Background Single-cell RNA sequencing (scRNA-seq) is an emerging technology that can assess the function of an individual cell and cell-to-cell variability at the single cell level in an unbiased manner. Dimensionalit...
详细信息
Background Single-cell RNA sequencing (scRNA-seq) is an emerging technology that can assess the function of an individual cell and cell-to-cell variability at the single cell level in an unbiased manner. Dimensionality reduction is an essential first step in downstream analysis of the scRNA-seq data. However, the scRNA-seq data are challenging for traditional methods due to their high dimensional measurements as well as an abundance of dropout events (that is, zero expression measurements). Results To overcome these difficulties, we propose DR-A (Dimensionality Reduction with adversarial variational autoencoder), a data-driven approach to fulfill the task of dimensionality reduction. DR-A leverages a novel adversarial variational autoencoder-based framework, a variant of generative adversarial networks. DR-A is well-suited for unsupervised learning tasks for the scRNA-seq data, where labels for cell types are costly and often impossible to acquire. Compared with existing methods, DR-A is able to provide a more accurate low dimensional representation of the scRNA-seq data. We illustrate this by utilizing DR-A for clustering of scRNA-seq data. Conclusions Our results indicate that DR-A significantly enhances clustering performance over state-of-the-art methods.
Deep generative adversarial networks (GANs) are the emerging technology in drug discovery and biomarker development. In our recent work, we demonstrated a proof-of-concept of implementing deep generative adversarial a...
详细信息
Deep generative adversarial networks (GANs) are the emerging technology in drug discovery and biomarker development. In our recent work, we demonstrated a proof-of-concept of implementing deep generative adversarial autoencoder (AAE) to identify new molecular fingerprints with predefined anticancer properties. Another popular generative model is the variational autoencoder (VAE), which is based on deep neural architectures. In this work, we developed an advanced AAE model for molecular feature extraction problems, and demonstrated its advantages compared to VAE in terms of (a) adjustability in generating molecular fingerprints;(b) capacity of processing very large molecular data sets;and (c) efficiency in unsupervised pretraining for regression model. Our results suggest that the proposed AAE model significantly enhances the capacity and efficiency of development of the new molecules with specific anticancer properties using the deep generative models.
With the vigorous development of mobile Internet technology and the popularization of smart devices, while the amount of multimedia data has exploded, its forms have become more and more diversified. People's dema...
详细信息
With the vigorous development of mobile Internet technology and the popularization of smart devices, while the amount of multimedia data has exploded, its forms have become more and more diversified. People's demand for information is no longer satisfied with single-modal data retrieval, and cross-modal retrieval has become a research hotspot in recent years. Due to the strong feature learning ability of deep learning, cross-modal deep hashing has been extensively studied. However, the similarity of different modalities is difficult to measure directly because of the different distribution and representation of cross-modal. Therefore, it is urgent to eliminate the modal gap and improve retrieval accuracy. Some previous research work has introduced GANs in cross-modal hashing to reduce semantic differences between different modalities. However, most of the existing GAN-based cross-modal hashing methods have some issues such as network training is unstable and gradient disappears, which affect the elimination of modal differences. To solve this issue, this paper proposed a novel Semantic-guided autoencoderadversarial Hashing method for cross-modal retrieval (SAAH). First of all, two kinds of adversarial autoencoder networks, under the guidance of semantic multi-labels, maximize the semantic relevance of instances and maintain the immutability of cross-modal. Secondly, under the supervision of semantics, the adversarial module guides the feature learning process and maintains the modality relations. In addition, to maintain the inter-modal correlation of all similar pairs, this paper use two types of loss functions to maintain the similarity. To verify the effectiveness of our proposed method, sufficient experiments were conducted on three widely used cross-modal datasets (MIRFLICKR, NUS-WIDE and MS COCO), and compared with several representatives advanced cross-modal retrieval methods, SAAH achieved leading retrieval performance.
The current paper presents an adversarial autoencoding strategy for voxelized point cloud geometry based on the principles of distributed source coding. The encoder characterizes the input voxel blocks with an array o...
