In modern communication technology, factors like broadband, speed and accuracy play a major role in placing the network in the best preformation area. Here, the continuous monitoring of the channel is important to understand the performance of the channel and its parameters. The ShannonHartley theorem plays a major role in leading the communication world. In the 1940s, Claude Shannon developed the concept of channel capacity, based in part on the ideas of Nyquist and Hartley, and then formulated a complete theory of information and its transmission. In communication and information theory, the ShannonHartley theorem (Fu, 1968; Ballard, 1984; and Eshera and King 1984) tells the maximum rate at which information can be transmitted over a communication channel of a specified bandwidth in the presence of noise. It is an application of the noisy channel coding theorem to the archetypal case of a continuoustime analog communication channel subject to Gaussian noise. The ShannonHartley theorem states the channel capacity C, meaning the theoretical tightest upper bound on the information rate (excluding error correcting codes) of clean (or arbitrarily low bit error rate) data that can be sent with a given average signal power S through an analog communication channel (Fu, 1968; and Wozencraft and Jacobs, 1993) subject to additive white Gaussian noise of power N is:
...(1)
where C is the channel capacity (Fu, 1968; Ballard, 1984; and Eshera and King 1984) in bits per second; B is the bandwidth of the channel in Hertz (passband bandwidth in case of a modulated signal); S is the average received signal power over the bandwidth (in case of a modulated signal, often denoted C, i.e., modulated carrier) measured in Watts (or Volts squared); N is the average noise or interference power over the bandwidth measured in Watts (or Volts squared); and S/N is the SignaltoNoise Ratio (SNR) or the CarriertoNoise Ratio (CNR) of the communication signal to the Gaussian noise interference expressed as a linear power ratio (not as logarithmic decibels). In this paper, we designed a network called CMAC, which is artificial intelligence and neural networkbased network with hundreds of thousands of adjustable weights that can be trained to approximate nonlinearities which are not explicitly written out or even understood. Artificial neural network offers the advantage of performance improvement through learning using parallel and distributed processing. These networks are reimplemented using massive connections among processing units with variable strengths, and they have tremendous applications in system identification. The CMAC was first described by Albus in 1975 as a simple model of the cortex of the cerebellum. Since then, it has been in and out of fashion, extended in many different ways, and used in a wide range of different applications. Despite its biological relevance, the main reason for using the CMAC is that it operates very fast, which makes it suitable for realtime adaptive control. The operation of the CMAC will be described in two ways: as a neural network and as a lookup table. This network is trained through system identification technique (Shannon et al., 1967; Horowitz and Sahni, 1978; and Liu and Chen, 2000). System identification is defined as the determination on the basis of input and output of a system within a specified class of systems to which the system under test is equivalent. Mostly, we focus on training and simulation of a network layer in MATLAB. MATLAB is a highlevel language and interactive environment for computations, visualizations and programming. Meanwhile, you have a chance to analyze data, develop algorithms and create models and applications. This language tool and builtin mathematical functions will enable you to explore multiple approaches and reach a solution faster than with spreadsheets or traditional programming languages such as C or C++ or VC++. The main key features of the MATLAB are: (1) Mathematical functions for linear algebra, statistics, Fourier analysis, filtering, optimization, numerical integration and solving ordinary differential equations; (2) Builtin graphics for visualizing data and tools for creating custom plots; (3) Development tools for improving code quality and maintainability and maximizing performance; (4) Tools for building applications with custom graphical interfaces; (5) Functions for integrating MATLABbased algorithms with external applications and languages such as C, Java, .NET and Microsoft Excel; and (6) Creating apps with graphical user interfaces in MATLAB.
