相关论文
2014 - HotCloud
A Novel Technique for Long-Term Anomaly Detection in the Cloud

High availability and performance of a web service is key, amongst other factors, to the overall user experience (which in turn directly impacts the bottom-line). Exogenic and/or endogenic factors often give rise to anomalies that make maintaining high availability and delivering high performance very challenging. Although there exists a large body of prior research in anomaly detection, existing techniques are not suitable for detecting long-term anomalies owing to a predominant underlying trend component in the time series data. To this end, we developed a novel statistical technique to automatically detect long-term anomalies in cloud data. Specifically, the technique employs statistical learning to detect anomalies in both application as well as system metrics. Further, the technique uses robust statistical metrics, viz., median, and median absolute deviation (MAD), and piecewise approximation of the underlying long-term trend to accurately detect anomalies even in the presence of intra-day and/or weekly seasonality. We demonstrate the efficacy of the proposed technique using production data and report Precision, Recall, and F-measure measure. Multiple teams at Twitter are currently using the proposed technique on a daily basis.

1997 - KDD
A Probabilistic Approach to Fast Pattern Matching in Time Series Databases

The problem of efficiently and accurately locating patterns of interest in massive time series data sets is an important and non-trivial problem in a wide variety of applications, including diagnosis and monitoring of complex systems, biomedical data analysis, and exploratory data analysis in scientific and business time series. In this paper a probabilistic approach is taken to this problem. Using piecewise linear segmentations as the underlying representation, local features (such as peaks, troughs, and plateaus) are defined using a prior distribution on expected deformations from a basic template. Global shape information is represented using another prior on the relative locations of the individual features. An appropriately defined probabilistic model integrates the local and global information and directly leads to an overall distance measure between sequence patterns based on prior knowledge. A search algorithm using this distance measure is shown to efficiently and accurately find matches for a variety of patterns on a number of data sets, including engineering sensor data from space Shuttle mission archives. The proposed approach provides a natural framework to support user-customizable "query by content" on time series data, taking prior domain information into account in a principled manner.

2007 - 2007 IEEE International Conference on Communications
Quarter Sphere Based Distributed Anomaly Detection in Wireless Sensor Networks

Anomaly detection is an important challenge for tasks such as fault diagnosis and intrusion detection in energy constrained wireless sensor networks. A key problem is how to minimise the communication overhead in the network while performing in-network computation when detecting anomalies. Our approach to this problem is based on a formulation that uses distributed, one-class quarter-sphere support vector machines to identify anomalous measurements in the data. We demonstrate using sensor data from the Great Duck Island Project that our distributed approach is energy efficient in terms of communication overhead while achieving comparable accuracy to a centralised scheme.

2017 - IEEE Transactions on Image Processing
Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes

This paper proposes a fast and reliable method for anomaly detection and localization in video data showing crowded scenes. Time-efficient anomaly localization is an ongoing challenge and subject of this paper. We propose a cubic-patch-based method, characterised by a cascade of classifiers, which makes use of an advanced feature-learning approach. Our cascade of classifiers has two main stages. First, a light but deep 3D auto-encoder is used for early identification of “many” normal cubic patches. This deep network operates on small cubic patches as being the first stage, before carefully resizing the remaining candidates of interest, and evaluating those at the second stage using a more complex and deeper 3D convolutional neural network (CNN). We divide the deep auto-encoder and the CNN into multiple sub-stages, which operate as cascaded classifiers. Shallow layers of the cascaded deep networks (designed as Gaussian classifiers, acting as weak single-class classifiers) detect “simple” normal patches, such as background patches and more complex normal patches, are detected at deeper layers. It is shown that the proposed novel technique (a cascade of two cascaded classifiers) performs comparable to current top-performing detection and localization methods on standard benchmarks, but outperforms those in general with respect to required computation time.

1996 - Journal of epidemiology and community health
Short term effects of air pollution on health: a European approach using epidemiologic time series data: the APHEA protocol.

