Damaged cable identification in cable-stayed bridge from bridge deck strain measurements using support vector machine

A new two-step approach is developed for damaged cable identification in a cable-stayed bridge from deck bending strain responses using Support Vector Machine. A Damaged Cable Identification Machine (DCIM) based on support vector classification is constructed to determine the damaged cable and a Damage Severity Identification Machine (DSIM) based on support vector regression is built to estimate the damage severity. A field cable-stayed bridge with a long-term monitoring system is used to verify the proposed method. The three-dimensional Finite Element Model (FEM) of the cable-stayed bridge is established using ANSYS, and the model is validated using the field testing results, such as the mode shape, natural frequencies and its bending strain responses of the bridge under a moving vehicle. Then the validated FEM is used to simulate the bending strain responses of the longitude deck near the cable anchors when the vehicle is passing over the bridge. Different damage scenarios are simulated for each cable with various severities. Based on damage indexes vector, the training datasets and testing datasets are acquired, including single damaged cable scenarios and double damaged cable scenarios. Eventually, DCIM is trained using Support Vector Classification Machine and DSIM is trained using Support Vector Regression Machine. The testing datasets are input in DCIM and DSIM to check their accuracy and generalization capability. Different noise levels including 5%, 10%, and 20% are considered to study their anti-noise capability. The results show that DCIM and DSIM both have good generalization capability and anti-noise capability.

Optimal Operation of a Microgrid with Hydrogen Storage Based on Deep Reinforcement Learning

Microgrid with hydrogen storage is an effective way to integrate renewable energy and reduce carbon emissions. This paper proposes an optimal operation method for a microgrid with hydrogen storage. The electrolyzer efficiency characteristic model is established based on the linear interpolation method. The optimal operation model of microgrid is incorporated with the electrolyzer efficiency characteristic model. The sequential decision-making problem of the optimal operation of microgrid is solved by a deep deterministic policy gradient algorithm. Simulation results show that the proposed method can reduce about 5% of the operation cost of the microgrid compared with traditional algorithms and has a certain generalization capability.

Virtual Adversarial Training-Based Semisupervised Specific Emitter Identification

Deep learning is a new direction of research for specific emitter identification (SEI). Radio frequency (RF) fingerprints of the emitter signal are small and sensitive to noise. It is difficult to assign labels containing category information in noncooperative communication scenarios. This makes network models obtained by conventional supervised learning methods perform unsatisfactorily, leading to poor identification performance. To address this limitation, this paper proposes a semisupervised SEI algorithm based on bispectrum analysis and virtual adversarial training (VAT). Bispectrum analysis is performed on RF signals to enhance individual discriminability. A convolutional neural network (CNN) is used for RF fingerprint extraction. We used a small amount of labelled data to train the CNN in an adversarial manner to improve the antinoise performance of the network in a supervised model. Virtual adversarial samples were calculated for VAT, which made full use of labelled and large unlabelled training data to further improve the generalization capability of the network. Results of numerical experiments on a set of six universal software radio peripheral (USRP; model B210) devices demonstrated the stable and fast convergence performance of the proposed method, which exhibited approximately 90% classification accuracy at 10 dB. Finally, the classification performance of our method was verified using other evaluation metrics including receiver operating characteristic and precision-recall.

Improvement of generalization capability of two-dimensional salt segmentation via iterative semi-supervised learning

Accurate interpretations of subsurface salts are vital to oil and gas exploration. Manually interpreting them from seismic depth images, however, is labor-intensive. Consequently, use of deep learning tools such as a convolutional neural network for automatic salt interpretation recently became popular. Because of poor generalization capabilities, interpreting salt boundaries using these tools is difficult when labeled data are available from one geological region and we like to make predictions for other nearby regions with varied geological features. At the same time, due to vast amount of the data involved and the associated computational complexities needed for training, such generalization is necessary for solving practical salt interpretation problems. In this work, we propose a semi-supervised training, which allows the predicted model to iteratively improve as more and more information is distilled from the unlabeled data into the model. In addition, by performing mixup between labeled and unlabeled data during training, we encourage the predicted models to linearly behave across training samples; thereby improving the generalization capability of the method. For each iteration, we use the model obtained from previous iteration to generate pseudo labels for the unlabeled data. This automated consecutive data distillation allows our model prediction to improve with iteration, without any need for human intervention. To demonstrate the effectiveness and efficiency, we apply the method on two-dimensional images extracted from a real three-dimensional seismic data volume. By comparing our predictions and fully supervised baseline predictions with those that were manually interpreted and we consider as “ground truth”, we find than the prediction quality our new method surpasses the baseline prediction. We therefore conclude that our new method is a viable tool for automated salt delineation from seismic depth images.

Performance Evaluation of Convolutional Neural Network Using Synthetic Medical Data Augmentation Generated by GAN

Data augmentation is widely used in image processing and pattern recognition problems in order to increase the richness in diversity of available data. It is commonly used to improve the classification accuracy of images when the available datasets are limited. Deep learning approaches have demonstrated an immense breakthrough in medical diagnostics over the last decade. A significant amount of datasets are needed for the effective training of deep neural networks. The appropriate use of data augmentation techniques prevents the model from over-fitting and thus increases the generalization capability of the network while testing afterward on unseen data. However, it remains a huge challenge to obtain such a large dataset from rare diseases in the medical field. This study presents the synthetic data augmentation technique using Generative Adversarial Networks to evaluate the generalization capability of neural networks using existing data more effectively. In this research, the convolutional neural network (CNN) model is used to classify the X-ray images of the human chest in both normal and pneumonia conditions; then, the synthetic images of the X-ray from the available dataset are generated by using the deep convolutional generative adversarial network (DCGAN) model. Finally, the CNN model is trained again with the original dataset and augmented data generated using the DCGAN model. The classification performance of the CNN model is improved by 3.2% when the augmented data were used along with the originally available dataset.

