender. Methods: Participants were 403 older community dwellers (male=206, female=197) aged 60 or above. In this study, 8 variables were identified as predictive factors that can result in an elderly person falling and as such, supports previous studies. The 8 variables were categorized as, exogenous variables; perceived health status, somatization, depression, physical performance, and cognitive state, and endogenous variables; fear of falling, ADL & IADL and frequency of falls. Results: For men, ability to perform ADL & IADL (${\beta}_{32}$=1.84, p<.001) accounted for 16% of the variance in the number of falls. For women, fear of falling (${\beta}_{31}$=0.14, p<.05) and ability to perform ADL & IADL (${\beta}_{32}$=1.01, p<.001) significantly contributed to the number of falls, accounting for 15% of the variance in the number of falls. Conclusion: The findings from this study confirm the gender-based fall prediction model as comprehensive in relation to community-dwelling elders. The fall prediction model can effectively contribute to future studies in developing fall prediction and intervention programs.

• 한국전자거래학회지
• /
• 제21권1호
• /
• pp.65-77
• /
• 2016

모바일 기기 데이터를 활용한 분석에서 사용자의 프라이버시를 보호하는 것이 주요한 이슈로 대두됨에 따라 데이터를 외부로 전송하지 않고 모바일 기기 안에서 분석을 수행하는 기기내 분석이 주목 받고 있다. 기기 내 분석을 활용하면 문자 메시지, 검색 단어, 북마크, 연락처등 매우 개인적이지만 성별 구분에 효과적이라고 알려진 모바일 텍스트를 이용한 성별 예측이 가능하며, 사전에 선정된 단어들의 집합을 모바일 기기로 전송하여 이 단어들과 모바일 텍스트를 비교를 통해 성별을 예측하는 단어 비교 방식을 이용하면 모바일 기기의 제한된 자원 문제를 극복할 수 있다. 특히, 확실한 근거를 이용하여 필터링 한 후 예측을 수행하면 정확도를 극대화하고 복잡도를 낮출 수 있다. 따라서 본 논문에서는 단어의 식별력과 인기도를 순차적으로 고려하는 2단계의 기기 내 성별 예측 방법을 제안한다. 구체적으로, 제안하는 방법론은 소수의 높은 식별력을 가지는 단어를 이용하여 전체 사용자의 성별을 예측하고 이어서 인기도가 높은 단어를 활용하여 앞서 예측이 되지 않은 사용자의 성별을 예측한다. 실제 데이터를 이용한 실험에서 제안하는 방법론은 비교 방법론보다 우수한 성능을 나타내었다.

• 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.

• 한국학교ㆍ지역보건교육학회지
• /
• 제22권3호
• /
• pp.41-54
• /
• 2021

Objectives: This study aimed to confirm the degree of gender sensitivity, gender role conflict, nursing professionalism of nursing students and the factors that affect nursing professionalism. Methods: During Jan. 19 to Feb. 5 in 2021, the structured questionnaire was used for 187 nursing students by on-line research methods. Data were analyzed by descriptive analysis, mean comparison(t-test, ANOVA), correlation analysis(Pearson's correlation coefficient) and multiple regression using SPSS/WIN 25.0. Results: The gender sensitivity had positive relationship with nursing professionalism, and gender role conflict had negative relationship with nursing professionalism. And the prediction factors influencing nursing professionalism were major satisfaction, gender sensitivity and gender role conflict. The total variance was 8.2% by predictors. Conclusions: In order to improve the nursing professionalism of nursing students, various ways to increase the satisfaction level of major should be sought, and program should be prepared to improve gender sensitivity and reduce gender role conflict.