BACKGROUND AND OBJECTIVES: Results from several studies over the past five years have shown that the current levels of pollutants in Europe and North America have adverse short term effects on health. The APHEA project aims to quantifying these in Europe, using standardised methodology. The project protocol and analytical methodology are presented here. DESIGN: Daily time series data were gathered for several air pollutants (sulphur dioxide; particulate matter, measured as total particles or as the particle fraction with an aerodynamic diameter smaller than a certain cut off, or as black smoke; nitrogen dioxide; and ozone) and health outcomes (the total and cause specific number of deaths and emergency hospital admissions). The data included fulfilled the quality criteria set by the APHEA protocol. SETTING: Fifteen European cities from 10 different countries with a total population over 25 million. METHODOLOGY: The APHEA collaborative group decided on a specific methodological procedure to control for confounding effects and evaluate the hypothesis. At the same time there was sufficient flexibility to allow local characteristics to be taken into account. The procedure included modelling of all potential confounding factors (that is, seasonal and long term patterns, meteorological factors, day of the week, holidays, and other unusual events), choosing the "best" air pollution models, and applying diagnostic tools to check the adequacy of the models. The final analysis used autoregressive Poisson models allowing for overdispersion. Effects were reported as relative risks contrasting defined increases in the corresponding pollutant levels. Each participating group applied the analyses to their own data. CONCLUSIONS: This methodology enabled results from many different European settings to be considered collectively. It represented the best available compromise between feasibility, comparability, and local adaptibility when using aggregated time series data not originally collected for the purpose of epidemiological studies.

2007 - SIGMETRICS '07
Sensitivity of PCA for traffic anomaly detection

Detecting anomalous traffic is a crucial part of managing IP networks. In recent years, network-wide anomaly detection based on Principal Component Analysis (PCA) has emerged as a powerful method for detecting a wide variety of anomalies. We show that tuning PCA to operate effectively in practice is difficult and requires more robust techniques than have been presented thus far. We analyze a week of network-wide traffic measurements from two IP backbones (Abilene and Geant) across three different traffic aggregations (ingress routers, OD flows, and input links), and conduct a detailed inspection of the feature time series for each suspected anomaly. Our study identifies and evaluates four main challenges of using PCA to detect traffic anomalies: (i) the false positive rate is very sensitive to small differences in the number of principal components in the normal subspace, (ii) the effectiveness of PCA is sensitive to the level of aggregation of the traffic measurements, (iii) a large anomaly may in advertently pollute the normal subspace, (iv) correctly identifying which flow triggered the anomaly detector is an inherently challenging problem.

2018 - ArXiv
Deep Anomaly Detection with Outlier Exposure

It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small- and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this issue. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.

2003 - DMKD '03
A symbolic representation of time series, with implications for streaming algorithms

The parallel explosions of interest in streaming data, and data mining of time series have had surprisingly little intersection. This is in spite of the fact that time series data are typically streaming data. The main reason for this apparent paradox is the fact that the vast majority of work on streaming data explicitly assumes that the data is discrete, whereas the vast majority of time series data is real valued.Many researchers have also considered transforming real valued time series into symbolic representations, nothing that such representations would potentially allow researchers to avail of the wealth of data structures and algorithms from the text processing and bioinformatics communities, in addition to allowing formerly "batch-only" problems to be tackled by the streaming community. While many symbolic representations of time series have been introduced over the past decades, they all suffer from three fatal flaws. Firstly, the dimensionality of the symbolic representation is the same as the original data, and virtually all data mining algorithms scale poorly with dimensionality. Secondly, although distance measures can be defined on the symbolic approaches, these distance measures have little correlation with distance measures defined on the original time series. Finally, most of these symbolic approaches require one to have access to all the data, before creating the symbolic representation. This last feature explicitly thwarts efforts to use the representations with streaming algorithms.In this work we introduce a new symbolic representation of time series. Our representation is unique in that it allows dimensionality/numerosity reduction, and it also allows distance measures to be defined on the symbolic approach that lower bound corresponding distance measures defined on the original series. As we shall demonstrate, this latter feature is particularly exciting because it allows one to run certain data mining algorithms on the efficiently manipulated symbolic representation, while producing identical results to the algorithms that operate on the original data. Finally, our representation allows the real valued data to be converted in a streaming fashion, with only an infinitesimal time and space overhead.We will demonstrate the utility of our representation on the classic data mining tasks of clustering, classification, query by content and anomaly detection.

