Improved local fisher discriminant analysis based dimensionality reduction for cancer disease prediction
- PDF / 2,892,436 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 34 Downloads / 175 Views
ORIGINAL RESEARCH
Improved local fisher discriminant analysis based dimensionality reduction for cancer disease prediction P. N. Senthil Prakash1 · N. Rajkumar2 Received: 27 April 2020 / Accepted: 5 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract A good dimensional reduction technique is needed to apply and improve the effectiveness of dimensionality reduction for medical data. High-dimensional data brings great challenges in terms of computational complexity and classification efficiency. It is necessary to compress effectively from high dimensional space to low dimensional space to design a learning curve with good performance. Therefore, dimensional reduction is necessary to study and understand the mechanism of the practical problems of medical data. In this paper, a hybrid local fisher discriminant analysis (HLFDA) method is proposed for the dimension reduction of the medical data. LFDA is a localized variant of Fisher discriminant analysis and it is popular for supervised dimensionality reduction method. The proposed HLFDA is a combination of Locality-preserving projection and LFDA. After the dimensionality reduction process, the data are given to the Type2fuzzy neural network classifier to classify a given data as normal or abnormal. The paper focused on improving performance in terms of prediction accuracy. Three types of UCI cancer dataset is used for analyzing the performance of the proposed method. Keywords Dimensionality reduction · Local fisher discriminant analysis · Locality-preserving projection · Cancer · Type2fuzzy neural network
1 Introduction Cancer is the deadliest malady and the worldwide cancer trouble has been expanded to 18.5 million and 9.5 million individuals were dead in 2018. The expansion in the death rate is because of different reasons, for example, populace, maturing process, way of life-related with financial improvement. The malady is common in the low economy nations since they are not analyzed at the beginning times of the sickness event (Mandal and Banerjee 2015). The mortality rate in Asia due to global cancer is 57.3% because of their lack of prognosis. Female breast cancer ranks 5th, leading to a 6.6% mortality rate including developed countries and breast cancer accounts for 24.2% of the global death rate * P. N. Senthil Prakash [email protected] N. Rajkumar [email protected] 1
RMK College of Engineering and Technology, Chennai, Tamil Nadu, India
Hindusthan College of Engineering and Technology, Coimbatore, Tamil Nadu, India
2
and is widespread in 154 countries, including developed and developing countries (Mitra et al. 2000). Bosom cancer contributes around 24.2% of the passing rate worldwide and it is pervasive in 154 nations that incorporate both the created and creating nations (Mitra et al. 2000). Over the past several decades, there has been a continuous evolution in cancer research. Researchers applied various strategies, for example, screening in the beginning time, to discover kinds of cancer before
Data Loading...
