Quantitative measurement of Parkinsonian gait from walking in monocular image sequences using a centroid tracking algorithm.

Parkinson's disease (PD) is a neurodegenerative disease of the central nervous system that results from the degeneration of dopaminergic neurons in the substantia nigra. Abnormal gait begins in the early stage and becomes severe as the disease progresses; therefore, the assessment of gait becomes an important issue in evaluating the progression of PD and the effectiveness of treatment. To provide a clinically useful gait assessment in environments with budget and space limitations, such as a small clinic or home, we propose and develop a portable method utilizing the monocular image sequences of walking to track and analyze a Parkinsonian gait pattern. In addition, a centroid tracking algorithm is developed and used here to enhance the method of quantifying kinematic gait parameters of PD in different states. Twelve healthy subjects and twelve mild patients with PD participate in this study. This method requires one digital video camera and subjects with two joint markers attached on the fibula head and the lateral malleolus of the leg. All subjects walk with a natural pace in front of a video camera during the trials. Results of our study demonstrate the stride length and walking velocity significantly decrease in PD without drug compared to PD with drug in both proposed method and simultaneous gait assessment performed by GAITRite(®) system. In gait initiation, step length and swing velocity also decrease in PD without drug compared to both PD with drug and controls. Our results showed high correlation in gait parameters between the two methods and prove the reliability of the proposed method. With the proposed method, quantitative measurement and analysis of Parkinsonian gait could be inexpensive to implement, portable within a small clinic or home, easy to administer, and simple to interpret. Although this study is assessed Parkinsonian gait, the proposed method has the potential to help clinicians and researchers assess the gait of patients with other neuromuscular diseases, such as traumatic brain injury and stroke patients.

Using K-Nearest Neighbor Classification to Diagnose Abnormal Lung Sounds.

A reported 30% of people worldwide have abnormal lung sounds, including crackles, rhonchi, and wheezes. To date, the traditional stethoscope remains the most popular tool used by physicians to diagnose such abnormal lung sounds, however, many problems arise with the use of a stethoscope, including the effects of environmental noise, the inability to record and store lung sounds for follow-up or tracking, and the physician's subjective diagnostic experience. This study has developed a digital stethoscope to help physicians overcome these problems when diagnosing abnormal lung sounds. In this digital system, mel-frequency cepstral coefficients (MFCCs) were used to extract the features of lung sounds, and then the K-means algorithm was used for feature clustering, to reduce the amount of data for computation. Finally, the K-nearest neighbor method was used to classify the lung sounds. The proposed system can also be used for home care: if the percentage of abnormal lung sound frames is > 30% of the whole test signal, the system can automatically warn the user to visit a physician for diagnosis. We also used bend sensors together with an amplification circuit, Bluetooth, and a microcontroller to implement a respiration detector. The respiratory signal extracted by the bend sensors can be transmitted to the computer via Bluetooth to calculate the respiratory cycle, for real-time assessment. If an abnormal status is detected, the device will warn the user automatically. Experimental results indicated that the error in respiratory cycles between measured and actual values was only 6.8%, illustrating the potential of our detector for home care applications.

Bidirectional and multi-user telerehabilitation system: clinical effect on balance, functional activity, and satisfaction in patients with chronic stroke living in long-term care facilities.

BACKGROUND: The application of internet technology for telerehabilitation in patients with stroke has developed rapidly. OBJECTIVE: The current study aimed to evaluate the effect of a bidirectional and multi-user telerehabilitation system on balance and satisfaction in patients with chronic stroke living in long-term care facilities (LTCFs). METHOD: This pilot study used a multi-site, blocked randomization design. Twenty-four participants from three LTCFs were recruited, and the participants were randomly assigned into the telerehabilitation (Tele) and conventional therapy (Conv) groups within each LTCF. Tele group received telerehabilitation but the Conv group received conventional therapy with two persons in each group for three sessions per week and for four weeks. The outcome measures included Berg Balance Scale (BBS), Barthel Index (BI), and the telerehabilitation satisfaction of the participants. SETTING: A telerehabilitation system included "therapist end" in a laboratory, and the "client end" in LTCFs. The conventional therapy was conducted in LTCFs. RESULTS: Training programs conducted for both the Tele and Conv groups showed significant effects within groups on the participant BBS as well as the total and self-care scores of BI. No significant difference between groups could be demonstrated. The satisfaction of participants between the Tele and the Conv groups also did not show significant difference. CONCLUSIONS: This pilot study indicated that the multi-user telerehabilitation program is feasible for improving the balance and functional activity similar to conventional therapy in patients with chronic stroke living in LTCFs.

Exquisite textiles sensors and wireless sensor network device for home health care.

In this study, we propose a wearing system with four sensors, ECG (electrocardiogram), three-axis accelerometer, temperature, and tight-switch, applied for remote monitoring system in home-care. The sensors ECG, measured with wearable electrodes made of the steel textile to generate the real-time heart-rate estimator, tight-switch, made of the steel textile to check whether wearing person dresses properly, accelerometer, and temperature parameters are received via the ZigBee receiver within an exquisite belt. Since the movable textile electrodes will cause of unfixed contacts when the wearing person is in motion, making the heart-rate estimation much a sophisticated work, the tight-switch sensor and FIR (Filter Impulse Response) filter technology are applied here to get the more satisfiable heart-rate. The other two bio-sensors can detect the whether fall-down or not and normal body-temperature of this wearing person. Moreover, the ZigBee device with small size, low-power consumption, and high-reliability characteristics is designed to transmit the detected bio-information from these four sensors. Therefore, the vital system embedded with the capability of real-time heart-rate estimation and transmission makes it highly suitable for applications of remote healthcare and wellness.

A novel design and evaluation of wearable digital sensor for monitoring posture.

In this study, we propose a novel design of the wearable digital sensor, embedded within a monitoring suit for posture monitoring. Our studies are going to solve wearable monitoring systems' drawbacks, include non-washable, uncomfortable, and high power -consumption due to complex signal processing. There are two digital sensor designs, dome shape type and clip shape type, knitted on clothes. The characteristics of these two digital sensor designs are easy implementation, small size, low power-consumption, and comfort. Our proposed system can catch up and monitor postures of the real-time information from the wearing person. Therefore, the monitoring system embedded with the capability of detecting real-time postures and transmission makes it highly suitable for applications of remote healthcare and wellness.