Conventional Generative Adversarial Networks Research Articles

Histopathology-based breast cancer prediction using deep learning methods for healthcare applications.

Breast cancer (BC) is the leading cause of female cancer mortality and is a type of cancer that is a major threat to women's health. Deep learning methods have been used extensively in many medical domains recently, especially in detection and classification applications. Studying histological images for the automatic diagnosis of BC is important for patients and their prognosis. Owing to the complication and variety of histology images, manual examination can be difficult and susceptible to errors and thus needs the services of experienced pathologists. Therefore, publicly accessible datasets called BreakHis and invasive ductal carcinoma (IDC) are used in this study to analyze histopathological images of BC. Next, using super-resolution generative adversarial networks (SRGANs), which create high-resolution images from low-quality images, the gathered images from BreakHis and IDC are pre-processed to provide useful results in the prediction stage. The components of conventional generative adversarial network (GAN) loss functions and effective sub-pixel nets were combined to create the concept of SRGAN. Next, the high-quality images are sent to the data augmentation stage, where new data points are created by making small adjustments to the dataset using rotation, random cropping, mirroring, and color-shifting. Next, patch-based feature extraction using Inception V3 and Resnet-50 (PFE-INC-RES) is employed to extract the features from the augmentation. After the features have been extracted, the next step involves processing them and applying transductive long short-term memory (TLSTM) to improve classification accuracy by decreasing the number of false positives. The results of suggested PFE-INC-RES is evaluated using existing methods on the BreakHis dataset, with respect to accuracy (99.84%), specificity (99.71%), sensitivity (99.78%), and F1-score (99.80%), while the suggested PFE-INC-RES performed better in the IDC dataset based on F1-score (99.08%), accuracy (99.79%), specificity (98.97%), and sensitivity (99.17%).

Time series data recovery in SHM of large-scale bridges: Leveraging GAN and Bi-LSTM networks

This paper proposes the utilization of a Bidirectional Long Short-Term Memory (Bi-LSTM) network and a Generative Adversarial Network (GAN) model, to recover measured time-series data from Structural Health Monitoring (SHM) systems. In civil engineering, time-series data plays a crucial role in SHM systems. However, unforeseen incidents, such as equipment malfunctions, flawed data collection procedures, or human errors may result in missing data or adversely affect the accuracy of the data collected. To address this challenge, researchers have recently introduced various methods for time series data imputation. Nevertheless, it is evident that many existing approaches are hindered by inherent limitations: (1) neglecting bidirectional temporal correlations; (2) failing to model correlations among variables; (3) generating data that inadequately reflects the distribution of the original dataset, leading to inaccuracies in the recovered data. To overcome these limitations, this study proposes the utilization of Bi-LSTM-GAN for recovering time-series data in the context of SHM. Bi-LSTM demonstrates remarkable proficiency in capturing bidirectional temporal and cross-variable correlations, while GAN is utilized to precisely acquire the distribution of the original data. Additionally, Bi-LSTM significantly bolsters the capacity for long-term data recovery in contrast to a conventional Recurrent Neural Network (RNN). To evaluate the efficacy of this approach, we employ two real-world models: a laboratory-based cable-stayed bridge and an actual three-span continuous bridge. The obtained results compellingly demonstrate that Bi-LSTM-GAN not only achieves data restoration effectively but also yields superior accuracy when compared to conventional GAN model.

Seismic data reconstruction method using generative adversarial network based on moment reconstruction error constraint.

The seismic data acquired are usually spatially undersampled due to the constraints of the field acquisition environment. However, the removal of multiple waves, offsets, and inversions requires high regularity and integrity of seismic data. Therefore, reasonable data reconstruction methods are usually applied to the missing data in the indoor processing stage to recover regular seismic data. The traditional reconstruction methods for seismic data reconstruction are generally based on some assumptions (e.g., assuming that the data satisfies linearity or sparsity, etc.) and have some limitations of use. To overcome the applicability problem of traditional seismic data reconstruction methods, this article proposes a generative adversarial network (GAN) seismic data reconstruction method based on moment reconstruction error constraints. The method can extract the deep features of the data nonlinearly without any assumptions. First, the error function in the GAN is improved, and the commonly used joint error function of adversarial loss plus L1/L2 amplitude reconstruction loss is improved to a new error function consisting of adversarial loss and moment reconstruction loss weighting. Then, an adversarial network data reconstruction generation method based on the moment reconstruction error constraint is given. Next, an experimental analysis of different types of data missing was carried out using theoretical model data, and the study method was analyzed by interpolation errors. Finally, actual seismic data is used to further validate the effect of the research method. The experimental results show that the improved algorithm performs superiorly in dealing with the data reconstruction problem. Compared with the error function of conventional GAN optimization, the reconstruction results of GAN based on the moment reconstruction error constraint have better amplitude preservation.

