Deep Convolutional Generative Adversarial Networks Research Articles

Ghost Imaging Quality Optimization Based on Deep Convolutional Generative Adversarial Networks

Ghost Imaging Quality Optimization Based on Deep Convolutional Generative Adversarial Networks

Improving synthetic media generation and detection using generative adversarial networks.

Synthetic images ar---e created using computer graphics modeling and artificial intelligence techniques, referred to as deepfakes. They modify human features by using generative models and deep learning algorithms, posing risks violations of social media regulations and spread false information. To address these concerns, the study proposed an improved generative adversarial network (GAN) model which improves accuracy while differentiating between real and fake images focusing on data augmentation and label smoothing strategies for GAN training. The study utilizes a dataset containing human faces and employs DCGAN (deep convolutional generative adversarial network) as the base model. In comparison with the traditional GANs, the proposed GAN outperform in terms of frequently used metrics i.e., Fréchet Inception Distance (FID) and accuracy. The model effectiveness is demonstrated through evaluation on the Flickr-Faces Nvidia dataset and Fakefaces d--ataset, achieving an FID score of 55.67, an accuracy of 98.82%, and an F1-score of 0.99 in detection. This study optimizes the model parameters to achieve optimal parameter settings. This study fine-tune the model parameters to reach optimal settings, thereby reducing risks in synthetic image generation. The article introduces an effective framework for both image manipulation and detection.

The Use of AI Technology in Digital Ceramic Technology

Abstract With the development of AI technology, the development of the ceramic industry has ushered in a good opportunity. This paper discusses the application of AI technology in the field of ceramics on the basis of deep convolutional generative adversarial network, using Adam optimizer to further improve the performance of the model, using the hidden space to add noise to each layer of the network, and proposing a digital ceramic texture image generation model based on DCGAN. Meanwhile, the K-Means algorithm and feature fusion mechanism with BWP as the evaluation index are introduced to improve the Faster R-CNN algorithm and construct the ceramic defect detection model. The scores of each subjective evaluation index of image generation quality are greater than 4, which are located in the interval of higher evaluation. The scores of IS, BRISQUE, and NIQE are 3.39, 22.57, and 4.43, and the quality of ceramic texture image generation of this paper’s model is better than that of other algorithms. The ceramic defect detection model’s detection accuracy for all five ceramic defects is higher than 92.68%, with an 8.54% improvement over the original algorithm’s defect detection performance. The research in this paper has important theoretical and practical significance for ceramic product design, quality control, and troubleshooting of production equipment.

Grain Protein Content Phenotyping in Rice via Hyperspectral Imaging Technology and a Genome-Wide Association Study.

Efficient and accurate acquisition of the rice grain protein content (GPC) is important for selecting high-quality rice varieties, and remote sensing technology is an attractive potential method for this task. However, the majority of multispectral sensors are poor predictors of GPC due to their broad spectral bands. Hyperspectral technology provides a new analytical technology for bridging the gap between phenomics and genomics. However, the small size of typical datasets is a constraint for model construction for estimating GPC, limiting their accuracy and reducing their ability to generalize to a wide range of varieties. In this study, we used hyperspectral data of rice grains from 515 japonica varieties and deep convolution generative adversarial networks (DCGANs) to generate simulated data to improve the model accuracy. Features sensitive to GPC were extracted after applying a continuous wavelet transform (CWT), and the estimated GPC model was constructed by partial least squares regression (PLSR). Finally, a genome-wide association study (GWAS) was applied to the measured and generated datasets to detect GPC loci. The results demonstrated that the simulated GPC values generated after 8,000 epochs were closest to the measured values. The wavelet feature (WF1743, 2), obtained from the data with the addition of 200 simulated samples, exhibited the highest GPC estimation accuracy (R 2 = 0.58 and RRMSE = 6.70%). The GWAS analysis showed that the estimated values based on the simulated data detected the same loci as the measured values, including the OsmtSSB1L gene related to grain storage protein. This study provides a new technique for the efficient genetic study of phenotypic traits in rice based on hyperspectral technology.

