MR‐DCAE: Manifold regularization‐based deep convolutional autoencoder for unauthorized broadcasting identification

Innovation in public health surveillance for social distancing during the COVID-19 pandemic: A deep learning and object detection based novel approach

The Corona Virus Disease (COVID-19) has a huge impact on all of humanity, and people's disregard for COVID-19 regulations has sped up the disease's spread. Our study uses a state-of-the-art object detection model like YOLOv4 (You Only Look Once, version 4), a very effective tool, on real-time 25fps, 1920 X 1080 video data streamed live by a camera-mounted Unmanned Aerial Vehicle (UAV) quad-copter to observe proper maintenance of social distance in an area of 35m range in this study. The model has demonstrated remarkable efficacy in identifying and quantifying instances of social distancing, with an accuracy of 82% and little latency. It has been able to work efficiently with real-time streaming at 25-30 ms. Our model is based on CSPDarkNet-53, which was trained on the MS COCO dataset for image classification. It includes additional layers to capture feature maps from different phases. Additionally, the model's neck is made up of PANet, which is used to aggregate the parameters from various CSPDarkNet-53 layers. The CSPDarkNet-53's 53 convolutional layers are followed by 53 more layers in the model head, for a total of 106 completely convolutional layers in the design. This architecture is further integrated with YOLOv3, resulting in the YOLOv4 model, which will be used by our detection model. Furthermore, to differentiate humans The aforementioned method was used to evaluate drone footage and count social distance violations in real time. Our findings show that our model was reliable and successful at detecting social distance violations in real-time with an average accuracy of 82%.

Differences in whole blood before and after hemodialysis session of subjects with chronic kidney disease measured by Raman spectroscopy

This study aimed to identify differences in the composition of whole blood of patients with chronic kidney disease (CKD), before and after a hemodialysis session (HDS), and possible differences in blood composition between stages and between genders using Raman spectroscopy and principal component analysis (PCA). Whole blood samples were collected from 40 patients (20 women and 20 men), before and after a HDS. Raman spectra were obtained and the spectra were evaluated by PCA and partial least squares (PLS) regression. Mean spectra and difference spectrum between the groups were calculated: stages Before and After HDS, and gender Women and Men, which had their most intense peaks identified. Stage: mean spectra and difference spectrum indicated positive peaks that could be assigned to red blood cells, hemoglobin and deoxi-hemoglobin in the group Before HDS. There was no statistically significant difference by PCA. Gender: mean spectra and difference spectrum Before HDS indicated positive peaks that could be assigned to red blood cells, hemoglobin and deoxi-hemoglobin with greater intensity in the group Women, and negative peaks to white blood cells and serum, with greater intensity in the group Men. There was statistically significant difference by PCA, which also identified the peaks assigned to white blood cells, serum and porphyrin for Women and red blood cells and amino acids (tryptophan) for Men. PLS model was able to classify the spectra of the gender with 83.7% accuracy considering the classification per patient. The Raman technique highlighted gender differences in pacients with CKD.

A hybrid EEG classification model using layered cascade deep learning architecture

The problem of multi-class classification is always a challenge in the field of EEG (electroencephalogram)-based seizure detection. The traditional studies focus on computing or learning a set of features from EEG to distinguish between different patterns. However, the extraction of characteristic information becomes increasingly difficult as the number of EEG types increases. To address this issue, a creative EEG classification technique is proposed by employing a principal component analysis network (PCANet) coupled with phase space reconstruction (PSR) and power spectrum density (PSD). We have introduced the PSR and PSD to prepare the inputs, where dynamic and frequency information are exposed from deep within PCANet. It is remarkable that a layered cascade strategy is designed to make a powerful deep learner according to the rule of one network vs one task (OVO). The proposed method has achieved greater effects than the individual models and shown superior performance in comparison with state-of-the-art algorithms, which present 98.0% of sensitivity, 99.90% of specificity, and 99.07% of accuracy. Our ensemble PCANet model works in an assembly line-like manner, obviating the need for hand-craft features. Results demonstrate that the proposed scheme can greatly enhances the accuracy and robustness of seizure detection from EEG signals.