详细信息
ISBN:
(纸本)9781665441155
The current paper presents an adversarial autoencoding strategy for voxelized point cloud geometry based on the principles of distributed source coding. The encoder characterizes the input voxel blocks with an array of hash bytes while the decoder combines them with side information blocks in order to reconstruct the original data. The reconstruction process is optimized by classifying the reconstructed block with an adversarial discriminator in order to make the recovered data as close as possible to an original block. Experimental results show that the proposed solution generalizes well while obtaining better coding performance with respect to other state-of-the-art solutions and allowing high flexibility in rate shaping and decoding operations.
Novelty detection is usually defined as the identification of new or abnormal objects (outliers) from the normal ones (inliers), which has wide potential applications including instrument fault, credit card theft warn...
详细信息
Novelty detection is usually defined as the identification of new or abnormal objects (outliers) from the normal ones (inliers), which has wide potential applications including instrument fault, credit card theft warning, and disease diagnosis in the real world. Most of the existing researches focus on the novelty detection for single- modal data, which may fail to provide an accurate and reliable decision because the single-modal data sometimes cannot fully reflect the actual condition of the problem. However, research on the novelty detection from multiple sources is limited. This study developed an end-to-end deep learning architecture of novelty detection for multi-modal data based on adversarial autoencoders (AAE), which requires no input data of the novelty class during the training process. The proposed model consists of three deep networks, which are trained to compete with each other, collaborate to understand the underlying concept in the normal class, and thus classify the testing samples. Among the three networks, two of them work as the novelty detectors, and the other one called the generator will support the two novelty detectors by enhancing the inliers and distorting the outliers. In addition, a pseudo novelty mechanism is developed to expand the groups of adversarial training with the aim to greatly improve the precision and robustness of the whole model. Then the proposed model is employed for the novelty detection based on the multi-modal data that is composed of images, audios, videos, and texts, etc. The experimental results on the PKU FG-XMedia dataset and the MSR-VTT dataset reveal that our proposed method learns the normal class effectively and is superior to the baseline and state-of-the-art methods.
Data-driven anomaly detection continues to be challenging due to the increased complexity of modern cyber physical systems(CPS s) and their temporal *** detection techniques are widely used through VAE-based framework...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
Data-driven anomaly detection continues to be challenging due to the increased complexity of modern cyber physical systems(CPS s) and their temporal *** detection techniques are widely used through VAE-based frameworks and RNN-based deep learning ***,VAE and its variants impose too much constraint on extracted latent code,and RNN's autoregressive essence indicates the shortage of parallelism and long-term *** tackle the above issues,we propose TransAAE(Transformer-augmented adversarial autoencoder),a novel unsupervised approach for multivariate time series anomaly *** use of the adversarial autoencoder(AAE) architecture loosens the regularization of latent code,and self-attention mechanism is utilized to extract temporal *** experiments show an average F1 score over 0.9 on three public datasets,which significantly outperforms among the baselines.
Thanks to the powerful feature learning capabilities of deep learning, some studies have introduced GANs into the cross-modal hashing. However, The GAN-based hashing methods are generally unstable and difficult to tra...
详细信息
ISBN:
(纸本)9781728114859
Thanks to the powerful feature learning capabilities of deep learning, some studies have introduced GANs into the cross-modal hashing. However, The GAN-based hashing methods are generally unstable and difficult to train in the process of adversarial learning. To address this problem, we propose a novel autoencoder Semantic adversarial Hashing for cross-modal retrieval (AESAH). Specifically, under the guidance of semantic multi-label, two types of adversarial autoencoder networks (inter-modality and intra-modality) are adopted to maximize the semantic relevance and maintain the invariance of cross-modal. Under semantic supervised, the adversarial modules guide the feature learning process, thus the modal relationship in both the common feature space and the common hamming space is maintained. Furthermore, in order to preserve the inter-modal correlation of all similar item pairs is higher than those of dissimilar ones, we use an inter-modal invariance triplet loss and a classification prediction loss to maintain *** experiments were carried out on two commonly used cross-modal datasets, compared with several existing cross-modal retrieval methods, AESAH has better retrieval performance.
