CN114501331A - Self-adaptive physiological monitoring and intelligent scheduling positioning system and method - Google Patents

Abstract

The invention relates to a self-adaptive physiological monitoring and intelligent scheduling positioning system and a method, wherein the system comprises a physiological data monitoring module and a rescue module; the physiological data monitoring module collects physiological data of a human body by using a somatosensory network, divides the priority level of the data by using an RM-MAC improved protocol, and performs self-adaptive transmission by using an RS algorithm; the rescue module is used for assisting medical workers to efficiently locate patients by utilizing a multi-source heterogeneous indoor sensing and positioning and sensing node advanced scheduling technology when physiological data of users are abnormal, so that the patients are rescued in time and energy consumption of an indoor heterogeneous sensing and positioning network is saved. According to the invention, a deep learning target track prediction technology is applied to an indoor rescue module, high-performance scheduling is carried out on the position tracking node in advance through track prediction, the perception tracking precision is ensured, the network energy consumption is reduced, and when the system monitors abnormal physiological data which possibly endangers the life of a patient, the rescue module can implement effective and rapid position rescue to avoid risks.

Description

An adaptive physiological monitoring and intelligent dispatching positioning system and method

technical field

The invention relates to the technical field of physiological monitoring and pedestrian trajectory prediction, in particular to an adaptive physiological monitoring and intelligent dispatching and positioning system and method.

Background technique

With the development of wireless wearable biosensors, more heterogeneous wireless wearable biosensors are used in combination to identify and monitor the complex physiological state of the human body, and these combinations are called low-power and low-cost wireless body area networks ( WBANs). WBSNs have multiple application areas such as healthcare, military, entertainment, and sports. At present, the application field of WBANs is mainly health monitoring. The increasing demand for high-performance WBANs has led to the birth of IEEE 802.15.6, a communication standard specially designed for WBANs. Scholars have designed many algorithms and communication protocols with advanced performance based on the IEEE802.15.6 standard to further improve the network lifetime (NL) and quality of service (QoS) of WBAN. Although most scholars regard data between normal and highly abnormal as a separate category, the scale of such data is large, and traditional routing protocols are prone to loss of more important and valuable data. In addition, WBAN has developed rapidly in medical monitoring and diagnosis, but most scholars have not considered taking corresponding emergency rescue measures when an emergency is detected. However, corresponding emergency rescue measures are necessary. Therefore, we innovatively use wireless sensor network (WSN) indoor positioning technology and deep learning pedestrian trajectory prediction technology to design an indoor rescue module (IRM). However, the indoor positioning scheme based on WSN also has problems such as limited energy and difficult replenishment. The most common method to prolong the life of WSN network is sleep scheduling, which makes some redundant nodes enter the sleep state under the condition of ensuring the coverage of the monitored area. , and then update the node state through the wake-up algorithm. However, this method may reduce the accuracy of location tracking. It is very difficult to carry out rescue work with insufficient positioning accuracy, and it is even possible to miss the best rescue time for the patient.

Therefore, how to provide a high-efficiency, high-intelligence adaptive physiological monitoring and intelligent dispatching and positioning system APMISPS, which can provide patients with more timely and higher life support in emergencies, and provide medical staff with more accurate rescue information, is the Problems to be solved by those skilled in the art.

SUMMARY OF THE INVENTION

In order to solve the technical problems existing in the prior art, the present invention provides an adaptive physiological monitoring and intelligent dispatching and positioning system and method, which applies the deep learning target trajectory prediction technology to the indoor rescue module, and conducts position tracking nodes in advance through trajectory prediction. High-performance scheduling ensures the accuracy of perception and tracking while reducing network energy consumption. When the system detects abnormal physiological data that may endanger the patient's life, the rescue module can implement effective and fast location rescue to avoid risks.

The system of the present invention adopts the following technical solutions to realize: an adaptive physiological monitoring and intelligent dispatching and positioning system, including a physiological data monitoring module and a rescue module, wherein:

The physiological data monitoring module collects the physiological data of the human body by using the somatosensory network, then divides the priority level of the data through the RM-MAC improved protocol, and finally performs adaptive transmission through the RS algorithm;

The rescue module is used to use multi-source heterogeneous indoor sensing positioning and sensing node advance scheduling technology to assist medical staff to efficiently locate patients when the user's physiological data is abnormal, so that patients can receive timely rescue and save the energy consumption of the indoor heterogeneous sensing and positioning network. .