Efficient Generalized Electroencephalography-Based Drowsiness Detection Approach with Minimal Electrodes

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an electroencephalography (EEG)-based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM), the K nearest neighbor (KNN), the Naive Bayes (NB), the Decision Tree (DT), and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake and drowsy). Segmentation into 10 s intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries.

A framework of evolutionary optimized convolutional neural network for classification of shang and chow dynasties bronze decorative patterns

As a UNESCO World Cultural Heritage, the aesthetic value of bronze artifacts from the Shang and Chow Dynasties has had a profound influence on Chinese traditional culture and art. To facilitate the digital preservation and protection of these Shang and Chow bronze artifacts (SCB), it becomes imperative to categorize their decorative patterns. Therefore, a SCB pattern classification method of differential evolution called Shang and Chow Bronze Convolutional Neural Network (SCB-CNN) is proposed. Firstly, the original bronze decorative patterns of Shang and Chow dynasties are collected, and the samples are expanded through image augmentation technology to form a training dataset. Secondly, based on the classical convolutional neural network structure, the recognition and classification of bronze patterns are implemented by adjusting the network parameters. Then, the initial parameters of the convolutional neural network are optimized by differential evolution algorithm, and the optimized SCB-CNN is simulated. Finally, comparative experiments were conducted between the optimized SCB-CNN, the unoptimized model, VGG-Net, and GoogleNet. The experimental results indicate that the optimized SCB-CNN significantly reduces training time while maintaining fast prediction speed, convergence speed, and high accuracy. This study provides new insights for the inheritance and innovation research of SCB patterns.

A real-time arbitrary-shape text detector

It is challenging to detect arbitrary-shape text accurately and effectively in natural scenes. While many methods have been implemented for arbitrary-shape text detection, most cannot achieve real-time detection or meet practical needs. In this work, we propose a YOLOv6-based detector that can effectively implement arbitrary-shape text detection and achieve real-time detection. We include two additional branches in the neck part of the YOLOv6 network to adapt the network to text detection, and the output side uses the pixel aggregation (PA) algorithm to decouple the PA output to use it as the detection head of the model. Experiments on benchmark Total-Text, CTW1500, ICDAR2015, and MSRA-TD500 showed that the proposed method outperformed competing methods in terms of detection accuracy and running time. Specifically, our method achieved an F-measure of 84.1% at 291.8 FPS for 640 × 640 Total-Text images and an F-measure of 81.5% at 199.6 FPS for 896 × 896 ICDAR2015 incidental text images.

A real-time constellation image classification method of wireless communication signals based on the lightweight network MobileViT

Automatic modulation classification (AMC) is a challenging topic in the development of cognitive radio, which can sense and learn surrounding electromagnetic environments and help to make corresponding decisions. In this paper, we propose to complete the real-time AMC through constructing a lightweight neural network MobileViT driven by the clustered constellation images. Firstly, the clustered constellation images are transformed from I/Q sequences to help extract robust and discriminative features. Then the lightweight neural network called MobileViT is developed for the real-time constellation image classification. Experimental results on the public dataset RadioML 2016.10a with edge computing platform demonstrate the superiority and efficiency of MobileViT. Furthermore, the extensive ablation tests prove the robustness of the proposed method to the learning rate and batch size. To the best of our knowledge, this is the first attempt to deploy the deep learning model to complete the real-time classification of modulation schemes of received signals at the edge.

Spatial deformable transformer for 3D point cloud registration

Deformable attention only focuses on a small group of key sample-points around the reference point and make itself be able to capture dynamically the local features of input feature map without considering the size of the feature map. Its introduction into point cloud registration will be quicker and easier to extract local geometric features from point cloud than attention. Therefore, we propose a point cloud registration method based on Spatial Deformable Transformer (SDT). SDT consists of a deformable self-attention module and a cross-attention module where the deformable self-attention module is used to enhance local geometric feature representation and the cross-attention module is employed to enhance feature discriminative capability of spatial correspondences. The experimental results show that compared to state-of-the-art registration methods, SDT has a better matching recall, inlier ratio, and registration recall on 3DMatch and 3DLoMatch scene, and has a better generalization ability and time efficiency on ModelNet40 and ModelLoNet40 scene.

