Development of a Stress Classification Model Using Deep Belief Networks for Stress Monitoring

송세희,김동근 대한의료정보학회 2017 Healthcare Informatics Research Vol.23 No.4

Objectives: Stress management is related to public healthcare and quality of life; an accurate stress classification method is necessary for the design of stress monitoring systems. Therefore, the goal of this study was to design a novel stress classification model using a deep learning method. Methods: In this paper, we present a stress classification model using the dataset from the sixth Korea National Health and Nutrition Examination Survey conducted from 2013 to 2015 (KNHANES VI) to analyze stress-related health data. Statistical analysis was performed to identify the nine features of stress detection, and we evaluated the performance of the proposed stress classification by comparison with several stress detection models. The proposed model was also evaluated using Deep Belief Networks (DBN). Results: We designed profiles depending on the number of hidden layers, nodes, and hyper-parameters according to the loss function results. The experimental results showed that the proposed model achieved an accuracy and a specificity of 66.23% and 75.32%, respectively. The proposed DBN model performed better than other classification models, such as support vector machine, naive Bayesian classifier, and random forest. Conclusions: The proposed model in this study was demonstrated to be effective in classifying stress detection, and in particular, it is expected to be applicable for stress prediction in stress monitoring systems.

Analysis of the Relation between Biological Classification Ability and Cortisol-hormonal Change of Middle School Students

( Ye Jun Bae ),( Il Sun Lee ),( Jung Ho Byeon ),( Yong Ju Kwon ) 한국과학교육학회 2012 한국과학교육학회지 Vol.32 No.6

The purpose of this study is to investigate the relation between the classification ability quotient and cortisol-hormonal change of middle school students. Thirty-three students, second graders in middle school, performed the classification task that can be an indicator of students` classification ability. And then amount of the secreted hormone was analyzed during task performance. The study results were as follows: First, the classification methods of students mostly utilized visual, qualitative. Their classification patterns for each subject were static, partial, and non-comparative. Second, the amount of stress-hormone was secreted from students during the experiment decreased in overall after the free classification. It seemed that student-centered activity relieved stress. Third, the classification ability quotient turned out to be significantly correlated to the stress hormone, which means that there was a close relationship between classification ability and stress level. It was also considered that stress had a positive effect on the improvement of classification ability. This study provided physiologically more accurate information on the stress increased in the learning process than other conventional studies based on reports or interviews. Finally, researchers could recognize the effect of stress in the cognitive activity and the need to find an appropriate level of stress in learning processes.

Revisiting Coherent Relationships between Bases and Suffixes through Stress Change: -ate and -al

오관영 대한영어영문학회 2017 영어영문학연구 Vol.43 No.4

Oh, Kwan Young. “Revisiting Coherent Relationships between Bases and Suffixes through Stress Change: -ate and -al.” Studies in English Language & Literature 43.4 (2017): 273-293. The purpose of the study is to identify what stress changes occur in -ate and -al suffixation in terms of aspects of strength relations through making a comparison between rule-based approaches and constraint-based ones. These suffixes perform dual functions: -ate belongs to Class I (Lee 1996), but plays a role as a stress-bearing or stress-neutral suffix in its specific context where it is affixed; -al is classified into either Class I or Class II, but oscillates between stress-neutral and stress-shifting modes in suffixation. Therefore, first we reclassify the suffixes according to their characteristics in stress-modes. Next, we examine the stress change through rule-based analyses (Ross 1972, Liberman and Prince 1977, Burzio 1994), and then account for it by adopting constraint-based approaches based on the foot structures. As a result, it is demonstrated that the approaches relying on the constraints are more satisfactory in explaining the stress change as well as the strength relations between the bases and the suffixes in suffixation. (Chonnam National University)

Stress Level Based Emotion Classification Using Hybrid Deep Learning Algorithm

Sivasankaran Pichandi,Gomathy Balasubramanian,Venkatesh Chakrapani 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.11