Nonlinear, non-Gaussian, and dynamic features pose a great challenge for complex fault detection and fault diagnosis (FDD). Focusing on fault detection, independent component analysis (ICA) and adversarial autoencoder...
详细信息
Nonlinear, non-Gaussian, and dynamic features pose a great challenge for complex fault detection and fault diagnosis (FDD). Focusing on fault detection, independent component analysis (ICA) and adversarial autoencoder (AAE) are fused to form a new method for nonlinear non-Gaussian latent variable extraction: ICA-AAE. In addition, a strategy for establishing more accurate fault detection thresholds using tail distribution features is presented. Furthermore, a new class of fault diagnosis frameworks to fully exploit the information obtained from normal samples is developed. Fault data are first re-represented using the established ICA-AAE model. Then, the low-dimensional spatial distribution features with their inherited high-dimensional temporal dependencies are synthesized into image information using an image-based approach, and a spatio-temporal fusion fault diagnosis method is implemented using a convolutional neural network (CNN). Tennessee Eastman (TE) process results show that the proposed methods can achieve more accurate fault detection and diagnosis.
To solve the problem of power imbalance under extreme and normal scenarios in high voltage (HV) and middle voltage (MV) distribution networks with high penetrations of photovoltaic (PV), the paper proposes a distribut...
详细信息
To solve the problem of power imbalance under extreme and normal scenarios in high voltage (HV) and middle voltage (MV) distribution networks with high penetrations of photovoltaic (PV), the paper proposes a distributionally robust optimal allocation method of energy storage system (ESS) for equilibrating resilience and economy. Firstly, due to the strong relation between resilience enhancement and ESS location, the siting-sizing sequential updating method is adopted to site ESS based on the planning resilience indexes. Secondly, to generate normal and extreme PV-load scenarios with continuous labels, an adversarial autoencoder (AAE) combined with transfer learning is improved by introducing the conditional neural network. Based on the improved AAE and clustering techniques, a Kullback-Leibler divergence-based ambiguity set is constructed to characterize the joint probability distribution of PV and load. Thirdly, considering the boundary information interaction of HV-MV distribution networks, a two-stage coordinated distributionally robust optimization model is established to size ESS. In the model, centralized ESS in HV distribution network participates in frequency regulation and peak shaving while distributed ESS in MV distribution network regulates voltage profiles in the four-quadrant mode. For further improving resilience, an operational resilience index as a chance constraint considering extreme scenarios is embedded into the model. Fourthly, the C&CG algorithm is nested into the analytical target cascading method to handle the model. Finally, case studies show that the proposed method can effectively balance resilience enhancement and economic operation.
Effective spectrum management critically depends on the ability to detect anomalies caused by both legal user (LU) violations and illegal user (IU) intrusions. In this study, we introduce TFAM-AAE-U-k, an innovative s...
详细信息
Effective spectrum management critically depends on the ability to detect anomalies caused by both legal user (LU) violations and illegal user (IU) intrusions. In this study, we introduce TFAM-AAE-U-k, an innovative spectrum anomaly detection framework that integrates an adversarial autoencoder (AAE) with a Time Frequency Attention Mechanism (TFAM) and a specialized user discriminator, U-k. This framework first employs the TFAM-AAE to reconstruct spectrum data by exploiting latent, time, and frequency features of the input. The reconstruction error serves as the primary anomaly detection metric. To address the challenges posed by low interference-to- signal ratio (ISR) IUs and camouflaged LUs, U-k is utilized to extract fingerprint features vectors from IQ data, establishing class center vectors for each LU. The Mahalanobis distance between these vectors is then calculated as a secondary metric for anomaly detection. Our experimental results demonstrate that TFAM-AAE-U-k consistently achieves excellent detection performance, particularly in scenarios involving challenging and hard-to-detect anomalies.
暂无评论