Search

Self-consistent field (SCF) analysis is an indispensable tool for predicting the microphase separation structures of polymer alloys. However, the computation of the phase-separated structures in the equilibrium state is computationally intensive, leading to high costs. To address this challenge, we propose a novel deep learning approach that leverages a generative adversarial network (GAN), a powerful deep generative model, to accelerate SCF analysis. Specifically, we trained the GAN using comprehensive data obtained from SCF analysis, enabling us to generate various images of feasible structures that are similar to the SCF analysis results. Our results demonstrate that the latent variables in the GAN are linked to the physical parameters and features of the phase-separation structures. [ABSTRACT FROM AUTHOR]

With the increasing number of financial transactions, financial fraud has become increasingly serious for financial institutions and the public. The core idea of this model is to integrate multiple neural network structures and utilize their respective advantages to improve the performance of fraud detection. Firstly, we employed the convolutional neural network with interpretable blocks (CNNIB) convolutional neural network (CNN) to extract key features from the data to capture patterns and patterns in fraud cases. Secondly, we introduced the autoencoder generative adversarial network (AE-GAN) adversarial network to perform feature analysis on sequence data to capture temporal features in transaction sequences. Finally, we used differential detection for classification to determine whether transactions were fraudulent. An independent detection module was established to accelerate the recognition of financial fraud, and parameter indicators were optimized. Finally, a hybrid neural network model was established. The experimental results indicate that our model has achieved significant results in quickly detecting financial fraud; compared with traditional single neural network models, hybrid neural network models have significant improvements in accuracy and efficiency. In addition, we conducted in-depth analysis of the model and revealed its performance stability under different training set sizes and data distributions. Our research findings provide an effective tool for financial institutions to quickly identify financial fraud. [ABSTRACT FROM AUTHOR]

Generative Artificial Intelligence (GAI) represents an emerging field that promises the creation of synthetic data and outputs in different modalities. GAI has recently shown impressive results across a large spectrum of applications ranging from biology, medicine, education, legislation, computer science, and finance. As one strives for enhanced safety, efficiency, and sustainability, generative AI indeed emerges as a key differentiator and promises a paradigm shift in the field. This article explores the potential applications of generative AI and large language models in geoscience. The recent developments in the field of machine learning and deep learning have enabled the generative model's utility for tackling diverse prediction problems, simulation, and multi‐criteria decision‐making challenges related to geoscience and Earth system dynamics. This survey discusses several GAI models that have been used in geoscience comprising generative adversarial networks (GANs), physics‐informed neural networks (PINNs), and generative pre‐trained transformer (GPT)‐based structures. These tools have helped the geoscience community in several applications, including (but not limited to) data generation/augmentation, super‐resolution, panchromatic sharpening, haze removal, restoration, and land surface changing. Some challenges still remain, such as ensuring physical interpretation, nefarious use cases, and trustworthiness. Beyond that, GAI models show promises to the geoscience community, especially with the support to climate change, urban science, atmospheric science, marine science, and planetary science through their extraordinary ability to data‐driven modelling and uncertainty quantification. [ABSTRACT FROM AUTHOR]

Dynamic latent scale GAN is an architecture‐agnostic encoder‐based generative model inversion method. This paper introduces a method to efficiently integrate perceptual VAE into dynamic latent scale GAN to improve the performance of dynamic latent scale GAN. When dynamic latent scale GAN is trained with a normal i.i.d. latent random variable and the latent encoder is integrated into the discriminator, a sum of a predicted latent random variable of real data and a scaled normal noise follows the normal i.i.d. random variable. Since this random variable is paired with real data and follows the latent random variable, it can be used for both VAE and GAN training. Furthermore, by considering the intermediate layer output of the discriminator as the feature encoder output, the VAE can be trained to minimise the perceptual reconstruction loss. The forward propagation & backpropagation for minimising this perceptual reconstruction loss can be integrated with those of GAN training. Therefore, the proposed method does not require additional computations compared to typical GAN or dynamic latent scale GAN. Integrating perceptual VAE to dynamic latent scale GAN improved the generative and inversion performance of the model. [ABSTRACT FROM AUTHOR]

Satellite cloud image sequences contain rich spatial and temporal information, and forecasting future cloud image sequences is of great significance for meteorological research. Traditional satellite cloud image prediction methods usually ignore nonlinear variations in cloud masses, leading to large errors in prediction results and low prediction efficiency. The use of existing video prediction methods for satellite cloud image sequence prediction also suffers from problems of blurred prediction images and the accumulation of sequence errors. To address these issues, we propose a Multi-feature Extraction and High-resolution Generative Network (MEHGNet) for the prediction of satellite cloud image sequences, which consists of an encoder, a translator, a decoder, and a generator. To learn the spatial features and spatiotemporal dependencies of cloud images, 2D convolution multi-head attention mechanisms and local residue connections are introduced to the encoder and decoder. The generator preserves detailed features and improves the resolution of the predicted images using the generative ability of generative adversarial networks. In addition, a motion-aware loss function is proposed to learn high-level features of motion variations among cloud image sequences. Experiments on satellite datasets demonstrate that the proposed method is superior compared to other prediction methods. [ABSTRACT FROM AUTHOR]

Acquiring global ocean digital elevation model (DEM) is a forefront branch of marine geology and hydrographic survey that plays a crucial role in the study of the Earth's system and seafloor's structure. Due to limitations in technological capabilities and surveying costs, large-scale sampling of ocean depths is very coarse, making it challenging to directly create complete ocean DEM. Many traditional interpolation and deep learning methods have been applied to reconstruct ocean DEM images. However, the continuity and heterogeneity of ocean terrain data are too complex to be approximated effectively by traditional interpolation models. Meanwhile, due to the scarcity of available data, training an sufficient network directly with deep learning methods is difficult. In this work, we propose a conditional generative adversarial network (CGAN) based on transfer learning, which applies knowledge learned from land terrain to ocean terrain. We pre-train the model using land DEM data and fine-tune it using ocean DEM data. Specifically, we utilize randomly sampled ocean terrain data as network input, employ CGAN with U-Net architecture and residual blocks to capture terrain features of images through adversarial training, resulting in reconstructed bathymetric terrain images. The training process is constrained by the combined loss composed of adversarial loss, reconstruction loss, and perceptual loss. Experimental results demonstrate that our approach reduces the required amount of training data, and achieves better reconstruction accuracy compared to traditional methods. [ABSTRACT FROM AUTHOR]

