Search

Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series analytics is therefore crucial to unlocking the wealth of information implicit in available data. With the recent advancements in graph neural networks (GNNs), there has been a surge in GNN-based approaches for time series analysis. These approaches can explicitly model inter-temporal and inter-variable relationships, which traditional and other deep neural network-based methods struggle to do. In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation. Our aim is to guide designers and practitioners to understand, build applications, and advance research of GNN4TS. At first, we provide a comprehensive task-oriented taxonomy of GNN4TS. Then, we present and discuss representative research works and introduce mainstream applications of GNN4TS. A comprehensive discussion of potential future research directions completes the survey. This survey, for the first time, brings together a vast array of knowledge on GNN-based time series research, highlighting foundations, practical applications, and opportunities of graph neural networks for time series analysis.

Many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs. In this article, we present an operational framework to unify this vast and diverse literature by describing pooling operators as the combination of three functions: selection, reduction, and connection (SRC). We then introduce a taxonomy of pooling operators, based on some of their key characteristics and implementation differences under the SRC framework. Finally, we propose three criteria to evaluate the performance of pooling operators and use them to investigate the behavior of different operators on a variety of tasks.

The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD approaches for nonlinear dynamic systems. More specifically, we parameterize nonlinear systems through a generalized kernel representation for system modeling and the associated fault diagnosis. An important result obtained is a unified form of kernel representations, applicable to both unsupervised and supervised learning. More importantly, through a rigorous theoretical analysis, we discover the existence of a bridge (i.e., a bijective mapping) between some supervised and unsupervised learning-based entities. Notably, the designed IFD approaches achieve the same performance with the use of this bridge. In order to have a better understanding of the results obtained, both unsupervised and supervised neural networks are chosen as the learning tools to identify the generalized kernel representations and design the IFD schemes; an invertible neural network is then employed to build the bridge between them. This article is a perspective article, whose contribution lies in proposing and formalizing the fundamental concepts for explainable intelligent learning methods, contributing to system modeling and data-driven IFD designs for nonlinear dynamic systems.

Over the past decade, representation learning has received particular attention in the intelligent inspection and maintenance of complex systems thanks to its overwhelming advantages in discovering and mining hidden knowledge representations. The room for in-depth investigations of representation learning-related topics remains open, especially explainable approaches for intelligent inspection and maintenance of complex systems. The primary objective of this special issue, entitled “Explainable Representation Learning-based Intelligent Inspection and Maintenance of Complex Systems,” of IEEE Transactions on Neural Networks and Learning Systems is to provide the related latest achievements made by researchers and practitioners on the one hand and to identify critical issues and challenges for future investigation on the other hand.

Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance. The recurrent part of these networks is not trained (e.g., via gradient descent), making them appealing for analytical studies by a large community of researchers with backgrounds spanning from dynamical systems to neuroscience. However, even in the simple linear case, the working principle of these networks is not fully understood and their design is usually driven by heuristics. A novel analysis of the dynamics of such networks is proposed, which allows the investigator to express the state evolution using the controllability matrix. Such a matrix encodes salient characteristics of the network dynamics; in particular, its rank represents an input-independent measure of the memory capacity of the network. Using the proposed approach, it is possible to compare different reservoir architectures and explain why a cyclic topology achieves favorable results as verified by practitioners. [ABSTRACT FROM AUTHOR]

In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the GNN learns new node representations and fits them to a pyramid of coarsened graphs, which is computed offline in a preprocessing stage. NDP consists of three steps. First, a node decimation procedure selects the nodes belonging to one side of the partition identified by a spectral algorithm that approximates the MAXCUT solution. Afterward, the selected nodes are connected with Kron reduction to form the coarsened graph. Finally, since the resulting graph is very dense, we apply a sparsification procedure that prunes the adjacency matrix of the coarsened graph to reduce the computational cost in the GNN. Notably, we show that it is possible to remove many edges without significantly altering the graph structure. Experimental results show that NDP is more efficient compared to state-of-the-art graph pooling operators while reaching, at the same time, competitive performance on a significant variety of graph classification tasks. [ABSTRACT FROM AUTHOR]

