Vanilla Generative Adversarial Networks Research Articles

Enhancing network intrusion detection performance using generative adversarial networks

Network intrusion detection systems (NIDS) play a pivotal role in safeguarding critical digital infrastructures against cyber threats. Machine learning-based detection models applied in NIDS are prevalent today. However, the effectiveness of these machine learning-based models is often limited by the evolving and sophisticated nature of intrusion techniques as well as the lack of diverse and updated training samples. In this research, a novel approach for enhancing the performance of an NIDS through the integration of Generative Adversarial Networks (GANs) is proposed. By harnessing the power of GANs in generating synthetic network traffic data that closely mimics real-world network behavior, we address a key challenge associated with NIDS training datasets, which is the data scarcity. Three distinct GAN models (Vanilla GAN, Wasserstein GAN and Conditional Tabular GAN) are implemented in this work to generate authentic network traffic patterns specifically tailored to represent the anomalous activity. We demonstrate how this synthetic data resampling technique can significantly improve the performance of the NIDS model for detecting such activity. By conducting comprehensive experiments using the CIC-IDS2017 benchmark dataset, augmented with GAN-generated data, we offer empirical evidence that shows the effectiveness of our proposed approach. Our findings show that the integration of GANs into NIDS can lead to enhancements in intrusion detection performance for attacks with limited training data, making it a promising avenue for bolstering the cybersecurity posture of organizations in an increasingly interconnected and vulnerable digital landscape.

Advancements and Applications of Generative Adversarial Networks: A Comprehensive Review

Abstracts: Our paper offers a comprehensive exploration of Generative Adversarial Networks (GANs), tracing their evolution from Ian Goodfellow's seminal work to their current state-of-the-art status. Delving into the intricacies of GAN architecture and training dynamics, we illuminate their pivotal role in diverse applications such as image synthesis, style transfer, and text-toimage conversion. Through an exhaustive literature review, we dissect the progression of GAN architectures, from Vanilla GANs [1] to advanced variants like Progressive GANs [7] and StyleGANs [8], highlighting their techniques, contributions, and performance across benchmark datasets. Moreover, we confront challenges such as training instability and mode collapse, while also presenting a meticulously curated repository of contemporary generative model advancements. This repository encapsulates the cutting edge of GAN research, showcasing innovative approaches across domains ranging from financial forecasting to image restoration. Despite hurdles and ethical considerations, GANs persist as the vanguard of generative modeling, propelling forward the frontiers of artificial intelligence and creative synthesis.

Orthogonal Subspace Representation for Generative Adversarial Networks.

Disentanglement learning aims to separate explanatory factors of variation so that different attributes of the data can be well characterized and isolated, which promotes efficient inference for downstream tasks. Mainstream disentanglement approaches based on generative adversarial networks (GANs) learn interpretable data representation. However, most typical GAN-based works lack the discussion of the latent subspace, causing insufficient consideration of the variation of independent factors. Although some recent research analyzes the latent space on pretrained GANs for image editing, they do not emphasize learning representation directly from the subspace perspective. Appropriate subspace properties could facilitate corresponding feature representation learning to satisfy the independent variation requirements of the obtained explanatory factors, which is crucial for better disentanglement. In this work, we propose a unified framework for ensuring disentanglement, which fully investigates latent subspace learning (SL) in GAN. The novel GAN-based architecture explores orthogonal subspace representation (OSR) on vanilla GAN, named OSRGAN. To guide a subspace with strong correlation, less redundancy, and robust distinguishability, our OSR includes three stages, self-latent-aware, orthogonal subspace-aware, and structure representation-aware, respectively. First, the self-latent-aware stage promotes the latent subspace strongly correlated with the data space to discover interpretable factors, but with poor independence of variation. Second, the following orthogonal subspace-aware stage adaptively learns some 1-D linear subspace spanned by a set of orthogonal bases in the latent space. There is less redundancy between them, expressing the corresponding independence. Third, the structure representation-aware stage aligns the projection on the orthogonal subspace and the latent variables. Accordingly, feature representation in each linear subspace can be distinguishable, enhancing the independent expression of interpretable factors. In addition, we design an alternating optimization step, achieving a tradeoff training of OSRGAN on different properties. Despite it strictly constrains orthogonality, the loss weight coefficient of distinguishability induced by orthogonality could be adjusted and balanced with correlation constraint. To elucidate, this tradeoff training prevents our OSRGAN from overemphasizing any property and damaging the expressiveness of the feature representation. It takes into account both interpretable factors and their independent variation characteristics. Meanwhile, alternating optimization could keep the cost and efficiency of forward inference unchanged and will not burden the computational complexity. In theory, we clarify the significance of OSR, which brings better independence of factors, along with interpretability as correlation could converge to a high range faster. Moreover, through the convergence behavior analysis, including the objective functions under different constraints and the evaluation curve with iterations, our model demonstrates enhanced stability and definitely converges toward a higher peak for disentanglement. To depict the performance in downstream tasks, we compared the state-of-the-art GAN-based and even VAE-based approaches on different datasets. Our OSRGAN achieves higher disentanglement scores on FactorVAE, SAP, MIG, and VP metrics. All the experimental results illustrate that our novel GAN-based framework has considerable advantages on disentanglement.

