Auxiliary Classifier Generative Adversarial Network Research Articles

Multi-granularity short circuit fault diagnosis for tokamak power converters under small sample conditions and noise interference

The power supply system of a tokamak device is a crucial subsystem responsible for providing the magnetic field for plasma confinement. The timely application of fault diagnosis techniques to identify abnormal states of the power supply is of crucial importance for the safe and efficient operation of tokamak devices. Intelligent diagnostic methods based on Convolutional Neural Networks (CNN) are widely employed nowadays. However, within the operational environment of the device, there exist multiple physical field couplings, and inevitable noise will impact the data. Moreover, the measurement equipment exhibits instability, resulting in limited availability of data that meets the required criteria. To address these issues, this paper investigates a fault diagnosis approach utilizing an Auxiliary Classifier Generative Adversarial Network (ACGAN) for data augmentation, and proposes a Multi-Granularity Denoising CNN (MGDCNN) that accounts for noise interference, enabling diagnosis of faults at different granularities. In our approach, we first construct a multi-granularity structure of the data based on prior knowledge. Then, a hierarchical structure corresponding to the multi-granularity data and robust to noise is built by introducing an embedded Discrete Wavelet Transform (DWT) into the one-dimensional (1-D) CNN. Finally, the natural stratification of the network is combined with individual granularity branches for fault diagnosis. Experimental results on simulated datasets and public benchmark datasets demonstrate that the proposed model achieves a diagnostic accuracy of 98.81 % for short-circuit faults in power supply converter at the finest granularity. Even with noisy data, the model maintains a diagnostic accuracy of approximately 97 %, indicating superior noise resistance performance in the inference process of the MGDCNN network.

Network intrusion detection: An optimized deep learning approach using big data analytics

Managing enormous amounts of data, such as big data, and detecting network traffic intrusions are inefficiently handled by current computing technologies. Traditional analytical techniques cannot manage the incursions in continuous internet traffic and the enormous log data of server activity, leading to many inaccurate results and a prolonged training period. As a result, this research provides an efficient deep learning-based approach to enhance the attack identification task by addressing the basic big data complexity linked to many heterogeneous security data types. This framework employs a novel feature selection method incorporatingthe Aquila Optimizer (AO) and Fuzzy Entropy Mutual Information (FEMI) algorithms to pick distinctive characteristics. Subsequently, a modified canonical correlation-based technique is applied to combine selected characteristics. Then, the intrusion identification and categorization are carried out using the optimized ResNet152V2 method. Additionally, data augmentation using Auxiliary Classifier Generative Adversarial Network (ACGAN) is performed. Finally, we used the CICDDoS2019 and ToN-IoT datasets to validate the suggested methodology. By comparing the presented approach to several baseline methods, the effectiveness of the suggested methodology is assessed using various performance measures, including F1-score, recall, precision, accuracy, confusion matrix, and ROC curve. Finally, simulation results show that the suggested strategy is superior to other existing techniques and demonstrate that it is a resilient solution for network intrusion detection.

Age Encoded Adversarial Learning for Pediatric CT Segmentation.

Organ segmentation from CT images is critical in the early diagnosis of diseases, progress monitoring, pre-operative planning, radiation therapy planning, and CT dose estimation. However, data limitation remains one of the main challenges in medical image segmentation tasks. This challenge is particularly huge in pediatric CT segmentation due to children's heightened sensitivity to radiation. In order to address this issue, we propose a novel segmentation framework with a built-in auxiliary classifier generative adversarial network (ACGAN) that conditions age, simultaneously generating additional features during training. The proposed conditional feature generation segmentation network (CFG-SegNet) was trained on a single loss function and used 2.5D segmentation batches. Our experiment was performed on a dataset with 359 subjects (180 male and 179 female) aged from 5 days to 16 years and a mean age of 7 years. CFG-SegNet achieved an average segmentation accuracy of 0.681 dice similarity coefficient (DSC) on the prostate, 0.619 DSC on the uterus, 0.912 DSC on the liver, and 0.832 DSC on the heart with four-fold cross-validation. We compared the segmentation accuracy of our proposed method with previously published U-Net results, and our network improved the segmentation accuracy by 2.7%, 2.6%, 2.8%, and 3.4% for the prostate, uterus, liver, and heart, respectively. The results indicate that our high-performing segmentation framework can more precisely segment organs when limited training images are available.

