• 감성과학
• /
• 제18권2호
• /
• pp.37-44
• /
• 2015

LED lighting has an advantage of adjusting color temperature. This change of color temperature may derive change in behavioral and physiological responses of the visual perception for indoor environments. This research examined the changes of behavioral and physiological responses caused by the color temperature. The environment was configured that the indoor temperature was 20 degrees centigrade or less as the perceived uncomfortable environment in winter. Then, the comfortable sensation vote (CSV) and the results of 3-back working memory test were measured as behavioral responses. In addition, the Electrodermal Activity (EDA) and Electrocardiogram (ECG) were measured as the responses of autonomics nervous system (ANS) in the three conditions of color temperature (red: 3862K, white: 5052K, blue: 11,460K). As a result, behavioral responses were not significant by the condition of color temperature, but the tendency of occupants' physiological relaxation appeared in the blue color temperature condition compared with the white color temperature condition. Although the color temperature of LED lighting might be a small factor in terms of the characteristics of indoor environment, it suggests that the color temperature could have an impact on the physiological changes in the parasympathetic nervous system.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.760-767
• /
• 2022

This paper introduces alert fatigue and presents methods to measure alert fatigue by using physiological signals. Alert fatigue is a phenomenon that which an individual is constantly exposed to frequent alarms and becomes desensitized to them. Blind spots are one leading cause of struck-by accidents, which is one most common causes of fatal accidents on construction sites. To reduce such accidents, construction equipment is equipped with an alarm system. However, the frequent alarm is inevitable due to the dynamic nature of construction sites and the situation can lead to alert fatigue. This paper introduces alert fatigue and proposes methods to use physiological signals such as electroencephalography, electrodermal activity, and event-related potential for the measurement of alert fatigue. Specifically, this paper presents how raw data from the physiological sensors measuring such signals can be processed to measure alert fatigue. By comparing the processed physiological data to behavioral data, validity of the measurement is tested. Using preliminary experimental results, this paper validates that physiological signals can be useful to measure alert fatigue. The findings of this study can contribute to investigating alert fatigue, which will lead to lowering the struck-by accidents caused by blind spots.

• ETRI Journal
• /
• 제45권1호
• /
• pp.105-118
• /
• 2023

We tested the feasibility of automated discrimination of patients with panic disorder (PD) from healthy controls (HCs) based on multimodal physiological responses using machine learning. Electrocardiogram (ECG), electrodermal activity (EDA), respiration (RESP), and peripheral temperature (PT) of the participants were measured during three experimental phases: rest, stress, and recovery. Eleven physiological features were extracted from each phase and used as input data. Logistic regression (LoR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) algorithms were implemented with nested cross-validation. Linear regression analysis showed that ECG and PT features obtained in the stress and recovery phases were significant predictors of PD. We achieved the highest accuracy (75.61%) with MLP using all 33 features. With the exception of MLP, applying the significant predictors led to a higher accuracy than using 24 ECG features. These results suggest that combining multimodal physiological signals measured during various states of autonomic arousal has the potential to differentiate patients with PD from HCs.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.387-396
• /
• 2020

Wearable biosensors have the potential to non-invasively and continuously monitor seniors' stress in their daily interaction with the urban environment, thereby enabling to address the stress and ultimately advance their outdoor mobility. However, current wearable biosensor-based stress detection methods have several drawbacks in field application due to their dependence on batch-learning algorithms. First, these methods train a single classifier, which might not account for multiple subjects' different physiological reactivity to stress. Second, they require a great deal of computational power to store and reuse all previous data for updating the signle classifier. To address this issue, we tested the feasibility of online multi-task learning (OMTL) algorithms to identify multiple seniors' stress from electrodermal activity (EDA) collected by a wristband-type biosensor in a daily trip setting. As a result, OMTL algorithms showed the higher test accuracy (75.7%, 76.2%, and 71.2%) than a batch-learning algorithm (64.8%). This finding demonstrates that the OMTL algorithms can strengthen the field applicability of the wearable biosensor-based stress detection, thereby contributing to better understanding the seniors' stress in the urban environment and ultimately advancing their mobility.

