CN211834368U - Athlete fatigue detection system - Google Patents

Abstract

The embodiment of the utility model discloses a sportsman's fatigue detection system, including first treater, the first treater is connected with recording element, acceleration sensor, locating element, heart rate detecting element, fall detecting element and human lack of water degree detecting element respectively; the recording element, the acceleration sensor, the positioning element, the heart rate detection element and the human body water shortage degree detection element are respectively connected with the first processor through storage elements; therefore, by additionally arranging the storage element, the problems of errors or inaccuracy caused by continuous data transmission of the recording element, the acceleration sensor, the positioning element, the heart rate detection element and the human body water shortage degree detection element to the first processor are solved, and a coach can more accurately know the state of an athlete during training.

Description

Athlete fatigue detection system

Technical Field

The utility model relates to a detecting system especially relates to an athlete fatigue detecting system.

Background

The training state inspection of athletes is always a subject studied in related fields, the accurate mastering of training fatigue of athletes is very beneficial to next training arrangement, the current evaluation of athletes mainly comprises step number detection, track detection and experience judgment, although all the evaluation means can obtain accurate evaluation results, the defects still exist, here, the step number detection and the track detection only obtain single data to infer the motion state, the obtained results are often objective, and misjudgment can be caused under special conditions (such as continuous data transmission) to obtain wrong prediction results. The empirical judgment depends on subjective observation of people, and an unobtrusive conclusion can be obtained more easily, so that the three methods obviously cannot meet the actual requirements.

SUMMERY OF THE UTILITY MODEL

For solving above technical problem, the embodiment of the utility model provides a sportsman's tiredness detecting system carries out more accurate collection through the data to each state of sportsman's health when the training to make the tiredness condition when coach can obtain the sportsman training comparatively accurately.

In order to achieve the above purpose, the embodiment of the present invention provides a technical solution that: the embodiment of the utility model provides a sportsman's fatigue detection system, including first treater, the first treater is connected with recording element, acceleration sensor, locating element, heart rate detecting element, fall detecting element and human lack of water degree detecting element respectively;

the recording element, the acceleration sensor, the positioning element, the heart rate detection element and the human body water shortage degree detection element are respectively connected with the first processor through a storage element.

The embodiment of the utility model provides an in, first treater pass through transmission element respectively with the recording component acceleration sensor the positioning element heart rate detecting element fall detecting element with human lack of water degree detecting element connects.

In an embodiment of the present invention, the recording element and the storage element on the acceleration sensor are further connected to a second processor, and the recording element and the acceleration sensor are connected to the first processor through the second processor.

In an embodiment of the invention, the first processor is further connected to a display element and a feedback element.

In an embodiment of the present invention, the first processor includes a convolutional neural network module, a long-short term memory model module, a weighted calculation module and an output module, the convolutional neural network module and the long-short term memory model module are all connected to the weighted calculation module, the weighted calculation module and the output module are connected.

In the embodiment of the present invention, the first processor is further connected to the step number detection module.

The embodiment of the utility model provides an in, the recording component sets up in first wearing equipment, acceleration sensor with rhythm of the heart detecting element sets up in second wearing equipment, the detecting element that tumbles sets up in third wearing equipment, positioning element sets up in fourth wearing equipment, human lack of water degree detecting element sets up in fifth wearing equipment.

The embodiment of the utility model provides a sportsman's fatigue detection system, the system includes first treater, the first treater is connected with recording element, acceleration sensor, locating element, heart rate detecting element, fall detecting element and human lack of water degree detecting element respectively; the recording element, the acceleration sensor, the positioning element, the heart rate detection element and the human body water shortage degree detection element are respectively connected with the first processor through storage elements; thus, when the device is used, the recording element is worn on the chest, the acceleration sensor and the heart rate detection element are worn on the wrist, the fall detection element is worn on the knee pad, the first processor and the positioning element are worn on the body of the athlete, so that the data of the body of the athlete during training can be acquired and collected, meanwhile, the recording element, the acceleration sensor, the positioning element, the heart rate detection element, the fall detection element and the human body water shortage degree detection element are connected with the first processor in parallel, so that the elements in the device are relatively independent, the mutual influence of the elements during use is avoided, and meanwhile, the recording element, the acceleration sensor, the positioning element, the water shortage degree detection element and the first processor are additionally arranged, so that the recording element, the acceleration sensor, the positioning element and the heart rate detection element are avoided, The heart rate detection element and the human body water shortage degree detection element continuously transmit data to the first processor, and errors or inaccuracy can occur.

Drawings

Fig. 1 is a schematic block diagram of a detection system according to an embodiment of the present invention;

fig. 2 is a block diagram of a first processor according to an embodiment of the present invention.

Detailed Description

The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

The embodiment of the utility model provides a sportsman's fatigue detection system, including first treater 1, first treater 1 is connected with recording element 2, acceleration sensor 3, locating element 4, heart rate detecting element 5, fall detecting element 6 and human lack of water degree detecting element 7 respectively; the recording element 2, the acceleration sensor 3, the positioning element 4, the heart rate detection element 5 and the human body water shortage degree detection element 7 are respectively connected with the first processor 1 through a storage element 81.

