Drug side effects are one of the public health concerns. Using powerful machine-learning methods to predict potential side effects before the drugs reach the clinical stages is of great importance to reduce time consumption and protect the security of patients. Recently, researchers have proved that the central nervous system (CNS) side effects of a drug are closely related to its permeability to the blood–brain barrier (BBB). Inspired by this, we proposed an extended neighborhood-based recommendation method to predict CNS side effects using drug permeability to the BBB and other known features of drug. To the best of our knowledge, this is the first attempt to predict CNS side effects considering drug permeability to the BBB. Computational experiments demonstrated that drug permeability to the BBB is an important factor in CNS side effects prediction. Moreover, we built an ensemble recommendation model and obtained higher AUC score (area under the receiver operating characteristic curve) and AUPR score (area under the precision-recall curve) on the data set of CNS side effects by integrating various features of drug.

Table detection is an important task of optical character recognition(OCR). At present, table detection for desktop applications has basically reached commercial requirements. With the advancement of informatization, personal demand for table detection has gradually increased. There is an urgent need to establish a table detection method that can be deployed on handheld devices. This paper proposes a mobile terminal table detection model based on YOLOv5. First, we used YOLOv5 as the main framework of the model. However, considering the problem of connection redundancy in the backbone of YOLOv5, on the basis of retaining the YOLOv5 multi-scale detection head, we replaced the backbone of YOLOv5 with the same excellent Mobilenetv2. In addition, considering the non-linear defects of the lightweight model, we use deformable convolution to make up for it. This paper has been evaluated on the ICDAR 2019 dataset, and the results show that compared with the baseline model, the model reduces the number of parameters by half and increases the detection speed by 47%. At the same time, the model can reach 35.25 FPS on ordinary Android phones.

In the face of a complex electromagnetic environment, the modulation mode of communication signals is becoming increasingly complicated. Existing modulation mode recognition methods of communication signals cannot accurately and quickly identify the modulation mode of communication signals. In this letter, we propose an efficient architecture for automatic modulation classification (AMC) based on residual neural network (ResNet). We combine the improved residual neural network with long short-term memory network (LSTM) to obtain a new network structure (MLResNet), which solves the problems of gradient disappearance and too many parameters. In the experiments, MLResNet reaches the overall 24-modulation classification rate of 96.60% at 18 dB SNR on the well-known DeepSig dataset.

Crowd counting, i.e. count the number of people in a crowded visual space, is emerging as an essential research problem with public security. A key in the design of the crowd counting system is to create a stable and accurate robust model, which requires to process on the feature channels of the counting network. In this study, the authors present a featured channel enhancement (FCE) block for crowd counting. First, they use a feature extraction unit to obtain the information of each channel and encodes the information of each channel. Then use a non‐linear variation unit to deal with the encoded channel information, finally, normalise the data and affixed to each channel separately. With the use of the FCE, the positive characteristic channel can be enhanced and weak or negative channel information can be suppressed. The authors successfully incorporate the FCE with two compact networks on the standard benchmarks and prove that the proposed FCE achieves promising results.

The goal of crowd counting is to estimate the number of people in the image. Presently, use regression to count people number became a mainstream method. It is worth noting that, with the development of convolutional neural networks (CNN), methods that are based on CNN have become a research hotspot. It is a more interesting topic that how to locate the site of the person in the image than simply predicting the number of people in the image. The perspective transformation present is still a challenge, because perspective distortion will cause differences in the size of the crowd in the image. To devote perspective distortion and locate the site of the person more accuracy, we design a novel framework named Adaptive Learning Network (CAL). We use the VGG as the backbone. After each pooling layer is output, we collect the 1/2, 1/4, 1/8, and 1/16 features of the original image and combine them with the weights learned by an adaptive learning branch. The object of our adaptive learning branch is each image in the datasets. By combining the output features of different sizes of each image, the challenge of drastic changes in the size of the image crowd due to perspective transformation is reduced. We conducted experiments on four population counting data sets (i.e., ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF-QNRF), and the results show that our model has a good performance.