• 대한의용생체공학회:의공학회지
• /
• 제42권3호
• /
• pp.107-115
• /
• 2021

Purpose: The aim of this study is to find the location of acupoints that are effective for increasing parasympathetic nervous system(PNS) activity among acupoints used to relieve symptoms such as dizziness and nausea. Materials and Methods: Twenty healthy adult men participated in this experiment. Transcutaneous electrical nerve stimulation(TENS) was applied to P6(Neiguan), ST36(Zusanli) and BL20(Pishu) for 30 minutes. For 5 minutes before and after stimulation, Electrocardiogram(ECG), Electrodermal activity(EDA), Respiration, and Skin temperature(SKT) were measured using biosignalsplux Professional(biosignalsplux; Portugal). Paired t-test was performed for the results before and after stimulation, and a one-way ANOVA test between stimulations was performed for the rate of change before and after stimulation. Results: When each acupoint was stimulated with TENS, it was found that the PNS was generally activated. In addition, when considering the change in biosignals after stimulation, the participants stimulated with P6 showed the most consistent results. Conclusion: As a result of stimulating each acupoint, it was found that stimulating P6 can effectively increase PNS activity. These results indicate that methods of stimulating P6 may be most effective in alleviating symptoms of motion sickness.

• 감성과학
• /
• 제20권3호
• /
• pp.169-180
• /
• 2017

특성불안이 높은 자들은 분노 표현을 억제하려하기 때문에 주관적인 행동평가로는 특성불안자의 분노 경험을 측정하는데 한계가 있다. 보다 객관적으로 특성불안자의 분노 경험을 측정하기 위하여 본 연구에서는 분노에 의해 유발된 자율신경계 반응이 특성불안 수준에 따라 차이가 있는지를 확인하고자 한다. 실험참가자들을 불안집단과 통제집단으로 구분하였으며, 분노자극을 제시하기 전과 후에 심전도(ECG), 호흡(RESP), 피부전기활동(EDA), 그리고 피부온도(SKT)를 측정하였다. ECG에서 심박률(HR), NN 간격의 표준편차(SDNN), 심박주기 제곱의 평균제곱근(RMSSD), 심박변이도의 저주파성분(LF), 심박변이도의 고주파성분(HF), 저주파성분과 고주파성분의 비율(LF/HF ratio), RESP에서 호흡주기(RR)를, EDA에서 피부전도수준(SCL)을, SKT에서 최대피부온도(maxSKT)를 산출하였다. 두 집단 간 분노자극에서 유발된 분노정서 강도의 차이를 검증한 결과, 집단 간 차이는 유의하였다. 자율신경계 반응 차이를 확인한 결과, 불안집단에서 유의미한 SDNN와 LF의 증가, HF, LF/HF ratio, 그리고 RR의 감소가 나타났다. 본 연구 결과는 특성불안이 높은 이들의 분노 경험을 측정하는데 자율신경계 반응이 객관적인 지표로 활용이 가능함을 시사한다.

• 대한의용생체공학회:의공학회지
• /
• 제42권5호
• /
• pp.211-224
• /
• 2021

Purpose: The purpose of this study is to present a way to alleviate motion sickness(MS) by stimulating acupoint through PEMFs, and to assess the effectiveness of PEMFs against stimulation previously used to stimulate acupoint using biosignal evaluations and surveys. Materials and Methods: Thirteen healthy men participated in the experiment. MS was induced in the participants, and MS relief stimulation was applied for 30 minutes. There were 4 types of MS relief stimulation, and Sham, Reliefband, Transcutaneous electrical nerve stimulation(TENS), and Pulsed electromagnetic fields stimulation(PEMFs) were used. The biosignals were measured during 30 minutes of applying MS relief stimulation, and the symptoms of MS were evaluated through a questionnaire survey. The measured biosignals are Electrocardiogram(ECG), Electrodermal activity(EDA), Respiration, Skin temperature(SKT), and Electrogastrogram(EGG). A one-way ANOVA test was performed for the rate of change by stimulation for MS relief over time. Results: Participants who were stimulated had a sharp decrease in MS symptoms. Biosignals were analyzed to evaluate autonomic nervous system activity, and the parasympathetic nervous system could be activated through stimulation. Conclusion: TENS and PEMFs were more effective in relieving MS symptoms than Reliefband. It is believed that PEMFs will be effective in consideration of the comfort of participants to be applied to actual vehicles, and studies to further verify the effects of PEMFs on MS should be conducted.

