Convolutional Autoencoder Research Articles

A Novel One‐Class Convolutional Autoencoder Combined With Excitation–Emission Matrix Fluorescence Spectroscopy for Authenticity Identification of Food

ABSTRACTIn this work, a novel one‐class classification algorithm one‐class convolutional autoencoder (OC‐CAE) was proposed for the detection of abnormal samples in the excitation–emission matrix (EEM) fluorescence spectra dataset. The OC‐CAE used Boxplot to analyze the reconstruction errors and used the LOF algorithm to handle features extracted by the hidden layer in the convolutional autoencoder (CAE). The fused information provides the basis for more accurate pattern recognition, ensures flexibility in model training, and can obtain higher model specificity, which is important in the field of food quality control. To demonstrate the reliability and advantages of OC‐CAE, two EEM cases related to the authentication of food including the Zhenjiang aromatic vinegar (ZAV) case and the camellia oil (CAO) case were studied. The results showed that OC‐CAE identified all abnormal samples in the two cases, reflecting excellent performance in the detection of abnormal samples, and that it, coupled with EEM, would be an effective tool for the authenticity identification of food.

Data-driven surrogate modeling and optimization of supercritical jet into supersonic crossflow

For the design and optimization of advanced aero-engines, the prohibitively computational resources required for numerical simulations pose a significant challenge, due to the extensive exploration of design parameters across a vast design space. Surrogate modeling techniques offer a viable alternative for efficiently emulating numerical results within a notably compressed timeframe. This study introduces parametric Reduced-Order Models (ROMs) based on Convolutional AutoEncoders (CAE), Fully Connected AutoEncoders (FCAE), and Proper Orthogonal Decomposition (POD) to fast emulate spatial distributions of physical variables for a supercritical jet into a supersonic crossflow under different operating conditions. To further accelerate the decision-making process, an optimization model is developed to enhance fuel-oxidizer mixing efficiency while minimizing total pressure loss. Results indicate that CAE-based ROMs exhibit superior prediction accuracy while FCAE-based ROMs show inferior predictive accuracy but minimal uncertainty. The latter may be ascribed to the markedly greater number of hyperparameters. POD-based ROMs underperform in regions of strong nonlinear flow dynamics, coupled with higher overall prediction uncertainties. Both AE- and POD-based ROMs achieve online predictions approximately 9 orders of magnitude faster than conventional simulations. The established optimization model enables the attainment of Pareto-optimal frontiers for spatial mixing deficiencies and total pressure recovery coefficient.

A Novel Hybridized Optimization Mechanism for Efficient Channel Estimation Using Adaptive and Attention-Based Convolutional Autoencoder in MIMO-NOMA for mm Wave Systems

A Novel Hybridized Optimization Mechanism for Efficient Channel Estimation Using Adaptive and Attention-Based Convolutional Autoencoder in MIMO-NOMA for mm Wave Systems

Predicting the severity of mood and neuropsychiatric symptoms from digital biomarkers using wearable physiological data and deep learning

Neuropsychiatric symptoms (NPS) and mood disorders are common in individuals with mild cognitive impairment (MCI) and increase the risk of progression to dementia. Wearable devices collecting physiological and behavioral data can help in remote, passive, and continuous monitoring of moods and NPS, overcoming limitations and inconveniences of current assessment methods. In this longitudinal study, we examined the predictive ability of digital biomarkers based on sensor data from a wrist-worn wearable to determine the severity of NPS and mood disorders on a daily basis in older adults with predominant MCI. In addition to conventional physiological biomarkers, such as heart rate variability and skin conductance levels, we leveraged deep-learning features derived from physiological data using a self-supervised convolutional autoencoder. Models combining common digital biomarkers and deep features predicted depression severity scores with a correlation of r = 0.73 on average, total severity of mood disorder symptoms with r = 0.67, and mild behavioral impairment scores with r = 0.69 in the study population. Our findings demonstrated the potential of physiological biomarkers collected from wearables and deep learning methods to be used for the continuous and unobtrusive assessments of mental health symptoms in older adults, including those with MCI. Trial registrationThis trial was registered with ClinicalTrials.gov (NCT05059353) on September 28, 2021, titled “Effectiveness and Safety of a Digitally Based Multidomain Intervention for Mild Cognitive Impairment”.