• 대한치과교정학회지
• /
• 제52권2호
• /
• pp.102-111
• /
• 2022

Objective: To develop and explore the usefulness of an artificial intelligence system for the prediction of the need for dental extractions during orthodontic treatments based on gender, model variables, and cephalometric records. Methods: The gender, model variables, and radiographic records of 214 patients were obtained from an anonymized data bank containing 314 cases treated by two experienced orthodontists. The data were processed using an automated machine learning software (Auto-WEKA) and used to predict the need for extractions. Results: By generating and comparing several prediction models, an accuracy of 93.9% was achieved for determining whether extraction is required or not based on the model and radiographic data. When only model variables were used, an accuracy of 87.4% was attained, whereas a 72.7% accuracy was achieved if only cephalometric information was used. Conclusions: The use of an automated machine learning system allows the generation of orthodontic extraction prediction models. The accuracy of the optimal extraction prediction models increases with the combination of model and cephalometric data for the analytical process.

• Child Health Nursing Research
• /
• 제16권3호
• /
• pp.230-238
• /
• 2010

Purpose: The purpose of this study was to examine gender differences in self-competence, social anxiety and depression in upper level primary school children. Methods: In this cross-sectional study, data were collected from 180 students in grades 5 or 6 (83 boys and 97 girls). The instruments used for this study were a self-report questionnaire, the Self-Perception Profile for Children, the Revised Social Anxiety Scales for Children (SASC-R) and a Depression Instrument. For data analysis, descriptive statistics, t-test, Pearson correlation coefficients, and stepwise multiple regression were used with the SPSS/PC ver 12.0 program. Results: The only gender difference was in depression and girls reported more depression than boys. Social competence showed significantly negative correlations with depression and social anxiety. Gender differences were found in self competence in the prediction of depression and social anxiety. Conclusion: The results of this study indicate that there are gender differences in self competence which influence depression and social anxiety. Thus, enhancing self-competence could prevent social anxiety and depression in children but, differences in gender should be considered when developing programs to enhance self-competence.

• Biomolecules & Therapeutics
• /
• 제28권6호
• /
• pp.491-502
• /
• 2020

Sex/gender disparity has been shown in the incidence and prognosis of many types of diseases, probably due to differences in genes, physiological conditions such as hormones, and lifestyle between the sexes. The mortality and survival rates of many cancers, especially liver cancer, differ between men and women. Due to the pronounced sex/gender disparity, considering sex/gender may be necessary for the diagnosis and treatment of liver cancer. By analyzing research articles through a PubMed literature search, the present review identified 12 genes which showed practical relevance to cancer and sex disparities. Among the 12 sex-specific genes, 7 genes (BAP1, CTNNB1, FOXA1, GSTO1, GSTP1, IL6, and SRPK1) showed sex-biased function in liver cancer. Here we summarized previous findings of cancer molecular signature including our own analysis, and showed that sex-biased molecular signature CTNNB1^High, IL6^High, RHOA^High and GLIPR1^Low may serve as a female-specific index for prediction and evaluation of OS in liver cancer patients. This review suggests a potential implication of sex-biased molecular signature in liver cancer, providing a useful information on diagnosis and prediction of disease progression based on gender.

• 한국전문물리치료학회지
• /
• 제16권3호
• /
• pp.60-68
• /
• 2009

Psychsocial factors appear to play an important role in the maintenance and development of chronic disability from low back pain. Fear of pain may be more disabling than the pain itself in patients with nonacute low back pain. The purpose of this study was to identify the contribution of gender, age, depression and pain-related fear to pain intensity and disability in nonacute low back pain patients. This was a cross-sectional survey study of eighty four patients who had low back pain for at least 4 weeks. More than moderate correlations were found between pain intensity, disability, fear-avoidance beliefs and depression. Regression analyses revealed that disability ratings and fear-avoidance beliefs for work activities significantly contributed to the prediction of pain intensity, even when controlling for age, gender and pain duration. Also, fear-avoidance beliefs for physical activity, pain intensity, age and depression, significantly contributed to the prediction of disability, even when controlling for gender and pain duration. These findings suggest that disability scores and fear-avoidance beliefs for work activities are important determinants of pain intensity. They also suggest that fear-avoidance beliefs for physical activity, pain intensity, age and depression are important determinants of disability.