This paper focuses on the recognition rate comparison for competing recognition algorithms, which is a common problem of many pattern recognition research areas. The paper firstly reviews some traditional recognition ...This paper focuses on the recognition rate comparison for competing recognition algorithms, which is a common problem of many pattern recognition research areas. The paper firstly reviews some traditional recognition rate comparison procedures and discusses their limitations. A new method, the posterior probability calculation（PPC） procedure is then proposed based on Bayesian technique. The paper analyzes the basic principle, process steps and computational complexity of the PPC procedure. In the Bayesian view, the posterior probability represents the credible degree（equal to confidence level） of the comparison results. The posterior probability of correctly selecting or sorting the competing recognition algorithms is derived, and the minimum sample size requirement is also pre-estimated and given out by the form of tables. To further illustrate how to use our method, the PPC procedure is used to prove the rationality of the experiential choice in one application and then to calculate the confidence level with the fixed-size datasets in another application. These applications reveal the superiority of the PPC procedure, and the discussions about the stopping rule further explain the underlying statistical causes. Finally we conclude that the PPC procedure achieves all the expected functions and be superior to the traditional methods.展开更多
Electronic Nose(ENose)technology has emerged as a transformative tool in medical diagnostics,leveraging sensor arrays that mimic the human olfactory system to detect odors and volatile organic compounds(VOCs)in variou...Electronic Nose(ENose)technology has emerged as a transformative tool in medical diagnostics,leveraging sensor arrays that mimic the human olfactory system to detect odors and volatile organic compounds(VOCs)in various biological samples.ENose systems utilize a range of sensor types,such as metal oxide semiconductors and conducting polymers,to generate unique“smell fingerprints”through pattern recognition algorithms.These systems have shown promise in diagnosing various medical conditions,including respiratory diseases,infectious diseases,metabolic disorders,and neurological conditions.Notably,ENose technology holds significant promise in cancer diagnostics,offering a non-invasive,cost-effective,and rapid approach to early detection and monitoring.It has demonstrated impressive accuracy(85%-95%)in detecting cancers and monitoring complications.However,challenges remain,including issues with standardization,sensor sensitivity,and data interpretation.Despite these hurdles,ENose technology’s market growth is fueled by the increasing prevalence of chronic diseases.Recent developments in Artificial Intelligence(AI),particularly machine learning techniques like deep learning,have enhanced the diagnostic accuracy and robustness of ENose devices.This paper explores the evolution,core principles,applications,challenges,and future potential of ENose technology,with particular emphasis on integrating recent advancements in AI for enhanced detection and interpretation.Future research and collaboration across sectors are essential to overcome existing challenges and integrate ENose into mainstream healthcare.展开更多
基金supported by the National Natural Science Foundation of China(61101179)
文摘This paper focuses on the recognition rate comparison for competing recognition algorithms, which is a common problem of many pattern recognition research areas. The paper firstly reviews some traditional recognition rate comparison procedures and discusses their limitations. A new method, the posterior probability calculation（PPC） procedure is then proposed based on Bayesian technique. The paper analyzes the basic principle, process steps and computational complexity of the PPC procedure. In the Bayesian view, the posterior probability represents the credible degree（equal to confidence level） of the comparison results. The posterior probability of correctly selecting or sorting the competing recognition algorithms is derived, and the minimum sample size requirement is also pre-estimated and given out by the form of tables. To further illustrate how to use our method, the PPC procedure is used to prove the rationality of the experiential choice in one application and then to calculate the confidence level with the fixed-size datasets in another application. These applications reveal the superiority of the PPC procedure, and the discussions about the stopping rule further explain the underlying statistical causes. Finally we conclude that the PPC procedure achieves all the expected functions and be superior to the traditional methods.
基金supported by Jiangxi University of Science and Technology,341000,Ganzhou,P.R.China,underfunding number 2021205200100563.
文摘Electronic Nose(ENose)technology has emerged as a transformative tool in medical diagnostics,leveraging sensor arrays that mimic the human olfactory system to detect odors and volatile organic compounds(VOCs)in various biological samples.ENose systems utilize a range of sensor types,such as metal oxide semiconductors and conducting polymers,to generate unique“smell fingerprints”through pattern recognition algorithms.These systems have shown promise in diagnosing various medical conditions,including respiratory diseases,infectious diseases,metabolic disorders,and neurological conditions.Notably,ENose technology holds significant promise in cancer diagnostics,offering a non-invasive,cost-effective,and rapid approach to early detection and monitoring.It has demonstrated impressive accuracy(85%-95%)in detecting cancers and monitoring complications.However,challenges remain,including issues with standardization,sensor sensitivity,and data interpretation.Despite these hurdles,ENose technology’s market growth is fueled by the increasing prevalence of chronic diseases.Recent developments in Artificial Intelligence(AI),particularly machine learning techniques like deep learning,have enhanced the diagnostic accuracy and robustness of ENose devices.This paper explores the evolution,core principles,applications,challenges,and future potential of ENose technology,with particular emphasis on integrating recent advancements in AI for enhanced detection and interpretation.Future research and collaboration across sectors are essential to overcome existing challenges and integrate ENose into mainstream healthcare.
