# Ophthalmic-microsurgical computer local area network for vitreoretinal operations

FIELD: information technology.

SUBSTANCE: in an ophthalmic-microsurgical computer local area network for vitreoretinal operations, formatting devices are in form of a radial-annular structure consisting of a single set of automated workstations (AWS), which synchronously or asynchronously functioning, processing, converting, transmitting, analysing, synthesising hierarchical structures of an artificial neural network: diagnosis AWS (DAWS), ophthalmic-microsurgical AWS (OMAWS), subsequent operation stages AWS (SOSAWS), component AWS (CAWS), surgeon's operating unit (SOUAWS), with opposite forward and reverse flow of information in between, where each AWS has at least one neural circuit, interconnected identification units (IU), an interpolation unit (INU), an extrapolation unit (EU), which are the neural network converting and transmitting elements (NNCTE), a decision unit (DU), which is the neural network analysis and synthesis element (NNASE).

EFFECT: simultaneous improvement of accuracy of determination and quality of identifying diagnoses, determining indications for conducting operations, high selectivity when conducting operations, accuracy in determining the sequence of operations, simulating operations, accuracy in choosing the anaesthetic method, accuracy of providing implants and expendable materials, optimisation of flow of information and necessities during vitreoretinal ophthalmic-microsurgical operations.

1 dwg

The invention relates to the field of computer networks.

The known device sharing, management and transfer of information over a computer network according to the patent of Russian Federation №2272316.

Device for transmitting information, comprising: formatting means for formatting the document in the code to represent the information contained in the document mentioned above, a predetermined image on a network device; compiling means for compiling the mentioned code in the file of compiled code, so that a necessary element for creating or invoking a first application to view the above document and/or for creating or invoking a second application provided with the said document included in said compiled code; distributing means for distributing the mentioned file on a computer network or unloading of the mentioned file on the server, or by providing the mentioned file as available through the transfer network with peers; forwarding means for forwarding referred to the compiled code of the mentioned file on the distribution channel to view the above document at the above-mentioned network device, and when receiving the aforementioned compiled code mentioned on the distribution channel is referred to the very basic element creates or causes mentioned first app to view the above document mentioned in advance in a certain way and/or creates or causes mentioned second application for submission with the above-mentioned document.

However, this device has significant drawbacks: it does not provide simultaneous improvement of the accuracy in the determination of the diagnosis, the quality of identification of diagnosis, determination of the indications for operations, improving selectivity in operation, accuracy in the determination of the sequence of operations, engineering operations, the accuracy in the choice of anesthesia, accuracy provide implants and consumables, ensuring optimization of information flow in the production of vitreoretinal oftalmohirurgicheskih operations.

The technical result - increase the detection accuracy and the quality of identification of diagnoses, determine the indications for performing operations, improving selectivity in operation, accuracy in the determination of the sequence of operations, modeling, operations, precision in the choice of anesthesia, accuracy, providing implants and consumables, ensuring optimization of information flows and needs in the production of vitreoretinal oftalmohirurgicheskih operations.

The technical result is achieved by the fact that in the local computer ophthalmoscopically network vitreoretinal operations containing formatrule the device, the formatting device made in the form of radial-ring structure consisting of one complex automated workplaces (AWP), which synchronously and asynchronously functioning, processing, transforming, transmitting, analyzing, synthesizing hierarchical structures of artificial neural networks: AWS diagnostics (ARMD), the arm ofthalmohirurgii (ARMH), AWS subsequent phases of the operation (AREEO), workstation components (ARMC), AWS surgical operating unit (ARMCO), colliding with the forward and reverse flows of information dissemination between them, and each arm includes at least one neural chain connected between a block identification (BI), block interpolation (BIN), block extrapolation (EB), which is transforming and transmitting elements of a neural network (PANS), block a decision (BPR), which is the element of analysis and synthesis of neural network (ACLS), while in the direct flow information:

the first information output of each diagnostic workstation is connected to the first information input of each ARMH;

the first information output of each ARMH associated with the first information input of each of ARNAO;