The method of the present invention is realized by the following technical solutions: a method for self-adaptive physiological monitoring and intelligent dispatching and positioning, comprising the following steps:

S1. Use the somatosensory network to collect the physiological data of the human body. If the data type of the collected data is 11, enter the rescue module, the somatosensory network enters a continuous sensing state, and assigns an independent communication channel to the user; otherwise, go to step S2;

S2, if the data type of the collected data is 10, directly transmit the collected data to the sink node; otherwise, go to step S3;

S3. If the data type of the collected data is 01, the priority level of the monitoring data is preliminarily determined, and the somatosensory network sends a transmission request to the sink node to obtain the information of all adjacent nodes. The sink node uses the RS algorithm to calculate the RS of its adjacent nodes. value, and then select the node with the largest RS value as its forwarding relay node, and the relay node transmits the data to the sink node;

S4. If the sink node checks that its remaining energy is lower than the set threshold, it ends the work, otherwise it enters the next sensing cycle.

Compared with the prior art, the present invention has the following advantages and beneficial effects:

1. The present invention incorporates the emergency rescue function based on indoor positioning into the traditional physiological monitoring system by using the RM-MAC improved protocol, and selects the appropriate relay and forwarding according to the importance of the physiological data by using the RS algorithm, thereby ensuring more efficient operation. Priority transmission of important monitoring data.

2. The present invention applies the deep learning target trajectory prediction technology to the indoor rescue module, and performs high-performance scheduling of location tracking nodes in advance through trajectory prediction, which ensures the accuracy of perception and tracking and reduces network energy consumption. When there is abnormal physiological data of life, the rescue module can implement effective and fast location rescue to avoid risks.

Description of drawings

Fig. 1 is the system block diagram of the present invention;

Fig. 2 is the RM-MAC improvement protocol frame structure diagram of the present invention;

3 is a schematic diagram of node pre-scheduling based on trajectory prediction of the present invention;

Fig. 4 is the frame schematic diagram of IRM module;

Figure 5(a) is a schematic diagram of the network lifetime comparison of the protocol algorithm;

Figure 5(b) is a schematic diagram of the comparison of the data transmission delay of the protocol algorithm;

Figure 5(c) is a schematic diagram of the network throughput comparison of the protocol algorithm;

Figure 6(a) is a schematic diagram of the network lifetime performance comparison of the priority-based RS algorithm;

FIG. 6(b) is a schematic diagram showing the comparison of the data transmission delay performance of the RS algorithm based on the priority;

Fig. 6(c) is a schematic diagram showing the comparison of throughput performance of RS algorithm data network based on priority;

Figure 7(a) is a schematic diagram of the network lifetime comparison of the protocol algorithm under different node densities;

Figure 7(b) is a schematic diagram of the comparison of the data transmission delay of the protocol algorithm under different node densities;

Figure 7(c) is a schematic diagram of the throughput comparison of the protocol algorithm under different node densities;

Figure 8(a) is a schematic diagram of the predicted scheduling situation of the sensor nodes in the ETH data set;

Figure 8(b) is a schematic diagram of the predicted scheduling situation of the sensor nodes in the HOTEL dataset;

Figure 8(c) is a schematic diagram of the predicted scheduling situation of the sensor nodes in the ZARA1 dataset;

Figure 8(d) is a schematic diagram of the predicted scheduling situation of sensor nodes in the ZARA2 dataset;

Figure 8(e) is a schematic diagram of the predicted scheduling situation of the sensor nodes in the UNIV dataset;

Figure 9 is a schematic diagram of the summary of the advance scheduling performance of wireless sensor nodes;

FIG. 10 is a flow chart of the method of the present invention.

Detailed ways

The present invention will be described in further detail below with reference to the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

Example

As shown in FIG. 1 , an adaptive physiological monitoring and intelligent dispatching and positioning system in this embodiment includes a physiological data monitoring module and a rescue module, wherein:

The physiological data monitoring module collects the physiological data of the human body by using the somatosensory network, then divides the priority level of the data through the RM-MAC improved protocol, and finally performs adaptive transmission through the RS algorithm;

The rescue module is used when the user's physiological data is abnormal or even life-threatening energy consumption.

Specifically, in this embodiment, the RM-MAC improved protocol is an improved protocol based on the RM-MAC protocol. By adding rescue type data packets to the superframe structure of the MAC protocol, the indoor positioning rescue function is integrated into the physiological function. in the monitoring system;

The RS algorithm is a relay node selection algorithm specially designed for the improved RM-MAC protocol. The algorithm is used to adaptively select an appropriate data forwarding relay node according to the priority level of the data.