A novel rolling bearing fault diagnosis method for limited data

The ability of deep learning based bearing fault diagnosis methods is developing rapidly. However, it is difficult to obtain sufficient and comprehensive fault data in industrial applications, and changes in vibration signals caused by machine operating conditions can also hinder the accuracy of the model. The problem of limited data and frequent changes in operating conditions can seriously affect the effectiveness of deep learning methods. To tackle these challenges, a novel transformer model named the Differential Window Transformer (Dwin Transformer), which employs a new differential window self-attention mechanism, is presented in this paper. Meanwhile, the model introduces a hierarchical structure and a new patch merging to further improve performance. Furthermore, a new fault diagnosis model dealing with limited training data is proposed, which combines the Auxiliary Classifier Generative Adversarial Network with the Dwin Transformer(DT-ACGAN). The DT-ACGAN model can generate high-quality fake samples to facilitate training with limited data, significantly improving diagnostic capabilities. The proposed model can achieve excellent results under the dual challenges of limited data and variable working conditions by combining Dwin Transformer with GAN. The DT-ACGAN owns superior diagnostic accuracy and generalization performance under limited sample data and varying working environments when compared with other existing models. A comparative test about cross-domain ability is conducted on the Case Western Reserve University dataset and Jiang Nan University dataset. The results show that the proposed method achieves an average accuracy of 11.3% and 3.76% higher than other existing methods with limited data respectively.

TRA-ACGAN: A motor bearing fault diagnosis model based on an auxiliary classifier generative adversarial network and transformer network

Motor bearing fault diagnosis is essential to guarantee production efficiency and avoid catastrophic accidents. Deep learning-based methods have been developed and widely used for fault diagnosis, and these methods have proven to be very effective in accurately diagnosing bearing faults. In this paper, study the application of generative adversarial networks (GANs) in motor bearing fault diagnosis to address the practical issue of insufficient fault data in industrial testing. Focus on the auxiliary classifier generative adversarial network (ACGAN), and the data expansion is carried out for small datasets. This paper present a novel transformer network and auxiliary classifier generative adversarial network (TRA-ACGAN) for motor bearing fault diagnosis, where the TRA-ACGAN combines an ACGAN with a transformer network to avoid the traditional iterative and convolutional structures. The attention mechanism is fully utilized to extract more effective features, and the dual-task coupling problem encountered in classical ACGANs is avoided. Experimental results with the CWRU dataset and the PU dataset in the field of motor bearing fault diagnosis demonstrate the suitability and superiority of the TRA-ACGAN.

GAN-Based Multi-Task Learning Approach for Prognostics and Health Management of IIoT

Health assessment (HA) & remaining useful life (RUL) estimation, the two essential pillars of the prognostics and health management (PHM) paradigm, help improve industrial equipment reliability while reducing maintenance costs. However, reported works treat HA and RUL estimation as disjoint problems though there exist unexploited similarities among these related issues. Additionally, in practical industrial working scenarios, equipment(s) stay in a normal condition for most of its lifespan, leading to a disproportionate training dataset, hampering the prediction accuracy. To overcome the above problems, we propose a data-driven multi-task learning framework aided by a novel least squares recurrent auxiliary classifier generative adversarial network (LS-R-ACGAN). LS-R-ACGAN employs recurrent neural networks (RNNs) in its generator & discriminator networks for multi-variate fault data generation while overcoming the vanishing gradient problem of ACGANs. Post-data-augmentation, a balanced training dataset, trains a multi-task learning model based on a deep gated RNN (DGRU) for joint HA and RUL estimation. Our simulations use the C-MAPSS dataset for testing the proposed approach’s accuracy. The final results showcase improvements by at least <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula> 3.54% and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula> 2.38% on the RMSE and Score metric over existing state-of-the-art works suggesting its competitiveness and competence for real-world implementations. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This study attacks multiple presumptions concerning the maintenance of complex systems including, ample availability of fault samples alongside normal samples and solving only one of the problems, i.e., health assessment (HA) or remaining useful life (RUL) estimations rather than both. Popular artificial intelligence (AI) based solutions rely heavily upon the quantity of training data for desired performance outcomes. However, in real-life industrial scenarios, fault instances are rare, inherently resulting in an imbalanced dataset. Additionally, it is both labor-intensive and costly to repeat multiple experiments for gathering required data as the equipment(s) pass through short-lived fault states. Thus conventional AI-based solutions may end up producing biased predictions. This work proposes to solve the imbalanced training dataset problem along with joint HA and RUL estimations, in one solution pipeline, currently unexplored in majority of the existing works in the literature. LS-R-ACGAN generates ample diverse fault samples for reducing the degree of imbalance between normal and fault classes. Subsequently, after data augmentation, the balanced training dataset helps train a multi-task learning model for joint HA and RUL estimations. The proposed framework has been implemented and tested on a benchmark dataset proving its superiority over multiple existing methods in the literature.

