Papers by kittikorn sriwichai
IOS Press eBooks, Nov 24, 2022
The purpose of this paper is to propose and study the structure of wavelet transformation (WT) an... more The purpose of this paper is to propose and study the structure of wavelet transformation (WT) and convolution neural networks (CNN). To get more insights into its effectiveness, three WCNN architectures are designed and tested against one another seeking which model provides the best performance in breast cancer detection using histopathological images. The Breast cancer histopathological database (BreakHis) is used for this task.
IOS Press eBooks, Nov 24, 2022
In this work, the wavelet transformation (WT) under the context of convolution neural network (CN... more In this work, the wavelet transformation (WT) under the context of convolution neural network (CNN) is developed and applied for breast cancer detection. The main objective is to investigate the effectiveness of the WCNN pooling architecture when compared to other two famous pooling strategies; max and average pooling, particularly targeting at the features extraction and classifying the phases of breast cancer by avoiding the under and overfitting problems. It is discovered in this work that the combination of WT and CNN outperforms the traditional and typical CNNs (with 96.49% of accuracy 95.81% of precision, 96.73% of recall and 96.23% of F measure).
A Numerical Investigation of Various Forms of Wavelet in Financial Time Series Analysis
2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), 2021
In this work, seven forms of discrete wavelet transformation under the mother wavelet type are nu... more In this work, seven forms of discrete wavelet transformation under the mother wavelet type are numerically studied for analyzing the financial time series data. They are Haar, Daubechies, Discrete FIR approximation of Meyer wavelet, Symlets, Coiflets, Biorthogonal, and Reverse biorthogonal. The data used consist of the Dow Jones Index (DJIA 30) from 17 July 2000 until 16 July 2020. Our numerical investigation shows that Haar performs best in solving the autocorrelation problem and denoising data.
In this paper, we propose and analyze a generalized α-nonexpansive mappings on a nonempty subset ... more In this paper, we propose and analyze a generalized α-nonexpansive mappings on a nonempty subset of a hyperbolic space i.e., 1 2 d(x,Tx)≤ d(x, y)=⇒ d(Tx,T y)≤αd(y,Tx)+αd(x,T y)+ (1−2α)d(x, y), and prove ∆-convergence theorems and convergence theorems for a generalized α-nonexpansive mappings in a hyperbolic space.
Communications in Mathematics and Applications, 2019
In this paper, we propose and analyze a \(L\)-Lipschitzian Suzuki-generalized nonexpansive mappin... more In this paper, we propose and analyze a \(L\)-Lipschitzian Suzuki-generalized nonexpansive mapping on a nonempty subset of a hyperbolic space and prove \(\Delta\)-convergence theorems and convergence theorems for a \(L\)-Lipschitzian Suzuki-generalized nonexpansive mapping in a hyperbolic space.
The Generalized \(\alpha\)-Nonexpansive Mappings and Related Convergence Theorems in Hyperbolic Spaces
Journal of Informatics and Mathematical Sciences, 2019
In this paper, we propose and analyze a generalized \(\alpha\)-nonexpansive mappings on a nonempt... more In this paper, we propose and analyze a generalized \(\alpha\)-nonexpansive mappings on a nonempty subset of a hyperbolic space i.e., \begin{align*} \frac{1}{2}d(x,Tx)\leq d(x,y)\Longrightarrow d(Tx,Ty)\leq \alpha d(y,Tx)+\alpha d(x,Ty)+ (1-2\alpha)d(x,y), \end{align*} and prove \(\Delta\)-convergence theorems and convergence theorems for a generalized \(\alpha\)-nonexpansive mappings in a hyperbolic space.
Uploads
Papers by kittikorn sriwichai