LeaNet: Lightweight U-shaped architecture for high-performance skin cancer image segmentation

Skin cancer diagnosis often relies on image segmentation as a crucial aid, and a high-performance segmentation can lower misdiagnosis risks. Part of the medical devices often have limited computing power for deploying image segmentation algorithms. However, existing high-performance algorithms for image segmentation primarily rely on computationally intensive large models, making it challenging to meet the lightweight deployment requirement of medical devices. State-of-the-art lightweight models are not able to capture both local and global feature information of lesion edges due to their model structures, result in pixel loss of lesion edge. To tackle this problem, we propose LeaNet, a novel U-shaped network for high-performance yet lightweight skin cancer image segmentation. Specifically, LeaNet employs multiple attention blocks in a lightweight symmetric U-shaped design. Each blocks contains a dilated efficient channel attention (DECA) module for global and local contour information and an inverted external attention (IEA) module to improve information correlation between data samples. Additionally, LeaNet uses an attention bridge (AB) module to connect the left and right sides of the U-shaped architecture, thereby enhancing the model's multi-level feature extraction capability. We tested our model on ISIC2017 and ISIC2018 datasets. Compared with large models like ResUNet, LeaNet improved the ACC, SEN, and SPEC metrics by 1.09 %, 2.58 %, and 1.6 %, respectively, while reducing the model's parameter number and computational complexity by 570x and 1182x. Compared with lightweight models like MALUNet, LeaNet achieved improvements of 2.07 %, 4.26 %, and 3.11 % in ACC, SEN, and SPEC, respectively, reducing the parameter number and computational complexity by 1.54x and 1.04x.

Machine learning-aided hydrothermal carbonization of biomass for coal-like hydrochar production: Parameters optimization and experimental verification

Biomass to coal-like hydrochar via hydrothermal carbonization (HTC) is a promising route for sustainability development. Yet conventional experimental method is time-consuming and costly to optimize HTC conditions and characterize hydrochar. Herein, machine learning was employed to predict the fuel properties of hydrochar. Random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB) models were developed, presenting acceptable prediction performance with R2 at 0.825---0.985 and root mean square error (RMSE) at 1.119---5.426, and XGB outperformed RF and SVM. The model interpretation indicated feedstock ash content, reaction temperature, and solid to liquid ratio were the three decisive factors. The optimized XGB multi-task model via feature re-examination illustrated improved generalization ability with R2 at 0.927 and RMSE at 3.279. Besides, the parameters optimization and experimental verification with wheat straw as feedstock further demonstrated the huge application potential of machine learning in hydrochar engineering.

L. Ouahidi B. A robust intrusion detection system based on a shallow learning model and feature extraction techniques

The escalating prevalence of cybersecurity risks calls for a focused strategy in order to attain efficient resolutions. This study introduces a detection model that employs a tailored methodology integrating feature selection using SHAP values, a shallow learning algorithm called PV-DM, and machine learning classifiers like XGBOOST. The efficacy of our suggested methodology is highlighted by employing the NSL-KDD and UNSW-NB15 datasets. Our approach in the NSL-KDD dataset exhibits exceptional performance, with an accuracy of 98.92%, precision of 98.92%, recall of 95.44%, and an F1-score of 96.77%. Notably, this performance is achieved by utilizing only four characteristics, indicating the efficiency of our approach. The proposed methodology achieves an accuracy of 82.86%, precision of 84.07%, recall of 77.70%, and an F1-score of 80.20% in the UNSW-NB15 dataset, using only six features. Our research findings provide substantial evidence of the enhanced performance of the proposed model compared to a traditional deep-learning model across all performance metrics.

Application of the Five-Step Phase-Shifting Method in Reflective Ghost Imaging for Efficient Phase Reconstruction

The conventional approach to phase reconstruction in Reflective Ghost Imaging (RGI) typically involves the introduction of three reference screens into the reference path, deeming the Fourier transform step indispensable. However, this method introduces complexity to the system and raises concerns regarding potential errors in phase retrieval. In response to these challenges, we advocate for adopting the Five-Step Phase-Shifting (FSPS) method in the RGI system. This method presents two key advantages over traditional approaches: (1) It streamlines the phase reconstruction process by eliminating the requirement for a Fourier inverse transform. (2) It avoids the need to insert objects into the reference optical path, simplifying the computation of reference optical path intensity and enabling seamless application to Computational Ghost Imaging (CGI), overcoming the constraints of Dual-Arm Ghost Imaging (DAGI). We substantiate the theoretical proposition through numerical simulations involving two intricate objects. Furthermore, our discussion delves into exploring the influence of varying reflective angles on the phase reconstruction performance.

