Heart Failure Detection Using Quantum-Enhanced Machine Learning and Traditional Machine Learning Techniques for Internet of Artificially Intelligent Medical Things
The author used quantum -nearest-neighbour algorithm to achieve better efficiency in image classification with 83.1% classification accuracy on the Graz-01 dataset and 78% on Caltech-101 dataset.
The author proposed the quantum decision tree model that implemented Neumann entropy in place of Shannon entropy to decide which attribute should be split effectively.
The author assigned each principal component a fraction-transition probability where they incorporated the QIS method into random forest and proposed quantum-inspired forest.
The author described auto-regressive (AR) model and quantum recurrent neural network (QRNN) and their proposed method, achieving an accuracy of 88.28%.
QNN inherits the basic properties of ANN and contains quantum computing paradigms. It has its application in automated control systems (ACS) and other associative memory devices.
For the analysis of COVID-19 pictures, the authors studied quantum machine learning and conventional machine learning methodologies.
They achieved 0.94 precision, accuracy, recall, and -score on POF hospital dataset while 0.96 precision, 0.96 accuracy, 0.95 recall, and 0.96 -score on UCSD-AI4H dataset.