AEGANB3: An Efficient Framework with Self-attention Mechanism and Deep Convolutional Generative Adversarial Network for Breast Cancer Classification

AEGANB3: An Efficient Framework with Self-attention Mechanism and Deep Convolutional Generative Adversarial Network for Breast Cancer Classification

Study on detection of dent defects of polariser based on deep convolutional generative adversarial network

Study on detection of dent defects of polariser based on deep convolutional generative adversarial network

Animated Avatar Generation Technology Research Based on Deep Convolutional Generative Adversarial Network Integrated With Self-Attention and Spectral Normalization

Animated Avatar Generation Technology Research Based on Deep Convolutional Generative Adversarial Network Integrated With Self-Attention and Spectral Normalization

Research on the Generative Mechanism of Intelligent Reconstruction for the Integration of Traditional Paper-cutting Art Symbols and Modern Pattern Designs

Abstract In the realm of Chinese traditional arts, paper-cutting symbols embody deep-seated aesthetic and cultural values. Within the framework of artificial intelligence, the fusion of these conventional symbols with contemporary pattern design through intelligent reconstruction processes promotes innovation in modern design. This paper introduces a novel pattern feature extraction algorithm specifically designed for identifying and extracting the essence of traditional paper-cutting art. Utilizing Deep Convolutional Generative Adversarial Networks (DCGAN), an automated method for generating woven patterns is developed, integrating conventional motifs with modern design elements. Additionally, a segmentation model based on DeepLabV3+ semantics is constructed to facilitate this integration. The study focuses on the fusion of traditional paper-cutting symbols with fabric patterns, providing a new direction for textile design research. The empirical evaluation involved seven experimenters who predominantly favored patterns that blended abstract and traditional styles, with the average style rating exceeding 3.2. Moreover, the color performance analysis of the reconstructed fabric patterns across five regions showed color difference values greater than 4, indicating superior color fidelity. These findings underscore the potential of combining AI-driven techniques with traditional art forms to enhance and revolutionize modern design practices.

Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach

AbstractThis study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC values 24 hr ahead in the vicinity of the Korean Peninsula (26.5°–40°N, 121°–134.5°E). The LSTM method predicts TEC at a single point based on time series of data at that point, whereas the ConvLSTM method simultaneously predicts TEC values at multiple points using spatiotemporal distribution of TEC. Both the LSTM and ConvLSTM models are trained using the complete regional TEC maps reconstructed by applying the Deep Convolutional Generative Adversarial Network–Poisson Blending (DCGAN‐PB) method to observed TEC data. The training period spans from 2002 to 2018, and the model performance is evaluated using 2019 data. Our results show that the ConvLSTM method outperforms the LSTM method, generating more reliable TEC maps with smaller root mean square errors when compared to the ground truth (DCGAN‐PB TEC maps). This outcome indicates that deep learning models can improve the prediction accuracy of TEC at a specific point by taking into account spatial information of TEC. We conclude that ConvLSTM is a reliable and efficient approach for the prompt ionospheric prediction.

Intelligent characterization of complex cracks in strain-hardening cementitious composites based on generative computer vision

This paper presents a generative artificial intelligence (AI) approach to generate images of strain-hardening cementitious composite (SHCC) with complex crack patterns such as dense microcracks. This approach is developed to address the challenge of lacking data for training deep learning models used to automatically measure cracks in SHCC. The development of the approach is based on a framework which results in a hybrid generative adversarial network (HGAN) that seamlessly integrates a deep convolutional generative adversarial network (DCGAN) for generating images and a conditional generative adversarial network (CGAN) for labelling images. From the results, it was found that this approach provided high-quality labelled images automatically, and using these images significantly improved the accuracy of the deep learning models for measuring cracks in SHCC. The F1 score and Intersection Over Union (IOU) for crack segmentation reached 0.982 and 0.980, respectively. This approach will significantly promote crack measurement for SHCC materials and structures.