Health indicator construction based on normal states through FFT‐graph embedding

AbstractUnexpected faults in rotating machinery can lead to cascading disruptions of the entire work process, emphasizing the importance of early detection of performance degradation and identification of the current state. To accurately assess the health of a machine, this study introduces an FFT‐based raw vibration data preprocessing and graph representation technique, which analyses changes in frequency bands to detect early degradation trends in vibration data that may appear normal. The approach proposes a methodology that utilizes a graph convolutional autoencoder trained using only normal data to extract health indicators using the differences in the vectors as degradation progresses. This approach has the advantage of using only normal data to detect subtle performance degradation early and effectively represent health indicators accordingly.

Exact coherent structures in two-dimensional turbulence identified with convolutional autoencoders

Convolutional autoencoders are used to deconstruct the changing dynamics of two-dimensional Kolmogorov flow as $Re$ is increased from weakly chaotic flow at $Re=40$ to a chaotic state dominated by a domain-filling vortex pair at $Re=400$ . ‘Latent Fourier analysis’ (Page et al., Phys. Rev. Fluids6, 2021, p. 034402) reveals a detached class of bursting dynamics at $Re=40$ which merge with the low-dissipation dynamics as $Re$ is increased to $100$ and provides an efficient representation within which to find unstable periodic orbits (UPOs) using recurrent flow analysis. Focusing on initial guesses with energy in higher latent Fourier wavenumbers allows a significant number of high-dissipation-rate UPOs associated with the bursting events to be found for the first time. At $Re=400$ , the UPOs discovered at lower $Re$ move away from the attractor, and an entirely different embedding structure is formed within the network devoid of small-scale vortices. Here latent Fourier projections identify an associated ‘large-scale’ UPO which we believe to be a finite- $Re$ continuation of a solution to the Euler equations.

A novel intelligent multicross domain fault diagnosis of servo motor-bearing system based on Domain Generalized Graph Convolution Autoencoder

A novel intelligent multicross domain fault diagnosis of servo motor-bearing system based on Domain Generalized Graph Convolution Autoencoder

Automated Defect Detection in Atomic Resolution STEM Images: A Machine Learning Approach with Variational Convolutional Autoencoders

Automated Defect Detection in Atomic Resolution STEM Images: A Machine Learning Approach with Variational Convolutional Autoencoders

Intelligent recognition of structural health state of EV lithium-ion Battery using transfer learning based on X-ray computed tomography

The lithium-ion battery (LIB) achieves wide applications on electric vehicles (EVs). The morphology of LIB electrode is highly correlated to the performance and safety of EV. Therefore, it is significant to monitor the structural health state of LIB to guarantee a reliable operation of EV. Currently, few research focused on the intelligent recognition of LIB structural health state. To bridge the gap, this paper proposes an image-based method to conduct structural health state recognition of LIB. The geometric deformation of LIB electrode is recorded by X-ray computed tomography (CT) images under different structure health state. Then a novel transfer learning network is incorporated to enhance the generalization ability of model. In the network, prior knowledge is first acquired from source domain data to initialize a convolutional autoencoder (CAE). Then the CAE is fine-tuned on CT images (target domain data), and a structural deviation index is established to reflect the structure health condition. Once the index exceeds the pre-set threshold, the alarm is triggered. The performance of the proposed method was evaluated on experimental data, and the results proved that the proposed method can perform structural health state monitoring effectively, and transfer learning can improve the generalization ability of detection model significantly.

Quality grading method for Pleurotus eryngii during postharvest storage based on hyperspectral imaging and multiple quality indicators

During storage, Pleurotus eryngii is prone to spoilage, significantly affecting their commercial value. This study addresses the issue of inconsistent quality grading standards and low detection accuracy for Pleurotus eryngii. It proposes a method for grading the quality of Pleurotus eryngii during post-harvest low-temperature (4 °C) storage, achieving rapid quality grading based on hyperspectral imaging technology combined with clustering algorithms and comprehensive evaluation methods. According to 11 physical and chemical indexes analyzed by K-means algorithm and principal component analysis, the samples were divided into three categories: high, medium and inferior. These clustering results were then used as labels to build classification models. We compared the feature extraction capabilities of convolutional autoencoder and competitive adaptive reweighted sampling, as well as the modeling effectiveness of support vector machine, linear discriminant analysis, and partial least squares discriminant analysis. The models' practicality was validated using external data. The results showed that the convolutional autoencoder-support vector machine model performed the best in quality classification, with an accuracy of 91.58%, an F1 score of 91.36%, a precision of 89.65%, and a recall of 90.60%. In summary, this study demonstrates the rationality of using clustering algorithms for quality grading of Pleurotus eryngii and highlights the significant improvement in prediction accuracy and generalization ability achieved by convolutional autoencoder.