Background: Vessel‐wall volume and localized three‐dimensional ultrasound (3DUS) metrics are sensitive to the change of carotid atherosclerosis in response to medical/dietary interventions. Manual segmentation of the media‐adventitia boundary (MAB) and lumen‐intima boundary (LIB) required to obtain these metrics is time‐consuming and prone to observer variability. Although supervised deep‐learning segmentation models have been proposed, training of these models requires a sizeable manually segmented training set, making larger clinical studies prohibitive. Purpose: We aim to develop a method to optimize pre‐trained segmentation models without requiring manual segmentation to supervise the fine‐tuning process. Methods: We developed an adversarial framework called the unsupervised shape‐and‐texture generative adversarial network (USTGAN) to fine‐tune a convolutional neural network (CNN) pre‐trained on a source dataset for accurate segmentation of a target dataset. The network integrates a novel texture‐based discriminator with a shape‐based discriminator, which together provide feedback for the CNN to segment the target images in a similar way as the source images. The texture‐based discriminator increases the accuracy of the CNN in locating the artery, thereby lowering the number of failed segmentations. Failed segmentation was further reduced by a self‐checking mechanism to flag longitudinal discontinuity of the artery and by self‐correction strategies involving surface interpolation followed by a case‐specific tuning of the CNN. The U‐Net was pre‐trained by the source dataset involving 224 3DUS volumes with 136, 44, and 44 volumes in the training, validation and testing sets. The training of USTGAN involved the same training group of 136 volumes in the source dataset and 533 volumes in the target dataset. No segmented boundaries for the target cohort were available for training USTGAN. The validation and testing of USTGAN involved 118 and 104 volumes from the target cohort, respectively. The segmentation accuracy was quantified by Dice Similarity Coefficient (DSC), and incorrect localization rate (ILR). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference of DSCs between models and settings, where p≤0.05$p\,\le \,0.05$ was considered statistically significant. Results: USTGAN attained a DSC of 85.7±13.0$85.7\,\pm \,13.0$% in LIB and 86.2±10.6${86.2}\,\pm \,{10.6}$% in MAB, improving from the baseline performance of 74.6±30.7${74.6}\,\pm \,{30.7}$% in LIB (p<10−12$<10^{-12}$) and 75.7±28.9${75.7}\,\pm \,{28.9}$% in MAB (p<10−12$<10^{-12}$). Our approach outperformed six state‐of‐the‐art domain‐adaptation models (MAB: p≤3.63×10−7$p \le 3.63\,\times \,10^{-7}$, LIB: p≤9.34×10−8$p\,\le \,9.34\,\times \,10^{-8}$). The proposed USTGAN also had the lowest ILR among the methods compared (LIB: 2.5%, MAB: 1.7%). Conclusion: Our framework improves segmentation generalizability, thereby facilitating efficient carotid disease monitoring in multicenter trials and in clinics with less expertise in 3DUS imaging. [ABSTRACT FROM AUTHOR]

New epidemics encourage the development of new mathematical models of the spread and forecasting of infectious diseases. Statistical epidemiology data are characterized by incomplete and inexact time series, which leads to an unstable and non-unique forecasting of infectious diseases. In this paper, a model of a conditional generative adversarial neural network (CGAN) for modeling and forecasting COVID-19 in St. Petersburg is constructed. It takes 20 processed historical statistics as a condition and is based on the solution of the minimax problem. The CGAN builds a short-term forecast of the number of newly diagnosed COVID-19 cases in the region for 5 days ahead. The CGAN approach allows modeling the distribution of statistical data, which allows obtaining the required amount of training data from the resulting distribution. When comparing the forecasting results with the classical differential SEIR-HCD model and a recurrent neural network with the same input parameters, it was shown that the forecast errors of all three models are in the same range. It is shown that the prediction error of the bagging model based on three models is lower than the results of each model separately. [ABSTRACT FROM AUTHOR]

Positioning service is a critical technology that bridges the physical world with digital information, significantly enhancing efficiency and convenience in life and work. The evolution of 5G technology has proven that positioning services are integral components of current and future cellular networks. However, positioning accuracy is hindered by non-line-of-sight (NLoS) propagation, which severely affects the measurements of angles and delays. In this study, we introduced a deep autoencoding channel transform-generative adversarial network model that utilizes line-of-sight (LoS) samples as a singular category training set to fully extract the latent features of LoS, ultimately employing a discriminator as an NLoS identifier. We validated the proposed model in 5G indoor and indoor factory (dense clutter, low base station) scenarios by assessing its generalization capability across different scenarios. The results indicate that, compared to the state-of-the-art method, the proposed model markedly diminished the utilization of device resources and achieved a 2.15% higher area under the curve while reducing computing time by 12.6%. This approach holds promise for deployment in future positioning terminals to achieve superior localization precision, catering to commercial and industrial Internet of Things applications. [ABSTRACT FROM AUTHOR]

This paper presents a novel framework for 3D face reconstruction from single 2D images and addresses critical limitations in existing methods. Our approach integrates modified adversarial neural networks with graph neural networks to achieve state-of-the-art performance. Key innovations include (1) a generator architecture based on Graph Convolutional Networks (GCNs) with a novel loss function and identity blocks, mitigating mode collapse and instability; (2) the integration of facial landmarks and a non-parametric efficient-net decoder for enhanced feature capture; and (3) a lightweight GCN-based discriminator for improved accuracy and stability. Evaluated on the 300W-LP and AFLW2000-3D datasets, our method outperforms existing approaches, reducing Chamfer Distance by 62.7% and Earth Mover's Distance by 57.1% on 300W-LP. Moreover, our framework demonstrates superior robustness to variations in head positioning, occlusion, noise, and lighting conditions while achieving significantly faster processing times. [ABSTRACT FROM AUTHOR]

Protamines play a critical role in DNA compaction and stabilization in sperm cells, significantly influencing male fertility and various biotechnological applications. Traditionally, identifying these proteins is a challenging and time-consuming process due to their species-specific variability and complexity. Leveraging advancements in computational biology, we present PROTA, a novel tool that combines machine learning (ML) and deep learning (DL) techniques to predict protamines with high accuracy. For the first time, we integrate Generative Adversarial Networks (GANs) with supervised learning methods to enhance the accuracy and generalizability of protamine prediction. Our methodology evaluated multiple ML models, including Light Gradient-Boosting Machine (LIGHTGBM), Multilayer Perceptron (MLP), Random Forest (RF), eXtreme Gradient Boosting (XGBOOST), k-Nearest Neighbors (KNN), Logistic Regression (LR), Naive Bayes (NB), and Radial Basis Function-Support Vector Machine (RBF-SVM). During ten-fold cross-validation on our training dataset, the MLP model with GAN-augmented data demonstrated superior performance metrics: 0.997 accuracy, 0.997 F1 score, 0.998 precision, 0.997 sensitivity, and 1.0 AUC. In the independent testing phase, this model achieved 0.999 accuracy, 0.999 F1 score, 1.0 precision, 0.999 sensitivity, and 1.0 AUC. These results establish PROTA, accessible via a user-friendly web application. We anticipate that PROTA will be a crucial resource for researchers, enabling the rapid and reliable prediction of protamines, thereby advancing our understanding of their roles in reproductive biology, biotechnology, and medicine. [ABSTRACT FROM AUTHOR]

This paper presents a novel two-stage optimization framework enhanced by deep learning-based robust optimization (GAN-RO) aimed at advancing the integration of photovoltaic (PV) systems into the power grid. Facing the challenge of inherent variability and unpredictability of renewable energy sources, such as solar and wind, traditional energy management systems often struggle with efficiency and grid stability. This research addresses these challenges by implementing a Generative Adversarial Network (GAN) to generate realistic and diverse scenarios of solar energy availability and demand patterns, which are integrated into a robust optimization model to dynamically adjust operational strategies. The proposed GAN-RO framework is demonstrated to significantly enhance grid management by improving several key performance metrics: reducing average energy costs by 20%, lowering carbon emissions by 30%, and increasing system efficiency by 8.5%. Additionally, it has effectively halved the operational downtime from 120 to 60 h annually. The scenario-based analysis further illustrates the framework's capacity to adapt and optimize under varying conditions, achieving up to 96% system efficiency and demonstrating substantial reductions in energy costs across different scenarios. This study not only underscores the technical advancements in managing renewable energy integration, but also highlights the economic and environmental benefits of utilizing AI-driven optimization techniques. The integration of GAN-generated scenarios with robust optimization represents a significant stride towards developing resilient, efficient, and sustainable energy management systems for the future. [ABSTRACT FROM AUTHOR]

