In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an...In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an improved SAR image small target detection method based on YOLOv7 was proposed in this study.The proposed method improved the feature extraction network by using Switchable Around Convolution(SAConv)in the backbone network to help the model capture target information at different scales,thus improving the feature extraction ability for small targets.Based on the attention mechanism,the DyHead module was embedded in the target detection head to reduce the impact of complex background,and better focus on the small targets.In addition,the NWD loss function was introduced and combined with CIoU loss.Compared to the CIoU loss function typically used in YOLOv7,the NWD loss function pays more attention to the processing of small targets,so as to further improve the detection ability of small targets.The experimental results on the HRSID dataset indicate that the proposed method achieved mAP@0.5 and mAP@0.95 scores of 93.5%and 71.5%,respectively.Compared to the baseline model,this represents an increase of 7.2%and 7.6%,respectively.The proposed method can effectively complete the task of SAR image small target detection.展开更多
In the realm of near-infrared spectroscopy,the detection of molecules has been achieved using on-chip waveguides and resonators.In the mid-infrared band,the integration and sensitivity of chemical sensing chips are of...In the realm of near-infrared spectroscopy,the detection of molecules has been achieved using on-chip waveguides and resonators.In the mid-infrared band,the integration and sensitivity of chemical sensing chips are often constrained by the reliance on off-chip light sources and detectors.In this study,we demonstrate an InAs/GaAsSb superlattice mid-infrared waveguide integrated detector.The GaAsSb waveguide layer and the InAs/GaAsSb superlattice absorbing layer are connected through evanescent coupling,facilitating efficient and highquality detection of mid-infrared light with minimal loss.We conducted a simulation to analyze the photoelectric characteristics of the device.Additionally,we investigated the factors that affect the integration of the InAs/GaAs⁃Sb superlattice photodetector and the GaAsSb waveguide.Optimal thicknesses and lengths for the absorption lay⁃er are determined.When the absorption layer has a thickness of 0.3μm and a length of 50μm,the noise equiva⁃lent power reaches its minimum value,and the quantum efficiency can achieve a value of 68.9%.The utilization of waveguide detectors constructed with Ⅲ-Ⅴ materials offers a more convenient means of integrating mid-infra⁃red light sources and achieving photoelectric detection chips.展开更多
In order to improve the accuracy and reliability of the driving fatigue detection based on a single feature, a new detection algorithm based on multiple features is proposed. Two direct driver＇s facial features refle...In order to improve the accuracy and reliability of the driving fatigue detection based on a single feature, a new detection algorithm based on multiple features is proposed. Two direct driver＇s facial features reflecting fatigue and one indirect vehicle behavior feature indicating fatigue are considered. Meanwhile, T-S fuzzy neural network（TSFNN）is adopted to recognize the driving fatigue of drivers. For the structure identification of the TSFNN, subtractive clustering（SC） is used to confirm the fuzzy rules and their correlative parameters. Moreover, the particle swarm optimization （PSO）algorithm is improved to train the TSFNN. Simulation results and experiments on vehicles show that the proposed algorithm can effectively improve the convergence speed and the recognition accuracy of the TSFNN, as well as enhance the correct rate of driving fatigue detection.展开更多
An S-N curve fitting approach is proposed based on the weighted least square method, and the weights are inversely proportional to the length of mean confidence intervals of experimental data sets. The assumption coin...An S-N curve fitting approach is proposed based on the weighted least square method, and the weights are inversely proportional to the length of mean confidence intervals of experimental data sets. The assumption coincides with the physical characteristics of the fatigue life scatter. Two examples demonstrate the method. It is shown that the method has better accuracy and reasonableness compared with the usual least square method.展开更多
Some metamorphic relations （MR） are not good at detecting faults in metamorphic testing. In this paper, the method of making compositional MR （CMR） based on the speculative law of proposition logic is presented. T...Some metamorphic relations （MR） are not good at detecting faults in metamorphic testing. In this paper, the method of making compositional MR （CMR） based on the speculative law of proposition logic is presented. This method constructs new MRs by composing existing MRs in a pairwise way. Because CMR contains all the advantages of the MRs that form it, its fault detection performance is wonderful. On the other hand, the number of relations will decrease greatly after composing, so a program can be tested with much fewer test cases when CMRs are used. In order to research the characteristics of a CMR, two case studies are analyzed. The experimental results show that the CMR＇s performance is mostly determined by the central MRs forming it and the sequence of composition. Testing efficiency is improved greatly when CMRs are used.展开更多
Monitoring on vector-borne virus lays foundation for control of vector-borne disease, and a scientific and highly-efficient surveil ance method is of great signifi-cance for prevention and control ing of vector-borne ...Monitoring on vector-borne virus lays foundation for control of vector-borne disease, and a scientific and highly-efficient surveil ance method is of great signifi-cance for prevention and control ing of vector-borne diseases. The research sum-marized mosquito and mosquito-borne disease monitoring methods and proposed problems in the monitoring system, as wel as introducing new monitoring methods at home and abroad, providing references for improvements of integrated surveil-lance of mosquito or mosquito-borne viruses.展开更多
文摘In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an improved SAR image small target detection method based on YOLOv7 was proposed in this study.The proposed method improved the feature extraction network by using Switchable Around Convolution(SAConv)in the backbone network to help the model capture target information at different scales,thus improving the feature extraction ability for small targets.Based on the attention mechanism,the DyHead module was embedded in the target detection head to reduce the impact of complex background,and better focus on the small targets.In addition,the NWD loss function was introduced and combined with CIoU loss.Compared to the CIoU loss function typically used in YOLOv7,the NWD loss function pays more attention to the processing of small targets,so as to further improve the detection ability of small targets.The experimental results on the HRSID dataset indicate that the proposed method achieved mAP@0.5 and mAP@0.95 scores of 93.5%and 71.5%,respectively.Compared to the baseline model,this represents an increase of 7.2%and 7.6%,respectively.The proposed method can effectively complete the task of SAR image small target detection.