the first information output of each of ARNAO associated with the first information input ARMS and ARMCO;

the first information output ka is Dogo ARMS associated with the second information input ARMH;

the second information output of each ARMH associated with the second information input ARMCO;

and:

each ARMH contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when performing vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack of/excess plugging substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses tactics of surgical treatment, in the form of deterministic finite state machine (DKA), containing the m at least four of not less than forty possible States, having at the output of one solution of at least eight possible variants;

each of ARMD contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK to clarify values FOOK and diagnosis and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses after production vitreoretinal operations, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses, indications for vitreoretinal operations, in the form of deterministic finite state machine (DKA), containing at least eight of not less than forty-eight possible States, having at the output of the od is about the solution, at least four possible;

each ARNAO contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when performing vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack of/excess plugging substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses, the appropriateness of subsequent stages of treatment, in the form of deterministic finite state machine (DKA), containing at least eight of n is less than forty-eight possible States, with the output of one solution of at least five possible options;

each ARMC contains the first BEE that produces identification by scanning the many possible variants of the operation, determine a subset of the possible variants of the operation and selection of one or more combinations of the combinatorial selection of personalized FOOK codes operating parameters of the eye, codes companiesa substances and consumables and directs this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis for subsequent vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies facing for the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of subsequent vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK healthy lifestyles which is the first of BPR on the required plugging and other components of the operation, in particular, in the form of DKA, containing at least four of not less than sixty possible States, having at the output of one solution of at least four possible;

each ARMCO contains the first BEE that produces identification by scanning a set of possible oftalmohirurgicheskih operations, define a subset of the possible oftalmohirurgicheskih operations and the selection of one or more combinations of operations of the combinatorial selection of personalized FOOK, code of the planned operation, the code of the operating surgeon, the date of the planned operation, code operating room and directs this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when planning vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses when planning vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of consequences is not the balance/excess plugging substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR about the necessary technical, anesthesia, Executive providing operations, in the form of DKA, containing at least four of not less than forty possible States, having at the output of one solution of at least eight possible variants;

while all counter flow direct primary and reverse lookup information dissemination form a single multigraph with no less than fourteen vertices consisting of a workstation, each of which is equipped with at least three elements PANS and one element ACLS, functioning in parallel, synchronously, with the possibility of increasing patterns and functional relationships that are connected to not less than ninety-six oriented edges.

Claimed by the authors of the unified set of essential distinguishing features is necessary and sufficient for an unambiguous positive achievements of the claimed technical result.

The invention is illustrated in the drawing.

The drawing is a diagram of a local computer ophthalmoscopically network vitreoretinal operations.

In the drawing:

1-4 - arm diagnostic (ARMD);

5-8 arm of ofthalmohirurgii (ARMH);

9-12 - arm the subsequent stage is in operation (AREEO);

13 - workstation components (ARMC);

14 - arm surgical operating unit (ARMCO).

Proposed local computer oftalmologica network vitreoretinal surgeries performed, and operates as follows.

The drawing shows the minimum possible variant structure.

The network contains formatting the device. The formatting device made in the form of radial-ring structure of the artificial neural network (NA).

The graph structure of the network in which the vertices of the graph - arm, and the edges represent communication between the workstation is radial, as part of the data transferred some of the many AWS, Roundstone for others.

The graph structure of the network in which the vertices of the graph - arm, and the edges represent communication between the workstation is circular, as part of the data is transferred from one workstation from a set to another, from this to the third arm and so on.

Under artificial neural network refers to hardware and software implementation of a computer network built on mathematical models of the functioning of biological neural networks.

The structure of the local computer ophthalmoscopically operating network consists of a single aggregate workstations (AWS): AWS diagnostic workstation of ofthalmohirurgii, AWS subsequent phases of operations, workstation components, And The M surgical operating unit (see the drawing).

Arm exchange between opposing forward and reverse flows of information dissemination, which multigraph.

