A New Camera Calibration Based on Neural Network with Tunable Activation Function in Intelligent Space

Yuan, Mingxin; Hu, Haixiu; Jiang, Yafeng; Hang, Sheng

doi:10.1109/iscid.2013.99

Cited by 6 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 18th to 21th functions are the Saturated, the hyperbolic secant (Sech), and two modified sigmoidals labeled as Sigmoidalm and Sigmoidalm2 [3]. The tunable activation function proposed by Yuan et al and labeled as Sigt is the 22th function [27]. Next is a skewed-sig derivative activation function proposed by Chandra et al…”

Section: Function Derivative Function Wavementioning

confidence: 99%

Improvement of the performance analysis of activation functions based on DLLSTM classifiers on Human Activity Recognition for classification

badry

Bedair

Atallah

et al. 2023

SVU-International Journal of Engineering Sciences and Applicati

View full text Add to dashboard Cite

Human activity recognition techniques have achieved significant advancements in recent years. However, the performance of the generalization model may be hampered by the methods' heavy reliance on human feature extraction. Deep learning methods are becoming more and more effective, which has led to a lot of interest in employing these approaches to understand human behaviors in mobile and wearable computing settings. In place of the conventional hyperbolic tangent (tanh) activation function for human activity recognition, which can be applied in a variety of applications, in this study, the main part of LSTM neural networks is developed by employing 26 state functions to suggest Deep Learning Long Short-Term Memory (DLLSTM) classifiers. In LSTM network units, the sigmoid and tanh functions are often used as activation functions. The vanishing gradient issue that RNNs encounter can be effectively solved by LSTM networks. The effectiveness of the suggested DLLSTM classifiers for classification tasks was investigated using three different deep learning optimization techniques. The simulation results show that the suggested classifiers, which utilize the Modified -Elliott, Gaussian, and wave as DLLSTM classifiers, outperform the tanh classifier by getting a perfect accuracy rate of 99.92%, 99.5%, and 99.95% as opposed to their 96.4%, respectively.

show abstract

Section: Function Derivative Function Wavementioning

confidence: 99%

Improvement of the performance analysis of activation functions based on DLLSTM classifiers on Human Activity Recognition for classification

badry

Bedair

Atallah

et al. 2023

SVU-International Journal of Engineering Sciences and Applicati

View full text Add to dashboard Cite

show abstract

“…An ANN is a computational model that mimics a biological neural network and consists of multiple interconnected neurons (or nodes) whose weights form a hierarchical structure 14 – 16 ANNs are widely used in the field of machine learning and artificial intelligence due to their ability of learning the relationship between inputs and outputs with large amount of data training. Using ANNs, we can automatically learn patterns on charge coupled device (CCD) and regularities in the input data and reconstruct the spectrum by forming a global and unique neural network without additional optimization.…”

Section: Introductionmentioning

confidence: 99%

Optimization of disorder dispersion spectrometer using artificial neural networks

Zhao

Zhang

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

.We propose an approach to reconstruct spectrum using artificial neural networks (ANNs) instead of directly solving a matrix equation using calibration coefficients. ANNs are particularly effective in reconstructing spectra in noise environment by learning the relationship between inputs and outputs with large amount of data training. There are several different training methods for ANNs. Compared with scaled conjugate gradient algorithm and Levenberg–Marquardt algorithm, Bayesian regularization (BR) algorithm is demonstrated to be a better training algorithm for spectral reconstruction. We also compare the spectral reconstruction of BR algorithm and that of the traditional algorithms. Experimental results indicate that the spectral reconstruction of BR algorithm is nearly in line with that measured by a commercial spectrometer. Obvious deviations are occurred in the spectral reconstruction of the traditional algorithms due to inevitable background noise, rounding errors, and temperature variations. Therefore, spectral reconstruction using ANNs with a train method of BR algorithm is a more suitable choice for the disorder dispersion spectrometer.

show abstract

A comparative performance analysis of different activation functions in LSTM networks for classification

Farzad

Mashayekhi

Hassanpour

2017

Neural Comput & Applic

107

View full text Add to dashboard Cite

A New Camera Calibration Based on Neural Network with Tunable Activation Function in Intelligent Space

Cited by 6 publications

References 3 publications

Improvement of the performance analysis of activation functions based on DLLSTM classifiers on Human Activity Recognition for classification

Improvement of the performance analysis of activation functions based on DLLSTM classifiers on Human Activity Recognition for classification

Optimization of disorder dispersion spectrometer using artificial neural networks

A comparative performance analysis of different activation functions in LSTM networks for classification

Contact Info

Product

Resources

About