Few-shot bearing fault detection based on multi-dimensional convolution and attention mechanism.

Bearings are critical components of industrial equipment and have a significant impact on the safety of industrial physical systems. Their failure may lead to equipment shutdown and accidents, posing a significant risk to production safety. However, it is difficult to obtain a large amount of bearing fault data in practice, which makes the problem of small sample size a major challenge for bearing fault detection. In addition, some methods may overlook important features in bearing vibration signals, leading to insufficient detection capabilities. To address the challenges in bearing fault detection, this paper proposed a few sample learning methods based on the multidimensional convolution and attention mechanism. First, a multichannel preprocessing method was designed to more effectively utilize the information in the bearing vibration signal. Second, by extracting multidimensional features and enhancing the attention to important features through multidimensional convolution operations and attention mechanisms, the feature extraction ability of the network was improved. Furthermore, nonlinear mapping of feature vectors into the metric space to calculate distance can better measure the similarity between samples, thereby improving the accuracy of bearing fault detection and providing important guarantees for the safe operation of industrial systems. Extensive experiments have shown that the proposed method has good fault detection performance under small sample conditions, which is beneficial for reducing machine downtime and economic losses.

A surface defect detection method for steel pipe based on improved YOLO.

Surface defect detection is of great significance as a tool to ensure the quality of steel pipes. The surface defects of steel pipes are charactered by insufficient texture, high similarity between different types of defects, large size differences, and high proportions of small targets, posing great challenges to defect detection algorithms. To overcome the above issues, we propose a novel steel pipe surface defect detection method based on the YOLO framework. First, for the problem of a low detection rate caused by insufficient texture and high similarity among different types of defects of steel pipes, a new backbone block is proposed. By increasing high-order spatial interaction and enhancing the capture of internal correlations of data features, different feature information for similar defects is extracted, thereby alleviating the false detection rate. Second, to enhance the detection performance for small defects, a new neck block is proposed. By fusing multiple features, the accuracy of steel pipe defect detection is improved. Third, for the problem of a low detection rate causing large size differences in steel pipe surface defects, a novel regression loss function that considers the aspect ratio and scale is proposed, and the focal loss is introduced to further solve the sample imbalance problem in steel pipe defect datasets. The experimental results show that the proposed method can effectively improve the accuracy of steel pipe surface defect detection.

Intelligent fault diagnosis algorithm of rolling bearing based on optimization algorithm fusion convolutional neural network.

As an essential component of mechanical equipment, the fault diagnosis of rolling bearings may not only guarantee the systematic operation of the equipment, but also minimize any financial losses caused by equipment shutdowns. Fault diagnosis algorithms based on convolutional neural networks (CNN) have been widely used. However, traditional CNNs have limited feature representation capabilities, thereby making it challenging to determine their hyperparameters. This paper proposes a fault diagnosis method that combines a 1D-CNN with an attention mechanism and hyperparameter optimization to overcome the aforementioned limitations; this method improves the search speed for optimal hyperparameters of CNN models, improves the diagnostic accuracy, and enhances the representation of fault feature information in CNNs. First, the 1D-CNN is improved by combining it with an attention mechanism to enhance the fault feature information. Second, a swarm intelligence algorithm based on Differential Evolution (DE) and Grey Wolf Optimization (GWO) is proposed, which not only improves the convergence accuracy, but also increases the search efficiency. Finally, the improved 1D-CNN alongside hyperparameters optimization are used to diagnose the faults of rolling bearings. By using the Case Western Reserve University (CWRU) and Jiangnan University (JNU) datasets, when compared to other common diagnosis models, the results demonstrate the usefulness and dependability of the DE-GWO-CNN algorithm in fault diagnosis applications by demonstrating the increased diagnostic accuracy and superior anti-noise capabilities of the proposed method. The fault diagnosis methodology presented in this paper can accurately identify faults and provide dependable fault classification, thereby assisting technicians in promptly resolving faults and minimizing equipment failures and operational instabilities.

EEG-Based Mental Workload Classification Method Based on Hybrid Deep Learning Model Under IoT.

Automatically detecting human mental workload to prevent mental diseases is highly important. With the development of information technology, remote detection of mental workload is expected. The development of artificial intelligence and Internet of Things technology will also enable the identification of mental workload remotely based on human physiological signals. In this paper, a method based on the spatial and time-frequency domains of electroencephalography (EEG) signals is proposed to improve the classification accuracy of mental workload. Moreover, a hybrid deep learning model is presented. First, the spatial domain features of different brain regions are proposed. Simultaneously, EEG time-frequency domain information is obtained based on wavelet transform. The spatial and time-frequency domain features are input into two types of deep learning models for mental workload classification. To validate the performance of the proposed method, the Simultaneous Task EEG Workload public database is used. Compared with the existing methods, the proposed approach shows higher classification accuracy. It provides a novel means of assessing mental workload.

