Abstract
In the nonmedical sputum monitoring system, a practical solution for phlegm stagnation care of patients was proposed. Through the camera, the video images of patients' laryngeal area were obtained in real time. After processing and analysis on these video frame images, the throat movement area was found out. A three-frame differential method was used to detect the throat moving targets. Anomalies were identified according to the information of moving targets and the proposed algorithm. Warning on the abnormal situation can help nursing personnel to deal with sputum blocking problem more effectively. To monitor the patients' situation in real time, this paper proposed a VDS algorithm, which extracted the speed characteristics of moving objects and combined with the DTW algorithm and SVM algorithm for sequence image classification. Phlegm stagnation symptoms of patients were identified timely for further medical care. In order to evaluate the effectiveness, our method was compared with the DTW, SVM, CTM, and HMM methods. The experimental results showed that this method had a higher recognition rate and was more practical in a nonmedical monitoring system.
Highlights
Phlegm stagnation, airway obstruction with phlegm, and other respiratory problems may occur during the care of older or terminal patients, resulting in serious complications such as hypoxia, asphyxia, pulmonary infection, and respiratory failure [1, 2]
To judge whether the patient has phlegm stagnation symptom, this thesis proposes a Velocity Distance Support (VDS) algorithm. It processes the velocity of the moving target with the dynamic time warping (DTW) algorithm and combines the classification of sequential images with the support vector machine (SVM) to identify the physical condition of the patient. e monitoring system sends the message back to the client in real time so that the caregiver can deal with problems promptly. e similarity distance between the feature vectors of input data and the prototype is calculated by DTW
It is a method based on nonparametric models. ese methods can be implemented and can automatically match action sequences and calculate the distance between two sequences as well, while keeping a higher recognition rate than general methods based on parametric models. ey can combine the similarity distance with velocity and establish a laryngeal action identification model based on the SVM classifier. e diagnosis of phlegm stagnation can be carried out through parameters learning of the original training data set and classification of phlegm stagnation status
Summary
Received 23 September 2019; Revised 4 December 2019; Accepted 19 December 2019; Published 24 January 2020. In the nonmedical sputum monitoring system, a practical solution for phlegm stagnation care of patients was proposed. Rough the camera, the video images of patients’ laryngeal area were obtained in real time. After processing and analysis on these video frame images, the throat movement area was found out. A three-frame differential method was used to detect the throat moving targets. Anomalies were identified according to the information of moving targets and the proposed algorithm. To monitor the patients’ situation in real time, this paper proposed a VDS algorithm, which extracted the speed characteristics of moving objects and combined with the DTW algorithm and SVM algorithm for sequence image classification. Phlegm stagnation symptoms of patients were identified timely for further medical care. E experimental results showed that this method had a higher recognition rate and was more practical in a nonmedical monitoring system In order to evaluate the effectiveness, our method was compared with the DTW, SVM, CTM, and HMM methods. e experimental results showed that this method had a higher recognition rate and was more practical in a nonmedical monitoring system
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
