Reference frame transformation methods are generally introduced in multiphase ac systems, so as to simplify system's high dimensional ac signals into low dimensional dc ones. Classical methods, such as Clark/Park ...
详细信息
Reference frame transformation methods are generally introduced in multiphase ac systems, so as to simplify system's high dimensional ac signals into low dimensional dc ones. Classical methods, such as Clark/Park transformations, are used in balanced systems whose models are known, but not suitable for model-unknown systems which may contain unbalanced components. To address this issue, this article proposes a model-free method, that can downscale both balanced and unbalanced multiphase ac signals into dc ones, without any access to prior model knowledge. The proposed method follows the principles of low rank and sparsity, and consists of two components: 1) a phase-lock orthogonal autoencoder is designed, to transform multiphase ac signals into two-phase orthogonal ac signals;2) a circular harmonic decomposition is introduced, to further simplify two-phase orthogonal ac signals into some dc constant values. The effectiveness of the proposed method is validated on a real-world model-unknown system, and the experimental results also indicate that the proposed method benefits of discovering some potential patterns of the system, which is helpful for an in-depth study of model-unknown systems. Comparative studies show that the proposed method is superior to classical methods in terms of interpretability, information integrity and scalability in model-unknown scenarios.
The efficient management of urban water distribution networks is crucial for public health and urban development. One of the major challenges is the quick and accurate detection of leaks, which can lead to water loss,...
详细信息
The efficient management of urban water distribution networks is crucial for public health and urban development. One of the major challenges is the quick and accurate detection of leaks, which can lead to water loss, infrastructure damage, and environmental hazards. Many existing leak detection methods are ineffective, especially in complex and aging pipeline networks. If these limitations are not overcome, it can result in a chain of infrastructure failures, exacerbating damage, increasing repair costs, and causing water shortages and public health risks. The leak issue is further complicated by increasing urban water demand, climate change, and population growth. Therefore, there is an urgent need for intelligent systems that can overcome the limitations of traditional methodologies and leverage sophisticated data analysis and machine learning technologies. In this study, we propose a reliable and advanced method for detecting leaks in water pipes using a framework based on Long Short-Term Memory (LSTM) networks combined with autoencoders. The framework is designed to manage the temporal dimension of time-series data and is enhanced with ensemble learning techniques, making it sensitive to subtle signals indicating leaks while robustly dealing with noise signals. Through the integration of signal processing and pattern recognition, the machine learning-based model addresses the leak detection problem, providing an intelligent system that enhances environmental protection and resource management. The proposed approach greatly enhances the accuracy and precision of leak detection, making essential contributions in the field and offering promising prospects for the future of sustainable water management strategies.
autoencoders are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the decoder represents the inv...
详细信息
autoencoders are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the decoder represents the inverse map, providing a parametrization of the data manifold by the manifold in latent space. We propose and analyze a novel regularization for learning the encoder component of an autoencoder: a loss functional that prefers isometric, extrinsically flat embeddings and allows to train the encoder on its own. To perform the training, it is assumed that the local Riemannian distance and the local Riemannian average can be evaluated for pairs of nearby points on the input manifold. The loss functional is computed via Monte Carlo integration. Our main theorem identifies a geometric loss functional of the embedding map as the Gamma-limit of the sampling-dependent loss functionals. Numerical tests, using image data that encodes different explicitly given data manifolds, show that smooth manifold embeddings into latent space are obtained. Furthermore, due to the promotion of extrinsic flatness, interpolation between not too distant points on the manifold is well approximated by linear interpolation in latent space.
Skeleton-based human action recognition (HAR) is being utilized in various fields like action classification and abnormal behavior detection. The accurate coordinates of the human joints are a crucial factor for the h...
详细信息
Skeleton-based human action recognition (HAR) is being utilized in various fields like action classification and abnormal behavior detection. The accurate coordinates of the human joints are a crucial factor for the high performance in skeleton-based HAR. However, the missing joints caused by occlusion and invisibility result in performance degradation. Hence, in this paper, a missing joint reconstruction model is proposed to improve the performance of skeleton-based HAR. The proposed model, based on a denoising graph autoencoder (DGAE), regards missing joints as noise corrupted information and aims to reconstruct them to be close to their original coordinates. When the encoder of the proposed model compresses the noised input into a latent vector, a masking Laplacian matrix is introduced to reduce the effect of the missing joints' features. The masking Laplacian matrix adjusts the effect of features between a missing joint and its adjacent joints by altering the weights of an adjacent matrix. In the decoder, a Laplacian matrix, which represents the connections among the joints, is utilized to reconstruct an output from the latent vector. The experiment result shows that the proposed model reconstructs the coordinates of missing joints with a marginal error. In addition, the performance of skeleton-based HAR is enhanced by reconstructing the missing joints.
Rolling bearing is a critical component of machinery that has been widely applied in manufacturing, transportation, aerospace, and power and energy industries. The timely and accurate bearing fault detection thus is o...
详细信息
Rolling bearing is a critical component of machinery that has been widely applied in manufacturing, transportation, aerospace, and power and energy industries. The timely and accurate bearing fault detection thus is of vital importance. Computational data-driven deep learning has recently become a prevailing approach for bearing fault detection. Despite the progress of the deep learning approach, the deep learning performance is hinged upon the size of labeled data, the acquisition of which is expensive in actual implementation. Unlabeled data, on the other hand, are inexpensive. In this research, we develop a new semi-supervised learning method built upon the autoencoder to fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance. Compared with the state-of-the-art semi-supervised learning methods, this proposed method can be more conveniently implemented with fewer hyperparameters to be tuned. In this method, a joint loss is established to account for the effects of labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other well-established baseline methods. Specifically, nearly all emulation runs using the proposed methodology can lead to around 2%-5% accuracy increase, indicating its robustness in performance enhancement.
