Search

Deep learning has recently received extensive attention in the field of rolling-bearing fault diagnosis owing to its powerful feature expression capability. With the help of deep learning, we can fully extract the deep features hidden in the data, significantly improving the accuracy and efficiency of fault diagnosis. Despite this progress, deep learning still faces two outstanding problems. (1) Each layer uses the same convolution kernel to extract features, making it difficult to adaptively select convolution kernels based on the features of the input image, which limits the network's adaptability to different input features and leads to weak feature extraction. (2) Large number of parameters and long training time. To solve the above problems, this paper proposes an integrated deep neural network that combines an improved selective kernel network (SKNet) with an enhanced Inception-ResNet-v2, named SIR-CNN. First, based on the SKNet, a new three-branch SKNet was designed. Second, the new SKNet is embedded into a depthwise separable convolution network such that the model can adaptively select convolution kernels of different sizes during training. Furthermore, the convolution structure in the Inception-ResNet-v2 network was replaced by the improved depthwise separable convolution network to achieve effective feature extraction. Finally, the time-frequency maps of the raw vibration signals are obtained through short-time Fourier transform (STFT) and then sent to the proposed SIR-CNN network for experiments. The experimental results show that the proposed SIR-CNN achieves superior performance compared to other methods. [ABSTRACT FROM AUTHOR]

We present a deep learning-based method that corrects motion artifacts and thus accelerates data acquisition and reconstruction of magnetic resonance images. The novel model, the Motion Artifact Correction by Swin Network (MACS-Net), uses a Swin transformer layer as the fundamental block and the Unet architecture as the neural network backbone. We employ a hierarchical transformer with shifted windows to extract multiscale contextual features during encoding. A new dual upsampling technique is employed to enhance the spatial resolutions of feature maps in the Swin transformer-based decoder layer. A raw magnetic resonance imaging dataset is used for network training and testing; the data contain various motion artifacts with ground truth images of the same subjects. The results were compared to six state-of-the-art MRI image motion correction methods using two types of motions. When motions were brief (within 5 s), the method reduced the average normalized root mean square error (NRMSE) from 45.25% to 17.51%, increased the mean structural similarity index measure (SSIM) from 79.43% to 91.72%, and increased the peak signal-to-noise ratio (PSNR) from 18.24 to 26.57 dB. Similarly, when motions were extended from 5 to 10 s, our approach decreased the average NRMSE from 60.30% to 21.04%, improved the mean SSIM from 33.86% to 90.33%, and increased the PSNR from 15.64 to 24.99 dB. The anatomical structures of the corrected images and the motion-free brain data were similar. [ABSTRACT FROM AUTHOR]

The cloudification of telecommunication network functions with 5G is a novelty that offers higher performance than that of previous generations. However, these virtual network functions (VNFs) are exposed to internet threats when hosted in the cloud, resulting in new security challenges. Another fact is that many VNFs vendors with different security policies will be implied in 5G deployment, creating a heterogeneous 5G network. The authorities also require data privacy enhancement in 5G deployment and there is the fact that mobile operators need to inspect data for malicious traffic detection. In this situation, how can network traffic inspections be conducted effectively without infringing on data privacy? This study addresses this gap by proposing a novel state-of-the-art hybrid deep neural network that combines a convolutional neural network (CNN) stacked to bidirectional long short-term memory (BiLSTM) and unidirectional long short-term memory (LSTM) for the deep inspection of network flow for malicious traffic detection. The approach utilizes federated learning (FL) to facilitate multiple VNFs vendors to collaboratively train the proposed model without sharing VNFs' raw data, which can mitigate the risk of data privacy violation. The proposed framework incorporates transport layer security (TLS) encryption to prevent data tempering or man-in-the-middle attacks between VNFs. The framework was validated through simulation using open-access benchmark datasets (InSDN and CICIDS2017). They achieved 99.99% and 99.58% accuracy and 0.048% and 0.617% false-positive rates for the InSDN and CICIDS2017 datasets, respectively, for FL. This study demonstrates the potential of hybrid deep learning-based FL for heterogeneous 5G network VNFs security monitoring. [ABSTRACT FROM AUTHOR]