The present fast-moving era brings a serious stress issue that affects elders and youngsters. Everyone has undergone stress factors at least once in their lifetime. Stress is more among youngsters as they are new to the working environment. whereas the stress factors for elders affect the individual and overall performance in an organization. Electroencephalogram (EEG) based stress level classification is one of the widely used methodologies for stress detection. However, the signal processing methods evolved so far have limitations as most of the stress classification models compute the stress level in a predefined environment to detect individual stress factors. Specifically, machine learning based stress classification models requires additional algorithm for feature extraction which increases the computation cost. Also due to the limited feature learning characteristics of machine learning algorithms, the classification performance reduces and inaccurate sometimes. It is evident from numerous research works that deep learning models outperforms machine learning techniques. Thus, to classify all the emotions based on stress level in this research work a hybrid deep learning algorithm is presented. Compared to conventional deep learning models, hybrid models outperforms in feature handing. Better feature extraction and selection can be made through deep learning models. Adding machine learning classifiers in deep learning architecture will enhance the classification performances. Thus, a hybrid convolutional neural network model was presented which extracts the features using CNN and classifies them through machine learning support vector machine. Simulation analysis of benchmark datasets demonstrates the proposed model performances. Finally, existing methods are comparatively analyzed to demonstrate the better performance of the proposed model as a result of the proposed hybrid combination.

스트레스 집단 구분에 따른 환경색채 감정 평가

오지영,박혜경 한국색채학회 2020 한국색채학회 논문집 Vol.34 No.1

The purpose of this study is to classify the groups according to the stress level for the composition of the consumer-centered healing environment, and to evaluate how the stress feelings of the environmental colors differ according to the groups. This will contribute to more efficient and user-centered space construction in the future planning of healing environment colors. The first method of this study was to classify the groups by measuring the stress level of the evaluator using the stress rating scale (PWI). Second, stress emotion evaluation environmental colors were produced by referring to the color data of domestic healing environment. Third, stress emotion vocabulary was extracted from previous studies related to color emotions to evaluate stress emotions for environmental colors on a five-point scale. As a result, the higher the saturation, the higher the saturation, the more positively the stress emotion was evaluated. Second, the color of the high brightness / low saturation range showed a high level of depressive and boring stress feelings regardless of the color, and a high degree of comfortable and free feelings. Third, depressive emotions in the medium and high saturation of the warm color group were found to be different among the groups, and in the G color, various stress feelings were different among the groups compared to other colors.

뇌파 신호 기반 스트레스 상태 분류

강준수,장길진,이민호 한국인터넷방송통신학회 2016 한국인터넷방송통신학회 논문지 Vol.16 No.3

일상생활에서 인간은 끊임없이 스트레스를 받으며 살아간다. 스트레스는 삶의 질과 밀접하게 연관이 있으며, 건강한 삶은 스트레스에 적절하게 대처하며 살아가는 삶이다. 스트레스는 호르몬 분비에 영향을 주며, 호르몬 분비의 변화는 뇌 신호 및 생체 신호에 영향을 준다. 이를 바탕으로, 본 논문은 스트레스와 뇌파 신호와의 관련성을 확인하였으며, 더 나아가 뇌파 신호 기반 정량적 스트레스 지수를 찾아보았다. 사용한 뇌파 장비는 32채널 유선 EEG 장비이며, 상업용 2채널(FP1, FP2) 뇌파 장비와의 비교를 위해, 상업용 뇌파 장비와 동일한 위치에 있는 2채널만 이용하여 데이터를 분석하였다. 뇌파의 주파수 특징점으로는 각 주파수 대역대의 파워 값, 주파수 대역대 파워 값들 간의 비율 및 차이 등을 테스트해 보았으며, 시간 특징점으로는 허스트 지수, 상관 지수, 리아프노프 지수 등을 테스트해 보았다. 총 6명의 피 실험자가 본 실험에 참여하였으며, 실험 과제로는 영어 지문이 사용되었다. 여러 특징점들 중 가 가장 좋은 테스트 성능을 보여줬으며, 테스트 데이터에 대하여 평균 70.8%의 스트레스 분류 정확도를 얻었다. 추후, 저가 상용 2채널 뇌파 장치를 이용해서 비슷한 결과가 나오는지 확인해 볼 예정이다. In daily life, humans get stress very often. Stress is one of the important factors of healthy life and closely related to the quality of life. Too much stress is known to cause hormone imbalance of our body, and it is observed by the brain and bio signals. Based on this, the relationship between brain signal and stress is explored, and brain signal based stress index is proposed in our work. In this study, an EEG measurement device with 32 channels is adopted. However, only two channels (FP1, FP2) are used to this study considering the applicability of the proposed method in real enveironment, and to compare it with the commercial 2 channel EEG device. Frequency domain features are power of each frequency bands, subtraction, addition, or division by each frequency bands. Features in time domain are hurst exponent, correlation dimension, lyapunov exponent, etc. Total 6 subjects are participated in this experiment with English sentence reading task given. Among several candidate features, shows the best test performance (70.8%). For future work, we will confirm the results is consistent in low price EEG device.