Multi-scale convolutional auto encoder for anomaly detection in 6G environment

With the increasing deployment of 6G networks in all industries, there is a growing risk of vulnerability and complexity due to continuous data flow from edge devices to specialized computers. One potential threat to 6G networks is fuzzing attacks, which involve sending random and invalid inputs to identify vulnerabilities and flaws. A successful fuzzing attack could compromise the network’s protocols, interfaces, and security mechanisms, leading to potential disruption or compromise of critical infrastructure. The proposed framework involves gathering relevant data from different sources within the 6G network and pre-processing it to prepare for analysis. Relevant features that indicate the presence of anomalies are identified using Tuna Swarm Optimization (TSO) Algorithm. The Multi-Scale Convolutional Auto Encoder (MSCAE) is then utilized by the proposed model to extract the feature and classify data. The intrusion Detection System is built to monitor and classify nodes producing anomalies. The proposed model is assessed utilizing various metrics, including recall, precision, accuracy, detection latency, and F1 score. The proposed framework achieved 97.50% accuracy, 94.81% precision, 93.50% F1-score, and 94.50% recall with notable improvements that surmount the deficiencies of previous studies. The results demonstrate that the proposed algorithm is more efficient and safe than current edge security methods, potentially mitigating the risk of fuzzing attacks in 6G networks.

A coarse and fine-grained deep multi view subspace clustering method for unsupervised fault diagnosis of rolling bearings

Abstract To address the issue of insufficient characterization of fault features in inherent vibration data that affects the performance of unsupervised learning-based fault diagnosis, a coarse and fine-grained deep multi view subspace clustering method (CFG-DMVSC) for unsupervised fault diagnosis of rolling bearings is proposed. The proposed method designs a convolutional autoencoder network based on the Gramian angular field transformation for multi-signal analysis domains. A multi-view coarse-grained self-expressive method based on information entropy is designed to handle differences in information across different views. Furthermore, a fine-grained common and independent information separation loss function based on mutual information is proposed to ensure compactness among multiple views. Both the Case Western Reserve University rolling bearing dataset and privately built bearing fault test bench data demonstrate that, compared to existing methods, the proposed method can perform coarse and fine-grained division in multi-view subspaces, achieving better clustering diagnosis performance on the extracted common information among views.

A hybrid semantic attribute-based zero-shot learning model for bearing fault diagnosis under unknown working conditions

Most current intelligent fault diagnosis models, dependent on specific working condition data for training, cannot effectively diagnose faults in unknown working conditions without data. Zero-shot learning (ZSL) can identify samples unseen during the training phase and has now been applied to the field of fault diagnosis. However, effective methods for constructing fault semantics in unknown conditions for zero-shot fault diagnosis are still lacking. This paper proposes a hybrid semantic attribute-based zero-shot learning model (HSAZLM) to address this issue. A novel approach to constructing the semantic space is introduced by combining manually defined semantic attributes (SA) with non-semantic attributes (NSA) to form hybrid semantic attributes (HSA). This addresses the issue of insufficient semantic information due to limitations in expert knowledge when defining SA. In the hybrid semantic attribute construction module, a denoising residual convolutional autoencoder (DRCAE) is employed as a semantic learning model to acquire NSA containing high-dimensional abstract features, enhancing the model's generalization and robustness. To verify the effectiveness and superiority of the proposed HSAZLM, experiments were conducted on both a publicly available bearing dataset and a self-built bearing dataset. The average accuracy rates are 96.82% and 96.42% respectively, exceeding the current state-of-the-art methods.