The sensing node advance scheduling technology uses the existing deep learning pedestrian trajectory prediction technology to predict the trajectory of pedestrians, and then uses the predicted trajectory combined with the adaptive scheduling radius ACR to schedule the sensing nodes in advance;

The adaptive scheduling radius ACR is the sum of the size of the confidence interval obtained by analyzing the error between the predicted trajectory and the real trajectory through the probability analysis technology and the minimum distance required to realize the coordinate positioning of the predicted trajectory;

All technologies and algorithms involved in the physiological data monitoring module and the rescue module interact and operate in physiological monitoring.

In this embodiment, the physiological data monitoring module is composed of WBANs composed of a variety of wearable wireless biosensors, an improved RM-MAC protocol and an RS algorithm.

Research shows that the MAC protocol plays an important role in improving the reliability and energy efficiency of network information transmission. A MAC frame consists of a frame header, a frame body and a frame check sequence FCS. The MAC frame header consists of four fields, the first field is the control field, which consists of four octets. Modified-MAC (M-MAC) is an improved version of the MAC protocol. A data type field is added to the MAC frame header, while the length of the frame header remains unchanged. The data types of RM-MAC are expanded into four categories, as shown in Figure 2, namely normal data ND, high normal data HD, critical data CD and rescue data RD, and the priority of HD packets is further refined to reduce high value Data loss rate. Data with different priority levels will use different transmission methods. RD data is transmitted through independent channels, CD data is directly transmitted to the sink node, HD data is transmitted in multi-hop mode, and ND data is not transmitted. Specifically, the expression and transmission methods of data are shown in Table 1:

Table 1

type of data binary representation sending method normal 00 Do not send abnormal 01 Use RS serious 10 send directly rescue 11 independent channel

However, there is still a deficiency in classifying the data for transmission, and the more important HD packets in multi-hop transmission may be discarded during transmission due to exceeding the validity period. In many studies, the data priority is not clearly marked, and the importance of the same type of data packets is also different. It is more beneficial to ensure the transmission of highly important data (HD data with high abnormality) for disease prevention and diagnosis. Furthermore, system lifetime and monitoring performance are two conflicting factors. Reducing energy consumption affects monitoring performance, while ensuring high monitoring performance requires more energy consumption. The RS algorithm can ensure the transmission of more important data according to the actual situation, balance the system life and monitoring performance, and improve the intelligence of the system's physiological monitoring. Specifically, the RS algorithm is defined as follows:

Among them, E _i is the remaining energy of the relay node, _Li is the real-time load of the relay node, α is a constant factor, k is the priority of similar data, and D _i is the real-time transmission delay of the relay node.

As shown in FIG. 4 , in this embodiment, the rescue module is composed of a WSN indoor positioning and tracking module, a pedestrian trajectory prediction network module and an adaptive scheduling radius ACR calculation module. The WSN indoor positioning and tracking module collects a trajectory of the target, and then inputs the trained pedestrian trajectory prediction network module, and uses the adaptive scheduling radius ACR calculation module to schedule the surrounding nodes in advance according to the predicted trajectory.

The indoor positioning and tracking technology of WSN has developed quite maturely, so the focus of rescue module research is not the tracking scheme, but the scheduling method of tracking nodes. In the rescue module, the sparse graph convolutional network SGCN is used as the network framework for pedestrian trajectory prediction. Different from the existing vision-based pedestrian trajectory prediction networks, the prediction network of the rescue module can take the trajectories collected by wireless sensor nodes as input. Compared with vision-based methods, this method will be more global.

则这种预调度是成功的，半径比是与自适应调度半径ACR的比率。具体地，自适应调度半径ACR计算的定义如下：During the trajectory prediction process, the error will increase as the prediction length increases. The predicted trajectory output by the sparse graph convolutional network SGCN is sent to the error analysis module to obtain the size of the error confidence interval where each predicted coordinate is located, so that the adaptive scheduling radius ACR calculation module can adaptively adjust the node pre-scheduling according to the prediction step size. scope. The pre-scheduling range is to take the predicted coordinates as the center of the circle, and activate all dormant nodes within the adaptive scheduling radius ACR, and the set of these nodes is called the pre-scheduling set PS. The actual coordinates of the pedestrian also correspond to a set of nodes to be scheduled, and the set of these nodes is called the actual scheduling set AS. In order to more clearly show the performance of the scheduling method based on ACR nodes, by defining two indicators, one is the scheduling accuracy SA, and the other is the radius ratio RR. The scheduling accuracy SA is the ratio between the number N of successful scheduling and the total number of scheduling TN, when

