Enhanced Detection of Weak Signals in Chaotic Systems Through Hybrid Neuro-Fuzzy Inference Techniques

The identification of weak signals in chaotic environment can be problematic because of unpredicted and complex characteristic of chaotic dynamics. This research presents a new method based on an Adaptive Neuro-Fuzzy Inference System (ANFIS) to improve the ability of detecting weak signals obscured by noise. In other words, the proposed approach utilize the ANFIS potential in implementing both static and dynamic models of learning for chaotic systems and clearly distinguish weak signals in contrast to noise. Since it allows a non-linear mixture between signals and noise power and the learning mechanism is adaptive, it forms a rather strong basis for identifying signals that cannot be identified in standard approaches. This work confirms the efficiency of the approach under consideration using a number of simulations on standard chaotic systems showing a higher detection accuracy and higher SNR. Combining fuzzy logic with neural network’s allows the system to process weak signals, which exhibit certain degree of ‘fuzziness;’ making it an excellent tool for use in systems that involve chaos or weak signal analysis in areas like communication systems, biomedical engineering, or other form of fault diagnosis. The obtained results affirm and spotlight the rationale of ANFIS as a bringing innovation in the field of the chaotic signal analysis.