A new model called the Transformer-Unet Generative Adversarial Network (TUGAN) is proposed for super-resolution reconstruction of digital elevation models (DEMs). Digital elevation models are used in many fields, including environmental science, geology and agriculture. The proposed model uses a self-similarity Transformer (SSTrans) as the generator and U-Net as the discriminator. SSTrans, a model that we previously proposed, can yield good reconstruction results in structurally complex areas but has little advantage when the surface is simple and smooth because too many additional details have been added to the data. To resolve this issue, we propose the novel TUGAN model, where U-Net is capable of multilayer jump connections, which enables the discriminator to consider both global and local information when making judgments. The experiments show that TUGAN achieves state-of-the-art results for all types of terrain details. [ABSTRACT FROM AUTHOR]

Thin clouds in Remote Sensing (RS) imagery can negatively impact subsequent applications. Current Deep Learning (DL) approaches often prioritize information recovery in cloud-covered areas but may not adequately preserve information in cloud-free regions, leading to color distortion, detail loss, and visual artifacts. This study proposes a Sparse Transformer-based Generative Adversarial Network (SpT-GAN) to solve these problems. First, a global enhancement feature extraction module is added to the generator's top layer to enhance the model's ability to preserve ground feature information in cloud-free areas. Then, the processed feature map is reconstructed using the sparse transformer-based encoder and decoder with an adaptive threshold filtering mechanism to ensure sparsity. This mechanism enables that the model preserves robust long-range modeling capabilities while disregarding irrelevant details. In addition, inverted residual Fourier transformation blocks are added at each level of the structure to filter redundant information and enhance the quality of the generated cloud-free images. Finally, a composite loss function is created to minimize error in the generated images, resulting in improved resolution and color fidelity. SpT-GAN achieves outstanding results in removing clouds both quantitatively and visually, with Structural Similarity Index (SSIM) values of 98.06% and 92.19% and Peak Signal-to-Noise Ratio (PSNR) values of 36.19 dB and 30.53 dB on the RICE1 and T-Cloud datasets, respectively. On the T-Cloud dataset, especially with more complex cloud components, the superior ability of SpT-GAN to restore ground details is more evident. [ABSTRACT FROM AUTHOR]

Aiming to solve the challenges of difficult training, mode collapse in current generative adversarial networks (GANs), and the efficiency issue of requiring multiple samples for Denoising Diffusion Probabilistic Models (DDPM), this paper proposes a satellite remote sensing grayscale image colorization method using a denoising GAN. Firstly, a denoising optimization method based on U-ViT for the generator network is introduced to further enhance the model's generation capability, along with two optimization strategies to significantly reduce the computational burden. Secondly, the discriminator network is optimized by proposing a feature statistical discrimination network, which imposes fewer constraints on the generator network. Finally, grayscale image colorization comparative experiments are conducted on three real satellite remote sensing grayscale image datasets. The results compared with existing typical colorization methods demonstrate that the proposed method can generate color images of higher quality, achieving better performance in both subjective human visual perception and objective metric evaluation. Experiments in building object detection show that the generated color images can improve target detection performance compared to the original grayscale images, demonstrating significant practical value. [ABSTRACT FROM AUTHOR]

Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalanced number between the target and the background spatially and the high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation-learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and spatial–spectral features to improve its representation ability. Firstly, a Graph Convolutional Network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene's underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing the detection and background suppression capabilities. The performance of the proposed approach is evaluated using the average scores of AU C D , F , AU C F , τ , AU C BS , and AU C SNPR . The corresponding values are 0.99660, 0.00078, 0.99587, and 333.629, respectively. These results demonstrate the accuracy of the model in different evaluation metrics, with AU C D , F achieving the highest score, indicating strong detection performance across varying thresholds. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture. [ABSTRACT FROM AUTHOR]

Functional magnetic resonance imaging (fMRI) is currently one of the most popular technologies for measuring brain activity in both research and clinical contexts. However, clinical constraints often result in short fMRI scan durations, limiting the diagnostic performance for brain disorders. To address this limitation, we developed an end‐to‐end frequency‐specific dual‐attention‐based adversarial network (FDAA‐Net) to extend the time series of existing blood oxygen level‐dependent (BOLD) data, enhancing their diagnostic utility. Our approach leverages the frequency‐dependent nature of fMRI signals using variational mode decomposition (VMD), which adaptively tracks brain activity across different frequency bands. We integrated the generative adversarial network (GAN) with a spatial–temporal attention mechanism to fully capture relationships among spatially distributed brain regions and temporally continuous time windows. We also introduced a novel loss function to estimate the upward and downward trends of each frequency component. We validated FDAA‐Net on the Human Connectome Project (HCP) database by comparing the original and predicted time series of brain regions in the default mode network (DMN), a key network activated during rest. FDAA‐Net effectively overcame linear frequency‐specific challenges and outperformed other popular prediction models. Test–retest reliability experiments demonstrated high consistency between the functional connectivity of predicted outcomes and targets. Furthermore, we examined the clinical applicability of FDAA‐Net using short‐term fMRI data from individuals with autism spectrum disorder (ASD) and major depressive disorder (MDD). The model achieved a maximum predicted sequence length of 40% of the original scan durations. The prolonged time series improved diagnostic performance by 8.0% for ASD and 11.3% for MDD compared with the original sequences. These findings highlight the potential of fMRI time series prediction to enhance diagnostic power of brain disorders in short fMRI scans. [ABSTRACT FROM AUTHOR]

Transmission electron microscopy (TEM) plays a crucial role in heterogeneous catalysis for assessing the size distribution of supported metal nanoparticles. Typically, nanoparticle size is quantified by measuring the diameter under the assumption of spherical geometry, a simplification that limits the precision needed for advancing synthesis‐structure‐performance relationships. Currently, there is a lack of techniques that can reliably extract more meaningful information from atomically resolved TEM images, like nuclearity or geometry. Here, cycle‐consistent generative adversarial networks (CycleGANs) are explored to bridge experimental and simulated images, directly linking experimental observations with information from their underlying atomic structure. Using the versatile Pt/CeO2 (Pt particles centered ≈2 nm) catalyst synthesized by impregnation, large datasets of experimental scanning transmission electron micrographs and physical image simulations are created to train a CycleGAN. A subsequent size‐estimation network is developed to determine the nuclearity of imaged nanoparticles, providing plausible estimates for ≈70% of experimentally observed particles. This automatic approach enables precise size determination of supported nanoparticle‐based catalysts overcoming crystal orientation limitations of conventional techniques, promising high accuracy with sufficient training data. Tools like this are envisioned to be of great use in designing and characterizing catalytic materials with improved atomic precision. [ABSTRACT FROM AUTHOR]

