• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.408-410
• /
• 2012

기존의 비디오 검색 방법들은 관련 주석이나 영상 정보에 기반하며 사용자의 반응과 관련하여서는 많은 정보를 활용하고 있지 않다. 비디오 시청시 사용자의 뇌신호나 시선추적 정보 등의 인지적 반응을 이용하여 연속적인 비디오 스트림의 각 부분에 대하여 사용자들이 나타내는 관심이나 감성 정보를 추출한다면 보다 인터랙티브한 비디오 데이터 검색 및 추천이 가능하다. 본 논문에서는 비디오를 시청하는 사용자의 안구전도(electrooculogram)를 기록한 후, 장면 전환이 발생한 부분에서의 사건관련전위 분석을 통해 해당 부분에서 나타나는 특징적 반응을 찾고 이에 대한 인지적 해석을 도출했다. 실험 결과 장면 전환 이후200~700ms 부분에서 P300 성분과 유사한 피크가 발생하는 것을 확인하였으며, 이러한 결과는 장면 전환에 따른 피험자의 비디오 내용 인지에 대한 의도 불일치 및 주의력 증가로 해석된다.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.484-486
• /
• 1998

In this paper, a new method for controlling the pointing device on digital display using EOG(electrooculogram) which is generated from eye movement, was suggested. The manufactured system is consisting of pre-amplifier, A/D converter, serial transmission device and PC program. The EOG is amplified by pre-amplifier. And the amplified EOG is digitized and transmitted to personal computer via rs-232c by PIC16C74A. Finally, the software for controlling the pointer on digital display is developed on computer. As the result, the error between the real subject's viewing point and the point indicated by the developed pointing device on digital display was investigated into the average value, 0.72 degree for horizontal axis, 0.96 degree for vertical axis. The pointing device developed in this study is controlled by subject's eye movement, that is, the user's intention. Furthermore, the algorithm of this study is applicable for many field such as a new method remote control, a new wheelchair control and so forth.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1111-1116
• /
• 2017

In this paper, we developed bio-signal based eye tracking system using electrooculogram (EOG) and electromyogram (EMG) which measured simultaneously from same electrodes. In this system, eye gazing position can be estimated using EOG signal and we can use EMG signal at the same time for additional command control interface. For EOG signal processing, PLA algorithms are applied to reduce processing complexity but still it can guarantee less than 0.2 seconds of reaction delay time. Also, we developed dual machine learning structure and it showed robust and enhanced tracking performances. Compare to conventional EOG based eye tracking system, developed system requires relatively light hardware system specification with only two skin contact electrodes on both sides of temples and it has advantages on application to mobile equipments or wearable devices. Developed system can provide a different UX for consumers and especially it would be helpful to disabled persons with application to orthotics for those of quadriplegia or communication tools for those of intellectual disabilities.

• Proceedings of the ESK Conference
• /
• 1997.10a
• /
• pp.220-225
• /
• 1997

졸음에 의한 순간적 과오는 자동차운전을 비롯한 각종 산업안전에 인명피해를 포함하는 치명적 손실 을 수반한다. 따라서 이분야에 대한 연구가 국내를 포함한 전세계에서 활발히 진행되어 상업화가 추진 중이다. 그러나 이러한 연구는 실용적 차원에서 주로 피부전기활동(Electrodermal Activity: EDA)과 눈 깜박임 등의 측정방법에 의존하고 있으며 졸음의 첫 지시치로서 중요하고 객관적인 각성-졸음 과도기 뇌파를 포함하는 수면 다원생리신호 측정에 관한 연구는 이 방법이 피험자에게 구속성을 주고 측정 자체가 까다로워서 현실적으로어려운 실정이다. 본 연구에서는 그 동안 Medilog SAC847 Polysomnography를 이용한 수면에 관련된 종합적 생리신호를 측정.분석 연구해온 경험을 토대로 정상적인 성인의 각성-졸음 과도기 생리신호특징으로서 뇌전도(Electroencephalogram:EEG), 턱 및 다리근전도(Electromyogram:EMG), 심전도( Electrocardiogram:ECG), 안전도(Electrooculogram:EOG) 등을 종합적으로 분석한 결과 졸음상태가 각성상 태에 비하여 EEG의 주파수는 감소하고, EMG와 ECG의 진폭은 줄어들고, EOG에서는 느린 안구운동의 특징을 갖는 것을 알 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.187-193
• /
• 2008

Interface technologies for a user to control home automation system in wearable computing environment has been studied recently. This paper proposes a new interface method for a disabled person to control home automation system in wearable computing environment by using EOG sensing circuit and marker recognition. In the proposed interface method, the operations of a home network device are represented with human readable markers and displayed around the device. A user wearing a HMD, a video camera, and a computer selects the desired operation by seeing the markers and selecting one of them with eye movement from the HMD display The requested operation is executed by sending the control command for the selected marker to the home network control device. By using the EOG sensing circuit and the marker recognition system a user having problem with moving hands and fit can manipulate a home automation system with only eye movement.

