Genomic signal processing of microarrays for cancer gene expression and identification using cluster-fuzzy adaptive networking

Genomic signal processing (GSP) is a functioning exploration area of recent times and a settled technique of digital signal processing for gathering information from genomic sequences. The recognition and identification of biological signals and analysis of sequences are the fundamental objectives of using GSP. Microarray data are typically used in GSP; microarray study decides genes that cause a specific disease and helps in anticipating and diagnosing a disease, and characterization of diseases. Microarray information is incredible innovation where information handled to an enormous number with plenty of genes. Recent research works show that microarray handling will be helpful for the classification of cancer genes. Different machine learning and artificial intelligence techniques are likewise used to distinguish the tumours and cancer cells. In this examination, the genomic signal processing is carried out utilizing cluster-fuzzy adaptive networking techniques. The major purpose of this research work is to evaluate the microarray data sets for recognizing the cancer genes. The microarray data set is generated using leukaemia, colon, prostate, breast cancer and lymphoma. Initially, the noise in the microarray is filtered and smoothened by utilizing a Kalman filter followed by an optimal clustering technique such as grid density-based clustering that is applied for clustering the microarray data sets. The clustered data of microarray are classified by adaptive neuro fuzzy interference system (ANFIS) for gene sequencing process of cancer identification. The adaptive network systems are developed based on autonomous networking concepts to change the static system into a dynamic. The efficiency of clustering is evaluated in terms of cluster indexes namely partition entropy, partition coefficient, Xie and Beni. The presented ANFIS is assessed in terms of precision, accuracy, recall, sensitivity, F-score and specificity. The proposed initiated methodology is mathematically designed and executed in the MATLAB platform and run for various test runs. During the implementation, the performance of cluster and classification efficiency of proposed techniques are compared with the existing strategies like fuzzy c-means with ANN and density-based clustering with ANN, respectively. Ultimately, the performance outcomes demonstrated that the proposed method can provide effective and optimal classification and identification of microarray cancer genes through genomic signal processing than the conventional methods, respectively.