• PDF / 130,830 Bytes
• 9 Pages / 439.37 x 666.142 pts Page_size
• 14 Downloads / 227 Views

DOWNLOAD

REPORT

ial Intelligence (AI) approaches for medical diagnosis and prediction of cancer are important and ever growing areas of research. Artificial Neural Networks (ANNs) is one such approach that have been successfully applied in these c Springer International Publishing Switzerland 2016  H. Cao et al. (Eds.): PAKDD 2016 Workshops, LNAI 9794, pp. 26–34, 2016. DOI: 10.1007/978-3-319-42996-0 3

Attribute Selection and Classification of Prostate Cancer Gene Expression

27

areas. Various types of clinical datasets have been used in intelligent decision making systems for medical diagnosis, especially cancer dfor over three decades. However, gene expression datasets are complex with large numbers of attributes which make it more difficult for AI approaches to classification and prediction. The importance of using AI techniques in bio-informatics has been known for some time [1]. Artificial Neural Networks (ANNs) have been implemented for classification and prediction of various types of cancers like [2], colorectal [3], Lung [4], colon [5] etc. Most of these implementation are performed using gene expression datasets [6]. Classification of complex non-linear data like gene expression data is a challenging task due to its high dimensionality especially when the number of samples are far less number of attributes in the dataset. With such datasets, analysing the importance of attributes and identifying the significance of an attribute become more difficult. Earlier research on using ANNs for gene expression analysis was limited to mainly single-layered ANNs due to nonavailability of powerful hardware. One such early work emphasizes the importance of identifying a set of significant genes among the thousands of genes in the dataset [7]. Among various types of cancer, prostate cancer is the second leading cancer for men. Some of the previous work on prostate cancer is confined to early detection and progress of prostate cancer using clinical data of the patient [8,9]. The only noted work on prostate gene expression data is done by Singh and others which provides an analysis on the impact of differences in the gene expression and the development of prostate tumour [10]. Recently there has been notable work on cancer gene expression dataset classification using Deep Learning which proves the complexity involved in classification of gene expression data [11]. However that work is limited to classification and lacks experimental details. The contribution of this paper is in identifying significant attributes (genes) from the gene expression dataset that have direct influence on classification as well as prediction of prostate cancer. This paper is organized as follows. Section 2 provides a brief explanation of attribute selection approaches used in this research along with results. The first part of Sect. 3 provides the experimental setup detailing ANN topology and parameters used in the experiments followed by comparative analysis of classification results using various attribute sets obtained from Sect. 2. Experimental results of predicting prostate c

Recommend Documents

Optimized gene selection and classification of cancer from microarray gene expression data using deep learning

194 75 2MB

Modelling gene interaction networks from time-series gene expression data using evolving spiking neural networks

178 75 2MB

Robust Prostate Cancer Classification with Siamese Neural Networks

142 15 149MB

Gene Expression Data Analysis: Classification

197 70 72MB

Molecular cancer classification method on microarrays gene expression data using hybrid deep neural network and grey wol

279 46 1MB

Comparative Analysis of Discretization Methods for Gene Selection of Breast Cancer Gene Expression Data

108 25 311KB

Fuzzy Classification for Gene Expression Data Analysis

172 24 140KB

Gene Expression-Based Supervised Classification Models for Discriminating Early- and Late-Stage Prostate Cancer

143 50 634KB

Data Normalisation-Based Solar Irradiance Forecasting Using Artificial Neural Networks

199 36 861KB

Classification and Analysis Topologies Known Artificial Neurons and Neural Networks

156 68 23MB

Simultaneous feature selection and clustering of micro-array and RNA-sequence gene expression data using multiobjective

148 15 11MB

Ensemble Malware Classification Using Neural Networks

209 82 2MB