Pest insect monitoring and control is crucial to ensure a safe and profitable crop growth in all plantation types, as well as guarantee food quality and limited use of pesticides. We aim at extending traditional monitoring by means of traps, by involving the general public in reporting the presence of insects by using smartphones. This includes the largely unexplored problem of detecting insects in images that are taken in noncontrolled conditions. Furthermore, pest insects are, in many cases, extremely similar to other species that are harmless. Therefore, computer vision algorithms must not be fooled by these similar insects, not to raise unmotivated alarms. In this work, we study the capabilities of state-of-the-art (SoA) object detection models based on convolutional neural networks (CNN) for the task of detecting beetle-like pest insects on nonhomogeneous images taken outdoors by different sources. Moreover, we focus on disambiguating a pest insect from similar harmless species. We consider not only detection performance of different models, but also required computational resources. This study aims at providing a baseline model for this kind of tasks. Our results show the suitability of current SoA models for this application, highlighting how FasterRCNN with a MobileNetV3 backbone is a particularly good starting point for accuracy and inference execution latency. This combination provided a mean average precision score of 92.66% that can be considered qualitatively at least as good as the score obtained by other authors that adopted more specific models.

The lethal novel coronavirus disease 2019 (COVID-19) pandemic is affecting the health of the global population severely, and a huge number of people may have to be screened in the future. There is a need for effective and reliable systems that perform automatic detection and mass screening of COVID-19 as a quick alternative diagnostic option to control its spread. A robust deep learning-based system is proposed to detect the COVID-19 using chest X-ray images. Infected patient's chest X-ray images reveal numerous opacities (denser, confluent, and more profuse) in comparison to healthy lungs images which are used by a deep learning algorithm to generate a model to facilitate an accurate diagnostics for multi-class classification (COVID vs. normal vs. bacterial pneumonia vs. viral pneumonia) and binary classification (COVID-19 vs. non-COVID). COVID-19 positive images have been used for training and model performance assessment from several hospitals of India and also from countries like Australia, Belgium, Canada, China, Egypt, Germany, Iran, Israel, Italy, Korea, Spain, Taiwan, USA, and Vietnam. The data were divided into training, validation and test sets. The average test accuracy of 97.11 ± 2.71% was achieved for multi-class (COVID vs. normal vs. pneumonia) and 99.81% for binary classification (COVID-19 vs. non-COVID). The proposed model performs rapid disease detection in 0.137 s per image in a system equipped with a GPU and can reduce the workload of radiologists by classifying thousands of images on a single click to generate a probabilistic report in real-time.

The space of graphs is often characterized by a nontrivial geometry, which complicates learning and inference in practical applications. A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited for embedding graphs. Among these, constant-curvature Riemannian manifolds (CCMs) offer embedding spaces suitable for studying the statistical properties of a graph distribution, as they provide ways to easily compute metric geodesic distances. In this paper, we focus on the problem of detecting changes in stationarity in a stream of attributed graphs. To this end, we introduce a novel change detection framework based on neural networks and CCMs, which takes into account the non-Euclidean nature of graphs. Our contribution in this paper is twofold. First, via a novel approach based on adversarial learning, we compute graph embeddings by training an autoencoder to represent graphs on CCMs. Second, we introduce two novel change detection tests operating on CCMs. We perform experiments on synthetic data, as well as two real-world application scenarios: the detection of epileptic seizures using functional connectivity brain networks and the detection of hostility between two subjects, using human skeletal graphs. Results show that the proposed methods are able to detect even small changes in a graph-generating process, consistently outperforming approaches based on Euclidean embeddings. [ABSTRACT FROM AUTHOR]

In this paper, a data-based fault tolerant control &#x0028 FTC &#x0029 scheme is investigated for unknown continuous-time &#x0028 CT &#x0029 affine nonlinear systems with actuator faults. First, a neural network &#x0028 NN &#x0029 identifier based on particle swarm optimization &#x0028 PSO &#x0029 is constructed to model the unknown system dynamics. By utilizing the estimated system states, the particle swarm optimized critic neural network &#x0028 PSOCNN &#x0029 is employed to solve the Hamilton-Jacobi-Bellman equation &#x0028 HJBE &#x0029 more efficiently. Then, a data-based FTC scheme, which consists of the NN identifier and the fault compensator, is proposed to achieve actuator fault tolerance. The stability of the closed-loop system under actuator faults is guaranteed by the Lyapunov stability theorem. Finally, simulations are provided to demonstrate the effectiveness of the developed method.

