Smart grid is an emerging system providing many benefits in digitizing the traditional power distribution systems. However, the added benefits of digitization and the use of the Internet of Things (IoT) technologies in smart grids also poses threats to its reliable continuous operation due to cyberattacks. Cyber–physical smart grid systems must be secured against increasing security threats and attacks. The most widely studied attacks in smart grids are false data injection attacks (FDIA), denial of service, distributed denial of service (DDoS), and spoofing attacks. These cyberattacks can jeopardize the smooth operation of a smart grid and result in considerable economic losses, equipment damages, and malicious control. This paper focuses on providing an extensive survey on defense mechanisms that can be used to detect these types of cyberattacks and mitigate the associated risks. The future research directions are also provided in the paper for efficient detection and prevention of such cyberattacks.
Many cloud providers offer very high precision services to exploit Optical Character Recognition (OCR). However, there is no provider offers Tifinagh Optical Character Recognition (OCR) as Web Services. Several works have been proposed to build powerful Tifinagh OCR. Unfortunately, there is no one developed as a Web Service. In this paper, we present a new architecture of Tifinagh Handwriting Recognition as a web service based on a deep learning model via Google Colab. For the implementation of our proposal, we used the new version of the TensorFlow library and a very large database of Tifinagh characters composed of 60,000 images from the Mohammed Vth University in Rabat. Experimental results show that the TensorFlow library based on a Tensor processing unit constitutes a very promising framework for developing fast and very precise Tifinagh OCR web services. The results show that our method based on convolutional neural network outperforms existing methods based on support vector machines and extreme learning machine.
Fuel cell technology has been rapidly developed in the last decade owing to its clean characteristic and high efficiency. Proton exchange membrane fuel cells (PEMFCs) are increasingly used in transportation applications and small stationary applications; however, the cost and the unsatisfying durability of the PEMFC stack have limited their successful commercialization and market penetration. In recent years, thanks to the availability and the quality of emerging data of PEMFCs, digitization is happening to offer possibilities to increase the productivity and the flexibility in fuel cell applications. Therefore, it is crucial to clarify the potential of digitization measures, how and where they can be applied, and their benefits. This paper focuses on the degradation performance of the PEMFC stacks and develops a data-driven intelligent method to predict both the short-term and long-term degradation. The dilated convolutional neural network is for the first time applied for predicting the time-dependent fuel cell performance and is proved to be more efficient than other recurrent networks. To deal with the long-term performance uncertainty, a conditional neural network is proposed. Results have shown that the proposed method can predict not only the degradation tendency, but also contain the degradation behaviour dynamics.
Many machine learning-based methods have been widely applied to Coronary Artery Disease (CAD) and are achieving high accuracy. However, they are black-box methods that are unable to explain the reasons behind the diagnosis. The trade-off between accuracy and interpretability of diagnosis models is important, especially for human disease. This work aims to propose an approach for generating rule-based models for CAD diagnosis. The classification rule generation is modeled as combinatorial optimization problem and it can be solved by means of metaheuristic algorithms. Swarm intelligence algorithms like Equilibrium Optimizer Algorithm (EOA) have demonstrated great performance in solving different optimization problems. Our present study comes up with a Novel Discrete Equilibrium Optimizer Algorithm (NDEOA) for the classification rule generation from training CAD dataset. The proposed NDEOA is a discrete version of EOA, which use a discrete encoding of a particle for representing a classification rule; new discrete operators are also defined for the particle’s position update equation to adapt real operators to discrete space. To evaluate the proposed approach, the real world Z-Alizadeh Sani dataset has been employed. The proposed approach generate a diagnosis model composed of 17 rules, among them, five rules for the class “Normal” and 12 rules for the class “CAD”. In comparison to nine black-box and eight white-box state-of-the-art approaches, the results show that the generated diagnosis model by the proposed approach is more accurate and more interpretable than all white-box models and are competitive to the black-box models. It achieved an overall accuracy, sensitivity and specificity of 93.54%, 80% and 100% respectively; which show that, the proposed approach can be successfully utilized to generate efficient rule-based CAD diagnosis models.
The grasshopper optimization algorithm is one of the recently population-based optimization techniques inspired by the behaviours of grasshoppers in nature. It is an efficient optimization algorithm and since demonstrates excellent performance in solving continuous problems, but cannot resolve directly binary optimization problems. Many optimization problems have been modelled as binary problems since their decision variables varied in binary space such as feature selection in data classification. The main goal of feature selection is to find a small size subset of feature from a sizeable original set of features that optimize the classification accuracy. In this paper, a new binary variant of the grasshopper optimization algorithm is proposed and used for the feature subset selection problem. This proposed new binary grasshopper optimization algorithm is tested and compared to five well-known swarm-based algorithms used in feature selection problem. All these algorithms are implemented and experimented assessed on twenty data sets with various sizes. The results demonstrated that the proposed approach could outperform the other tested methods.
