Current methods for sleep stage detection rely on sensors to collect physiological data. These methods are inaccurate and take up considerable medical resources. Thus, in this study, we propose a Taguchi-based multiscale convolutional compensatory fuzzy neural network (T-MCCFNN) model to automatically detect and classify sleep stages. In the proposed T-MCCFNN model, multiscale convolution kernels extract features of the input electroencephalogram signal and a compensatory fuzzy neural network is used in place of a traditional fully connected network as a classifier to improve the convergence rate during learning and to reduce the number of model parameters required. Due to the complexity of general deep learning networks, trial and error methods are often used to determine their parameters. However, this method is very time-consuming. Therefore, this study uses the Taguchi method instead, where the optimal parameter combination is identified over a minimal number of experiments. We use the Sleep-EDF database to evaluate the proposed model. The results indicate that the proposed T-MCCFNN sleep stage classification accuracy is 85.3%, which is superior to methods proposed by other scholars.

Deep learning technology has extensive application in the classification and recognition of medical images. However, several challenges persist in such application, such as the need for acquiring large-scale labeled data, configuring network parameters, and handling excessive network parameters. To address these challenges, in this study, we developed an adversarial-learning-based Taguchi convolutional fuzzy neural classifier (AL-TCFNC) for classifying malignant and benign lung tumors displayed in computed tomography images. In the framework of the developed AL-TCFNC, a fuzzy neural classifier replaces a conventional fully connected network, thereby reducing the number of network parameters and the training duration. To reduce experimental cost and training time, the Taguchi method was used. This method helps to identify the optimal combination of model parameters through a small number of experiments. The transfer learning of models across databases often results in subpar performance because of the paucity of labeled samples. To resolve this problem, we used a combination of maximum mean discrepancy and cross-entropy for adversarial learning with the proposed model. Two data sets, namely the SPIE-AAPM Lung CT Challenge data set and LIDC-IDRI Lung Imaging Research data set, were used to validate the AL-TCFNC model. When the AL-TCFNC model was used for transfer learning, it exhibited an accuracy rate of 89.55% and outperformed other deep learning models in terms of classification performance.

In the field of machining, product quality must meet customer specifications. In general, surface roughness is an essential indicator of machining quality. Low surface roughness correlates with increased fatigue strength and corrosion resistance. However, the main factor that affects surface roughness is the selection of the machining parameters. When different parameters are combined, the resulting machining quality varies. Therefore, to achieve the desired machining quality, appropriate machining parameters must be selected. In this study, an ultrasonic-assisted machining system (UAMS) was designed to help users determine the machining parameters and machine SiC materials. To establish a prediction model for surface roughness, a novel network mapping fusion (NMF) convolutional neuro-fuzzy network (CNFN) model was used in the designed UAMS. The differential evolution algorithm was then used to search for optimized machining parameters. To explain the prediction model, which can help analyze the factors that have the greatest influence on surface roughness, a Shapley additive explanations method is proposed. The proposed NMF–CNFN model was more accurate than were the other deep learning models and exhibited a MAPE of 1.98%. When optimized machining parameters were selected, the desired surface roughness was obtained, thereby confirming the effectiveness and accuracy of the proposed UAMS. Moreover, the proposed model was implemented in a field-programmable gate array (FPGA) to reduce its power consumption and increase its computational performance. Experimental results indicated that the computational speed of the FPGA was 99.64% and 99.16% higher than those of the CPU and GPU, respectively.

Unmanned ground vehicle control in unknown environments is hindered by terrain variation, obstacle complexity, and sensor noise. This study proposes a light-detection-and-ranging-based control system that integrates fuzzy terrain traversability assessment (FTTA) and adaptive artificial potential field (AAPF) algorithms for terrain detection and obstacle avoidance. Cloth simulation filtering (CSF) is used to preprocess point clouds for distinguishing between terrain and aboveground points. The FTTA algorithm then identifies terrain obstacles using slope and height features, with aboveground points classified as obstacles by height. Moreover, the AAPF algorithm integrates both terrain and aboveground points to adaptively adjust the exclusion radius and improve path planning. Experimental analysis revealed that FTTA with CSF achieved a ground point retention rate of 0.682, a height variance of 0.087, and a processing time of 0.016 s. These values maintained the slope estimation angles close to the true values and ensured stable and rapid computation. In navigation experiments, the AAPF algorithm achieved a reduced travel distance of 62.4 ± 3.2 m and a reduced travel time of 154 ± 5 s. Compared with the baseline APF method, this represents a reduction of 21% in navigation time, indicating improved efficiency and stability.

With the continuing development of autonomous driving systems, the drivable area segmentation problem has become an indispensable part of self-driving cars. The drivable area segmentation technology introduces many features to self-driving car technology, such as providing information about the surrounding environment, assisting decision-making mechanisms, selecting appropriate driving paths, and avoiding obstacles. In addition, accurate segmentation of drivable areas is crucial for improving self-driving navigation and avoiding obstacles. To enable effective identification of drivable areas on the basis of environmental information, this study designed a drivable area segmentation network named DASNet. The proposed DASNet utilizes depthwise separable convolution as a basis/platform for feature extraction to enable features to be efficiently extracted to reduce both the computational load and required network parameters. Additionally, the proposed DASNet enhances the inference speed of the network while maintaining high accuracy. In order to reduce point cloud density without compromising essential information, we perform sampling and fusion on the point clouds in both Cartesian and spherical coordinate spaces during data preprocessing. The fused point cloud serves as the input to DASNet, while the output is the drivable area map. Finally, the proposed DASNet is ported to a field programmable gate array to achieve real-time drivable area detection. This study employs the publicly available KITTI dataset and proposed wooded environment dataset for experimental evaluation. By evaluating the model on two distinct datasets, we aim to demonstrate the capabilities across three types of urban road scenes and more densely wooded environments. The experimental results indicate that DASNet achieved an F1-score of 0.9449 and an inference speed of 9.32 ms on the KITTI dataset. Furthermore, the proposed DASNet was applied to unmanned vehicles operating in a wooded environment, achieving an F1-score of 98.64%.