Research Area:  Machine Learning

Abstract:

Machine learning (ML) is the most promising subset of artificial intelligence. Quantum computing is prevalent for fast problem-solving approaches. The complex problems are classified and solved using huge multi-dimensional space. The various algorithms can interfere in multi-dimensional space and resolve the problems. Quantum Machine Learning provides the platform for various mining processes with to the point developments in quantum computing. Quantum computing & Machine learning both are very complex. Quantum Machine learning focuses on quick problem-solving synthesis with a quantum framework using different algorithms. Machine Learning functions by supervised, unsupervised, and semi-supervised learning mechanisms. ML uses label and unlabeled data to implement different classification, clustering, and decision trees for complex problems. Quantum computing comprises quantum counterparts for various computational complexity. Quantum Machine Learning provides a profound sympathetic approach for various subjects to derive new dimensioned results. There are several serious life-threatening diseases such as cancer, hepatotoxicity, cardiotoxicity, nephrotoxicity, etc. require prompt and precise detection at the early stages of progression. The need of the hour is to develop rapid, accurate, and more efficient strategies for various disease predictions which are also cost-effective and non-invasive in nature. Breast cancer is also such a disease that early screening is challenging owning to hereditary predisposition. Quantum computation techniques emerged with Machine learning as the promising approach in the past decade concerning the prediction of breast cancer. The quantum computes can be utilized for assisting cancer detection by employing quantum neural networks, quantum simulators, Super Vector Machine (SVM); Artificial Neural Networks (ANN), Dimensionality Reduction Algorithms etc. are used on the pre-processed dataset for the derived prediction of breast cancer. This book chapter will focus on current trends of Quantum Machine leaning for the prediction of breast cancers by solving complex computational problems using above stated algorithms. This chapter discusses the Molecular Classification of Breast Cancer as Luminal-A, Luminal-B, Normal-like, HER2 enriched, and Basal-like with Breast Cancer Diagnostic Techniques. It covers the study of Brest cancer prediction using Quantum Neural Network, Dimensionality Reduction Algorithms, and Support vector machines (SVM). It includes comparative discussions about different algorithms for breast cancer prediction.

Keywords:  

Author(s) Name:  Jigna B. Prajapati, Himanshu Paliwal, Bhupendra G. Prajapati, Surovi Saikia & Rajiv Pandey

Publisher name:  Springer

DOI:  10.1007/978-981-19-9530-9_19

Volume Information:  Volume 45,pages 351-382, (2023)

Paper Link:   https://link.springer.com/chapter/10.1007/978-981-19-9530-9_19