Model pruning based on filter similarity for edge device deployment.

Filter pruning is widely used for inference acceleration and compatibility with off-the-shelf hardware devices. Some filter pruning methods have proposed various criteria to approximate the importance of filters, and then sort the filters globally or locally to prune the redundant parameters. However, the current criterion-based methods have problems: (1) parameters with smaller criterion values for extracting edge features are easily ignored, and (2) there is a strong correlation between different criteria, resulting in similar pruning structures. In this article, we propose a novel simple but effective pruning method based on filter similarity, which is used to evaluate the similarity between filters instead of the importance of a single filter. The proposed method first calculates the similarity of the filters pairwise in one convolutional layer and then obtains the similarity distribution. Finally, the filters with high similarity to others are deleted from the distribution or set to zero. In addition, the proposed algorithm does not need to specify the pruning rate for each layer, and only needs to set the desired FLOPs or parameter reduction to obtain the final compression model. We also provide iterative pruning strategies for hard pruning and soft pruning to satisfy the tradeoff requirements of accuracy and memory in different scenarios. Extensive experiments on various representative benchmark datasets across different network architectures demonstrate the effectiveness of our proposed method. For example, on CIFAR10, the proposed algorithm achieves 61.1% FLOPs reduction by removing 58.3% of the parameters, with no loss in Top-1 accuracy on ResNet-56; and reduces 53.05% FLOPs on ResNet-50 with only 0.29% Top-1 accuracy degradation on ILSVRC-2012.

Deep Reinforcement Learning for Charging Scheduling of Electric Vehicles Considering Distribution Network Voltage Stability.

The rapid development of electric vehicle (EV) technology and the consequent charging demand have brought challenges to the stable operation of distribution networks (DNs). The problem of the collaborative optimization of the charging scheduling of EVs and voltage control of the DN is intractable because the uncertainties of both EVs and the DN need to be considered. In this paper, we propose a deep reinforcement learning (DRL) approach to coordinate EV charging scheduling and distribution network voltage control. The DRL-based strategy contains two layers, the upper layer aims to reduce the operating costs of power generation of distributed generators and power consumption of EVs, and the lower layer controls the Volt/Var devices to maintain the voltage stability of the distribution network. We model the coordinate EV charging scheduling and voltage control problem in the distribution network as a Markov decision process (MDP). The model considers uncertainties of charging process caused by the charging behavior of EV users, as well as the uncertainty of uncontrollable load, system dynamic electricity price and renewable energy generation. Since the model has a dynamic state space and mixed action outputs, a framework of deep deterministic policy gradient (DDPG) is adopted to train the two-layer agent and the policy network is designed to output discrete and continuous control actions. Simulation and numerical results on the IEEE-33 bus test system demonstrate the effectiveness of the proposed method in collaborative EV charging scheduling and distribution network voltage stabilization.

RLSegNet: An Medical Image Segmentation Network Based on Reinforcement Learning.

In the area of medical image segmentation, the spatial information can be further used to enhance the image segmentation performance. And the 3D convolution is mainly used to better utilize the spatial information. However, how to better utilize the spatial information in the 2D convolution is still a challenging task. In this paper, we propose an image segmentation network based on reinforcement learning (RLSegNet), which can translate the image segmentation process into a serial of decision-making problem. The proposed RLSegNet is a U-shaped network, which is composed of three components: the feature extraction network, the Mask Prediction Network (MPNet), and the up-sampling network with the cascade attention module. The deep semantic feature in the image is first extracted by adopting the feature extraction network. Then, the Mask Prediction Network (MPNet) is proposed to generate the prediction mask for the current frame based on the prior knowledge (segmentation result). And the proposed cascade attention module is mainly used to generate the weighted feature mask so that the up-sampling network pays more attention to the interesting region. Specifically, the state, action and reward used in the reinforcement learning are redesigned in the proposed RLSegNet to translate the segmentation process as the decision-making process, which performs as the reinforcement learning to realize the brain tumor segmentation. Extensive experiments are conducted on the BRATS 2015 dataset to evaluate the proposed RLSegNet. The experimental results demonstrate that the proposed method can achieve a better segmentation performance, in comparison with other state-of-the-art methods.