Generating synthetic medical images with limited data using auxiliary classifier generative adversarial network: a study on thyroid ultrasound images.

The availability of labeled data is crucial for training deep neural networks. However, in some cases, the available data is limited or unlabeled, which poses a significant obstacle in developing accurate models. Various approaches exist to address this issue, such as Image Augmentation, Transfer Learning, and GANs. However, these approaches often require a significant amount of training data or may not generate desired results. In this article, we present a novel method for generating synthetic images from very limited data using the ACGAN. We conducted experiments on a real dataset consisting of 198 ultrasound images of calcified and cystic thyroid gland nodules. We explored and improved different architectures and techniques in the Axillary Classifier Generative Adversarial Network (ACGAN) to generate high-quality synthetic images. To evaluate the generated images, we used the Fréchet Inception Distance (FID) test and human observation. Additionally, we developed an image blending method to generate larger images that simulate the output of an ultrasound device. To validate the accuracy of the merged images, a specialist doctor reviewed the generated data. The modified ACGAN architecture successfully generated new synthetic images from limited data. The output images were assessed based on the image progress ratio with the FID test and human observation. Moreover, the Image blending method was successful in producing larger output images that mimic the nature of the ultrasound device output images. The final merged images were validated by a specialist doctor who confirmed their accuracy. Our method has significant implications for medical imaging, as it enables the generation of synthetic labeled data for training deep learning models, leading to better diagnostic accuracy and improved patient outcomes. This study provides a proof-of-concept for generating synthetic medical images from limited labeled data and can inspire future research in this area.

Virtual Scenarios of Earthquake Early Warning to Disaster Management in Smart Cities Based on Auxiliary Classifier Generative Adversarial Networks.

Effective response strategies to earthquake disasters are crucial for disaster management in smart cities. However, in regions where earthquakes do not occur frequently, model construction may be difficult due to a lack of training data. To address this issue, there is a need for technology that can generate earthquake scenarios for response training at any location. We proposed a model for generating earthquake scenarios using an auxiliary classifier Generative Adversarial Network (AC-GAN)-based data synthesis. The proposed ACGAN model generates various earthquake scenarios by incorporating an auxiliary classifier learning process into the discriminator of GAN. Our results at borehole sensors showed that the seismic data generated by the proposed model had similar characteristics to actual data. To further validate our results, we compared the generated IM (such as PGA, PGV, and SA) with Ground Motion Prediction Equations (GMPE). Furthermore, we evaluated the potential of using the generated scenarios for earthquake early warning training. The proposed model and algorithm have significant potential in advancing seismic analysis and detection management systems, and also contribute to disaster management.

Evasion Generative Adversarial Network for Low Data Regimes

A myriad of recent literary works has leveraged generative adversarial networks (GANs) to generate unseen evasion samples. The purpose is to annex the generated data with the original train set for adversarial training to improve the detection performance of machine learning (ML) classifiers. The quality of generated adversarial samples relies on the adequacy of training data samples. However, in low data regimes like medical diagnostic imaging and cybersecurity, the anomaly samples are scarce in number. This paper proposes a novel GAN design called Evasion Generative Adversarial Network (EVAGAN) that is more suitable for low data regime problems that use oversampling for detection improvement of ML classifiers. EVAGAN not only can generate evasion samples, but its discriminator can act as an evasion-aware classifier. We have considered Auxiliary Classifier GAN (ACGAN) as a benchmark to evaluate the performance of EVAGAN on cybersecurity (ISCX-2014, CIC-2017 and CIC2018) botnet and computer vision (MNIST) datasets. We demonstrate that EVAGAN outperforms ACGAN for unbalanced datasets with respect to detection performance, training stability and time complexity. EVAGAN&#x0027;s generator quickly learns to generate the low sample class and hardens its discriminator simultaneously. In contrast to ML classifiers that require security hardening after being adversarially trained by GAN-generated data, EVAGAN renders it needless. The experimental analysis proves that EVAGAN is an efficient evasion hardened model for low data regimes for the selected cybersecurity and computer vision datasets. Code will be available at HTTPS://www.github.com/rhr407/EVAGAN. <i>ImpStatement</i> Artificial Intelligence (AI) applications can help improve the quality of human life. The use of AI is not only limited to medical anomaly detection and drug discovery but can be leveraged in computer networks to keep people safe from malicious activities on the Internet. However, the AI-based models can be biased towards the majority class of data on which they are trained due to data imbalance. Anomaly data samples are always scarce as compared to normal data samples. So this is an open research problem to solve. Our work is an effort to improve the AI-based methods in detection performance, stability and time complexity. Using the proposed technique, we can train our AI model using fewer anomaly samples, improving the cost-efficiency compared to state-of-the-art in anomaly detection.

