Communication system using EOG for persons with disabilities and its judgment by EEG

The Electrooculogram (EOG) signal is often contaminated with artifacts and power-line while recording. It is very much essential to denoise the EOG signal for quality diagnosis. The present study deals with denoising of noisy EOG signals using Stationary Wavelet Transformation (SWT) technique by two different approaches, namely, increasing segments of the EOG signal and different equal segments of the EOG signal. For performing the segmental denoising analysis, an EOG signal is simulated and added with controlled noise powers of 5 dB, 10 dB, 15 dB, 20 dB, and 25 dB so as to obtain five different noisy EOG signals. The results obtained after denoising them are extremely encouraging. Root Mean Square Error (RMSE) values between reference EOG signal and EOG signals with noise powers of 5 dB, 10 dB, and 15 dB are very less when compared with 20 dB and 25 dB noise powers. The findings suggest that the SWT technique can be used to denoise the noisy EOG signal with optimum noise powers ranging from 5 dB to 15 dB. This technique might be useful in quality diagnosis of various neurological or eye disorders.

In this paper, we present a comparison Support Vector Machine (SVM) and Artificial Neural Network (ANN) for classification of electrooculogram (EOG) signals acquired under specific eye movements. These methods that are required for an eye controlled system are compared by means of their accuracy and response time. Acquired EOG signals consist of 5 different eye movements - being horizontal (right and left), vertical (up and down) and blink. EOG signal acquisition was achieved from 20 different subjects by using two EOG channels (vertical and horizontal) and 3 element feature vectors were extracted. The first two elements of the feature vectors are the peak amplitudes of two channels whereas the third element, being our proposed parameter, is the kurtosis value of the active channel. 10 of 20 randomly selected feature vectors were used for training of the classifiers whereas the rest was used for performance tests. Offline tests yield 100 % success rate for both of the classifiers. The response times of both methods make them suitable for real-time usage.

In this study, Electrooculogram (EOG) based Human-Machine Interface (HMI) application is proposed for partial or completely paralyzed and physically limited people as Amyotrophic Lateral Sclerosis (ALS) patients. In the designed system, EOG signals consisted of vertical and horizontal eye movements are detected by using 6 Ag-AgCl electrodes which placed around the eye. Then, by applying amplifying and filtering processes to the detected signals, EOG signals at 0-+5V amplitude levels are obtained at the output of analog stage. In consequence of digital processing of analog EOG data with microcontroller unit, control signals for HMI applications are acquired. At signal processing stage, after preprocessing step for eye movements (vertical, horizontal and blink) maximum and minimum voltage amplitude values are detected. These values are directly determine the performance of the classification process. K-Nearest Neighbor (k-NN) classifier and Support Vector Machines (SVM) are used for classification. According to the results, k-NN and SVM perform the classification task with %90.3 and %92.6 accuracy, respectively. Simulation results show that with the proposed EOG based HMI system, physically limited patients can communicate with their environments in a successful manner.

Human-machine interfaces (HMIs) based on Electro-oculogram (EOG) signals have been widely explored. However, due to the individual variability, it is still challenging for an EOG-based eye movement recognition model to achieve favorable results among cross-subjects. The classical transfer learning methods such as CORrelation Alignment (CORAL), Transfer Component Analysis (TCA), and Joint Distribution Adaptation (JDA) are mainly based on feature transformation and distribution alignment, which do not consider similarities/dissimilarities between target subject and source subjects. In this paper, the Kullback-Leibler (KL) divergence of the log-Power Spectral Density (log-PSD) features of horizontal EOG (HEOG) between the target subject and each source subject is calculated for adaptively selecting partial subjects that suppose to have similar distribution with target subject for further training. It not only consider the similarity but also reduce computational consumption. The results show that the proposed approach is superior to the baseline and classical transfer learning methods, and significantly improves the performance of target subjects who have poor performance with the primary classifiers. The best improvement of Support Vector Machines (SVM) classifier has improved by 13.1% for subject 31 compared with baseline result. The preliminary results of this study demonstrate the effectiveness of the proposed transfer framework and provide a promising tool for implementing cross-subject eye movement recognition models in real-life scenarios.