2012 - 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Exploiting sparseness in deep neural networks for large vocabulary speech recognition

Recently, we developed context-dependent deep neural network (DNN) hidden Markov models for large vocabulary speech recognition. While reducing errors by 33% compared to its discriminatively trained Gaussian-mixture counterpart on the switchboard benchmark task, DNN requires much more parameters. In this paper, we report our recent work on DNN for improved generalization, model size, and computation speed by exploiting parameter sparseness. We formulate the goal of enforcing sparseness as soft regularization and convex constraint optimization problems, and propose solutions under the stochastic gradient ascent setting. We also propose novel data structures to exploit the random sparseness patterns to reduce model size and computation time. The proposed solutions have been evaluated on the voice-search and switchboard datasets. They have decreased the number of nonzero connections to one third while reducing the error rate by 0.2-0.3% over the fully connected model on both datasets. The nonzero connections have been further reduced to only 12% and 19% on the two respective datasets without sacrificing speech recognition performance. Under these conditions we can reduce the model size to 18% and 29%, and computation to 14% and 23%, respectively, on these two datasets.

2019 - Future Gener. Comput. Syst.
Optimal deep learning model for classification of lung cancer on CT images

Abstract Lung cancer is one of the dangerous diseases that cause huge cancer death worldwide. Early detection of lung cancer is the only possible way to improve a patient’s chance for survival. A Computed Tomography (CT) scan used to find the position of tumor and identify the level of cancer in the body. The current study presents an innovative automated diagnosis classification method for Computed Tomography (CT) images of lungs. In this paper, the CT scan of lung images was analyzed with the assistance of Optimal Deep Neural Network (ODNN) and Linear Discriminate Analysis (LDA). The deep features extracted from a CT lung images and then dimensionality of feature is reduced using LDR to classify lung nodules as either malignant or benign. The ODNN is applied to CT images and then, optimized using Modified Gravitational Search Algorithm (MGSA) for identify the lung cancer classification The comparative results show that the proposed classifier gives the sensitivity of 96.2%, specificity of 94.2% and accuracy of 94.56%.

2014 - Journal of Process Control
Data-driven soft sensor development based on deep learning technique

Abstract In industrial process control, some product qualities and key variables are always difficult to measure online due to technical or economic limitations. As an effective solution, data-driven soft sensors provide stable and reliable online estimation of these variables based on historical measurements of easy-to-measure process variables. Deep learning, as a novel training strategy for deep neural networks, has recently become a popular data-driven approach in the area of machine learning. In the present study, the deep learning technique is employed to build soft sensors and applied to an industrial case to estimate the heavy diesel 95% cut point of a crude distillation unit (CDU). The comparison of modeling results demonstrates that the deep learning technique is especially suitable for soft sensor modeling because of the following advantages over traditional methods. First, with a complex multi-layer structure, the deep neural network is able to contain richer information and yield improved representation ability compared with traditional data-driven models. Second, deep neural networks are established as latent variable models that help to describe highly correlated process variables. Third, the deep learning is semi-supervised so that all available process data can be utilized. Fourth, the deep learning technique is particularly efficient dealing with massive data in practice.

2016 - ArXiv
Adversarial Perturbations Against Deep Neural Networks for Malware Classification

Deep neural networks, like many other machine learning models, have recently been shown to lack robustness against adversarially crafted inputs. These inputs are derived from regular inputs by minor yet carefully selected perturbations that deceive machine learning models into desired misclassifications. Existing work in this emerging field was largely specific to the domain of image classification, since the high-entropy of images can be conveniently manipulated without changing the images' overall visual appearance. Yet, it remains unclear how such attacks translate to more security-sensitive applications such as malware detection - which may pose significant challenges in sample generation and arguably grave consequences for failure. In this paper, we show how to construct highly-effective adversarial sample crafting attacks for neural networks used as malware classifiers. The application domain of malware classification introduces additional constraints in the adversarial sample crafting problem when compared to the computer vision domain: (i) continuous, differentiable input domains are replaced by discrete, often binary inputs; and (ii) the loose condition of leaving visual appearance unchanged is replaced by requiring equivalent functional behavior. We demonstrate the feasibility of these attacks on many different instances of malware classifiers that we trained using the DREBIN Android malware data set. We furthermore evaluate to which extent potential defensive mechanisms against adversarial crafting can be leveraged to the setting of malware classification. While feature reduction did not prove to have a positive impact, distillation and re-training on adversarially crafted samples show promising results.