MeltPoolGAN: Auxiliary Classifier Generative Adversarial Network for melt pool classification and generation of laser power, scan speed and scan direction in Laser Powder Bed Fusion

A reliable classification architecture for melt pool images is crucial for real-time monitoring and control in additive manufacturing. It enables for the identification of discrepancies between actual and desired process parameters, which could lead to defects in printed part. Moreover, adjusting process parameters according to classification results promotes consistent melt pool geometry and leads to enhanced part quality. In addition to the classification, controlled generation of melt pool images can be employed for data generation, training of classifiers, and offline process parameter optimization along the scan path. This study introduces MeltPoolGAN, a novel machine-learning architecture designed for handling both of these tasks. The architecture is able to classify up to 371 classes consisting of process parameters such as laser power, scan speed and scan direction. This is a significant increase in the total number of classes as well as process parameters compared to state-of-the-art that only classified a maximum of 6 classes, consisting of a single process parameter. With this input, the MeltPoolGAN reaches accuracies of around 97% for power and scan speed class classification, and scan direction estimation errors below 3 degrees making it a reliable solution. Furthermore, the MeltPoolGAN is able to generate plausible melt pool images in controlled and flexible manner based on disentangled input parameters. Finally, since the architecture was trained and tested on two distinct datasets, the publicly available NIST dataset and the in-house created ETH dataset, its robustness and capabilities of being a general-purpose AI model are also demonstrated.

Label Smoothing Auxiliary Classifier Generative Adversarial Network with Triplet Loss for SAR Ship Classification

Deep-learning-based SAR ship classification has become a research hotspot in the military and civilian fields and achieved remarkable performance. However, the volume of available SAR ship classification data is relatively small, meaning that previous deep-learning-based methods have usually struggled with overfitting problems. Moreover, due to the limitation of the SAR imaging mechanism, the large intraclass diversity and small interclass similarity further degrade the classification performance. To address these issues, we propose a label smoothing auxiliary classifier generative adversarial network with triplet loss (LST-ACGAN) for SAR ship classification. In our method, an ACGAN is introduced to generate SAR ship samples with category labels. To address the model collapse problem in the ACGAN, the smooth category labels are assigned to generated samples. Moreover, triplet loss is integrated into the ACGAN for discriminative feature learning to enhance the margin of different classes. Extensive experiments on the OpenSARShip dataset demonstrate the superior performance of our method compared to the previous methods.

SPE-ACGAN: A Resampling Approach for Class Imbalance Problem in Network Intrusion Detection Systems

Network Intrusion Detection Systems (NIDSs) play a vital role in detecting and stopping network attacks. However, the prevalent imbalance of training samples in network traffic interferes with NIDS detection performance. This paper proposes a resampling method based on Self-Paced Ensemble and Auxiliary Classifier Generative Adversarial Networks (SPE-ACGAN) to address the imbalance problem of sample classes. To deal with the class imbalance problem, SPE-ACGAN oversamples the minority class samples by ACGAN and undersamples the majority class samples by SPE. In addition, we merged the CICIDS-2017 dataset and the CICIDS-2018 dataset into a more imbalanced dataset named CICIDS-17-18 and validated the effectiveness of the proposed method using the three datasets mentioned above. SPE-ACGAN is more effective than other resampling methods in improving NIDS detection performance. In particular, SPE-ACGAN improved the F1-score of Random Forest, CNN, GoogLeNet, and CNN + WDLSTM by 5.59%, 3.75%, 3.60%, and 3.56% after resampling.