Under direct main flows of information dissemination refers to the transfer of such information, which must be received from the sending workstation (or any other) host workstation to ensure it functions.

Under reverse lookup flows of information dissemination refers to the transfer of such information, which is transmitted to the initiating host workstation, in particular, confirmation of receipt or peristernia parameter, or initiate the sending workstation, in particular the correction of erroneously transmitted parameter is first a transfer request, then receive confirmation and, finally, the transfer of fixed information, which increases the adequacy of the submitted information, and without which the transmitted information may be misrepresented in the production technology oftalmohirurgicheskih operations.

Each arm contains at least one neural chain of interconnected blocks identify BI, blocks interpolation BIN, blocks extrapolation EB, block decision BPR.

BI is used to identify the parameters.

Identification is the establishment of the identity of the incoming person tirovannyh FOOK each patient taking into account the totality of the personalized settings of the eyes of the system of internal parameters of the workstation.

Each arm of ofthalmohirurgii contains the first identification block (BI) diagnostic parameters of the eye, which is transforming and transmitting neural network element (PANS). He identifies by scanning the many possible oftalmohirurgicheskih diagnoses, determine the subset oftalmohirurgicheskih diagnoses and selection of one or more combinations of diagnoses of combinatorial sample personalized formatted control codes (FOOK) isometrie, autorefractometry, autokeratometry, biometrics, ceratopogonidae, thresholds lability, electroacoustically, electrophysiological evoked potentials, ophthalmoscopically, Doppler.

Such method of identification of diagnoses due to the fact that one clinical case, representing the eye of a patient, may be from one to several necessary concomitant diagnoses (depending on the pathological condition of the eye). In the international classification of diseases tenth revision (MCB) to diseases of the eye is about four hundred titles. To ensure the annual mass reproduction of high-tech oftalmohirurgicheskih operations this list is expanded. Taking into account comorbidities list of diagnoses which leaves about six items. As definitely put exactly one diagnosis on a certain set of diagnostic studies may rarely advisable to choose the diagnoses and their combinations, by ranking them according to frequency of occurrence with the given set of results of diagnostic studies (if necessary, additional studies) among all possible diagnoses and their combinations based on possible combinations of results of diagnostic tests. In practice, there are combinations of two to six diagnoses. In General pathological conditions of the eye at some point in time the diagnosis is a vector whose components represent the main diagnosis that determines what disease should be treated associated with one or a few, if any, concomitant and secondary diagnoses. Further, the thread FOOK goes in the BIN.

BIN is designed for the interpolation parameters. Under the interpolation is a way of finding intermediate values according to the available discrete set of measured values. In block BIN interpolate certain functional dependence for intermediate values FOOK. Interpolation is piecewise linear, polynomial, and for values FOOK focused on local areas, the spline interpolation. N is each iteration of the processing flow FOOK is determined by the Lebesgue constant, characterize the accuracy of the interpolation. Intermediate values FOOK used for diagnosis when performing vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of cementing substances.

All BEAN, described in this invention, is constructed similarly.

BAE is intended for extrapolation parameters. Under extrapolation refers to the distribution established in the past trends for the future (extrapolation in time) or the distribution of sample data to another part of the population not subjected to observation (extrapolation in space). EB is used for handling the FOOK for all possible values in the physiological range, including outside the measured values. Extrapolated values FOOK are used to determine the possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors. All BAE, described in this invention, is constructed similarly. BPR is made in the form of a deterministic finite state machine (DKA) with a certain number of possible States, with input coming FOOK and having output one solution and is a number of possible solutions.

DKA constructed in accordance with the structural description: B=(Q1, S1, D1, q01, F1) and consists of the following components: Q1 - many States; S1 is the set of input symbols; D1 is the transition function, the arguments of which are the current state q and input symbol a, and the value is the new state p from the set Q1:p=D1(q, a); q0 is the initial state, which is an element of the set Q1; F1 - the set of final States, which is a subset of the set Q1; BPR B1 yields one the solution of the possible solutions formed by many L1 (B1) words of the output language of DKA is defined using DD - enhanced navigation features, which puts in correspondence to the state q and the chain of input symbols w=(a1, a2, ..., ak) condition p: p=DD(q, w)=D(D(D(...D(D(D(q, a1), a2), a3), ...), ak), which will come DKA after performing k cycles of the processing chain input characters w of length k; L (B) - the language of DKA is defined by the formula: L (B)={the set of words w such that DD(q0, w) belongs to the set F}.