Distribution transformer mechanical faults diagnosis method incorporating cross-domain feature extraction and recognition of unknown-type faults

The complexity and uncertainty of vibration signals from distribution transformers pose significant challenges for diagnosing mechanical faults. To address this, this paper proposes a novel fault diagnosis model for distribution transformers, which combines a cross-domain fusion multi-scale convolutional autoencoder (CFMS-CAE) with an open-set domain adaptation classifier (OSDA-C). Specifically, in order to extract more comprehensive features, a convolutional autoencoder (CAE) model based on multi-output objectives is constructed to extract the time-frequency domain characteristics of transformer vibration signals. Multiple-scale convolutional layers are incorporated into the convolutional autoencoder to enable multi-range feature extraction. Additionally, parameter optimization is achieved using the crayfish optimization algorithm (COA). Subsequently, an open-set domain adaptation module is integrated into the convolutional neural network classifier to establish boundaries for each category and facilitate the identification of transformer fault categories, including unknown-type faults. The experimental results demonstrate that the proposed method is effective for fault identification in both dry-type and oil-immersed transformers, with average accuracy reaching 99.35% and 99.62%, respectively. For unknown-type faults, the accuracy also achieved 100% and 97.5%, respectively.

Sensor Fault Detection in Smart Extraterrestrial Habitats Using Unsupervised Learning

Various types of sensors are needed to monitor the health state of smart deep-space habitats. However, measured data can be affected by sensor faults, which influence the health management system and consequently the decision-making. In this paper, an unsupervised learning approach based on convolutional autoencoders (CAEs) is developed to detect anomalies in temperature and pressure sensors. The proposed method is systematically investigated using a habitat simulator (HabSim). Several illustrative examples are demonstrated in the nominal and hazardous states of the habitat, including micrometeorite impact and fire scenarios. The performance of the proposed method using CAEs is compared with that of existing methods using auto-associative neural networks (AANNs) and variational autoencoders. This comparison is based on typical evaluation metrics, including precision, recall, F1 score, training time, and testing time. The effect of temperature–pressure coupling on the detection performance of CAEs and AANNs is explored by training different data-driven models, including one with temperature sensors, one with pressure sensors, and one with both temperature and pressure sensors. The effect of the number of faulty sensors on the performance of CAEs is studied, as with an increase in the number of faulty sensors, redundant information among the sensors is reduced. The capability of CAEs to change the number of sensors without redesigning the network architecture and retraining the neural network is investigated and demonstrated. The capabilities and limitations of the proposed solution are discussed.

SCAE-Stacked Convolutional Autoencoder for Fault Diagnosis of a Hydraulic Piston Pump with Limited Data Samples.

Deep learning (DL) models require enormous amounts of data to produce reliable diagnosis results. The superiority of DL models over traditional machine learning (ML) methods in terms of feature extraction, feature dimension reduction, and diagnosis performance has been shown in various studies of fault diagnosis systems. However, data acquisition can sometimes be compromised by sensor issues, resulting in limited data samples. In this study, we propose a novel DL model based on a stacked convolutional autoencoder (SCAE) to address the challenge of limited data. The innovation of the SCAE model lies in its ability to enhance gradient information flow and extract richer hierarchical features, leading to superior diagnostic performance even with limited and noisy data samples. This article describes the development of a fault diagnosis method for a hydraulic piston pump using time-frequency visual pattern recognition. The proposed SCAE model has been evaluated on limited data samples of a hydraulic piston pump. The findings of the experiment demonstrate that the suggested approach can achieve excellent diagnostic performance with over 99.5% accuracy. Additionally, the SCAE model has outperformed traditional DL models such as deep neural networks (DNN), standard stacked sparse autoencoders (SSAE), and convolutional neural networks (CNN) in terms of diagnosis performance. Furthermore, the proposed model demonstrates robust performance under noisy data conditions, further highlighting its effectiveness and reliability.

Local phase-constrained convolutional autoencoder network for identifying multivariate geochemical anomalies

Autoencoder is a powerful tool for identifying multivariate geochemical anomalies. However, existing autoencoder-based geochemical anomaly detection methods primarily rely on a global reconstruction error (e.g., mean square error) to define the lower limit of geochemical anomalies, neglecting the common, local structure information of geochemical data. This limitation inevitably results in the decreased accuracy of geochemical anomaly identification. This study proposed a local Phase-Constrained Convolutional AutoEncoder network (PC-CAE) for the identification of multivariate geochemical anomalies. Initially, we employed a local Fourier transform to extract phase information from both the original and the reconstructed data. Subsequently, a convolutional autoencoder network was utilized to learn the latent representation of geochemical background, using the local phase difference between the original and reconstructed data to preserve the local data structure related to geology setting. Additionally, an adaptive weighting strategy was employed to mitigate the overfitting issue. The training samples with high reconstruction errors were finally identified as anomalies. We tested the validity of PC-CAE using the stream sediment geochemical dataset collected in the Jiaodong gold province, Eastern China. The results demonstrated that PC-CAE outperforms existing convolutional autoencoder network and spectrum–area multifractal model in identifying multivariate geochemical anomalies associated with Au mineralization.

