Thermoplasticity Of Superfine Wool Powder And Its Blending With Polypropylene

With China's aging society,the problem of social pension service has become prominent.As the physical function of the elderly begins to age,many elderly people suffer from a variety of chronic diseases,so the physical health monitoring of the elderly plays an important role in the elderly care service.At present,there are some products for monitoring the health of the elderly,but there are some shortcomings in these products.Some offer only simple physiological monitoring services,with most measuring heart rate and blood pressure only.Moreover,these product anomaly analysis algorithms are too simplistic.They simply set a threshold for heart rate and blood pressure,and trigger an alarm when the measured data exceed this threshold.In addition,although there are a lot of researches on various abnormal analysis algorithms of physiological information,these researches are all aimed at improving the recognition accuracy and lack of corresponding researches on the recognition speed of the algorithm,which is also very important in the practical application process.Therefore,in view of the above problems,this paper does the following work:(1)Use ECG sensor,heart sound sensor and blood pressure sensor to collect three physiological signals of the elderly in real time,and use Beidou positioning module to collect the position information of the elderly in real time.Then,the collected information is transmitted to the coordinator through the ZigBee network by taking advantage of the ZigBee transmission speed and high security features,and the information is sent to the server through the network by the ZigBee to WiFi module of the coordinator.The server will receive the data for analysis and processing,and save to the database.The elderly family members can log in to the Web site to check the elderly person's physical condition through their account and password and mobile smart devices such as mobile phones and computers.(2)This paper aims to improve the speed of abnormal analysis algorithm of physiological information.The algorithm is designed for PCG heart sound signal and ECG ECG signal respectively.For PCG heart sound signals,this paper proposes to use HSMM to segment the heart sound signals,and then extract the eigenvalues.Finally,the eigenvalues are used as input vectors to train the DBN deep confidence network to obtain the DBN abnormal heart sound analysis model,and the abnormal heart sound analysis model is used to analyze the heart sound.For ECG ECG signal,this paper firstly decomposes the heart sound signal by using the binary spline four-layer wavelet transform,then uses the extreme value method to find the position of R wave,and then finds the position of other waves according to the position of R wave.According to the position information,the ECG waveform information is extracted as the input vector,and the ANFIS adaptive fuzzy neural system is trained to obtain the recognition model of the abnormal ECG signals by the adaptive fuzzy neural network,which is used to analyze the abnormal ECG signals.In this paper,the above algorithm and the current convolutional neural network CNN as the core algorithm were compared and tested.The experimental results show that the algorithm described in this paper has greatly improved the test speed under the condition of similar recognition accuracy.