Global trading is undergoing significant changes, necessitating modifications to the trading strategies. This study presents a newly developed cloud-based trading strategy that uses Amazon Web Services (AWS), machine ...
详细信息
This study examines the impact of environmental, social, and governance (ESG) factors on economic investment from a statistical perspective, aiming to develop a tested investment strategy that capitalizes on the conne...
详细信息
Distributed Control Systems (DCS) are deployed in power utilities as well as communication, transportation, and financial infrastructures. As demonstrated by power distribution grid failures, most recently in August o...
详细信息
Distributed Control Systems (DCS) are deployed in power utilities as well as communication, transportation, and financial infrastructures. As demonstrated by power distribution grid failures, most recently in August of 2003, designing for reliability is an important need. In addition to inherent design weaknesses, critical infrastructures are potential targets of cyber-terrorism and protecting critical infrastructures against terrorist attacks is a national priority. DCS security and survivability need increased attention. One of the Norwich University electrical and computerengineering courses that address these issues is EE411 Microcomputer Based Applications. EE411 is designed to give computer and electricalengineering students a capstone DCS design experience applying concepts covered in earlier courses. They are introduced to "SCAD A ville", a municipal water system emulator modeled after a typical municipal water distribution system. The concepts of safety instrumentation and networking are introduced using Allen Bradley programmable Logic Controllers (PLCs). Students come to understand the advantages and disadvantages of ladder logic code for digital controller reliability. In designing Distributed Control Systems that make any connection to the outside world, the system must withstand attack from disgruntled employees, hackers or cyber terrorists. The system must function well even when the attacker breaks through the security barrier. In the EE411 course, the concepts of redundancy, robustness, and resilience are developed and reinforced in the laboratories.
This work is about the use of a microcomputer network as a parallel processing environment. In order to allow the communication, the synchronization and the distribution of the tasks among processes, the PVM (Parallel...
详细信息
We have recently proposed a Distributed Reconfigurable Active SSD computation platform (RASSD) for processing data-intensive applications at the storage node itself, without having to move data over slow networks. In ...
详细信息
In optoelectronics, achieving electrical reconfigurability is crucial as it enables the encoding, decoding, manipulating, and processing of information carried by light. In recent years, two-dimensional van der Waals ...
详细信息
作者:
Atkins, Daniel E.Ong, Shau-ChiProgram in Computer
Information and Control Engineering the Systems Engineering Laboratory of the Department of Electrical and Computer Engineering University of Michigan Ann Arbor MI 48109 United States
Component and time complexity measures in terms of number of gates and gate delays, respectively, are derived for two multioperand adder structures: a tree of carry-save adders and a tree of carry-lookahead adders. Th...
详细信息
Cloud computing is increasingly becoming a desirable and foundational element in international enterprise computing. There are many companies which design, develop, and offer cloud technologies. However, cloud provide...
详细信息
In this paper, we apply General Order Statistics (GOS) theorem for the antenna selection in dual-hop amplify-forward fixed-gain relay transmission. The antenna selection is employed at multi-antenna relay terminal for...
详细信息
Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the a...
详细信息
Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d
暂无评论