CN111513731A - Flexible intelligent detection device based on sufficient state monitoring attention - Google Patents

Abstract

The invention discloses a flexible intelligent detection device based on attention monitoring of foot states, which comprises a flexible array type pressure sensor, an analog signal multiplexer, an analog-to-digital conversion circuit, a Bluetooth module, an artificial intelligent learning system and an insole base, wherein the flexible array type pressure sensor is connected with the analog signal multiplexer; the invention adopts a flexible array type pressure sensor to collect plantar pressure signals of dynamic or static sitting postures of a human body, the online pressure signals are input into an analog-to-digital conversion circuit through an analog signal multiplexer and are transmitted to a computer of an artificial intelligent learning system through a Bluetooth module, the online pressure signals are compared with standard pressure signals in a classifier by the computer, collected data are analyzed through a clustering algorithm, human behavior and attention quality are associated, real-time results are displayed in a display screen through signal identification and characteristic processing, and thus intelligent detection of human attention is realized. The invention has the advantages of high detection accuracy, small volume, light weight, convenient use and no limitation of regional environment.

Description

A flexible intelligent detection device based on foot posture monitoring attention

technical field

The invention relates to the field of intelligent wearable technology, in particular to a flexible intelligent detection device based on foot posture monitoring attention.

Background technique

Attention refers to the ability of a person's mental activities to point and focus on something. Attention is one of the five basic factors of intelligence, and it is the state of readiness for memory, observation, imagination, and thinking, so attention is called the gateway of the mind. Attention is not a static psychological feature, but is highly dynamic and fluctuating. Various intellectual activities of human beings, including posture, emotion, will, etc., all require the participation of attention to take place effectively. A large number of studies at this stage have already confirmed that attention affects individual work efficiency or academic performance. It can be seen that the importance of studying individual attention quality, especially in the "offline" classroom, is more worthy of exploration. .

With the development of technology, in addition to the traditional attentional observation methods: homework test method, empirical observation, etc., many people have devoted themselves to measuring attentional quality from instruments. According to the measurement entry point, it is divided into three categories, and the instrumental measurement methods are: brain wave measurement (EEG), visual measurement, and behavior measurement. The application number is 201620006749.1, the patent name is a student classroom participation detection system, and a student classroom participation detection system is disclosed, including a student intelligent terminal, a check-in camera, a check-in computer, an attention detection camera and a video processing computer; The output end of the check-in camera is connected to the input end of the check-in computer, the output end of the check-in computer is connected to the input end of the video processing computer, the output end of the camera is connected to the input end of the video processing computer for attention detection, and the intelligent terminal is used to scan the check-in computer to generate To complete the check-in and automatically log in to the classroom interaction system, monitor and analyze the participation of students in the classroom by means of visual instrument measurement.

The principle of the brain wave measurement instrument is based on the fact that the main activity of the alpha band in the individual brain waves in the quiet and wakeful state is 8-12 Hz, while the frontal brain wave frequency of the individual with attention deficit decreases, the theta slow wave power increases, and theta/beta The power ratio is increased, and brain waves are then measured and recorded by a sensor device, which is converted by an algorithm into an easy-to-understand data form to measure attention. Such instruments are bulky and expensive, and are only used in small-scale experimental environments.

In the visual measurement method, the camera is used to collect the information of the learner's learning process, and the facial expression is analyzed by a computer algorithm (such as face recognition technology) to analyze the individual's psychological state, thereby analyzing the individual's attention. Eye-tracking technology and Kinect are important examples of visual measurement. Eye-tracking technology analyzes individual attention based on eye annotation position (attention allocation), annotation time (task difficulty and amount of attention resources required) and scanning path; Kinect As a 3D somatosensory camera, it recognizes human images, voices, etc. to analyze mental states to obtain attention information. This type of instrument consumes high time cost in data acquisition and processing, and also has high requirements for data storage.

In the behavior measurement method, relatively basic materials and equipment are mainly used, which has the characteristics of low cost and high popularity. At present, the products that measure attention through behavior mainly obtain attention information based on the principle of different concentration of attention in different sitting postures, including sitting posture inclination and sitting pressure measurement methods to analyze sitting posture. Among them, the sitting posture inclination is to use the gyroscope to obtain the inclination of the body, while the pressure measurement uses the pressure sensor to obtain the pressure distribution of the seat cushion. Information about sitting posture, and different sitting postures represent different quality of attention. However, there is a big problem with this method. The test is affected by special sitting postures such as Erlang's legs and cross-legs, and the scenarios used are very limited.