基金Supported by the National Natural Science Foundation of China(NSFC)(61904183,61974152,62104237,62004205)the Youth Innovation Promotion Association of the Chinese Academy of Sciences(Y202057)+1 种基金Shanghai Science and Technology Committee Rising-Star Program(20QA1410500)Shanghai Sail Plans(21YF1455000)。
文摘In the realm of near-infrared spectroscopy,the detection of molecules has been achieved using on-chip waveguides and resonators.In the mid-infrared band,the integration and sensitivity of chemical sensing chips are often constrained by the reliance on off-chip light sources and detectors.In this study,we demonstrate an InAs/GaAsSb superlattice mid-infrared waveguide integrated detector.The GaAsSb waveguide layer and the InAs/GaAsSb superlattice absorbing layer are connected through evanescent coupling,facilitating efficient and highquality detection of mid-infrared light with minimal loss.We conducted a simulation to analyze the photoelectric characteristics of the device.Additionally,we investigated the factors that affect the integration of the InAs/GaAs⁃Sb superlattice photodetector and the GaAsSb waveguide.Optimal thicknesses and lengths for the absorption lay⁃er are determined.When the absorption layer has a thickness of 0.3μm and a length of 50μm,the noise equiva⁃lent power reaches its minimum value,and the quantum efficiency can achieve a value of 68.9%.The utilization of waveguide detectors constructed with Ⅲ-Ⅴ materials offers a more convenient means of integrating mid-infra⁃red light sources and achieving photoelectric detection chips.
基金The National Key Technologies R & D Program during the 11th Five-Year Plan Period(No.2009BAG13A04)the Ph.D.Programs Foundation of Ministry of Education of China(No.200802861061)the Transportation Science Research Project of Jiangsu Province(No.08X09)
文摘In order to improve the accuracy and reliability of the driving fatigue detection based on a single feature, a new detection algorithm based on multiple features is proposed. Two direct driver＇s facial features reflecting fatigue and one indirect vehicle behavior feature indicating fatigue are considered. Meanwhile, T-S fuzzy neural network（TSFNN）is adopted to recognize the driving fatigue of drivers. For the structure identification of the TSFNN, subtractive clustering（SC） is used to confirm the fuzzy rules and their correlative parameters. Moreover, the particle swarm optimization （PSO）algorithm is improved to train the TSFNN. Simulation results and experiments on vehicles show that the proposed algorithm can effectively improve the convergence speed and the recognition accuracy of the TSFNN, as well as enhance the correct rate of driving fatigue detection.
文摘An S-N curve fitting approach is proposed based on the weighted least square method, and the weights are inversely proportional to the length of mean confidence intervals of experimental data sets. The assumption coincides with the physical characteristics of the fatigue life scatter. Two examples demonstrate the method. It is shown that the method has better accuracy and reasonableness compared with the usual least square method.
基金The National Natural Science Foundation of China(No.60425206,60633010,60773104,60503033)the Excellent Talent Foundation of Teaching and Research of Southeast University
文摘Some metamorphic relations （MR） are not good at detecting faults in metamorphic testing. In this paper, the method of making compositional MR （CMR） based on the speculative law of proposition logic is presented. This method constructs new MRs by composing existing MRs in a pairwise way. Because CMR contains all the advantages of the MRs that form it, its fault detection performance is wonderful. On the other hand, the number of relations will decrease greatly after composing, so a program can be tested with much fewer test cases when CMRs are used. In order to research the characteristics of a CMR, two case studies are analyzed. The experimental results show that the CMR＇s performance is mostly determined by the central MRs forming it and the sequence of composition. Testing efficiency is improved greatly when CMRs are used.
基金Supported by Nanchang Center for Disease Control and Prevention~~
文摘Monitoring on vector-borne virus lays foundation for control of vector-borne disease, and a scientific and highly-efficient surveil ance method is of great signifi-cance for prevention and control ing of vector-borne diseases. The research sum-marized mosquito and mosquito-borne disease monitoring methods and proposed problems in the monitoring system, as wel as introducing new monitoring methods at home and abroad, providing references for improvements of integrated surveil-lance of mosquito or mosquito-borne viruses.
