A Wearable System for Cervical Spondylosis Prevention Based on Artificial Intelligence / 中国医疗器械杂志

Accompanied by changes in modern work and lifestyle, the incidence of cervical spondylosis has increased year by year. In view of the fact long-term fixed posture of the head and neck is one of the main causes of cervical spondylosis, a set of wearable cervical spondylosis prevention system is developed. The system comprises a head and neck movement collection module based on the acceleration sensor and a head and neck motion recognition module based on artificial intelligence. Experimental results showed that the system can accurately identify long-term posture of the head and neck, and guide users to complete effective exercise therapy under the supervision of motion recognition module. Using this system can be beneficial for the prevention of cervical spondylosis.

Proposal of conditional random inter-stimulus interval method for unconstrained enclosure based GPIAS measurement systems

Gap prepulse inhibition of acoustic startle (GPIAS) method has been used effectively for the objective assessment of tinnitus in animals. Among two types of enclosures for the GPIAS, the unconstrained type carries less risk of animal death due to the absence of binding stress in the enclosure, and lack of need for alteration to animal size variation as it grows. However, animals' voluntary movements, which have no relation to the startles evoked by acoustic stimuli, are problematic, as they cannot be excluded in the case of the unconstrained enclosure based GPIAS measurement system. In order to discount voluntary movements which are not associated with external acoustic stimuli, we propose the conditional random interstimulus interval (CR ISI) method for unconstrained enclosure based GPIAS measurement. With the proposed ISI method, the unconstrained enclosure based acoustic startle response measurement system has been implemented in this paper. As a result, the effectiveness of the proposed CR ISI method has been verified and compared with those of conventional ISI methods through animal experiments using SD-rats. The experimental results showed that abnormal startle responses and invalid GPIAS values caused by motion were prevented when our proposed CR ISI method was applied to our implemented system. It was also verified that our proposed CR ISI method is advantageous in reducing the total experimental time for acquiring normal startle responses and valid GPIAS values, compared to conventional ISI methods, since our proposed CR ISI can begin the acoustic stimulation only when the animal gets stable and motionless.

Unconstrained detection of ballistocardiogram and heart rate based on vibration acceleration / 生物医学工程学杂志

The requirement for unconstrained monitoring of heartbeat during sleep is increasing, but the current detection devices can not meet the requirements of convenience and accuracy. This study designed an unconstrained ballistocardiogram (BCG) detection system using acceleration sensor and developed a heart rate extraction algorithm. BCG is a directional signal which is stronger and less affected by respiratory movements along spine direction than in other directions. In order to measure the BCG signal along spine direction during sleep, a 3-axis acceleration sensor was fixed on the bed to collect the vibration signals caused by heartbeat. An approximate frequency range was firstly assumed by frequency analysis to the BCG signals and segmental filtering was conducted to the original vibration signals within the frequency range. Secondly, to identify the true BCG waveform, the accurate frequency band was obtained by comparison with the theoretical waveform. The J waves were detected by BCG energy waveform and an adaptive threshold method was proposed to extract heart rates by using the information of both amplitude and period. The accuracy and robustness of the BCG detection system proposed and the algorithm developed in this study were confirmed by comparison with electrocardiogram (ECG). The test results of 30 subjects showed a high average accuracy of 99.21% to demonstrate the feasibility of the unconstrained BCG detection method based on vibration acceleration.