Generative Adversarial Network Method Research Articles

Short-Term Probabilistic Wind Speed Predictions Integrating Multivariate Linear Regression and Generative Adversarial Network Methods

The precise forecasting of wind speeds is critical to lessen the harmful impacts of wind fluctuations on power networks and aid in merging wind energy into the grid system. However, prior research has predominantly focused on point forecasts, often overlooking the uncertainties inherent in the prediction accuracy. For this research, we suggest a new approach for forecasting wind speed intervals (PI). Specifically, the actual wind speed series are initially procured, and the complete ensemble empirical mode decomposition coupled with adaptive noise (CEEMDAN) method decomposes the actual wind speed series into constituent numerous mode functions. Furthermore, a generative adversarial network (GAN) is utilized to achieve the wind speed PI in conjunction with the multivariate linear regression method. To confirm the effectiveness of the suggested model, four datasets are selected. The validation results suggest that this suggested model attains a superior PI accuracy compared with those of numerous benchmark techniques. In the context of PI of dataset 4, the PINAW values show improvements of 68.06% and 32.35% over the CEEMDAN-CNN and VMD-GRU values in single-step forecasting, respectively. In conclusion, the proposed model excels over the counterpart models by exhibiting diminished a PINAW and CWC, while maintaining a similar PICP.

Optimization of a thermal energy storage system enhanced with fins using generative adversarial networks method

Optimizing fin configurations is an effective method to improve the performance of a thermal energy storage system. The present research aims to determine the optimal fin spacing and inclination angle to minimize the melting process of a phase change material (PCM) in a rectangular enclosure, which is exposed to a constant temperate finned wall while other walls are adiabatic. Oleic acid (OA) is used as a PCM with a melting temperature of 287–288 K. Computational fluid dynamics (CFD) simulations are employed to comprehensively investigate the thermal behavior of the system by solving continuity, momentum, and energy equations simultaneously. Initially, fifteen different datasets are simulated using CFD methods to explore various fin configurations. After that, fifteen additional datasets are generated to verify the reliability of the generative adversarial networks (GANs) method, which supplements the CFD approach. An ensemble learning approach is implemented to create a hybrid dataset consisting of thirty datasets, and then the optimum dataset is determined. To validate this approach, a single numerical simulation is conducted at the optimum dataset, and the obtained optimum value, minimum melting time of PCM, is compared with the result obtained from CFD simulation. It is identified as the optimal fin configuration, resulting in a fin spacing of 15.75 mm and an inclination angle of −11.6°, highlights the efficacy of the combined CFD and GANs approach. The melting time captured from the numerical simulation and the one produced with GANs differed by about 4.7 %. The current study concludes that the GANs method might be effectively worthwhile in many energy storage applications.

Analysis of the Effectiveness of Generative Adversarial Technology in Intelligent Buildings in terms of Design

Abstract This paper combines the training method of generative adversarial network and the robust row layout design method of building based on CGAN, and selects pix2pix model to carry out the spatial layout design of intelligent building, to explore the actual effect of intelligent building design. Using the building layout design of a generative adversarial network, different parameters and residual block numbers are set to compare the impact of building texture generation. The intelligent building using GAN technology is selected to carry out the spatial design characterization of both Light and shadow and luminance, and the SD spatial environment evaluation factor is used to refine the discussion of the spatial design experience of intelligent buildings designed using generative adversarial technology. The Light and shadow distribution of intelligent building design is mainly presented as four types, in which the light and shadow location types of reading room, hall, rest space and exhibition hall are primarily offered as horizontal division types. In a public intelligent building, the rest area is separated into 25% of the distance and 25% of the vertical division, with an improved design balance.