Dynamical graph neural network with attention mechanism for epilepsy detection using single channel EEG

Epilepsy is a chronic brain disease, and identifying seizures based on electroencephalogram (EEG) signals would be conducive to implement interventions to help patients reduce impairment and improve quality of life. In this paper, we propose a classification algorithm to apply dynamical graph neural network with attention mechanism to single channel EEG signals. Empirical mode decomposition (EMD) are adopted to construct graphs and the optimal adjacency matrix is obtained by model optimization. A multilayer dynamic graph neural network with attention mechanism is proposed to learn more discriminative graph features. The MLP-pooling structure is proposed to fuse graph features. We performed 12 classification tasks on the epileptic EEG database of the University of Bonn, and experimental results showed that using 25 runs of ten-fold cross-validation produced the best classification results with an average of 99.83[Formula: see text] accuracy, 99.91[Formula: see text] specificity, 99.78[Formula: see text] sensitivity, 99.87[Formula: see text] precision, and 99.47[Formula: see text] [Formula: see text] score for the 12 classification tasks.

Uncertainty-guided transformer for brain tumor segmentation

Multi-model data can enhance brain tumor segmentation for the rich information it provides. However, it also introduces some redundant information that interferes with the segmentation estimation, as some modalities may catch features irrelevant to the tissue of interest. Besides, the ambiguous boundaries and irregulate shapes of different grade tumors lead to a non-confidence estimate of segmentation quality. Given these concerns, we exploit an uncertainty-guided U-shaped transformer with multiple heads to construct drop-out format masks for robust training. Specifically, our drop-out masks are composed of boundary mask, prior probability mask, and conditional probability mask, which can help our approach focus more on uncertainty regions. Extensive experimental results show that our method achieves comparable or higher results than previous state-of-the-art brain tumor segmentation methods, achieving average dice coefficients of [Formula: see text] and Hausdorff distance of 4.91 on the BraTS2021 dataset. Our code is freely available at https://github.com/chaineypung/BTS-UGT.

Neural-Symbolic Ensemble Learning for early-stage prediction of critical state of Covid-19 patients

Recently, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied to many domains of interest including medical diagnosis. Due to the availability of a large quantity of data, it is possible to build reliable AI systems that assist humans in making decisions. The recent Covid-19 pandemic quickly spread over the world causing serious health problems and severe economic and social damage. Computer scientists are actively working together with doctors on different ML models to diagnose Covid-19 patients using Computed Tomography (CT) scans and clinical data. In this work, we propose a neural-symbolic system that predicts if a Covid-19 patient arriving at the hospital will end in a critical condition. The proposed system relies on Deep 3D Convolutional Neural Networks (3D-CNNs) for analyzing lung CT scans of Covid-19 patients, Decision Trees (DTs) for predicting if a Covid-19 patient will eventually pass away by analyzing its clinical data, and a neural system that integrates the previous ones using Hierarchical Probabilistic Logic Programs (HPLPs). Predicting if a Covid-19 patient will end in a critical condition is useful for managing the limited number of intensive care at the hospital. Moreover, knowing early that a Covid-19 patient could end in serious conditions allows doctors to gain early knowledge on patients and provide special treatment to those predicted to finish in critical conditions. The proposed system, entitled Neural HPLP, obtains good performance in terms of area under the receiver operating characteristic and precision curves with values of about 0.96 for both metrics. Therefore, with Neural HPLP, it is possible not only to efficiently predict if Covid-19 patients will end in severe conditions but also possible to provide an explanation of the prediction. This makes Neural HPLP explainable, interpretable, and reliable. Graphical abstract Representation of Neural HPLP. From top to bottom, the two different types of data collected from the same patient and used in this project are represented. This data feeds the two different machine learning systems and the integration of the two systems using Hierarchical Probabilistic Logic Program.

