• The Journal of the Acoustical Society of Korea
• /
• 제21권2E호
• /
• pp.98-104
• /
• 2002

The present study describes a combination method to recognize the human affective states such as anger, happiness, sadness, or surprise. For this, we extracted emotional features from voice signals and facial expressions, and then trained them to recognize emotional states using hidden Markov model (HMM) and neural network (NN). For voices, we used prosodic parameters such as pitch signals, energy, and their derivatives, which were then trained by HMM for recognition. For facial expressions, on the other hands, we used feature parameters extracted from thermal and visible images, and these feature parameters were then trained by NN for recognition. The recognition rates for the combined parameters obtained from voice and facial expressions showed better performance than any of two isolated sets of parameters. The simulation results were also compared with human questionnaire results.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 춘계학술대회
• /
• pp.935-939
• /
• 2003

The emotion recognition is one of the most significant interface technologies which make the high level of human-machine communication possible. The central nervous system stimulated by emotional stimuli affects the autonomous nervous system like a heart, blood vessel, endocrine organs, and so on. Therefore bio-signals like HRV, ECG and EEG can reflect one' emotional state. This study investigates the correlation between emotional states and bio-signals to realize the emotion recognition. This study also covers classification of human emotional states, selection of the effective bio-signal and signal processing. The experimental results presented in this paper show possibility of the emotion recognition.

• 한국산업융합학회 논문집
• /
• 제26권2_1호
• /
• pp.225-230
• /
• 2023

This research addresses sound command based human tracking problems for autonomous cleaning mobile robot in a networked AI space. To solve the problem, the difference among the traveling times of the sound command to each of three microphones has been used to calculate the distance and orientation of the sound from the cleaning mobile robot, which carries the microphone array. The cross-correlation between two signals has been applied for detecting the time difference between two signals, which provides reliable and precise value of the time difference compared to the conventional methods. To generate the tracking direction to the sound command, fuzzy rules are applied and the results are used to control the cleaning mobile robot in a real-time. Finally the experiment results show that the proposed algorithm works well, even though the mobile robot knows little about the environment.

• 대한의용생체공학회:의공학회지
• /
• 제27권3호
• /
• pp.101-109
• /
• 2006

It has been known that there is strong relationship between human voices and the movements of the articulatory facial muscles. In this paper, we utilize this knowledge to implement an automatic speech recognition scheme which uses solely surface electromyogram (EMG) signals. The EMG signals were acquired from three articulatory facial muscles. Preliminary, 10 Korean digits were used as recognition variables. The various feature parameters including filter bank outputs, linear predictive coefficients and cepstrum coefficients were evaluated to find the appropriate parameters for EMG-based speech recognition. The sequence of the EMG signals for each word is modelled by a hidden Markov model (HMM) framework. A continuous word recognition approach was investigated in this work. Hence, the model for each word is obtained by concatenating the subword models and the embedded re-estimation techniques were employed in the training stage. The findings indicate that such a system may have a capacity to recognize speech signals with an accuracy of up to 90%, in case when mel-filter bank output was used as the feature parameters for recognition.

• 한국통신학회논문지
• /
• 제35권5A호
• /
• pp.440-446
• /
• 2010

다양한 분야에서 IT와 BT의 융합이 논의되고 있으며 의료 산업에서 캡슐 내시경의 개발은 인체를 매개로 무선 통신을 한다는 점에서 그 예라 할 수 있을 것이다. 하지만 인체 채널에서의 통신은 송신 전력의 제한이 엄격할 수 밖에 없으며, 아직 채널 특성에 대한 활발한 연구도 이루어지지 않아서 그 채널을 추정하기가 매우 어렵다. 따라서 정확한 채널 추정이 필요한 일반적인 부호화 / 복호화 기법을 사용할 수 없으며, 기존 통신망에서 유입되는 간섭 신호에 취약할 수 밖에 없다. 본 논문에서는 채널 추정이 필요 없으면서도, 주위 간섭 신호의 영향에 강인한 Chirp Spread Spectrum Differential Binary Phase Shift Keying(CSS-DBPSK) 기법을 소개하고, Chirp Spread Spectrum On-Off Keying (CSS-OOK) 기법을 제안한다. CSS-DBPSK, CSS-OOK를 이용하면 일반 OOK에 비하여 target BER (Bit Error Rate) 10-5)을 위한 Eb/N0을 약 5dB, 2dB 낮출 수 있으며 간섭 신호에 대한 성능 저하도 막을 수 있다.

