• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2001.05a
• /
• pp.15-19
• /
• 2001

This paper describes effectiveness and characteristics of 3 P(point) task analysis as a new Ergonomic and Kansei design method for extracting user demand especially. The key point in 3 P task analysis is to describe the flow of tasks and extract any problems in each task. A solution of a problem means a user demand. 3 P task analysis cal eliminate an oversight of check items by examining the users' information processing level. The suers' information processing level was divided into the following three stages for problem extraction: acquirement of information ---> understanding and judgment ---> operation. Three stages has fourteenth cues such as difficulty of seeing, no emphasis, mapping for extracting problems. To link analysis results to the formulation of a product concept. I added a column on the right side of the table for writing the requirements (user demand) to resolve the problems extracted from each task. The requirements are extracted by using seventh cues. Finally 3 P task analysis was compared with group interview to make the characteristics of 3 P task analysis, especially extracting user demand, clear.

• Science of Emotion and Sensibility
• /
• v.20 no.4
• /
• pp.101-112
• /
• 2017

We investigated the neural representation of reward probability recognition and its neural connectivity with other regions of the brain. Using functional magnetic resonance imaging (fMRI), we used a simple guessing task with different probabilities of obtaining rewards across trials to assay local and global regions processing reward probability. The results of whole brain analysis demonstrated that lateral prefrontal cortex, inferior parietal lobe, and postcentral gyrus were activated during probability-based decision making. Specifically, the higher the expected value was, the more these regions were activated. Fronto-parietal connectivity, comprising inferior parietal regions and right lateral prefrontal cortex, conjointly engaged during high reward probability recognition compared to low reward condition, regardless of whether the reward information was extrinsically presented. Finally, the result of a regression analysis identified that cortico-subcortical connectivity was strengthened during the high reward anticipation for the subjects with higher cognitive impulsivity. Our findings demonstrate that interregional functional involvement is involved in valuation based on reward probability and that personality trait such as cognitive impulsivity plays a role in modulating the connectivity among different brain regions.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.1
• /
• pp.24-30
• /
• 2019

Modern people argue that mental health care is necessary because of various factors such as unstable income and conflict with others. Recently, equipments capable of measuring electrocardiogram (ECG) in wearable equipment have been widely used. In the case of overseas, it can be seen as a medical assistant [14]. By using such functions, studies are being conducted to distinguish representative emotions (joy, sadness, anger, etc.) with objective values. However, most studies are increasing accuracy by collecting complex bio-signals in a limited environment. Therefore, we examine the factors that have the greatest influence on the change and discrimination of biometric information on each stimulus.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.706-708
• /
• 2023

In this study, we embark on a journey to uncover the essence of emotions by exploring the depths of transfer learning on three pre-trained transformer models. Our quest to classify five emotions culminates in discovering the KLUE (Korean Language Understanding Evaluation)-BERT (Bidirectional Encoder Representations from Transformers) model, which is the most exceptional among its peers. Our analysis of F1 scores attests to its superior learning and generalization abilities on the experimental data. To delve deeper into the mystery behind its success, we employ the powerful SHAP (Shapley Additive Explanations) method to unravel the intricacies of the KLUE-BERT model. The findings of our investigation are presented with a mesmerizing text plot visualization, which serves as a window into the model's soul. This approach enables us to grasp the impact of individual tokens on emotion classification and provides irrefutable, visually appealing evidence to support the predictions of the KLUE-BERT model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.195-202
• /
• 2020

The ultimate goal of CSV activities is to increase consumer loyalty to the company, brand or organization concerned. Thus, for a professional sports club, CSV activities will ultimately aim to enhance the loyalty of spectators who are consumers of the club. Subjects of this study are the spectators of professional volleyball. We distributed 300 survey to people who were aware of the club's CSV activities among the home spectators of Hyundai Capital SkyWalkers. Data processing was performed using SPSS 23 and AMOS 18 for the analysis of confirmed factors, correlation analysis, reliability analysis, and structural equation model analysis. From these results, we were able to come up with the social problem resolution and long-term orientation among the CSV activities of professional volleyball clubs which affect the club identification. And the identification formed within the spectators of the clubs through CSV affects the club loyalty directly or through the medium of club emotion. Professional volleyball clubs need to identify the problems the community has in planning and proceeding with CSV activities and seek strategies to address them together, and approach them from a long-term oriented perspective.