Graph representations offer powerful and intuitive ways to describe data in a multitude of application domains. Here, we consider stochastic processes generating graphs and propose a methodology for detecting changes in stationarity of such processes. The methodology is general and considers a process generating attributed graphs with a variable number of vertices/edges, without the need to assume a one-to-one correspondence between vertices at different time steps. The methodology acts by embedding every graph of the stream into a vector domain, where a conventional multivariate change detection procedure can be easily applied. We ground the soundness of our proposal by proving several theoretical results. In addition, we provide a specific implementation of the methodology and evaluate its effectiveness on several detection problems involving attributed graphs representing biological molecules and drawings. Experimental results are contrasted with respect to suitable baseline methods, demonstrating the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Detecting frauds in credit card transactions is perhaps one of the best testbeds for computational intelligence algorithms. In fact, this problem involves a number of relevant challenges, namely: concept drift (customers’ habits evolve and fraudsters change their strategies over time), class imbalance (genuine transactions far outnumber frauds), and verification latency (only a small set of transactions are timely checked by investigators). However, the vast majority of learning algorithms that have been proposed for fraud detection rely on assumptions that hardly hold in a real-world fraud-detection system (FDS). This lack of realism concerns two main aspects: 1) the way and timing with which supervised information is provided and 2) the measures used to assess fraud-detection performance. This paper has three major contributions. First, we propose, with the help of our industrial partner, a formalization of the fraud-detection problem that realistically describes the operating conditions of FDSs that everyday analyze massive streams of credit card transactions. We also illustrate the most appropriate performance measures to be used for fraud-detection purposes. Second, we design and assess a novel learning strategy that effectively addresses class imbalance, concept drift, and verification latency. Third, in our experiments, we demonstrate the impact of class unbalance and concept drift in a real-world data stream containing more than 75 million transactions, authorized over a time window of three years.

It is a widely accepted fact that the computational capability of recurrent neural networks (RNNs) is maximized on the so-called “edge of criticality.” Once the network operates in this configuration, it performs efficiently on a specific application both in terms of: 1) low prediction error and 2) high short-term memory capacity. Since the behavior of recurrent networks is strongly influenced by the particular input signal driving the dynamics, a universal, application-independent method for determining the edge of criticality is still missing. In this paper, we aim at addressing this issue by proposing a theoretically motivated, unsupervised method based on Fisher information for determining the edge of criticality in RNNs. It is proved that Fisher information is maximized for (finite-size) systems operating in such critical regions. However, Fisher information is notoriously difficult to compute and requires the analytic form of the probability density function ruling the system behavior. This paper takes advantage of a recently developed nonparametric estimator of the Fisher information matrix and provides a method to determine the critical region of echo state networks (ESNs), a particular class of recurrent networks. The considered control parameters, which indirectly affect the ESN performance, are explored to identify those configurations lying on the edge of criticality and, as such, maximizing Fisher information and computational performance. Experimental results on benchmarks and real-world data demonstrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

