Shih-Chung Chen

The BCI Control Applied to the Interactive Autonomous Robot with the Function of Meal Assistance

A brain–computer interface (BCI) system is proposed to control an interactive autonomous robot with a function to assist with feeding meals. The subject’s electroencephalogram (EEG), regarded as the control command, can be utilized to combine with system integration technologies to establish a BCI control robot system with an automatic feeding function. At present, the integrated technologies of the automatic feeding robot encompasses image recognition, voice recognition, the robot’s mechanism design, the gripper, tactile sensor design, etc. The automatic feeding robot can be controlled by steady state visual evoked potential (SSVEP)-based BCI to use the gripper grasping a utensil to ladle food to the subject’s mouth successfully. The signal processing algorithm adopted for the SSVEP-based BCI is magnitude squared coherence (MSC). Ten subjects participated in the BCI test for choosing the food on the plate. The average of MSC values for different visual stimulation frequencies were calculated and compared.

A Hybrid Vector Quantization Combining a Tree Structure and a Voronoi Diagram

Multimedia data is a popular communication medium, but requires substantial storage space and network bandwidth. Vector quantization (VQ) is suitable for multimedia data applications because of its simple architecture, fast decoding ability, and high compression rate. Full-search VQ can typically be used to determine optimal codewords, but requires considerable computational time and resources. In this study, a hybrid VQ combining a tree structure and a Voronoi diagram is proposed to improve VQ efficiency. To efficiently reduce the search space, a tree structure integrated with principal component analysis is proposed, to rapidly determine an initial codeword in low-dimensional space. To increase accuracy, a Voronoi diagram is applied to precisely enlarge the search space by modeling relations between each codeword. This enables an optimal codeword to be efficiently identified by rippling an optimal neighbor from parts of neighboring Voronoi regions. The experimental results demonstrated that the proposed approach improved VQ performance, outperforming other approaches. The proposed approach also satisfies the requirements of handheld device application, namely, the use of limited memory and network bandwidth, when a suitable number of dimensions in principal component analysis is selected.

Smart home control for the people with severe disabilities

The issue of smart home control is one of popular applications of Internet of Things (IoT). However, most of the smart home designs are for normal people, just few applications of home appliance automation are designed for the disabled. This study shows the novel implementation of home appliance automation based on a Morse code text input (McTin) controller designed by research team for the people with severe disabilities and analyzes the living behavior of the subject with disabilities according to the operation frequencies of different home appliances.

A new estimate technology of non-invasive continuous blood pressure measurement based on electrocardiograph

Various physiological parameters have been widely used in the prevention and detection of diseases. In particular, the occurrence of cardiovascular diseases can be observed through daily measurement of blood pressure. Currently, the most common blood pressure measurement method records blood pressure on the upper arm. This can lead to the subject feeling uncomfortable and tension in the arm from the stress may lead to measurement errors. An electrocardiogram represents the electrical activity during heart function, but also contains blood pressure–related information. This study is an attempt to extract features related to blood pressure from the electrocardiogram signal using a new non-invasive blood pressure measurement technology that utilizes intelligent neural network algorithms to calculate blood pressure values from electrocardiogram parameters. In this study, the average error rate of the blood pressure measurement was lower than 5% compared to the common blood pressure machine. The proposed approach alleviates the errors caused by discomfort, which provides a more feasible method to continuously monitor blood pressure in less stressful conditions. This technology has significant potential for advancing healthcare.

Prediction of Depth of Sedation from Biological Signals Using Continuous Restricted Boltzmann Machine

Proper anesthesia is very important for patients to get through surgery without pain and then avoid some other problems. By monitoring the depth of sedation for a patient, it could help a clinician to provide a suitable amount of anesthetic and other clinical treatment. In hospital, a patient is usually monitored by different types of biological systems. To predict the depth of sedation from biological signals is able to ease patient monitoring services. In this study, continuous restricted Boltzmann machines based neural network is proposed to predict the depth of sedation. The biological signals including heart rate, blood pressure, peripheral capillary oxygen saturation, and body weight are selected as analytic features. To improve the accuracy, the signals related to the state of anesthesia including fractional anesthetic concentration, end-tidal carbon dioxide, fraction inspiration carbon dioxide, and minimum alveolar concentration are also adopted in this study. Using minimizing contrastive divergence, a continuous restricted Boltzmann machine is trained and then used to predict the depth of sedation. The experimental results showed that the proposed approach outperforms feed-forward neural network and modular neural network. Besides, it would be able to ease patient monitoring services by using biological systems and promote healthcare quality.

Design a bio-signal automatic measurement analysis and warning system for the long-term health care of severe disabled

This study designed a bio-signal automatic measurement analysis and warning system for the severe disabled in the long-term health care, that including a fuzzy threshold algorithm to adjust the threshold of peak detection for ECG and PPG signal that the accuracy of thirty experiment data are higher than 97% and a PTT-BP model to estimate the continue-blood pressure (BP) that is a cuff-off technology. Through the vital parameters (BP, heart rate variability (HRV), SPO2) by this system provides, the health care workers will be able to make the most appropriate treatment for patients, when the system sends alert notifications.

Using modular neural network to SSVEP-based BCI

A patient with amyotrophic lateral sclerosis is difficult to talk with other people and the cognitive function is generally spared for most people. Therefore, to develop a steady state visually evoked potential based brain computer interfaces can effectively help patients. To precisely represent the characteristics of frequency responses, three types of features estimated by fast Fourier transform, power cepstrum analysis, and canonical correlation analysis are adopted. To fuse these features, a modular neural network is applied find a decision. The experimental results demonstrated that the proposed approach outperform previous approaches.

The SSVEP-Based BCI Text Input System Using Entropy Encoding Algorithm

The so-called amyotrophic lateral sclerosis (ALS) or motor neuron disease (MND) is a neurodegenerative disease with various causes. It is characterized by muscle spasticity, rapidly progressive weakness due to muscle atrophy, and difficulty in speaking, swallowing, and breathing. The severe disabled always have a common problem that is about communication except physical malfunctions. The steady-state visually evoked potential based brain computer interfaces (BCI), which apply visual stimulus, are very suitable to play the role of communication interface for patients with neuromuscular impairments. In this study, the entropy encoding algorithm is proposed to encode the letters of multilevel selection interface for BCI text input systems. According to the appearance frequency of each letter, the entropy encoding algorithm is proposed to construct a variable-length tree for the letter arrangement of multilevel selection interface. Then, the Gaussian mixture models are applied to recognize electrical activity of the brain. According to the recognition results, the multilevel selection interface guides the subject to spell and type the words. The experimental results showed that the proposed approach outperforms the baseline system, which does not consider the appearance frequency of each letter. Hence, the proposed approach is able to ease text input interface for patients with neuromuscular impairments.