Federated learning (FL) is a data-privacy-preserving, decentralized process that allows local edge devices of smart infrastructures to train a collaborative model independently while keeping data localized. FL algorithms, encompassing a well-structured average of the training parameters (e.g., the weights and biases resulting from training-based stochastic gradient descent variants), are subject to many challenges, namely expensive communication, systems heterogeneity, statistical heterogeneity, and privacy concerns. In this context, our paper targets the four aforementioned challenges while focusing on reducing communication and computational costs by involving recursive least squares (RLS) training rules. Accordingly, to the best of our knowledge, this is the first time that the RLS algorithm is modified to completely accommodate non-independent and identically distributed data (non-IID) for federated transfer learning (FTL). Furthermore, this paper also introduces a newly generated dataset capable of emulating such real conditions and of making data investigation available on ordinary commercial computers with quad-core microprocessors and less need for higher computing hardware. Applications of FTL-RLS on the generated data under different levels of complexity closely related to different levels of cardinality lead to a variety of conclusions supporting its performance for future uses.
The green conversion of proton exchange membrane fuel cells (PEMFCs) has received particular attention in both stationary and transportation applications. However, the poor durability of PEMFC represents a major problem that hampers its commercial application since dynamic operating conditions, including physical deterioration, have a serious impact on the cell performance. Under these circumstances, prognosis and health management (PHM) plays an important role in prolonging durability and preventing damage propagation via the accurate planning of a condition-based maintenance (CBM) schedule. In this specific topic, health deterioration modeling with deep learning (DL) is the widely studied representation learning tool due to its adaptation ability to rapid changes in data complexity and drift. In this context, the present paper proposes an investigation of further deeper representations by exposing DL models themselves to recurrent expansion with multiple repeats. Such a recurrent expansion of DL (REDL) allows new, more meaningful representations to be explored by repeatedly using generated feature maps and responses to create new robust models. The proposed REDL, which is designed to be an adaptive learning algorithm, is tested on a PEMFC deterioration dataset and compared to its deep learning baseline version under time series analysis. Using multiple numeric and visual metrics, the results support the REDL learning scheme by showing promising performances.
In modern Smart Grids (SGs) ruled by advanced computing and networking technologies, condition monitoring relies on secure cyberphysical connectivity. Due to this connection, a portion of transported data, containing confidential information, must be protected as it is vulnerable and subject to several cyber threats. SG cyberspace adversaries attempt to gain access through networking platforms to commit several criminal activities such as disrupting or malicious manipulation of whole electricity delivery process including generation, distribution, and even customer services such as billing, leading to serious damage, including financial losses and loss of reputation. Therefore, human awareness training and software technologies are necessary precautions to ensure the reliability of data traffic and power transmission. By exploring the available literature, it is undeniable that Machine Learning (ML) has become the latest in the timeline and one of the leading artificial intelligence technologies capable of detecting, identifying, and responding by mitigating adversary attacks in SGs. In this context, the main objective of this paper is to review different ML tools used in recent years for cyberattacks analysis in SGs. It also provides important guidelines on ML model selection as a global solution when building an attack predictive model. A detailed classification is therefore developed with respect to data security triad, i.e., Confidentiality, Integrity, and Availability (CIA) within different types of cyber threats, systems, and datasets. Furthermore, this review highlights the various encountered challenges, drawbacks, and possible solutions as future prospects for ML cybersecurity applications in SGs.
Reliability and security of power distribution and data traffic in smart grid (SG) are very important for industrial control systems (ICS). Indeed, SG cyber-physical connectivity is subject to several vulnerabilities that can damage or disrupt its process immunity via cyberthreats. Today's ICSs are experiencing highly complex data change and dynamism, increasing the complexity of detecting and mitigating cyberattacks. Subsequently, and since Machine Learning (ML) is widely studied in cybersecurity, the objectives of this paper are twofold. First, for algorithmic simplicity, a small-scale ML algorithm that attempts to reduce computational costs is proposed. The algorithm adopts a neural network with an augmented hidden layer (NAHL) to easily and efficiently accomplish the learning procedures. Second, to solve the data complexity problem regarding rapid change and dynamism, a label autoencoding approach is introduced for Embedding Labels in the NAHL (EL-NAHL) architecture to take advantage of labels propagation when separating data scatters. Furthermore, to provide a more realistic analysis by addressing real-world threat scenarios, a dataset of an electric traction substation used in the high-speed rail industry is adopted in this work. Compared to some existing algorithms and other previous works, the achieved results show that the proposed EL-NAHL architecture is effective even under massive dynamically changed and imbalanced data.