• Journal of the Korean Academy of Clinical Electrophysiology
• /
• v.8 no.1
• /
• pp.43-50
• /
• 2010

Purpose : The objective of this study is to effect of an aquatic rotation control and obstacle avoidance when conducted underwater on hemiplegia patient's balance ability and vestibular function. Methods : Twelve hemiplegia patients participated and were randomly assigned to a control group(I) with standard physical therapy and an aquatic group(II) with an aquatic rotation control, obstacle avoidance and standard physical therapy as well. The aquatic group trained using a Halliwick rotation control and obstacle avoidance through 3 times per week over 6 weeks. For all subjects, vestibular function, their balance, the change of electrooculogram (EOG), the change of accelerometer axis and torsiometer according to visual sense, vestibular sense with galvanic vestibular stimulation (GVS) or not during leg close stance were measured. Results : The EOG in the vertical and horizontal (p<0.05) were both significantly lowered. The change was significantly lower in the trajectory range of motion of trunk and spine with torsiometer when leg close stand (p<0.01) and leg close stand with GVS (p<0.01). The centre of gravity accelerated, there were reduced significantly difference X and Y axis of accelerometer during the closing of the leg without vision (p<0.05). There were reduced significantly difference X and Z axis of accelerometer during the closing of the leg with GVS (p<0.05). There were reduced significantly difference X and Z axis of accelerometer during the closing of the leg and close eyes with GVS (p<0.05). Conclusion : The balance ability, vestibular system and postural control is improved.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.3
• /
• pp.136-141
• /
• 2012

One of the main reasons for serious road accidents is driving while drowsy. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. One of the effective signals is to measure electroencephalogram (EEG) signals and electrooculogram (EOG) signals. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, drowsiness, sleepiness. This paper proposes a neural-network-based drowsiness detection system using Linear Predictive Coding (LPC) coefficients as feature vectors and Multi-Layer Perceptron (MLP) as a classifier. Samples of EEG data from each predefined state were used to train the MLP program by using the proposed feature extraction algorithms. The trained MLP program was tested on unclassified EEG data and subsequently reviewed according to manual classification. The classification rate of the proposed system is over 96.5% for only very small number of samples (250ms, 64 samples). Therefore, it can be applied to real driving incident situation that can occur for a split second.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.768-773
• /
• 2012

One of the main reasons for serious road accidents is driving while drowsy. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. One of the effective signals is to measure electroencephalogram (EEG) signals and electrooculogram (EOG) signals. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, drowsiness, sleepiness. This paper proposes a drowsiness detection system using Linear Predictive Coding (LPC) coefficients and Support Vector Machine (SVM). Samples of EEG data from each predefined state were used to train the SVM program by using the proposed feature extraction algorithms. The trained SVM program was tested on unclassified EEG data and subsequently reviewed according to manual classification. The classification rate of the proposed system is over 96.5% for only very small number of samples (250ms, 64 samples). Therefore, it can be applied to real driving incident situation that can occur for a split second.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.129-137
• /
• 2013

As the usage of computer based systems continues to increase in our normal life, there are constant efforts to enhance the accessibility of information for handicapped people. For this, it is essential to develop new interface ways for physical disabled peoples by means of human-computer interface (HCI) or human-machine interface (HMI). In this paper, we developed HMI using electromyogram (EMG) and electrooculogram (EOG) for people with physical disabilities. Developed system is composed of two modules, hardware module for signal sensing and software module for feature extraction and pattern classification. To maximize ease of use, only two skin contact electrodes are attached on both ends of brow, and EOG and EMG are measured simultaneously through these two electrodes. From measured signal, nine kinds of command patterns are extracted and defined using signal processing and pattern classification method. Through Java based real-time monitoring program, developed system showed 92.52% of command recognition rate. In addition, to show the capability of the developed system on real applications, five different types of commands are used to control ER1 robot. The results show that developed system can be applied to disabled person with quadriplegia as a novel interface way.

• Science of Emotion and Sensibility
• /
• v.6 no.4
• /
• pp.9-14
• /
• 2003

Sleep stages have been useful indicator to check a person's comfortableness in a sleep, But the traditional method of scoring sleep stages with polysomnography based on the integrated analysis of the electroencephalogram(EEG), electrooculogram(EOG), electrocardiogram(ECG), and electromyogram(EMG) is too restrictive to take a comfortable sleep for the participants, While the sympathetic nervous system is predominant during a wakefulness, the parasympathetic nervous system is more active during a sleep, Cardiovascular function is controlled by this autonomic nervous system, So, we have interpreted the heart rate variability(HRV) among sleep stages to find a simple method of classifying sleep stages, Six healthy male college students participated, and 12 night sleeps were recorded in this research, Sleep stages based on the "Standard scoring system for sleep stage" were automatically classified with polysomnograph by measuring EEG, EOG, ECG, and EMG(chin and leg) for the six participants during sleeping, To extract only the ECG signals from the polysomnograph and to interpret the HRV, a Sleep Data Acquisition/Analysis System was devised in this research, The power spectrum of HRV was divided into three ranges; low frequency(LF), medium frequency(MF), and high frequency(HF), It showed that, the LF/HF ratio of the Stage W(Wakefulness) was 325% higher than that of the Stage 2(p＜.05), 628% higher than that of the Stage 3(p＜.001), and 800% higher than that of the Stage 4(p＜.001), Moreover, this ratio of the Stage 4 was 427% lower than that of the Stage REM (rapid eye movement) (p＜.05) and 418% lower than that of the Stage l(p＜.05), respectively, It was observed that the LF/HF ratio decreased monotonously as the sleep stage changes from the Stage W, Stage REM, Stage 1, Stage 2, Stage 3, to Stage 4, While the difference of the MF/(LF+HF) ratio among sleep Stages was not significant, it was higher in the Stage REM and Stage 3 than that of in the other sleep stages in view of descriptive statistic analysis for the sample group.