Cancers are the most disastrous and inevitable ailment that occurs in individuals. Due to the hazardous effects of cancer, people get at death in very early age. In today's date, cancer is categorized into many types, which are affected by the external and internal parts of the body. In general, cancers are caused by the growth of abnormal tissues where cancer originates and it is gradually spread to other parts. Therefore, the medical industry struggles to detect the different types of cancer disorders without any loss of people. Hence, the automated detection system is implemented to predict cancer in its early stages to prevent the people gets worsening. Normally, the collection of individual data is another challenging concern. Several methods have been implemented yet they exist with constraints to provide better results. Machine learning models are also used, but it does not tackle the big data collection process and also fail to obtain the relevant features. Henceforth, the deep learning model has emerged for various processes like prediction, classification, and recognition. So, a new and improved classification framework for classifying cancer is executed in this paper. At first, the data is gathered from the benchmark database. From the data, the genes are optimally selected using an Improved Arithmetic Optimization Algorithm (IAOA). Then, the optimally chosen genes are given as input to the “Optimized Deep Neural Network (ODNN)” for classification. The constraints in the DNN framework are optimized by the improved AOA. From the DNN, the classified output is obtained. Various experimentations are carried out by contrasting the developed optimization algorithm enhanced DNN model to verify the efficient working of the suggested cancer classification model. Throughout the result analysis, the accuracy and precision rate of the designed method is 93.42% and 9363% for all datasets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Efficient Cancer Classification Model Using Deep Neural Network with Arithmetic Optimization Algorithm-Based Optimal Gene Selection


    Contributors:


    Publication date :

    2023-11-22


    Size :

    1008832 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fingerprint classification using fuzzy cerebellar model arithmetic computer neural networks

    Geng, Z. J. / Shen, W. | British Library Online Contents | 1997


    Efficient Global Optimization Algorithm Using Neural Network-Based Prediction and Uncertainty

    Koratikere, Pavankumar / Leifsson, Leifur T. / Barnet, Laurel et al. | TIBKAT | 2023


    Arithmetic-Trigonometric Optimization Algorithm

    Panneer Selvam, Arun Mozhi Devan / Hussin, Fawnizu Azmadi / Ibrahim, Rosdiazli et al. | Springer Verlag | 2022


    Efficient Global Optimization Algorithm Using Neural Network-based Prediction and Uncertainty

    Koratikere, Pavankumar / Leifsson, Leifur T. / Barnet, Laurel et al. | AIAA | 2023