2017 - ArXiv
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify. Existing methods for crafting adversarial examples are based on $L_2$ and $L_\infty$ distortion metrics. However, despite the fact that $L_1$ distortion accounts for the total variation and encourages sparsity in the perturbation, little has been developed for crafting $L_1$-based adversarial examples. In this paper, we formulate the process of attacking DNNs via adversarial examples as an elastic-net regularized optimization problem. Our elastic-net attacks to DNNs (EAD) feature $L_1$-oriented adversarial examples and include the state-of-the-art $L_2$ attack as a special case. Experimental results on MNIST, CIFAR10 and ImageNet show that EAD can yield a distinct set of adversarial examples with small $L_1$ distortion and attains similar attack performance to the state-of-the-art methods in different attack scenarios. More importantly, EAD leads to improved attack transferability and complements adversarial training for DNNs, suggesting novel insights on leveraging $L_1$ distortion in adversarial machine learning and security implications of DNNs.

2018 - Frontiers of Information Technology & Electronic Engineering
Visual interpretability for deep learning: a survey

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, interpretability is always Achilles’ heel of deep neural networks. At present, deep neural networks obtain high discrimination power at the cost of a low interpretability of their black-box representations. We believe that high model interpretability may help people break several bottlenecks of deep learning, e.g., learning from a few annotations, learning via human–computer communications at the semantic level, and semantically debugging network representations. We focus on convolutional neural networks (CNNs), and revisit the visualization of CNN representations, methods of diagnosing representations of pre-trained CNNs, approaches for disentangling pre-trained CNN representations, learning of CNNs with disentangled representations, and middle-to-end learning based on model interpretability. Finally, we discuss prospective trends in explainable artificial intelligence.

2016 - ArXiv
Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes

We present an efficient method for detecting and localizing anomalies in videos showing crowded scenes. Research on {\it fully convolutional neural networks} (FCNs) has shown the potentials of this technology for object detection and localization, especially in images. We investigate how to involve temporal data, and how to transform a supervised FCN into an unsupervised one such that the resulting FCN ensures anomaly detection. Altogether, we propose an FCN-based architecture for anomaly detection and localization in crowded scenes videos. For reducing computations and, consequently, improving performance both with respect to speed and accuracy, we investigate the use of cascaded out-layer detection. Our architecture includes two main components, one for feature representation, and one for cascaded out-layer detection. Experimental results on Subway and UCSD benchmarks confirm that the detection and localization accuracy of our method is comparable to state-of-the-art methods, but at a significantly increased speed of 370 fps.

2017 - 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Deep Hashing Network for Unsupervised Domain Adaptation

In recent years, deep neural networks have emerged as a dominant machine learning tool for a wide variety of application domains. However, training a deep neural network requires a large amount of labeled data, which is an expensive process in terms of time, labor and human expertise. Domain adaptation or transfer learning algorithms address this challenge by leveraging labeled data in a different, but related source domain, to develop a model for the target domain. Further, the explosive growth of digital data has posed a fundamental challenge concerning its storage and retrieval. Due to its storage and retrieval efficiency, recent years have witnessed a wide application of hashing in a variety of computer vision applications. In this paper, we first introduce a new dataset, Office-Home, to evaluate domain adaptation algorithms. The dataset contains images of a variety of everyday objects from multiple domains. We then propose a novel deep learning framework that can exploit labeled source data and unlabeled target data to learn informative hash codes, to accurately classify unseen target data. To the best of our knowledge, this is the first research effort to exploit the feature learning capabilities of deep neural networks to learn representative hash codes to address the domain adaptation problem. Our extensive empirical studies on multiple transfer tasks corroborate the usefulness of the framework in learning efficient hash codes which outperform existing competitive baselines for unsupervised domain adaptation.

2018 - ArXiv
Beyond Data and Model Parallelism for Deep Neural Networks

The computational requirements for training deep neural networks (DNNs) have grown to the point that it is now standard practice to parallelize training. Existing deep learning systems commonly use data or model parallelism, but unfortunately, these strategies often result in suboptimal parallelization performance. In this paper, we define a more comprehensive search space of parallelization strategies for DNNs called SOAP, which includes strategies to parallelize a DNN in the Sample, Operation, Attribute, and Parameter dimensions. We also propose FlexFlow, a deep learning framework that uses guided randomized search of the SOAP space to find a fast parallelization strategy for a specific parallel machine. To accelerate this search, FlexFlow introduces a novel execution simulator that can accurately predict a parallelization strategy's performance and is three orders of magnitude faster than prior approaches that have to execute each strategy. We evaluate FlexFlow with six real-world DNN benchmarks on two GPU clusters and show that FlexFlow can increase training throughput by up to 3.8x over state-of-the-art approaches, even when including its search time, and also improves scalability.