Then this pre-scheduling is successful and the radius ratio is the ratio to the adaptive scheduling radius ACR. Specifically, the definition of the adaptive scheduling radius ACR calculation is as follows:

是置信区间大小求解函，即计算置信区间的上下限的差值，显著水平α＝0.05；D_min是成功定位预测坐标的最短距离。IRM采用经典的三点定位算法，所以D_min＝max(dis(N[n₁,n₂,n₃]))，如图3所示。上式中N是成功定位预测坐标所需的调度节点集，函数dis为计算预测坐标与节点之间的距离。where set is the set of errors between the actual coordinates and the predicted coordinates, sort is the sorting function,

is the confidence interval size solution function, that is, the difference between the upper and lower limits of the confidence interval is calculated, and the significant level α=0.05; D _min is the shortest distance to successfully locate the predicted coordinates. The IRM adopts the classical three-point positioning algorithm, so D _min =max(dis(N[n ₁ ,n ₂ ,n ₃ ])), as shown in FIG. 3 . In the above formula, N is the set of scheduling nodes required to successfully locate the predicted coordinates, and the function dis is to calculate the distance between the predicted coordinates and the nodes.

The experiment of the present invention is divided into two parts: the physiological monitoring data processing experiment and the wireless sensor node scheduling experiment. The physiological monitoring data processing experiment is mainly to compare the performance of the communication protocol, and the wireless sensor node scheduling experiment is mainly to the scheduling effect of the node. to evaluate.

1. Physiological monitoring data processing;

The comprehensive performance of LBEE, WEQ, SIMPLE and RS in the most energy-saving mode is compared. As shown in Fig. 5(a), the RS and LBEE algorithms have the longest network lifetime, and the WEQ algorithm has the shortest. This is because the WEQ algorithm tends to select nodes that are closer to the sink node to forward data, resulting in the rapid exhaustion and death of these nodes' energy. As shown in Figure 5(b), the transmission delays of RS, LBEE and WEQ algorithms are not much different, but the data transmission delay of SIMPLE algorithm is much higher than the other three algorithms, because SIMPLE algorithm does not Consider the forwarding delay of the node. As shown in Figure 5(c), the RS algorithm has the highest throughput, and the throughput of the RS and LBEE algorithms is much higher than that of the WEQ and SIMPLE algorithms. Among all the comparison algorithms, the RS algorithm has the highest comprehensive performance.

Data transmission delay and throughput are important parameters of QoS, as shown in Fig. 6, the effect of RS performance and data response of different priorities (k). As shown in Figure 6(a), when a lower transmission delay is provided for data with a larger value of k, the energy of the network is concentratedly lost, resulting in a 28.33% decrease in network lifetime. However, Fig. 6(b) and Fig. 6(c) show that as the network lifetime decreases, the data transmission delay decreases by 30.77% and the throughput increases by 14.94%. The growth rates of data transfer latency and throughput are the highest stages, reaching 26.25% and 15.85%, respectively.

Network structure compatibility is also an important criterion to consider the performance of network operation. Figure 7 shows the performance of RS, LBEE, WEQ and SIMPLE algorithms under different node densities. As shown in Figure 7(a), despite the increase in network node density, the RS and LBEE algorithms maintain the highest and most stable network lifetime, followed by the SIMPLE algorithm, while the WEQ algorithm has the shortest network lifetime. As shown in Figure 7(b), under different node densities, the transmission delay of SIMPLE is the highest, the change of data transmission delay of WEQ is relatively stable and kept at a low level, while the data transmission delay of RS and LBEE algorithms It drops sharply as node density increases. When X=30, the delay of the RS algorithm is the lowest. As shown in Fig. 7(c), the throughputs of WEQ and SIMPLE algorithms remain stable, while those of RS and LBEE algorithms increase with increasing node density. Among them, RS has the highest growth rate. The analysis of Fig. 7(a), (b) and (c) shows that the RS algorithm maintains a stable network lifetime, reduces the transmission delay by about 60%, and increases the network throughput by 640% as the network node density increases. %. It is more flexible than the LBEE algorithm because the packet can adaptively choose a more suitable sending path. In addition, the RS algorithm is more suitable to be applied to the network with high node density, which is fully in line with the trend of network complexity and high performance of WBANs. Specifically, the detailed performance comparison of the physiological monitoring module comparison algorithm is shown in Table 2:

