Dual-channel Neural Network Research Articles

Prediction of the vehicle lane‐changing distance in an urban inter‐tunnel weaving section based on wavelet transform and dual‐channel neural network

AbstractVehicle lane‐changing behaviour is often regarded as transient traffic behaviour while ignoring behavioural characteristics of the lane‐changing process. A combined prediction model based on wavelet transform (WT) and dual‐channel neural network (DCNN) is proposed to explore the selection behaviour of lane‐changing distance by taking lane‐changing behaviour in an urban inter‐tunnel weaving section. Firstly, the extracted lane‐changing data are analysed for correlation and noise reduction, and the main factors affecting lane‐changing distance are taken as input variables of the model. The trajectory data of the inter‐tunnel weaving section of the “Jiuhuashan‐Xi'anmen” tunnel in Nanjing, China, are used to improve the prediction of vehicle lane‐changing distance by training the model. The results show that the proposed WT‐DCNN model has high prediction performance when compared with existing artificial neural network (ANN), DCNN and wavelet neural network (WNN) models. The characterization and study of the typical lane‐changing behaviour in the weaving section can lay the theoretical foundation for the development of an urban inter‐tunnel weaving section management scheme.

Compound Jamming Recognition Based on a Dual-Channel Neural Network and Feature Fusion

Jamming recognition is a significant prior step to achieving effective jamming suppression, and the precise results of the jamming recognition will be beneficial to anti-jamming decisions. However, as the electromagnetic environment becomes more complex, the received signals may contain both suppression jamming and deception jamming, which is more challenging for existing methods focused on a single kind of jamming. In this paper, a recognition method for compound jamming based on a dual-channel neural network and feature fusion is proposed. First, feature images of compound jamming are extracted by the short-time Fourier transform and the wavelet transform. Feature images are then employed as inputs for the proposed network. During parallel processing in dual-channel, the proposed network can adaptively extract and learn task-relevant features via the attention modules. Finally, the output features in dual-channel are fused in the fusion subnetwork. Compared with existing methods, the proposed method can yield better recognition performance with less inference time. Additionally, compared with existing fusion strategies, the fusion subnetwork can further improve the recognition performance under low jamming-to-noise ratio conditions. Results with the semi-measured datasets also verify the feasibility and generalization performance of the proposed method.

UWB Localization Based on Dual-Channel Neural Network and Total Least Square Method

UWB Localization Based on Dual-Channel Neural Network and Total Least Square Method

Device-Free Human Activity Recognition Based on Dual-Channel Transformer Using WiFi Signals

Human activity recognition plays a significant role in smart building applications, healthcare services, and security monitoring. In particular, WiFi-based indoor wireless sensing system becomes increasingly popular due to its noninvasiveness. This work presents the design and implementation of DARMS, a Device-free human Activity Recognition and Monitoring System that can be deployed with low-cost commodity WiFi devices. DARMS is a passive wireless sensing system, and it can accurately distinguish various daily activities without the user wearing any sensor. DARMS makes two key technical contributions. First, an effective signal processing methodology is designed to extract the CSI features both in the time domain and frequency domain. Second, a dual-channel neural network that combines temporal and frequency information is proposed to achieve fine-grained activity recognition. In our experiments, DARMS shows outstanding performance in different indoor environments, with an average accuracy of 96.9% for fall detection and 93.3% for human activity recognition.

CT image quality enhancement via a dual-channel neural network with jointing denoising and super-resolution

In recent years, computed tomography (CT) has been widely used in various clinical diagnosis. Given potential health risks bring by the X-ray radiation, the major objective of the current research is to achieve high-quality CT imaging while reducing X-ray radiation. However, most existing studies on low-dose CT image super-resolution reconstruction do not focus on the interaction between the denoising task and the super-resolution task. In this paper, we propose a dual-channel joint learning framework to accurately reconstruct high-resolution CT images from low-resolution CT images. Unlike the previous cascaded models which directly combine the denoising network and the super-resolution network, our method can process the denoising reconstruction and the super-resolution reconstruction in parallel. Additionally, we design a filter gate module that can filter features from the denoising branch and highlight important features which can benefit the super-resolution task. We evaluate the performance of our method in medical image enhancement by testing on the 2016 Low-Dose CT Grand Challenge dataset and the piglet dataset. The experimental results show that the proposed network is superior to other state-of-the-art methods in terms of both peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). We also demonstrate that our method can better remove noise and recover details. Furthermore, the method achieves competitive results not only for super-resolution reconstruction of low-dose CT, but also for super-resolution reconstruction of sparse-view CT.

Prediction Method of Human Group Emotion Perception Tendency Based on a Machine Learning Model

Humans with the same attribute tend to assume similar emotional and cognitive tendencies. In this study, a machine learning model was constructed to calculate the sample emotion categories’ membership matrices of human groups towards a group of aria samples, thus making a prediction of the human groups’ emotion perception tendencies. Subjects’ binary attributes in terms of gender, family environment and professional background were collected. The subjects were invited to perform an emotion identification of aria segments to build a multi-classification standard dataset of differences in subjects’ emotion identification. A dual-channel neural network model was proposed, and three neural networks based on it were adopted to predict the emotion perception tendencies of the categorical groups with three attributes. Subjects were clustered according to the predicted values of the emotion perception tendencies towards the sample test group, followed by a comparison of the clustering results with the actual attribute group classifications. As suggested by the experimental results, the neural network accurately predicted the classification groups’ emotion perception tendencies with the three attributes of the subjects. The cluster experiment results of subjects, based on the predicted values of the neural networks’ output, had better performance only under the professional background attribute.