In this paper we present a novel multi-attribute face manipulation method based on textual descriptions. Previous text-based image editing methods either require test-time optimization for each individual image or are restricted to single attribute editing. Extending these methods to multi-attribute face image editing scenarios will introduce undesired excessive attribute change, e.g., text-relevant attributes are overly manipulated and text-irrelevant attributes are also changed. In order to address these challenges and achieve natural editing over multiple face attributes, we propose a new decoupling training scheme where we use group sampling to get text segments from same attribute categories, instead of whole complex sentences. Further, to preserve other existing face attributes, we encourage the model to edit the latent code of each attribute separately via an entropy constraint. During the inference phase, our model is able to edit new face images without any test-time optimization, even from complex textual prompts. We show extensive experiments and analysis to demonstrate the efficacy of our method, which generates natural manipulated faces with minimal text-irrelevant attribute editing. Code and pre-trained model are available at https://github.com/hwang1996/ManiCLIP. [ABSTRACT FROM AUTHOR]

Understanding time-series interplay of genes is essential for diagnosis and treatment of disease. Spatio-temporally enriched NGS data contain important underlying regulatory mechanisms of biological processes. Generative adversarial networks (GANs) have been used to augment biological data to describe hidden intermediate time-series gene expression profiles during specific biological processes. Developing a pipeline that uses augmented time-series gene expression profiles is needed to provide an unbiased systemic-level map of biological processes and test for the statistical significance of the generated dataset, leading to the discovery of hidden intermediate regulators. Two analytical methods, GAN-WGCNA (weighted gene co-expression network analysis) and rDEG (rescued differentially expressed gene), interpreted spatiotemporal information and screened intermediate genes during cocaine addiction. GAN-WGCNA enables correlation calculations between phenotype and gene expression profiles and visualizes time-series gene module interplay. We analyzed a transcriptome dataset of two weeks of cocaine self-administration in C57BL/6J mice. Utilizing GAN-WGCNA, two genes (Alcam and Celf4) were selected as missed intermediate significant genes that showed high correlation with addiction behavior. Their correlation with addictive behavior was observed to be notably significant in aspect of statistics, and their expression and co-regulation were comprehensively mapped in terms of time, brain region, and biological process. [ABSTRACT FROM AUTHOR]

Background: Deep learning (DL)-based denoising has been proven to improve image quality and quantitation accuracy of low dose (LD) SPECT. However, conventional DL-based methods used SPECT images with mixed frequency components. This work aims to develop an integrated multi-frequency denoising network to further enhance LD myocardial perfusion (MP) SPECT denoising. Methods: Fifty anonymized patients who underwent routine 99mTc-sestamibi stress SPECT/CT scans were retrospectively recruited. Three LD datasets were obtained by reducing the 10 s acquisition time of full dose (FD) SPECT to be 5, 2 and 1 s per projection based on the list mode data for a total of 60 projections. FD and LD projections were Fourier transformed to magnitude and phase images, which were then separated into two or three frequency bands. Each frequency band was then inversed Fourier transformed back to the image domain. We proposed a 3D integrated attention-guided multi-frequency conditional generative adversarial network (AttMFGAN) and compared with AttGAN, and separate AttGAN for multi-frequency bands denoising (AttGAN-MF).The multi-frequency FD and LD projections of 35, 5 and 10 patients were paired for training, validation and testing. The LD projections to be tested were separated to multi-frequency components and input to corresponding networks to get the denoised components, which were summed to get the final denoised projections. Voxel-based error indices were measured on the cardiac region on the reconstructed images. The perfusion defect size (PDS) was also analyzed. Results: AttGAN-MF and AttMFGAN have superior performance on all physical and clinical indices as compared to conventional AttGAN. The integrated AttMFGAN is better than AttGAN-MF. Multi-frequency denoising with two frequency bands have generally better results than corresponding three-frequency bands methods. Conclusions: AttGAN-MF and AttMFGAN are promising to further improve LD MP SPECT denoising. [ABSTRACT FROM AUTHOR]

Video error concealment can effectively improve the visual perception quality of videos damaged by packet loss in video transmission or error reception at the decoder. The latest versatile video coding (VVC) standard further improves the compression performance and lacks error recovery mechanism, which makes the VVC bitstream highly sensitive to errors. Most of the existing error concealment algorithms are designed for the video coding standards before VVC and are not applicable to VVC; thus, the research on video error concealment for VVC is urgently needed. In this paper, a novel deep video error concealment model for VVC is proposed, called Swin-VEC. The model innovatively integrates Video Swin Transformer into the generator of generative adversarial network (GAN). Specifically, the generator of the model employs convolutional neural network (CNN) to extract shallow features, and utilizes the Video Swin Transformer to extract deep multi-scale features. Subsequently, the designed dual upsampling modules are used to accomplish the recovery of spatiotemporal dimensions, and combined with CNN to achieve frame reconstruction. Moreover, an augmented dataset BVI-DVC-VVC is constructed for model training and verification. The optimization of the model is realized by adversarial training. Extensive experiments on BVI-DVC-VVC and UCF101 demonstrate the effectiveness and superiority of our proposed model for the video error concealment of VVC. [ABSTRACT FROM AUTHOR]

Semi-supervised learning, which entails training a model with manually labeled images and pseudo-labels for unlabeled images, has garnered considerable attention for its potential to improve image classification performance. Nevertheless, incorrect decision boundaries of classifiers and wrong pseudo-labels for beneficial unlabeled images below the confidence threshold increase the generalization error in semi-supervised learning. This study proposes a novel framework for semi-supervised learning termed consistency-regularized bad generative adversarial network (CRBSGAN) through a new loss function. The proposed model comprises a discriminator, a bad generator, and a classifier that employs data augmentation and consistency regularization. Local augmentation is created to compensate for data scarcity and boost bad generators. Moreover, label consistency regularization is considered for bad fake images, real labeled images, unlabeled images, and latent space for the discriminator and bad generator. In the adversarial game between the discriminator and the bad generator, feature space is better captured under these conditions. Furthermore, local consistency regularization for good-augmented images applied to the classifier strengthens the bad generator in the generator–classifier adversarial game. The consistency-regularized bad generator produces informative fake images similar to the support vectors located near the correct classification boundary. In addition, the pseudo-label error is reduced for low-confidence unlabeled images used in training. The proposed method reduces the state-of-the-art error rate from 6.44 to 4.02 on CIFAR-10, 2.06 to 1.56 on MNIST, and 6.07 to 3.26 on SVHN using 4000, 3000, and 500 labeled training images, respectively. Furthermore, it achieves a reduction in the error rate on the CINIC-10 dataset from 19.38 to 15.32 and on the STL-10 dataset from 27 to 16.34 when utilizing 1000 and 500 labeled images per class, respectively. Experimental results and visual synthesis indicate that the CRBSGAN algorithm is more efficient than the methods proposed in previous works. The source code is available at https://github.com/ms-iraji/CRBSGAN ↗. [ABSTRACT FROM AUTHOR]

Concrete building structures are prone to cracking as they are subjected to environmental temperatures, freeze-thaw cycles, and other operational environmental factors. Failure to detect cracks in the key building structure at the early stage can result in serious accidents and associated economic losses. A new method using the SE-U-Net model based on a conditional generative adversarial network (CGAN) has been developed to identify small cracks in concrete structures in this paper. This proposed method was a pixel-level U-Net model based on a generative network, that was integrated the original convolutional layer with an attention mechanism, and an SE module in the jump connection section was added to improve the identifiability of the model. The discriminative network compared the generated images with real images using the PatchGAN model. Through the adversarial training of generator and discriminator, the performance of generator in crack image segmentation task is improved, and the trained generation network is used to segment cracks. In damage assessments, the crack skeleton was represented by the individual pixel width and recognized using the binary morphological crack skeleton method, in which the final length, area, and average width of the crack could be determined through the geometric correction index. The results showed that compared with other methods, the proposed method could better identify subtle pixel-level cracks, and the identification accuracy is 98.48%. These methods are of great significance for the identification of cracks and the damage assessment of concrete structures in practice. [ABSTRACT FROM AUTHOR]

