As one of the most important research fields in the brain–computer interface (BCI) field, electroencephalogram (EEG) classification has a wide range of application values. However, for the EEG signal, it is difficult for the traditional neural networks to capture the characteristics of the EEG signal more comprehensively from the time and space dimensions, which has a certain effect on the accuracy of EEG classification. To solve this problem, we can improve the accuracy of classification via end-to-end learning of the time and space dimensions of EEG. In this paper, a new type of EEG classification network, the separable EEGNet (S-EEGNet), is proposed based on Hilbert–Huang transform (HHT) and a separable convolutional neural network (CNN) with bilinear interpolation. The EEG signal is transformed into time-frequency representation by HHT, which allows the EEG signal to be better described in the frequency domain. Then, the depthwise and pointwise elements of the network are combined to extract the feature map. The displacement variable is added by the bilinear interpolation method to the convolution layer of the separable CNN, allowing the free deformation of the sampling grid. The deformation depends on the local, dense, and adaptive input characteristics of the EEG data. The network can learn from the time and space dimensions of EEG signals end to end to extract features to improve the accuracy of EEG classification. To show the effectiveness of S-EEGNet, the team used this method to test two different types of EEG public datasets (motor imagery classification and emotion classification). The accuracy of motor imagery classification is 77.9%, and the accuracy of emotion classification is 89.91%, and 88.31%, respectively. The experimental results showed that the classification accuracy of S-EEGNet improved by 3.6%, 1.15%, and 1.33%, respectively.

In this paper, a variable structure pneumatic soft robot is proposed. Its structure is variable in that when it grasps irregular objects, it can adapt to different sizes by active expansion or contraction. Its expansion range is from diameter 200 to 300 mm, its four soft pneumatic actuators (SPAs) can be rotated independently to adapt to different shapes, and it has high flexibility. The active compliant grasping method enables it to capture at the best position, which can improve the success rate of capture and reduce damage to the object being grasped. The experiment proves the effectiveness of the variable structure mechanism, and the proposed soft robot has low cost and a simple manufacturing process, so the mechanism has great application prospects.

Conventional robots have shown good positioning accuracy and reliability in multiple environment. However, the robots’ lack of flexibility makes them unsuitable for application in certain areas. Thus, a soft robotic system should be considered, due to its adaptivity and flexibility. This work proposes a novel shape memory alloy (SMA) actuated multiple degrees of freedom (DOF) soft robot, which theoretically supports a maximum of 9-DOF movement and good positioning accuracy. A motion test and positioning evaluation are conducted for the proposed multi-DOF soft robot. The structural design, control method, and analysis of the kinematics and the coordinate system are also given.

A capsule network (CapsNet) is a recently proposed neural network model with a new structure. The purpose of CapsNet is to form activation capsules. In this paper, our team proposes a dual attention mechanism capsule network (DA-CapsNet). In DA-CapsNet, the first layer of the attention mechanism is added after the convolution layer and is referred to as Conv-Attention; the second layer is added after the PrimaryCaps and is referred to as Caps-Attention. The experimental results show that DA-CapsNet performs better than CapsNet. For MNIST, the trained DA-CapsNet is tested in the testset, the accuracy of the DA-CapsNet is 100% after 8 epochs, compared to 25 epochs for CapsNet. For SVHN, CIFAR10, FashionMNIST, smallNORB, and COIL-20, the highest accuracy of DA-CapsNet was 3.46%, 2.52%, 1.57%, 1.33% and 1.16% higher than that of CapsNet. And the results of image reconstruction in COIL-20 show that DA-CapsNet has a more competitive performance than CapsNet.

Soft robots have the characteristics of good adaptability to an environment. But at present, most soft robots only complete a single specific task, and as a result, their ability to adapt to complex environments is limited. In order to solve the weak ability of soft robots to adapt to complex and diverse environments, this paper presents a new bionic omnidirectional bending actuator (BOBA) inspired by leeches, caterpillars, and other mollusks. BOBA has less radial expansion, fast response, good flexibility, and omnidirectional bending. Using modular methods, it can be quickly assembled into a soft robot with a variety of motion modes. Experiments show the multimodal soft robot can climb vertical walls, transition from one surface to another, climb stairs, leap obstacles, cross narrow pipes, and move with heavy objects. This greatly improves the ability of soft robots to adapt to complex and diverse environments.

Detection of pulmonary nodules is an important aspect of an automatic detection system. Incomputer-aided diagnosis (CAD) systems, the ability to detect pulmonary nodules is highly important, which plays an important role in the diagnosis and early treatment of lung cancer. Currently, the detection of pulmonary nodules depends mainly on doctor experience, which varies. This paper aims to address the challenge of pulmonary nodule detection more effectively. A method for detecting pulmonary nodules based on an improved neural network is presented in this paper. Nodules are clusters of tissue with a diameter of 3 mm to 30 mm in the pulmonary parenchyma. Because pulmonary nodules are similar to other lung structures and have a low density, false positive nodules often occur. Thus, our team proposed an improved convolutional neural network (CNN) framework to detect nodules. First, a nonsharpening mask is used to enhance the nodules in computed tomography (CT) images; then, CT images of 512×512 pixels are segmented into smaller images of 96×96 pixels. Second, in the 96×96 pixel images which contain or exclude pulmonary nodules, the plaques corresponding to positive and negative samples are segmented. Third, CT images segmented into 96×96 pixels are down-sampled to 64×64 and 32×32 size respectively. Fourth, an improved fusion neural network structure is constructed that consists of three three-dimensional convolutional neural networks, designated as CNN-1, CNN-2, and CNN-3, to detect false positive pulmonary nodules. The networks’ input sizes are 32×32×32, 64×64×64, and 96×96×96 and include 5, 7, and 9 layers, respectively. Finally, we use the AdaBoost classifier to fuse the results of CNN-1, CNN-2, and CNN-3. We call this new neural network framework the Amalgamated-Convolutional Neural Network (A-CNN) and use it to detect pulmonary nodules. Our team trained A-CNN using the LUNA16 and Ali Tianchi datasets and evaluated its performance using the LUNA16 dataset. We discarded nodules less than 5mm in diameter. When the average number of false positives per scan was 0.125 and 0.25, the sensitivity of A-CNN reached as high as 81.7% and 85.1%, respectively.