Search results

1 – 4 of 4
Article
Publication date: 4 September 2019

Li Na, Xiong Zhiyong, Deng Tianqi and Ren Kai

The precise segmentation of brain tumors is the most important and crucial step in their diagnosis and treatment. Due to the presence of noise, uneven gray levels, blurred…

Abstract

Purpose

The precise segmentation of brain tumors is the most important and crucial step in their diagnosis and treatment. Due to the presence of noise, uneven gray levels, blurred boundaries and edema around the brain tumor region, the brain tumor image has indistinct features in the tumor region, which pose a problem for diagnostics. The paper aims to discuss these issues.

Design/methodology/approach

In this paper, the authors propose an original solution for segmentation using Tamura Texture and ensemble Support Vector Machine (SVM) structure. In the proposed technique, 124 features of each voxel are extracted, including Tamura texture features and grayscale features. Then, these features are ranked using the SVM-Recursive Feature Elimination method, which is also adopted to optimize the parameters of the Radial Basis Function kernel of SVMs. Finally, the bagging random sampling method is utilized to construct the ensemble SVM classifier based on a weighted voting mechanism to classify the types of voxel.

Findings

The experiments are conducted over a sample data set to be called BraTS2015. The experiments demonstrate that Tamura texture is very useful in the segmentation of brain tumors, especially the feature of line-likeness. The superior performance of the proposed ensemble SVM classifier is demonstrated by comparison with single SVM classifiers as well as other methods.

Originality/value

The authors propose an original solution for segmentation using Tamura Texture and ensemble SVM structure.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 12 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

Abstract

Details

Chinese Social Media
Type: Book
ISBN: 978-1-83909-136-0

Article
Publication date: 28 June 2013

Sheau‐yueh J. Chao

The purpose of this paper is to provide the historical background of genealogical records and analyze the value of Chinese genealogical research through the study of names and…

Abstract

Purpose

The purpose of this paper is to provide the historical background of genealogical records and analyze the value of Chinese genealogical research through the study of names and genealogical resources.

Design/methodology/approach

The paper examines the historical evolution and value of Chinese genealogical records, with the focus on researching the Islamic Chinese names used by the people living in Guilin. The highlight of this paper includes the analysis and evolution of the Islamic Chinese names commonly adopted by the local people in Guilin. It concludes with the recommendations on emphasizing and making the best use of genealogical records to enhance the research value of Chinese overseas studies.

Findings

The paper covers the history of Islam and describes how the religion was introduced into China, as well as Muslims' ethnicity and identity. It also places focus on the importance of building a research collection in Asian history and Chinese genealogy.

Research limitations/implications

This research study has a strong subject focus on Chinese genealogy, Asian history, and Islamic Chinese surnames. It is a narrow field that few researchers have delved into.

Practical implications

The results of this study will assist students, researchers, and the general public in tracing the origin of their surnames and developing their interest in the social and historical value of Chinese local history and genealogies.

Social implications

The study of Chinese surnames is, by itself, a particular field for researching the social and political implications of contemporary Chinese society during the time the family members lived.

Originality/value

Very little research has been done in the area of Chinese local history and genealogy. The paper would be of value to researchers such as historians, sociologists, ethnologists and archaeologists, as well as students and anyone interested in researching a surname origin, its history and evolution.

Abstract

Details

Journal of Intelligent Manufacturing and Special Equipment, vol. 4 no. 1
Type: Research Article
ISSN: 2633-6596

1 – 4 of 4