Small-sample Engine Fault Diagnosis Method Based on IACGAN and DNNs

The reliability of engines, particularly aero engines, has become increasingly important in recent years. Accurate fault diagnosis can prevent accidents and minimize property damage. Deep neural network methods (DNNs) are commonly used for fault diagnosis, but their performance relies heavily on large amounts of high-quality training data. Unfortunately, obtaining high-quality engine fault data is challenging in practice. To address this problem, this paper proposes an improved auxiliary classifier generative adversarial network (IACGAN) that incorporates Wasserstein distance and a gradient penalty term. Meanwhile, a variable learning rate is also proposed to accelerate the model convergence. This approach effectively mitigates the problem of model gradient disappearance and expands one-dimensional time-series data. The proposed method was verified on a small aero-engine through a failure simulation test. The results show that the accuracy of DNN can be significantly raised by data enhancement of IACGAN, especially in the case of a limited number of samples. Therefore, this method shows promise as an auxiliary tool for DNN-based fault diagnosis.

Universal Adversarial Training Using Auxiliary Conditional Generative Model-Based Adversarial Attack Generation

While Machine Learning has become the holy grail of modern-day computing, it has many security flaws that have yet to be addressed and resolved. Adversarial attacks are one of these security flaws, in which an attacker appends noise to data samples that machine learning models take as input with the aim of fooling the model. Various adversarial training methods have been proposed that augment adversarial examples in the training dataset for defense against such attacks. However, a general limitation exists where a robust model can only protect itself against adversarial attacks that are known or similar to those it was trained on. To address this limitation, this paper proposes a Universal Adversarial Training algorithm using adversarial examples generated by an Auxiliary Classifier Generative Adversarial Network (AC-GAN) in parallel with other data augmentation techniques, such as the mixup method. This method builds on a previously proposed technique, Adversarial Training, in which adversarial examples produced by gradient-based methods are augmented and added to the training data. Our method improves the AC-GAN architecture for adversarial example generation to make it more suitable for adversarial training by updating different loss terms and testing its performance against various attacks compared to other robust adversarial models. In this way, it becomes apparent that generative models are better suited for boosting adversarial robustness through adversarial training. When tested using various attack types, our proposed model had an average accuracy of 97.48% on the MNIST dataset and 94.02% on the CelebA dataset, proving that generative models have a higher chance of boosting adversarial security through adversarial training.

Portfolio optimization using predictive auxiliary classifier generative adversarial networks

In financial engineering, portfolio optimization has been of consistent interest. Portfolio optimization is a process of modulating asset distributions to maximize expected returns and minimize risks. Despite numerous studies on shallow learning models, they have shown limited success in analyzing the complex nature of massive stock data, a task where recent deep learning models excel. However, the deterministic nature of conventional deep learning models impedes their consideration of portfolio risk due to an inherent lack of uncertainty quantification in their predictions. This paper proposes a novel portfolio weighting strategy, incorporating both risk and return considerations within a deep learning framework. We propose the Predictive Auxiliary Classifier Generative Adversarial Networks (PredACGAN), a probabilistic deep learning model, to measure prediction uncertainty. The PredACGAN generator leverages latent vectors and historical stock prices to predict future returns. The model synthesizes predictive distributions from various latent vectors and past prices. The associated risk is produced via the entropy of these distributions, facilitating portfolio optimization through both return and risk considerations. The proposed algorithm removes high-risk assets from the investment universe at rebalancing moments, enabling PredACGAN to optimize portfolios considering both return and risk. We evaluated PredACGAN and the accompanying algorithm with S&P 500 stocks from 1990 to 2020, with portfolios rebalanced monthly based on PredACGAN predictions and risk measures. The PredACGAN portfolios yielded 9.123% annual returns and a 1.054 Sharpe ratio, outperforming a risk-agnostic portfolio yielding 1.024% annual returns and a 0.236 Sharpe ratio. The PredACGAN portfolio also exhibited lower maximum drawdowns, highlighting its effectiveness.

