The advancement of automated medical diagnosis in biomedical engineering has become an important area of research.Image classification is one of the diagnostic approaches that do not require segmentation which can dra...The advancement of automated medical diagnosis in biomedical engineering has become an important area of research.Image classification is one of the diagnostic approaches that do not require segmentation which can draw quicker inferences.The proposed non-invasive diagnostic support system in this study is considered as an image classification system where the given brain image is classified as normal or abnormal.The ability of deep learning allows a single model for feature extraction as well as classification whereas the rational models require separate models.One of the best models for image localization and classification is the Visual Geometric Group(VGG)model.In this study,an efficient modified VGG architecture for brain image classification is developed using transfer learning.The pooling layer is modified to enhance the classification capability of VGG architecture.Results show that the modified VGG architecture outperforms the conventional VGG architecture with a 5%improvement in classification accuracy using 16 layers on MRI images of the REpository of Molecular BRAin Neoplasia DaTa(REMBRANDT)database.展开更多
This paper presents a low power tunable active inductor and RF band pass filter suitable for multiband RF front end circuits. The active inductor circuit uses the PMOS cascode structure as the negative transconductor ...This paper presents a low power tunable active inductor and RF band pass filter suitable for multiband RF front end circuits. The active inductor circuit uses the PMOS cascode structure as the negative transconductor of a gyrator to reduce the noise voltage. Also, this structure provides possible negative resistance to reduce the inductor loss with wide inductive bandwidth and high resonance frequency. The RF band pass filter is realized using the proposed active inductor with suitable input and output buffer stages. The tuning of the center frequency for multiband operation is achieved through the controllable current source. The designed active inductor and RF band pass filter are simulated in 180 nm and 45 nm CMOS process using the Synopsys HSPICE simulation tool and their performances are compared. The parameters, such as resonance frequency, tuning capability, noise and power dissipation, are analyzed for these CMOS technologies and discussed. The design of a third order band pass filter using an active inductor is also presented.展开更多
文摘The advancement of automated medical diagnosis in biomedical engineering has become an important area of research.Image classification is one of the diagnostic approaches that do not require segmentation which can draw quicker inferences.The proposed non-invasive diagnostic support system in this study is considered as an image classification system where the given brain image is classified as normal or abnormal.The ability of deep learning allows a single model for feature extraction as well as classification whereas the rational models require separate models.One of the best models for image localization and classification is the Visual Geometric Group(VGG)model.In this study,an efficient modified VGG architecture for brain image classification is developed using transfer learning.The pooling layer is modified to enhance the classification capability of VGG architecture.Results show that the modified VGG architecture outperforms the conventional VGG architecture with a 5%improvement in classification accuracy using 16 layers on MRI images of the REpository of Molecular BRAin Neoplasia DaTa(REMBRANDT)database.
文摘This paper presents a low power tunable active inductor and RF band pass filter suitable for multiband RF front end circuits. The active inductor circuit uses the PMOS cascode structure as the negative transconductor of a gyrator to reduce the noise voltage. Also, this structure provides possible negative resistance to reduce the inductor loss with wide inductive bandwidth and high resonance frequency. The RF band pass filter is realized using the proposed active inductor with suitable input and output buffer stages. The tuning of the center frequency for multiband operation is achieved through the controllable current source. The designed active inductor and RF band pass filter are simulated in 180 nm and 45 nm CMOS process using the Synopsys HSPICE simulation tool and their performances are compared. The parameters, such as resonance frequency, tuning capability, noise and power dissipation, are analyzed for these CMOS technologies and discussed. The design of a third order band pass filter using an active inductor is also presented.