The restoration of blurred images is a crucial topic in the field of machine vision, with far-reaching implications for enhancing information acquisition quality, improving algorithmic accuracy and enriching image texture. Efforts to mitigate the phenomenon of blur have progressed from statistical approaches to those utilizing deep learning techniques. In this paper, we propose a Generative Adversarial Network (GAN)-based image restoration method to address the limitations of existing techniques in restoring color and detail in motion-blurred images. To reduce the computational complexity of generative adversarial networks and the vanishing gradient during learning, an U-net-based generator is used, and it is configured to emphasize the channel and spatial characteristics of the original information through a proposed CSAR(Channel and Spatial Attention Residual) blocks module rather than a simple concatenate operation. To validate the efficacy of the algorithm, comprehensive comparative experiments have been conducted on the GoPro dataset. Experimental results show that the peak signal-to-noise ratio is improved compared to SRN and MPRNet algorithms with good image restoration ability. Objects detection experiments using Yolo V3 showed that the proposed algorithms can generate deblerring images with higher information quality. [ABSTRACT FROM AUTHOR]

In this work we assess the impact of the limited availability of wall-embedded sensors on the full 3D estimation of the flow field in a turbulent channel with R e τ = 200 . The estimation technique is based on a 3D generative adversarial network (3D-GAN). We recently demonstrated that 3D-GANs are capable of estimating fields with good accuracy by employing fully-resolved wall quantities (pressure and streamwise/spanwise wall shear stress on a grid with DNS resolution). However, the practical implementation in an experimental setting is challenging due to the large number of sensors required. In this work, we aim to estimate the flow fields with substantially fewer sensors. The impact of the reduction of the number of sensors on the quality of the flow reconstruction is assessed in terms of accuracy degradation and spectral length-scales involved. It is found that the accuracy degradation is mainly due to the spatial undersampling of scales, rather than the reduction of the number of sensors per se. We explore the performance of the estimator in case only one wall quantity is available. When a large number of sensors is available, pressure measurements provide more accurate flow field estimations. Conversely, the elongated patterns of the streamwise wall shear stress make this quantity the most suitable when only few sensors are available. As a further step towards a real application, the effect of sensor noise is also quantified. It is shown that configurations with fewer sensors are less sensitive to measurement noise. [ABSTRACT FROM AUTHOR]

Generalized zero-shot learning (GZSL) can classify both seen and unseen class samples, which plays a significant role in practical applications such as emerging species recognition and medical image recognition. However, most existing GZSL methods directly use the pre-trained deep model to learn the image feature. Due to the data distribution inconsistency between the GZSL dataset and the pre-training dataset, the obtained image features have an inferior performance. The distribution of different class image features is similar, which makes them difficult to distinguish. To solve this problem, we propose a dual-path feature enhancement (DPFE) model, which consists of four modules: the feature generation network (FGN), the local fine-grained feature enhancement (LFFE) module, the global coarse-grained feature enhancement (GCFE) module, and the feedback module (FM). The feature generation network can synthesize unseen class image features. We enhance the image features’ discriminative and semantic relevance from both local and global perspectives. To focus on the image’s local discriminative regions, the LFFE module processes the image in blocks and minimizes the semantic cycle-consistency loss to ensure that the region block features contain key classification semantic information. To prevent information loss caused by image blocking, we design the GCFE module. It ensures the consistency between the global image features and the semantic centers, thereby improving the discriminative power of the features. In addition, the feedback module feeds the discriminator network’s middle layer information back to the generator network. As a result, the synthesized image features are more similar to the real features. Experimental results demonstrate that the proposed DPFE method outperforms the state-of-the-arts on four zero-shot learning benchmark datasets. [ABSTRACT FROM AUTHOR]

To address issues such as instability during the training of Generative Adversarial Networks, insufficient clarity in facial structure restoration, inadequate utilization of known information, and lack of attention to color information in images, a Cross-Attention Restoration Network is proposed. Initially, in the decoding part of the basic first-stage U-Net network, a combination of sub-pixel convolution and upsampling modules is employed to remedy the low-quality image restoration issue associated with single upsampling in the image recovery process. Subsequently, the restoration part of the first-stage network and the un-restored images are used to compute cross-attention in both spatial and channel dimensions, recovering the complete facial restoration image from the known repaired information. At the same time, we propose a loss function based on HSV space, assigning appropriate weights within the function to significantly improve the color aspects of the image. Compared to classical methods, this model exhibits good performance in terms of peak signal-to-noise ratio, structural similarity, and FID. [ABSTRACT FROM AUTHOR]

Combining synthetic aperture radar and optical imagery can effectively improve crop type identification. However, optical remote sensing imagery is limited by cloud contamination. In this study, fake optical images were generated using seven image-to-image translation methods and their performance in improving crop classification accuracies was evaluated. Although the sensitivity analysis of the classification models showed lower similarity between real and fake images in the near-infrared band compared to the green and red bands, a significant improvement was confirmed after adding fake images created by generative adversarial networks (GANs). In this study, we generated fake optical images using GAN–based SAR–optical image transformations and evaluated whether adding these fake optical images contributes to improving the accuracy of crop identification from SAR images. This was especially true for the signed attribute vector image-to-image transformation (SAVI2I) method, which was the most effective, achieving an overall accuracy (OA) of 81.3 % with an allocation disagreement (AD) of 11.8 % and a quantity disagreement (QD) of 6.9 %. In contrast, the OA, AD, and QD were respectively 75.9 %, 18.2 %, and 5.9 % when only vertical-horizontal polarization, vertical–vertical polarization, or the polarization ratio were applied. As a result, it was demonstrated that utilizing fake images generated through GAN–based SAR–optical image transformations is effective in improving the accuracy of crop identification from SAR images. [ABSTRACT FROM AUTHOR]

In tutorial format, this paper explores the intricate relationship between Artificial Intelligence (AI) and managerial decision-making, emphasizing the alignment problem--a critical challenge in ensuring AI systems align with human values and ethical standards. It defines AI and examines various methods, including machine learning algorithms, natural language processing, recommendation systems, sentiment analysis, data visualization, anomaly detection, expert systems, neural networks, and deep learning. The alignment problem is dissected into key aspects such as defining goals, value misalignment, robustness and safety, long-term consequences, and interpreting human preferences. The types of AI most affected by the alignment problem, including deep learning, reinforcement learning, generative adversarial networks, evolutionary algorithms, and open-ended learning systems, are highlighted. Practical examples illustrate how biases and misalignments manifest in business processes like recruitment, credit scoring, and automated trading. The paper also categorizes managerial decisions and discusses how AI methods support these decisions while addressing alignment issues. This document underscores the importance of aligning AI systems with human values to ensure ethical and effective outcomes in business environments. This paper is intended to be a road map of possible research topics on the effect of AI on Business Decision Making through the lens of the Alignment Problem. [ABSTRACT FROM AUTHOR]

