Power system event identification based on deep neural network with information loading

J Shi, B Foggo, N Yu - IEEE Transactions on Power Systems, 2021 - ieeexplore.ieee.org
Online power system event identification and classification are crucial to enhancing the
reliability of transmission systems. In this paper, we develop a deep neural network (DNN) …

Improving supervised phase identification through the theory of information losses

B Foggo, N Yu - IEEE Transactions on Smart Grid, 2019 - ieeexplore.ieee.org
This paper considers the problem of Phase Identification in power distribution systems. In
particular, it focuses on improving supervised learning accuracies by focusing on exploiting …

Effects of nonlinearity and network architecture on the performance of supervised neural networks

N Kulathunga, NR Ranasinghe, D Vrinceanu… - Algorithms, 2021 - mdpi.com
The nonlinearity of activation functions used in deep learning models is crucial for the
success of predictive models. Several simple nonlinear functions, including Rectified Linear …

Adversarial attacks on deep neural network-based power system event classification models

Y Cheng, K Yamashita, N Yu - 2022 IEEE PES Innovative Smart …, 2022 - ieeexplore.ieee.org
Online event classification is essential to strengthening the reliability of the power
transmission system. Recently, deep learning based methods have achieved great success …

On the maximum mutual information capacity of neural architectures

B Foggo, N Yu - arxiv preprint arxiv:2006.06037, 2020 - arxiv.org
We derive the closed-form expression of the maximum mutual information-the maximum
value of $ I (X; Z) $ obtainable via training-for a broad family of neural network architectures …

Analyzing data selection techniques with tools from the theory of information losses

B Foggo, N Yu - 2021 IEEE International Conference on Big …, 2021 - ieeexplore.ieee.org
In this paper, we present and illustrate some new tools for rigorously analyzing training data
selection methods. These tools focus on the information theoretic losses that occur when …

[BUKU][B] Intelligent Control and Data-Driven Algorithms for Critical Infrastructure Systems

J Shi - 2021 - search.proquest.com
The rapid development of computing devices and artificial intelligence (AI) in recent
decades have dramatically reshaped the ecosystem of critical infrastructure systems …

[BUKU][B] Information Losses in Neural Classifiers With Applications to Training Data Selection Strategies and Cyber Physical Systems

BJ Foggo - 2019 - search.proquest.com
This dissertation considers the subject of information losses arising from finite datasets used
in the training of neural classifiers. It proves a relationship between such losses and the …