GDL

Journal from gdlhub / 2019-09-19 10:46:56
Oleh : Atefeh Nekouie, Mohammad Hossein Moattar, King Saud University
Dibuat : 2019-09-19, dengan 1 file

Keyword : Breast cancer diagnosis, Tensor factorization, Particle swarm optimization, Bayesian networks, Support vector machine, Chaos
Url : http://www.sciencedirect.com/science/article/pii/S1319157817303506
Sumber pengambilan dokumen : WEB

Cancer refers to a disease in which a group of cells show uncontrolled growth, invasion and metastasis. Data mining and machine learning are common approaches for clinical diagnosis. An important issue in this filed is that these data often include missing value which reduces the diagnostic accuracy. In this paper, a modified tensor factorization method is used for estimating the missing data. When tensor approach intends to estimate the missing value, there should be a class balance in the dataset and tensor does not properly estimate data in the case of data insufficiency. In the proposed schema, particle swarm optimization algorithm with adaptive adjustment (RAPSO) which is improved by chaotic search is used to solve this problem. In this approach, in order to inhibit the random initialization of the particle swarm algorithm, a distinctive approach is adopted and Bayesian network is used. Finally, the accuracy of disease diagnosis is estimated through different classifiers and RMSE measure. The results suggested that the proposed method is superior to other methods in terms of RMSE, accuracy, sensitivity and specificity.

Beri Komentar ?#(0) | Bookmark

Properti	Nilai Properti
ID Publisher	gdlhub
Organisasi	King Saud University
Nama Kontak	Herti Yani, S.Kom
Alamat	Jln. Jenderal Sudirman
Kota	Jambi
Daerah	Jambi
Negara	Indonesia
Telepon	0741-35095
Fax	0741-35093
E-mail Administrator	elibrarystikom@gmail.com
E-mail CKO	elibrarystikom@gmail.com