Thomas J. Mikhail, Raghi S. El Shami, M. Swillam, Xun Li
{"title":"基于微环谐振器和深度学习的介质化学浓度预测","authors":"Thomas J. Mikhail, Raghi S. El Shami, M. Swillam, Xun Li","doi":"10.1117/12.2655968","DOIUrl":null,"url":null,"abstract":"A new approach for determining the concentration composition of a multi-element media using a micro-ring resonator (MRR) is proposed which allows for noise removal as well as moderately higher average accuracy. This method uses two neural networks, namely a convolutional neural network (CNN) and a deep neural network (DNN). The CNN differentiates the transmission spectrum from the noise. This spectrum is used to obtain selected features before being fed into the DNN, which determines the concentration of each chemical in the analyte. Both models are trained to work with a silicon on-insulator ring resonator operating between the infrared wavelengths of λ=1.46 μm to λ=1.6μm on mixtures of water, ethanol, methanol, and propanol by using simulation data obtained from finite difference eigenmode, although the same approach can be used with other designs and chemical combinations. The CNN was trained using the MRR transmission spectra superimposed with white Gaussian noise as well as Poisson noise to mimic various noise sources, while the DNN underwent training on the extracted features. Average Root-Mean-Square Error was for a range of concentrations from 0.0357-75% is 5.531%.","PeriodicalId":54670,"journal":{"name":"Opto-Electronics Review","volume":"18 1","pages":"124250D - 124250D-4"},"PeriodicalIF":0.9000,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prediction of medium chemical concentration with micro-ring resonators and deep learning\",\"authors\":\"Thomas J. Mikhail, Raghi S. El Shami, M. Swillam, Xun Li\",\"doi\":\"10.1117/12.2655968\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A new approach for determining the concentration composition of a multi-element media using a micro-ring resonator (MRR) is proposed which allows for noise removal as well as moderately higher average accuracy. This method uses two neural networks, namely a convolutional neural network (CNN) and a deep neural network (DNN). The CNN differentiates the transmission spectrum from the noise. This spectrum is used to obtain selected features before being fed into the DNN, which determines the concentration of each chemical in the analyte. Both models are trained to work with a silicon on-insulator ring resonator operating between the infrared wavelengths of λ=1.46 μm to λ=1.6μm on mixtures of water, ethanol, methanol, and propanol by using simulation data obtained from finite difference eigenmode, although the same approach can be used with other designs and chemical combinations. The CNN was trained using the MRR transmission spectra superimposed with white Gaussian noise as well as Poisson noise to mimic various noise sources, while the DNN underwent training on the extracted features. Average Root-Mean-Square Error was for a range of concentrations from 0.0357-75% is 5.531%.\",\"PeriodicalId\":54670,\"journal\":{\"name\":\"Opto-Electronics Review\",\"volume\":\"18 1\",\"pages\":\"124250D - 124250D-4\"},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2023-03-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Opto-Electronics Review\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1117/12.2655968\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Opto-Electronics Review","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1117/12.2655968","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Prediction of medium chemical concentration with micro-ring resonators and deep learning
A new approach for determining the concentration composition of a multi-element media using a micro-ring resonator (MRR) is proposed which allows for noise removal as well as moderately higher average accuracy. This method uses two neural networks, namely a convolutional neural network (CNN) and a deep neural network (DNN). The CNN differentiates the transmission spectrum from the noise. This spectrum is used to obtain selected features before being fed into the DNN, which determines the concentration of each chemical in the analyte. Both models are trained to work with a silicon on-insulator ring resonator operating between the infrared wavelengths of λ=1.46 μm to λ=1.6μm on mixtures of water, ethanol, methanol, and propanol by using simulation data obtained from finite difference eigenmode, although the same approach can be used with other designs and chemical combinations. The CNN was trained using the MRR transmission spectra superimposed with white Gaussian noise as well as Poisson noise to mimic various noise sources, while the DNN underwent training on the extracted features. Average Root-Mean-Square Error was for a range of concentrations from 0.0357-75% is 5.531%.
期刊介绍:
Opto-Electronics Review is peer-reviewed and quarterly published by the Polish Academy of Sciences (PAN) and the Association of Polish Electrical Engineers (SEP) in electronic version. It covers the whole field of theory, experimental techniques, and instrumentation and brings together, within one journal, contributions from a wide range of disciplines. The scope of the published papers includes any aspect of scientific, technological, technical and industrial works concerning generation, transmission, transformation, detection and application of light and other forms of radiative energy whose quantum unit is photon. Papers covering novel topics extending the frontiers in optoelectronics or photonics are very encouraged.
It has been established for the publication of high quality original papers from the following fields:
Optical Design and Applications,
Image Processing
Metamaterials,
Optoelectronic Materials,
Micro-Opto-Electro-Mechanical Systems,
Infrared Physics and Technology,
Modelling of Optoelectronic Devices, Semiconductor Lasers
Technology and Fabrication of Optoelectronic Devices,
Photonic Crystals,
Laser Physics, Technology and Applications,
Optical Sensors and Applications,
Photovoltaics,
Biomedical Optics and Photonics