Here, the first processor 1 is a network model, and the first processor 1 is configured to receive data of each sensor during training of the athlete, and perform operation processing on each data according to a preset rule, so as to obtain a corresponding operation value, thereby enabling a coach to intuitively obtain a physical condition of the athlete during training.

Specifically, as shown in fig. 2, the first processor 1 includes a convolutional neural network module 11, a long-short term memory model module 12, a weight calculation module 13, and an output module 14, where the convolutional neural network module 11 and the long-short term memory model module 12 are both connected to the weight calculation module 13, and the weight calculation module 13 is connected to the output module 14.

The convolutional neural network model comprises two parts, namely a convolutional layer and a fully-connected layer, wherein convolutional calculation of the convolutional layer realizes training of a Deep Neural Network (DNN), and the deep network structure of the convolutional neural network model comprises a forward propagation algorithm and a backward propagation algorithm. The forward propagation algorithm is to calculate the output of the next layer using the output of the previous layer. The deep neural network back propagation algorithm is a process of iteratively solving a minimum value of a loss function by using a gradient descent method, and can solve the classification regression problem of various supervised learning; the long-short term memory model module 12 (LSTM model) is a time-recursive neural network suitable for processing and predicting important events with relatively long intervals and delays in a time series. The convolutional neural network model and the long-short term memory model module 12 are well known to those skilled in the art and therefore will not be described herein. The convolutional neural network model and the long-short term memory model module 12 are used for performing separate calculation processing on the acquired data. The convolutional neural network and the LSTM can adopt supervised learning and unsupervised learning to classify data, and can adopt K-mean clustering algorithm, K-center clustering algorithm, clarans, birch, CLIQUE, dbscan and other algorithms to classify. The ratio of learning data to test data was 80% and 20% or 70% and 30%, with the specific ratio adjusted in practice.

And the weighting calculation module 13 performs summary weighting on the two results according to a preset rule, and obtains a corresponding predicted value. The output module 14 is configured to output the corresponding prediction value.

More specifically, as shown in fig. 1, the first processor 1 is also connected with a display element 91 and a feedback element 92. The predicted value is input to the display element 91 through the output module 14, so that the predicted value is convenient for a coach to view. The output module 14 may be a signal emitting device, the display element 91 may be a display screen, and the feedback element 92 is used to enhance or reduce the received signal, so as to enhance the important signal and attenuate the general signal.

Further, as shown in fig. 1, the recording element 2, the acceleration sensor 3, the positioning element 4, the heart rate detecting element 5, the fall detecting element 6 and the human body water shortage detecting element 7 are all connected to the first processor 1 through the transmission element 82.

Here, the transmission element 82 is configured to send signals sensed by the sensors to the first processor 1, and the transmission element 82 includes a receiver and a transmitter, wherein the receiver is disposed on the first processor 1, and the transmitters are disposed on the recording element 2, the acceleration sensor 3, the positioning element 4, the heart rate detecting element 5, the fall detecting element 6, and the human body water shortage detecting element 7, respectively.

The receiver and the transmitter may be connected by a wire or a wireless connection, and specifically, the wireless connection may be a mobile network, or may be a transmission method such as zigbee or bluetooth.

The fall detection element 6 is used to detect whether an athlete has fallen, where falls tend to consume more than usual physical strength, which is one of the important signals when physical strength is about to run out. The fall detection element 6 is a gyroscope, and the fall detection element 6 can be placed at a knee pad or the like of an athlete when in use.

Furthermore, the positioning element 4, the heart rate detecting element 5 and the human body water shortage detecting element 7 need to acquire data of an athlete within a period of time when in use, and therefore need to be stored by the storage element 81 and then sent to the transmission element 82 when being transmitted by the transmission element 82. Here, the storage elements 81 may be connected to the positioning element 4, the heart rate detection element 5, and the human body water shortage detection element in a one-to-one correspondence.

The positioning element 4 is used for recording the movement track of the athlete and evaluating the physical consumption condition of the athlete according to the length of the movement track, and the positioning element 4 can be a GPS personal locator or other electrical elements with positioning functions. Furthermore, in order to match the positioning element 4 to accurately evaluate the physical ability consumption of the athlete, a step number detection module is added, and the physical ability consumption of the athlete can be further accurately judged through the step number detection module.

Heart rate detecting element 5 is used for detecting the rhythm of the heart condition when the sportsman moves, heart rate detecting element 5 can be for the detection bracelet that can buy on the existing market, or other have the device that detects to the rhythm of the heart.

The human body water shortage detection element is used for detecting the loss of water in a body when an athlete moves so as to judge the water shortage condition in the body of the athlete, and can be a double-capacitance sensor used for detecting the capacitance of the water in the horny layer of the skin and measuring the relative humidity of the skin of the athlete.

Further, the recording element 2 and the acceleration sensor 3 are connected to the transmission element 82 through the storage element 81 and the second processor 84 in this order.