To observe the clinical efficacy of transcutaneous electrical acupoint stimulation (TEAS) at Changqiang (GV 1) based on the modulation of electro-oculogram (EOG) signal for children with mental retardation, and explore the evaluation effect of the goal attainment scale (GAS) in children with mental retardation. Sixty children with mental retardation were randomly divided into a treatment group and a control group, with 30 cases in each one. The children in the control group were treated with conventional rehabilitation, 5 times a week. On the basis of the control group, TEAS at Changqiang (GV 1) under the modulation of EOG signal was adopted in the treatment group. When the similarity between the collected EOG signal and the template was within the range of EOG threshold, one electric stimulation was triggered at Changqiang (GV 1) for 20 s (continuous wave, 70-100 Hz in frequency, 0.1-0.2 ms in pulse width), lasting 30 min in each treatment, the intervention was given twice a week. One course of treatment was composed of 4 weeks, and 3 courses were required in total in the two groups. The infant-junior high school student's social living ability scale (S-M) and GAS were scored and compared before and after treatment in the two groups. After treatment, the scores of self-living ability in the treatment group and communication ability in the control group were higher than those before treatment (P<0.01, P<0.05). The scores of collective activity and motor ability in the treatment group were higher than those in the control group (P<0.05). After treatment, GAS scores were higher than before treatment in both groups (P<0.001), and the score in the treatment group was higher than the control group (P<0.05). TEAS under the modulation of EOG signal is conductive to improving the collective, motor and self-living abilities of the children with mental retardation and promoting children's individual goals. Compared with the standard score of S-M, the T value of GAS can better reflect the subtle progress of individual.

A meal assistance orthosis is developed for elderly and/or disable persons who have partly or completely lost the ability of moving their upper limbs by themselves independently. The meal assistance orthosis supports the disabled persons and brings foods from dishes to their mouth by their own forearms. Human intention, i.e., which foods they want to eat, can be extracted from electrooculogram (EOG) signals which are measured by electrodes on the face. Position control is adopted for control strategy of the meal assistance orthosis, and forcefree control which can realize flexible motion of the meal assistance orthosis is adopted in order to avoid the meal assistance orthosis injure the subject. The effectiveness of the developed meal assistance orthosis is assured by experimental works on normal persons

Assistive robots play an increasingly important role in the lives of people with disabilities. More and more research efforts are being focused on using Electrooculogram (EOG) signals in driving assistive robots. This paper presents a new shared control architecture based on EOG signal and global vision for assistive robots. This paper firstly introduces the shared control concept with detailed block diagrams and then presents the work flow process of EOG signal acquisition and angle recognition. A state machine design is also presented that makes the control command transfer sequentially. Finally, control strategies of intent conflict and intent consistency, respectively, are also presented for different intent expression scenarios. Experiment results demonstrate that the shared control architecture proposed in this paper is effective that can reduce the user's operational load significantly.

Electrooculogram (EOG) is an important bio-electricity signal generated by physical activities of eyeballs. Information about gaze position can be obtained by analyzing EOG signals, which can lay a foundation for a novel way of human-computer interaction (HCI) based on EOG signals. In this paper, we propose a gaze estimation method based on EOG signals. After filtering and amplifying the acquired EOG signals, framing and normalization is done to make the signals easier to classify. The wavelet coefficients are extracted as the feature vectors, and BP classifier is trained to classify EOG signals of different directions. The results show that this method works well with different people and the average accuracy achieves 96%.

Human–computer interface (HCI) methods based on the electrooculogram (EOG) signals generated from eye movement have been continuously studied because they can transmit the commands to a computer or machine without using both arms. However, usability and appearance are the big obstacles to practical applications since conventional EOG-based HCI methods require skin electrodes outside the eye near the lateral and medial canthus. To solve these problems, in this paper, we report development of an HCI method that can simultaneously acquire EOG and surface-electromyogram (sEMG) signals through electrodes integrated into bone conduction headphones and transmit the commands through the horizontal eye movements and various biting movements. The developed system can classify the position of the eyes by dividing the 80-degree range (from −40 degrees to the left to +40 degrees to the right) into 20-degree sections and can also recognize the three biting movements based on the bio-signals obtained from the three electrodes, so a total of 11 commands can be delivered to a computer or machine. The experimental results showed the interface has accuracy of 92.04% and 96.10% for EOG signal-based commands and sEMG signal-based commands, respectively. As for the results of virtual keyboard interface application, the accuracy was 97.19%, the precision was 90.51%, and the typing speed was 5.75–18.97 letters/min. The proposed interface system can be applied to various HCI and HMI fields as well as virtual keyboard applications.