Predicting Cardiovascular and Cerebrovascular Events Based on Instantaneous High-Order Singular Entropy and Deep Belief Network.

Automatically predicting cardiovascular and cerebrovascular events (CCEs) is a key technology that can prevent deaths and disabilities. Herein, we propose predicting CCE occurrences based on heart rate variability (HRV) analysis and a deep belief network (DBN). The proposed prediction algorithm uses eight novel HRV signal features, which are calculated based on the following steps. First, the instantaneous amplitude (IA), instantaneous frequency (IF), and instantaneous phase (IP) are calculated for the HRV signals. Second, the high-order cumulant is estimated for the HRV and its IA, IF, and IP. Third, a high-order singular entropy is calculated to measure the fluctuation in signals. Fourth, eight novel features are obtained and processed using a DBN classifier designed for CCE prediction. The DBN classification method, with the novel HRV features, outperformed existing methods in terms of accuracy. Thus, the scheme proposed herein provided a novel direction for predicting CCEs.

Optimizing Robotic Task Sequencing and Trajectory Planning on the Basis of Deep Reinforcement Learning.

The robot task sequencing problem and trajectory planning problem are two important issues in the robotic optimization domain and are solved sequentially in two separate levels in traditional studies. This paradigm disregards the potential synergistic impact between the two problems, resulting in a local optimum solution. To address this problem, this paper formulates a co-optimization model that integrates the task sequencing problem and trajectory planning problem into a holistic problem, abbreviated as the robot TSTP problem. To solve the TSTP problem, we model the optimization process as a Markov decision process and propose a deep reinforcement learning (DRL)-based method to facilitate problem solving. To validate the proposed approach, multiple test cases are used to verify the feasibility of the TSTP model and the solving capability of the DRL method. The real-world experimental results demonstrate that the DRL method can achieve a 30.54% energy savings compared to the traditional evolution algorithm, and the computational time required by the proposed DRL method is much shorter than those of the evolutionary algorithms. In addition, when adopting the TSTP model, a 18.22% energy reduction can be achieved compared to using the sequential optimization model.

A Sampling-Based Algorithm with the Metropolis Acceptance Criterion for Robot Motion Planning.

Motion planning is one of the important research topics of robotics. As an improvement of Rapidly exploring Random Tree (RRT), the RRT* motion planning algorithm is widely used because of its asymptotic optimality. However, the running time of RRT* increases rapidly with the number of potential path vertices, resulting in slow convergence or even an inability to converge, which seriously reduces the performance and practical value of RRT*. To solve this issue, this paper proposes a two-phase motion planning algorithm named Metropolis RRT* (M-RRT*) based on the Metropolis acceptance criterion. First, to efficiently obtain the initial path and start the optimal path search phase earlier, an asymptotic vertex acceptance criterion is defined in the initial path estimation phase of M-RRT*. Second, to improve the convergence rate of the algorithm, a nonlinear dynamic vertex acceptance criterion is defined in the optimal path search phase, which preferentially accepts vertices that may improve the current path. The effectiveness of M-RRT* is verified by comparing it with existing algorithms through the simulation results in three test environments.

Obstructive Sleep Apnea Detection Scheme Based on Manually Generated Features and Parallel Heterogeneous Deep Learning Model Under IoMT.

Obstructive sleep apnea (OSA) syndrome is a common sleep disorder and a key cause of cardiovascular and cerebrovascular diseases that seriously affect the lives and health of people. The development of Internet of Medical Things (IoMT) has enabled the remote diagnosis of OSA. The physiological signals of human sleep are sent to the cloud or medical facilities through Internet of Things, after which diagnostic models are employed for OSA detection. In order to improve the detection accuracy of OSA, in this study, a novel OSA detection system based on manually generated features and utilizing a parallel heterogeneous deep learning model in the context of IoMT is proposed, and the accuracy of the proposed diagnostic model is investigated. The OSA recognition scheme used in our model is based on short-term heart rate variability (HRV) signals extracted from ECG signals. First, the HRV signals and the linear and nonlinear features of HRV are combined into a one-dimensional (1-D) sequence. Simultaneously, a two-dimensional (2-D) HRV time-frequency spectrum image is obtained. The 1-D data sequences and 2-D images are coded in different branches of the proposed deep learning network for OSA diagnosis. To validate the performance of the proposed scheme, the Physionet Apnea-ECG public database is used. The proposed scheme outperforms the existing methods in terms of accuracy and provides a novel direction for OSA recognition.