COVID-19 Detection from Chest X-rays Using Trained Output Based Transfer Learning Approach

The recent Coronavirus disease (COVID-19), which started in 2019, has spread across the globe and become a global pandemic. The efficient and effective COVID-19 detection using chest X-rays helps in early detection and curtailing the spread of the disease. In this paper, we propose a novel Trained Output-based Transfer Learning (TOTL) approach for COVID-19 detection from chest X-rays. We start by preprocessing the Chest X-rays of the patients with techniques like denoising, contrasting, segmentation. These processed images are then fed to several pre-trained transfer learning models like InceptionV3, InceptionResNetV2, Xception, MobileNet, ResNet50, ResNet50V2, VGG16, and VGG19. We fine-tune these models on the processed chest X-rays. Then we further train the outputs of these models using a deep neural network architecture to achieve enhanced performance and aggregate the capabilities of each of them. The proposed model has been tested on four recent COVID-19 chest X-rays datasets by computing several popular evaluation metrics. The performance of our model has also been compared with various deep transfer learning models and several contemporary COVID-19 detection methods. The obtained results demonstrate the efficiency and efficacy of our proposed model.

Rapid quantification of COVID-19 pneumonia burden from computed tomography with convolutional long short-term memory networks

Purpose: Quantitative lung measures derived from computed tomography (CT) have been demonstrated to improve prognostication in coronavirus disease 2019 (COVID-19) patients but are not part of clinical routine because the required manual segmentation of lung lesions is prohibitively time consuming. We aim to automatically segment ground-glass opacities and high opacities (comprising consolidation and pleural effusion). Approach: We propose a new fully automated deep-learning framework for fast multi-class segmentation of lung lesions in COVID-19 pneumonia from both contrast and non-contrast CT images using convolutional long short-term memory (ConvLSTM) networks. Utilizing the expert annotations, model training was performed using five-fold cross-validation to segment COVID-19 lesions. The performance of the method was evaluated on CT datasets from 197 patients with a positive reverse transcription polymerase chain reaction test result for SARS-CoV-2, 68 unseen test cases, and 695 independent controls. Results: Strong agreement between expert manual and automatic segmentation was obtained for lung lesions with a Dice score of 0.89 ± 0.07 ; excellent correlations of 0.93 and 0.98 for ground-glass opacity (GGO) and high opacity volumes, respectively, were obtained. In the external testing set of 68 patients, we observed a Dice score of 0.89 ± 0.06 as well as excellent correlations of 0.99 and 0.98 for GGO and high opacity volumes, respectively. Computations for a CT scan comprising 120 slices were performed under 3 s on a computer equipped with an NVIDIA TITAN RTX GPU. Diagnostically, the automated quantification of the lung burden % discriminate COVID-19 patients from controls with an area under the receiver operating curve of 0.96 (0.95-0.98). Conclusions: Our method allows for the rapid fully automated quantitative measurement of the pneumonia burden from CT, which can be used to rapidly assess the severity of COVID-19 pneumonia on chest CT.

Atom Search Optimization with Deep Learning Enabled Arabic Sign Language Recognition for Speaking and Hearing Disability Persons

Sign language has played a crucial role in the lives of impaired people having hearing and speaking disabilities. They can send messages via hand gesture movement. Arabic Sign Language (ASL) recognition is a very difficult task because of its high complexity and the increasing intraclass similarity. Sign language may be utilized for the communication of sentences, letters, or words using diverse signs of the hands. Such communication helps to bridge the communication gap between people with hearing impairment and other people and also makes it easy for people with hearing impairment to express their opinions. Recently, a large number of studies have been ongoing in developing a system that is capable of classifying signs of dissimilar sign languages into the given class. Therefore, this study designs an atom search optimization with a deep convolutional autoencoder-enabled sign language recognition (ASODCAE-SLR) model for speaking and hearing disabled persons. The presented ASODCAE-SLR technique mainly aims to assist the communication of speaking and hearing disabled persons via the SLR process. To accomplish this, the ASODCAE-SLR technique initially pre-processes the input frames by a weighted average filtering approach. In addition, the ASODCAE-SLR technique employs a capsule network (CapsNet) feature extractor to produce a collection of feature vectors. For the recognition of sign language, the DCAE model is exploited in the study. At the final stage, the ASO algorithm is utilized as a hyperparameter optimizer which in turn increases the efficacy of the DCAE model. The experimental validation of the ASODCAE-SLR model is tested using the Arabic Sign Language dataset. The simulation analysis exhibit the enhanced performance of the ASODCAE-SLR model compared to existing models.