In 1993, Teasdale et al reported that when the plantar pressure of a person is closer to the center of the foot, the posture is more stable, and the mechanism responsible for regulating posture stability requires less attention, that is, more attention can be paid. among other things. In 1984, Armstrong and Edgley found from animal and human gaits that single support costs more attention, so we can compare the attention of Erlang's legs with other sitting postures. A 2015 study by four U.S. universities analyzing children with ADHD found that when focusing on one thing, the involuntary repetitive movements of shaking the legs help improve concentration and concentration. So we know that different sitting postures will form different foot pressure distributions with different foot postures, so as to get attention. In addition, the frequency of limb changes is also closely related to attention. For example, tests on ADHD and attention can confirm that a symptom of ADHD patients is that they often feel awkward when sitting, play with hands or feet , or keep twisting the body. We can analyze the sitting posture and the frequency of limb changes by observing the foot pressure, so as to obtain the attention situation. The flexible smart wearable insole can achieve this purpose, and has stronger convenience and portability. influences.

Most of the existing technologies are expensive, have high requirements on scenes and equipment, and do not consider the influence of the frequency of limb changes on attention. The detection of attention is not accurate, effective and convenient, and foot pressure is closely related to sitting posture. Foot pressure affects attention, so we designed this smart flexible device to analyze attention by detecting foot pressure.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a flexible intelligent detection device based on foot posture monitoring attention based on the deficiencies of the prior art. It is input to the analog-to-digital conversion circuit through the analog signal multiplexer, and transmitted to the computer of the artificial intelligence learning system through the bluetooth module. The computer compares the online pressure signal with the standard pressure signal in the classifier, and uses the clustering algorithm to collect The data is analyzed, the human behavior is correlated with the quality of attention, and the real-time results are displayed on the display screen through signal recognition and feature processing, so as to realize the intelligent detection of human attention.

The concrete technical scheme that realizes the object of the present invention is:

A flexible intelligent detection device based on foot posture monitoring attention, which is characterized by a flexible array pressure sensor, an analog signal multiplexer, an analog-to-digital conversion circuit, a Bluetooth module, an artificial intelligence learning system and an insole base;

The artificial intelligence learning system is composed of a computer, a classifier and a display screen, and the computer is connected with the classifier and the display screen data line;

The insole base is one on the left and right, and the insole base is divided into an upper cushion layer and a lower device layer;

The flexible array pressure sensor is arranged on the cushion layer of the insole base, and the analog signal multiplexer, the analog-to-digital conversion circuit and the Bluetooth module are arranged on the device layer of the insole base;

The computer, the classifier and the display screen of the artificial intelligence learning system are independently set in sequence;

The flexible array pressure sensor, the analog signal multiplexer, the analog-to-digital conversion circuit and the bluetooth module are connected with wires in sequence, and the bluetooth module is connected with the computer of the artificial intelligence learning system by wireless communication.

The present invention collects the plantar pressure signal of the dynamic or static sitting posture of the human body through the flexible array pressure sensor, the online pressure signal is input to the analog-digital conversion circuit through the analog signal multiplexer, and is transmitted to the computer of the artificial intelligence learning system through the bluetooth module, The computer compares the online pressure signal with the standard pressure signal in the classifier, analyzes the collected data through a clustering algorithm, correlates human behavior with the quality of attention, through signal recognition and feature processing, and displays it on the display screen. Real-time results are displayed in the system, so as to realize intelligent detection of human attention.

Description of drawings

Fig. 1 is the structural representation of the present invention;

Fig. 2 is the assembly structure schematic diagram of insole base;

3 is a schematic circuit diagram of an analog signal multiplexer;

Figure 4 is a schematic diagram of the structure of an artificial intelligence learning system;

Figure 5 is a schematic diagram of ten static sitting postures of the human body;

FIG. 6 is a schematic diagram of an implementation state of the present invention.

Detailed ways

1, the present invention includes a flexible array pressure sensor 1, an analog signal multiplexer 2, an analog-to-digital conversion circuit 3, a Bluetooth module 4, an artificial intelligence learning system 5 and an insole base 6;

The artificial intelligence learning system 5 is composed of a computer 51, a classifier 52 and a display screen 53, and the computer 51 is connected with the classifier 52 and the display screen 53 by data lines;

The insole base 6 is one on the left and right, and the insole base 6 is divided into an upper cushion layer 61 and a lower device layer 62;

The flexible array pressure sensor 1 is arranged on the cushion layer 61 of the insole base 6 , and the analog signal multiplexer 2 , the analog-to-digital conversion circuit 3 and the Bluetooth module 4 are arranged on the device layer 62 of the insole base 6 ;

The computer 51, the classifier 52 and the display screen 53 of the artificial intelligence learning system 5 are independently set in sequence;

The flexible array pressure sensor 1 , the analog signal multiplexer 2 , the analog-to-digital conversion circuit 3 and the bluetooth module 4 are connected by wires in sequence, and the bluetooth module 4 is connected to the computer 51 of the artificial intelligence learning system 5 by wireless communication.

