Application of a neural network model with multimodal fusion for fluorescence spectroscopy

作     者：Lin Tang Shuang Zhou Kai-Bo Shi Hong-Tao Shen Lei You Lin Tang;Shuang Zhou;Kai-Bo Shi;Hong-Tao Shen;Lei You

作者机构：College of Electronic Information and Electrical EngineeringChengdu UniversityChengdu 610106China Guangxi Key Laboratory of Nuclear Physics and Nuclear TechnologyGuangxi Normal UniversityGuilin 541004China National Engineering Research Center for Agro-Ecological Big Data Analysis&ApplicationAnhui UniversityHefei 230039China School of Electrical and Electronic EngineeringNanyang Technological UniversitySingapore 639798Singapore Vanadium and Titanium Resource Comprehensive Utilization Key Laboratory of Sichuan ProvincePanzhihua UniversityPanzhihua 617000China Key Laboratory of Interior Layout optimization and SecurityInstitutions of Higher Education of Sichuan ProvinceChengdu Normal UniversityChengdu 611130China 

出 版 物：《Nuclear Science and Techniques》 (核技术（英文）)

年 卷 期：2024年第35卷第10期

页      面：135-148页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 070302[理学-分析化学] 0835[工学-软件工程] 0703[理学-化学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the Open Project of Guangxi Key Laboratory of Nuclear Physics and Nuclear Technology(No.NLK2022-05) the Central Government Guidance Funds for Local Scientific and Technological Development,China(No.Guike ZY22096024) the Sichuan Natural Science Youth Fund Project(No.2023NSFSC1366) Key R&D Projects of Sichuan Provincial Department of Science and Technology(No.2023YFG0287) the Open Research Fund of National Engineering Research Center for Agro-Ecological Big Data Analysis&Application,Anhui University(No.AE202209) the National Natural Science Youth Foundation of China(No.12305214) the Vanadium and Titanium Resource Comprehensive Utilization Key Laboratory of Sichuan Province(No.2023FTSZ03) the Key Laboratory of Interior Layout optimization and Security,Institutions of Higher Education of Sichuan Province(No.2023SNKJ-01) 

主　　题：UNet Long-and short-term memory Pulse distortion Pulse height estimation Fluorescent spectroscopy 

摘      要：In energy-dispersive X-ray fluorescence spectroscopy,the estimation of the pulse amplitude determines the accuracy of the spectrum *** error generated by the amplitude estimation of the pulse output distorted by the measurement system leads to false peaks in the measured *** eliminate these false peaks and achieve an accurate estimation of the distorted pulse amplitude,a composite neural network model is proposed,which embeds long and short-term memory(LSTM)into the UNet *** UNet network realizes the fusion of pulse sequence features and the LSTM model realizes pulse amplitude *** model is trained using simulated pulse datasets with different amplitudes and distortion *** the pulse height estimation,the average relative error of the trained model on the test set was approximately 0.64%,which is 27.37% lower than that of the traditional trapezoidal shaping *** processing of a standard iron source further validated the pulse height estimation performance of the UNet-LSTM *** estimating the amplitude of the distorted pulses using the model,the false peak area was reduced by approximately 91% over the full spectrum and was corrected to the characteristic peak region of interest(ROI).The corrected peak area accounted for approximately 1.32%of the characteristic peak ROI *** results indicate that the model can accurately estimate the height of distorted pulses and has substantial corrective effects on false peaks.