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

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

Threshold-guided multi-objective Generative Adversarial Networks for constructing artificial yet representative driving cycles

A Driving Cycle (DC) is a speed-time series that represents how people drive in a region. It is used to assess the vehicle’s energy and environmental performance. Constructing representative DCs has been widely studied with well-known methods. However, challenges remain regarding the reproducibility of results and the need for a large set of sampled trips, which can be costly and time-consuming. This work presents a novel approach to constructing DCs using Generative Adversarial Networks (GANs). A multi-objective training approach incorporates model-based losses represented by discriminators to capture time-series trends of speed, acceleration, and jerk, and function-based losses to ensure that the generator respects physical constraints. These losses are activated sequentially according to a convergence measure that utilizes the Characteristic Parameters (CPs) of the generated DCs for the latest activated loss. A new loss is activated if the convergence measure is lower than a threshold. An early stopping mechanism can be triggered when the threshold condition is met at the last loss. The DC generator was validated comparing the artificial trips with real trips from four cities. This comparison involved computing the Relative Difference (RD) between the CPs. The results indicate that the approach can achieve less than a 10% RD, thus providing superior results than a classical approach, a vanilla GAN, and other variations. Additionally, the threshold-based loss activation led to a reduction in training time. Transfer Learning (TL) was employed to construct DCs for other regions. This approach reduces the need for extensive data collection and ensures the reproducibility of artificial DCs.

On the convergence acceleration of vanilla Generative Adversarial Network

Generative Adversarial Network (GAN) is very successful and widely used in both academic and industrial fields. It is inspired by game theory where two models, a generator and a critic, compete with each other, learn from each other, and make each other stronger and stronger. Most improvements focused on stability and there are already many different models such as deep convolutional GAN (DCGAN) and Wassertein GAN (WGAN) that have succeeded. But the speed of the convergence during training process is also an essential ability that needs to be enhanced. In this paper, a decreasing noise is added to the MNIST data and these new data are delivered to the discriminator of the vanilla GAN to accelerate the training process. The result shows that this change could accelerate the convergence and not affect the results’ quality a lot. And this improvement should be general enough to apply to the other models.

Understanding the mathematical background of Generative Adversarial Networks (GANs)

Generative Adversarial Networks (GANs) have gained widespread attention since their introduction, leading to numerous extensions and applications of the original GAN idea. A thorough understanding of GANs' mathematical foundations is necessary to use and build upon these techniques. However, most studies on GANs are presented from a computer science or engineering perspective, which can be challenging for beginners to understand fully. Therefore, this paper aims to provide an overview of the mathematical background of GANs, including detailed proofs of optimal solutions for vanilla GANs and boundaries for $f$-GANs that minimize a variational approximation of the $f$-divergence between two distributions. These contributions will enhance the understanding of GANs for those with a mathematical background and pave the way for future research.

Generative Adversarial Network (GAN)-Based Autonomous Penetration Testing for Web Applications.