Measurement and Modeling of Job Stress of Electric Overhead Traveling Crane Operators

Krishna, Obilisetty B.,Maiti, Jhareswar,Ray, Pradip K.,Samanta, Biswajit,Mandal, Saptarshi,Sarkar, Sobhan Occupational Safety and Health Research Institute 2015 Safety and health at work Vol.6 No.4

Background: In this study, the measurement of job stress of electric overhead traveling crane operators and quantification of the effects of operator and workplace characteristics on job stress were assessed. Methods: Job stress was measured on five subscales: employee empowerment, role overload, role ambiguity, rule violation, and job hazard. The characteristics of the operators that were studied were age, experience, body weight, and body height. The workplace characteristics considered were hours of exposure, cabin type, cabin feature, and crane height. The proposed methodology included administration of a questionnaire survey to 76 electric overhead traveling crane operators followed by analysis using analysis of variance and a classification and regression tree. Results: The key findings were: (1) the five subscales can be used to measure job stress; (2) employee empowerment was the most significant factor followed by the role overload; (3) workplace characteristics contributed more towards job stress than operator's characteristics; and (4) of the workplace characteristics, crane height was the major contributor. Conclusion: The issues related to crane height and cabin feature can be fixed by providing engineering or foolproof solutions than relying on interventions related to the demographic factors.

원자력발전소의 직무 스트레스 측정방법에 대한 비교 연구

Meiling Luo,Yeon Ju Oh,Tong Il Jang,Yong Hee Lee 대한인간공학회 2012 대한인간공학회 학술대회논문집 Vol.2012 No.11

고신뢰도 체계인 원자력발전소(이하 원전)에서는 스트레스로 인한 인적오류는 중대한 사고를 초래할 수 있다. 따라서 직무 관련 스트레스에 대한 보다 정확한 평가가 필요하다. 스트레스 측정 사례를 살펴보면 설문, 인터뷰, 생리학적 실험, 혈액 및 타액 채취 등 다양한 평가방법들이 사용되고 있다. 원전에서의 스트레스 측정은 주로 설문기반의 주관적인 방법이 사용되고 있지만, 그 적합성에 대한 연구는 미흡하다. 본 논문에서는 기존의 직무스트레스 측정방법을 비교하고, 원전의 직무 스트레스 평가에 적합한 측정방법을 모색하였다. 새로운 방법으로 원전에서 수행되는 직무의 유형을 분류하고 유사한 타 산업에서의 직무에 적용되는 스트레스 측정법을 검토하였다. 원전 직무의 특성상 추가적인 고려사항을 합산하거나, 직무요소의 분할을 통해 원전 직무에 적용 가능한 스트레스 측정법을 제안하였다. 또한 이들을 종합하여 원전 종사자의 스트레스를 보다 정확하게 평가할 수 있도록 단계적 접근 방안을 제시하였다.