The present invention works like this:

Referring to Figure 1 and Figure 6, to detect the sitting posture adopted by the person, place the soles of the two feet on the flexible array pressure sensor 1 of the insole base 6, under the action of the pressure at each point of the sole, the flexible array pressure sensor 1. The multiple sets of pressure signals obtained from the soles of the two feet are input to the analog-to-digital conversion circuit 3 through the analog signal multiplexer 2, and are transmitted to the computer 51 of the artificial intelligence learning system 5 through the Bluetooth module 4. 51 compares the online pressure signal with the standard pressure signal in the classifier 52, and displays the real-time results on the display screen 53 through signal identification and feature processing, thereby realizing intelligent detection of human attention.

Referring to Fig. 1, Fig. 5, Fig. 6, it is found from the research on the relationship between human behavior and attention that different sitting postures of the human body maintain a close relationship with attention. In order to realize the real-time detection of students' attention, the present invention first collects different The static and dynamic pressure signals of the sitting posture are input into the classifier 52 as standard pressure signals, and the standard pressure signals of different static sitting postures of the human body are divided into upright sitting, left inclination, right inclination, with the soles of the feet facing the ground, and the soles of the feet. There are ten states of feet flat, forward leaning toes on the ground, backward leaning feet flat, backward leaning heels, and backwards heels touching the ground. The dynamic standard pressure signals are two states of leg shaking and postural hyperactivity.

Referring to FIG. 1, FIG. 5, and FIG. 6, since the sole of the person to be detected is attached to the flexible array pressure sensor 1, the flexible array pressure sensor 1 collects the online pressure of each part of one sole or two soles in real time. Signal, the online pressure signal is input to the analog-to-digital conversion circuit 3 through the analog signal multiplexer 2, and wirelessly transmitted to the computer 51 of the artificial intelligence learning system 5 through the Bluetooth module 4, and the computer 51 combines the online pressure signal with the classifier 52. The standard pressure signal is identified and compared, and the real-time result is displayed on the display screen 53 through signal identification and feature processing, so as to complete the intelligent detection of human attention.

Compared with the prior art, the present invention has the advantages of high detection accuracy, small size, light weight, convenient use, and is not restricted by the geographical environment, and overcomes the disadvantages of the existing scene-based, image-based and wearable detection on equipment and the environment. Strictly demanding defects, the present invention can improve students' study attention by correcting the sitting posture under the premise of not interfering with the normal study and lifestyle of the person to be tested, and provide a reliable and effective analysis for the correlation study of human behavior and attention. data.

Example

Referring to Figures 1 and 2, the flexible array pressure sensor 1 of the present invention selects a sensing array with 64 rows and 64 columns, and is composed of 64*64 RX-D2027 flexible pressure sensors. The sensors are arranged on the base of the insole. The cushion layer 61 of the seat 6 collects the pressure value of each contact point of the foot as an online pressure signal; the range and size of the flexible array pressure sensor 1 can be set according to the user's weight and foot length; each sensor array is distributed on the foot. Each position of the foot can be obtained from different pressure values of each point of the foot. Multiple sensor arrays work at the same time. The entire system is powered by stm32. The analog signal multiplexer 2 is used to provide working voltage to the sensor array in turn, and high-speed conversion Gating the position to achieve the purpose of continuously collecting the pressure values of various parts of the sole of the foot; the analog signal multiplexer 2, the analog-to-digital conversion circuit 3 and the Bluetooth module 4 are arranged on the device layer of the insole base 6, and the online pressure signal is passed through Bluetooth The module 4 is wirelessly transmitted to the computer 51 of the artificial intelligence learning system 5 .

Referring to FIG. 1 and FIG. 3, the analog signal multiplexer 2 of the present invention uses two TP0164 analog signal 64-way multiplexers to control 64 rows and 64 columns respectively, and the analog signal multiplexer functions as an analog switch. It controls the output of one of the sensors. Due to the high-speed conversion of the sensor corresponding to the output, it is approximate that each sensor continuously outputs data;

The analog signal multiplexer 2 realizes the output measurement of the sensor array. The analog switch has low power consumption, high speed, and low on-resistance. The on-resistance remains relatively stable in the entire input signal range.