Learning bilingual word embedding for automatic text summarization in low resource language

Studies in low-resource languages have become more challenging with the increasing volume of texts in today's digital era. Also, the lack of labeled data and text processing libraries in a language further widens the research gap between high and low-resource languages, such as English and Indonesian. This has led to the use of a transfer learning approach, which applies pre-trained models to solve similar problems, even in different languages by using bilingual or cross-lingual word embedding. Therefore, this study aims to investigate two bilingual word embedding methods, namely VecMap and BiVec, for Indonesian – English language and evaluates them for bilingual lexicon induction and text summarization tasks. The generated bilingual embedding was compared with MUSE (Multilingual Unsupervised and Supervised Embeddings) as the existing multilingual word created with the generative adversarial network method. Furthermore, the VecMap was improved by creating shared vocabulary spaces and mapping the unshared ones between languages. The result showed the embedding produced by the joint methods of BiVec, performed better in intrinsic evaluation, especially with CSLS (Cross-Domain Similarity Local Scaling) retrieval. Meanwhile, the improved VecMap outperformed the regular type by 16.6% without surpassing the BiVec evaluation score. These methods enabled model transfer between languages when applied to cross-lingual-based text summarization. Moreover, the ROUGE score outperformed classical text summarization by adding only 10% of the training dataset of the target language.

Adversarial Patch Attacks on Deep-Learning-Based Face Recognition Systems Using Generative Adversarial Networks.

Deep learning technology has developed rapidly in recent years and has been successfully applied in many fields, including face recognition. Face recognition is used in many scenarios nowadays, including security control systems, access control management, health and safety management, employee attendance monitoring, automatic border control, and face scan payment. However, deep learning models are vulnerable to adversarial attacks conducted by perturbing probe images to generate adversarial examples, or using adversarial patches to generate well-designed perturbations in specific regions of the image. Most previous studies on adversarial attacks assume that the attacker hacks into the system and knows the architecture and parameters behind the deep learning model. In other words, the attacked model is a white box. However, this scenario is unrepresentative of most real-world adversarial attacks. Consequently, the present study assumes the face recognition system to be a black box, over which the attacker has no control. A Generative Adversarial Network method is proposed for generating adversarial patches to carry out dodging and impersonation attacks on the targeted face recognition system. The experimental results show that the proposed method yields a higher attack success rate than previous works.

Motion artifact correction in fetal MRI based on a Generative Adversarial network method

Fetal MR imaging is subject to artifacts, where the most common type is caused by motion. These artifacts can appear as blurring and/or ghosting in the affected sequences. Currently if the motion artifact is severe or covers essential fetal tissue, the sequence acquisition must be repeated for diagnostic decision-making. We propose a novel deep learning network to reduce and remove motion artifacts in fetal MRIs. It follows a Generative Adversarial Network (GAN) framework where the Generator consists of an Autoencoder structure containing Residual blocks with Squeeze and Excitation (SE), and the Discriminator uses a sequential Convolutional Neural Network (CNN) design. The loss function is composed of weighted subcomponents involving WGAN, L1, and perceptual losses. The proposed network was trained on a synthetically created motion artifact dataset, and further validated on real motion-degraded images. The creation of the synthetic dataset consisted of randomly modifying the k-space of each scan. On the synthetic dataset, the proposed network achieved an average SSIM and PSNR of 93.7 % and 33.5 dB respectively. For the real motion affected dataset, the proposed network attained an average BRISQUE score of 21.1. These results outperformed current state-of-the-art techniques including BM3D, RED-Net, NLM filtering, and WGAN-VGG. The presented network facilitates rapid and accurate post-processing for fetal MRI. It can also improve diagnostic accuracy and can save time and money by reducing the number of rescans caused by severe motion artifacts.

Makeup transfer: A review

AbstractMakeup transfer (MT) aims to transfer the makeup style from a given reference makeup face image to a source image while preserving face identity and background information. In recent years, MT has attracted the attention of many scholars, and it has a wide range of application prospects and research value. Since then, many methods have been proposed to accomplish MT, most of which are based on Generative Adversarial Network methods. A taxonomy of existing algorithms in the field of MT is first proposed. Then, evaluation methods are proposed, existing methods are analysed, and existing datasets are introduced. This paper finally discusses the current problems in the field of MT and the trend of future research.

Gesture Recognition using Conditional Generative Adversarial Networks

Sign language is very useful for giving signs to communication partners, in this case, signs are not only for people with disabilities but can also be used by normal people. Even in children's or adult games, sign language is used as a language or a means of communication with one another. Recognition of sign language using a computer by doing several methods, because the computer does not recognize the image of a sign with a certain meaning. Therefore, it is necessary to train computers to recognize these signs. One of the fields that discusses gesture image recognition is the field of Computer Vision. Where the science of computer vision is able to process the image. In addition, in image processing, it is necessary to carry out deep learning processes such as Convolutional Neural Networks. In the Convolutional Neural Network algorithm, there are also many methods or architectures such as VGG16, VGG19, ResNet-50, DenseNet, Inception_V3, and many more. The use of architecture is used in accordance with existing needs. Therefore, the choice of architecture will determine the model is built or not to build from scratch, only transfer learning or pre-train. Pre-training is done by using the initial model and then using it only. Or do some training. The purpose of this study was to detect sign language using the Generative Adversarial Network (GAN). Actually, the Generative Adversarial Network method is widely used in making synthetic images, but this time the Generative Adversarial Network can also detect images from sign language.