All BPR described in this invention, is constructed similarly.

In the direct flow of information (in the drawing)

the first information output of each of ARMD (1-4) connected to the first information input of each ARMH (5-8);

the first information output of each ARMH (5-8) is associated with the first information input of each of ARNAO (9-12);

the first information output of each of ARNAO associated sparvieri information inputs ARMS (19) and ARMCO (14);

the first information output of each ARMS (19) associated with the second information input ARMH (5-8);

the second information output of each ARMH (5-8) is associated with the second information input ARMCO (14).

Each ARMH (5-8) contains the first BI diagnostic parameters of the eye, which makes identification by scanning a set of possible oftalmohirurgicheskih diagnoses, determine the subset oftalmohirurgicheskih diagnoses and selection of one or more combinations of diagnoses of combinatorial sample personalized formatted control codes (FOOK) isometrie, autorefractometry, autokeratometry, biometrics, ceratopogonidae, thresholds lability, electroacoustically, electrophysiological evoked potentials, ophthalmoscopically, Doppler and directs this personalized information in the first BIN.

Each ARMH (5-8) first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when performing vitreoretinal operations, estimates of the volume of cementing substances, definition of the term Zam is by plugging substances and other PHUC; further, the thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses tactics of surgical treatment, in the form of deterministic finite state machine (DKA), containing at least four of not less than forty possible States, having at the output of one solution of at least eight possible options.

Each ARNAO (9-12) contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when performing vitreoretinal operations, estimates of the volume of cementing substances, defined what I term replacement plugging substances and other PHUC; further, the thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses, the appropriateness of subsequent stages of treatment, in the form of deterministic finite state machine (DKA), containing at least eight of not less than forty-eight possible States, having at the output of one solution of at least five possible options.

Each ARMS (13) contains the first BEE that produces identification by scanning the many possible variants of the operation, determine a subset of the possible variants of the operation and selection of one or more combinations of the combinatorial selection of personalized FOOK codes operating parameters of the eye, codes plugging substances and consumables and directs this personified the second information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis for subsequent vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of subsequent vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR about the required plugging and other components of the operation, in particular in the form of DKA, containing at least four of not less than sixty possible States, having at the output of one solution of at least four possible options.

Each ARMCO (14) contains the first BEE that produces identification by scanning a set of possible oftalmohirurgicheskih operations, define a subset of the possible oftalmohirurgicheskih operations and the selection of one or more combinations of operations of the combinatorial selection of personalized FOOK, code of the planned operation, the code of the operating surgeon, the date of the planned operation to the operating room and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when planning vitreoretinal operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses when planning vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR about the necessary technical, anesthesia, Executive providing operations, in the form of DKA, containing at least four of not less than forty possible States, having at the output of one solution of at least eight possible options.

All counter flow direct primary and reverse lookup information dissemination form a single multigraph with no less than thirteen peaks, consisting of a workstation operating in parallel, synchronously, with the possibility of increasing patterns and functional relationships that are connected to not less than ninety-six oriented edges.

All AWS operate in parallel, simultaneously, with Chrono, forming artificial NS.

NA represents the structure of the interacting AWS, is a network of counter-information dissemination. The national Assembly has the topology of a network with a large number of inputs and outputs and is a network with a uniform hierarchical access to information flows. NA is the structure of pattern recognition (diagnoses, operations, design vitreoretinal oftalmohirurgicheskih operations, ensuring vitreoretinal oftalmohirurgicheskih operations, anesthesia) and appropriate-motivated decisions.