Cluster-Based Structural Redundancy Identification for Neural Network Compression.

The increasingly large structure of neural networks makes it difficult to deploy on edge devices with limited computing resources. Network pruning has become one of the most successful model compression methods in recent years. Existing works typically compress models based on importance, removing unimportant filters. This paper reconsiders model pruning from the perspective of structural redundancy, claiming that identifying functionally similar filters plays a more important role, and proposes a model pruning framework for clustering-based redundancy identification. First, we perform cluster analysis on the filters of each layer to generate similar sets with different functions. We then propose a criterion for identifying redundant filters within similar sets. Finally, we propose a pruning scheme that automatically determines the pruning rate of each layer. Extensive experiments on various benchmark network architectures and datasets demonstrate the effectiveness of our proposed framework.

MR-Forest: A Deep Decision Framework for False Positive Reduction in Pulmonary Nodule Detection.

With the development of deep learning methods such as convolutional neural network (CNN), the accuracy of automated pulmonary nodule detection has been greatly improved. However, the high computational and storage costs of the large-scale network have been a potential concern for the future widespread clinical application. In this paper, an alternative Multi-ringed (MR)-Forest framework, against the resource-consuming neural networks (NN)-based architectures, has been proposed for false positive reduction in pulmonary nodule detection, which consists of three steps. First, a novel multi-ringed scanning method is used to extract the order ring facets (ORFs) from the surface voxels of the volumetric nodule models; Second, Mesh-LBP and mapping deformation are employed to estimate the texture and shape features. By sliding and resampling the multi-ringed ORFs, feature volumes with different lengths are generated. Finally, the outputs of multi-level are cascaded to predict the candidate class. On 1034 scans merging the dataset from the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine (AH-LUTCM) and the LUNA16 Challenge dataset, our framework performs enough competitiveness than state-of-the-art in false positive reduction task (CPM score of 0.865). Experimental results demonstrate that MR-Forest is a successful solution to satisfy both resource-consuming and effectiveness for automated pulmonary nodule detection. The proposed MR-forest is a general architecture for 3D target detection, it can be easily extended in many other medical imaging analysis tasks, where the growth trend of the targeting object is approximated as a spheroidal expansion.

Obstructive Sleep Apnea Recognition Based on Multi-Bands Spectral Entropy Analysis of Short-Time Heart Rate Variability.

Obstructive sleep apnea (OSA) syndrome is a common sleep disorder. As an alternative to polysomnography (PSG) for OSA screening, the current automatic OSA detection methods mainly concentrate on feature extraction and classifier selection based on physiological signals. It has been reported that OSA is, along with autonomic nervous system (ANS) dysfunction and heart rate variability (HRV), a useful tool for ANS assessment. Therefore, in this paper, eight novel indices of short-time HRV are extracted for OSA detection, which are based on the proposed multi-bands time-frequency spectrum entropy (MTFSE) method. In the MTFSE, firstly, the power spectrum of HRV is estimated by the Burg-AR model, and the time-frequency spectrum image (TFSI) is obtained. Secondly, according to the physiological significance of HRV, the TFSI is divided into multiple sub-bands according to frequency. Last but not least, by studying the Shannon entropy of different sub-bands and the relationships among them, the eight indices are obtained. In order to validate the performance of MTFSE-based indices, the Physionet Apnea-ECG database and K-nearest neighbor (KNN), support vector machine (SVM), and decision tree (DT) classification methods are used. The SVM classification method gets the highest classification accuracy, its average accuracy is 91.89%, the average sensitivity is 88.01%, and the average specificity is 93.98%. Undeniably, the MTFSE-based indices provide a novel idea for the screening of OSA disease.

A novel lung cancer detection algorithm for CADs based on SSP and Level Set.

The fuzzy degree of lung nodule boundary is the most important cue to judge the lung cancer in CT images. Based on this feature, the paper proposes a novel lung cancer detection method for CT images based on the super-pixels and the level set segmentation methods. In the proposed methods, the super-pixels method is used to segment the lung region and the suspected lung cancer lesion region in the CT image. The super-pixels method and a level set method are used to segment the suspected lung cancer lesion region simultaneously. Finally, the cancer is determined by the difference between results of the two segmentation methods. Experimental results show that the proposed algorithm has a high accuracy for lung cancer detection in CT images. For gross glass nodule, pleural nodule, the vascular nodules and solitary nodules, the sensitivity of the detection algorithm are respectively 91.3%, 96.3%, 80.9% and 82.3%.