Generative vs. Non-Generative Models in Engineering Shape Optimization

Generative models offer design diversity but tend to be computationally expensive, while non-generative models are computationally cost-effective but produce less diverse and often invalid designs. However, the limitations of non-generative models can be overcome with the introduction of augmented shape signature vectors (SSVs) to represent both geometric and physical information. This recent advancement has inspired a systematic comparison of the effectiveness and efficiency of generative and non-generative models in constructing design spaces for novel and efficient design exploration and shape optimization, which is demonstrated in this work. These models are showcased in airfoil/hydrofoil design, and a comparison of the resulting design spaces is conducted in this work. A conventional generative adversarial network (GAN) and a state-of-the-art generative model, the performance-augmented diverse generative adversarial network (PaDGAN), are juxtaposed with a linear non-generative model based on the coupling of the Karhunen–Loève Expansion and a physics-informed shape signature vector (SSV-KLE). The comparison demonstrates that, with an appropriate shape encoding and a physics-augmented design space, non-generative models have the potential to cost-effectively generate high-performing valid designs with enhanced coverage of the design space. In this work, both approaches were applied to two large foil profile datasets comprising real-world and artificial designs generated through either a profile-generating parametric model or a deep-learning approach. These datasets were further enriched with integral properties of their members’ shapes, as well as physics-informed parameters. The obtained results illustrate that the design spaces constructed by the non-generative model outperform the generative model in terms of design validity, generating robust latent spaces with no or significantly fewer invalid designs when compared to generative models. The performance and diversity of the generated designs were compared to provide further insights about the quality of the resulting spaces. These findings can aid the engineering design community in making informed decisions when constructing design spaces for shape optimization, as it has been demonstrated that, under certain conditions, computationally inexpensive approaches can closely match or even outperform state-of-the art generative models.

EigenGAN: An SVD subspace-based learning for image generation using Conditional GAN

Generative adversarial networks (GANs) represent a significant advance in the field of deep learning for image generation problems. With their ability to generate highly realistic and diverse images, GANs are quickly becoming the preferred technique for a wide range of applications. However, GANs come with several limitations and challenges, chief among which are their collapse mode and instability during training. In this paper, we propose a novel generator GAN model that incorporates the singular value decomposition (SVD) process into the decoder module. The SVD integration allows the generator to recognize the underlying structures in the feature space, resulting in more robust and effective image generation. This is achieved by adjusting the singular values during the training process, effectively optimizing the SVD-based generator to produce images that match the ground truth. Another advantage of SVD integration is its ability to perform discriminative spatial decomposition that clearly reflects the differences between the generated features and the target features. By including SVD in the generator model, the resulting loss values are higher and less prone to gradient vanishing than conventional GANs, such as Pix2Pix. Our proposed SVD-based generator model can be integrated into any auto-encoder architecture, making it as a generic and versatile solution for various image-generation tasks. The effectiveness of the proposed SVD-based GAN in image generation has been validated in three challenging benchmarks for image restoration and visible-to-infrared image translation. Extensive experiments demonstrate the significant quantitative and qualitative improvements achieved by our SVD-based GAN compared to baseline GAN architectures. The overall system outperforms the current state of the art in all benchmarks tested.

A hybrid meteorological data simulation framework based on time-series generative adversarial network for global daily solar radiation estimation

Solar energy has received considerable attention worldwide because of its clean, safe and easily accessible characteristics. Accurate global solar radiation estimation is crucial for local energy potential assessments and deployment of photovoltaic power generation systems. However, the distribution of metrological data varies considerably between regions, and its quality considerably affects the accuracy of the estimation model. Motivated by these concerns, a metrological data estimation framework based on the time-series generative adversarial network (TimeGAN) and deep belief network (DBN) was proposed. First, the metrological data collected from 30 urban meteorological stations in China were analyzed through time-series aggregation. Next, a novel metrological data simulation model based on TimeGAN was proposed to enrich the quality of training samples. Furthermore, a generalized estimation model of daily solar radiation based on DBN was constructed. In the case study in China, TimeGAN outperforms other conventional generative adversarial networks in terms of data generation performance. The simulation results reveal that the TimeGAN-based simulation model can capture the inherent temporal characteristics of the original data, generate high-quality simulation data to reasonably improve the distribution of training data in various cities. In addition, the estimation results indicate that the proposed hybrid framework improve the accuracy of daily solar radiation estimation.