Design for additive manufacturing of topology-optimized structures based on deep learning and transfer learning

PurposeThis paper aims to improve the manufacturability of additive manufacturing (AM) for topology-optimized (TO) structures. Enhancement of manufacturability focuses on modifying geometric constraints and classifying the building orientation (BO) of AM parts to reduce stresses and support structures (SSs). To this end, artificial intelligence (AI) networks are being developed to automate design for additive manufacturing (DfAM).Design/methodology/approachThis study considers three geometric constraints for their correction by convolutional autoencoders (CAEs) and transfer learning (TL). Furthermore, BOs of AM parts are classified using generative adversarial (GAN) and classification networks to reduce the SS. To verify the results, finite element analysis (FEA) is performed to compare the stresses of modified components with the original ones. Moreover, one sample is produced by the laser-based powder bed fusion (LB-PBF) in the BO predicted by the AI to observe its SSs.FindingsCAE and TL resulted in promoting the manufacturability of TO components. FEA demonstrated that enhancing manufacturability leads to a 50% reduction in stresses. Additionally, training GAN and pre-training the ResNet-18 resulted in 80%, 95% and 96% accuracy for training, validation and testing. The production of a sample with LB-PBF demonstrated that the predicted BO by ResNet-18 does not require SSs.Originality/valueThis paper provides an automatic platform for DfAM of TO parts. Consequently, complex TO parts can be designed most feasibly and manufactured by AM technologies with minimal material usage, residual stresses and distortions.

CAEM-GBDT: a cancer subtype identifying method using multi-omics data and convolutional autoencoder network.

The identification of cancer subtypes plays a very important role in the field of medicine. Accurate identification of cancer subtypes is helpful for both cancer treatment and prognosis Currently, most methods for cancer subtype identification are based on single-omics data, such as gene expression data. However, multi-omics data can show various characteristics about cancer, which also can improve the accuracy of cancer subtype identification. Therefore, how to extract features from multi-omics data for cancer subtype identification is the main challenge currently faced by researchers. In this paper, we propose a cancer subtype identification method named CAEM-GBDT, which takes gene expression data, miRNA expression data, and DNA methylation data as input, and adopts convolutional autoencoder network to identify cancer subtypes. Through a convolutional encoder layer, the method performs feature extraction on the input data. Within the convolutional encoder layer, a convolutional self-attention module is embedded to recognize higher-level representations of the multi-omics data. The extracted high-level representations from the convolutional encoder are then concatenated with the input to the decoder. The GBDT (Gradient Boosting Decision Tree) is utilized for cancer subtype identification. In the experiments, we compare CAEM-GBDT with existing cancer subtype identifying methods. Experimental results demonstrate that the proposed CAEM-GBDT outperforms other methods. The source code is available from GitHub at https://github.com/gxh-1/CAEM-GBDT.git.

Flow field prediction in bed configurations: A parametric spatio-temporal convolutional autoencoder approach

The use of deep learning methods for modeling fluid flow has drawn a lot of attention in the past few years. Here we present a data-driven reduced-order model (ROM) for predicting flow fields in a bed configuration of hot particles. The ROM consists of a parametric spatio-temporal convolutional autoencoder. The neural network architecture comprises two main components. The first part resolves the spatial and temporal dependencies present in the input sequence, while the second part of the architecture is responsible for predicting the solution at the subsequent timestep based on the information gathered from the preceding part. We also propose the utilization of a post-processing non-trainable output layer following the decoding path to incorporate the physical knowledge, e.g. no-slip condition, into the prediction. The ROM is evaluated by comparing its predicted solution with the high-fidelity counterpart. In addition, proper orthogonal decomposition (POD) is employed to systematically analyze and compare the dominant structures present in both sets of solutions. The assessment of the ROM for a bed configuration with variable particle temperature showed accurate results at a fraction of the computational cost required by traditional numerical simulation methods.