Referring to Figure 1, Figure 2, Figure 5, the pressure value of each pressure sensor is serially output to the analog-to-digital conversion circuit 3 through the gated analog signal and converted into a digital signal that is convenient for the computer 51 to process. The analog-to-digital converters share up to 16 external channels, and the conversion time can reach 1 μs. It can convert the analog signals of ten kinds of static and two types of dynamic pressure data of the subject 6 into digital signals. The analog-to-digital conversion circuit 3 uses stm32 The ADC multi-channel scan conversion of the embedded 2 12-bit analog-to-digital converters, and the Bluetooth communication is carried out through the USART serial port of the stm32 in the embedded system through DMA transmission, and connected to the Bluetooth module 4 to transmit the packaged data to the computer. 51.

1 and 4, the artificial intelligence learning system 5 of the present invention is composed of a computer 51, a classifier 52 and a display screen 53. In the artificial intelligence learning system 5, a clustering algorithm program is set in the computer 51; Various standard pressure signals are set in the , including dynamic or static classification standard pressure signals, dynamic sitting posture standard pressure signals, and static sitting posture standard pressure signals.

Referring to Figure 1, Figure 4, Figure 6, the work of the artificial intelligence learning system 5 of the present invention is divided into the following three steps:

The first step, the classification of dynamic and static sitting posture: the computer 51 receives a set of data transmitted by Bluetooth every 0.05s, each set of data contains the online pressure signal of the corresponding coordinates of each sensor array, and the computer 51 receives the online pressure transmitted by the Bluetooth module 4 . The computer 51 slides and stores two online pressure signals with a duration of 100 s to form two online pressure signal data packets, and compares the online pressure signal data packets with the dynamic or static classification standard pressure signals in the classifier 52, and the computer 51 First, analyze and confirm that the signal is a dynamic sitting posture signal or a static sitting posture signal from the online pressure signal data packet. If it is confirmed to be a static sitting posture signal, the confirmed static sitting posture signal is sent to the classifier 52, and the corresponding signal is matched by the classifier 52. The standard pressure signal of static sitting posture;

The second step, specific sitting posture classification: the computer 51 identifies and compares the first online pressure signal data packet with the static sitting posture standard pressure signal in the classifier 52, and analyzes the static sitting posture type with the highest matching degree. The pressure signal data packet makes the first sitting posture classification determination; the computer 51 identifies and compares the second online pressure signal data packet with the static sitting posture standard pressure signal in the classifier 52, and analyzes the static sitting posture type with the highest matching degree , make a second sitting posture classification determination on the online pressure signal data packet of the foot; if the two classification results are inconsistent, the online pressure signal data packet needs to be collected again, if the two classification results are consistent, go to the next step;

The third step is to analyze the attention through the sitting posture and output the detection result: the computer 51 compares and corrects the two online stress signal data packets, obtains the attention quality data packets, and analyzes the attention quality data packets through the clustering algorithm. , that is, analyze the attention quality parameters, and the full score is 100. The higher the score, the more concentrated the corresponding attention is. The analyzed sitting posture and attention quality parameters are output to the display screen 53, and the real-time results are displayed on the display screen 53. , so as to realize intelligent detection from foot pressure to human attention.

Claims (1)

1. A flexible intelligent detection device based on attention monitoring of foot states is characterized by comprising a flexible array type pressure sensor (1), an analog signal multiplexer (2), an analog-to-digital conversion circuit (3), a Bluetooth module (4), an artificial intelligent learning system (5) and an insole base (6);

the artificial intelligence learning system (5) is composed of a computer (51), a classifier (52) and a display screen (53), and the computer (51) is connected with the classifier (52) and the display screen (53) through data lines;

the insole base (6) is arranged at the left and right, and the insole base (6) is divided into an upper cushion layer (61) and a lower device layer (62);

the flexible array type pressure sensor (1) is arranged on a cushion layer (61) of the insole base (6), and the analog signal multiplexer (2), the analog-to-digital conversion circuit (3) and the Bluetooth module (4) are arranged on a device layer (62) of the insole base (6);

the computer (51), the classifier (52) and the display screen (53) of the artificial intelligence learning system (5) are sequentially and independently arranged;

the flexible array type pressure sensor (1), the analog signal multiplexer (2), the analog-to-digital conversion circuit (3) and the Bluetooth module (4) are sequentially connected through leads, and the Bluetooth module (4) is in wireless communication connection with a computer (51) of the artificial intelligent learning system (5).

Images