HCI system with the help of bio-signals such as EEG, EOG, EMG, etc. stand out to be the peaking subject of research in the recent years. This paper presents the design system for the cursor movement through eyes using Electrooculogram (EOG) signal for a physically disabled people to assist them in operating the basic home appliances. In this work, a Home Automation System using Arduino UNO has been developed, so that it can function by the movement and click of the cursor when positioned to the particular location of the switches. Eye movement have been detected by extracting and recording the EOG signal using a BIOPAC System. The interfacing of this system design has been developed in the platform of MAT LAB Software. Operation of home appliances such as switching on a light or a fan by the cursor movement and click through eyes on screen for physically impaired people is the outcome of this research.

Paralysis patients, particularly those with amyotrophic lateral sclerosis (ALS), gradually lose the ability to speak because of muscle loss. Even communication through gestures becomes difficult as their condition progresses. Eventually, the only means of communication left is eye movement. Using electrooculogram (EOG) signals, it is possible to improve the communication abilities of those patients who can move their eyes. We examined whether blinking could be detected from the back of the head in a noncontact manner using an in-pillow cloth electrode. We conducted an experiment aimed at detecting blinks in five subjects. The results revealed the possibility of measuring the change of potential related to blinks, with average sensitivity of 96%. This suggested the possibility of establishing a simple tool for ALS patients and paralysis patients to communicate through blinking.

Validating and improving the correction of ocular artifacts in electro-encephalography

One of the most common factors of road accidents is the drowsiness of drivers. The project's key purpose is to define the strategies for detecting and alerting driver somnolence, thus growing transportation safety. Via uses several physiological variables, such as pulse rate, EEG, ECG, eyelid closure, skin conductance. This scenario indicates that the driver is not in reasonable driving shape. EOG signals are used in this suggested framework. The Electrooculogram (EOG) is an electrical activity indicator related to eye motions. Other signal origins, called objects, may contaminate the electrooculography signal. Eye wink is one of the key causes of disturbance in the EOG signals among the various artefact sources. Blink attributes are determined from these signals, and they are evaluated using Fuzzy logic.

The Cornea-Retinal Potential (CRP) is the main source of the Electrooculogram (EOG) signals. These potential are in small microvolt and required to be amplified upto the applicable and usable level. The place of electrode attachment, the eyeball rotation, the motion of head, the ambient light as well as the conductivity of skin can also vary this signal. These numerous artifacts with power-line interference and other unwanted noise had made the EOG signal quite unattractive for any real biomedical applications. This work thus mainly focuses on the elimination of the above major artifacts while striving to maintain signal linearity. The hardware design part also considers the cost effectiveness without negotiating accuracy. The circuit is then rigorously tested and checked over the varied sample of people. It is found to give an efficient and significantly consistent result with minimum noise level. The development and design of a low cost EOG signal amplifier and acquisition system that counters all the major problems is investigated and achieved making it suitable for both theoretical research analysis as well as for real practical applications.

An alternative for the physically challenged people to live independently is smart houses with assistive technology. Here an assistive computer aided multitasking graphical user interface (GUI) controlled by eye movements for the disabled individuals, especially for those with severe paralysis, has been presented. Electrooculogram (EOG) signals were acquired for horizontal, vertical eye movements and blinks using Ag/AgCl surface electrodes. After pre-processing, the signals were classified based on their amplitudes to generate control commands to drive a GUI. Finally the application of the GUI is tested with six healthy subjects by performing different icon selection by controlling the mouse pointer with eye movements. The users completed the testing process in a reasonable time and the speed improves with training. For the real-time control of the GUI, the proposed approach yields 95.83% accuracy. The results suggest that the GUI can be used by disabled people with more improved control scheme.