2017 - ArXiv
Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks

In this work, we tackle the problem of car license plate detection and recognition in natural scene images. We propose a unified deep neural network which can localize license plates and recognize the letters simultaneously in a single forward pass. The whole network can be trained end-to-end. In contrast to existing approaches which take license plate detection and recognition as two separate tasks and settle them step by step, our method jointly solves these two tasks by a single network. It not only avoids intermediate error accumulation, but also accelerates the processing speed. For performance evaluation, three datasets including images captured from various scenes under different conditions are tested. Extensive experiments show the effectiveness and efficiency of our proposed approach.

2019 - Nature Medicine
Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network

Computerized electrocardiogram (ECG) interpretation plays a critical role in the clinical ECG workflow1. Widely available digital ECG data and the algorithmic paradigm of deep learning2 present an opportunity to substantially improve the accuracy and scalability of automated ECG analysis. However, a comprehensive evaluation of an end-to-end deep learning approach for ECG analysis across a wide variety of diagnostic classes has not been previously reported. Here, we develop a deep neural network (DNN) to classify 12 rhythm classes using 91,232 single-lead ECGs from 53,549 patients who used a single-lead ambulatory ECG monitoring device. When validated against an independent test dataset annotated by a consensus committee of board-certified practicing cardiologists, the DNN achieved an average area under the receiver operating characteristic curve (ROC) of 0.97. The average F1 score, which is the harmonic mean of the positive predictive value and sensitivity, for the DNN (0.837) exceeded that of average cardiologists (0.780). With specificity fixed at the average specificity achieved by cardiologists, the sensitivity of the DNN exceeded the average cardiologist sensitivity for all rhythm classes. These findings demonstrate that an end-to-end deep learning approach can classify a broad range of distinct arrhythmias from single-lead ECGs with high diagnostic performance similar to that of cardiologists. If confirmed in clinical settings, this approach could reduce the rate of misdiagnosed computerized ECG interpretations and improve the efficiency of expert human ECG interpretation by accurately triaging or prioritizing the most urgent conditions.Analysis of electrocardiograms using an end-to-end deep learning approach can detect and classify cardiac arrhythmia with high accuracy, similar to that of cardiologists.

2018 - Data Mining and Knowledge Discovery
Deep learning for time series classification: a review

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.

Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform

Michael E. Fitzpatrick
|
Stratis Kanarachos
|
Alexander Chroneos
|
Stavros-Richard G. Christopoulos
|
M. Fitzpatrick
|
A. Chroneos
|
S. Christopoulos
|
S. Kanarachos

Abstract:Design of a transferable time series anomaly detection method.Novel deep neural network structure facilitates learning short and long-term pattern interdependencies.Detection of anomalies in the Seismic Electrical Signal for predicting earthquake activity.Detection of road anomalies using smartphone data, facilitating crowdsourcing applications. The quest for more efficient real-time detection of anomalies in time series data is critically important in numerous applications and systems ranging from intelligent transportation, structural health monitoring, heart disease, and earthquake prediction. Although the range of application is wide, anomaly detection algorithms are usually domain specific and build on experts knowledge. Here a new signal processing algorithm inspired by the deep learning paradigm is presented that combines wavelets, neural networks, and Hilbert transform. The algorithm performs robustly and is transferable. The proposed neural network structure facilitates learning short and long-term pattern interdependencies; a task usually hard to accomplish using standard neural network training algorithms. The paper provides guidelines for selecting the neural network's buffer size, training algorithm, and anomaly detection features. The algorithm learns the system's normal behavior and does not require the existence of anomalous data for assessing its statistical significance. This is an essential attribute in applications that require customization. Anomalies are detected by analysing hierarchically the instantaneous frequency and amplitude of the residual signal using probabilistic Receiver Operating Characteristics. The method is shown to be able to automatically detect anomalies in the Seismic Electrical Signal that could be used to predict earthquake activity. Furthermore, the method can be used in combination with crowdsourcing of smartphone data to locate road defects such as potholes and bumps for intervention and repair.