The ability to detect online changes in stationarity or time variance in a data stream is a hot research topic with striking implications. In this paper, we propose a novel probability density function-free change detection test, which is based on the least squares density-difference estimation method and operates online on multidimensional inputs. The test does not require any assumption about the underlying data distribution, and is able to operate immediately after having been configured by adopting a reservoir sampling mechanism. Thresholds requested to detect a change are automatically derived once a false positive rate is set by the application designer. Comprehensive experiments validate the effectiveness in detection of the proposed method both in terms of detection promptness and accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we elaborate over the well-known interpretability issue in echo-state networks (ESNs). The idea is to investigate the dynamics of reservoir neurons with time-series analysis techniques developed in complex systems research. Notably, we analyze time series of neuron activations with recurrence plots (RPs) and recurrence quantification analysis (RQA), which permit to visualize and characterize high-dimensional dynamical systems. We show that this approach is useful in a number of ways. First, the 2-D representation offered by RPs provides a visualization of the high-dimensional reservoir dynamics. Our results suggest that, if the network is stable, reservoir and input generate similar line patterns in the respective RPs. Conversely, as the ESN becomes unstable, the patterns in the RP of the reservoir change. As a second result, we show that an RQA measure, called $L_\mathrm {max}$ , is highly correlated with the well-established maximal local Lyapunov exponent. This suggests that complexity measures based on RP diagonal lines distribution can quantify network stability. Finally, our analysis shows that all RQA measures fluctuate on the proximity of the so-called edge of stability, where an ESN typically achieves maximum computational capability. We leverage on this property to determine the edge of stability and show that our criterion is more accurate than two well-known counterparts, both based on the Jacobian matrix of the reservoir. Therefore, we claim that RPs and RQA-based analyses are valuable tools to design an ESN, given a specific problem.

One-class classifiers offer valuable tools to assess the presence of outliers in data. In this paper, we propose a design methodology for one-class classifiers based on entropic spanning graphs. Our approach also takes into account the possibility to process nonnumeric data by means of an embedding procedure. The spanning graph is learned on the embedded input data, and the outcoming partition of vertices defines the classifier. The final partition is derived by exploiting a criterion based on mutual information minimization. Here, we compute the mutual information by using a convenient formulation provided in terms of the $\alpha $ -Jensen difference. Once training is completed, in order to associate a confidence level with the classifier decision, a graph-based fuzzy model is constructed. The fuzzification process is based only on topological information of the vertices of the entropic spanning graph. As such, the proposed one-class classifier is suitable also for data characterized by complex geometric structures. We provide experiments on well-known benchmarks containing both feature vectors and labeled graphs. In addition, we apply the method to the protein solubility recognition problem by considering several representations for the input samples. Experimental results demonstrate the effectiveness and versatility of the proposed method with respect to other state-of-the-art approaches. [ABSTRACT FROM PUBLISHER]

The paper proposes an effective change detection test for online monitoring data streams by inspecting the least squares density difference (LSDD) features extracted from two non-overlapped windows. The first window contains samples associated with the pre-change probability distribution function (pdf) and the second one with the post-change one (that differs from the former if a change in stationarity occurs). This method can detect changes by also controlling the false positive rate. However, since the window sizes is fixed after the test has been configured (it has to be small to reduce the execution time), the method may fail to detect changes with small magnitude which need more samples to reach the requested level of confidence. In this paper, we extend our work to the Big Data framework by applying the Kolmogorov-Smirnov test (KS test) to infer changes. Experiments show that the proposed method is effective in detecting changes.

We present hierarchical change-detection tests (HCDTs), as effective online algorithms for detecting changes in datastreams. HCDTs are characterized by a hierarchical architecture composed of a detection layer and a validation layer. The detection layer steadily analyzes the input datastream by means of an online, sequential CDT, which operates as a low-complexity trigger that promptly detects possible changes in the process generating the data. The validation layer is activated when the detection one reveals a change, and performs an offline, more sophisticated analysis on recently acquired data to reduce false alarms. Our experiments show that, when the process generating the datastream is unknown, as it is mostly the case in the real world, HCDTs achieve a far more advantageous tradeoff between false-positive rate and detection delay than their single-layered, more traditional counterpart. Moreover, the successful interplay between the two layers permits HCDTs to automatically reconfigure after having detected and validated a change. Thus, HCDTs are able to reveal further departures from the postchange state of the data-generating process. [ABSTRACT FROM AUTHOR]

