Data communications within the smart power grid components are susceptible to cyberattacks due to the inter-connected nature of the grid and reliance on communication networks. Such cyberattacks can exploit the integr...
详细信息
ISBN:
(数字)9789464593617
ISBN:
(纸本)9798331519773
Data communications within the smart power grid components are susceptible to cyberattacks due to the inter-connected nature of the grid and reliance on communication networks. Such cyberattacks can exploit the integrity of the exchanged data and result in operational instability. Existing data-driven cyberattack detection systems (CDSs) are proposed in the literature but their effectiveness is only verified against one type of cyberattacks. In reality, a smart grid system could encounter more than one attack type at once. Thus, in this paper, we investigate the resilience of state-of-the-art data-driven CDSs against replay false data injection, adversarial evasion, and adversarial data poisoning attacks on a realistic IEEE 118-bus system model. It turns out that a convolutional recurrent graph autoencoder-based CDS offers an attack detection rate of 96 – 97.5%, which outperforms other machine learning and deep learning-based data-driven CDSs by 16 – 54% since it captures the recurrent and spatial aspects of the data without being trained on attack data.
We introduce cytoNet, a cloud-based tool to characterize cell populations from microscopy images. cytoNet quantifies spatial topology and functional relationships in cell communities using principles of network scienc...
详细信息
We introduce cytoNet, a cloud-based tool to characterize cell populations from microscopy images. cytoNet quantifies spatial topology and functional relationships in cell communities using principles of network science. Capturing multicellular dynamics through graph features, cytoNet also evaluates the effect of cell-cell interactions on individual cell phenotypes. We demonstrate cytoNet's capabilities in four case studies: 1) characterizing the temporal dynamics of neural progenitor cell communities during neural differentiation, 2) identifying communities of pain-sensing neurons in vivo, 3) capturing the effect of cell community on endothelial cell morphology, and 4) investigating the effect of laminin α4 on perivascular niches in adipose tissue. The analytical framework introduced here can be used to study the dynamics of complex cell communities in a quantitative manner, leading to a deeper understanding of environmental effects on cellular behavior. The versatile, cloud-based format of cytoNet makes the image analysis framework accessible to researchers across domains.
Barriers to the participation of distributed energy resources (DERs) in wholesale electricity markets have limited the use of DERs for power system security and resilience. In September 2020, the Federal Energy Regula...
Barriers to the participation of distributed energy resources (DERs) in wholesale electricity markets have limited the use of DERs for power system security and resilience. In September 2020, the Federal Energy Regulatory Commission (FERC) approved an order to reduce these barriers. FERC Order No. 2222 enables the participation of DER aggregators in wholesale electricity markets. DERs include renewable generation and technologies that support the integration of renewable generation by increasing grid flexibility and resilience. Requiring wholesale energy markets to allow DER aggregator participation provides a path for DERs to become competitive in these markets. As the contribution from aggregated DERs continues to increase, the aggregator's role in supporting grid security and resilience will become more critical. This paper reviews work that demonstrates how DER aggregators can provide resilience support through technical capabilities, operational strategies, and secure communication architectures. Socioeconomic influences and impacts of aggregators, including implications for social resilience, are presented. In surveying the current state-of-the-art across different but interconnected topics, we illustrate how aggregators can be power system participants that enhance grid security. There is no one-size-fits-all approach to enhancing resilience in a power grid that includes a growing cohort of DER aggregators, but there are many options for aggregators to contribute to a more resilient and secure power grid.
Stunting in toddlers is a chronic nutritional issue that affects the physical and cognitive development of children, with serious long-term consequences such as reduced cognitive function and an increased risk of chro...
详细信息
ISBN:
(数字)9798350379839
ISBN:
(纸本)9798350379846
Stunting in toddlers is a chronic nutritional issue that affects the physical and cognitive development of children, with serious long-term consequences such as reduced cognitive function and an increased risk of chronic diseases in adulthood. Therefore, early identification and prevention efforts for stunting are crucial. Classifying toddlers into categories of at-risk for stunting or not is essential to provide timely and appropriate interventions. This study employs data mining techniques using the decision tree algorithm to expedite the stunting detection process and improve the accuracy of nutritional status classification in children. The results indicate that the constructed decision tree model can classify children's nutritional status with an accuracy of 83.26%. The decision tree achieves high accuracy in classifying stunting in toddlers due to its ability to handle complex data and identify significant patterns within the data.
Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling. By di...
ISBN:
(纸本)9781713871088
Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling. By directly learning maps (operators) between infinite dimensional function spaces, these models are able to learn discretization invariant representations of target functions. A common approach is to represent such target functions as linear combinations of basis elements learned from data. However, there are simple scenarios where, even though the target functions form a low dimensional submanifold, a very large number of basis elements is needed for an accurate linear representation. Here we present NOMAD, a novel operator learning framework with a nonlinear decoder map capable of learning finite dimensional representations of nonlinear submanifolds in function spaces. We show this method is able to accurately learn low dimensional representations of solution manifolds to partial differential equations while outperforming linear models of larger size. Additionally, we compare to state-of-the-art operator learning methods on a complex fluid dynamics benchmark and achieve competitive performance with a significantly smaller model size and training cost.
We show, semi-analytically and numerically, how the relativistic accelerated motion of a waveguide's parallel plates induces fast mode conversion including reflection, similar to the temporal interface by sudden v...
详细信息
Synchronization is a widespread phenomenon observed across natural and artificial networked systems. It often manifests itself by clusters of units exhibiting coincident dynamics. These clusters are a direct consequen...
详细信息
The ability of robots to imitate human learning strategies-rapidly adapting to new tasks without large datasets-has garnered significant attention in meta-learning. Meta-reinforcement learning seeks to enhance robotic...
详细信息
ISBN:
(数字)9798331521554
ISBN:
(纸本)9798331521561
The ability of robots to imitate human learning strategies-rapidly adapting to new tasks without large datasets-has garnered significant attention in meta-learning. Meta-reinforcement learning seeks to enhance robotic agent flexibility across diverse tasks and contexts, offering promise where single-task learning often fails. Despite advancements like multi-task diffusion models and task-weighted optimization mechanisms, effectively training tasks with varying complexities simultaneously remains a major challenge. This paper introduces a novel meta-reinforcement learning method that addresses this issue by clustering the training tasks of robotic arms based on semantic and trajectory similarities, while leveraging adaptive learning rates and task-specific weights proposed by the multitask optimization techniques. Our approach, TEAM, emphasizes performance-driven semantic clustering, optimizing based on robotic task similarity, complexity, and convergence objectives. We also integrate fast adaptive and multi-task optimization of the diffusion model to enhance computational efficiency and adaptability. More specifically, we introduce a cluster-specific optimization technique, using specialized parameters for each group to allow more refined task handling. The experimental validation demonstrates the effectiveness of this scalable method in improving performance, adaptability, and efficiency in real-world, heterogeneous robotic tasks, further advancing robotic computing in meta-reinforcement learning.
In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is sl...
详细信息
The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utiliz...
详细信息
暂无评论