Prognosis and health management (PHM) are mandatory tasks for real-time monitoring of damage propagation and aging of operating systems during working conditions. More definitely, PHM simplifies conditional maintenance planning by assessing the actual state of health (SoH) through the level of aging indicators. In fact, an accurate estimate of SoH helps determine remaining useful life (RUL), which is the period between the present and the end of a system’s useful life. Traditional residue-based modeling approaches that rely on the interpretation of appropriate physical laws to simulate operating behaviors fail as the complexity of systems increases. Therefore, machine learning (ML) becomes an unquestionable alternative that employs the behavior of historical data to mimic a large number of SoHs under varying working conditions. In this context, the objective of this paper is twofold. First, to provide an overview of recent developments of RUL prediction while reviewing recent ML tools used for RUL prediction in different critical systems. Second, and more importantly, to ensure that the RUL prediction process from data acquisition to model building and evaluation is straightforward. This paper also provides step-by-step guidelines to help determine the appropriate solution for any specific type of driven data. This guide is followed by a classification of different types of ML tools to cover all the discussed cases. Ultimately, this review-based study uses these guidelines to determine learning model limitations, reconstruction challenges, and future prospects.
The Ki-67 proliferation index is an essential biomarker that helps pathologists to diagnose and select appropriate treatments. However, automatic evaluation of Ki-67 is difficult due to nuclei overlapping and complex variations in their properties. This paper proposes an integrated pipeline for accurate automatic counting of Ki-67, where the impact of nuclei separation techniques is highlighted. First, semantic segmentation is performed by combining the Squeez and Excitation Resnet and Unet algorithms to extract nuclei from the background. The extracted nuclei are then divided into overlapped and non-overlapped regions based on eight geometric and statistical features. A marker-based Watershed algorithm is subsequently proposed and applied only to the overlapped regions to separate nuclei. Finally, deep features are extracted from each nucleus patch using Resnet18 and classified into positive or negative by a random forest classifier. The proposed pipeline's performance is validated on a dataset from the Department of Pathology at Hôpital Nord Franche-Comté hospital.
This paper proposes a new approach for remaining useful life prediction that combines a bond graph, the Gaussian Mixture Model and similarity techniques to allow the use of both physical knowledge and the data available. The proposed method is based on the identification of relevant variables that carry information on degradation. To this end, the causal properties of the bond graph (BG) are first used to identify the relevant sensors through the fault observability. Then, a second stage of analysis based on statistical metrics is performed to reduce the number of sensors to only the ones carrying useful information for failure prognosis, thus, optimizing the data to be used in the prognosis phase. To generate data in the different system state, a simulator based on the developed BG is used. A Gaussian Mixture Model is then applied on the generated data for fault diagnosis and clustering. The Remaining Useful Life is estimated using a similarity technique. An application on a mechatronic system is considered for highlighting the effectiveness of the proposed approach.
In the last recent years, a large community of researchers and industrial practitioners has been attracted by combining different prognostics models as such strategy results in boosted accuracy and robust performance compared to the exploitation of single models. The present work is devoted to the investigation of three new fusion schemes for the remaining useful life forecast. These integrated frameworks are based on aggregating a set of Gaussian process regression models thanks to the Induced Ordered Weighted Averaging Operators. The combination procedure is built upon three proposed analytical weighting schemes including exponential, logarithmic and inverse functions. In addition, the uncertainty aspect is supported in this work, where the proposed functions are used to weighted average the variances released from competitive Gaussian process regression models. The training data are transformed into gradient values, which are adopted as new training data instead of the original observations. A lithium-ion battery data set is used as a benchmark to prove the efficiency of the proposed weighting schemes. The obtained results are promising and may provide some guidelines for future advances in performing robust fusion options to accurately estimate the remaining useful life.
Deep learning techniques have recently brought many improvements in the field of neural network training, especially for prognosis and health management. The success of such an intelligent health assessment model depends not only on the availability of labeled historical data but also on the careful samples selection. However, in real operating systems such as induction machines, which generally have a long reliable life, storing the entire operation history, including deterioration (i.e., bearings), will be very expensive and difficult to feed accurately into the training model. Other alternatives sequentially store samples that hold degradation patterns similar to real ones in damage behavior by imposing an accelerated deterioration. Labels lack and differences in distributions caused by the imposed deterioration will ultimately discriminate the training model and limit its knowledge capacity. In an attempt to overcome these drawbacks, a novel sequence-by-sequence deep learning algorithm able to expand the generalization capacity by transferring obtained knowledge from life cycles of similar systems is proposed. The new algorithm aims to determine health status by involving long short-term memory neural network as a primary component of adaptive learning to extract both health stage and health index inferences. Experimental validation performed using the PRONOSTIA induction machine bearing degradation datasets clearly proves the capacity and higher performance of the proposed deep learning knowledge transfer-based prognosis approach.