Enhancing Pneumonia Disease Classification using Genetic Algorithm-Tuned DCGANs and VGG-16 Integration

Diagnostic complications arise from pneumonia, characterized by lung inflammation caused by alveolar fluid accumulation, particularly in regions with limited radiologists. To tackle this issue, a new method utilizes the VGG16 methodology for categorization, bolstered by genetic algorithms. In addition, Deep Convolutional Generative Adversarial Networks (DCGANs) improve the dataset by adding fake X-rays of pneumonia. Genetic algorithms are used to optimize hyperparameters in classification tasks. In contrast, DCGANs are employed to increase data augmentation techniques, boosting models' accuracy in identifying and categorizing pneumonia cases. The study partitioned a dataset into training, testing, and validation sets for pneumonia X-ray pictures. The training of GANs entails utilizing both generators and discriminators to produce increasingly realistic pictures gradually. The genetic algorithm enhances the hyperparameter tuning process, resulting in a substantial increase in accuracy. Initially, VGG16 achieved a success rate of 89.50% and a fitness score of 87.50%. Post-optimization and DCGAN augmentation, accuracy climbed to 95.50%, and F1-Score improved to 94.75%. This study combines genetic algorithms and DCGANs to create a model that can produce genuine pneumonia X-ray pictures and enhance categorization accuracy.

Improved bioimpedance spectroscopy tissue classification through data augmentation from generative adversarial networks.

Bioimpedance spectroscopy is a tissue classification technique with many clinical applications. Similarly to other data-driven methods, it requires large amounts of data to accurately distinguish similar classes of tissue. Classifiers trained on small datasets typically suffer from over-fitting and lack the ability to generalise to previously unseen data. However, a large in or ex vivo spectral database is difficult to attain. Data collection is usually limited to studies that occur infrequently, and publicly available data is often not available. A solution to this problem is to artificially increase the training dataset by creating modified, yet accurate, copies of the original dataset. The most common techniques in spectral classification are to add noise to copies of the original data, over-sample it, or randomly interpolate pairs of the original data. However, simply perturbing or interpolating the data does not guarantee that the new dataset captures the key features of the original data needed for accurate classification. This study proposes a novel way to augment bioimpedance spectral data. It uses generative adversarial networks (GAN)-a model in which two neural networks (NN) compete with each other: while one NN artificially manufactures data that could be mistaken for real data, the role of the second NN is to identify which data it receives has been artificially created. The first NN then interactively adapts its output until the second NN can no longer flag artificially created data. The result is a new dataset that truly represents the features of the original data. In this study, three GAN architectures are used, i.e., the vanilla GAN, the deep convolutional GAN, and the Wasserstein GAN. Then, the generated data is used to train five classification methods, and their results are compared to a baseline that only uses the original data. The results from a dataset of 13 different tissue classes show that the deep convolutional GAN is most statistically similar to the original data and improves classification accuracy by 15% when compared to the same model trained only on the original data. The Wasserstein-GAN architecture also provides significant improvements of up to 24% better accuracy.

Clinical Utility of Breast Ultrasound Images Synthesized by a Generative Adversarial Network.

This study compares the clinical properties of original breast ultrasound images and those synthesized by a generative adversarial network (GAN) to assess the clinical usefulness of GAN-synthesized images. We retrospectively collected approximately 200 breast ultrasound images for each of five representative histological tissue types (cyst, fibroadenoma, scirrhous, solid, and tubule-forming invasive ductal carcinomas) as training images. A deep convolutional GAN (DCGAN) image-generation model synthesized images of the five histological types. Two diagnostic radiologists (reader 1 with 13 years of experience and reader 2 with 7 years of experience) were given a reading test consisting of 50 synthesized and 50 original images (≥1-month interval between sets) to assign the perceived histological tissue type. The percentages of correct diagnoses were calculated, and the reader agreement was assessed using the kappa coefficient. The synthetic and original images were indistinguishable. The correct diagnostic rates from the synthetic images for readers 1 and 2 were 86.0% and 78.0% and from the original images were 88.0% and 78.0%, respectively. The kappa values were 0.625 and 0.650 for the synthetic and original images, respectively. The diagnoses made from the DCGAN synthetic images and original images were similar. The DCGAN-synthesized images closely resemble the original ultrasound images in clinical characteristics, suggesting their potential utility in clinical education and training, particularly for enhancing diagnostic skills in breast ultrasound imaging.

