Optical fiber sensors have gained significant attention in recent years owing to their remarkable advantages of remote operation and rapid response.The integration of optical fiber sensing with the microfluidics techn...Optical fiber sensors have gained significant attention in recent years owing to their remarkable advantages of remote operation and rapid response.The integration of optical fiber sensing with the microfluidics technology has paved the way for the establishment of optical fiber optofluidic sensing.Optical fiber optofluidic systems possess the advantages of the low invasiveness,compact structure,excellent biocompatibility,and the ability to handle small analyte volumes,rendering them particularly suitable for serving as chemical sensors and biosensors.In this paper,we present an in-depth overview of optical fiber optofluidic chemical sensors and biosensors.Firstly,we provide a comprehensive summary of the types of optical fibers commonly employed in optofluidic chemical and biosensing,elucidating their distinct attributes and performance characteristics.Subsequently,we introduce and thoroughly analyze several representative sensing mechanisms employed in optical fiber optofluidic systems and main performance parameters.Furthermore,this review delves into the modification and functionalization of optical fibers.Additionally,we showcase typical biosensing and chemical sensing applications to demonstrate the practicality and versatility of optical fiber optofluidic sensing.Finally,the conclusion and outlook are given.展开更多
In recent years,Deep Learning(DL)technique has been widely used in Internet of Things(IoT)and Industrial Internet of Things(IIoT)for edge computing,and achieved good performances.But more and more studies have shown t...In recent years,Deep Learning(DL)technique has been widely used in Internet of Things(IoT)and Industrial Internet of Things(IIoT)for edge computing,and achieved good performances.But more and more studies have shown the vulnerability of neural networks.So,it is important to test the robustness and vulnerability of neural networks.More specifically,inspired by layer-wise relevance propagation and neural network verification,we propose a novel measurement of sensitive neurons and important neurons,and propose a novel neuron coverage criterion for robustness testing.Based on the novel criterion,we design a novel testing sample generation method,named DeepSI,which involves definitions of sensitive neurons and important neurons.Furthermore,we construct sensitive-decision paths of the neural network through selecting sensitive neurons and important neurons.Finally,we verify our idea by setting up several experiments,then results show our proposed method achieves superior performances.展开更多
基金supported by the Heilongjiang Provincial Natural Science Foundation of China(Grant No.LH2021F019)Fundamental Research Funds for the Central Universities,China(Grant No.3072022CF2506)National Natural Science Foundation of China(Grant Nos.62305082,11574061,and 62065001).
文摘Optical fiber sensors have gained significant attention in recent years owing to their remarkable advantages of remote operation and rapid response.The integration of optical fiber sensing with the microfluidics technology has paved the way for the establishment of optical fiber optofluidic sensing.Optical fiber optofluidic systems possess the advantages of the low invasiveness,compact structure,excellent biocompatibility,and the ability to handle small analyte volumes,rendering them particularly suitable for serving as chemical sensors and biosensors.In this paper,we present an in-depth overview of optical fiber optofluidic chemical sensors and biosensors.Firstly,we provide a comprehensive summary of the types of optical fibers commonly employed in optofluidic chemical and biosensing,elucidating their distinct attributes and performance characteristics.Subsequently,we introduce and thoroughly analyze several representative sensing mechanisms employed in optical fiber optofluidic systems and main performance parameters.Furthermore,this review delves into the modification and functionalization of optical fibers.Additionally,we showcase typical biosensing and chemical sensing applications to demonstrate the practicality and versatility of optical fiber optofluidic sensing.Finally,the conclusion and outlook are given.
基金supported by the National Key R&DProgram of China(No.2021YFF0602104-2)。
文摘In recent years,Deep Learning(DL)technique has been widely used in Internet of Things(IoT)and Industrial Internet of Things(IIoT)for edge computing,and achieved good performances.But more and more studies have shown the vulnerability of neural networks.So,it is important to test the robustness and vulnerability of neural networks.More specifically,inspired by layer-wise relevance propagation and neural network verification,we propose a novel measurement of sensitive neurons and important neurons,and propose a novel neuron coverage criterion for robustness testing.Based on the novel criterion,we design a novel testing sample generation method,named DeepSI,which involves definitions of sensitive neurons and important neurons.Furthermore,we construct sensitive-decision paths of the neural network through selecting sensitive neurons and important neurons.Finally,we verify our idea by setting up several experiments,then results show our proposed method achieves superior performances.
