3. Results of the practical application of developments of the recognition of EMG based on the neural network for disabled people at the management of bionic artificial limbs of hands and for game devices for people without disability

As already it has been noted above, thanks to the created technology researches of innovative feedback based on EMG for people without loss of limbs and also with loss of limbs regarding management of the systems of recognition of EMG based on the neural network have been conducted. Categories of people who participated in the research are the following:


Results of the analysis of an experiment have not included people who took only single part in a research as to reveal certain regularities, and there are needs to hold regular testing and checks; single participation is not natural and does not give understanding about feedback which is formed, and also in connection with complex psychological structure of people, the probability of obtaining wrong data is high.

The research objective is to reveal regularities using the control system of recognition of EMG from the shoulder and the forearm based on the neural network for different groups of people.

If to carry out the comparative analysis at people without amputation and with amputation, then results showed that physical training and a training of muscles plays a significant role regarding recognition of an EMG of a signal.

In spite of the fact that the signal in itself at people with an amputation of a hand is much more weak than people without loss have arms, the muscular training sometimes at people with amputation of an amputation allows to receive more accurate signal than a signal at the person of the same age group without loss of the limbs. Regular researches of people with amputation of limbs showed that more often there is a training of muscles and the muscle tone and also a comprehension and "representation" of gripper which are carried out by the person with amputation, and as a result, the subsequent already management of a bionic limb comes back quicker.

Figure 15. Flowchart of the algorithm.

106 Biofeedback

If to compare groups of people with the amputation of arms and different age categories, then the research showed that management does not depend on age in any way, but depends on the term of amputation and existence at the disabled person of a bionic/myoelectric prosthesis during this period. People who right after amputation began to use bionic/myoelectric prostheses or had a possibility of a training of muscles, had better discernible signals on frequency, and better coped with a task of management of a bionic prosthesis based on an EMG. There is an assumption that this feature arises because when the person lost a limb, at it the phantom feeling of an arm continues certain time to be held muscle in remembrance (even taking into account that injuries sometimes happen various and a part of muscles cannot remain or undergo other operations), as well as sometimes. If after that are not carried out a series of actions for maintenance of a muscle tone, then eventually there is a sharp atrophy of muscles which is harder and harder for restoring every year.

division as signals which are sent to the executive mechanism which are executed by the

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

109

Moreover, it is important to note that for the first time when people begin to use neural-control

Fundamental difference of the given neurointerfaces at external observation and according to users in how there is a management and receiving feedback. For example, the neurointerface of the computer-person allows to carry out rehabilitation and has no hidden mechanisms of management; for example, the bracelet is put on an arm, the computer is connected, and there is a calibration of a control system. Further, the user has to carry out the gripper or programs of a task at the movement by an arm. The computer signals about successful or wrong performance of a task. It is important to notice that in this "simplest" mechanism of the neurointerface a very important technique of a training of muscles is hidden; in particular the people who lost limbs or after a stroke when performing these tasks train not only muscular activity but also cerebrally, sometimes framing new neuronic communications which allow to cope with tasks more effectively. Special case, for example, of the most successful use of the neurointerface of the computer-person is used by his disabled person with amputation—at amputation of a brachium compression of "fist" took about 6 seconds; the patient that considerably complicatedly use it for control of other devices therefore the user thought up new approach and a signal on compression, that is it not compression of a fist, but compression of four fingers, except a thumb. Its execution lasted about 1–1.5 s; as a result the user learned to control an imaginary arm by means of new signals which very quickly became current. It is important to notice that feedback on gripper turns out by means of visual signals and the additional vibromotor in a bracelet, which can react at successful performance of a task. Possesses the similar scheme neurointerface with virtual reality which, in difference from augmented reality, transfers the person completely to the virtual world, but it is important to notice that psychologists long use of virtual reality because of yet not studied injuries which this reality can cause is not recommended. Therefore, all methods of rehabilitation take no

Absolutely, a new principle regarding the neurointerface the hand person—it fundamental difference is especially shown at disabled people for whom the hand fastens to a sleeve and allows to control an arm actively. It is important to note that according to disabled people, it is perfect other perceptions and adaptations, namely, unlike the previous mechanism when there is a special ligament of people computer, in this case there is a communication of people hands

And essentially another from all previous diagrams on neurointerface, is neurointerfaces on control of machines, quadcopters, etc. Their distinctive feature is, first of all, existence of the additional software on reassignment of grippers; for example, movement "turn to the right" is

which frames tactile perception and feelings when performing tasks.

• The neural-control interface of the computer or a mobile application (the person)

• The neural-control interface of the artificial hand (the person)

interfaces, there is a fear, and after time there is adaptability.

• The neural-control interface of other executive mechanism (the person)

mechanism strongly differ has been allocated):

more than 15–30 min, and even it is less.