A cylinder block dynamic characteristics-based data augmentation method for wear state identification under data imbalance condition

The deterioration of the wear state in the key friction pairs will degenerate the performance of the axial piston pump. The wear rates differ under different wear states in practical applications. Therefore, the amount of monitoring data is significantly different under different wear states, which causes data imbalance problem. In addition, the distribution characteristics of the external signals are often drowned by environmental noise. To address these issues, a novel cylinder block dynamic characteristics-based data augmentation method is presented for wear state identification. Firstly, a cylinder block’s dynamic characteristics state perception method is proposed to obtain the time domain data. Then, to reduce the computing costs, the raw data is fused into multi-channel time–frequency domain data by the short-time Fourier transform (STFT) based method. Finally, the minority time–frequency data is augmented by the designed deep convolutional generative adversarial network (DCGAN). To verify the wear state identification performance of the proposed method, a convolutional neural network (CNN) is designed. Wear states injection experiments are adopted to verify the feasibility of the proposed method. The advantage of the developed method is that it obtains prominent data distribution characteristics from internal signals to enhance the performance of the data augmentation process.

Convolutional neural network for classifying cartoon images augmented by DCGAN

Convolutional Neural Network (CNN) tend to have better results on large data sets and poor performance on small data sets, so the data augmentation is crucial for a CNN to get better performance based on the dataset with limited size. In this paper, Deep Convolution Generative Adversarial Network (DCGAN) was used to augment data to make the AlexNet perform better on an image classification task with small data sets. AlexNet was trained on a small anime face training set with only 160 samples to determine whether the anime face was male or female, and then tested its accuracy on a test set with 240 sample. Then, a pre-trained DCGAN was transferred to train on the male and female training sets respectively. And 2 DCGANs were obtained, one could generate male cartoon faces and another could generate female cartoon faces. The images generated by DCGANs were put in train set, which was used to train AlexNet again and the result was recorded. Other data augmentation methods such as cutout, cutmix and Noise Injection were compared as well. Finally, it is found that AlexNet has the best performance when using the DCGAN augmentation method, which can significantly improve the verification accuracy of the model.

Anomaly detection using deep convolutional generative adversarial networks in the internet of things

Advanced 5 G and 6 G technologies have accelerated the adoption of the Internet of Things (IoT) and are a priority in providing support for high-speed communication and fast data analysis. One of IoT networks benefits is automated networking, which unfortunately increases the risk of security, integrity, and privacy breaches. Therefore, in this paper, we propose a weighted stacked ensemble model combining deep convolutional generative adversarial and bidirectional long short-term memory networks. The proposed model has been regularized, and hyperparameter tuning has been performed. The tuned model is then evaluated on four publicly available current IoT datasets. The proposed model exhibits significant improvement in standard performance measures for both binary and multiclass classification. Generalization error has been reduced by a rate of 0.005% and to overcome the issue of overfitting, a L2 regularization technique has been deployed. The overall Accuracy of the model on various datasets is 99.99% for BOT-IoT, 99.08% for IoT23, 99.82% for UNSWNB15, and 99.96% for ToN_IoT, respectively, alongside improvements in Precision, Recall, and F1-score.

Expansion of the CT-scans image set based on the pretrained DCGAN for improving the performance of the CNN

Diagnosis of COVID-19 based on CT scans images using artificial intelligence can massively reduce medical manpower, time, and resources and reduce misdiagnosis rate. However, there are few relevant image sets publicly available at present, which is not conducive to the training of models such as classification. Transfer learning has been extensively considered in image classification, but less utilized in image generation. This work attempts to expand this dataset with discriminators using Deep Convolutional Generative Adversarial Network (DCGAN) models of Imagenet pre-training models and verify the significance of pre-training models for generating image veracity. A DCGAN model using the Imagenet pre-training model (i.e. resnet18) and a DCGAN network without the pre-train model generated 100 positive and 100 negative images to extend the original dataset, respectively. These images were classified using a Convolutional Neural Network (CNN) binary classifier, and the accuracy improved from 82.67% to 85.33% after adding the pre-training model. Furthermore, the comparison shown by the Gradcam visualization shows that the discriminator with the pre-training model can better capture the key details of the images. This experiment shows that even though Imagenet and lung images are totally uncorrelated, there are still some features that can be transferred. It also demonstrates that Imagenet pre-training models can improve the quality of GAN-generated images, extending the application of migration transfer learning.