We obtain the air quality index (AQI) for a descriptive system aimed to communicate pollution risks to the population. The AQI is calculated based on major air pollutants including O3, CO, SO2, NO, NO2, benzene, and particulate matter PM2.5 that should be continuously balanced in clean air. Air pollution is a major limitation for urbanization and population growth in developing countries. Hence, automated AQI prediction by a deep learning method applied to time series may be advantageous. We use a seasonal autoregressive integrated moving average (SARIMA) model for predicting values reflecting past trends considered as seasonal patterns. In addition, a transductive long short‐term memory (TLSTM) model learns dependencies through recurring memory blocks, thus learning long‐term dependencies for AQI prediction. Further, the TLSTM increases the accuracy close to test points, which constitute a validation group. AQI prediction results confirm that the proposed SARIMA–TLSTM model achieves a higher accuracy (93%) than an existing convolutional neural network (87.98%), least absolute shrinkage and selection operator model (78%), and generative adversarial network (89.4%). [ABSTRACT FROM AUTHOR]

As the next-generation power system, smart grid presents challenges to enterprises in managing and analyzing massive data, meeting complex operational and decision-making demands, and predicting future power demand for grid optimization. This paper aims to proposed a fusion algorithm for smart grid enterprise decision-making and economic benefit analysis, enhancing the accuracy of decision-making and predictive capability of economic benefits. The proposed method combines techniques such as Long Short-Term Memory (LSTM), Generative Adversarial Networks (GAN), and edge computing. The LSTM model is employed to model historical data of the smart grid. The GAN model generates diverse scenarios for future power demand and economic benefits. The proposed method is evaluated on four public datasets, including the ENTSO-E Dataset, and outperforms several traditional algorithms in terms of prediction accuracy, efficiency, and stability. Notably, on the ENTSO-E Dataset, the proposed algorithm achieves a reduction of over 46.6% in FLOP, and a decrease in inference time by over 48.3%, and an improvement of 38% in MAPE. The novel fusion algorithm proposed in this paper demonstrates significant advantages in accuracy and predictive capability, providing a scientific basis for smart grid enterprise decision-making and economic benefit analysis while offering practical value for real-world applications. • A novel fusion algorithm for accurate load demand prediction in smart grids. • Training were conducted on multiple datasets and validation was performed. • Significant contributions to risk assessment planning in smart grid enterprises. [ABSTRACT FROM AUTHOR]

Traffic data imputation is crucial for the reliability and efficiency of intelligent transportation systems (ITSs), forming the foundation for downstream tasks like traffic prediction and management. However, existing deep learning-based imputation methods struggle with two significant challenges: poor performance under high missing data rates and the limited incorporation of external traffic-related factors. To address these challenges, we propose a novel knowledge graph-enhanced generative adversarial network (KG-GAN) for traffic data imputation. Our approach uniquely integrates external knowledge with traffic spatiotemporal dependencies to improve data imputation quality. Specifically, we construct a fine-grained knowledge graph (KG) that differentiates attributes and relationships of external factors such as points of interest (POI) and weather conditions, facilitating more robust knowledge representation learning. We then introduce a knowledge-aware embedding cell (EM-cell) that merges traffic data with these learned external representations, providing richer inputs for the spatiotemporal GAN. Extensive experiments on a large-scale real-world traffic dataset demonstrate that KG-GAN significantly outperforms state-of-the-art methods under various missing data scenarios. Additionally, ablation studies confirm the superior performance gained from incorporating external knowledge, underscoring the importance of this approach in addressing complex missing data patterns. [ABSTRACT FROM AUTHOR]

A Wi-Fi-sensing gesture control system for smart homes has been developed based on a theoretical investigation of the Fresnel region sensing model, addressing the need for non-contact gesture control in household environments. The system collects channel state information (CSI) related to gestures from Wi-Fi signals transmitted and received by network cards within a specific area. The collected data undergoes preprocessing to eliminate environmental interference, allowing for the extraction of complete gesture sets. Dynamic feature extraction is then performed, followed by the identification of unknown gestures using pattern recognition techniques. An improved dynamic double threshold gesture interception algorithm is introduced, achieving a gesture interception accuracy of 98.20%. Furthermore, dynamic feature extraction is enhanced using the Gramian Angular Summation Field (GASF) transform, which converts CSI data into GASF graphs for more effective gesture recognition. An enhanced generative adversarial network (GAN) algorithm with an embedded classifier is employed to classify unknown gestures, enabling the simultaneous recognition of multiple gestures. A semi-supervised learning algorithm designed to perform well even with limited labeled data demonstrates high performance in cross-scene gesture recognition. Compared to traditional fully-supervised algorithms like linear discriminant analysis (LDA), Light Gradient Boosting Machine (LightGBM), and support vector machine (SVM), the semi-supervised GAN algorithm achieves an average accuracy of 95.67%, significantly outperforming LDA (58.20%), LightGBM (78.20%), and SVM (75.67%). In conclusion, this novel algorithm maintains an accuracy of over 94% across various scenarios, offering both faster training times and superior accuracy, even with minimal labeled data. [ABSTRACT FROM AUTHOR]

Recent advances in auditory attention detection from multichannel electroencephalography (EEG) signals encounter the challenges of the scarcity of available online EEG data and the detection of auditory attention with low latency. To this end, we propose a complete deep auditory generative adversarial network auxiliary, named auditory-GAN, designed to handle these challenges while generating EEG data and executing auditory spatial detection. The proposed auditory-GAN system consists of a spectro-spatial feature extraction (SSF) module and an auditory generative adversarial network auxiliary (AD-GAN) classifier. The SSF module extracts the spatial feature maps by learning the topographic specificity of alpha power from EEG signals. The designed AD-GAN network addresses the need for extensive training data by synthesizing augmented versions of original EEG data. We validated the proposed method on the widely used KUL dataset. The model assesses the quality of generated EEG images and the accuracy of auditory spatial attention detection. Results show that the proposed auditory-GAN can produce convincing EEG data and achieves a significant i.e., 98.5% spatial attention detection accuracy for a 10-s decision window of 64-channel EEG data. Comparative analysis reveals that the proposed neural approach outperforms existing state-of-the-art models across EEG data ranging from 64 to 32 channels. The Auditory-GAN model is available at https://github.com/tasleem-hello/Auditory-GAN-/tree/Auditory-GAN. [ABSTRACT FROM AUTHOR]

