• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2004.11a
• /
• pp.37-37
• /
• 2004

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.366-369
• /
• 2000

This paper examines three algorithms to recognize speaker's emotion using the speech signals. Target emotions are happiness, sadness, anger, fear, boredom and neutral state. MLB(Maximum-Likeligood Bayes), NN(Nearest Neighbor) and HMM (Hidden Markov Model) algorithms are used as the pattern matching techniques. In all cases, pitch and energy are used as the features. The feature vectors for MLB and NN are composed of pitch mean, pitch standard deviation, energy mean, energy standard deviation, etc. For HMM, vectors of delta pitch with delta-delta pitch and delta energy with delta-delta energy are used. We recorded a corpus of emotional speech data and performed the subjective evaluation for the data. The subjective recognition result was 56% and was compared with the classifiers' recognition rates. MLB, NN, and HMM classifiers achieved recognition rates of 68.9%, 69.3% and 89.1% respectively, for the speaker dependent, and context-independent classification.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.11a
• /
• pp.245-249
• /
• 2002

인간 감성변화의 기본인 피부온도 및 피복내 온습도 측정을 위한 시스템과 감성공학적 해석을 위한 보다 정밀하고 안정성이 있는 센서의 응답성 및 회로의 선형화에 대한 연구를 수행하고, 의복내 환경평가 및 실내 온습도 측정등의 다양한 감성공학적 해석을 위한 소프트웨어의 개발이 본 연구의 목적이다. 본 연구에는 손쉬운 온습도 변환장치와 풍부한 저장능력등 다양한 분야에서 활용이 가능한 온습도 측정기와 이에 필요한 센서를 개발하고 측정기의 선형화특성을 평가하였다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.31-31
• /
• 1999

In the preliminary design stage of an automotive interior, human sensibility is first analyzed and applied to design parameters for satisfying consumers needs using optimization and engineering judgement. Then designers try to design components that meet these needs using empirical and trial-and-error procedures. This process usually yields poor results because it is difficult to find a feasible design that satisfies the targets by trial-and-error (a feasible design is one that satisfies consumers needs and design constraints). To improve this process, we need tools to link the human sensibility with the design parameters that define the geometry of the components of an automotive interior. A methodology is presented for developing a tool for design guidance of an automotive interior. This tool translates the human sensibility into the design parameters that define the geometry of the components of an automotive interior. This tool, called interpreter, rapidly predicts the human sensibility of a given automotive interior and presents design parameters that meet or exceed given human sensibility to satisfy consumers needs and design constraints. The methodology is demonstrated on the interior design of an actual automotive.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2001.11a
• /
• pp.173-178
• /
• 2001

제품 및 환경에 대한 감성평가를 위한 한국인 체형에 맞는 인체모델을 개발하기 위해 인체측정자료를 수집 및 분석한다. 분석된 인체측정 자료를 이용하여 15개의 지체와 14개의 조인트로 구성된 인체모델을 구성하고 기구학적 특성 값을 기술한다. 구성된 인체모델은 3차원 그래픽 기술을 통해 가시화하며, 가상현실 상에서 제품 및 환경과 상호 작용하도록 구성함으로써 감성평가가 가능하도록 구성한다. 정면충돌 상황시의 각 지체의 거동을 분석하고 국제 인체모델과 비교함으로써 동역학적으로 인체모델이 타당한지를 평가한다. 가상환경에서 차량 내부의 감성평가에 인체모델을 이용한다.

• Science of Emotion and Sensibility
• /
• v.20 no.2
• /
• pp.161-170
• /
• 2017

Emotion affects many parts of human life such as learning ability, behavior and judgment. It is important to understand human nature. Emotion can only be inferred from facial expressions or gestures, what it actually is. In particular, emotion is difficult to classify not only because individuals feel differently about emotion but also because visually induced emotion does not sustain during whole testing period. To solve the problem, we acquired bio-signals and extracted features from those signals, which offer objective information about emotion stimulus. The emotion pattern classifier was composed of unsupervised learning algorithm with hidden nodes and feature vectors. Restricted Boltzmann machine (RBM) based on probability estimation was used in the unsupervised learning and maps emotion features to transformed dimensions. The emotion was characterized by non-linear classifiers with hidden nodes of a multi layer neural network, named deep belief network (DBN). The accuracy of DBN (about 94 %) was better than that of back-propagation neural network (about 40 %). The DBN showed good performance as the emotion pattern classifier.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.71-75
• /
• 2000

국내 동적 환경에 대한 감성 연구는 아직 미흡한 상태다. 본 연구는 자동차의 운전자세에 관해 연구하였다. 왼발을 사용하지 않는 A/T(Automatic Transmission) 차량과 두 발을 모두 사용하는 M/T(Manual Transmission) 차량의 운전자세 차이를 Position tracking sensor를 통해 측정하였으며, 각 차량에 따른 운전자들의 감성을 비교 및 분석하였다. 본 연구에 참여한 피험자들은 운전면허 소지자로 운전 경험이 있는 남자 대학생 및 대학원생이 참여하였으며, 운전자세를 분석해 본 결과 A/T 차량이 M/T 차량의 경우보다 Seat가 더 뒤로 위치하였고, 두 차량의 운전자세에서 무릎관절의 각도에 많은 차이가 났다. 또, 신체 각 부위 관절의 위치나 모양도 조금씩 다르게 측정되었다. A/T 차량과 M/T 차량의 운전자세에 따른 감성 평가는 동적 환경의 감성 연구에 도움이 될 것이다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2001.05a
• /
• pp.10-14
• /
• 2001

Physical chemistry states that electric potential is due to Gibb's free energy from chemical reaction of the electric cell. However we have not the electromagnetic meaning of Gibb's free energy. the free energy is discovered to be a kinetic energy part of the rotating electromagnetic wave ($\pi$-ray), which is different from conventional Coulomb attraction energy and can anticipate that there is a current difference between before and after the electric load. This paper manipulates the relationship between $\pi$-rays (Gibb's free energy) and electrolysis, cell reaction and brown gas reaction.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2004.11a
• /
• pp.57-57
• /
• 2004

• Science of Emotion and Sensibility
• /
• v.20 no.4
• /
• pp.127-134
• /
• 2017

Color is a significant factor for evoking human emotion. Therefore, the effects of color have been analyzed to predict and evaluate human emotion. The purpose of this study was to measure the cardiovascular responses depending on color stimuli in order to observe differences in color-emotions. Images consisting of six colors (red, green, blue, cyan, magenta, yellow) were used as visual stimuli. 26 college or graduate students (13 males) watched the color stimuli on the monitor and scored their subjective emotion while electrocardiogram (ECG) was meausred. The effects of the color on emotion were tested using Kruskal-Wallis test and Mann-Whitney U test. The coherence ratio showed significant differences between green and magenta (p = .004), green and red (p = .006), and green and yellow (p = .004). The significant differences of cardiovascular and emotions were relevant to emotional valence. This study shows significance as an empirical study by indicating that green induces pleasant and red induces unpleasant.