유아의 기질프로파일에 따른 어머니의 심리적 특성과 양육스트레스에 대한 차이분석

김지효 ( Ji Hyo Kim ) 한국유아교육학회 2015 유아교육연구 Vol.35 No.1

The purpose of this study was to identify child`s temperament profiles by using a diagnosis classification model and to investigate the differences in mothers` psychological characteristic, parenting stress by child`s temperament profiles. To accomplish this purpose, by using sample of 1,616 Korean child-mothers from the 4th year of Korean Children and Youth Panel Survey. The summary of the main results of this study is as follows: First, child`s temperament were grouped into four profiles: (1) 110(higher sociability & emotional sensitivity group), (2) 001(higher activity group), (3) 100(higher sociability group), (4)101(higher sociability & activity group). Second, differences in the mothers` self efficacy, depression, parenting stress among child`s temperament profiles were significant. Specifically, mothers` self efficacy in the 110 showed relatively higher than the 001. And mothers` parenting stress and depression in the 001 showed relatively higher than the 110. 본 연구의 목적은 진단분류모형(Diagnostic Classification Model)을 활용하여 유아의 기질프로파일을 추출하고 이에 따른 어머니의 자기효능감, 자아존중감, 양육스트레스 및 우울에 어떠한 차이가 있는지를 알아보는 것이었다. 이를 위해 한국아동패널 4차년도 조사 자료를 활용했고 DINO(deterministic input, noisy or gate)모형을 적용하여 유아의 기질프로파일을 추출하였다. 연구결과, 첫째, DINO모형을 활용하여 기질프로파일을 추출한 결과 1) 110(사회성, 정서민감성 높은 집단), 2) 001(활동성 높은 집단), 3) 100(사회성 높은 집단), 4) 101(사회성, 활동성 높은 집단)인 네 개의 잠재계층이 확인되었다. 둘째, 기질프로파일에 따른 어머니의 자기효능감, 자아존중감, 양육스트레스 및 우울의 차이를 분석한 결과, 유아의 기질프로파일에 따라 어머니의 자기효능감, 양육스트레스 및 우울은 통계적으로 유의한 차이가 있었다. 잠재계층 110(사회성, 정서민감성 높은 집단)에 속한 자녀를 양육하는 어머니의 자기효능 감은 잠재계층 001(활동성 높은 집단)보다 높았으며 어머니의 자아존중감은 유아의 기질프로파일에 따라 유의한 차이가 없었다. 또한, 어머니의 양육스트레스와 우울의 경우, 잠재계층001(활동성 높은 집단)에 속한 유아를 양육하는 어머니가 110(사회성, 정서민감성 높은 집단)의 어머니보다 더 높았다. 본 연구결과를 통해 유아의 기질프로파일에 따른 어머니의 심리적 특성을 확인할 수 있었으며 어머니의 긍정적인 심리적 특성을 증진시키기 위한 부모교육프로그램 개발에 유용한 정보로 활용될 수 있을 것이다.

Evaporative Stress Index (ESI)의 국내 가뭄 심도 분류 기준 제시

이희진 ( Lee Hee-jin ),남원호 ( Nam Won-ho ),윤동현 ( Yoon Dong-hyun ),홍은미 ( Hong Eun-mi ),김태곤 ( Kim Taegon ),박종환 ( Park Jong-hwan ),김대의 ( Kim Dae-eui ) 한국농공학회 2020 한국농공학회논문집 Vol.62 No.2

Drought is considered as a devastating hazard that causes serious agricultural, ecological and socio-economic impacts worldwide. Fundamentally, the drought can be defined as temporarily different levels of inadequate precipitation, soil moisture, and water supply relative to the long-term average conditions. From no unified definition of droughts, droughts have been divided into different severity level, i.e., moderate drought, severe drought, extreme drought and exceptional drought. The drought severity classification defined the ranges for each indicator for each dryness level. Because the ranges of the various indicators often don’t coincide, the final drought category tends to be based on what the majority of the indicators show and on local observations. Evaporative Stress Index (ESI), a satellite-based drought index using the ratio of potential and actual evaporation, is being used as a index of the droughts occurring rapidly in a short period of time from studies showing a more sensitive and fast response to drought compared to Standardized Precipitation Index (SPI), and Palmer Drought Severity Index (PDSI). However, ESI is difficult to provide an objective drought assessment because it does not have clear drought severity classification criteria. In this study, U.S. Drought Monitor (USDM), the standard for drought determination used in the United States, was applied to ESI, and the Percentile method was used to classify drought categories by severity. Regarding the actual 2017 drought event in South Korea, we compare the spatial distribution of drought area and understand the USDM-based ESI by comparing the results of Standardized Groundwater level Index (SGI) and drought impact information. These results demonstrated that the USDM-based ESI could be an effective tool to provide objective drought conditions to inform management decisions for drought policy.