Proposed local computer oftalmologica operating network vitreoretinal operations has the possibility of increasing the selectivity, namely, conducting targeted, specific research and treatment of narrow specialists vitreoretinal ofthalmohirurgii. This is essential in large multidisciplinary specialized oftalmohirurgicheskih institutions. In such clinics exist diagnostic and oftalmologica equipment and highly qualified professionals, specializing in particular in the field of vitreoretinal surgery. Improving the selectivity improves the quality of treatment is to reduce the number of complications, to increase capacity and improve productivity.

A single set of essential characteristics of the invention is necessary and sufficient for an unambiguous positive solution to the stated technical problem is to simultaneously improve the detection accuracy and the quality of identification of diagnoses, determine the indications for vitreoretinal operations, improve selectivity when performing vitreoretinal surgery, the accuracy in the determination of the sequence of vitreoretinal operations, modeling vitreoretinal operations, the accuracy in the choice of anesthesia, accuracy, providing implants and consumables.

Local computer oftalmologica network vitreoretinal operations that contains the formatting device, characterized in that the formatting device made in the form of radial-ring structure consisting of one complex automated workplaces (AWP), which synchronously and asynchronously functioning, processing, transforming, transmitting, analyzing, synthesizing hierarchical structures of artificial neural networks: AWS diagnostics (ARMD), the arm ofthalmohirurgii (ARMH), AWS subsequent phases of the operation (AREEO), AWS complement what their (ARMC),
AWS surgical operating unit (ARMCO), colliding with the forward and reverse flows of information dissemination between them, and each arm includes at least one neural chain of interconnected blocks identification (BI), interpolation blocks (BIN), blocks extrapolation (EB), which is transforming and transmitting elements of a neural network (PANS), block a decision (BPR), which is the element of analysis and synthesis of neural network (ACLS), while in the direct flow information:

the first information output of each diagnostic workstation is connected to the first information input of each ARMH;

the first information output of each ARMH associated with the first information input of each of ARNAO;

the first information output of each of ARNAO associated with the first information input ARMS and ARMCO;

the first information output of each ARMS associated with the second information input ARMH;

the second information output of each ARMH associated with the second information input ARMCO;

and:

each ARMH contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FU is to clarify the diagnosis when performing vitreoretinal operations,
estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses tactics of surgical treatment, in the form of deterministic finite state machine (DKA)containing at least four of not less than forty possible States, having at the output of one solution of at least eight possible variants;

each of ARMD contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK to Refine the values of the criminal code and diagnosis and other PHUC;
further, the thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses after production vitreoretinal operations, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses, indications for vitreoretinal operations, in the form of deterministic finite state machine (DKA), containing at least eight of not less than forty-eight possible States with the output one solution of at least four possible options;

each ARNAO contains the first BI diagnostic parameters of the eye, which identifies personalized formatted control codes (FOOK) and sends this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when performing vitreoretinal operations, estimates of the volume of cementing substances, replacement timing t is nonaroused substances and other PHUC;
further, the thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR, producing identification of pathological conditions of the patient's eye vectors diagnoses, the appropriateness of subsequent stages of treatment, in the form of deterministic finite state machine (DKA), containing at least eight of not less than forty-eight possible States, having at the output of one solution of at least five possible options;

each ARMC contains the first BEE that produces identification by scanning the many possible variants of the operation, determine a subset of the possible variants of the operation and selection of one or more combinations of the combinatorial selection of personalized FOOK codes operating parameters of the eye, codes plugging substances and consumables and directs this personified and the formation in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis for subsequent vitreoretinal operations,
estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses in the production of subsequent vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR about the required plugging and other components of the operation, in particular in the form of DKA, containing at least four of not less than sixty possible States, having at the output of one solution of at least four possible options;

