IET Cyber-Physical Systems: Theory and Applications最新文献

Testing the visual field is a valuable diagnostic tool for identifying eye conditions such as cataract, glaucoma, and retinal disease. Its quick and straightforward testing process has become an essential component in our efforts to prevent blindness. Still, the device must be accessible to the general masses. This research has developed a machine learning model that can work with Edge devices like smartphones. As a result, it is opening the opportunity to integrate the disease-detecting model into multiple Edge devices to automate their operation. The authors intend to use convolutional neural network (CNN) and deep learning to deduce which optimisers have the best results when detecting cataracts from live photos of eyes. This is done by comparing different models and optimisers. Using these methods, a reliable model can be obtained that detects cataracts. The proposed TensorFlow Lite model constructed by combining CNN layers and Adam in this study is called Optimised Light Weight Sequential Deep Learning Model (SDLM). SDLM is trained using a smaller number of CNN layers and parameters, which gives SDLM its compatibility, fast execution time, and low memory requirements. The proposed Android app, I-Scan, uses SDLM in the form of TensorFlow Lite for demonstration of the model in Edge devices.

In recent years, cyber security-related studies in the power grid have drawn wide attention, with much focus on its detection, mainly for data injection type of attacks. The vulnerability of power components as a result of attack and their impact on generator dynamics have been largely ignored so far. With the aim of addressing some of these issues, the authors propose a novel approach using real-time sliding surface-based switching attack (SA) construction. This approach targets the circuit breaker, excitation system, and governor system of the generator. The vulnerability of these power components to cyber-physical attacks and assessment of their potential impact on the stability of generator are discussed. The study is presented to show the progression of cascading generator dynamics on account of single or multiple time instants of SA launched on these power components. The results are discussed according to criteria in terms of deviations in rotor speed of the generator and identify some of possible combinations of power components that are most critical to grid stability. The proposed study is implemented on standard IEEE 3-machine, 9-bus network in real-time digital simulator via transmission control protocol/internet protocol (TCP/IP) communication network established as cyber-physical system. The sliding surface-based SA algorithm developed in MATLAB is launched from another computer.

Given the short time intervals in which short-circuit faults occur in a power system, a certain time delay between the moment of a fault's inception in the system to the moment in which the fault is actually detected is introduced. In this small time margin, the high amplitudes of the fault current can deal significant damage to the power system. A technique to characterise different types of short circuit faults in a power system for real-time detection, namely AB, BC, CA, ABC, AG, BG and CG faults (and normal operation), is presented based on the geometry of the curve generated by the Clarke transform of the three-phase voltages of the power system. The process was conducted in real time using the HIL402 system and a Raspberry Pi 3, and all programming done in the Python programming language. It was concluded that the tested types of faults can be accurately characterised using the eigenvalues and eigenvectors of the matrix that characterises an ellipse associated with each fault: eigenvalues can be used to determine the fault inception distance and eigenvectors can be used to determine the type of fault that occurred. Next, the design of a machine learning model was done based on the previously mentioned characterisation technique. The model was embedded into a Raspberry Pi 3, thus enabling fault detection and classification in a base power system in real time. Finally, the accuracy of the model was tested under different measurement conditions, yielding satisfactory results for a selected set of conditions and overcoming the shortcomings presented in the current research, which do not perform detection and classification in real time.

A predictive queue management method is proposed for constrained congestion control in internet routers in the face of communication delays. The proposed method uses the queue and router models, input traffic rate, and queue length to precisely characterise the entire process. The model that has been built is then used to construct an optimal constrained active queue management (CAQM) strategy using the model predictive control method. Important factors, such as link capacity, Transmission Control Protocol (TCP) sessions, round-trip time, and a few others, have been selected and used to linearise the interconnection of TCP. Then, an efficient MPC-based structure to manage the CAQM in the face of unknown disturbances is designed. Simulations are used to validate the proposed method's effectiveness and robustness.