ENABLING SMART FACTORY WITH DEEP RESIDUAL-AIDED GENERATIVE ADVERSARIAL NETWORK: PERFORMANCE ANALYSIS END-TO-END LEARNING OF MACHINE-TO-MACHINE

Improving Machine-to-Machine (M2M) communication is essential for the development of Smart Factory as data can be exchanged and processed more efficiently. Herein this study, we employ the Deep Learning (DL) concepts aimed at improving end-to-end performance (E2E) M2M communication systems. Training the physical layers requires the explicit channel information to be fully known, which can be solved with generative adversarial network (GAN). Nonetheless, due to its deep neural network (DNN) structure, the GAN scheme is subjected to gradient vanishing and over-fitting, two major obstacles that can hinder the training process and limit the performance of the model. As a result, the system is significantly downgraded. To address these issues, we study a method known as Residual-Aided generative adversarial network (RA-GAN) learning scheme, in which the two problems are dealt with respectively by introducing a better propagation mechanism and a regularizer to the loss function. Herein this paper, the system model is described and the two problems are derived analytically. We also analyze the optimal learning scheme (where the channel-agnostic) and a Rayleigh-based learning scheme for comparison study. Through analyzing the block error rate (BLER), we can demonstrate that the RA-GAN approach achieves performance comparable to the optimal scheme, and significantly outperforms the conventional GAN method.

TextControlGAN: Text-to-Image Synthesis with Controllable Generative Adversarial Networks

Generative adversarial networks (GANs) have demonstrated remarkable potential in the realm of text-to-image synthesis. Nevertheless, conventional GANs employing conditional latent space interpolation and manifold interpolation (GAN-CLS-INT) encounter challenges in generating images that accurately reflect the given text descriptions. To overcome these limitations, we introduce TextControlGAN, a controllable GAN-based model specifically designed for text-to-image synthesis tasks. In contrast to traditional GANs, TextControlGAN incorporates a neural network structure, known as a regressor, to effectively learn features from conditional texts. To further enhance the learning performance of the regressor, data augmentation techniques are employed. As a result, the generator within TextControlGAN can learn conditional texts more effectively, leading to the production of images that more closely adhere to the textual conditions. Furthermore, by concentrating the discriminator’s training efforts on GAN training exclusively, the overall quality of the generated images is significantly improved. Evaluations conducted on the Caltech-UCSD Birds-200 (CUB) dataset demonstrate that TextControlGAN surpasses the performance of the cGAN-based GAN-INT-CLS model, achieving a 17.6% improvement in Inception Score (IS) and a 36.6% reduction in Fréchet Inception Distance (FID). In supplementary experiments utilizing 128 × 128 resolution images, TextControlGAN exhibits a remarkable ability to manipulate minor features of the generated bird images according to the given text descriptions. These findings highlight the potential of TextControlGAN as a powerful tool for generating high-quality, text-conditioned images, paving the way for future advancements in the field of text-to-image synthesis.

Automatic Kidney Segmentation Method Based on an Enhanced Generative Adversarial Network

When deciding on a kidney tumor's diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.

Seismic random noise suppression using improved CycleGAN

Random noise adversely affects the signal-to-noise ratio of complex seismic signals in complex surface conditions and media. The primary challenges related to processing seismic data have always been reducing the random noise and increasing the signal-to-noise ratio. In this study, we propose an improved cycle-consistent generative adversarial network (CycleGAN) seismic random noise suppression method. First, the generator replaces the original cycle-consistent generative adversarial network generator network structure with the Unet structure combined with the Resnet structure in order to increase the diversity of seismic data feature extraction and decrease the loss of seismic data details. Second, in order to improve the network’s stability, the feature extraction effect, the event texture preservation effect, and the signal-to-noise ratio, the Least Square GAN (LSGAN) square difference loss is used in place of the conventional generative adversarial network cross-entropy loss. The feasibility of the proposed method was confirmed using model and real seismic data, both of which demonstrated that the improved cycle-consistent generative adversarial network method effectively suppressed random noise in seismic data. In addition, the denoising effect was superior to both the widely used FX deconvolution denoising method and original cycle-consistent generative adversarial network denoising method.

