2. Implementation of the project based on the neural network for the recognition of the gripper for bionic artificial limbs and for virtual reality and game devices

As it was already noted earlier, within the project the hi-tech bionic artificial limb which surpasses all internal functional electromechanical and cosmetic artificial limbs is developed and also will surpass foreign bionic artificial limbs in functionality by industrial production. And, the LLC "Bionic Natali" company is faced by a task to make him available to most disabled people due to considerable reduction of cost in comparison with foreign bionic artificial limbs, about by five to six times. Also, it should be noted about a know-how the project, creation of innovative system of reading on bigger quantity of electrodes, than in the current foreign bionic artificial limbs which is also radio and it is constructed on the principles of neural network and other algorithms.

The technology of recognition of gestures of electromyographic activity based on neural network or an analog of network is the cornerstone. The bracelet is put on a hand (in case of disabled people, a stump), further noninvasive electrodes remove potential difference of neuromuscular activity; by means of an electric circuit, there is data handling and their transmission to the processor where by means of a neural network there is a recognition of a gripper or movement of a knee, further data are transferred for control of a bionic hand or leg.

Information on how usually artificial limbs are working can be found in article [1].

Within the carried-out scientific research works of more than 1 year, the basic divergences with data of muscular activity were found in disabled people and given to muscular activity at people without amputation. Distinctive feature is the range of frequencies at which the signal registers, and importance of maintenance of a tone of muscular activity at disabled people, otherwise there are artifacts of the movement, which at people without amputations are not registered. For this task now with Ilizarov's center, the system of rehabilitation is studied, and also the separate product "an electromyographic bracelet" which is taken out in the separate company LLC "BioN EMG" has been created. In Figure 1, the picture on a control system of any executive mechanism of the recognition of EMG based on the neural network is given below.

General explanation of EMG can be found in the book [2].

### 2.1. Technology of bionic artificial limbs

Technical tasks, realized within works and development, were the following:


The main problems, which have been put before LLC "Bionic Natali" company at implementation of the project, are the following:


Emphasis on a project know-how, creation of innovative system of reading on bigger quantity of electrodes than in the current foreign bionic artificial limbs which also is wireless and constructed on the principles of the neural network, is worth placing. The matter is that in all foreign artificial limbs at the moment the management is based on the basis of management from two sensors and threshold value of a signal, grippers are programmed by means of phone or the button on an artificial limb. There is selection of an algorithm of data processing of electromyographic activity of muscles for the best recognition of the gripper and experi-

Control Systems of Bionic Limbs of the New Generation and Control Systems with EMG Signals of VR and Games…

http://dx.doi.org/10.5772/intechopen.74794

95

Materials are the knowledge of developers and experience of the advising experts (the mentor on algorithms—professor of Skoltech Victor Lempitsky; prosthetists Levon Kirakozov, S. Golovin, V. Golovin, and A. Dozhdev; experts of the Federal State Budgetary Institution SPb NCEPR of G.A. Albrecht of Ministry of Labour and Social Protection of the Russian Federation; experts of the center of Ilizarov; etc.) and also completely experimental data that had been

The method which was used in the course of selection of an algorithm is the experimental

It is important to mark that at the first stages of the project it was planned to select algorithms, processing collected these electromyograms of muscular activity of disabled people from open sources, but as it was clarified later, in open access information was practically not, and what managed to be found, was very far from reality and is poorly described regarding process of removal of data that does not exclude existence of an error in data. As a result, the decision to

As for the solution of a task of optimization of gripper, decrease in cognitive load of the person and increase in effective management of an artificial limb is reached due to use of a hybrid control system which combines ways of decoding electro-neuromyosignals with elements of autonomous robotic manipulations on capture of a subject at achievement of threshold value of distance to him by means of the decision-making which is not demanding participation of the user on the beginning or the termination of implementation of the gripper by means of information from additional sensors (temperature and distance), and about force of compres-

Also, in a picture, the example of an arrangement of sensors on the hand artificial limb has

Example of the scheme of realization of the data acquisition in the form of the myoelectric system (poses 1—system of reading, poses 2—sensor of registration of biopotential, poses 3—

The use of wireless data transmission between the artificial limb and the system of control provides usability of system and interchangeability of components, besides a possibility of

It is important to notice that in the course of the analysis of putting off data it was revealed that a bracelet for management of a prosthesis of the hand and a forearm in a case with the use of

create an own experimental database that was successfully realized was made.

sion of a subject by means of information from sensors.

mental confirmation of developments.

used.

"trial-and-error method."

been shown below (Figure 2).

their use independently of each other.

elastic cuff) (Figure 3).



Figure 1. The scheme of control of any executive mechanism of the recognition of EMG based on the neural network.