• Transactions on Control, Automation and Systems Engineering
• /
• 제4권1호
• /
• pp.49-55
• /
• 2002

A decrease in the birthrate and aging are progressing in Japan and several countries. In that society, it is important that physically weak persons such as elderly persons are able to take care of themselves. We have been developing exoskeletal robots for human (especially for physically weak persons) motion support. In this study, the controller controls the angular position and impedance of the exoskeltal robot system using multiple fuzzy-neuro controllers based on biological signals that reflect the human subject's intention. Skin surface electromyogram (EMG) signals and the generated wrist force by the human subject during the elbow motion have been used as input information of the controller. Since the activation level of working muscles tends to vary in accordance with the flexion angle of elbow, multiple fuzzy-neuro controllers are applied in the proposed method. The multiple fuzzy-neuro controllers are moderately switched in accordance with the elbow flexion angle. Because of the adaptation ability of the fuzzy-neuro controllers, the exoskeletal robot is flexible enough to deal with biological signal such as EMG. The experimental results show the effectiveness of the proposed controller.

• The Journal of the Acoustical Society of Korea
• /
• 제23권2E호
• /
• pp.56-67
• /
• 2004

Despite abundant research outcomes of blind source separation (BSS) in many types of simulated environments, their performances are still not satisfactory to be applied to the real environments. The major obstacle may seem the finite filter length of the assumed mixing model and the nonlinear sensor noises. This paper presents a two-step speech enhancement method with multiple microphone inputs. The first step performs a frequency-domain BSS algorithm to produce multiple outputs without any prior knowledge of the mixed source signals. The second step further removes the remaining cross-channel interference by a spectral cancellation approach using a probabilistic source absence/presence detection technique. The desired primary source is detected every frame of the signal, and the secondary source is estimated in the power spectral domain using the other BSS output as a reference interfering source. Then the estimated secondary source is subtracted to reduce the cross-channel interference. Our experimental results show good separation enhancement performances on the real recordings of speech and music signals compared to the conventional BSS methods.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1995년도 춘계학술대회
• /
• pp.160-163
• /
• 1995

An optimal EEG and artifact classifier is proposed using neural network operating characteristics. The neural network operating characteristics are two dimensional parametric representations of the right and false identification probabilities of the network classifier. Since the EEG and EP signals acquired from multi -channel electrodes placed on the head surface are often interfered by other relatively large physiological signals such as electromyogram (EMG) or electroculogram (EOG), the removal of the artifact-affected EEGs is one of the key elements in neuro-functional mapping. Conventionally this task has been carried out by human experts spending lots of examination time. Using the neural-network based classification, human expert's efforts and time can be substantially reduced. From experiments, the neural-network based classification performs as good as human experts: variation of decisions between the neural network and human expert appears even smaller than that between human experts.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.364-371
• /
• 2015

In this study, we developed a feasible structure of a textile-based inductive sensor using a machine embroidery method, and applied it to a non-contact type vital sign sensing device based on the principle of magnetic-induced conductivity. The mechanical heart activity signals acquired through the inductive sensor embroidered with conductive textile on fabric were compared with the Lead II ECG signals and with respiration signals, which were simultaneously measured in every case with five subjects. The analysis result showed that the locations of the R-peak in the ECG signal were highly associated with sharp peaks in the signals obtained through the textile-based inductive sensor (r=0.9681). Based on the results, we determined the feasibility of the developed textile-based inductive sensor as a measurement device for the heart rate and respiration characteristics.

• 디지털콘텐츠학회 논문지
• /
• 제19권4호
• /
• pp.821-827
• /
• 2018

Affective Computing은 HCI (Human Computer Interaction) 및 건강 관리 분야에서 다양한 애플리케이션이 개발됨에 따라 최근 몇 년 동안 관심이 높아지고 있다. 이에 필수적으로 필요한 인간의 감정 인식에 대한 중요한 연구가 있었지만, 언어 및 표정과 비교하여 심전도 (ECG) 또는 뇌파계 (EEG) 신호와 같은 생리적 신호 분석에 따른 감정 분석에 대한 관심은 적었다. 본 논문에서는 이산 웨이블릿 변환을 이용한 EEG 기반 감정 인식 시스템을 제안하고 감정 관련 정보를 얻기 위해 다른 뇌파와 뇌 영역을 연구 하였으며, 웨이블릿 계수에 기초한 특징 세트가 웨이블릿 에너지 특징과 함께 추출되었다. 중복성을 최소화하고 피처 간의 관련성을 극대화하기 위해 mRMR 알고리즘이 피쳐 선택에 적용된다. 다중클래스 Support Vector Machine을 사용하여 4 가지 종류의 인간 감정을 크게 분류하였으며 공개적으로 이용 가능한 "DEAP"데이터베이스의 뇌파 기록이 실험에서 사용되었다. 제안 된 접근법은 기존의 알고리즘에 비해 향상된 성능을 보여준다.