Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks

V Kunc, J Kléma - arXiv preprint arXiv:2402.09092, 2024 - arxiv.org
Neural networks have proven to be a highly effective tool for solving complex problems in
many areas of life. Recently, their importance and practical usability have further been …

A novel optimized parametric hyperbolic tangent swish activation function for 1D-CNN: application of sensor-based human activity recognition and anomaly detection

S Ankalaki, MN Thippeswamy - Multimedia Tools and Applications, 2023 - Springer
Human activity recognition (HAR) and abnormal/anomaly detection have significant
applications for health monitoring in a smart environment. Abnormal/anomaly prediction …

Multifeedstock and multiproduct process design using neural network surrogate flexibility constraints

Y Luo, M Ierapetritou - Industrial & Engineering Chemistry …, 2023 - ACS Publications
Biorefineries are designed to utilize a combination of various technologies to transform
biomass derived raw materials into different value-added products. This strategy has been …

[HTML][HTML] An improved machine learning approach to estimate hemicellulose, cellulose, and lignin in biomass

F Kartal, U Özveren - Carbohydrate Polymer Technologies and Applications, 2021 - Elsevier
Biomass consists of predominantly a biochemical mixture of three major lignocellulosic
components: hemicellulose, cellulose, and lignin. The amounts of these three major …

Incorporating stock prices and text for stock movement prediction based on information fusion

Q Zhang, Y Zhang, F Bao, Y Liu, C Zhang… - Engineering Applications of …, 2024 - Elsevier
Forecasting stock market via historical financial data is an important issue for market
participants because even if the prediction accuracy is only slightly improved, better trading …

Voice activity detection optimized by adaptive attention span transformer

W Mu, B Liu - IEEE Access, 2023 - ieeexplore.ieee.org
Voice Activity Detection (VAD) is a widely used technique for separating vocal regions from
audio signals, with applications in voice language coding, noise reduction, and other …

MobileSAM-Track: Lightweight One-Shot Tracking and Segmentation of Small Objects on Edge Devices

Y Liu, Y Zhao, X Zhang, X Wang, C Lian, J Li, P Shan… - Remote Sensing, 2023 - mdpi.com
Tracking and segmenting small targets in remote sensing videos on edge devices carries
significant engineering implications. However, many semi-supervised video object …

Novel technique for the preparation and analysis of powder-based polished sections by automated optical mineralogy: Part 2–Use of deep learning approach for …

B De Castro, M Benzaazoua, S Roychowdhury… - Minerals …, 2024 - Elsevier
Automated reflected light optical microscopy represents an alternative and affordable
technique compared to automated scanning electron microscopy for quantitative …

Detection and identification of fish skin health status referring to four common diseases based on improved YOLOv4 Model

G Yu, J Zhang, A Chen, R Wan - Fishes, 2023 - mdpi.com
A primary problem affecting the sustainable development of aquaculture is fish skin
diseases. In order to prevent the outbreak of fish diseases and to provide prompt treatment …

Revisiting tensor basis neural network for Reynolds stress modeling: Application to plane channel and square duct flows

J Cai, PE Angeli, JM Martinez, G Damblin, D Lucor - Computers & Fluids, 2024 - Elsevier
Recent advances in computing power devoted to Computational Fluid Dynamics (CFD)
have opened up a new avenue for addressing the turbulence closure problem through …