Development of an approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms

Purpose: In stable coronary artery disease (CAD), reduction in mortality and/or myocardial infarction with revascularization over medical therapy has not been reliably achieved. Coronary arteries are usually extracted to perform stenosis detection. As such, developing accurate segmentation of vascular structures and quantification of coronary arterial stenosis in invasive coronary angiograms (ICA) is necessary. Approach: A multi-input and multiscale (MIMS) U-Net with a two-stage recurrent training strategy was proposed for the automatic vessel segmentation. The proposed model generated a refined prediction map with the following two training stages: (i) stage I coarsely segmented the major coronary arteries from preprocessed single-channel ICAs and generated the probability map of arteries; and (ii) during the stage II, a three-channel image consisting of the original preprocessed image, a generated probability map, and an edge-enhanced image generated from the preprocessed image was fed to the proposed MIMS U-Net to produce the final segmentation result. After segmentation, an arterial stenosis detection algorithm was developed to extract vascular centerlines and calculate arterial diameters to evaluate stenotic level. Results: Experimental results demonstrated that the proposed method achieved an average Dice similarity coefficient of 0.8329, an average sensitivity of 0.8281, and an average specificity of 0.9979 in our dataset with 294 ICAs obtained from 73 patients. Moreover, our stenosis detection algorithm achieved a true positive rate of 0.6668 and a positive predictive value of 0.7043. Conclusions: Our proposed approach has great promise for clinical use and could help physicians improve diagnosis and therapeutic decisions for CAD.

Development of a Low-Cost 6 DOF Brick Tracking System for Use in Advanced Gas-Cooled Reactor Model Tests

This paper presents the design of a low-cost, compact instrumentation system to enable six degree of freedom motion tracking of acetal bricks within an experimental model of a cracked Advanced Gas-Cooled Reactor (AGR) core. The system comprises optical and inertial sensors and capitalises on the advantages offered by data fusion techniques. The optical system tracks LED indicators, allowing a brick to be accurately located even in cluttered images. The LED positions are identified using a geometrical correspondence algorithm, which was optimised to be computationally efficient for shallow movements, and complex camera distortions are corrected using a versatile Incident Ray-Tracking calibration. Then, a Perspective-Ray-based Scaled Orthographic projection with Iteration (PRSOI) algorithm is applied to each LED position to determine the six degree of freedom pose. Results from experiments show that the system achieves a low Root Mean Squared (RMS) error of 0.2296 mm in x, 0.3943 mm in y, and 0.0703 mm in z. Although providing an accurate measurement solution, the optical tracking system has a low sample rate and requires the line of sight to be maintained throughout each test. To increase the robustness, accuracy, and sampling frequency of the system, the optical system can be augmented with an Inertial Measurement Unit (IMU). This paper presents a method to integrate the optical system and IMU data by accurately timestamping data from each set of sensors and aligning the two coordinate axes. Once miniaturised, the developed system will be used to track smaller components within the AGR models that cannot be tracked with current instrumentation, expanding reactor core modelling capabilities.

A High-Dimensional and Small-Sample Submersible Fault Detection Method Based on Feature Selection and Data Augmentation

The fault detection of manned submersibles plays a very important role in protecting the safety of submersible equipment and personnel. However, the diving sensor data is scarce and high-dimensional, so this paper proposes a submersible fault detection method, which is made up of feature selection module based on hierarchical clustering and Autoencoder (AE), the improved Deep Convolutional Generative Adversarial Networks (DCGAN)-based data augmentation module and fault detection module using Convolutional Neural Network (CNN) with LeNet-5 structure. First, feature selection is developed to select the features that have a strong correlation with failure event. Second, data augmentation model is conducted to generate sufficient data for training the CNN model, including rough data generation and data refiners. Finally, a fault detection framework with LeNet-5 is trained and fine-tuned by synthetic data, and tested using real data. Experiment results based on sensor data from submersible hydraulic system demonstrate that our proposed method can successfully detect the fault samples. The detection accuracy of proposed method can reach 97% and our method significantly outperforms other classic detection algorithms.