For example, the girl with amputation of the arm at accident of semiannual prescription, signals are equivalent to signals of the person without loss of a limb, even despite the performed two operations, and arenot comparable with the girl's signals at all with amputation of an arm of 3-year prescription, they after to which loss of a limb established a cosmetic prosthesis. The girl with amputation of semiannual prescription is capable to carry out 8 of 11 grippers of the hand, while the girl from 3-year prescription is capable to execute only 3 grippers taking into account that each user adapts signals for itself, that is, the neural network with the teacher is used and also taking into account that on all grippers the portable electromyograph fixed signals have been in both cases.

Conclusion: after carrying out operations within rehabilitation and the subsequent use to establish to the recommendation immediately bionic artificial limbs as eventually without trainings and also because of psychology of people "experience of management" the hand is lost, and without trainings of the muscle atrophy. However, restoration is possible; alas, it will demand much more time than in cases of immediate prosthetics by bionic/myoelectric artificial limbs.

In the course of the research pattern at the people using myoelectric prostheses and appreciable difference from the framed system on recognition of an EMG on the basis of neural network from eight sensors and more was taped, namely, at amputation of an arm, for example, management of myoelectric prostheses happens at a muscle tension of a biceps and a triceps at amputation of an arm.

The daily training leads to their appreciable development, but in cases when the same people begin to test an innovative control system on recognition of an EMG based on neural network with the teacher of Bi-oN, excellent recognition of signals regarding the turn of the hand has been provided to them. But performance of other grippers is problematic. The similar story at amputation of a hand is slightly higher than a hand at amputation term more than 3 years: management of signals of muscles to which disabled people got used is accurately traced, but at extension of the list of the gripper and a request to involve other muscles, there are problems with management which are surmountable at a training eventually but at the beginning bring difficulties.

It is important to note that the innovation of developments of Bi-oN has allowed to speak about new types of neural-control interface and feedback on the basis of signal EMG (such division as signals which are sent to the executive mechanism which are executed by the mechanism strongly differ has been allocated):


If to compare groups of people with the amputation of arms and different age categories, then the research showed that management does not depend on age in any way, but depends on the term of amputation and existence at the disabled person of a bionic/myoelectric prosthesis during this period. People who right after amputation began to use bionic/myoelectric prostheses or had a possibility of a training of muscles, had better discernible signals on frequency, and better coped with a task of management of a bionic prosthesis based on an EMG. There is an assumption that this feature arises because when the person lost a limb, at it the phantom feeling of an arm continues certain time to be held muscle in remembrance (even taking into account that injuries sometimes happen various and a part of muscles cannot remain or undergo other operations), as well as sometimes. If after that are not carried out a series of actions for maintenance of a muscle tone, then eventually there is a sharp atrophy of muscles

For example, the girl with amputation of the arm at accident of semiannual prescription, signals are equivalent to signals of the person without loss of a limb, even despite the performed two operations, and arenot comparable with the girl's signals at all with amputation of an arm of 3-year prescription, they after to which loss of a limb established a cosmetic prosthesis. The girl with amputation of semiannual prescription is capable to carry out 8 of 11 grippers of the hand, while the girl from 3-year prescription is capable to execute only 3 grippers taking into account that each user adapts signals for itself, that is, the neural network with the teacher is used and also taking into account that on all grippers the portable electro-

Conclusion: after carrying out operations within rehabilitation and the subsequent use to establish to the recommendation immediately bionic artificial limbs as eventually without trainings and also because of psychology of people "experience of management" the hand is lost, and without trainings of the muscle atrophy. However, restoration is possible; alas, it will demand much more time than in cases of immediate prosthetics by bionic/myoelectric artificial limbs.

In the course of the research pattern at the people using myoelectric prostheses and appreciable difference from the framed system on recognition of an EMG on the basis of neural network from eight sensors and more was taped, namely, at amputation of an arm, for example, management of myoelectric prostheses happens at a muscle tension of a biceps and

The daily training leads to their appreciable development, but in cases when the same people begin to test an innovative control system on recognition of an EMG based on neural network with the teacher of Bi-oN, excellent recognition of signals regarding the turn of the hand has been provided to them. But performance of other grippers is problematic. The similar story at amputation of a hand is slightly higher than a hand at amputation term more than 3 years: management of signals of muscles to which disabled people got used is accurately traced, but at extension of the list of the gripper and a request to involve other muscles, there are problems with management which are surmountable at a training eventually but at the beginning bring difficulties.

It is important to note that the innovation of developments of Bi-oN has allowed to speak about new types of neural-control interface and feedback on the basis of signal EMG (such

which is harder and harder for restoring every year.

108 Biofeedback

myograph fixed signals have been in both cases.

a triceps at amputation of an arm.

• The neural-control interface of other executive mechanism (the person)

Moreover, it is important to note that for the first time when people begin to use neural-control interfaces, there is a fear, and after time there is adaptability.

