• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.421-424
• /
• 2015

컴퓨터 기술이 발전하고 컴퓨터 사용이 일반화 되면서 휴먼 인터페이스에 대한 많은 연구들이 진행되어 왔다. 휴먼 인터페이스에서 감정을 인식하는 기술은 컴퓨터와 사람간의 상호작용을 위해 중요한 기술이다. 감정을 인식하는 기술에서 분류 정확도를 높이기 위해 특징벡터를 정확하게 추출하는 것이 중요하다. 본 논문에서는 정확한 피치검출을 위하여 음성신호에서 음성 구간과 비 음성구간을 추출하였으며, Speech Processing 분야에서 사용되는 전 처리 기법인 저역 필터와 유성음 추출 기법, 후처리 기법인 Smoothing 기법을 사용하여 피치 검출을 수행하고 비교하였다. 그 결과, 전 처리 기법인 유성음 추출 기법과 후처리 기법인 Smoothing 기법은 피치 검출의 정확도를 높였고, 저역 필터를 사용한 경우는 피치 검출의 정확도가 떨어트렸다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.941-944
• /
• 2015

저장 장치의 급속한 발전으로 인해 기존에 서비스할 수 없었던 개인 사용자를 위한 클라우드 서비스가 활성화되고 있다. 이 중 음악을 대상으로 하는 스트리밍 및 공유 서비스는 다양한 음악의 종류를 수용하기 위해 체계적인 분류를 필요로 한다. 기존의 분류체계는 단순히 작곡가나 업로더의 의견에 의해서 일방적으로 정해지기 때문에 사용자가 중심이 되는 클라우드 서비스에는 어울리지 않는다. 따라서 본 논문은 이와 같은 문제점을 해결하기 위해 사랑의 감정을 기준으로 새로운 분류체계를 제안한다. 자동적인 분류를 위해 데이터마이닝 기법을 접목시켰으며, 원활한 마이닝을 위해 오디오 음악 파일(raw data)을 정해진 크기로 자르고 feature extraction을 통해 오디오 음악 파일에 대한 전처리를 수행하였다. 이후 feature selection을 수행하기 위해 clustering을 이용해 유효한 중요도를 지나는 feature를 선별하였으며 선별된 feature를 토대로 SVN(Support Vector Machine)을 이용해 feature의 중요도에 대한 유효성을 검증함과 동시에 분류를 수행하여 감정을 기반으로 분류한 결과를 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.493-494
• /
• 2023

음성 기반의 감정 분석은 인간의 감정을 정확하게 파악하는 데 중요한 연구 분야로 자리잡고 있다. 최근에는 wav2vec2.0과 같은 트랜스포머 기반의 모델이 음성 인식 분야에서 뛰어난 성능을 보이며 주목받고 있다. 본 연구에서는 wav2vec2.0 모델을 활용하여 한국어 감성 발화 데이터에 대한 감정 분류를 위한 데이터 샘플링 전략을 제안한다. 실험을 통해 한국어 음성 감성분석을 위해 학습 데이터를 활용할 때 감정별로 샘플링하여 데이터의 개수를 유사하게 하는 것이 성능 향상에 도움이 되며, 긴 음성 데이터부터 이용하는 것이 성능 향상에 도움이 됨을 보인다.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.141-146
• /
• 2016

대화 시스템에서 사용자가 나타내는 발화에 내재된 감정을 분류하는 것은, 시스템이 적절한 응답과 서비스를 제공하는데 있어 매우 중요하다. 본 연구에서는 대화 내 감정 분류를 하는데 있어 직접적, 간접적으로 드러나는 감정 자질을 자동으로 학습하고 감정이 지속되는 대화 문맥을 효과적으로 반영하기 위해 CNN-LSTM 방식의 딥 뉴럴 네트워크 구조를 제안한다. 그리고 대량의 구어체 코퍼스를 이용한 사전 학습으로 데이터 부족 문제를 완화하였다. 실험 결과 제안하는 방법이 기존의 SVM이나, 단순한 RNN, CNN 네트워크 구조에 비해 전반전인 성능 향상을 보였고, 특히 감정이 있는 경우 더 잘 분류하는 것을 확인할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.141-146
• /
• 2016

대화 시스템에서 사용자가 나타내는 발화에 내재된 감정을 분류하는 것은, 시스템이 적절한 응답과 서비스를 제공하는데 있어 매우 중요하다. 본 연구에서는 대화 내 감정 분류를 하는데 있어 직접적, 간접적으로 드러나는 감정 자질을 자동으로 학습하고 감정이 지속되는 대화 문맥을 효과적으로 반영하기 위해 CNN-LSTM 방식의 딥 뉴럴 네트워크 구조를 제안한다. 그리고 대량의 구어체 코퍼스를 이용한 사전 학습으로 데이터 부족 문제를 완화하였다. 실험 결과 제안하는 방법이 기존의 SVM이나, 단순한 RNN, CNN 네트워크 구조에 비해 전반전인 성능 향상을 보였고, 특히 감정이 있는 경우 더 잘 분류하는 것을 확인할 수 있었다.

