• Dementia and Neurocognitive Disorders
• /
• v.23 no.3
• /
• pp.146-160
• /
• 2024

Background and Purpose: The emotions of people at various stages of dementia need to be effectively utilized for prevention, early intervention, and care planning. With technology available for understanding and addressing the emotional needs of people, this study aims to develop speech emotion recognition (SER) technology to classify emotions for people at high risk of dementia. Methods: Speech samples from people at high risk of dementia were categorized into distinct emotions via human auditory assessment, the outcomes of which were annotated for guided deep-learning method. The architecture incorporated convolutional neural network, long short-term memory, attention layers, and Wav2Vec2, a novel feature extractor to develop automated speech-emotion recognition. Results: Twenty-seven kinds of Emotions were found in the speech of the participants. These emotions were grouped into 6 detailed emotions: happiness, interest, sadness, frustration, anger, and neutrality, and further into 3 basic emotions: positive, negative, and neutral. To improve algorithmic performance, multiple learning approaches were applied using different data sources-voice and text-and varying the number of emotions. Ultimately, a 2-stage algorithm-initial text-based classification followed by voice-based analysis-achieved the highest accuracy, reaching 70%. Conclusions: The diverse emotions identified in this study were attributed to the characteristics of the participants and the method of data collection. The speech of people at high risk of dementia to companion robots also explains the relatively low performance of the SER algorithm. Accordingly, this study suggests the systematic and comprehensive construction of a dataset from people with dementia.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.221-228
• /
• 2023

Physical and mental changes caused by emotions can affect various behaviors, such as driving or learning behavior. Therefore, recognizing these emotions is a very important task because it can be used in various industries, such as recognizing and controlling dangerous emotions while driving. In this paper, we attempted to solve the emotion recognition task by implementing a multimodal model that recognizes emotions using both audio and video data from different domains. After extracting voice from video data using RAVDESS data, features of voice data are extracted through a model using 2D-CNN. In addition, the video data features are extracted using a slowfast feature extractor. And the information contained in the audio and video data, which have different domains, are combined into one feature that contains all the information. Afterwards, emotion recognition is performed using the combined features. Lastly, we evaluate the conventional methods that how to combine results from models and how to vote two model's results and a method of unifying the domain through feature extraction, then combining the features and performing classification using a classifier.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.145-148
• /
• 2004

규칙 기반 추론 시스템에서 규칙의 속성 감축은 다양한 방법으로 제안되어 왔다. 규칙의 속성 감축은 퍼지 추론 시스템을 구현하는데 있어서 처리 시간을 단축시킬 수 있으나 규칙의 종속성 및 상관성을 고려하지 않을 경우 예상하지 못한 추론 결과를 얻을 수 있다. 따라서, 본 논문에서는 복합속성을 가진 규칙의 속성 감축과 상관성을 고려하기 위하여 러프집합의 특성 중 식별가능 행렬과 식별가능 함수를 이용하였다. 그리고 속성 감축에 사용된 규칙은 복합속성(composite attribute)을 가지는 감성 데이터를 이용하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.52.5-52
• /
• 2002

In this paper, we develop analysis models for classification of temporal data from human subjects. The study focuses on the analysis of electroencephalogram (EEG) signals obtained during various emotional states. We demonstrate a generally applicable method of removing EOG and EMG artifacts from EEGs based on independent component analysis (ICA). All EEG channel maps were interpolated from 10 EEG subbands. ICA methods are based on the assumptions that the signals recorded on the scalp are mixtures of signals from independent cerebral and artifactual sources, that potentials arising from different parts of the brain, scalp and body are summed linearly at the electrodes and that prop...

