Anatoly Sachenko

Smart license plate recognition system based on image processing using neural network

We describe the smart vehicle screening system, which can be installed into a tollbooth for automated recognition of vehicle license plate information using a photograph of a vehicle. An automated system could then be implemented to control the payment of fees, parking areas, highways, bridges or tunnels, etc. There are considered an approach to identify vehicle through recognizing of it license plate using image fusion, neural networks and threshold techniques as well as some experimental results to recognize the license plate successfully

Sensor errors prediction using neural networks

The features of neural networks used for increasing the accuracy of physical quantity measurement are considered by prediction of sensor drift. The technique of data volume increasing for predicting neural network training is offered at the expense of various data types replacement for neural network training and at the expense of the separate approximating neural network use.

Intelligent distributed sensor network

The intelligent functions of sensor measurement instrumentation are formed on basis of the original calibration and prediction methods. Measuring module structure as basic distributed sensor network (DSN) component is considered and an intelligent DSN (IDSN) structure is proposed. Procedures and functions of various levels of information processing in IDSN are formed. Developed IDSN is tested on design and exploitation stages.

Intelligent nodes for distributed sensor network

Neural networks models and their training algorithms on a central computer with reference to a previously developed distributed sensor network are considered. The requirements for its intelligent node are formulated. Also the nodes structure is offered which realises such intelligent functions, as sensor and other measuring channel components drift prediction using remote reprogramming.

Approach to recognition of license plate numbers using neural networks

We considered an approach to identify vehicle through recognizing of it license plate using image fusion, neural networks and threshold techniques as well as some experimental results to recognize the license plate successfully.

Error compensation in an intelligent sensing instrumentation system

Methods of improving the measurement accuracy by estimation and correction of the maximum error components, are analyzed. The functional structure of the measurement channel in an intelligent sensing instrumentation system is described along with the procedures of component error correction. An experimental setup, implementing such methods in a multi-processing neural network configuration, is presented.

Technique of learning rate estimation for efficient training of MLP

A new computational technique for training of multilayer feedforward neural networks with sigmoid activation function of the units is proposed. The proposed algorithm consists two phases. The first phase is an adaptive training step calculation, which implements the steepest descent method in the weight space. The second phase is estimation of calculated training step rate, which reaches a state of activity of the units for each training iteration. The simulation results are provided for the test example to demonstrate the efficiency of the proposed method, which solves the problem of training step choice in multilayer perceptrons.

Approach to Face Recognition Using Neural Networks

The paper describes the approach to automatic face recognition for access control application area using wavelet transform and neural networks ensemble. Wavelet transform implements the compression of the face images and thus accelerates the classifiers work, while neural networks ensemble with proposed decision rule provides low recognition error. Proposed ensembles decision rule carries out a high level of unknown peoples access rejection, which is the most significant requirement for the access control systems, and gives a good balance between known and unknown peoples recognition errors.

Estimation of Computational Complexity of Sensor Accuracy Improvement Algorithm Based on Neural Networks

The estimation method of computational complexity of sensor data acquisition and processing algorithm based on neural networks is considered in this paper. An application of this method allows to propose a three-level structure of distributed sensor network with improved accuracy.

Development of neural network immune detectors for computer attacks recognition and classification

There is developed a combined method that is based on the integration of neural network detectors in an artificial immune system. This allowed them to adapt to new attacks with the help of cloning and mutation operations.