The web application market has shown rapid growth in recent years. The expansion of Wireless Sensor Networks (WSNs) and the Internet of Things (IoT) has created new web-based communication and sensing frameworks. Current security research utilizes source code analysis and manual exploitation of web applications, to identify security vulnerabilities, such as Cross-Site Scripting (XSS) and SQL Injection, in these emerging fields. The attack samples generated as part of web application penetration testing on sensor networks can be easily blocked, using Web Application Firewalls (WAFs). In this research work, we propose an autonomous penetration testing framework that utilizes Generative Adversarial Networks (GANs). We overcome the limitations of vanilla GANs by using conditional sequence generation. This technique helps in identifying key features for XSS attacks. We trained a generative model based on attack labels and attack features. The attack features were identified using semantic tokenization, and the attack payloads were generated using conditional sequence GAN. The generated attack samples can be used to target web applications protected by WAFs in an automated manner. This model scales well on a large-scale web application platform, and it saves the significant effort invested in manual penetration testing.

Multichannel One-Dimensional Data Augmentation with Generative Adversarial Network.

Data augmentation is one of the most important problems in deep learning. There have been many algorithms proposed to solve this problem, such as simple noise injection, the generative adversarial network (GAN), and diffusion models. However, to the best of our knowledge, these works mainly focused on computer vision-related tasks, and there have not been many proposed works for one-dimensional data. This paper proposes a GAN-based data augmentation for generating multichannel one-dimensional data given single-channel inputs. Our architecture consists of multiple discriminators that adapt deep convolution GAN (DCGAN) and patchGAN to extract the overall pattern of the multichannel generated data while also considering the local information of each channel. We conducted an experiment with website fingerprinting data. The result for the three channels' data augmentation showed that our proposed model obtained FID scores of 0.005,0.017,0.051 for each channel, respectively, compared to 0.458,0.551,0.521 when using the vanilla GAN.

Quality-Aware Self-Training on Differentiable Synthesis of Rare Relational Data

Data scarcity is a very common real-world problem that poses a major challenge to data-driven analytics. Although a lot of data-balancing approaches have been proposed to mitigate this problem, they may drop some useful information or fall into the overfitting problem. Generative Adversarial Network (GAN) based data synthesis methods can alleviate such a problem but lack of quality control over the generated samples. Moreover, the latent associations between the attribute set and the class labels in a relational data cannot be easily captured by a vanilla GAN. In light of this, we introduce an end-to-end self-training scheme (namely, Quality-Aware Self-Training) for rare relational data synthesis, which generates labeled synthetic data via pseudo labeling on GAN-based synthesis. We design a semantic pseudo labeling module to first control the quality of the generated features/samples, then calibrate their semantic labels via a classifier committee consisting of multiple pre-trained shallow classifiers. The high-confident generated samples with calibrated pseudo labels are then fed into a semantic classification network as augmented samples for self-training. We conduct extensive experiments on 20 benchmark datasets of different domains, including 14 industrial datasets. The results show that our method significantly outperforms state-of-the-art methods, including two recent GAN-based data synthesis schemes. Codes are available at https://github.com/yaxinhou/QAST.

GLSTM: A novel approach for prediction of real & synthetic PID diabetes data using GANs and LSTM classification model

Generative Adversarial Network (GAN) is a revolution in modern artificial systems. Deep learning-based Generative adversarial networks generate realistic synthetic tabular data. Synthetic data are used to enhance the size of a relatively small training dataset while ensuring the confidentiality of the original data. In this context, we implemented the GAN framework for generating diabetes data to help the health care professional in more clinical applications. GAN is used to validate the Pima Indian Diabetes (PID) Dataset. Various preprocessing techniques, such as handling missing values, outliers and data imbalance problems, enhance data quality. Some exploratory data analyses, such as heat maps, bar graphs and histograms, are used for data visualisation. We employed hypothesis testing to examine the resemblance between real data and GAN-generated synthetic data. In this study, we proposed a GAN-Long Short-Term Memory (GLSTM) system, in which GAN is used for data augmentation, and LSTM is used for diabetes classification. Additionally, various GAN models such as CTGAN, Vanilla GAN, Coupula GAN, Gaussian Coupula GAN, and TVAE GAN are used to generate the synthetic dataset. Experiments were conducted on real data, synthetic data, and by combining real and synthetic data. The model that used both real and synthetic data obtained a substantially better accuracy of 97% compared to 92% when only real data was used. We also observed that synthetic data could be used in place of real data, as the mean correlation between synthetic and real data is 0.93. Our study's findings outperformed when compared to state-of-the-art methodologies.