Dependency analysis can better help neural network to capture semantic features in sentences, so as to extract entity relation. Currently, hard pruning strategies and soft pruning strategies based on dependency tree structure coding have been proposed to balance beneficial additional information and adverse interference in extraction tasks. A new model based on graph convolutional networks, which uses a variety of representations describing dependency trees from different perspectives and combining these representations to obtain a better sentence representation for relation classification is proposed. A newly defined module is added, and this module uses the attention mechanism to capture deeper semantic features from the context representation as the global semantic features of the input text, thus helping the model to capture deeper semantic information at the sentence level for relational extraction tasks. In order to get more information about a given entity pair from the input sentence, the authors also model implicit co-references (references) to entities. This model can extract semantic features related to the relationship between entities from sentences to the maximum extent. The results show that the model in this paper achieves good results on SemEval2010-Task8 and KBP37 datasets.

Recent work has shown that deep reinforcement learning (DRL) is vulnerable to adversarial attacks, so that exploiting vulnerabilities in DRL systems through adversarial attack techniques has become a necessary prerequisite for building robust DRL systems. Compared to traditional deep learning systems, DRL systems are characterised by long sequential decisions rather than one-step decision, so attackers must perform multi-step attacks on them. To successfully attack a DRL system, the number of attacks must be minimised to avoid detecting by the victim agent and to ensure the effectiveness of the attack. Some selective attack methods proposed in recent researches, that is, attacking an agent at partial time steps, are not applicable to real-time attack scenarios, although they can avoid detecting by the victim agent. A real-time selective attack method that is applicable to environments with discrete action spaces is proposed. Firstly, the optimal attack threshold T for performing selective attacks in the environment Env is determined. Then, the observation states corresponding to when the value of the action preference function of the victim agent in multiple eposides exceeds the threshold T are added to the training set according to this threshold. Finally, a universal perturbation is generated based on this training set, and it is used to perform real-time selective attacks on the victim agent. Comparative experiments show that our attack method can perform real-time attacks while maintaining the attack effect and stealthiness.

Single-image dehazing is a highly challenging ill-posed task in the field of computer vision. To address this, a new image dehazing model with feature attention, named feature attention gated context aggregation network (FAGCA-Net), is proposed to tackle the issues of incomplete or over-dehazing caused by the original model's inability to handle non-uniform haze density distributions. A feature attention module that combines channel attention and spatial attention is introduced. Additionally, the authors propose a new extended attention convolutional block, which not only addresses the grid artefacts caused by the extended convolution but also provides added flexibility in handling different types of feature information. At the same time, in addition to the input image itself, incorporating the dark channel and edge channel of the image as the final input of the model is helpful for the model learning process. To demonstrate the robustness of the new model, it is applied to two completely different dehazing datasets, and it achieves significant dehazing performance improvement over the original model. Finally, to verify the effectiveness of the model in practical production processes, the authors apply it as an image preprocessing step to a set of UAV (Unmanned Aerial Vehicle) images of foreign objects. The result shows that the UAV images after being processed by FAGCA-Net for haze removal have a better impact on subsequent usage.

Cyberattacks on cyber-physical systems (CPS) have the potential to cause widespread disruption and affect the safety of millions of people. Machine learning can be an effective tool for detecting attacks on CPS, including the most stealthy types of attacks, known as covert channel attacks. In this study, the authors describe a novel hierarchical ensemble architecture for detecting covert channel attacks in CPS. Our proposed approach uses a combination of TCP payload entropy and network flows for feature engineering. Our approach achieves high detection performance, shortens the model training duration, and shows promise for effective detection of covert channel communications. This novel architecture closely mirrors the CPS attack stages in real-life, providing flexibility and adaptability in detecting new types of attacks.

The dimension of relevant text feature space and feature weight of substation main equipment defect information is high, so it is difficult to accurately select mining features. The Natural Language Processing (NLP) medium and short-term neural network model is used to realise the defect information text feature word segmentation in the log. After extracting the text features of defect information of main substation equipment with high categories to form the feature space; the TF-IDF algorithm is designed to calculate the importance weight of text keywords, judge the criticality of defect information text feature vocabulary, accurately locate defect information text features, and realise defect information text feature mining. Experiments show that the algorithm has high precision for specific word segmentation of massive substation main equipment log information.