Conventional Machine Learning based on Feature Engineering for Detecting Pneumonia from Chest X-rays

被引：3

作者：

Ebiele, F. M. J. ^{[1
]}

Ansah-Narh, T. ^{[2
]}

Djiokap, S. R. T. ^{[1
,3
]}

Proven-Adzri, E. ^{[2
]}

Atemkeng, M. ^{[4
]}

机构：

[1] African Inst Math Sci AIMS, Kigali, Rwanda

[2] Ghana Space Sci & Technol Inst GSSTI, Accra, Ghana

[3] Univ Dschang, Inst Fine Arts Foumban, Dschang, Cameroon

[4] Rhodes Univ, Dept Math, Grahamstown, South Africa

来源：

PROCEEDINGS OF THE SOUTH AFRICAN INSTITUTE OF COMPUTER SCIENTISTS AND INFORMATION TECHNOLOGISTS, SAICSIT 2020 | 2020年

关键词：

Pneumonia; chest X-rays; feature extraction; principal component analysis; supervised learning;

D O I：

10.1145/3410886.3410898

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Chest X-ray is the standard approach used to diagnose pneumonia and other chest diseases. Early diagnosis of the disease is very relevant in the life of people, but analyzing X-ray images can be complicated and needs the competence of a radiographer. In this paper, we demonstrate the potential of detecting the disease in chest X-rays using conventional machine learning classifiers. The principal component analysis is used for the data dimensionality reduction and features extraction then the extracted features are used to train several model classifiers. We obtained an accuracy of 90 %, using 95 % of the principal explained variance.

引用

页码：149 / 155

页数：7

共 21 条

[1]

Aich S, 2018, INT CONF ADV COMMUN, P638, DOI 10.23919/ICACT.2018.8323864

[2] Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification [J].

Baltruschat, Ivo M. ;

Nickisch, Hannes ;

Grass, Michael ;

Knopp, Tobias ;

Saalbach, Axel .

SCIENTIFIC REPORTS, 2019, 9 (1)

[3]

Bozorgi M, 2017, 2017 COMPUTING CONFERENCE, P416, DOI 10.1109/SAI.2017.8252133

[4] On the use of decision tree induction for discovery of interactions in a photolithographic process [J].

Braha, D ;

Shmilovici, A .

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2003, 16 (04) :644-652

[5]

Crockett KA, 2000, NINTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE 2000), VOLS 1 AND 2, P209, DOI 10.1109/FUZZY.2000.838660

[6]

Dai Wei., 2014, International Journal of Database Theory and Application, V7, P49, DOI DOI 10.14257/IJDTA.2014.7.1.05

[7] Evaluation Measures of the Classification Performance of Imbalanced Data Sets [J].

Gu, Qiong ;

Zhu, Li ;

Cai, Zhihua .

COMPUTATIONAL INTELLIGENCE AND INTELLIGENT SYSTEMS, 2009, 51 :461-+

[8]

Howie Stephen R.C., 2017, International Encyclopedia of Public Health, P500, DOI [10.1016/B978-0-12-803678-5.00334-9, DOI 10.1016/B978-0-12-803678-5.00334-9]

[9] Applications of Support Vector Machine (SVM) Learning in Cancer Genomics [J].

Huang, Shujun ;

Cai, Nianguang ;

Pacheco, Pedro Penzuti ;

Narandes, Shavira ;

Wang, Yang ;

Xu, Wayne .

CANCER GENOMICS & PROTEOMICS, 2018, 15 (01) :41-51

[10]

Jiao Yasen, 2016, [Quantitative Biology, 定量生物学], V4, P320

← 1 2 3 →