Enhanced fault diagnosis via stochastic resonance in a piecewise asymmetric bistable system.

Weak fault signals are often overwhelmed by strong noise or interference. The key issue in fault diagnosis is to accurately extract useful fault characteristics. Stochastic resonance is an important signal processing method that utilizes noise to enhance weak signals. In this paper, to address the issues of output saturation and imperfect optimization of potential structure models in classical bistable stochastic resonance (CBSR), we propose a piecewise asymmetric stochastic resonance system. A two-state model is used to theoretically derive the output signal-to-noise ratio (SNR) of the bistable system under harmonic excitations, which is compared with the SNR of CBSR to demonstrate the superiority of the method. The method is then applied to fault data. The results indicate that it can achieve a higher output SNR and higher spectral peaks at fault characteristic frequencies/orders, regardless of whether the system operates under fixed or time-varying speed conditions. This study provides new ideas and theoretical guidance for improving the accuracy and reliability of fault diagnosis technology.

Classification of Alzheimer's Disease Based on Abnormal Hippocampal Functional Connectivity and Machine Learning.

Objective: Alzheimer's disease (AD) is a neurodegenerative disease characterized by progressive deterioration of memory and cognition. Mild cognitive impairment (MCI) has been implicated as a prodromal phase of AD. Although abnormal functional connectivity (FC) has been demonstrated in AD and MCI, the clinical differentiation of AD, MCI, and normal aging remains difficult, and the distinction between MCI and normal aging is especially problematic. We hypothesized that FC between the hippocampus and other brain structures is altered in AD and MCI, and that measurement of abnormal FC could have diagnostic utility for the classification of different AD stages. Methods: Elderly adults aged 60-85 years were assigned to AD, MCI, or normal control (NC) groups based on clinical criteria. Functional magnetic resonance scanning was completed by 119 subjects. Five dimension reduction/classification methods were applied, using hippocampus-derived FC strengths as input features. Classification performance of the five dimensionality reduction methods was compared between AD, MCI, and NC groups. Results: FCs between the hippocampus and left insula, left thalamus, cerebellum, right lingual gyrus, posterior cingulate cortex, and precuneus were significantly reduced in AD and MCI. Support vector machine learning coupled with sparse principal component analysis demonstrated the best discriminative performance, yielding classification accuracies of 82.02% (AD vs. NC), 81.33% (MCI vs. NC), and 81.08% (AD vs. MCI). Conclusion: Hippocampus-seed-based FCs were significantly different between AD, MCI, and NC groups. FC assessment combined with widely used machine learning methods can improve AD differential diagnosis, and may be especially useful to distinguish MCI from normal aging.