The popularity of Received Signal Strength (RSS) fingerprint-based indoor localization is mainly due to ubiquitous nature of Wi-Fi signals. However, environment changes, device heterogeneity and change in Access Point...
详细信息
The popularity of Received Signal Strength (RSS) fingerprint-based indoor localization is mainly due to ubiquitous nature of Wi-Fi signals. However, environment changes, device heterogeneity and change in Access Points (APs) results in domain shift between offline and online RSS fingerprints. This article proposes a novel Domain Adversarial Neural Network for Regression (DANN-R) over a compressed RSS representation derived from autoencoders used as a dimension reduction technique to alleviate the challenges of a dynamic IoT environment. In addition, adversarially learn domain-invariant representation in DANN-R using gradient reversal layer (GRL) mitigates these RSS fluctuations by learning a common representation, where source domain (offline RSS data) and target domain (online RSS data) cannot be distinguished. The proposed method outperforms both state-of-art machine learning algorithms and deep domain adaptation frameworks on two public localization testbeds.
The hyperspectral anomaly detection (HAD) aims to identify potential anomalies from complex backgrounds. Most reconstruction-based autoencoders equally treat background pixels and anomalies or ignore potential spatial...
详细信息
The hyperspectral anomaly detection (HAD) aims to identify potential anomalies from complex backgrounds. Most reconstruction-based autoencoders equally treat background pixels and anomalies or ignore potential spatial information. In this letter, we propose an HAD method based on multiscale memory autoencoder and spatial filtering, abbreviated as SFM2AE. Specifically, by introducing memory modules into different hidden layers of the autoencoder, multiscale reconstruction of background and anomaly pixels is achieved in the spectral domain. In addition, morphological filtering in the spatial domain is used to extract spatial structural information from anomalies. Joint spatial-spectral anomaly detection is achieved by combining multiscale memory autoencoder and spatial filtering. Experiments demonstrate superior detection performance of the proposed method over the state-of-the-art methods.
Due to the continuously increasing number of resources and data availability in the cloud, the threats related to the security of computer networks and IT systems are critical. Threat detection systems based on deep n...
详细信息
ISBN:
(纸本)9798331506643;9798331506650
Due to the continuously increasing number of resources and data availability in the cloud, the threats related to the security of computer networks and IT systems are critical. Threat detection systems based on deep neural networks and anomaly detection are trained on data related to normal activity so that the network can recognize unusual patterns and behaviours in the event of an attack or an attempt to infiltrate a given IT infrastructure. This paper presents the results of developing a neural network based on an autoencoder for anomaly detection in network packet data. The network was trained on data from the HIKARI-2021 dataset. The autoencoder aims to learn representations of normal network traffic and associate this type of traffic with a minimal reconstruction error. The obtained results were compared with those achieved by authors of other works. High accuracy and sensitivity were achieved at the cost of rather low precision, resulting in many false-positive results. A simple algorithm based on a single threshold value proved efficient but limited in terms of effectiveness. This problem can be resolved by changing the method of calculating the individual components of the vector, using only a subset of features, and deriving multiple vectors, one for each class separately, which has been described and analyzed in more detail.
In the context of discrete-event systems (DES), the terms detection and diagnosis refer to two distinct stages of handling faults and anomalies. Both steps are critical for ensuring the reliable and safe operation of ...
详细信息
In the context of discrete-event systems (DES), the terms detection and diagnosis refer to two distinct stages of handling faults and anomalies. Both steps are critical for ensuring the reliable and safe operation of complex systems. In this paper, we propose the use of autoencoders for fault detection in an automated production system with sensors and actuators delivering discrete binary signals that can be modeled as DES. We train an autoencoder exclusively on data representing normal behavior. The model learns to encode typical patterns and reconstruct input data with low loss. A predetermined threshold, determined by the characteristics of the training data, is set for the reconstruction error. During normal behavior, the autoencoder is expected to achieve low reconstruction error below this threshold. When a fault occurs, the autoencoder strives to accurately reconstruct faulty data, leading to a higher error. The detection of a reconstruction error exceeding the threshold signals a potential fault in the system. The results of applying our method to the Factory IO software sorting system demonstrate the significant contribution and the interest of this method for detecting faults.
Tread wear rates of the right and left wheels of a wheelset are not the same because of the complexity of the track condition, which causes the wheel diameter difference (WDD). The WDD can influence vehicle dynamic pe...
详细信息
Tread wear rates of the right and left wheels of a wheelset are not the same because of the complexity of the track condition, which causes the wheel diameter difference (WDD). The WDD can influence vehicle dynamic performances and shorten the service life of the wheelset. To diagnose and recognize the condition of the WDD in time, a data-driven method based on multi-sensor information fusion is proposed. Different statistical features are extracted from the time and frequency domains of the axle-box acceleration signals. The features can be fused by integrating stacked autoencoder and multiple kernel learning. The comparative experimental analysis shows that compared with other commonly used intelligent methods, the proposed method can achieve higher diagnostic accuracy and give better performance with small training sample sizes. The statistical features sensitive to the WDD are also analyzed for industrial application.
暂无评论