Entropy-Based Variational Scheme with Component Splitting for the Efficient Learning of Gamma Mixtures

Finite Gamma mixture models have proved to be flexible and can take prior information into account to improve generalization capability, which make them interesting for several machine learning and data mining applications. In this study, an efficient Gamma mixture model-based approach for proportional vector clustering is proposed. In particular, a sophisticated entropy-based variational algorithm is developed to learn the model and optimize its complexity simultaneously. Moreover, a component-splitting principle is investigated, here, to handle the problem of model selection and to prevent over-fitting, which is an added advantage, as it is done within the variational framework. The performance and merits of the proposed framework are evaluated on multiple, real-challenging applications including dynamic textures clustering, objects categorization and human gesture recognition.

A Novel Maximum Mean Discrepancy-Based Semi-Supervised Learning Algorithm

To provide more external knowledge for training self-supervised learning (SSL) algorithms, this paper proposes a maximum mean discrepancy-based SSL (MMD-SSL) algorithm, which trains a well-performing classifier by iteratively refining the classifier using highly confident unlabeled samples. The MMD-SSL algorithm performs three main steps. First, a multilayer perceptron (MLP) is trained based on the labeled samples and is then used to assign labels to unlabeled samples. Second, the unlabeled samples are divided into multiple groups with the k-means clustering algorithm. Third, the maximum mean discrepancy (MMD) criterion is used to measure the distribution consistency between k-means-clustered samples and MLP-classified samples. The samples having a consistent distribution are labeled as highly confident samples and used to retrain the MLP. The MMD-SSL algorithm performs an iterative training until all unlabeled samples are consistently labeled. We conducted extensive experiments on 29 benchmark data sets to validate the rationality and effectiveness of the MMD-SSL algorithm. Experimental results show that the generalization capability of the MLP algorithm can gradually improve with the increase of labeled samples and the statistical analysis demonstrates that the MMD-SSL algorithm can provide better testing accuracy and kappa values than 10 other self-training and co-training SSL algorithms.

Separation of multiple motor memories through implicit and explicit processes

Acquisition of multiple motor skills without interference is a remarkable ability in daily life. During adaptation to opposing perturbations, a common paradigm to study this ability, each perturbation can be successfully learned when a contextual follow-through movement is associated with the direction of the perturbation. It is still unclear, however, to what extent this learning engages the cognitive explicit process and the implicit process. Here, we untangled the individual contributions of the explicit and implicit components while participants learned opposing visuomotor perturbations, with a second unperturbed follow-through movement. In Exp. 1 we replicated previous adaptation results and showed that follow-through movements also allow learning for opposing visuomotor rotations. For one group of participants in Exp. 2 we isolated strategic explicit learning, while for another group we isolated the implicit component. Our data showed that opposing perturbations could be fully learned by explicit strategies; but when strategy was restricted, distinct implicit processes contributed to learning. In Exp.3, we examined whether learning is influenced by the disparity between the follow-through contexts. We found that the location of follow-through targets had little effect on total learning, yet it led to more instances in which participants failed to learn the task. In Exp. 4, we explored the generalization capability to untrained targets. Participants showed near-flat generalization of the implicit and explicit processes. Overall, our results indicate that follow-through contextual cues might activate, in part, top-down cognitive factors that influence not only the dynamics of the explicit learning, but also the implicit process.

A Practical Alzheimer Disease Classifier via Brain Imaging-Based Deep Learning on 85,721 Samples

BackgroundBeyond detecting brain lesions or tumors, comparatively little success has been attained in identifying brain disorders such as Alzheimer’s disease (AD), based on magnetic resonance imaging (MRI). Many machine learning algorithms to detect AD have been trained using limited training data, meaning they often generalize poorly when applied to scans from previously unseen populations. Therefore, we built a practical brain MRI-based AD diagnostic classifier using deep learning/transfer learning on dataset of unprecedented size and diversity. MethodsA retrospective MRI dataset pooled from more than 217 sites/scanners constituted the largest brain MRI sample to date (85,721 scans from 50,876 participants) between January 2017 and August 2021. Next, a state-of-the-art deep convolutional neural network, Inception-ResNet-V2, was built as a sex classifier with high generalization capability. The sex classifier achieved 94.9% accuracy and served as a base model in transfer learning for the objective diagnosis of AD. FindingsAfter transfer learning, the model fine-tuned for AD classification achieved 91.3% accuracy in leave-sites-out cross-validation on the Alzheimer's Disease Neuroimaging Initiative (ADNI, 6,857 samples) dataset and 94.2%/93.6%/90.5% accuracy for direct tests on three unseen independent datasets (AIBL, 669 samples / MIRIAD, 644 samples / OASIS, 1,123 samples). When this AD classifier was tested on brain images from unseen mild cognitive impairment (MCI) patients, MCI patients who finally converted to AD were 3 times more likely to be predicted as AD than MCI patients who did not convert (65.2% vs 20.6%). Predicted scores from the AD classifier showed significant correlations with illness severity. InterpretationIn sum, the proposed AD classifier could offer a medical-grade marker that have potential to be integrated into AD diagnostic practice.