Table 2

2. Wireless sensor node scheduling experiment;

To verify the effectiveness of the proposed method, two public pedestrian trajectory datasets are first used to train SCCN networks, namely ETH and UCY, which are the most widely used trajectory benchmarks. We ignore the actual environment at the time of ETH and UCY acquisition, and place these trajectories on an unobstructed plane space on which wireless sensor nodes are evenly distributed. As shown in Fig. 8(a), Fig. 8(b), Fig. 8(c), Fig. 8(d), and Fig. (e), the predicted scheduling of sensor nodes of five different data sets are evenly distributed in the figure The solid dots of , represent the sensing nodes. Except for the range covered by the circle and the node for forwarding data is active, other nodes are in a dormant state, and other nodes are working normally. In addition, the input trajectory used for trajectory prediction in the figure is also ignored, and the range covered by the small circle represents the scheduling range in the ideal state. The range covered by the small circle in the figure represents the minimum node coverage required to locate the real coordinates, and the range covered by the large circle represents the coverage of the pre-scheduled nodes. The error of trajectory prediction will accumulate as the length of the predicted trajectory increases, so the scope of advance scheduling will also expand. The advance scheduling range of sensor nodes is related to the prediction quality of the target trajectory. The smaller the error of the predicted trajectory, the smaller the advance scheduling range, and the higher the energy efficiency of the network. The pre-scheduling results of the five datasets show that even if the trajectory prediction accuracy is not high enough, the adaptive confidence scheduling radius can better achieve the pre-scheduling of nodes. In the figure, the pre-scheduling effect of the ETH and ZARA1 trajectory segments is the best, and the pre-scheduling effect of ZARA2 is slightly insufficient, but according to the coverage of the pre-scheduling nodes, it can be judged that the pre-scheduling can still achieve the positioning of the real coordinates. Furthermore, the scope of the pre-scheduling is related to the density of the monitored spatial sensing nodes. Figure 9 shows the SA and RR of the five datasets ETH, HOTEL, NUIV, ZARA1, and ZARA2. The SA values of the five datasets are all over 90% and are relatively stable, but the RR values are not high, between 0.4 and 0.6, which is obviously related to the quality of trajectory prediction. Therefore, in order to achieve more accurate sensor node pre-scheduling, improving the accuracy and stability of trajectory prediction is a key breakthrough.

Based on the same inventor's conception, a method for adaptive physiological monitoring and intelligent scheduling and positioning in this embodiment includes the following steps:

S1. Use the somatosensory network to collect the physiological data of the human body. If the data type of the collected data is 11, enter the rescue module, the somatosensory network enters a continuous sensing state, and assigns an independent communication channel to the user; otherwise, go to step S2;

S2, if the data type of the collected data is 10, directly transmit the collected data to the sink node; otherwise, go to step S3;

S3. If the data type of the collected data is 01, make a preliminary judgment on the priority level of the monitoring data. The priority level is arranged from high to low as 11>10>01>00, and the somatosensory network sends a transmission request to the sink node to obtain all adjacent nodes. Node information, the sink node uses the RS algorithm to calculate the RS value of its adjacent nodes, and then selects the node with the largest RS value as its forwarding relay node, and the relay node transmits the data to the sink node;

S4. If the sink node checks that its remaining energy is lower than the set threshold, that is, 5% of the total energy, the work ends, otherwise it enters the next sensing cycle.

The above-mentioned embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited by the above-mentioned embodiments, and any other changes, modifications, substitutions, combinations, The simplification should be equivalent replacement manners, which are all included in the protection scope of the present invention.

Claims (10)

