Effects of Weight Initialization in a Feedforward Neural Network for Classification Using a Modified Genetic Algorithm

Nienhold, Dino; Schwab, Kilian; Dornberger, Rolf; Hanne, Thomas

doi:10.1109/iscbi.2015.9

Cited by 10 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is advisable to find an optimal weight matrix that performs better on a certain architecture for a complex lithofacies identification problem. Recently, a number of global optimization algorithms have been applied to optimize the initialization weights and biases of deep learning network (Nienhold et al ., 2015; Paul Ijjina and Krishna Mohan, 2016; Khalifa et al ., 2017; Yamasaki et al ., 2017; Wang et al ., 2018; Itano et al ., 2018; Li and Liu, 2019).…”

Section: Discussionmentioning

confidence: 99%

Semi‐supervised deep autoencoder for seismic facies classification

Liu

et al. 2021

Geophysical Prospecting

View full text Add to dashboard Cite

Facies boundaries are critical for flow performance in a reservoir and are significant for lithofacies identification in well interpretation and reservoir prediction. Facies identification based on supervised machine learning methods usually requires a large amount of labelled data, which are sometimes difficult to obtain. Here, we introduce the deep autoencoder to learn the hidden features and conduct facies classification from elastic attributes. Both labelled and unlabelled data are involved in the training process. Then, we develop a semi‐supervised deep autoencoder by taking the mean of intra‐class and the whole population of facies into account to construct a classification regularization term, thereby improving the classification accuracy and reducing the uncertainty. The new method inherits the profits of deep autoencoder and absorbs the information provided by labelled data. The proposed method performs well and produces promising results when it is used to address problems of reservoir prediction and facies identification. The new method is evaluated on both well and seismic data and compared with the conventional deep autoencoder method, which demonstrates its feasibility and superiority with respect to classification accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Semi‐supervised deep autoencoder for seismic facies classification

Liu

et al. 2021

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…The accuracy of the results was 86.41% in [8] and 85.62% in [9], respectively. Nienhold D et al [10] used genetic algorithm and feedforward neural network to classify and identify EEG data, and the error rate was reduced by about 10%. Alomari et al [11] used Coiflets wavelet to analyze and process the EEG signals, and used amplitude estimation to extract the features, and finally employed machine learning algorithms for classification and recognition.…”

Section: Related Workmentioning

confidence: 99%

“…According to the empirical formula, the number of hidden layer neurons can be calculated and located at the interval [10,20]. This is an approach to verify the rationality of the number of hidden layer neurons in our experiment.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…𝑟𝑒𝑐𝑎𝑙𝑙 = 𝑇𝑃 𝑇𝑃 + 𝐹𝑁 (10) where TP is true positive, indicating that the ground truth is positive and the prediction is positive; FP is a false positive, indicating that the ground truth is negative but the prediction is positive; FN is false negative, indicating that the ground truth is positive but the prediction is negative.…”

Section: Fig 5 Confusion Matrix Visualizationmentioning

confidence: 99%

See 1 more Smart Citation

Classification and recognition of encrypted EEG data based on neural network

Liu

Huang

Xiao

et al. 2020

Journal of Information Security and Applications

View full text Add to dashboard Cite

“…Then finally, the characters were segmented using a contour-based bounding box segmentation method [16].In phase two, the GLCM feature extraction technique was applied to the segmented character to extract the statistical features of an image which includes contrast, energy, homogeneity, correlation, dissimilarity and Angular Second Moment (ASM). By obtaining these features, the network was trained using RBF [17] with the Nguyen-Widrow weight initialization method [19] and the CART algorithm as shown in Fig. 3 and Fig.4.…”

Section: Proposed Workmentioning

confidence: 99%

Systematic Classification of Historical Handwritten Tamil Palm Leaf Manuscript using CART algorithm and RBF Network

Sornam*¹,

M²

2019

IJITEE

View full text Add to dashboard Cite

Character classification in the handwritten Tamil palm-leaf manuscript is more challenging than the other document character classification due to degradation and ancient characters in the palm-leaf manuscript. In this work, RBF (Radial Basis Function) network and CART (Classification and Regression Tree) were used to classify the Tamil palm leaf segmented characters. This work consists of two phases: In the first phase, the scanned Tamil palm leaf images were preprocessed by converting them into a grayscale image and then the images were allowed to remove noise using a median filter. In the second phase, GLCM (Gray Level Co-occurrence Matrix) feature extraction method was used to extract the statistical features from the segmented characters and these features were used to train the RBF network and CART algorithm. For the RBF network, Nguyen-Widrow weight initialization technique was used to generate the weight instead of random initialization. The dataset used in this work is Kuzhanthai Pini Maruthuvam (Medicine for child-related disease). By comparing RBF using Nguyen-Widrow method with CART algorithm, RBF yields promising result of 98.4% of accuracy whereas CART produced 98.8% of accuracy for character classification. The digitization of the Tamil palm-leaf manuscript will preserve the historical secrets, traditional medicine to cure disease, healthy lifestyle, etc. It can be used in the archeological department and Tamil libraries having a palm leaf script to preserve the manuscript from degrading.

show abstract

Effects of Weight Initialization in a Feedforward Neural Network for Classification Using a Modified Genetic Algorithm

Cited by 10 publications

References 37 publications

Semi‐supervised deep autoencoder for seismic facies classification

Semi‐supervised deep autoencoder for seismic facies classification

Classification and recognition of encrypted EEG data based on neural network

Systematic Classification of Historical Handwritten Tamil Palm Leaf Manuscript using CART algorithm and RBF Network

Contact Info

Product

Resources

About