Classical machine learning algorithms seem to be totally incapable of processing tremendous data,while quantum machine learning algorithms could deal with big data unhurriedly and provide exponential acceleration over...Classical machine learning algorithms seem to be totally incapable of processing tremendous data,while quantum machine learning algorithms could deal with big data unhurriedly and provide exponential acceleration over classical counterparts.In this paper,we propose two quantum support vector machine algorithms for multi classification.One is the quantum version of the directed acyclic graph support vector machine.The other one is to use the Grover search algorithm before measurement,which amplifies the amplitude of the phase storing of the classification result.For k classification,the former provides quadratic reduction in computational complexity when classifying.The latter accelerates the training speed significantly and more importantly,the classification result can be read out with a probability of at least 50%using only one measurement.We conduct numerical simulations on two algorithms,and their classification success rates are 96%and 88.7%,respectively.展开更多
Background:The kidney is one of the most essential organs in our body,and any problems with it are perilous,hence,the early diagnosis of chronic kidney disease(CKD)is crucial.support vector machine(SVM),a popular mach...Background:The kidney is one of the most essential organs in our body,and any problems with it are perilous,hence,the early diagnosis of chronic kidney disease(CKD)is crucial.support vector machine(SVM),a popular machine learning(ML)technique,is an effective solution for building an early CKD diagnosis system.Nowadays ML techniques like SVM are often combined with upcoming quantum computing technology to improve over classical ML.Methods:This research uses classical SVM(CSVM)and Quantum SVM(QSVM)to develop a CKD diagnosis system and compare the efficiency of the two diagnosis systems.This research performs different preprocessing on a CKD dataset.Based on the analysis and preprocessing,two data optimization approaches principal component analysis(PCA)and singular value decomposition(SVD)are applied to generate two optimized datasets.More-over,classification is done on these two datasets by utilizing both CSVM and QSVM.Findings:The comprehensive analysis of various techniques reveals that PCA outperforms SVD when paired with both CSVM and QSVM.Utilizing PCA,CSVM achieves a remarkable accuracy of 98.75%,while QSVM achieves 87.5%accuracy.In contrast,by utilizing SVD,both CSVM and QSVM achieve relatively lower accuracies,with CSVM achieving 96.25%accuracy and QSVM achieving 60%accuracy.Interpretation:The final assessment of this research confirms that QSVM requires more time in classical experi-mental settings compared to CSVM.Furthermore,the research aims to make it easier to catch CKD early by providing reliable and efficient diagnosis methods.At the same time,it opens the door for trying out new quantum ML ideas in healthcare down the line.展开更多
基金supported by the Shandong Provincial Natural Science Foundation for Quantum Science(No.ZR2021LLZ002)the Fundamental Research Funds for the Central Universities(No.22CX03005A).
文摘Classical machine learning algorithms seem to be totally incapable of processing tremendous data,while quantum machine learning algorithms could deal with big data unhurriedly and provide exponential acceleration over classical counterparts.In this paper,we propose two quantum support vector machine algorithms for multi classification.One is the quantum version of the directed acyclic graph support vector machine.The other one is to use the Grover search algorithm before measurement,which amplifies the amplitude of the phase storing of the classification result.For k classification,the former provides quadratic reduction in computational complexity when classifying.The latter accelerates the training speed significantly and more importantly,the classification result can be read out with a probability of at least 50%using only one measurement.We conduct numerical simulations on two algorithms,and their classification success rates are 96%and 88.7%,respectively.
文摘Background:The kidney is one of the most essential organs in our body,and any problems with it are perilous,hence,the early diagnosis of chronic kidney disease(CKD)is crucial.support vector machine(SVM),a popular machine learning(ML)technique,is an effective solution for building an early CKD diagnosis system.Nowadays ML techniques like SVM are often combined with upcoming quantum computing technology to improve over classical ML.Methods:This research uses classical SVM(CSVM)and Quantum SVM(QSVM)to develop a CKD diagnosis system and compare the efficiency of the two diagnosis systems.This research performs different preprocessing on a CKD dataset.Based on the analysis and preprocessing,two data optimization approaches principal component analysis(PCA)and singular value decomposition(SVD)are applied to generate two optimized datasets.More-over,classification is done on these two datasets by utilizing both CSVM and QSVM.Findings:The comprehensive analysis of various techniques reveals that PCA outperforms SVD when paired with both CSVM and QSVM.Utilizing PCA,CSVM achieves a remarkable accuracy of 98.75%,while QSVM achieves 87.5%accuracy.In contrast,by utilizing SVD,both CSVM and QSVM achieve relatively lower accuracies,with CSVM achieving 96.25%accuracy and QSVM achieving 60%accuracy.Interpretation:The final assessment of this research confirms that QSVM requires more time in classical experi-mental settings compared to CSVM.Furthermore,the research aims to make it easier to catch CKD early by providing reliable and efficient diagnosis methods.At the same time,it opens the door for trying out new quantum ML ideas in healthcare down the line.
