In this article we describe the idea of the router architecture for packet routing in optical telecommunication networks, based on IPv6 protocol. The proposed solution of this architecture contains two blocks: the first one, based on continuous learning techniques (e. g. reinforcement learning algorithms) and the second one (executive block) implemented on FPGA structure. That structure permits division of routing policy between: direct switching the packets and using the accumulate knowledge. In this case a learning algorithm module is embedded into each node of a switching network. At the beginning of this article we present the short description of the systems with abilities of continuous learning. Among many algorithms belonging to AI (Artificial Intelligence) area, in particularly we concentrate on reinforcement learning algorithms.

In this article we present results of compressing an example signal by means of discrete wavelet transform for the sake of comparison, we did the same calculations also in the case of discrete fourier transform. The results show efficiency of compressing based on cumulative energy of the same number of coeffiicients.

In the article we present the idea of the data preprocessing in the optoelectronic measurement system for monitoring the industrial gas pollutants. Additionally, a single optical measurement path can carry big amount of data in entirely parallel manner (e.g. spectral response of light in an absorbing media). To meet the requirements coming from optical system properties, the new algorithm called Local Discriminant Basis with Feature Selection - LDBFS is proposed. It based on discrete wavelet transform and multidimensional data decomposition techniques. In order to assess the performance of the proposed method, the article presents the simulation results of data analysis of gas spectral absorption.