Corrosion leakage risk diagnosis of oil and gas pipelines based on semi-supervised domain generalization model

Pipeline corrosion will lead to leakage, significantly affecting pipeline reliability and transportation safety. Accurate leakage diagnosis is vital to the operational safety of the oil and gas industry. However, current supervised learning diagnosis methods are limited in addressing cross-domain problems and limited labeled fault samples. And the potential leakage which has the leakage risk is difficult to diagnosis. Therefore, we propose a novel semi-supervised domain generalization method for leakage diagnosis based on laser optical sensing technology. An improved auxiliary classifier generative adversarial network (IACGAN) is developed with new structure and loss function to extract discriminative features. The Capsule network is improved with DenseBlock (D-CapsNet) for determining the leakage situation of source domain and unseen target domain. To make full use of limited data, the metric learning is combined with pseudo-label strategy in semi-supervised learning to enhance feature representations. The experimental results demonstrate that the domain generalization model performs well in cross-domain leakage diagnosis, where the potential leakage risk can also be accurately recognized. The average recognition accuracy is greater than 95%, which has better diagnosis accuracy than other state-of-the-art methods.

MS-ACGAN: A modified auxiliary classifier generative adversarial network for schizophrenia's samples augmentation based on microarray gene expression data

Artificial intelligence-based models and robust computational methods have expedited the data-to-knowledge trajectory in precision medicine. Although machine learning models have been widely applied in medical data analysis, some barriers are yet to be challenging, such as available biosample shortage, prohibitive costs, rare diseases, and ethical considerations. Transcriptomics, an omics approach that studies gene activities and provides gene expression data such as microarray and RNA-Sequences faces the difficulties of biospecimen collection, particularly for mental disorders, as some psychiatric patients avoid medical care. Microarray data suffers from the low number of available samples, making it challenging to apply machine learning models. However, adversarial generative network (GAN), the hottest paradigm in deep learning, has created unprecedented momentum in data augmentation and efficiently expands datasets. This paper proposes a novel model termed MS-ACGAN, where the generator feeds on a bordered Gaussian distribution. In machine learning, calibration is of utmost importance, which gives insight into model uncertainty and is considered a crucial step toward improving the robustness and reliability of models. Therefore, we apply calibration techniques to classifiers and focus on estimating their probabilities as accurately as possible. Additionally, we present our trustworthy outputs by harnessing confidence intervals that confine the point estimate limitations and report a range of expected values for performance metrics. Both concepts statistically describe the implemented model's reliability in this study. Furthermore, we employ two quantitative measures, GAN-train and GAN-test, to demonstrate that the artificial data generated by our robust approach remarkably resembles the original data characteristics.

Brain tumor segmentation by auxiliary classifier generative adversarial network

Brain tumor segmentation by auxiliary classifier generative adversarial network

Federated transfer learning for auxiliary classifier generative adversarial networks: framework and industrial application.

Machine learning with considering data privacy-preservation and personalized models has received attentions, especially in the manufacturing field. The data often exist in the form of isolated islands and cannot be shared because of data privacy in real industrial scenarios. It is difficult to gather the data to train a personalized model without compromising data privacy. To address this issue, we proposed a Federated Transfer Learning framework based on Auxiliary Classifier Generative Adversarial Networks named ACGAN-FTL. In the framework, Federated Learning (FL) trains a global model on decentralized datasets of the clients with data privacy-preservation and Transfer Learning (TL) transfers the knowledge from the global model to a personalized model with a relatively small data volume. ACGAN acts as a data bridge to connect FL and TL by generating similar probability distribution data of clients since the client datasets in FL cannot be directly used in TL for data privacy-preservation. A real industrial scenario of pre-baked carbon anode quality prediction is applied to verify the performance of the proposed framework. The results show that ACGAN-FTL can not only obtain acceptable performance on 0.81 accuracy, 0.86 precision, 0.74 recall, and 0.79 F1 but also ensure data privacy-preservation in the whole learning process. Compared to the baseline method without FL and TL, the former metrics have increased by 13%, 11%, 16%, and 15% respectively. The experiments verify that the performance of the proposed ACGAN-FTL framework fulfills the requirements of industrial scenarios.

Multi-object tracking for horse racing

Multi-object tracking has been extensively studied in pedestrian behavior analysis and vehicle analysis, but has yet to be well extended to the more challenging horse racing scenarios. This work makes the first attempt to systematically analyze challenges for horse racing tracking problems, including occlusion, trajectory staggered, often switching of cameras (i.e., angles of views), and blurred sprint caused by horse competition. An augmentation-based multi-object tracking method (GMOT) is proposed to solve the above-mentioned challenges. The auxiliary classifier generative adversarial network is adopted in GMOT to augment the horse racing data to enhance target detection and re-identification results. Horse racing videos recorded in day and night scenes are both tested in our experiments. Experimental results show that the proposed method yields good results.