• Science of Emotion and Sensibility
• /
• v.18 no.2
• /
• pp.55-64
• /
• 2015

The aim of the study was to investigate the neural substrates associated with processing anger among young males with alcohol use disorders (AUDs) using functional magnetic resonance imaging (fMRI). Eighteen individuals with AUD and 15 demographically similar non-abusers participated in the study. Participants were scanned on their brain functioning while they viewed an audio-visual film clip that was previously designed specifically to induce anger emotion, followed by anpsychological assessment. Greater brain activities were detected in the left inferior frontal gyrus (IFG) and dorsal anterior cingulate cortex (dACC) among subjects with AUD compared to the controls during the exposure to anger-provoking stimuli. Despite the same level of subjective anger during anger induction, the greater activations both in the IFG and dACC regions may suggestthat individuals with AUD have a greater propensity to undergo cognitive control and self-regulation while experiencing anger.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.411-412
• /
• 2010

전통적으로 자연어 텍스트로부터의 감정인식 연구는 감정 키워드에 기반한다. 그러나 감정 키워드만을 이용하면 자연어 문장이 원래 갖고 있는 통사정보나 의미정보는 잃어버리게 된다. 이를 극복하기 위해 본 논문에서는 자연어 텍스트를 Predicate Logic 형태로 변환하여 감정 정보처리의 기반데이터로 사용한다. Predicate Logic형태로 변환하기 위해서 의존 문법 구문분석기를 사용하였다. 이렇게 생성된 Predicate 데이터 중 감정 정보를 갖고 있는 Predicate만을 찾아내는데 이를 위해 Emotional Predicate Dictionary를 구축하였고 이 사전에는 하나의 Predicate마다 미리 정의된 개념 클래스로 사상 시킬 수 있는 정보를 갖고 있다. 개념 클래스는 감정정보를 갖고 있는지, 어떤 감정인지, 어떤 상황에서 발생하는 감정인지에 대한 정보를 나타낸다. 자연어 텍스트가 Predicate으로 변환되고 다시 개념 클래스로 사상되고 나면 KBANN으로 구현된 Lazarus의 감정 생성 규칙에 적용시켜 최종적으로 인식된 감정을 판단한다. 실험을 통해 구현된 시스템이 인간이 인식한 감정과 약 70%이상 유사한 인식 결과를 나타냄을 보인다.

• Science of Emotion and Sensibility
• /
• v.21 no.4
• /
• pp.103-112
• /
• 2018

This study aimed to identify specific psychological and brain activation responses relating to the processing of negative emotions in patients with alcohol dependency. The authors hypothesized that patients with alcohol dependency would demonstrate the abnormal functioning of brain regions involved in negative emotions. Eleven male patients diagnosed with alcohol dependence in an inpatient alcohol treatment facility and 13 social drinkers with similar demographics were scanned using functional magnetic resonance imaging (fMRI) as they viewed film clips that evoked negative emotions. During exposure to negative emotional stimuli, the control group evinced significantly greater activity in the right anterior cingulate cortex (ACC) in comparison to patients with alcohol dependency. Correlation analyses demonstrated a negative association in the relationship between beta values from the right ACC and amygdala in participants classified in the control group. No statistically significant relationship was observed for blood oxygenation level-dependent (BOLD) changes between the two regions in the patient group during the elicitation of negative emotions. On the other hand, patients exhibited a greater activation of the amygdala as negative emotions were induced. These results suggest that alcoholism presents pathophysiology of brain activation that is distinct from the responses of healthy individuals functioning as controls.

• Journal of Semiconductor Engineering
• /
• v.2 no.2
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.