Emphasis on a project know-how, creation of innovative system of reading on bigger quantity of electrodes than in the current foreign bionic artificial limbs which also is wireless and constructed on the principles of the neural network, is worth placing. The matter is that in all foreign artificial limbs at the moment the management is based on the basis of management from two sensors and threshold value of a signal, grippers are programmed by means of phone or the button on an artificial limb. There is selection of an algorithm of data processing of electromyographic activity of muscles for the best recognition of the gripper and experimental confirmation of developments.

product "an electromyographic bracelet" which is taken out in the separate company LLC "BioN EMG" has been created. In Figure 1, the picture on a control system of any executive

• Reliable functional intellectual bionic artificial limb of an extremity with return of tactile

The main problems, which have been put before LLC "Bionic Natali" company at implemen-

4. Making decision on the capture of a subject and increase in controllability of gripper

Figure 1. The scheme of control of any executive mechanism of the recognition of EMG based on the neural network.

mechanism of the recognition of EMG based on the neural network is given below.

Technical tasks, realized within works and development, were the following:

• Way and control system of the auxiliary device, such as extremity artificial limb

General explanation of EMG can be found in the book [2].

communication by means of neuromuscular signals

2. Increase in accuracy of the obtained data at recognition of gripper

3. Increase in accuracy and probability of recognition of gripper

2.1. Technology of bionic artificial limbs

94 Biofeedback

tation of the project, are the following:

1. Increase in accuracy of positioning of engines

Materials are the knowledge of developers and experience of the advising experts (the mentor on algorithms—professor of Skoltech Victor Lempitsky; prosthetists Levon Kirakozov, S. Golovin, V. Golovin, and A. Dozhdev; experts of the Federal State Budgetary Institution SPb NCEPR of G.A. Albrecht of Ministry of Labour and Social Protection of the Russian Federation; experts of the center of Ilizarov; etc.) and also completely experimental data that had been used.

The method which was used in the course of selection of an algorithm is the experimental "trial-and-error method."

It is important to mark that at the first stages of the project it was planned to select algorithms, processing collected these electromyograms of muscular activity of disabled people from open sources, but as it was clarified later, in open access information was practically not, and what managed to be found, was very far from reality and is poorly described regarding process of removal of data that does not exclude existence of an error in data. As a result, the decision to create an own experimental database that was successfully realized was made.

As for the solution of a task of optimization of gripper, decrease in cognitive load of the person and increase in effective management of an artificial limb is reached due to use of a hybrid control system which combines ways of decoding electro-neuromyosignals with elements of autonomous robotic manipulations on capture of a subject at achievement of threshold value of distance to him by means of the decision-making which is not demanding participation of the user on the beginning or the termination of implementation of the gripper by means of information from additional sensors (temperature and distance), and about force of compression of a subject by means of information from sensors.

Also, in a picture, the example of an arrangement of sensors on the hand artificial limb has been shown below (Figure 2).

Example of the scheme of realization of the data acquisition in the form of the myoelectric system (poses 1—system of reading, poses 2—sensor of registration of biopotential, poses 3 elastic cuff) (Figure 3).

The use of wireless data transmission between the artificial limb and the system of control provides usability of system and interchangeability of components, besides a possibility of their use independently of each other.

It is important to notice that in the course of the analysis of putting off data it was revealed that a bracelet for management of a prosthesis of the hand and a forearm in a case with the use of

2.2. Technology of the work of the virtual reality and game devices with the use of the

on the computer, the phone (Figure 4), as also without the computer or the phone.

The control of the virtual reality happens as follows: the myoelectric device of reading in the form of a bracelet (or a similar design the device) is put on a forearm or an arm, or other parts of an extremity, as the example, legs, occurs calibration and control of a bracelet, it can be made

Control Systems of Bionic Limbs of the New Generation and Control Systems with EMG Signals of VR and Games…

http://dx.doi.org/10.5772/intechopen.74794

97

Points of virtual reality consist at least of different types of lenses, the display, the details of the case, the computing system, the accelerometer, the gyroscope, and the sensor of the wireless

Communication between the bracelet and points of virtual reality is been organized by means of any wireless communication, in our case are used by Bluetooth at what by Bluetooth of a bracelet it is ready as conducted, and Bluetooth of points of virtual reality as the master. The myoelectric device for reading, in the form of the bracelet (or the similar design of the device), carries out registration and filtration of the electromyogram (EMG), defines position of the hand, depending on it sends the corresponding command to points of virtual reality, or obtains information on feedback. It is important that the myoelectric device of reading besides the gripper given according to numbers sends to points information from the gyroscope and the accelerometer that allows to define position of the hand in space better. The arrangement of the myoelectric device for reading not only on hands but also on legs, the back, and the neck

electromyographic bracelet

communication (Bluetooth) (Figure 5).

Figure 4. The virtual reality and bracelet.

Figure 2. Example of the arrangement of sensors on the hand artificial limb.

Figure 3. The scheme of realization of the data acquisition in the form of the myoelectric system.

neural network, it is possible to wear not only on a forearm and to take off data from a forearm, but also for management of the hand to take off data from a brachium that considerably dilated opportunities at a prosthetic repair by bionic prostheses of arms (of course, there is a restriction on number of gripper and features of management, at some disabled people different grippers are defined variously in connection with features of a stump).
