A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SV...A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SVMs MM not only provides satisfactory approximation and generalization property, but also achieves superior performance to USOCPN multiple modeling method and single modeling method based on standard SVMs.展开更多
This paper describes a development of multilevel meteorological data acquisition system implemented at Kalpakkam coastal site for atmospheric dispersion and model validation studies. Meteorological data are one of the...This paper describes a development of multilevel meteorological data acquisition system implemented at Kalpakkam coastal site for atmospheric dispersion and model validation studies. Meteorological data are one of the most important inputs into any air dispersion model. As a part of atmospheric dispersion modeling studies and developing a methodology to forecast the site-specific dispersion characteristics, the real time monitoring of meteorological parameters assumes significance. This is achieved by erecting met towers instrumented at multilevel and single level at different locations with sensors for measuring various meteorological parameters. Real-world data logging applications involve not only just acquiring and recording signals, but also combination of offline analysis, display, report generation and data sharing. This paper covers development of low cost compact MMDAS (modular meteorological data acquisition system), its performance evaluation, field deployment test and data comparison analysis with fast response and high accuracy internationally acclaimed sonic anemometer. The system is based on embedded modules from Advantech and is designed to acquire analogue and digital signals from a multilevel instrumented met tower. The collected data are transferred from remote base station to central server for storage and further processing using wireless interface. MMDAS has many advantages like cost effectiveness, less complex signal conditioning electronics and easy maintenance. This system has good application during radiation emergency as well as site specific meteorological data collection and model validation studies.展开更多
Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is pro...Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is proposed.Methods To obtain refined features of retinal blood vessels,three cascade connected UNet networks are employed.To deal with the problem of difference between the parts of encoder and decoder,in MF2ResU-Net,shortcut connections are used to combine the encoder and decoder layers in the blocks.To refine the feature of segmentation,atrous spatial pyramid pooling(ASPP)is embedded to achieve multi-scale features for the final segmentation networks.Results The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity(Sen),specificity(Spe),accuracy(ACC),and area under curve(AUC),the values of which are 0.8013 and 0.8102,0.9842 and 0.9809,0.9700 and 0.9776,and 0.9797 and 0.9837,respectively for DRIVE and CHASE DB1.The results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.Conclusion Based on residual connections and multi-feature fusion,the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features,which can provide another diagnosis method for computer-aided Chinese medical diagnosis.展开更多
基金National High Technology Research andDevelopment Program of China( Project 863 G2 0 0 1AA413 13 0
文摘A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SVMs MM not only provides satisfactory approximation and generalization property, but also achieves superior performance to USOCPN multiple modeling method and single modeling method based on standard SVMs.
文摘This paper describes a development of multilevel meteorological data acquisition system implemented at Kalpakkam coastal site for atmospheric dispersion and model validation studies. Meteorological data are one of the most important inputs into any air dispersion model. As a part of atmospheric dispersion modeling studies and developing a methodology to forecast the site-specific dispersion characteristics, the real time monitoring of meteorological parameters assumes significance. This is achieved by erecting met towers instrumented at multilevel and single level at different locations with sensors for measuring various meteorological parameters. Real-world data logging applications involve not only just acquiring and recording signals, but also combination of offline analysis, display, report generation and data sharing. This paper covers development of low cost compact MMDAS (modular meteorological data acquisition system), its performance evaluation, field deployment test and data comparison analysis with fast response and high accuracy internationally acclaimed sonic anemometer. The system is based on embedded modules from Advantech and is designed to acquire analogue and digital signals from a multilevel instrumented met tower. The collected data are transferred from remote base station to central server for storage and further processing using wireless interface. MMDAS has many advantages like cost effectiveness, less complex signal conditioning electronics and easy maintenance. This system has good application during radiation emergency as well as site specific meteorological data collection and model validation studies.
基金Key R&D Projects in Hebei Province(22370301D)Scientific Research Foundation of Hebei University for Distinguished Young Scholars(521100221081)Scientific Research Foundation of Colleges and Universities in Hebei Province(QN2022107)。
文摘Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is proposed.Methods To obtain refined features of retinal blood vessels,three cascade connected UNet networks are employed.To deal with the problem of difference between the parts of encoder and decoder,in MF2ResU-Net,shortcut connections are used to combine the encoder and decoder layers in the blocks.To refine the feature of segmentation,atrous spatial pyramid pooling(ASPP)is embedded to achieve multi-scale features for the final segmentation networks.Results The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity(Sen),specificity(Spe),accuracy(ACC),and area under curve(AUC),the values of which are 0.8013 and 0.8102,0.9842 and 0.9809,0.9700 and 0.9776,and 0.9797 and 0.9837,respectively for DRIVE and CHASE DB1.The results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.Conclusion Based on residual connections and multi-feature fusion,the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features,which can provide another diagnosis method for computer-aided Chinese medical diagnosis.