each ARMCO contains the first BEE that produces identification by scanning a set of possible oftalmohirurgicheskih operations, define a subset of the possible oftalmohirurgicheskih operations and the selection of one or more combinations of operations of the combinatorial selection of personalized FOOK, code of the planned operation, the code of the operating surgeon, the date of the planned operation, the code is personnage hall and directs this personalized information in the first BIN for the interpolation of certain functional dependencies intermediate values FOOK for further diagnosis when planning vitreoretinal
operations, estimates of the volume of cementing substances, the replacement timing of plugging substances and other PHUC; next thread FOOK is routed to the first EB for recursive processing, smoothing, extrapolation of certain functional dependencies beyond the analyzed interval of values FOOK in the physiological range for specification of possible diagnoses when planning vitreoretinal operations, taking into account the inaccuracy of measurements, evaluation of the impact of lack/excess of cementing substances, evaluation of refractive indices in intraocular correction of refractive errors; further, the thread FOOK is sent in the first BPR about the necessary technical, anesthesia, Executive ensuring operation in the form of DKA, containing at least four of not less than forty possible States, having at the output of one solution of at least eight possible variants;

while all counter flow direct primary and reverse lookup information dissemination form a single multigraph with no less than fourteen vertices consisting of a workstation, each of which is equipped with at least three elements PANS and one element ACLS, functioning in parallel, synchronously, with the possibility of increasing patterns and functional relationships that are connected with not less than d is Venosta six oriented edges.

**Same patents:**

FIELD: physics.

SUBSTANCE: neuron simulation method is based on calculation of squares of Euclidean distance from the input vector to each of 2^{n} vertices of a unit n-dimensional cube in weighting units, and multiplication of values inverse to these distance values with components of the target vector respectively, and then summation in an adder and conversion in the activation unit through an activation function.

EFFECT: possibility of simulating a neuron of any given Boolean function from a complete set of from n variables.

6 dwg, 1 tbl

FIELD: information technology.

SUBSTANCE: multilayer modular computer system has several layers, including a neural network layer, a transport layer and a processor layer, wherein the transport layer contains network controller-router modules, the processor layer contains processor modules, and all the said modules have multiple inputs and outputs connected to each other and connected to the inputs and outputs of the system. The processor modules train neural network domain modules.

EFFECT: high decision speed, possibility of grafting layers and modules in each layer during operation of the system with a complex task, high reliability of the computer system.

3 cl, 1 dwg

FIELD: information technologies.

SUBSTANCE: invention may be used for building of modular neural computers, which function in symmetrical system of residual classes. Stated neuron network comprises unit of neuron network of end ring of senior coefficient generation for generalised positional system of numeration, unit of polarity shift, unit of error detection, buses "with errors" and "without errors".

EFFECT: reduced hardware complexity.

3 dwg

FIELD: physics; computer engineering.

SUBSTANCE: present invention pertains to neurocomputers. The device has a unit for storing a binary input signal, a logic AND-OR circuit, internal memory unit, unit for generating the output string of codes, a generator of synchronising pulses, control unit, a unit for selecting duration and extracting information, analysis block and a corrector unit.

EFFECT: increased rate of operation, providing for the possibility of distinguishing change in state of processed signals, increased noise immunity, possibility of making super-complex neural networks, and simplification of design.

9 cl, 1 dwg

FIELD: modular neuro-computing systems.

SUBSTANCE: neuron network contains input layer of neurons, at inputs of which residuals of number being divided are received through system of modules, (n-1) neuron networks of finite ring for addition, (n-1) neuron networks of finite ring for multiplication, neuron network for expanding a tuple of numerical system of residues, and as output of neuron network for dividing numbers represented in system of residual classes are outputs of neuron network of finite ring for multiplication and output of neuron network for expansion of tuple of numerical system of residues.

EFFECT: expanded functional capabilities, increased speed of division, reduced volume of equipment.

1 dwg

FIELD: neuron-like computing structures, possible use as processor for high speed computer systems.

SUBSTANCE: device contains artificial neuron network composed of analog neurons, at least one controllable voltage block, a group of long neuron-like nonlinear communication units, each one of which contains serially connected circuit for synchronization and selection of radio impulse envelope, auto-generator with self-suppression circuit, a length of coaxial line, realizing functions of antenna, additional circuit for synchronization and selection of radio-impulse envelope.