Distribution Bias Aware Collaborative Generative Adversarial Network for Imbalanced Deep Learning in Industrial IoT

The impact of Internet of Things (IoT) has become increasingly significant in smart manufacturing, while deep generative model (DGM) is viewed as a promising learning technique to work with large amount of continuously generated industrial Big Data in facilitating modern industrial applications. However, it is still challenging to handle the imbalanced data when using conventional Generative Adversarial Network (GAN) based learning strategies. In this article, we propose a distribution bias aware collaborative GAN (DB-CGAN) model for imbalanced deep learning in industrial IoT, especially to solve limitations caused by distribution bias issue between the generated data and original data, via a more robust data augmentation. An integrated data augmentation framework is constructed by introducing a complementary classifier into the basic GAN model. Specifically, a conditional generator with random labels is designed and trained adversarially with the classifier to effectively enhance augmentation of the number of data samples in minority classes, while a weight sharing scheme is newly designed between two separated feature extractors, enabling the collaborative adversarial training among generator, discriminator, and classifier. An augmentation algorithm is then developed for intelligent anomaly detection in imbalanced learning, which can significantly improve the classification accuracy based on the correction of distribution bias using the rebalanced data. Compared with five baseline methods, experiment evaluations based on two real-world imbalanced datasets demonstrate the outstanding performance of our proposed model in tackling the distribution bias issue for multiclass classification in imbalanced learning for industrial IoT applications.

Fast and Efficient Image Generation Using Variational Autoencoders and K-Nearest Neighbor OveRsampling Approach

Researchers gravitate towards Generative Adversarial Networks (GAN) to create artificial images. However, GANs suffer from convergence issues, mode collapse, and overall complexity in balancing the Nash Equilibrium. Images generated are often distorted, rendering them useless. We propose a combination of Variational Autoencoders (VAEs) and a statistical oversampling method called K-Nearest Neighbor OveRsampling (KNNOR) to create artificial images. This combination of VAE and KNNOR results in more life-like images with reduced distortion. We fine-tune several pre-trained networks on a separate set of real and fake face images to test images generated by our method against images generated by conventional Deep Convolutional GANs (DCGANs). We also compare the combination of VAEs and Synthetic Minority Oversampling Technique (SMOTE) to establish the efficacy of KNNOR against naive oversampling methods. Not only are our methods better able to convince the classifiers that the images generated are authentic, but the models are also half in size of DCGANs. The code is available at GitHub for public use.

Deep reinforcement learning autoencoder with RA-GAN and GAN

Deep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectively. As a solution for this, we first investigate typical end-to-end learning for a communication system, Generative Adversarial Network (GAN). Then, two problems associated with GAN-based systems, the gradient vanishing and overfitting, are reviewed. Subsequently, a residual aided GAN (RA-GAN) is proposed as means to overcome these problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. Finally, the numerical results performed in MATLAB for simulation and Codelabs for training have proven that the RA-GAN scheme has near-optimal performance and outperforms the conventional GAN scheme. Throughout this case study, readers can understand the issues that would occur when deep learning is applied to a communication system and possible approaches to address them.

AAGAN: Accuracy-Aware Generative Adversarial Network for Supervised Tasks

Owing to their great success in unsupervised tasks, generative adversarial networks (GANs) are widely adopted for supervised (conditional) image-generation tasks such as in-painting. Unfortunately, designing an objective function using GANs is not trivial. For supervised tasks, the generator trained only with GAN loss does not yield the corresponding target for the given input because GAN is trained to match the data distribution, not to find the exact answer. Therefore, the loss function of a generator is often formulated by linearly combining supervised loss and GAN loss as similar to multi-task learning, expecting that each loss’s weakness is complemented. Contrary to expectation, both losses cause a conflict in practice due to different optimum of each loss, yielding low objective and subjective image qualities. To address this problem, we empirically investigated the conflict caused by using a conventional GAN with pixel-wise losses; we then propose a novel (relativistic) accuracy-aware discriminator. Based on the proposed discriminator, we developed an accuracy-aware GAN (AAGAN) and proved its optimality under an ideal assumption. We then propose a relativistic accuracy-aware GAN (RAAGAN) by considering practical assumptions. Experimental results on supervised tasks demonstrated that the proposed schemes alleviated the competition between losses and outperformed conventional GANs in terms of both objective and subjective qualities.