The lack of clearly noticeable forerunners, the need to acquire large amounts of data coming from sensors sampled at middle/high rates, and the potentially catastrophic effects of the physical phenomenon under monitoring make rock-collapse forecasting a challenging and valuable environmental monitoring application. In this paper, we describe a rock-collapse forecasting system based on a hybrid wireless-wired architecture, where a set of acquisition units is connected through a fieldbus to a base station, which collects and wirelessly transmits acquired measurements to a remote control room. The main features of the proposed rock-collapse forecasting system are the ability to process data sampled at high-frequency rates locally and in real time, the run-time remote reconfigurability of the forecasting application, and the possibility to distribute intelligent processing through the system layers to balance energy consumption and the application performance. Five instances of the proposed system have been deployed along the Swiss-Italian Alps.

Cognitive fault diagnosis systems differentiate from more traditional solutions by providing online strategies to create and update the fault-free and the faulty classes directly from incoming data. This aspect is of paramount relevance within the big data framework, since measurements are there immediately processed to detect and identify the upsurge of potential faults. This paper introduces a novel cognitive fault diagnosis framework for processes described by nonlinear dynamic systems that inspects changes in the existing relationships among sensors. The proposed framework is based on an evolving clustering algorithm that operates in the parameter space of time invariant linear models approximating such relationships. During the operational life, parameter vectors associated with models thought not to belong to the nominal state are either labeled as outlier or fault. New classes of faults, here considered to propagate to the model parameters according to an abrupt profile, are created online as they appear. At the same time, existing classes can merge, depending on the information content carried by incoming data. [ABSTRACT FROM AUTHOR]

This paper introduces a novel cognitive fault diagnosis system (FDS) for distributed sensor networks that takes advantage of spatial and temporal relationships among sensors. The proposed FDS relies on a suitable functional graph representation of the network and a two-layer hierarchical architecture designed to promptly detect and isolate faults. The lower processing layer exploits a novel change detection test (CDT) based on hidden Markov models (HMMs) configured to detect variations in the relationships between couples of sensors. HMMs work in the parameter space of linear time-invariant dynamic systems, approximating, over time, the relationship between two sensors; changes in the approximating model are detected by inspecting the HMM likelihood. Information provided by the CDT layer is then passed to the cognitive one, which, by exploiting the graph representation of the network, aggregates information to discriminate among faults, changes in the environment, and false positives induced by the model bias of the HMMs. [ABSTRACT FROM AUTHOR]

The success of wireless sensor networks and their pervasive use is somehow constrained by energy supply which, generally provided by batteries, is a finite resource. Energy harvesting mechanisms must hence be taken into account to grant a long time operational life, with solar energy being the most interesting one in outdoor deployments due to its relatively high power density. In this paper we propose a low-power maximum power point tracker (MPPT) circuit specifically designed for wireless sensor nodes (hence effective, flexible, low cost and power-aware), i.e., a power transferring circuit for optimally conveying solar energy into rechargeable batteries even in not optimal weather conditions. High efficiency is granted by an ad hoc adaptive algorithm which, by keeping the MPPT electronics in its optimal working point, maximizes energy transfer from the solar cell to the batteries. The suggested implementation is particularly effective in critical weather conditions where traditional solutions do not work and is characterized by a flexible enough design for immediately hosting, in a plug in fashion, different solar panels and battery typologies. [ABSTRACT FROM AUTHOR]

This paper shows the effectiveness of using neural paradigms to filter, enhance and restore radar images of ships sailing in low visibility conditions. The task, to be accomplished in real time, is inserted in a processing chain which provides the mobile trajectory. Adaptive vector quantization techniques (supervised and unsupervised) and back-propagation neural algorithms are considered. The final optimized architecture contains a small set of processing modules comprising, at most, two pipelined neural convolvers (an enhancing filter and a classifier). Each neural-convolver mask is characterized by a symmetrical structure whose optimal coefficients have been determined via learning.

An introduction is presented in which the editor discusses various reports within the issue on topics including extraction approach for improving the performance of a detection algorithm, adaptive radial basis function neural network-based approach, and learning algorithms on synthetic datasets.