Jen- Chien

A Study of Heart Sound and Lung Sound Separation by Independent Component Analysis Technique

In the hospital, using percussion and auscultation are the most common ways for physical examination. Recently, in order to develop tele-medicine and home care system and to assist physician getting better auscultation results; electric stethoscope and computer analysis have become an inevitable trend. However, two important physical signals heart sound and lung sound recorded from chest overlap on spectrum chart. Therefore, in order to reduce human factor (ex. misplace or untrained of using) and minimize correlated effect in computer analysis; its necessary for separated heart sound and lung sound. Independent component analysis can divide these sounds efficiency. In this paper, we use two microphones to collect signals from left and right chest. We have successfully divide heart and lung sounds by fast ICA algorithm. Therefore, it can assist physician examine and also using on tele-medicine and home care by this way

Respiratory Wheeze Detection System

Respiratory sound is associated with many lung diseases. By observing respiratory sound symptoms, we can know more about lung conditions. In this research, we construct an efficient lung sound recording system according to CORSA, and develop a spectrogram process flow technique to object wheeze. It is a low cost and efficient system. In clinic test, we also can precisely objective wheeze up to about 89%

Electric compass aided global positioning system navigation for powered wheelchairs

Powered wheelchairs are an important mobility aid for the elderly and for persons with disability. According to World Health Organization statistics, most of the accidents were due to personal mistakes; if there is an auto-navigating system such as auxiliary, mistaken manipulation will decrease efficiency. This study attempted to improve the global positioning system (GPS) navigation of electric powered wheelchairs (EPWs) through the addition of an electric compass (EC) and tested the navigation of EPWs with EC-aided and non-EC-aided GPS navigation along a 25 m road. According to these tests, the use of the EC significantly reduces the errors in GPS navigation during movements such as go straight ahead, turn right and turn left. Therefore, the navigation reduced the error of the expected trajectories with the EC-aided navigation.

SECURITY BIOSIGNAL TRANSMISSION BASED ON FACE RECOGNITION FOR TELEMEDICINE

In telemedicine, an insecure and vulnerability medicine information system is important for nursing staff and patients. Relatively private information stolen by others still can be corrected. However, if attacked by hackers, mistakes in diagnosis can threaten the patients life. In order to simplify the procedures in the authentication of telemedicine and to emphasize security in the patients data, this paper proposes utilizing the symmetric key cryptography and the biometric authentication. We use a face eigenvector to insert the patients physiological signals and to combine symmetric key cryptography thus protecting the integrity of the patients data and improving the mode of operations.

Transform domain adaptive enhancement filter for evoked potential

This paper is to present the use of transform domain adaptive filter (TDADF) to process evoked potential (EP). The use of adaptive filter (ADF) in processing EP is effective than traditional averaging method. However to design an ADF with normalized LMS with good convergence performance is not an easy task. Thus, we proposed the TDADF method to improve the convergence performance of processing EP. Simulations were conducted to obtain the SNR of visual evoked potential. Moreover, collected data from somatosensory evoked potential was used in the testing. We observed that TDADF method has better performance than ADF with normalized LMS algorithm.

Estimation of evoked potentials using high order statistics-based adaptive filter

This paper is to present a high order statistics-based adaptive interference cancel filter (AIC-HOS) to process evoked potential (EP). In the conventional ensemble averaging method, experiments have to conduct repetitively to record the required data. In normalized LMS adaptive filter, inappropriate step size always causes deficiency. This AIC-HOS system has none of the above disadvantages. This system was experimented in somatosensory evoked potential corrupted with EEG. A gradient type algorithm is used in this AIC-HOS structure to regulate the SNR of EEG and EP. This method is also simulated with visual evoked potential and audio evoked potential. The results obtained are satisfactory and acceptable in clinical usage. The AIC-HOS is superior to normalized LMS using adaptive filter in that it converges easily. Moreover, it is not sensitive to selection of step size in stabilities in convergency.