参考文献

[1]  Panayiotis A. Varotsos,et al.  Physical properties of the variations of the electric field of the earth preceding earthquakes, I , 1984 .

[2]  Panayiotis A. Varotsos,et al.  Natural Time Analysis: The New View of Time : Precursory Seismic Electric Signals, Earthquakes and other Complex Time Series , 2011 .

[3]  Dong Li,et al.  Negative selection algorithm with constant detectors for anomaly detection , 2015, Appl. Soft Comput..

[4]  Jukka Riekki,et al.  Applying Wavelet Packet Decomposition and One-Class Support Vector Machine on Vehicle Acceleration Traces for Road Anomaly Detection , 2013, ISNN.

[5]  Bilge Yildiz,et al.  Mapping strain rate dependence of dislocation-defect interactions by atomistic simulations , 2013, Proceedings of the National Academy of Sciences.

[6]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[7]  P. Varotsos,et al.  Electric fields that "arrive" before the time derivative of the magnetic field prior to major earthquakes. , 2003, Physical review letters.

[8]  Paul S. Addison,et al.  The Illustrated Wavelet Transform Handbook , 2002 .

[9]  M. Akhoondzadeh,et al.  Application of Artificial Bee Colony algorithm in TEC seismo-ionospheric anomalies detection , 2015 .

[10]  I. Johnstone,et al.  Minimax estimation via wavelet shrinkage , 1998 .

[11]  Miltiadis Alamaniotis,et al.  Gaussian Processes for State Identification in Pressurized Water Reactors , 2013 .

[12]  Nicholas V. Sarlis,et al.  An Application of the Coherent Noise Model for the Prediction of Aftershock Magnitude Time Series , 2017, Complex..

[13]  A. Chroneos,et al.  Impact of uniaxial strain and doping on oxygen diffusion in CeO2 , 2014, Scientific Reports.

[14]  Adam P. Piotrowski,et al.  Differential Evolution algorithms applied to Neural Network training suffer from stagnation , 2014, Appl. Soft Comput..

[15]  Amy Loutfi,et al.  A review of unsupervised feature learning and deep learning for time-series modeling , 2014, Pattern Recognit. Lett..

[16]  Ilya Sutskever,et al.  Training Deep and Recurrent Networks with Hessian-Free Optimization , 2012, Neural Networks: Tricks of the Trade.

[17]  M. S. Lazaridou,et al.  Latest aspects of earthquake prediction in Greece based on seismic electric signals, II☆ , 1993 .

[18]  Albert E. Hoefel,et al.  Algorithms for estimating instantaneous frequency , 2004, Signal Process..

[19]  P. Varotsos,et al.  Physical properties of the variations of the electric field of the earth preceding earthquakes, I , 1984 .

[20]  Panayiotis A. Varotsos,et al.  Physical properties of the variations of the electric field of the earth preceding earthquakes. II. determination of epicenter and magnitude , 1984 .

[21]  Farid Kadri,et al.  Improved principal component analysis for anomaly detection: Application to an emergency department , 2015, Comput. Ind. Eng..

[22]  Blas P. Uberuaga,et al.  Non-uniform Solute Segregation at Semi-Coherent Metal/Oxide Interfaces , 2015, Scientific Reports.

[23]  Geoffrey E. Hinton.  Learning multiple layers of representation , 2007, Trends in Cognitive Sciences.

[24]  Efthimios S. Skordas,et al.  Identifying sudden cardiac death risk and specifying its occurrence time by analyzing electrocardiograms in natural time , 2007 .

[25]  Stratis Kanarachos.  A new min-max methodology for computing optimised obstacle avoidance steering manoeuvres of ground vehicles , 2014, Int. J. Syst. Sci..

[26]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[27]  Zoubin Ghahramani,et al.  Probabilistic machine learning and artificial intelligence , 2015, Nature.

[28]  Astarita Vittorio,et al.  Automated Sensing System for Monitoring of Road Surface Quality by Mobile Devices , 2014 .

[29]  P. Varotsos,et al.  Long-range correlations in the electric signals that precede rupture. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[30]  Chrysostomos D. Stylios,et al.  Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition , 2013 .

