Explainable deep learning model for automatic mulberry leaf disease classification

Mulberry leaves feed Bombyx mori silkworms to generate silk thread. Diseases that affect mulberry leaves have reduced crop and silk yields in sericulture, which produces 90% of the world's raw silk. Manual leaf disease identification is tedious and error-prone. Computer vision can categorize leaf diseases early and overcome the challenges of manual identification. No mulberry leaf deep learning (DL) models have been reported. Therefore, in this study, two types of leaf diseases: leaf rust and leaf spot, with disease-free leaves, were collected from two regions of Bangladesh. Sericulture experts annotated the leaf images. The images were pre-processed, and 6,000 synthetic images were generated using typical image augmentation methods from the original 764 training images. Additional 218 and 109 images were employed for testing and validation respectively. In addition, a unique lightweight parallel depth-wise separable CNN model, PDS-CNN was developed by applying depth-wise separable convolutional layers to reduce parameters, layers, and size while boosting classification performance. Finally, the explainable capability of PDS-CNN is obtained through the use of SHapley Additive exPlanations (SHAP) evaluated by a sericulture specialist. The proposed PDS-CNN outperforms well-known deep transfer learning models, achieving an optimistic accuracy of 95.05 ± 2.86% for three-class classifications and 96.06 ± 3.01% for binary classifications with only 0.53 million parameters, 8 layers, and a size of 6.3 megabytes. Furthermore, when compared with other well-known transfer models, the proposed model identified mulberry leaf diseases with higher accuracy, fewer factors, fewer layers, and lower overall size. The visually expressive SHAP explanation images validate the models' findings aligning with the predictions made the sericulture specialist. Based on these findings, it is possible to conclude that the explainable AI (XAI)-based PDS-CNN can provide sericulture specialists with an effective tool for accurately categorizing mulberry leaves.

MultiResUNet3+: A Full-Scale Connected Multi-Residual UNet Model to Denoise Electrooculogram and Electromyogram Artifacts from Corrupted Electroencephalogram Signals

Electroencephalogram (EEG) signals immensely suffer from several physiological artifacts, including electrooculogram (EOG), electromyogram (EMG), and electrocardiogram (ECG) artifacts, which must be removed to ensure EEG's usability. This paper proposes a novel one-dimensional convolutional neural network (1D-CNN), i.e., MultiResUNet3+, to denoise physiological artifacts from corrupted EEG. A publicly available dataset containing clean EEG, EOG, and EMG segments is used to generate semi-synthetic noisy EEG to train, validate and test the proposed MultiResUNet3+, along with four other 1D-CNN models (FPN, UNet, MCGUNet, LinkNet). Adopting a five-fold cross-validation technique, all five models' performance is measured by estimating temporal and spectral percentage reduction in artifacts, temporal and spectral relative root mean squared error, and average power ratio of each of the five EEG bands to whole spectra. The proposed MultiResUNet3+ achieved the highest temporal and spectral percentage reduction of 94.82% and 92.84%, respectively, in EOG artifacts removal from EOG-contaminated EEG. Moreover, compared to the other four 1D-segmentation models, the proposed MultiResUNet3+ eliminated 83.21% of the spectral artifacts from the EMG-corrupted EEG, which is also the highest. In most situations, our proposed model performed better than the other four 1D-CNN models, evident by the computed performance evaluation metrics.

Simultaneous EEG-fMRI: Evaluating the Effect of the EEG Cap-Cabling Configuration on the Gradient Artifact

Electroencephalography (EEG) data recorded during simultaneous EEG-fMRI experiments are contaminated by large gradient artifacts (GA). The amplitude of the GA depends on the area of the wire loops formed by the EEG leads, as well as on the rate of switching of the magnetic field gradients, which are essential for MR imaging. Average artifact subtraction (AAS), the most commonly used method for GA correction, relies on the EEG amplifier having a large enough dynamic range to characterize the artifact voltages. Low-pass filtering (250 Hz cut-off) is generally used to attenuate the high-frequency voltage fluctuations of the GA, but even with this precaution channel saturation can occur, particularly during acquisition of high spatial resolution MRI data. Previous work has shown that the ribbon cable, used to connect the EEG cap and amplifier, makes a significant contribution to the GA, since the cable geometry produces large effective wire-loop areas. However, by appropriately connecting the wires of the ribbon cable to the EEG cap it should be possible to minimize the overall range and root mean square (RMS) amplitude of the GA by producing partial cancelation of the cap and cable contributions. Here by modifying the connections of the EEG cap to a 1 m ribbon cable we were able to reduce the range of the GA for a high-resolution coronal echo planar Imaging (EPI) acquisition by a factor of ∼ 1.6 and by a factor of ∼ 1.15 for a standard axial EPI acquisition. These changes could potentially be translated into a reduction in the required dynamic range, an increase in the EEG bandwidth or an increase in the achievable image resolution without saturation, all of which could be beneficially exploited in EEG-fMRI studies. The re-wiring could also prevent the system from saturating when small subject movements occur using the standard recording bandwidth.