EFFECT: increased information processing speed due to increased paralleling degree of computing processes.

2 dwg

FIELD: neuro-cybernetics, possible use in artificial neuron networks for solving various problems of logical processing of binary data.

SUBSTANCE: method for realization of logical nonequivalence function by neuron with two inputs is based on multiplication of input signals with corresponding weight coefficients and summing them, after that the total is transformed in activation block firstly by quadratic transfer function, and then by threshold function at neuron output.

EFFECT: realization by one neuron of first order of logical nonequivalence function of two variables.

5 dwg, 1 tbl

FIELD: computer engineering, possible use in modular neuro-computer systems.

SUBSTANCE: in accordance to invention, neuron network contains input layer, neuron nets of finite ring for determining errors syndrome, memory block for storing constants, neuron nets for computing correct result and OR element for determining whether an error is present.

EFFECT: increased error correction speed, decreased amount of equipment, expanded functional capabilities.

1 dwg, 3 tbl

FIELD: cybernetics, possible use as a cell for neuron networks.

SUBSTANCE: neuron-like element may be used for realization on its basis of neuron network for solving problems of estimation of functioning of complicated open systems, estimation of degree of optimality of various solutions by ensuring possible construction of model of researched system, both hierarchical and recurrent, with consideration of varying original and working condition of its elements and variants of their functioning, during modeling taking into consideration the level of self-sufficiency of neuron-like elements, susceptibility to effect of external signals, type and errors of setting of their parameters and parameters of input signals, and also provision of given precision of self-teaching of neuron network. Device contains input block, block for setting and normalizing weight coefficients, block for computing parameters of input signals, adder, signals share limiter, block for computing input part of condition, block for setting internal state, block for computing internal part of distance, block for counting distance, memory block, analyzer of state change value, block for determining precision of self-teaching of neuron network, block of determined dependencies, switch, output block, control block, random numbers generator.

EFFECT: creation of neuron-like element.

2 cl, 1 dwg

FIELD: cybernetics, possible use as a cell for neuron networks.

SUBSTANCE: neuron-like element may be used for realization on its basis of neuron network for solving problems of estimation of functioning of complicated open systems, estimation of degree of optimality of various solutions by ensuring possible construction of model of researched system, both hierarchical and recurrent, with consideration of varying original and working condition of its elements and variants of their functioning, during modeling taking into consideration the level of self-sufficiency of neuron-like elements, susceptibility to effect of external signals, type and errors of setting of their parameters and parameters of input signals, and also provision of given precision of self-teaching of neuron network. Device contains input block, block for setting and normalizing weight coefficients, block for computing parameters of input signals, adder, signals share limiter, block for computing input part of condition, block for setting internal state, block for computing internal part of distance, block for counting distance, memory block, analyzer of state change value, block for determining precision of self-teaching of neuron network, block of determined dependencies, switch, output block, control block, random numbers generator.

EFFECT: creation of neuron-like element.

2 cl, 1 dwg

FIELD: computer engineering, possible use in modular neuro-computer systems.

SUBSTANCE: in accordance to invention, neuron network contains input layer, neuron nets of finite ring for determining errors syndrome, memory block for storing constants, neuron nets for computing correct result and OR element for determining whether an error is present.

EFFECT: increased error correction speed, decreased amount of equipment, expanded functional capabilities.

1 dwg, 3 tbl

FIELD: neuro-cybernetics, possible use in artificial neuron networks for solving various problems of logical processing of binary data.

SUBSTANCE: method for realization of logical nonequivalence function by neuron with two inputs is based on multiplication of input signals with corresponding weight coefficients and summing them, after that the total is transformed in activation block firstly by quadratic transfer function, and then by threshold function at neuron output.

EFFECT: realization by one neuron of first order of logical nonequivalence function of two variables.

5 dwg, 1 tbl

FIELD: neuron-like computing structures, possible use as processor for high speed computer systems.