Towards Generating Realistic Wrist Pulse Signals Using Enhanced One Dimensional Wasserstein GAN.

For the past several years, there has been an increasing focus on deep learning methods applied into computational pulse diagnosis. However, one factor restraining its development lies in the small wrist pulse dataset, due to privacy risks or lengthy experiments cost. In this study, for the first time, we address the challenging by presenting a novel one-dimension generative adversarial networks (GAN) for generating wrist pulse signals, which manages to learn a mapping strategy from a random noise space to the original wrist pulse data distribution automatically. Concretely, Wasserstein GAN with gradient penalty (WGAN-GP) is employed to alleviate the mode collapse problem of vanilla GANs, which could be able to further enhance the performance of the generated pulse data. We compared our proposed model performance with several typical GAN models, including vanilla GAN, deep convolutional GAN (DCGAN) and Wasserstein GAN (WGAN). To verify the feasibility of the proposed algorithm, we trained our model with a dataset of real recorded wrist pulse signals. In conducted experiments, qualitative visual inspection and several quantitative metrics, such as maximum mean deviation (MMD), sliced Wasserstein distance (SWD) and percent root mean square difference (PRD), are examined to measure performance comprehensively. Overall, WGAN-GP achieves the best performance and quantitative results show that the above three metrics can be as low as 0.2325, 0.0112 and 5.8748, respectively. The positive results support that generating wrist pulse data from a small ground truth is possible. Consequently, our proposed WGAN-GP model offers a potential innovative solution to address data scarcity challenge for researchers working with computational pulse diagnosis, which are expected to improve the performance of pulse diagnosis algorithms in the future.

Systematic Evaluation of Synthetic Panel Data Quality with an Application to Chronic Lymphocytic Leukemia

OBJECTIVES The dynamic and evolving clinical trial landscape, with its nascent incorporation of real-world data, has the potential to transform healthcare. With these exciting developments come challenges in protecting patient privacy, while retaining data information and encouraging transparency and reproducibility of methods. An emerging technology to ameliorate this challenge is synthetic data generation (SDG). The promises of SDG are to provide realistic, representative, and sharable data that retains all the potential learning of the original (parent) data. We demonstrate a flexible framework for generating and evaluating synthetic data from a challenging clinical use case of chronic lymphocytic leukemia (CLL) patients. We demonstrate the potential to generate a synthetic cohort using real-world data on a cohort of patients treated with chimeric antigen receptor T-cell (CAR T) therapy. Many analytes, and their longitudinal progression, have been shown to predict clinical outcomes in CLL. Therefore, when generating synthetic data for this cohort, it is essential to preserve these longitudinal analyte 'fingerprints’ associated with other clinical information to capture latent disease progression adequately. METHODS We used Generative Adversarial Networks (GANs), a type of unsupervised deep learning algorithm, to generate synthetic CLL patients and their latent disease progression over time. 389 Patients were identified within a large tertiary healthcare system (providing care to approximately 5mil patients) by ICD9/10 codes who could provide longitudinal values for the synthetic cohort. We simulated synthetic patient data using EMR (Electronic Medical Record) data, including laboratory test values, patient-reported health state utility values (HSUVs), and other baseline characteristics. RESULTS Clinical attributes showed a strong relation between analyte trajectories and outcomes. Synthetic data was indistinguishable from original data in both statistical tests and in performance in machine learning algorithms to predict disease progression and worsening outcomes. Wasserstein Conditional GAN outperformed vanilla GAN, conditional GAN, and Wasserstein GAN. Synthetic patient data generated by GAN accurately reflect the means, standard deviations, and correlations of each variable over time to the extent that synthetic data cannot be distinguished from actual data by a logistic regression. Moreover, our unsupervised model predicts changes in total HSUVs with the same accuracy as specifically trained supervised models, additionally capturing the correlation structure of the covariates. LIMITATIONS and CONCLUSIONS Many synthetic data-generative methods emphasize retention of relationship among data elements and may preclude certain data anomalies. The real-world data may retain properties associated with the experiment or data generation process and carry them over into the synthetic cohort. The ideal synthetic cohort would support any statistical discovery possible in, and be verifiable against, the parent dataset - while reducing probability of patient identification to zero. This application of statistical tests to evaluate deep learning algorithms provides a novel perspective on synthetic data generation and poses the bases for the establishment of best practices for synthetic data quality assessment.