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1391-1392
• /
• 2015

최근 컴퓨터 기술이 발전하고, 컴퓨터의 형태가 다양해지면서 여러 wearable device들이 생겨났다. 이에 따라 휴먼 인터페이스 기술에서 사람의 감정정보가 중요해졌고, 감정인식에 대한 연구들이 많이 진행 되어 왔다. 본 논문에서는 감정분석에 적합한 특징벡터를 제시하고자 한다. 이를 위해 사람의 감정을 보통, 기쁨, 슬픔, 화남 4가지로 분류하고 방송매체를 통하여 잡음 없이 녹음하였다. 특징벡터는 MFCC, LPC, LPCC 3가지를 추출하였고 Bhattacharyya거리 측정을 통하여 분리도를 비교하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.55-58
• /
• 2023

본 논문에서는 스마트 미러 사용자의 얼굴 인식, 표정 인식, 얼굴형 인식을 활용하여 감정에 적절한 멘트와 화장법을 제공하는 시스템의 개발 내용에 관해 기술한다. 이 시스템을 사용함으로써 사람들은 자신의 감정을 정확하게 인지할 뿐만 아니라 위로와 공감을 받을 수 있으며, 자신의 스타일에 적절한 화장법을 추천받을 수 있다. 스마트 미러를 통해, 사용자는 자기 이해도가 늘어나게 되어 스스로에게 더욱 집중할 수 있고 화장법을 찾는 시간이나 화장에 실패할 가능성이 줄어들어 시간과 비용을 절약할 수 있게 될 것이다.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.870-874
• /
• 2009

Genetic algorithms can be effectively used when generating abstract images in an automatic way. However, managing huge number of automatically generated images has been problematic without sufficient managing mechanisms. This paper presents effective classification scheme for the abstract Affine images using form, emotion and color facets, and implements image databases.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.532-536
• /
• 2018

심층인공신경망을 이용한 대화 모델링 연구가 활발하게 진행되고 있다. 본 논문에서는 대화에서 발화의 감정과 화행을 분류하기 위해 멀티태스크(multitask) 학습을 이용한 End-to-End 시스템을 제안한다. 우리는 감정과 화행을 동시에 분류하는 시스템을 개발하기 위해 멀티태스크 학습을 수행한다. 또한 불균형 범주 분류를 위해 계단식분류(cascaded classification) 구조를 사용하였다. 일상대화 데이터셋을 사용하여 실험을 수행하였고 macro average precision으로 성능을 측정하여 감정 분류 60.43%, 화행 분류 74.29%를 각각 달성하였다. 이는 baseline 모델 대비 각각 29.00%, 1.54% 향상된 성능이다. 본 논문에서는 제안하는 구조를 이용하여, 발화의 감정 및 화행 분류가 End-to-End 방식으로 모델링 가능함을 보였다. 그리고, 두 분류 문제를 하나의 구조로 적절히 학습하기 위한 방법과 분류 문제에서의 범주 불균형 문제를 해결하기 위한 분류 방법을 제시하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2E
• /
• pp.74-78
• /
• 2006

This paper proposes an effective method for classifying emotions of the music from its acoustical signals. Two feature sets, timbre and tempo, are directly extracted from the modified discrete cosine transform coefficients (MDCT), which are the output of partial MP3 (MPEG 1 Layer 3) decoder. Our tempo feature extraction method is based on the long-term modulation spectrum analysis. In order to effectively combine these two feature sets with different time resolution in an integrated system, a classifier with two layers based on AdaBoost algorithm is used. In the first layer the MDCT-driven timbre features are employed. By adding the MDCT-driven tempo feature in the second layer, the classification precision is improved dramatically.

• Journal of Korea Multimedia Society
• /
• v.17 no.12
• /
• pp.1521-1527
• /
• 2014

This paper presents to design User eXperience(UX) of anthropomorphic animal characters search system (hereinafter, AACSS) for efficient user search. To this end, meta data were utilized herein to elevate the search efficiency of multimedia information and text information. Anthropomorphic animal characters require the human elements and the animal elements, thus this paper extracted the key elements of meta data as below; phenotypic element in animal system classification (Morphologic property elements, Ecological property elements, Behavioral property elements), emotion classification, which is the trait of personification and the Step of Anthropomorphic Animal Characters.