Hyper-Fuzzy Modeling and Control for Bio-Inspired Radar Processing Omar M. Salim 1 , Hoda S. Abdel-Aty-Zohdy 2 , Mohamad A. Zohdy 2 1 High Institute of Technology, Benha University, Egypt; 2 School of Engineering and Computer Science, Oakland University, Rochester, MI 48309; Abstract: Modern RF Radar signal processing has been receiving much attention for wide range of domains that include industrial, environmental, and military applications. Inherently, the received raw spatial-temporal signals can be 1-D, 2-D, or 3-D and are usually of uncertain nature, because of changing conditions and optical background variations. In this paper, we apply novel concepts for hyper-neural theory that allow for incorporation of variables attribute definitions and uncertainties for the purpose of effective evidential learning and subsequent key output features determination in the radar processing. Application to wide-band angle of arrival data sets at several carrier frequencies has been carried out in order to illustrate the strengths as well weakness of the approach. Using interval set-based operations together with segmentation of the data is proved useful and gave good sensitivity of detection. Keywords: Fuzzy Logic, Membership function, Neural Networks 1. Introduction As modern radar signals and systems become more sophisticated in terms of its short pulse waveform optimization and wideband nature, the receivers need to have surveillance and direction finding capabilities. Characterization and identification of the threat signals by bounding the angle of arrival (AOA) to specific interval enables location of the source of threat signal [1, 2]. Current wideband digital receiver systems are typically based on a channelization [1]. This channelization can be implemented to have wideband coverage [2]. For a phased array system, implementation requires similar set of components following each antenna element, which may be impractical. This system needs a controller to scan through channels to function as a wideband receiver [2]. Phased array receiver system is the extensively used modern day technology. The multiple antenna elements provide not only the spatial-temporal capability, but also an extra gain due to coherence and less confounding compared to single antenna receiver system [2]. The AOA can be for example measured by processing the spatial-temporal data, using the Fast Fourier Transform (FFT) in 2-D for time-frequency conversion. The peak FFT component in the frequency bin contains the frequency and power information of the input signal. Likewise, the peak FFT component in the spatial FFT bin contains the direction and power information of the input signal. Applications involving direction surveillance, the phased array is usually scanned through a range of positive and negative angles [2]. Applications involving direction surveillance, the phased array is usually scanned through a range of angles. For these applications, microwave lens [3], Butler Matrix [4], Blass Matrix, and time delay line [5] are among the analog beam forming methods that can be used. Digital time delay line and FIR filter are among the digital beam forming implementation methods [6]. In this paper, a hyper-neural technique is proposed, where the time series data points are processed directly to obtain the target AOA from the information embedded in the measured 2-D spatial-temporal patterns. These techniques which are based on learning, adaptation, and testing are representative of Fuzzy Logic Systems (FLS), Neural Networks (NN), and hybrid systems like Adaptive Neuro-fuzzy Inference System (ANFIS). 2. Fuzzy Logic Systems Fuzzy logic has gained attention of researchers for last couple of decades. It has displaced conventional technologies in different scientific and system engineering applications, especially in pattern recognition, signal processing communication, integrated circuit manufacturing, biomedical systems, and mostly overall control systems [7]. The same fuzzy technology, in approximation reasoning form, is resurging also in the information technology, where it is now giving support to decision-making, bio-inspired systems, and expert systems with powerful reasoning capacity especially for limited rules [7]. The fuzzy sets were presented by L.A. Zadeh in 1965 to process / manipulate data and information affected by unprobabilistic uncertainty/imprecision [7]. These were designed to mathematically represent the vagueness and uncertainty of linguistic problems; thereby obtaining formal tools to work with intrinsic imprecision in different problems; it is considered a generalization of the classic set theory. Intelligent Systems based on fuzzy logic are fundamental tools for nonlinear 978-1-4244-6578-1/10/$26.00 ©2010 IEEE 392