Activation functions in deep learning: A comprehensive survey and benchmark

SR Dubey, SK Singh, BB Chaudhuri - Neurocomputing, 2022‏ - Elsevier
Neural networks have shown tremendous growth in recent years to solve numerous
problems. Various types of neural networks have been introduced to deal with different types …

A novel deep learning method for intelligent fault diagnosis of rotating machinery based on improved CNN-SVM and multichannel data fusion

W Gong, H Chen, Z Zhang, M Zhang, R Wang, C Guan… - Sensors, 2019‏ - mdpi.com
Intelligent fault diagnosis methods based on deep learning becomes a research hotspot in
the fault diagnosis field. Automatically and accurately identifying the incipient micro-fault of …

Modelling of soil moisture retention curve using machine learning techniques: Artificial and deep neural networks vs support vector regression models

KO Achieng - Computers & Geosciences, 2019‏ - Elsevier
Soil water retention curve (SWRC) is of fundamental importance in analyzing both flow and
contaminant transport in the vadose zone. Field and/or laboratory-based measurements of …

Explainable machine learning rapid approach to evaluate coal ash content based on X-ray fluorescence

Z Wen, H Liu, M Zhou, C Liu, C Zhou - Fuel, 2023‏ - Elsevier
As one of the most important indexes of coal quality, accurate and rapid prediction of ash
content is urgent and important significance for the coal processing industry. In this work …

[HTML][HTML] Combining computational fluid dynamics and neural networks to characterize microclimate extremes: Learning the complex interactions between meso …

K Javanroodi, VM Nik, MG Giometto… - Science of The Total …, 2022‏ - Elsevier
The urban form and extreme microclimate events can have an important impact on the
energy performance of buildings, urban comfort and human health. State-of-the-art building …

[HTML][HTML] Enhancing neural network classification using fractional-order activation functions

M Kumar, U Mehta, G Cirrincione - AI Open, 2024‏ - Elsevier
In this paper, a series of novel activation functions is presented, which is derived using the
improved Riemann–Liouville conformable fractional derivative (RL CFD). This study …

A comparison between sentinel-2 and landsat 8 OLI satellite images for soil salinity distribution map** using a deep learning convolutional neural network

M Kazemi Garajeh, T Blaschke… - Canadian Journal of …, 2022‏ - Taylor & Francis
In this paper, we aim to compare the suitability of Sentinel-2 and Landsat 8 OLI images for
detecting and map** soil salinity distribution (SSD) using a deep learning convolutional …

Sentinel-1 backscatter and interferometric coherence for soil moisture retrieval in Winter wheat fields within a semiarid South-Mediterranean climate: Machine learning …

J Ezzahar, A Chehbouni, N Ouaadi… - IEEE Journal of …, 2023‏ - ieeexplore.ieee.org
This work aims to assess the effectiveness of machine learning (ML) algorithms and
semiempirical models for surface soil moisture (SSM) retrieval by exploring the Sentinel-1 …

Fault diagnosis of electric submersible pumps using a three‐stage multiscale feature transformation combined with CNN–SVM

J Chen, W Li, P Yang, S Li, B Chen - Energy Technology, 2023‏ - Wiley Online Library
A convolutional neural network support vector machine (CNN–SVM) method based on
multichannel feature fusion is used for progressive fault diagnosis of offshore oil and gas …

[HTML][HTML] ReLU surrogates in mixed-integer MPC for irrigation scheduling

BT Agyeman, J Liu, SL Shah - Chemical Engineering Research and Design, 2024‏ - Elsevier
Efficient water management in agriculture is important for mitigating the growing freshwater
scarcity crisis. Mixed-integer Model Predictive Control (MPC) has emerged as an effective …