SUBSTANCE: device contains artificial neuron network composed of analog neurons, at least one controllable voltage block, a group of long neuron-like nonlinear communication units, each one of which contains serially connected circuit for synchronization and selection of radio impulse envelope, auto-generator with self-suppression circuit, a length of coaxial line, realizing functions of antenna, additional circuit for synchronization and selection of radio-impulse envelope.

EFFECT: increased information processing speed due to increased paralleling degree of computing processes.

2 dwg

FIELD: modular neuro-computing systems.

SUBSTANCE: neuron network contains input layer of neurons, at inputs of which residuals of number being divided are received through system of modules, (n-1) neuron networks of finite ring for addition, (n-1) neuron networks of finite ring for multiplication, neuron network for expanding a tuple of numerical system of residues, and as output of neuron network for dividing numbers represented in system of residual classes are outputs of neuron network of finite ring for multiplication and output of neuron network for expansion of tuple of numerical system of residues.

EFFECT: expanded functional capabilities, increased speed of division, reduced volume of equipment.

1 dwg

FIELD: physics; computer engineering.

SUBSTANCE: present invention pertains to neurocomputers. The device has a unit for storing a binary input signal, a logic AND-OR circuit, internal memory unit, unit for generating the output string of codes, a generator of synchronising pulses, control unit, a unit for selecting duration and extracting information, analysis block and a corrector unit.

EFFECT: increased rate of operation, providing for the possibility of distinguishing change in state of processed signals, increased noise immunity, possibility of making super-complex neural networks, and simplification of design.

9 cl, 1 dwg

FIELD: information technologies.

SUBSTANCE: invention may be used for building of modular neural computers, which function in symmetrical system of residual classes. Stated neuron network comprises unit of neuron network of end ring of senior coefficient generation for generalised positional system of numeration, unit of polarity shift, unit of error detection, buses "with errors" and "without errors".

EFFECT: reduced hardware complexity.

3 dwg

FIELD: information technology.

SUBSTANCE: multilayer modular computer system has several layers, including a neural network layer, a transport layer and a processor layer, wherein the transport layer contains network controller-router modules, the processor layer contains processor modules, and all the said modules have multiple inputs and outputs connected to each other and connected to the inputs and outputs of the system. The processor modules train neural network domain modules.

EFFECT: high decision speed, possibility of grafting layers and modules in each layer during operation of the system with a complex task, high reliability of the computer system.

3 cl, 1 dwg

FIELD: physics.

SUBSTANCE: neuron simulation method is based on calculation of squares of Euclidean distance from the input vector to each of 2^{n} vertices of a unit n-dimensional cube in weighting units, and multiplication of values inverse to these distance values with components of the target vector respectively, and then summation in an adder and conversion in the activation unit through an activation function.

EFFECT: possibility of simulating a neuron of any given Boolean function from a complete set of from n variables.

6 dwg, 1 tbl

FIELD: information technology.

SUBSTANCE: in an ophthalmic-microsurgical computer local area network for vitreoretinal operations, formatting devices are in form of a radial-annular structure consisting of a single set of automated workstations (AWS), which synchronously or asynchronously functioning, processing, converting, transmitting, analysing, synthesising hierarchical structures of an artificial neural network: diagnosis AWS (DAWS), ophthalmic-microsurgical AWS (OMAWS), subsequent operation stages AWS (SOSAWS), component AWS (CAWS), surgeon's operating unit (SOUAWS), with opposite forward and reverse flow of information in between, where each AWS has at least one neural circuit, interconnected identification units (IU), an interpolation unit (INU), an extrapolation unit (EU), which are the neural network converting and transmitting elements (NNCTE), a decision unit (DU), which is the neural network analysis and synthesis element (NNASE).

EFFECT: simultaneous improvement of accuracy of determination and quality of identifying diagnoses, determining indications for conducting operations, high selectivity when conducting operations, accuracy in determining the sequence of operations, simulating operations, accuracy in choosing the anaesthetic method, accuracy of providing implants and expendable materials, optimisation of flow of information and necessities during vitreoretinal ophthalmic-microsurgical operations.

1 dwg