Cotton is one of the major cash crop in the agriculture led economies across the world. Cotton leaf diseases affects its yield globally. Determining cotton lesions on leaves is difficult when the area is big and the size of lesions is varied. Automated cotton lesion detection is quite useful; however, it is challenging due to fewer disease class, limited size datasets, class imbalance problems, and need of comprehensive evaluation metrics. We propose a novel deep learning based method that augments the data using generative adversarial networks (GANs) to reduce the class imbalance issue and an ensemble-based method that combines the feature vector obtained from the three deep learning architectures including VGG16, Inception V3, and ResNet50. The proposed method offers a more precise, efficient and scalable method for automated detection of diseases of cotton crops. We have implemented the proposed method on publicly available dataset with seven disease and one health classes and have achieved highest accuracy of 95% and F-1 score of 98%. The proposed method performs better than existing state of the art methods. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The segmentation of retinal blood vessels in fundus images is critical for the diagnosis and analysis of various ocular, circulatory, and neurological conditions. Accurate segmentation aids in the early detection of diseases such as diabetic retinopathy and glaucoma. Traditional automated segmentation methods often rely on extensive labeled datasets for model pre-training, which limits their generalization capacity. Recent advancements in artificial intelligence and computer vision have introduced foundational models, such as the Segment Anything Model (SAM), which demonstrate strong zero-shot segmentation performance and transferability in natural image processing. However, SAM's application to medical imaging, particularly in retinal vessel segmentation, has produced suboptimal results. This study proposes an improved approach to retinal fundus image segmentation by integrating a Generative Adversarial Network (GAN)-based data augmentation technique to enhance training data diversity. Additionally, a dynamic batch size mechanism was introduced, optimizing the loss function for mask prediction and allowing flexible control over slice selection during loss calculation. This dual enhancement aims to improve the precision of blood vessel segmentation in retinal fundus images, overcoming the limitations observed in previous applications of SAM to medical image segmentation. The proposed method demonstrates potential for advancing the accuracy of retinal vessel segmentation, providing a robust tool for clinical diagnosis. [ABSTRACT FROM AUTHOR]

Tree-structured deep learning classifier models are widely used in dimensional sentiment analysis for efficient feature representation and learning. From this perspective, an Adversarial Tree-structured Convolutional Neural Network with Long Short-Term Memory (A-T-CNN-LSTM) model was developed that adopts the Semantic-enabled Frequency-aware Generative Adversarial Network (SFGAN) to create more adversarial samples for predicting the Valence-Arousal (VA) of the texts or image classes. In contrast, an abrupt change in input data was not handled that impacts the model accuracy. Hence, this article proposes an Adversarial Attention T-CNN-LSTM (AA-T-CNN-LSTM) model to handle abrupt changes and uncertainties in the input data for dimensional sentiment analysis. This model aims to enhance self-adaptation and self-learning efficiency by integrating an attention strategy with the A-T-CNN-LSTM network. This model is constructed based on the SFGAN, CNN, LSTM and attention strategy layers. The CNN captures the spatial dependencies, whereas the LSTM captures the temporal dependencies of the given input data. The attention strategy layer is included after LSTM to adaptively control the proportion of spatial and temporal dependencies by emphasizing a few weights for final output vectors. Moreover, the prediction of VA ratings of the texts or image classes is achieved based on the final output vectors. Finally, the testing outcomes reveal that the AA-T-CNN-LSTM model on the Stanford Sentiment Treebank (SST) and CIFAR-10 datasets reaches an accuracy of 91.84% and 93.14%, respectively, contrasted with the state-of-the-art models. [ABSTRACT FROM AUTHOR]

Accurately upgoing and downgoing wavefield separation is a critical step in vertical seismic profile (VSP) data processing, as its accuracy is directly related to the imaging quality of VSP data. Traditional methods are based mainly on transforms, and their windows are manually set in the transformed domain to obtain the target wavefield. The manual operations often cause errors and affect the accuracy of wavefield separation. In contrast, deep learning algorithms are more automatic, and have achieved a lot in seismic data processing. We propose to employ a conditional generative adversarial network (CGAN) for wavefield separation in VSP data. A CGAN consists of two main components: a generator, which generates new data samples, and a discriminator, which evaluates the generated samples against real data, with both components trained simultaneously in an adversarial manner to improve the quality of generated samples. The full wavefield serves as a constraint to link the generator and discriminator, ensuring that the separated up- and downgoing wavefields align better with the full wavefield. An asymmetric convolution block is introduced to more effectively capture the directional features of the VSP wavefield. To mitigate the influence of amplitude differences between the waves on the network update, the relative downgoing wavefield (obtained by subtracting the predicted upgoing wavefield from the full wavefield) is included in the loss function. Numerical experiments demonstrate that the trained network can effectively learn the characteristics of the up- and downgoing waves, especially their propagation directions, achieving high-precision wavefield separation. [ABSTRACT FROM AUTHOR]

Deep learning presents a generalizable solution for motion correction requiring no pulse sequence modifications or additional hardware, but previous networks have all been applied to coil‐combined data. Multichannel MRI data provide a degree of spatial encoding that may be useful for motion correction. We hypothesize that incorporating deep learning for motion correction prior to coil combination will improve results. A conditional generative adversarial network was trained using simulated rigid motion artifacts in brain images acquired at multiple sites with multiple contrasts (not limited to healthy subjects). We compared the performance of deep‐learning‐based motion correction on individual channel images (single‐channel model) with that performed after coil combination (channel‐combined model). We also investigate simultaneous motion correction of all channel data from an image volume (multichannel model). The single‐channel model significantly (p < 0.0001) improved mean absolute error, with an average 50.9% improvement compared with the uncorrected images. This was significantly (p < 0.0001) better than the 36.3% improvement achieved by the channel‐combined model (conventional approach). The multichannel model provided no significant improvement in quantitative measures of image quality compared with the uncorrected images. Results were independent of the presence of pathology, and generalizable to a new center unseen during training. Performing motion correction on single‐channel images prior to coil combination provided an improvement in performance compared with conventional deep‐learning‐based motion correction. Improved deep learning methods for retrospective correction of motion‐affected MR images could reduce the need for repeat scans if applied in a clinical setting. [ABSTRACT FROM AUTHOR]

Histological stains, such as hematoxylin and eosin, tend to fade over time, compromising subsequent analysis accuracy. Traditional methods of restoring stain color in faded samples involve physical re-staining, which is time-consuming and expensive and may damage tissue samples. In addition, digital post-processing techniques, such as color normalization, face limitations when dealing with highly faded slides. To address this, we propose the non-invasive phase-to-color "virtual re-staining" framework. This approach utilizes a trained generative adversarial network with label-free quantitative phase imaging, capturing the intrinsic physiochemical properties of histological samples. It employs multi-channel Fourier ptychographic microscopy to generate pixel-wise paired phase and color images in a high-throughput manner. To streamline data generation, near-infrared illumination is used to mitigate the impact of absorption variations in faded and stained samples, eliminating the need for repetitive data acquisition and potential physical alterations in samples. Our trained network yields comparable or better results to other digitally staining methods, successfully demonstrating the re-staining of approximately decade-old faded slides archived in hospital storage. [ABSTRACT FROM AUTHOR]

Credit card fraud detection is a critical challenge in the financial industry, with substantial economic implications. Conventional machine learning (ML) techniques often fail to adapt to evolving fraud patterns and underperform with imbalanced datasets. This study proposes a hybrid deep learning framework that integrates Generative Adversarial Networks (GANs) with Recurrent Neural Networks (RNNs) to enhance fraud detection capabilities. The GAN component generates realistic synthetic fraudulent transactions, addressing data imbalance and enhancing the training set. The discriminator, implemented using various DL architectures, including Simple RNN, Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRUs), is trained to distinguish between real and synthetic transactions and further fine-tuned to classify transactions as fraudulent or legitimate. Experimental results demonstrate significant improvements over traditional methods, with the GAN-GRU model achieving a sensitivity of 0.992 and specificity of 1.000 on the European credit card dataset. This work highlights the potential of GANs combined with deep learning architectures to provide a more effective and adaptable solution for credit card fraud detection. [ABSTRACT FROM AUTHOR]