Here, the recording element 2 is used for collecting the sound condition of the athlete during the sport, and the rough degree of the panting can represent the physical performance condition of the athlete after the athlete moves for a long time, so that the collection is needed through the recording element 2, and the recording element 2 can be a recorder or other equipment with a sound collection function.

The acceleration sensor is used for measuring the acceleration of the arm of the athlete in a certain time period, so as to evaluate the rough strength and duration of arm swing of the athlete in a certain time period, and the rough strength and duration are used as one of the bases for evaluating the physical energy consumption of the athlete. The acceleration sensor can be an acceleration sensor, namely a motion sensor (an inertial sensor), and can be used for detecting the acceleration in the direction of X, Y, Z axes, the gravity detection unit of the X axis or the Z axis sends a detected acceleration variation signal to a charge integrator to be subjected to integral operation, then sampling, holding and signal amplification processing are carried out, finally a low-pass filter is used for filtering high-frequency noise, and the acceleration information can be output after temperature compensation processing. The acceleration sensor 3 is typically placed at the arm of the athlete.

During testing, the recording element 2 and the acceleration sensor measure training conditions within a certain period of time, and therefore need to be stored through the storage element 81, and during use, the recording element 2 and the acceleration sensor are respectively connected with one of the storage element 81. Meanwhile, after the sound acquired by the recording element 2 is determined, the sound signal is processed, so that the acquired sound data needs to be sent to the second processor 84 for conversion, and then sent to the first processor 1 for evaluation; the acceleration sensor converts the acquired acceleration to acquire data of force and time, so that the acquired speed data needs to be sent to the second processor 84 for conversion and then to the first processor 1 for evaluation.

The second processor 84 is used for edge calculation, and directly preprocesses sensor data such as sound, acceleration, heart rate and the like, and standardizes the data so as to reduce the data processing amount of the first processor 1. The first processor 1 determines the physical fatigue of the athlete by using an AI artificial intelligence algorithm such as a decision tree, a random forest, an SVM, a K-nearest neighbor algorithm, and the like, for the data transmitted from the second processor 84.

Indeed, in the embodiment of the utility model provides an in, recording component 2 sets up in first wearing equipment, acceleration sensor 3 with heart rate detecting element 5 sets up in second wearing equipment, fall detecting element 6 sets up in third wearing equipment, locating element 4 sets up in fourth wearing equipment, human lack of water degree detecting element 7 sets up in fifth wearing equipment.

Here, the first wearable device may be a clip for clipping at a neckline, the recording original is fixedly mounted on the clip, the second wearable device may be a bracelet, the acceleration sensor 3 and the heart rate detection element 5 are mounted on the bracelet, the third wearable device may be a knee pad, the fall detection element 6 is mounted in the third wearable device, and the fourth wearable device and the fifth wearable device may be the same as or different from the first wearable device/the second wearable device/the third wearable device.

The above is only a preferred embodiment of the present invention, and it should be noted that the above preferred embodiment should not be considered as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. It will be apparent to those skilled in the art that various modifications and enhancements can be made without departing from the spirit and scope of the invention, and such modifications and enhancements are intended to be within the scope of the invention.

Claims (7)

1. The athlete fatigue detection system is characterized by comprising a first processor (1), wherein the first processor (1) is respectively connected with a recording element (2), an acceleration sensor (3), a positioning element (4), a heart rate detection element (5), a falling detection element (6) and a human body water shortage degree detection element (7);

wherein, record component (2), acceleration sensor (3), locating element (4), heart rate detecting element (5) and human lack of water degree detecting element (7) respectively through storage element (81) with first treater (1) is connected.

2. The athlete fatigue detection system according to claim 1, wherein the first processor (1) is connected to the recording element (2), the acceleration sensor (3), the positioning element (4), the heart rate detection element (5), the fall detection element (6) and the human body water shortage detection element (7) through transmission elements (82).

3. An athlete fatigue detection system according to claim 1, wherein the recording element (2) and the storage element (81) on the acceleration sensor (3) are further connected to a second processor (84), and the recording element (2) and the acceleration sensor (3) are connected to the first processor (1) through the second processor (84).

4. An athlete fatigue detection system according to claim 1, wherein the first processor (1) is further connected to a display element (91) and a feedback element (92).

5. The athlete fatigue detection system according to claim 1, wherein the first processor (1) comprises a convolutional neural network module (11), a long-short term memory model module (12), a weighting calculation module (13), and an output module (14), wherein the convolutional neural network module (11) and the long-short term memory model module (12) are both connected to the weighting calculation module (13), and the weighting calculation module (13) is connected to the output module (14).

6. An athlete fatigue detection system according to claim 1, wherein the first processor (1) is further connected to a step count detection module.

7. The athlete fatigue detection system according to claim 1, wherein the recording element (2) is arranged in a first wearable device, the acceleration sensor (3) and the heart rate detection element (5) are arranged in a second wearable device, the fall detection element (6) is arranged in a third wearable device, the positioning element (4) is arranged in a fourth wearable device, and the human body water shortage detection element (7) is arranged in a fifth wearable device.

Images