Generative Adversarial Networks for Unmanned Aerial Vehicle Object Detection with Fusion Technology

Unmanned aerial vehicles (UAVs) also called as a drone comprises of a controller from the base station along with a communications system with the UAV. The UAV plane can be precisely controlled by a machine operator, similar to remotely directed aircraft, or with increasing grades of autonomy, as like autopilot assistance, up to completely self-directed aircraft that require no human input. Obstacle detection and avoidance is important for UAVs, particularly lightweight micro aerial vehicles, but it is a difficult problem to solve because pay load restrictions limit the number of sensors that can be mounted onto the vehicle. Lidar uses Laser for finding the distance between objects and vehicle. The speed and direction of the moving objects are detected and tracked with the help of radar. When many sensors are deployed, both thermal and electro-optro cameras have great clustering capabilities as well as accurate localization and ranging. The purpose of the proposed architecture is to create a fusion system that is cost-effective, lightweight, modular, and robust as well. Also, for tiny object detection, we recommend a novel Perceptual Generative Adversarial Network method that bridges the representation gap between small and large objects. It employs the Generative Adversarial Networks (GAN) algorithm, which iimproves object detection accuracy above benchmark models at the same time maintaining real-time efficiency in an embedded computer for UAVs. Its generator, in particular, learns to turn unsatisfactory tiny object representations into super-resolved items that are similar to large objects to deceive a rival discriminator. At the same time, its discriminator contests with the generator to classify the engendered representation, imposing a perceptual restriction on the generator: created representations of tiny objects must be helpful for detection. With three different obstacles, we were able to successfully identify and determine the magnitude of the barriers in the first trial. The accuracy of proposed models is 83.65% and recall is 81% which is higher than the existing models.

A Three-Dimensional Microstructure Reconstruction Framework for Permeable Pavement Analysis Based on 3D-IWGAN with Enhanced Gradient Penalty.

Owing to the increasing use of permeable pavement, there is a growing need for studies that can improve its design and durability. One of the most important factors that can reduce the functionality of permeable pavement is the clogging issue. Field experiments for investigating the clogging potential are relatively expensive owing to the high-cost testing equipment and materials. Moreover, a lot of time is required for conducting real physical experiments to obtain physical properties for permeable pavement. In this paper, to overcome these limitations, we propose a three-dimensional microstructure reconstruction framework based on 3D-IDWGAN with an enhanced gradient penalty, which is an image-based computational system for clogging analysis in permeable pavement. Our proposed system first takes a two-dimensional image as an input and extracts latent features from the 2D image. Then, it generates a 3D microstructure image through the generative adversarial network part of our model with the enhanced gradient penalty. For checking the effectiveness of our system, we utilize the reconstructed 3D image combined with the numerical method for pavement microstructure analysis. Our results show improvements in the three-dimensional image generation of the microstructure, compared with other generative adversarial network methods, and the values of physical properties extracted from our model are similar to those obtained via real pavement samples.

Influence of Training Times and Sample Size on Results in Visual Try-On with GAN

With online shopping becoming more and more trendy these days, Virtual Try-On Approach is proposed. It is a method of Generative Adversarial Network (GAN) composes of two models: Geometry Matching Module (GMM) and Try-On Module (TOM). It is proposed to solve the inconvenience of customers for not being able to see the fitting effect before receiving the goods. This paper is about finding the relationship between dataset and the effect of the experiment in the GAN experiment. After implementing the models and gaining the result images, we do some observations on the GMM one and try to analyze it and improve the effect. Comparison is made on different aspects: training times of the model and sample size of the training input. Similar trends are shown on the decrease of loss value when the training times or sample size rises. However, the visual effect is not necessarily improved all the time. Compared with the times it has been trained, the improvement from training times is far less than that from the sample size. Finally, we draw the conclusion that the effect is gradually improved as the training times or sample size increases at the beginning. Nevertheless, the improvement cannot be recognized evidently when the training times and sample size have grown large enough. Additionally, the sample size seems to be a more significant factor in the improvement of the visual effect than the training times.

