No abstract

Computational visual encoding models play a key role in understanding the stimulus–response characteristics of neuronal populations in the brain visual cortex. However, building such models typically faces challenges in the effective construction of non-linear feature spaces to fit the neuronal responses. In this work, we propose the GaborNet visual encoding (GaborNet-VE) model, a novel end-to-end encoding model for the visual ventral stream. This model comprises a Gabor convolutional layer, two regular convolutional layers, and a fully connected layer. The key design principle for the GaborNet-VE model is to replace regular convolutional kernels in the first convolutional layer with Gabor kernels with learnable parameters. One GaborNet-VE model efficiently and simultaneously encodes all voxels in one region of interest of functional magnetic resonance imaging data. The experimental results show that the proposed model achieves state-of-the-art prediction performance for the primary visual cortex. Moreover, the visualizations demonstrate the regularity of the region of interest fitting to the visual features and the estimated receptive fields. These results suggest that the lightweight region-based GaborNet-VE model based on combining handcrafted and deep learning features exhibits good expressiveness and biological interpretability.

To detect open circuit faults of grid-connected T-type inverters, this paper proposed a real-time method based on fast S transform and random forest. The three-phase fault currents of the inverter were used as the inputs of the new method and no additional sensors were needed. Some fault current harmonics and direct current components were selected as the fault features. Then, fast S transform was used to extract the features of fault currents, and random forest was used to recognize the features and the fault type, as well as locate the faulted switches. The simulation and experiments showed that the new method could detect open-circuit faults with low computation complexity and the detection accuracy was 100%. The real-time and accurate open circuit fault detection method was proven effective for grid-connected T-type inverter monitoring.

No abstract

No abstract