A deep learning method with wrapper based feature extraction for wireless intrusion detection system

SM Kasongo, Y Sun - Computers & Security, 2020 - Elsevier
In the past decade, wired and wireless computer networks have substantially evolved
because of the rapid development of technologies such as the Internet of Things (IoT) …

ReLTanh: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis

X Wang, Y Qin, Y Wang, S **ang, H Chen - Neurocomputing, 2019 - Elsevier
Tanh is a sigmoidal activation function that suffers from vanishing gradient problem, so
researchers have proposed some alternative functions including rectified linear unit (ReLU) …

Models for battery health assessment: a comparative evaluation

E Vasta, T Scimone, G Nobile, O Eberhardt, D Dugo… - Energies, 2023 - mdpi.com
Considering the importance of lithium-ion (Li-ion) batteries and the attention that the study of
their degradation deserves, this work provides a review of the most important battery state of …

Bitcoin technical trading with artificial neural network

M Nakano, A Takahashi, S Takahashi - Physica A: Statistical Mechanics …, 2018 - Elsevier
This paper explores Bitcoin intraday technical trading based on artificial neural networks for
the return prediction. In particular, our deep learning method successfully discovers trading …

A survey on activation functions and their relation with xavier and he normal initialization

L Datta - arxiv preprint arxiv:2004.06632, 2020 - arxiv.org
In artificial neural network, the activation function and the weight initialization method play
important roles in training and performance of a neural network. The question arises is what …

A comparative analysis of machine/deep learning models for parking space availability prediction

FM Awan, Y Saleem, R Minerva, N Crespi - Sensors, 2020 - mdpi.com
Machine/Deep Learning (ML/DL) techniques have been applied to large data sets in order
to extract relevant information and for making predictions. The performance and the …

Blockchain-enabled Internet of Vehicles with cooperative positioning: A deep neural network approach

Y Song, Y Fu, FR Yu, L Zhou - IEEE Internet of Things Journal, 2020 - ieeexplore.ieee.org
Although vehicular global positioning system (GPS) has been widely applied in many traffic
scenarios, it is far from achieving lane-level positioning due to its low accuracy. Existing …

Detecting quantum attacks: A machine learning based defense strategy for practical continuous-variable quantum key distribution

Y Mao, W Huang, H Zhong, Y Wang, H Qin… - New Journal of …, 2020 - iopscience.iop.org
The practical security of a continuous-variable quantum key distribution (CVQKD) system is
compromised by various attack strategies. The existing countermeasures against these …

Effective activation functions for homomorphic evaluation of deep neural networks

S Obla, X Gong, A Aloufi, P Hu, D Takabi - IEEE access, 2020 - ieeexplore.ieee.org
CryptoNets and subsequent work have demonstrated the capability of homomorphic
encryption (HE) in the applications of private artificial intelligence (AI). In convolutional …

Deep learning for classification of the chemical composition of particle defects on semiconductor wafers

J O'Leary, K Sawlani, A Mesbah - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Manual classification of particle defects on semiconductor wafers is labor-intensive, which
leads to slow solutions and longer learning curves on product failures while being prone to …