1. an adaptive physiological monitoring and intelligent dispatch positioning system, is characterized in that, comprises physiological data monitoring module and rescue module, wherein: The physiological data monitoring module collects the physiological data of the human body by using the somatosensory network, then divides the priority level of the data through the RM-MAC improved protocol, and finally performs adaptive transmission through the RS algorithm; The rescue module is used to use multi-source heterogeneous indoor sensing positioning and sensing node advance scheduling technology to assist medical staff to efficiently locate patients when the user's physiological data is abnormal, so that patients can be rescued in time and save the energy consumption of the indoor heterogeneous sensing and positioning network. . 2. a kind of self-adaptive physiological monitoring and intelligent dispatching positioning system according to claim 1, is characterized in that, by adding rescue type data packet in the superframe structure of MAC agreement, RM-MAC improved protocol, by indoor positioning rescue function. Integrate into the physiological monitoring system; The RS algorithm is a relay node selection algorithm designed for the RM-MAC improved protocol. The algorithm is used to adaptively select an appropriate data forwarding relay node according to the priority level of the data. 3. An adaptive physiological monitoring and intelligent dispatching and positioning system according to claim 2, wherein the sensing node advance dispatching technology is to use the deep learning pedestrian trajectory prediction technology to predict the trajectory of the pedestrian, and then use the predicted trajectory to predict the trajectory of the pedestrian. Combined with the adaptive scheduling radius ACR, the sensor nodes are scheduled in advance; The adaptive scheduling radius ACR is the sum of the size of the confidence interval obtained by analyzing the error between the predicted trajectory and the real trajectory through the probability analysis technology and the minimum distance required to realize the coordinate positioning of the predicted trajectory; All technologies and algorithms in the physiological data monitoring module and the rescue module conduct information exchange and operation in the physiological monitoring. 4. A kind of adaptive physiological monitoring and intelligent dispatching positioning system according to claim 3, is characterized in that, the physiological data monitoring module is made up of a variety of wearable wireless biosensors through WBANs, RM-MAC improved protocol and RS algorithm composition. 5. a kind of self-adaptive physiological monitoring and intelligent scheduling positioning system according to claim 2, is characterized in that, the frame header of RM-MAC improved protocol adds data type field, and this field is extended into four types, including normal data ND, high normal data HD, key data CD and rescue data RD; among them, normal data ND is not sent, high normal data HD uses RS algorithm to select relay nodes for forwarding, critical data CD is directly sent to sink node, rescue data RD uses independent channel send. 6. a kind of self-adaptive physiological monitoring and intelligent dispatch positioning system according to claim 2, is characterized in that, the definition of RS algorithm is as follows:

Among them, E _i is the remaining energy of the relay node, _Li is the real-time load of the relay node, α is a constant factor, k is the priority of similar data, and D _i is the real-time transmission delay of the relay node. 7. A kind of self-adaptive physiological monitoring and intelligent dispatching and positioning system according to claim 3, is characterized in that, rescue module is made up of WSN indoor positioning and tracking module, pedestrian trajectory prediction network module and self-adaptive dispatch radius ACR calculation module; The WSN indoor positioning and tracking module collects a trajectory of the target, and then inputs the trained pedestrian trajectory prediction network module, and uses the adaptive scheduling radius ACR calculation module to schedule the surrounding nodes in advance according to the predicted trajectory. 8. A kind of self-adaptive physiological monitoring and intelligent dispatching and positioning system according to claim 7, is characterized in that, rescue module, by citing sparse graph convolutional network SGCN as the network framework of pedestrian trajectory prediction; The network framework of pedestrian trajectory prediction The trajectories collected by the wireless sensor nodes are used as input. 9. a kind of adaptive physiological monitoring and intelligent dispatch positioning system according to claim 3, is characterized in that, the definition of self-adaptive dispatch radius ACR calculation is as follows:

where set[] is the set of errors between the actual coordinates and the predicted coordinates, sort() is the sorting function,

is the confidence interval size solution function, D _min is the shortest distance to successfully locate the predicted coordinates; in, D _min =max(dis(N[n ₁ ,n ₂ ,n ₃ ])) Among them, N[] is the set of scheduling nodes required to successfully locate the predicted coordinates, and the function dis() calculates the distance between the predicted coordinates and the nodes. 10. A method for self-adaptive physiological monitoring and intelligent scheduling and positioning, comprising the following steps: S1. Use the somatosensory network to collect the physiological data of the human body. If the data type of the collected data is 11, enter the rescue module, the somatosensory network enters a continuous sensing state, and assigns an independent communication channel to the user; otherwise, go to step S2; S2, if the data type of the collected data is 10, directly transmit the collected data to the sink node; otherwise, go to step S3; S3. If the data type of the collected data is 01, the priority level of the monitoring data is preliminarily determined, and the somatosensory network sends a transmission request to the sink node to obtain the information of all adjacent nodes. The sink node uses the RS algorithm to calculate the RS of its adjacent nodes. value, and then select the node with the largest RS value as its forwarding relay node, and the relay node transmits the data to the sink node; S4. If the sink node checks that its remaining energy is lower than the set threshold, it ends the work, otherwise it enters the next sensing cycle.

Images