• Journal of Sasang Constitutional Medicine
• /
• v.10 no.1
• /
• pp.215-233
• /
• 1998

The object of this study is 27 patients who had been treated in the Oriental Medical Hospital at Dong Eui Medical Center during 6 months from January 1998 to June 1998. We proceeded the judgment of Sasang Constitution by Questionaire of Sasang Constitution Classification II(QSCC II). The following conclusion were made in comparison with Questionaire of Sasang Constitution Classification II(QSCC II) and Questionaire of Pusan Sasang seminar. 1. The subject of "the facial type is small and sharp" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is more than Taeumin group and Soyangin group. 2. The subject of "the walking form is fast and shake the body" is significant differences in Sasang Constitution classification. The frequency of Taeumin group and Soeumin group is less than Soyangin group. 3. The subject of "the skin type is white and thin" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is more than Soyangin group, and the frequency of Taeumin group is low marks. 4. The subject of "the skin type is tender and dry" is significant differences in Sasang Constitution classification. The frequency of Taeumin group and Soyangin group is less than Soeumin group. 5. The subject of "the image of face is smart" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is more than Taeumin group and the frequency of Soyangin group is low marks. 6. The subject of "the sweating type is not sweatier" is significant differences in Sasang Constitution classification. The frequency of Taeumin group and Soeumin group is less than Soyangin group. 7. The subject of "the desire of eating is changeable accoding to emotion" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is more than Taeumin group and Soyangin group. 8. The subject of "the health is changeable accoding to the type of stool" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is more than Soyangin group and the frequency of Taeumin group is low marks. 9. The subject of "the type of voiding is changeable accoding to the drinking when they have a fever" is significant differences in Sasang Constitution classification. The frequency of Taeumin group and Soyangin group is less than Soeumin group. 10. The subject of "the skin type is soft" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is more than Taeumin group and Soyangin group. 11. The subject of "the chief complaint is the forgetfulness" is significant differences in Sasang Constitution classification. The frequency of Soeumin group is less than Taeumin group and Soyangin group.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.409-416
• /
• 2013

Attention is one of important cognitive functions in human affecting on the selectional concentration of relevant events and ignorance of irrelevant events. The discrimination of attentional and inattentional status is the first step to manage human's attentional capability using computer assisted device. In this paper, we newly combine the non-linear recurrence pattern analysis and spectrum analysis to effectively extract features(total number of 13) from the electroencephalographic signal used in the input to classifiers. The performance of diverse types of attention-inattention classifiers, including supporting vector machine, back-propagation algorithm, linear discrimination, gradient decent, and logistic regression classifiers were evaluated. Among them, the support vector machine classifier shows the best performance with the classification accuracy of 81 %. The use of spectral band feature set alone(accuracy of 76 %) shows better performance than that of non-linear recurrence pattern feature set alone(accuracy of 67 %). The support vector machine classifier with hybrid combination of non-linear and spectral analysis can be used in later designing attention-related devices.

• Science of Emotion and Sensibility
• /
• v.23 no.2
• /
• pp.61-74
• /
• 2020

Voice user interface has become a commercially viable and extensive interaction mechanism with the development of voice assistants. Despite the popularity of voice assistants, the academic community does not utterly understand about what, when, and how users chat with them. Chatting with a voice assistant is crucial as it defines how a user will seek the help of the assistant in the future. This study aims to cover the essence and construct of conversational AI, to develop a classification method to deal with user utterances, and, most importantly, to understand about what, when, and how Chinese users chat with voice assistants. We collected user utterances from the real conventional database of a commercial voice assistant, NetEase Sing in China. We also identified different utterance categories on the basis of previous studies and real usage conditions and annotated the utterances with 17 labels. Furthermore, we found that the three top reasons for the usage of voice assistants in China are the following: (1) greeting, (2) function, and (3) music. Chinese users like to interact with voice assistants at night from 7 PM to 10 PM, and they are polite toward the assistants. The whole percentage of negative feedback utterances is less than 6%, which is considerably low. These findings appear to be useful in voice interaction designs for intelligent hardware.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.334-342
• /
• 2022

Nowadays, as we can notice on social media, most users choose to use more than one language in their online postings. Thus, social media analytics needs reviewing as code-switching analytics instead of traditional analytics. This paper aims to present evidence comparable to the accuracy of code-switching analytics techniques in analysing the mood state of social media users. We conducted a systematic literature review (SLR) to study the social media analytics that examined the effectiveness of code-switching analytics techniques. One primary question and three sub-questions have been raised for this purpose. The study investigates the computational models used to detect and measures emotional well-being. The study primarily focuses on online postings text, including the extended text analysis, analysing and predicting using past experiences, and classifying the mood upon analysis. We used thirty-two (32) papers for our evidence synthesis and identified four main task classifications that can be used potentially in code-switching analytics. The tasks include determining analytics algorithms, classification techniques, mood classes, and analytics flow. Results showed that CNN-BiLSTM was the machine learning algorithm that affected code-switching analytics accuracy the most with 83.21%. In addition, the analytics accuracy when using the code-mixing emotion corpus could enhance by about 20% compared to when performing with one language. Our meta-analyses showed that code-mixing emotion corpus was effective in improving the mood analytics accuracy level. This SLR result has pointed to two apparent gaps in the research field: i) lack of studies that focus on Malay-English code-mixing analytics and ii) lack of studies investigating various mood classes via the code-mixing approach.

• Science of Emotion and Sensibility
• /
• v.6 no.2
• /
• pp.59-64
• /
• 2003

The national standard anthropometry of Korea is conducted every 5∼6 year term after its first research was started in 1979, The fourth research was conducted in 1997. The result of the national standard anthropometry has been reflected in manufactured goods design of allied industries such as clothing, shoes and furniture. In this paper, we measured anthropometry data for every bodily figurative classification after dividing users according to gender, age and bodily figure using the result of the national standard anthropometry. We constructed 3D character through the process of analyzing interrelation of measured anthropomeoy and measuring representative category. In the process for organization , we measured anthropometry which can effectively express sports action of golf, tennis etc. We made it by presenting measurement which is able to form each type of 3D character after the category was decided. Quantitative and objective valuation for posture and action became possible by developing visible information offer and posture action analysis protocol in theoretical approach for analysis of posture and action in sports.