[31]  Adam P. Piotrowski,et al.  Optimizing neural networks for river flow forecasting – Evolutionary Computation methods versus the Levenberg–Marquardt approach , 2011 .

[32]  Ralph O. Simmons,et al.  Thermodynamics of Point Defects and Their Relation With Bulk Properties , 1985 .

[33]  P. Varotsos,et al.  Attempt to distinguish electric signals of a dichotomous nature. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[34]  M. S. Lazaridou,et al.  Latest aspects of earthquake prediction in Greece based on seismic electric signals : Tectonophysics V188, N3/4, March 1991, P321–347 , 1991 .

[35]  Achilleas Zapranis,et al.  Wavelet Neural Networks: A Practical Guide , 2011, Neural Networks.

[36]  Wei Chen,et al.  Nucleation of metastable aragonite CaCO[subscript 3] in seawater , 2015 .

[37]  James G. Lyons,et al.  Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning , 2015, Scientific Reports.

[38]  Masashi Kamogawa,et al.  Spatiotemporal variations of seismicity before major earthquakes in the Japanese area and their relation with the epicentral locations , 2014, Proceedings of the National Academy of Sciences.

[39]  Nicholas V. Sarlis,et al.  Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses , 2014, Comput. Phys. Commun..

[40]  Michael E. Fitzpatrick,et al.  Efficient truss optimization using the contrast-based fruit fly optimization algorithm , 2017 .

[41]  Richard J. Povinelli,et al.  Probabilistic anomaly detection in natural gas time series data , 2016 .

[42]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[43]  Xiao-yun Chen,et al.  Multi-scale anomaly detection algorithm based on infrequent pattern of time series , 2008 .

[44]  Stavros Christopoulos,et al.  Change ΔS of the entropy in natural time under time reversal: Complexity measures upon change of scale , 2015 .

[45]  Baris Asikgil,et al.  Nonlinear time series forecasting with Bayesian neural networks , 2014, Expert Syst. Appl..

[46]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

引用
Pothole Detection in Asphalt: An Automated Approach to Threshold Computation Based on the Haar Wavelet Transform
2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC)
2019
Intelligent Wavelet Based Techniques for Advanced Multimedia Applications
2020
Wavelets and Intelligent Multimedia Applications: An Introduction
2020
Reducing Traffic Congestion by LSTM-LOF Framework
2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA)
2019
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
IEEE Access
2019
SHNN-CAD+: An Improvement on SHNN-CAD for Adaptive Online Trajectory Anomaly Detection
Sensors
2018
Accelerating time series motif discovery in the Intel Xeon Phi KNL processor
The Journal of Supercomputing
2019
A GAN-Based Anomaly Detection Approach for Imbalanced Industrial Time Series
IEEE Access
2019
Anomaly Detection in Multivariate Time Series Using Fuzzy AdaBoost and Dynamic Naive Bayesian Classifier
2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
2019
Learning Driver Braking Behavior Using Smartphones, Neural Networks and the Sliding Correlation Coefficient: Road Anomaly Case Study
IEEE Transactions on Intelligent Transportation Systems
2019
Inland Ship Trajectory Restoration by Recurrent Neural Network
Journal of Navigation
2019
Deep Learning based Multiple Sensors Monitoring and Abnormal Discovery for Satellite Power System
2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)
2019
The Behavior of VLF/LF Variations Associated with Geomagnetic Activity, Earthquakes, and the Quiet Condition Using a Neural Network Approach
Entropy
2018
Generic Application of Deep Learning Framework for Real-Time Engineering Data Analysis
2018 International Joint Conference on Neural Networks (IJCNN)
2018
Intelligent Multimedia Applications in Wavelet Domain: New Trends and Future Research Directions
2020
Anomaly Detection And Classification In Time Series With Kervolutional Neural Networks
Proceedings of the 30th European Safety and Reliability Conference and 15th Probabilistic Safety Assessment and Management Conference
2020
Application of Artificial Intelligence in Predicting Earthquakes: State-of-the-Art and Future Challenges
IEEE Access
2020
Pavement Management Utilizing Mobile Crowd Sensing
2020
Energy consumption forecasting based on Elman neural networks with evolutive optimization
Expert Syst. Appl.
2018
Deep Learning-Based Damage, Load and Support Identification for a Composite Pipeline by Extracting Modal Macro Strains from Dynamic Excitations
Applied Sciences
2018