• 대한인간공학회지
• /
• 제31권2호
• /
• pp.271-279
• /
• 2012

Objective: This study classified three different emotional states(boredom, pain, and surprise) using physiological signals. Background: Emotion recognition studies have tried to recognize human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 122 college students participated in this experiment. Three different emotional stimuli were presented to participants and physiological signals, i.e., EDA(Electrodermal Activity), SKT(Skin Temperature), PPG(Photoplethysmogram), and ECG (Electrocardiogram) were measured for 1 minute as baseline and for 1~1.5 minutes during emotional state. The obtained signals were analyzed for 30 seconds from the baseline and the emotional state and 27 features were extracted from these signals. Statistical analysis for emotion classification were done by DFA(discriminant function analysis) (SPSS 15.0) by using the difference values subtracting baseline values from the emotional state. Results: The result showed that physiological responses during emotional states were significantly differed as compared to during baseline. Also, an accuracy rate of emotion classification was 84.7%. Conclusion: Our study have identified that emotions were classified by various physiological signals. However, future study is needed to obtain additional signals from other modalities such as facial expression, face temperature, or voice to improve classification rate and to examine the stability and reliability of this result compare with accuracy of emotion classification using other algorithms. Application: This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals as well as is able to be applied on human-computer interaction system for emotion recognition. Also, it can be useful in developing an emotion theory, or profiling emotion-specific physiological responses as well as establishing the basis for emotion recognition system in human-computer interaction.

• 한국지능시스템학회논문지
• /
• 제24권3호
• /
• pp.316-322
• /
• 2014

본 논문은 TV를 이용한 영화시청 환경에서 해당 컨텐트에 대한 시청자의 암묵적 반응과 컨텐트의 멀티모달 피쳐를 실시간으로 측정 및 동기화하여 이를 기반으로 동영상 선호모델을 지속적으로 개선하고 필요시 영화추천을 수행하는 시스템을 제안한다. 제안한 시스템에선 이미지, 소리, 자막 스트림으로부터 실시간 추출되는 저수준 피쳐들과 동기화되어 측정된 얼굴표정, 자세 및 생체신호로부터 해당 동영상이 유발한 시청자의 감정상태를 추정하여 선호모델 학습에 사용한다. 제안한 컨텐트-시청자 연계 추천모델의 일례로서 컨텐트의 오디오 및 자막 정보를 이용하여 시청자의 피부전기활성도로 측정된 arousal반응을 예측할 수 있음을 보인다.

• 감성과학
• /
• 제14권4호
• /
• pp.503-512
• /
• 2011

최근 HCI 분야에서 정서 인식은 정서 지능을 구현하기 위한 핵심적인 단계 중의 하나이다. 생체신호를 이용하여 정서 인식을 시도하는 연구들이 시도되고 있으나, 기본 정서 이외의 다른 정서에 대한 연구는 거의 이루어지지 않았다. 본 연구의 목적은 무료함, 통증, 그리고 놀람의 세 가지 정서 간 자율신경계 반응의 차이를 확인하는 것이다. 실험자는 217명의 실험참여자(남 96명)들을 대상으로 시/청각 자극을 조합하여 무료함과 놀람 정서를 유발하였고, 혈압기를 이용하여 통증 정서를 유발하였다. 정서 자극이 제시되는 동안 피부전기활동, 피부온도, 심전도와 광혈량도를 측정하였고, 실험참여자들이 경험한 정서 범주와 강도를 정서평가척도 상에 평정하게 하였다. 정서 자극에 대한 평가 결과, 사용된 정서 자극은 평균 92.5%의 적합성과 5.43의 효과성을 보였는데, 이는 각 정서 자극이 해당 정서를 효과적으로 유발한 것을 의미한다. 자율신경계 측정 결과, 피부전기활동, 피부온도, 심박률, 심박률의 저주파수 성분과 평균 혈류량은 안정 상태와 정서 상태 간의 유의한 차이를 보였다. 또한 각 정서에 의해 유발된 자율신경계 반응은 정서 간에도 유의한 차이가 있는 것으로 나타났다. 이러한 결과는 정서이론의 확장과 자율신경계 반응 측정 지표를 활용하여 정서를 인식하는 알고리즘 및 인간 정서를 변별하는 컴퓨터 시스템 개발에 응용 가능할 것이다.