Real-time high quality font generation with Conditional Font GAN

Designing and generating novels fonts manually is a laborious and time-consuming process owing to the large number and complexity of characters in the majority of language systems. Recent advancements in generative adversarial networks (GANs) have significantly improved font generation. These GAN-based approaches either handle the font generation as a vanilla GAN problem (that is, by synthesizing characters from a uniform latent vector) or an image-to-image translation problem. While the former approach has no limitation in generating diverse font styles, the generated fonts contain artifacts and can operate only on low-resolution images, thus impairing their usability. The latter approach generates high-quality font images for previously observed fonts, but the quality degrades during the inference phase while designing novel fonts. Furthermore, additional fine-tuning steps are required to achieve photorealistic results, which is computationally expensive and time-consuming. To address the shortcomings of these approaches, we propose a font generation method that employs the vanilla GAN approach to generate an infinite number of font styles but focuses on the real-time generation of photo-realistic font images. Additionally, we strive to create high-resolution images that can be used in practical applications. To accomplish this, we propose a conditional font GAN (CFGAN) with a sophisticated network architecture that is designed to generate novel style-consistent diverse font character sets. We control the generated characters in the proposed network using a non-trainable fixed character vector, while the style variation sampled from a Gaussian distribution is fused at all blocks of the generator through adaptive instance normalization (AdaIN) operation. Thus, the generator architecture can simultaneously generate an infinite number of font styles with style consistency and diversity during inference. We conducted various quantitative and qualitative experiments to demonstrate the effectiveness of the proposed model in terms of both image quality and computational cost.

Generating images for Supervised Hyperspectral Image Classification with Generative Adversarial Nets

With the advancement of remote sensing technologies, hyperspectral imagery has garnered significant interest in the remote sensing community. These developments have inspired improvement in various hyperspectral images (HSI) classification applications, such as land cover mapping, amongst other earth observation applications. Deep Neural Networks have revolutionized image classification tasks in areas of computer vision. However, in the domain of hyperspectral images, insufficient training samples have been earmarked as a significant bottleneck for supervised HSI classification. Moreover, acquiring HSI from satellites and other remote sensors is expensive. Thus, researchers have turned to generative models to leverage the existing data to increase training samples, such as particularly generative adversarial networks (GAN). This paper explores the use of a vanilla GAN to generate synthetic data. The network employed in this paper was built using a deep learning python package, PyTorch and tested on a popular HSI dataset called Indian Pines dataset. The network achieved an overall accuracy of 64%. While promising, there is still room for improvement.

BrainGAN: Brain MRI Image Generation and Classification Framework Using GAN Architectures and CNN Models.

Deep learning models have been used in several domains, however, adjusting is still required to be applied in sensitive areas such as medical imaging. As the use of technology in the medical domain is needed because of the time limit, the level of accuracy assures trustworthiness. Because of privacy concerns, machine learning applications in the medical field are unable to use medical data. For example, the lack of brain MRI images makes it difficult to classify brain tumors using image-based classification. The solution to this challenge was achieved through the application of Generative Adversarial Network (GAN)-based augmentation techniques. Deep Convolutional GAN (DCGAN) and Vanilla GAN are two examples of GAN architectures used for image generation. In this paper, a framework, denoted as BrainGAN, for generating and classifying brain MRI images using GAN architectures and deep learning models was proposed. Consequently, this study proposed an automatic way to check that generated images are satisfactory. It uses three models: CNN, MobileNetV2, and ResNet152V2. Training the deep transfer models with images made by Vanilla GAN and DCGAN, and then evaluating their performance on a test set composed of real brain MRI images. From the results of the experiment, it was found that the ResNet152V2 model outperformed the other two models. The ResNet152V2 achieved 99.09% accuracy, 99.12% precision, 99.08% recall, 99.51% area under the curve (AUC), and 0.196 loss based on the brain MRI images generated by DCGAN architecture.