GAN‐C: A generative adversarial network with a classifier for effective event prediction

AbstractEvent prediction is essential in social network (SN) analysis to study the SN's evolutionary patterns (communities). Machine learning (ML) models are often used to predict events in SN communities. The ML algorithms manifest the results with biasness for the same dataset. Hence, the performance of an ML model requires validation for the unseen data to avoid biasness in learning. Generally, researchers use the generative adversarial network (GAN) model for generating realistic sample data to enhance the prediction of events. It is challenging for the discriminator to learn features using a single layer with similar weights in a conventional GAN technique. Therefore, this article proposes an improved version of the GAN model named generative adversarial network classifier (GAN‐C). The proposed GAN‐C model contains an additional layer, called classifier, that generates different feature maps. Wherein weights are adjusted dynamically based on the conditions to predict the events. To be precise, conditioning the weights in a classifier layer using entropy values of the features is a simple and effective way to minimize the classifier loss function (categorical cross‐entropy). GAN‐C model results in 16% loss up to 10 batches, and after that, the loss becomes negligible and can generate non‐overlapping events. The gaps between such non‐overlapping events are analyzed using the Jensen–Shannon divergence technique. The experimental results show that the existing single‐GAN and multi‐GAN methods predict events with 79.34% and 82.17% accuracy, respectively. While the proposed GAN‐C comparatively predicts events with improved accuracy of 88.56% on the same dataset. The data generated by the GAN‐C model are also approximately 55.85% and 80.59% more realistic than multi‐GAN and single‐GAN, respectively, based on root mean square error and inception score comparisons. GAN‐C is also approximately 68.01% faster than other GAN models. Thus, this article's theoretical and experimental analysis justifies that GAN‐C works suitably for predicting events in a massive dataset.

Content loss and conditional space relationship in conditional generative adversarial networks

In the machine learning community, generative models, especially generative adversarial networks (GANs) continue to be an attractive yet challenging research topic. Right after the invention of GAN, many GAN models have been proposed by the researchers with the same goal: creating better images. The first and foremost feature that a GAN model should have is that creating realistic images that cannot be distinguished from genuine ones. A large portion of the GAN models proposed to this end have a common approach which can be defined as factoring the image generation process into multiple states for decomposing the difficult task into several more manageable sub tasks. This can be realized by using sequential conditional/unconditional generators. Although images generated by sequential generators experimentally prove the effectiveness of this approach, visually inspecting the generated images are far away of being objective and it is not yet quantitatively showed in an objective manner. In this paper, we quantitatively show the effectiveness of shrinking the conditional space by using the sequential generators instead of utilizing single but large generator. At the light of the content loss we demonstrate that in sequential designs, each generator helps to shrink the conditional space, and therefore reduces the loss and the uncertainties at the generated images. In order to quantitatively validate this approach, we tried different combinations of connecting generators sequentially and/or increasing the capacity of generators and using single or multiple discriminators under four different scenarios applied to image-to-image translation tasks. Scenario-1 uses the conventional pix2pix GAN model which serves as the based line model for the rest of the scenarios. In Scenario-2, we utilized two generators connected sequentially. Each generator is identical to the one used in Scenario-1. Another possibility is just doubling the size of a single generator which is evaluated in the Scenario-3. In the last scenario, we used two different discriminators in order to train two sequentially connected generators. Our quantitative results support that simply increasing the capacity of one generator, instead of using sequential generators, does not help a lot to reduce the content loss which is used in addition to adversarial loss and hence does not create better images.

GIU-GANs: Global Information Utilization for Generative Adversarial Networks

Recently, with the rapid development of artificial intelligence, image generation based on deep learning has advanced significantly. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, because convolutions are limited by spatial-agnostic and channel-specific, features extracted by conventional GANs based on convolution are constrained. Therefore, GANs cannot capture in-depth details per image. Moreover, straightforwardly stacking of convolutions causes too many parameters and layers in GANs, yielding a high overfitting risk. To overcome the abovementioned limitations, in this study, we propose a GANs called GIU-GANs (where Global Information Utilization: GIU). GIU-GANs leverages a new module called the GIU module, which integrates the squeeze-and-excitation module and involution to focus on global information via the channel attention mechanism, enhancing the generated image quality. Moreover, Batch Normalization (BN) inevitably ignores the representation differences among noise sampled by the generator and thus degrades the generated image quality. Thus, we introduce the representative BN to the GANs’ architecture. The CIFAR-10 and CelebA datasets are employed to demonstrate the effectiveness of the proposed model. Numerous experiments indicate that the proposed model achieves state-of-the-art performance.