An Effective Image Measurement in Brachial Flow-Mediated Dilation Response Analysis

Non-invasive cardiovascular measurements are used to evaluate cardiovascular diseases early and to cure early. By using various evaluation methods of cardiovascular features to diagnose cardiovascular disease. Flow-mediated dilation (FMD) evaluated by ultrasound offers a mechanism to characterize endothelial function and, therefore, may play a role in the diagnosis of cardiovascular diseases. Cardiovascular endothelial is intermedia between blood and cardiovascular muscle. It has important effect for keeping balance of the environment in vessel. Nitric oxide (NO) is the most important fact. Many cardiovascular diseases, like high cholesterol, high blood pressure, coronary heart disease, diabetes, smoking, is the cause of endothelial dysfunction. We design a series of images analysis methods to compute the change of cardiovascular radius in ultrasound images for evaluating endothelial function instead of measuring by-hand. We use B-mode ultrasound system to measure brachial cardiovascular radius. Then we capture the images by image capture card 10 images per second. We evaluate the average radius of brachial cardiovascular radius before we cut off blood flow. And we evaluate the maximum radius of brachial cardiovascular radius after we cut off blood flow and release it. Using the two radii we can compute the FMD value to evaluate endothelial function. First, we use Hough transform to detect possible center possible of vessel. Then we use edge-reserved filter to filtrate speckle noise and preserve edge. After filtrating noise, we utilize Laplacian of Gaussian to detect edge-points. Finally, we use gradient-based Hough transform to determine the center position, major axis, minor axis, and angle of evaluated ellipse. We use radius of the circle witch has equal area with the evaluated ellipse to be our final result. We measure the FMD value for 8 people (age from 23 to 26 years old). Comparing the result measured by our design system with by hand, the accuracy is 96.31%

Functional link network with genetic algorithm for evoked potentials

In this study, a functional link network with genetic algorithm is employed for extracting evoked potentials. Evoked potentials are time-varying signals typically buried in relatively large noises of electroencephalogram. Recently, to extract evoked potentials more effectively from noises, adaptive filtering techniques are widely employed for evoked potentials. In general, least-mean-square algorithm is used to adapt filter weights. However, it is well-known that the selection of step-sizes is a trade-off on the convergence rate and steady state performance. In practice, an inappropriate step-size always causes deficiency. Therefore, the proposed method employs genetic algorithm to improve this issue. Genetic algorithm is basically a kind of evolutionary strategies. The step-size candidates are regularly generated and evaluated, and the fittest candidate is selected for subsequent adaptation. Results show that the proposed method is insensitive to the selection of step sizes and reference inputs. It is applicable for extracting EP in different noise levels.

The phenomenon of breathing pattern of weaning for success and failure groups

Weaning the discontinuation of mechanical ventilator, it can be regarded as a stress process. It will trigger central neural feedback response to maintain the balance of our body and environments. This phenomenon is usually easily observed in breathing pattern. Weaning will caused a rhythmic change in breathing pattern. We collect data before and after weaning success and weaning failure in clinical environment. Statistical analysis methods are used to investigate this rhythm change. It also provides valuable information about respiratory system. In this paper, we showed that there is obviously difference in normalized standard deviation of after weaning data minus before weaning data between weaning success and weaning failure groups. The success groups also have lower value (bellow to zero) in after minus before weaning data than failure groups. In frequency domain, we find there is obviously difference in weaning success and weaning failure groups in total power of inspiratory time spectrum (p value = 0.028). The result obtains in the time and frequency domain is the same. However, the third frequency peak power amplitude of the spectrum has the same result (p value = 0.021). This phenomenon in breathing pattern may be used as a good weaning index to predict weaning success and failure.

Based digital signal processor to develop the M3S novel kernel system

The multiple masters multiple slave (M3S) is an intelligent protocol. It provides the disable a concrete integral control for his movement, working, environment control and communication. This is an integrated real time control capability protocol. It is a plug and play device interface. Once plug-in, the new device with integrate and communicate with existing devices in use. Our proposal is aim at this purpose. We intend to design and develop a M3S protocol that meets the requirement lay down in the M3S working group. Integrating different types of tools will absolutely bring lots of comforts to the disable. We set up the system using equipments purchase from the market, tested the system and ready it to be tested by other subgroups.