Sensors play an important role in shaping and monitoring human health.Exploration of methods to use Fiber Bragg Grating(FBG)with enhanced sensitivity has attracted great interest in the field of medical research.In th...Sensors play an important role in shaping and monitoring human health.Exploration of methods to use Fiber Bragg Grating(FBG)with enhanced sensitivity has attracted great interest in the field of medical research.In this paper,a novel apodization function is proposed and performance evaluation and optimization of the same have been made.A comparison was conducted between various existing apodization functions and the proposed one based on optical characteristics and sensor parameters.The results evince the implementation of the proposed apodization function for vital sign measurement.The optical characteristics considered for evaluation are Peak Resonance Reflectivity level,Side Lobes Reflectivity level and FullWidth HalfMaximum(FWHM).The proposed novel apodization novel function has better FWHM,which is narrower than the FWHM of uniform FBG.Sensor characteristics like a quality parameter,detection accuracy and sensitivity also show improvement.The proposed novel apodization function is demonstrated to have a better shift in wavelength in terms of temperature and pulse measurement than the existing functions.The sensitivity of the proposed apodized function is enhanced with a Poly-dimethylsiloxane coating of varying thickness,which is 6 times and 5.14 times greater than uniform Fiber Bragg grating and FBG with the proposed novel apodization function,respectively,enhancing its utilization in the field of medicine.展开更多
Object recognition and computer vision techniques for automated object identification are attracting marine biologist’s interest as a quicker and easier tool for estimating the fish abundance in marine environments.H...Object recognition and computer vision techniques for automated object identification are attracting marine biologist’s interest as a quicker and easier tool for estimating the fish abundance in marine environments.However,the biggest problem posed by unrestricted aquatic imaging is low luminance,turbidity,background ambiguity,and context camouflage,which make traditional approaches rely on their efficiency due to inaccurate detection or elevated false-positive rates.To address these challenges,we suggest a systemic approach to merge visual features and Gaussian mixture models with You Only Look Once(YOLOv3)deep network,a coherent strategy for recognizing fish in challenging underwater images.As an image restoration phase,pre-processing based on diffraction correction is primarily applied to frames.The YOLOv3 based object recognition system is used to identify fish occurrences.The objects in the background that are camouflaged are often overlooked by the YOLOv3 model.A proposed Bi-dimensional Empirical Mode Decomposition(BEMD)algorithm,adapted by Gaussian mixture models,and integrating the results of YOLOv3 improves detection efficiency of the proposed automated underwater object detection method.The proposed approach was tested on four challenging video datasets,the Life Cross Language Evaluation Forum(CLEF)benchmark from the F4K data repository,the University of Western Australia(UWA)dataset,the bubble vision dataset and theDeepFish dataset.The accuracy for fish identification is 98.5 percent,96.77 percent,97.99 percent and 95.3 percent respectively for the various datasets which demonstrate the feasibility of our proposed automated underwater object detection method.展开更多
基金supported in part by Universiti Malaya,and ACU UK under Project No.IF063-2021.
文摘Sensors play an important role in shaping and monitoring human health.Exploration of methods to use Fiber Bragg Grating(FBG)with enhanced sensitivity has attracted great interest in the field of medical research.In this paper,a novel apodization function is proposed and performance evaluation and optimization of the same have been made.A comparison was conducted between various existing apodization functions and the proposed one based on optical characteristics and sensor parameters.The results evince the implementation of the proposed apodization function for vital sign measurement.The optical characteristics considered for evaluation are Peak Resonance Reflectivity level,Side Lobes Reflectivity level and FullWidth HalfMaximum(FWHM).The proposed novel apodization novel function has better FWHM,which is narrower than the FWHM of uniform FBG.Sensor characteristics like a quality parameter,detection accuracy and sensitivity also show improvement.The proposed novel apodization function is demonstrated to have a better shift in wavelength in terms of temperature and pulse measurement than the existing functions.The sensitivity of the proposed apodized function is enhanced with a Poly-dimethylsiloxane coating of varying thickness,which is 6 times and 5.14 times greater than uniform Fiber Bragg grating and FBG with the proposed novel apodization function,respectively,enhancing its utilization in the field of medicine.
文摘Object recognition and computer vision techniques for automated object identification are attracting marine biologist’s interest as a quicker and easier tool for estimating the fish abundance in marine environments.However,the biggest problem posed by unrestricted aquatic imaging is low luminance,turbidity,background ambiguity,and context camouflage,which make traditional approaches rely on their efficiency due to inaccurate detection or elevated false-positive rates.To address these challenges,we suggest a systemic approach to merge visual features and Gaussian mixture models with You Only Look Once(YOLOv3)deep network,a coherent strategy for recognizing fish in challenging underwater images.As an image restoration phase,pre-processing based on diffraction correction is primarily applied to frames.The YOLOv3 based object recognition system is used to identify fish occurrences.The objects in the background that are camouflaged are often overlooked by the YOLOv3 model.A proposed Bi-dimensional Empirical Mode Decomposition(BEMD)algorithm,adapted by Gaussian mixture models,and integrating the results of YOLOv3 improves detection efficiency of the proposed automated underwater object detection method.The proposed approach was tested on four challenging video datasets,the Life Cross Language Evaluation Forum(CLEF)benchmark from the F4K data repository,the University of Western Australia(UWA)dataset,the bubble vision dataset and theDeepFish dataset.The accuracy for fish identification is 98.5 percent,96.77 percent,97.99 percent and 95.3 percent respectively for the various datasets which demonstrate the feasibility of our proposed automated underwater object detection method.