GrapeGAN: Unsupervised image enhancement for improved grape leaf disease recognition

Grape leaf disease seriously affects the yield and quality of grapes. Limited by actual conditions, collecting a large number of grape disease images is time-consuming and labor intensive, which makes it difficult to train grape disease identification models with excellent performance. Currently, using generative adversarial networks(GANs) to generate grape leaf images is a popular method. Unfortunately, the leaf disease images generated by conventional GANs are not clear enough and the structural integrity is insufficient. To address this problem, a novel architecture named GrapeGAN is proposed in this paper. First, suppress the loss of texture detail information during image generation, a U-Net-like generator is designed by integrating convolutions with residual blocks and reorganization (reorg) methods. Simultaneously, the concatenation (concat) method is used in the generator to retain more scale texture information. Then, to make the generated grape images structurally complete and avoid petiole and leaf structure misalignment, a discriminator is designed with a convolution block and capsule structure. Convolution is used to extract general features, and the capsule structure encodes the spatial information and the probability of the presence of spots. In subsequent experiments on the same raw data, GrapeGAN is compared to WGAN and DCGAN, and the results show that GrapeGAN outperforms the comparative models. Specifically, the Fréchet inception distance (FID) is 5.495, and the neural image assessment (NIMA) is 4.937 ± 1.515. Moreover, four convolutional neural network (CNN) recognition models are used to identify the generated grape leaf diseases. The results demonstrate that the recognition accuracy of grape leaf disease images generated by the GrapeGAN is higher than 86.36%, and the identification accuracy of VGG16 and InceptionV1 achieve 96.13%. In summary, the experimental results show the effectiveness of GrapeGAN, which proves that GrapeGAN can efficiently detect grape leaf disease detection.

A Semi-Supervised Modulation Identification in MIMO Systems: A Deep Learning Strategy

Accurate modulation identification of the received signals is undoubtedly a central component in multiple-input multiple-output (MIMO) communication systems, facilitating the demodulation task. This study presents a flexible and semi-supervised deep learning-driven strategy for automatic modulation identification. To this end, the multiclass classification problem is treated as multiple binary discrimination problems to address modulation identification challenges. Here, we merge the features extraction ability of the Generative Adversarial Network (GAN) model and the semi-supervised anomaly detection scheme, the one-class Support Vector Machine (1SVM). Essentially, a single GAN-based 1SVM detector is trained using training data of each class, with the samples of that class as inlier and all other samples as anomalies (i.e., one-vs.-rest). The 1SVM is trained using the features learned by the GAN model. A dataset consisting of three digital modulations (i.e., BFSK, CPFSK, and PAM4) and three analog modulations (i.e., AM-DSB, AM-SSB, and WB-FM), widely used in wireless communications systems, is employed to demonstrate the performance of the considered deep learning-based methods. Compared to Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN)-based 1SVM, the conventional GAN, DBN, and RBM with softmax layer as discriminator layer, the proposed GAN-based 1SVM detector offers superior discrimination performance of modulation types by achieving an averaged accuracy of 0.951 and F1-Score of 0.954. Results also showed that the GAN-1SVM detector dominates the state-of-the-art modulation classification techniques.

Fast Adaptive Meta-Learning for Few-Shot Image Generation

Generative Adversarial Networks (GANs) are capable of effectively synthesising new realistic images and estimating the potential distribution of samples utilising adversarial learning. Nevertheless, conventional GANs require a large amount of training data samples to produce plausible results. Inspired by the capacity for humans to quickly learn new concepts from a small number of examples, several meta-learning approaches for the few-shot datasets are presented. However, most of meta-learning algorithms are designed to tackle few-shot classification and reinforcement learning tasks. Moreover, the existing meta-learning models for image generation are complex, thereby affecting the length of training time required. Fast Adaptive Meta-Learning (FAML) based on GAN and the encoder network is proposed in this study for few-shot image generation. This model demonstrates the capability to generate new realistic images from previously unseen target classes with only a small number of examples required. With 10 times faster convergence, FAML requires only one-fourth of the trainable parameters in comparison baseline models by training a simpler network with conditional feature vectors from the encoder, while increasing the number of generator iterations. The visualisation results are demonstrated in the paper. This model is able to improve few-shot image generation with the lowest FID score, highest IS, and comparable LPIPS to MNIST, Omniglot, VGG-Faces, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mini</i> ImageNet datasets. The source code is available on <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/phaphuang/FAML</uri> .