VGAN: Generalizing MSE GAN and WGAN-GP for Robot Fault Diagnosis

Generative adversarial networks (GANs) have shown their potential for data generation. However, this type of generative model often suffers from oscillating training processes and mode collapse, among other issues. To mitigate these, this work proposes a generalization of both mean square error (mse) GAN and Wasserstein GAN (WGAN) with gradient penalty, referred to as VGAN. Within the framework of conditional WGAN with gradient penalty, VGAN resorts to the Vapnik V-matrix-based criterion that generalizes mse. Also, a novel early stopping-like strategy is proposed that keeps track during training of the most suitable model. A comprehensive set of experiments on a fault-diagnosis task for an industrial robot where the generative model is used as a data augmentation tool for dealing with imbalance datasets is presented. The statistical analysis of the results shows that the proposed model outperforms nine other models, including vanilla GAN, conditional WGAN with and without conventional regularization, and synthetic minority oversampling technique, a classic data augmentation technique.

Lung cancer classification using exponential mean saturation linear unit activation function in various generative adversarial network models

AbstractNowadays, the mortality rate due to lung cancer increases rapidly worldwide as it can be classified only at the later stages. Early classification of lung cancer will help patients to take treatment and decrease the death rate. The limited dataset and diversity of data samples are the bottlenecks for early classification. In this paper, robust deep learning generative adversarial network (GAN) models are employed to enhance the dataset and to increase classification accuracy. The activation function plays an important feature‐learning role in neural networks. Since the existing activation functions suffer from various drawbacks such as vanishing gradient, dead neurons, output offset, etc., this paper proposes a novel activation function exponential mean saturation linear unit (EMSLU), which aims to speed up training, reduce network running time, and improve classification accuracy. The experiments were conducted using vanilla GAN, Wasserstein generative adversarial network, Wasserstein generative adversarial network with gradient penalty, conditional generative adversarial network, and deep convolutional generative adversarial network. Each GAN is tested with rectified linear unit, exponential linear unit, and proposed EMSLU activation functions. The results show that all the GAN's with EMSLU yields improved precision, recall, F1‐score, and accuracy.

Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.

Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies that deliver software services in order to monitor the networks and identify faults and respective solutions. A common barrier faced by these specialized companies is the lack of data to develop and test their products. This paper investigates the use of generative adversarial networks (GANs), which are state-of-the-art generative models, for generating synthetic telecommunication data related to Wi-Fi signal quality. We developed, trained, and compared two of the most used GAN architectures: the Vanilla GAN and the Wasserstein GAN (WGAN). Both models presented satisfactory results and were able to generate synthetic data similar to the real ones. In particular, the distribution of the synthetic data overlaps the distribution of the real data for all of the considered features. Moreover, the considered generative models can reproduce the same associations observed for the synthetic features. We chose the WGAN as the final model, but both models are suitable for addressing the problem at hand.

Enabling non-intrusive occupant activity modeling using WiFi signals and a generative adversarial network

Occupant activity (OA) is a crucial prerequisite for providing energy-efficient and occupant-centric services in intelligent buildings. To understand OAs well, conventional technologies require either wearable equipment of smart devices or the deployment of specialized cameras, raising relevant issues of body and privacy-intrusion. Recent WiFi-based methods circumvent the above issues and characterize the OA patterns in a non-intrusive manner. However, they demand the cooperation of occupants for a sufficient amount of collected samples, otherwise, the performance might degrade significantly. In this paper, we propose a non-intrusive approach that models distinct OA patterns for comprehensive understanding. Based on the idea of generative adversarial network (GAN), our technical novelties are three-fold. First, we modify the working principle of vanilla GAN with external constraints to avoid brute-force generation. Second, we integrate a self-attention mechanism to establish contextual relations from both local and global perspectives. Third, to recover the informative details, we construct a powerful generator with deep residual convolutional operations. We conduct extensive experiments on a real dataset and visualize the generation results for intuitive evaluation. Numerical results compared with several state-of-the-art baselines further illustrate the superior performance of our proposed GAN approach.