Normalization of multicenter CT radiomics by a generative adversarial network method

To reduce the variability of radiomics features caused by computed tomography (CT) imaging protocols through using a generative adversarial network (GAN) method. In this study, we defined a set of images acquired with a certain imaging protocol as a domain, and a total of four domains (A, B, C, and T [target]) from three different scanners was included. In data set#1, 60 patients for each domain were collected. Data sets#2 and #3 included 40 slices of spleen for each of the domains. In data set#4, the slices of three colorectal cancer groups (n = 28, 38 and 32) were separately retrieved from three different scanners, and each group contained short-term and long-term survivors. Seventy-seven features were extracted for evaluation by comparing the feature distributions. First, we trained the GAN model on data set#1 to learn how to normalize images from domains A, B and C to T. Next, by comparing feature distributions between normalized images of the different domains, we identified the appropriate model and assessed it, in data set#2 and data set#3, respectively. Finally, to investigate whether our proposed method could facilitate multicenter radiomics analysis, we built the least absolute shrinkage and selection operator classifier to distinguish short-term from long-term survivors based on a certain group in data set#4, and validate it in another two groups, which formed a cross-validation between groups in data set#4. After normalization, the percentage of aligned features between domains A versus T, B versus T, and C versus T increased from 10.4 %, 18.2% and 50.1% to 93.5%, 89.6% and 77.9%, respectively. In the cross-validation results, the average improvement of the area under the receiver operating characteristic curve achieved 11% (3%–32%). Our proposed GAN-based normalization method could reduce the variability of radiomics features caused by different CT imaging protocols and facilitate multicenter radiomics analysis.

A robot calligraphy writing method based on style transferring algorithm and similarity evaluation

This paper proposes a robot calligraphy writing method based on style transfer algorithm, which can transfer the art style of Chinese font and maintain the imitation accuracy of the calligraphy. A prototypical similarity evaluation approach is also presented to analyze the calligraphy writing effect, including the similarity ratio of balance, inclination and writing intensity. The robot writing system mainly consists of a six-DOF robot, manipulator, Chinese brush and PC controller. Firstly, input character images are transformed into target style font through training and style transferring process based on generative adversarial networks method. Then, the description parameters of the character images with target style are extracted to control the robot calligraphy writing process precisely. Experimental results show that the minimum similarity between the styles of robot writing characters and target characters is larger than 0.75. The proposed method shows good calligraphy writing effect, which can be used for various calligraphy training processes and trajectory planning applications.

Dual-Path Adversarial Learning for Fully Convolutional Network (FCN)-Based Medical Image Segmentation

Segmentation of regions of interest (ROIs) in medical images is an important step for image analysis in computer-aided diagnosis systems. In recent years, segmentation methods based on fully convolutional networks (FCNs) have achieved great success in general images. FCN performance is primarily due to it leveraging large labeled datasets to hierarchically learn the features that correspond to the shallow appearance as well as the deep semantics of the images. However, such dependence on large dataset does not translate well into medical images where there is a scarcity of annotated medical training data, and FCN results in coarse ROI detections and poor boundary definitions. To overcome this limitation, medical image-specific FCN methods have been introduced with post-processing techniques to refine the segmentation results; however, the performance of these methods is reliant on the appropriate tuning of a large number of parameters and dependence on data-specific post-processing techniques. In this study, we leverage the state-of-the-art image feature learning method of generative adversarial network (GAN) for its inherent ability to produce consistent and realistic images features by using deep neural networks and adversarial learning concept. We improve upon GAN such that ROI features can be learned at different levels of complexities (simple and complex), in a controlled manner, via our proposed dual-path adversarial learning (DAL). The outputs from our DAL are then augmented to the learned ROI features into the existing FCN training data, which increases the overall feature diversity. We conducted experiments on three public datasets with a variety of visual characteristics. Our results demonstrate that our DAL can improve FCN-based segmentation methods and outperform or be competitive in performances to the state-of-the-art methods without using medical image-specific optimizations.