Fundamental difference of the given neurointerfaces at external observation and according to users in how there is a management and receiving feedback. For example, the neurointerface of the computer-person allows to carry out rehabilitation and has no hidden mechanisms of management; for example, the bracelet is put on an arm, the computer is connected, and there is a calibration of a control system. Further, the user has to carry out the gripper or programs of a task at the movement by an arm. The computer signals about successful or wrong performance of a task. It is important to notice that in this "simplest" mechanism of the neurointerface a very important technique of a training of muscles is hidden; in particular the people who lost limbs or after a stroke when performing these tasks train not only muscular activity but also cerebrally, sometimes framing new neuronic communications which allow to cope with tasks more effectively. Special case, for example, of the most successful use of the neurointerface of the computer-person is used by his disabled person with amputation—at amputation of a brachium compression of "fist" took about 6 seconds; the patient that considerably complicatedly use it for control of other devices therefore the user thought up new approach and a signal on compression, that is it not compression of a fist, but compression of four fingers, except a thumb. Its execution lasted about 1–1.5 s; as a result the user learned to control an imaginary arm by means of new signals which very quickly became current. It is important to notice that feedback on gripper turns out by means of visual signals and the additional vibromotor in a bracelet, which can react at successful performance of a task. Possesses the similar scheme neurointerface with virtual reality which, in difference from augmented reality, transfers the person completely to the virtual world, but it is important to notice that psychologists long use of virtual reality because of yet not studied injuries which this reality can cause is not recommended. Therefore, all methods of rehabilitation take no more than 15–30 min, and even it is less.

Absolutely, a new principle regarding the neurointerface the hand person—it fundamental difference is especially shown at disabled people for whom the hand fastens to a sleeve and allows to control an arm actively. It is important to note that according to disabled people, it is perfect other perceptions and adaptations, namely, unlike the previous mechanism when there is a special ligament of people computer, in this case there is a communication of people hands which frames tactile perception and feelings when performing tasks.

And essentially another from all previous diagrams on neurointerface, is neurointerfaces on control of machines, quadcopters, etc. Their distinctive feature is, first of all, existence of the additional software on reassignment of grippers; for example, movement "turn to the right" is transferred "movement of a hand to the right," "fist"—advance, "disclosure of a palm"—a stop, etc. That is, the use of system of reassignment leads to new perceptions and appearance of neural communications. This development is for the present researches and finishing, but in the next year shall be complete and receive practical application on bigger number of users.

and technological (service of the registration of patents, professor Victor Lempitsky from Skoltech, etc.) support of Innovation center "Skolkovo," thanks to whom projects are working.

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

111

[1] Vorotnikov SA, Strunin VS, Vybornov NA. The Biometric Control System of the Artificial

[3] Englehart K, Hudgins B. A robust, real-time control scheme for multifunction myoelectric

[4] Van den Broek EL, Lis'y V, Janssen JH, Westerink JHDM, Schut MH, Tuinenbreijer K. Affective Man–machine Interface: Unveiling Human Emotions through Biosignals. Biomedical Engineering Systems and Technologies: Communications in Computer and

[5] Haziakhmetov MS. Properties of window dispersion of a myogramma as casual process.

[6] Chernyshev AA, Mustetsov NP. Algorithm upravleniyamnogofunktsionalnym hand arti-

[7] Haziakhmetov MSh. Properties of window dispersion of a myogramma as casual process

[9] Ivaniuk N, Ponimash Z, Karimov V. Art of recognition the electromyographic signals for control of the bionic artificial limb of the hand. In: International Conference of Artificial Intelligence, Medical Engineering, Education, AIMEE 2017: Advances in Artificial Systems for Medicine and Education. 2017. pp. 176-181. https://link.springer.com/chapter/

[10] Natallia I, Zahar P, Vladimir K. Control systems of bionic limbs of the new generation. Int Rob Auto J. 2017;3(3):00059. DOI: 10.15406/iratj.2017.03.00059. http://medcraveonline.

[11] Galushkin AI. Synthesis of multi-layer pattern recognition systems. M.: Energy. 1974

Natallia Ivaniuk\*, Zahar Ponimash, Vladimir Karimov and Valentsin Shepanskiy

[2] Nikolaev SG. Electromyography: Clinical practical work. Ivanovo. 2013

Information Science. Berlin, Germany: Springer Verlag; 2010

Systems and Means Inform. 2014;24(3):110-120

[8] https://en.wikipedia.org/wiki/Curse\_of\_dimensionality

10.1007/978-3-319-67349-3\_16

com/IRATJ/IRATJ-03-00059.pdf

control. IEEE Transactions on Biomedical Engineering. 2003;50(7):848-854

\*Address all correspondence to: ivaniuk@bi-on.ru

LLC Bionic Natali/LLC Bi-oN EMG, Moscow, Russia

Author details

References

Limb

ficial limb

#### Videos

There are many videos about research; most of them can be found with the following links:

