+7 (495) 987 43 74 ext. 3304
Join us -              
Рус   |   Eng

Authors

Lavrenkov Y.

Degree
PhD in Technique, Kaluga Branch of the Bauman Moscow State Technical University
E-mail
georglawr@yandex.ru
Location
Kaluga
Articles

Using neural associative machines to detect intrusion into local networks

A MLP based algorithm for combining expert opinions using algorithmic composition with a dynamic mechanism to assess the coefficient of confidence in each expert is suggested. In order to increase the effectiveness of the experts the possibility of modifying the standard gradient algorithms learning methods based on the use of combined heuristics as well using experts in the Intrusion Detection System in the network is discussed.

Read more...

Adaptive digital data flows router based on fuzzy neural network approach

We consider the combined algorithm for radial basis neural network parameters selection based on fuzzy immune optimization algorithm. Evolutional construction of antibodies and the use of fuzzy adaptive resonance neural network are used to adapt the neural controller learning algorithm for solving the optimization problem. The possibility of using this kind of neural networks to construct an adaptive network information router and ensuring the integrity of its structure from the targeted destruction is considered.
Read more...

Analysis of the data transmission channel characteristics using neural network

The article describes a hybrid algorithm of neural network settings using sigma-pi neurons concept. Core of the learning algorithm is a combination of random search algorithms and heuristic algorithms. The process of heuristic algorithm control based on an oscillating neural network is considered. An integrated approach to neural networks training based on sigma-pi neurons allows them to perform training for the time required to adjust the neural network to problems solving. The possibility of using sigma-pi network to estimate the parameters of data transmission channel security based on the analysis of the reflected signal-probing spectrum is discussed. To form the training and test sample network a wireline analysing device was developed.
Read more...

Security of information transmission over wireless communication channels based on neural network modules

The article refers to the possibility of using neural network security methods of digital transmission in wireless networks. Analyzed the organization of information transfer and synchronization signals by two groups of transmitters operating in different frequency ranges. Organization of the system involves the transfer of synchronization signals by a group of transmitters with the same characteristics, but located at certain points in space. As a result, the correct information sequences can be accepted only if you know the area of the intersection of coverage zones of all clock transmitters. For protection of the transmitted information, it is proposed to use two neural network structures. The first neural network is constructed of two modified dynamic neural modules and a neuron with excitatory- inhibition dynamics. Its main purpose is to produce a background of the information signal, which is applied to conceal the information transmission, and also does not allow to determine activity times of transmitting stations. A modified Hungarian algorithm was used to configure the neural network and identify entry points of feedback signals was used. The second neural network structure consist of a dynamic digital neuron. One of the structures of a neuron is a block of memory, the content of its cells completely determines the dynamics of the development of states of the neuron. Its primary purpose is to generate a unique signal to synchronize the whole wireless network. Configuring of the neuron was carried out using a random search algorithm with self-learning. The main purpose of the algorithm was to initialize the memory block of a neural element. The joint functioning of the two developed neural network structures can protect the transmitted information without using of scrambling methods.
Read more...

Synchronization of communication nodes of the communication network on the basis of neural metanet

The complexity of synchronizing local timers on individual nodes of the communication network is to assess the time needed for an information message with current time stamp for transporting from the source to the target node. Transportation time depends on the state of information transmission channels and routing protocols. To estimate the time advance of the package with time stamp it is proposed to use a distributed neural network architecture, which contains a delay line with taps, which changes the information part of the temporary package during its movement through the communication network. To perform time correction at the delivery of the packet to the target node of the neural network expert that has the ability to increase the complexity of the internal architecture without loss of stability of functioning of the cascade-correlation neural network. The learning procedure consists in tuning only added neuroelements, which makes it possible to increase the speed of operation of the system as a whole. To improve the efficiency of the entire system has been used a method for compressing data information part of the temporary package with the use of neural network built on neuroelement made to a summing integrator with losses on the scheme with switching capacitors. A complex of two trigonometric neural networks performs data compression by considering the most significant characteristics of the analyzed signal combinations. Analysis of process of functioning of the cascade-correlation neural network showed the ability to perform correction of timers located in the network nodes. Evaluation of the averaged dynamics of change of the error counts time in units of the communication network proved the effectiveness of the proposed synchronization approach.
Read more...

Adaptive control of frequency efficient data transmission system based on the neural network with optically-coupled elements

The transmission of data in multichannel systems with many carriers is implemented in order to increase the reliability of delivery of data messages. The article is dedicated to the solution of problem of optimal use of the available frequency band (limitations on power capability of the transmitter and complexity of the receiver should be taken into account). The construction of the adaptive system, which can be used for the determination of optimal set of frequencies for data distribution, requires the usage of cellular neural networks. These networks can be used for the analysis of signal environment and selection of set of carrier frequencies. Characteristics of cellular networks correspond to principles of fast tunable transformations, which can be effectively implemented at the hardware level. The reduction of the number of synaptic connections increases the computational efficiency and makes it possible to use such networks for processing of high-dimensional data. The article considers the structural synthesis of the cellular network, which has optical connections between neurons and has a high efficiency in data processing. The proposed connections can be used as a basis for the construction of modular intellectual structures, which consist of homogeneous fragments. The neural network learning is implemented with the help of methods of local learning (with elements of the swarm intelligence). The presence of 32‑bit microcontroller in every neuron core justifies the use of this strategy (despite high memory requirements). The proposed modular structure effectively combines the local learning of neural structures and global learning of the whole network. The evaluation of the obtained set of frequencies at specific moments of time proved the effectiveness of the use of reconfigurable cellular neural networks. The structure of such network can be optimized for a specific computational task. The unitization of the structure allows you to simultaneously construct a large number of networks. Such approach makes it possible to form a large number of carriers within the predefined frequency band.
Read more...

Optimal redistribution of radio frequencies based on reverberative spiking neuron networks interacted with communication electronics

The article deals with application of spiking neural network for solving the problem of optimal frequency redistribution within the group of wireless communication systems. Large number of communication electronics and complicated methods of their interacting to jointly operate cause the complexity of the optimal frequency distribution. Solving this problem using Monte Carlo methods and global search algorithms leads to the elaboration of many possible frequency assignment options. When designing the algorithms for operational frequency readjustment, it is necessary to take into account both intermodulation effects and group interference effects. Multilayer neural network is composed of spiking neural elements, which architecture is based on interacting reverberative loops. Examined electro- optic commutation system is the base for architecting of communication system between neurons, enabling mixing of neural element signals. Application of optical communication and liquid crystal modulators simplifies the signal propagation process to multitude of neurons and chaning of its settings, enabling data processing not only in neurons, but also in pulse transmission systems. The optical switching system is used not only as a communication system, but also as snooping mechanism for neural network rhythmicity changes. Application of electrochemical analog integrating element enables to acquire data about activity of neuronal groups over a long time interval. Obtained activity values are used to improve the efficiency of applied learning algorithm. Data are encoded into spike pulse sequences within groups of 5 neurons based on pulsed phase modulation. This enables to adapt the learning algorithm for networking within the set of interacting neural populations. Designed neural network structure is used to solve the task of frequency dynamic assigning and defining the transmitter activity intervals under changable electromagnetic environment.
Read more...

Management of a multi-position system for identifying elements of adaptive transmitters based on hybrid data integration by a heterogeneous neural network

The article discusses the design of a neural network system to determine the position of a source of information signals. Determining the coordinates of an unknown source is an important procedure in improving the efficiency of wireless electronic communications systems. Solving the problem requires overcoming a number of difficulties associated with the optimal reception of signals from sources, placement of elements of information transmission systems, and relative complexity of the meter, which includes means for converting incoming signals. The method of information processing is based on the use of systems having a variety of spaced reception points organized as a complex of receivers for remote data transmission. After passing through the group of functional blocks, the preprocessed signal from each receiver enters the computational module, which is based on a heterogeneous neural network. The neurocontroller is made of three types of neural blocks forming a threelayer neural network structure. The first layer is composed of oscillator neurons to maintain the constant functioning of two other types of neurons, the organization of which requires constant stimulation for the functioning of the entire network. The second type and third type neural network modules are designed as signal processing devices adding and cutting off harmonic components. The substantiation of the applied learning algorithm is performed and the effectiveness of the designed neural network information processing system is shown.
Read more...

Control of distributed communication systems of information space-time duplication using neural networks of paired oscillators

The procedure for the synthesis of a neural network, which is based on a complex structure of paired neurons-oscillators that function in a certain topological map, is discussed. The use of neurons-oscillators with a variable activation threshold makes it possible to create reconfigurable neural memory circuits that act as a memory structure that can recreate the solution of a problem based on individual environmental signals. The use of mirror differential neurons that implement this principle of memory operation is proposed. This method of organizing a neural network makes it possible to implement an approach to neural network training that involves the reconfi ation of all variable parameters of neurons. Setting up individual cluster groups and their further interaction leads to the formation of a set of samples that correspond to the training sample. The use of interneuron switches, based on the use of an acoustic metamaterial, which properties can be changed by using electrocapillary phenomena, is reviewed. Switches are able to simultaneously accumulate multiple neural signals and then process them through an intermediate conversion into acoustic waves that propagate over the surface and through the volume of the metamaterial. Setting the parameters of switching elements using the optical diffusion tomography method makes it possible to create artificial neuristor lines and arrange signal processing in the interneuron space. The procedure for configuring and adapting the neural network architecture to solve the problem of increasing the reliability of transmitted information using the technology of multiple transmission of duplicate messages, is considered. Control of the method of access to the data transmission medium, as well as determination of the optimal number of frequency channels used, is carried out using the developed neural network of paired oscillators based on the analysis of the noise-signal environment. The effectiveness of the proposed neural network management is justified and the effectiveness of solving the task is evaluated. Read more...

Heterogeneous convolutional neural networks to build movement routes of the objects in spatial environment with accumulated energy potential

We consider the synthesis of a hybrid neural convolutional network with the modular topology-based architecture, which allows to arrange a parallel convolutional computing system to combine both the energy transfer and data processing, in order to simulate complex functions of natural biological neural populations. The system of interlayer neural commutation, based on the distributed resonance circuits with the layers of electromagnetic metamaterial between the inductive elements, is a base for simulation of the interaction between the astrocyte networks and the neural clusters responsible for information processing. Consequently, the data processing is considered both at the level of signal transmission through neural elements, and as interaction of artificial neurons and astrocytic networks ensuring their functioning. The resulting two-level neural system of data processing implements a set of measures to solve the issue based on the neural network committee. The specific arrangement of the neural network enables us to implement and configure the educational procedure using the properties absent in the neural networks consisting of neural populations only. The training of the convolutional network is based on a preliminary analysis of rhythmic activity, where artificial astrocytes play the main role of interneural switches. The analysis of the signals moving through the neural network enables us to adjust variable components to present information from training bunches in the available memory circuits in the most efficient way. Moreover, in the training process we observe the activity of neurons in various areas to evenly distribute the computational load on neural network modules to achieve maximum performance. The trained and formed convolutional network is used to solve the problem of determining the optimal path for the object moving due to the energy from the environment. Read more...

Synthesis of an optical neuromorphic structure with differentiated artificial neurons for information flow distribution

The work presents analysis of possible application of self-generating neural networks, which can independently generate a topological map of neuron connections while modelling biological neurogenesis, in multi-threaded information communication systems. A basic optical neural network cell is designed on the basis of the applied layered composition performing data processing. A map of neuron connections represents not an ordered structure providing a regular graph for exchange of information between neurons, but a set of cognitive reserve represented as an unconnected set of neuromorphic cells. Modelling of neuron death (apoptosis) and creation of dendrite-axon connections makes it possible to implement a stepwise neural network growth algorithm. Despite challenges in implementing this process, creating a growing network in an optical neural network framework solves the problem of initial forming of the neural network architecture, which greatly simplifies the learning process. Neural network cells used with the network growth algorithm resulted in neural network structures that use internal self-sustaining rhythmic activity to process information. This activity is a result of spontaneously formed closed neural circuits with common neurons among neuronal cells. Such organisation of recirculation memory leads to solutions with reference to such intra-network activity. As a result, response of the network is determined not only by stimuli, but also by the internal state of the network and its rhythmic activity. Network functioning is affected by internal rhythms, which depend on the information passing through the neuron clusters, which results in formation of a specific rhythmic memory. This can be used for tasks that require solutions to be worked out based on certain parameters, but they shall be unreproducible when the network is repeatedly stimulated by the same influences. Such tasks include ensuring information transmission security when using some set of carriers. The task of determining a number of frequencies and their frequency plan depends on external factors. To exclude possible repeating generation of the same carrier allocation, it is necessary to use networks of the configuration under consideration that can influence generation of solutions through the gathered experience. Read more...

Functional formation of a neuromorphic reservoir computational element based on a memristive metamaterial

A neural network structure is designed based on the ability of a certain class of calculators to recombine internal resources in order to produce neuromorphic elements to solve applied problems. This approach is rooted in a composite material with controlled local conductivity to form volumetric inhomogeneities capable of responding to and influencing external electrostatic effects. Such compounds aggregate into stable clusters suitable for modelling the processes that occur during information processing in natural neuronal entities. The use of conductive transitions between substrate-formed neuromorphic clusters as a learning structure makes it possible to increase the reliability of the neural network system. Long-term, non-volatile storage of information about the elements of the training sample in variable structures is possible. The basic approach to information conversion is to manage the electrostatic influence as it passes through the layered structures formed. The response to the input is not formed by propagating the signal through conductive elements with variable conductivity, but by passing the energy impact through a limited volume of metamaterial. Thus, a massively parallel processing of information can be achieved with the implementation of a mechanism for combining the opinions of independent neural network clusters that influence the final decision. Furthermore, this method of spreading effects in such an environment greatly simplifies the process of adding elements to the neural network. The lack of direct electrical interconnection facilitates the easy addition of new computational elements without significant rearrangement of the conductive media. Networks of this type are capable of significant growth without loss of experience. The input conversion process using modified delta coding prevents premature wear and tear on reconfigurable network elements. The manner in which information is presented and the manner in which neural network computing is organised enabled the creation of limited autonomous oscillations within the volume of the calculator to maintain circulating memory and the ability to gradually accumulate network experience for its subsequent recording in configurable elements. The identified features resulted in the application of this kind of calculators in the task of developing radio frequency management plans for the organisation of stable communication in a complex electromagnetic environment. Read more...

Neuromorphic electroactive macrocells for improvement of spatial orientation reliability

Neural network architecture based on polymer macrocells acting as neural elements and capable to generate electrically conductive synaptic junctions is developed. The architecture of a neural network processor where each component can record and produce a response to energy effects of different nature: electrical, optical and electrostatic has been developed. This function of the neural network eliminates the limitations related to the perception of the input information only by the input layer of the neural network processor. The impact of the influence of different input data representations on the information processing by the macrocell has been studied. The efficiency of temporal and electrical degradation of a neural network macrocell as a complex phenomenon directed on adaptation of a neural network to this process and generation of an algorithm for distribution of elements of a tutorial sample evenly over the total volume of available neural cells has been studied. The article studies a method of generation of episodic circulating memory, which significantly improves the speed of generation of a solution by the network, taking into account the gravitational interaction with macrocells. The revealed specific nature of the influence of the gravitational field on the functioning of neural network clusters was the basis for natural selection of cells by the performed properties depending on the spatial position in the neural network architecture. A method of exposure of the cell to physical equivalents of tutorial sample elements converted into different energy patterns to control the configuration of the macrocell using all available modes of information perception has been provided. Each exposure containing information on the tutorial element (optical and electrostatic) supports the generated generalising abilities of the neural macrocells composition. Practical significance of the performed research comprises the designed neural network system, which achieves an increase in performance due to self-organising oscillating neural clusters. The developed neural network model is used to reduce radio deviation and associated navigation errors due to conductive obstacles or atmospheric formations. Read more...