The accurate segmentation of cracks in structural materials is crucial for assessing the safety and durability of infrastructure. Although conventional segmentation models based on deep learning techniques have shown impressive detection capabilities in these tasks, their performance can be restricted by small amounts of training data. Data augmentation techniques have been proposed to mitigate the data availability issue; however, these systems often have limitations in texture diversity, scalability over multiple physical structures, and the need for manual annotation. In this paper, a novel generative artificial intelligence (GAI)-driven data augmentation framework is proposed to overcome these limitations by integrating a projected generative adversarial network (ProjectedGAN) and a multi-crack texture transfer generative adversarial network (MCT2GAN). Additionally, a novel metric is proposed to evaluate the quality of the generated data. The proposed method is evaluated using three datasets: the bridge crack library (BCL), DeepCrack, and Volker. From the simulation results, it is confirmed that the segmentation performance can be improved by the proposed method in terms of intersection over union (IoU) and Dice scores across three datasets. [ABSTRACT FROM AUTHOR]

The accurate segmentation of skin lesions plays an important role in the diagnosis and treatment of skin cancers. However, skin lesion areas are rich in details and local features, including the appearance, size, shape, texture, etc., which pose challenges for the accurate localization and segmentation of the target area. Unfortunately, the consecutive pooling and stride convolutional operations in existing convolutional neural network (CNN)-based solutions lead to the loss of some spatial information and thus constrain the accuracy of lesion region segmentation. In addition, using only the traditional loss function in CNN cannot ensure that the model is adequately trained. In this study, a generative adversarial network is proposed, with global and local semantic feature awareness (GLSFA-GAN) for skin lesion segmentation based on adversarial training. Specifically, in the generator, a multi-scale localized feature fusion module and an effective channel-attention module are designed to acquire the multi-scale local detailed information of the skin lesion area. In addition, a global context extraction module in the bottleneck between the encoder and decoder of the generator is used to capture more global semantic features and spatial information about the lesion. After that, we use an adversarial training strategy to make the discriminator discern the generated labels and the segmentation prediction maps, which assists the generator in yielding more accurate segmentation maps. Our proposed model was trained and validated on three public skin lesion challenge datasets involving the ISIC2017, ISIC2018, and HAM10000, and the experimental results confirm that our proposed method provides a superior segmentation performance and outperforms several comparative methods. [ABSTRACT FROM AUTHOR]

In this paper, we skillfully utilize the discriminative ability of the discriminator to construct a conditional generative adversarial network, and propose a scheme that uses few symbols to achieve high accuracy recognition of modulation formats under low signal-to-noise ratio conditions in coherent optical communication. In the one thousand kilometres G.654E optical fiber transmission system, transmission experiments are conducted on the PDM-QPSK/-8PSK/-16QAM/-32QAM/-64QAM modulation format at 8G/16G/32G baud rates, and the signal-to-noise ratio parameters are traversed under experimental conditions. As a key technology in the next-generation elastic optical networks, the modulation format recognition scheme proposed in this paper achieves 100% recognition of the above five modulation formats without distinguishing signal transmission rates. The optical signal-to-noise ratio thresholds required to achieve 100% recognition accuracy are 12.4 dB, 14.3 dB, 15.4 dB, 16.2 dB, and 17.3 dB, respectively. [ABSTRACT FROM AUTHOR]

Generative AI represents a transformative branch of artificial intelligence focused on creating new data, such as images, text, or audio, based on patterns learned from existing data. Unlike traditional AI, which primarily focuses on classification, prediction, or optimization tasks, generative AI models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), aim to simulate creative processes by generating outputs that resemble real-world data. This paper reviews the current state of generative AI technologies, exploring the underlying architectures, including deep learning techniques that power models like GPT and DALL·E. It also examines applications across various fields, such as healthcare, art, entertainment, and natural language processing. Moreover, the ethical considerations surrounding AI-generated content, including issues of bias, authenticity, and misuse, are critically analyzed. By synthesizing current research and advancements, this paper highlights both the opportunities and challenges that generative AI presents for the future of AI development and its societal impact. In recent years, the study of artificial intelligence (AI) has undergone a paradigm shift. This has been propelled by the groundbreaking capabilities of generative models both in supervised and unsupervised learning scenarios. Generative AI has shown state-of-the-art performance in solving perplexing real-world conundrums in fields such as image translation, medical diagnostics, textual imagery fusion, natural language processing, and beyond. This paper documents the systematic review and analysis of recent advancements and techniques in Generative AI with a detailed discussion of their applications including application-specific models. Indeed, the major impact that generative AI has made to date, has been in language generation with the development of large language models, in the field of image translation and several other interdisciplinary applications of generative AI. Moreover, the primary contribution of this paper lies in its coherent synthesis of the latest advancements in these areas, seamlessly weaving together contemporary breakthroughs in the field. Particularly, how it shares an exploration of the future trajectory for generative AI. In conclusion, the paper ends with a dis0ussion of Responsible AI principles, and the necessary ethical considerations for the sustainability and growth of these generative models. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The objectives of this study were to create a mutual conversion system between contrast-enhanced computed tomography (CECT) and non-CECT images using a cycle generative adversarial network (cycleGAN) for the internal jugular region. Image patches were cropped from CT images in 25 patients who underwent both CECT and non-CECT imaging. Using a cycleGAN, synthetic CECT and non-CECT images were generated from original non-CECT and CECT images, respectively. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were calculated. Visual Turing tests were used to determine whether oral and maxillofacial radiologists could tell the difference between synthetic versus original images, and receiver operating characteristic (ROC) analyses were used to assess the radiologists' performances in discriminating lymph nodes from blood vessels. The PSNR of non-CECT images was higher than that of CECT images, while the SSIM was higher in CECT images. The Visual Turing test showed a higher perceptual quality in CECT images. The area under the ROC curve showed almost perfect performances in synthetic as well as original CECT images. In conclusion, synthetic CECT images created by cycleGAN appeared to have the potential to provide effective information in patients who could not receive contrast enhancement. [ABSTRACT FROM AUTHOR]

Additive manufacturing (AM) and topology optimization (TO) emerge as vital processes in modern industries, with broad adoption driven by reduced expenses and the desire for lightweight and complex designs. However, iterative topology optimization can be inefficient and time-consuming for individual products with a large set of parameters. To address this shortcoming, machine learning (ML), primarily neural networks, is considered a viable tool to enhance topology optimization and streamline AM processes. In this work, a machine learning (ML) model that generates a parameterized optimized topology is presented, capable of eliminating the conventional iterative steps of TO, which shortens the development cycle and decreases overall development costs. The ML algorithm used, a conditional generative adversarial network (cGAN) known as Pix2Pix-GAN, is adopted to train using a variety of training data pairs consisting of color-coded images and is applied to an example of cantilever optimization, significantly enhancing model accuracy and operational efficiency. The analysis of training data numbers in relation to the model's accuracy shows that as data volume increases, the accuracy of the model improves. Various ML models are developed and validated in this study; however, some artefacts are still present in the generated designs. Structures that are free from these artefacts achieve 91% reliability successfully. On the other hand, the images generated with artefacts may still serve as suitable design templates with minimal adjustments. Furthermore, this research also assesses compliance with two manufacturing constraints: the limitations on build space and passive elements (voids). Incorporating manufacturing constraints into model design ensures that the generated designs are not only optimized for performance but also feasible for production. By adhering to these constraints, the models can deliver superior performance in future use while maintaining practicality in real-world applications. [ABSTRACT FROM AUTHOR]