SAM-GAN: An improved DCGAN for rice seed viability determination using near-infrared hyperspectral imaging

Viability is a significant indicator of rice seeds, affecting rice yield and quality. Existing viability determination methods cannot meet the requirements of rapidity, non-destructive and accuracy. In this study, near-infrared hyperspectral imaging was used to detect the viability of natural aging seeds. Generative Adversarial Network (GAN) is the main means of coping with Few-shot learning. Considering that natural aging seed samples were difficult to obtain and the number was scarce, this study used Spectral Angle Mapper Generative Adversarial Network (SAM-GAN) to generate rice seed spectral data based on the spectra of obtained natural aging seeds to solve the problem of sample scarcity. SAM-GAN is based on Deep Convolution GAN (DCGAN), introduced by SAM. SAM-GAN was compared with Wasserstein Generative Adversarial Nets with Gradient Penalty (WGAN-GP) and DCGAN, and the Convolutional Neural Network (CNN) model was established by three modeling methods: real data modeling, fake data modeling and mixed modeling of real data and fake data. The experimental results show that the accuracy of the CNN model established by mixing real data with fake data generated by SAM-GAN reaches nearly 100%. This study provides an effective method for rapid, non-destructive and accurate determination of rice seed viability with a limited sample number.

Hybrid Deep Convolutional Generative Adversarial Network (DCGAN) and Xtreme Gradient Boost for X-ray Image Augmentation and Detection

The COVID-19 pandemic has exerted a widespread influence on a global scale, leading numerous nations to prepare for the endemicity of COVID-19. The polymerase chain reaction (PCR) swab test has emerged as the prevailing technique for identifying viral infections within the current pandemic. Following this, the application of chest X-ray imaging in individuals provides an alternate approach for evaluating the existence of viral infection. However, it is imperative to further boost the quality of collected chest pictures via additional data augmentation. The aim of this paper is to provide a technique for the automated analysis of X-ray pictures using server processing with a deep convolutional generative adversarial network (DCGAN). The proposed methodology aims to improve the overall image quality of X-ray scans. The integration of deep learning with Xtreme Gradient Boosting in the DCGAN technique aims to improve the quality of X-ray pictures processed on the server. The training model employed in this work is based on the Inception V3 learning model, which is combined with XGradient Boost. The results obtained from the training procedure were quite interesting: the training model had an accuracy rate of 98.86%, a sensitivity score of 99.1%, and a recall rate of 98.7%.

Enhancing coal-gangue object detection using GAN-based data augmentation strategy with dual attention mechanism

Coal separation based on computer vision has attracted substantial attention in recent years. However, developing reliable object detection models relies on large-scale annotated dataset, which in industrial practice is time-consuming and labor-intensive to obtain. In this paper, we propose a novel data augmentation model called dual attention deep convolutional generative adversarial network (DADCGAN) to expand dataset scale and improve object detection. For the first time, the proposed DADCGAN, which adopts DCGAN as its foundation architecture, introduces efficient channel attention and external attention mechanisms to capture essential feature information from the channel and spatial dimensions of images, respectively. Moreover, spectral normalization and two time-scale update rule strategies are incorporated to stabilize the training process. The implementation of our proposed data augmentation strategy includes two steps. First, traditional pixel transformation is used to expand an original small dataset. Then, our GAN-based data augmentation is executed to further expand the dataset by generating synthetic images. Experimental results show that our DADCGAN model achieves the lowest FID value, decreasing the FID by 21.30–71.96 % compared to other baseline GAN models, showcasing its ability to produce more realistic coal-gangue images. Finally, the data augmentation strategies are applied to the YOLOv4 model, enhancing the mAP by 9.26 %, highlighting its significance in enhancing coal-gangue object detection. These results have important implications for the development and implementation of computer vision-based technologies, enabling the realization of cleaner and more efficient coal separation methods.