A measurement system for the scattering characteristics of warhead fragments based on high-speed imaging systems offers advantages such as simple deployment,flexible maneuverability,and high spatiotemporal resolution,...A measurement system for the scattering characteristics of warhead fragments based on high-speed imaging systems offers advantages such as simple deployment,flexible maneuverability,and high spatiotemporal resolution,enabling the acquisition of full-process data of the fragment scattering process.However,mismatches between camera frame rates and target velocities can lead to long motion blur tails of high-speed fragment targets,resulting in low signal-to-noise ratios and rendering conventional detection algorithms ineffective in dynamic strong interference testing environments.In this study,we propose a detection framework centered on dynamic strong interference disturbance signal separation and suppression.We introduce a mixture Gaussian model constrained under a joint spatialtemporal-transform domain Dirichlet process,combined with total variation regularization to achieve disturbance signal suppression.Experimental results demonstrate that the proposed disturbance suppression method can be integrated with certain conventional motion target detection tasks,enabling adaptation to real-world data to a certain extent.Moreover,we provide a specific implementation of this process,which achieves a detection rate close to 100%with an approximate 0%false alarm rate in multiple sets of real target field test data.This research effectively advances the development of the field of damage parameter testing.展开更多
Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view,but their unique imaging characteristics pose challenges like distortion,complex scenes,scale variations,and small objec...Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view,but their unique imaging characteristics pose challenges like distortion,complex scenes,scale variations,and small objects near image edges.To tackle these,we proposed peripheral focus you only look once(PF-YOLO),an enhanced YOLOv8n-based method.Firstly,we introduced a cutting-patch data augmentation strategy to mitigate the problem of insufficient small-object samples in various scenes.Secondly,to enhance the model's focus on small objects near the edges,we designed the peripheral focus loss,which uses dynamic focus coefficients to provide greater gradient gains for these objects,improving their regression accuracy.Finally,we designed the three dimensional(3D)spatial-channel coordinate attention C2f module,enhancing spatial and channel perception,suppressing noise,and improving personnel detection.Experimental results demonstrate that PF-YOLO achieves strong performance on the challenging events for person detection from overhead fisheye images(CEPDTOF)and in-the-wild events for people detection and tracking from overhead fisheye cameras(WEPDTOF)datasets.Compared to the original YOLOv8n model,PFYOLO achieves improvements on CEPDTOF with increases of 2.1%,1.7%and 2.9%in mean average precision 50(mAP 50),mAP 50-95,and tively.On WEPDTOF,PF-YOLO achieves substantial improvements with increases of 31.4%,14.9%,61.1%and 21.0%in 91.2%and 57.2%,respectively.展开更多
Detection of target analytes at low concentrations is significant in various fields,including pharmaceuticals,healthcare,and environmental protection.Theophylline(TP),a natural alkaloid used as a bronchodilator to tre...Detection of target analytes at low concentrations is significant in various fields,including pharmaceuticals,healthcare,and environmental protection.Theophylline(TP),a natural alkaloid used as a bronchodilator to treat respiratory disorders such as asthma,bronchitis,and emphysema,has a narrow therapeutic window with a safe plasma concentration ranging from 55.5-111.0μmol·L^(-1)in adults.Accurate monitoring of TP levels is essential because too low or too high can cause se-rious side effects.In this regard,non-enzymatic electrochemical sensors offer a practical solution with rapidity,portability,and high sensitivity.This article aims to provide a comprehensive review of the recent developments of non-enzymatic electrochemical sensors for TP detection,highlighting the basic principles,electro-oxidation mechanisms,catalytic effects,and the role of modifying materials on electrode performance.Carbon-based electrodes such as glassy carbon electrodes(GCEs),carbon paste electrodes(CPEs),and carbon screen-printed electrodes(SPCEs)have become the primary choices for non-enzymatic sensors due to their chemical stability,low cost,and flexibility in modification.This article identifies the sig-nificant contribution of various modifying materials,including nanomaterials such as carbon nanotubes(CNTs),graphene,metal oxides,and multi-element nanocomposites.These modifications enhance sensors’electron transfer,sensitivity,and selectivity in detecting TP at low concentrations in complex media such as blood plasma and pharmaceutical samples.The electro-oxidation mechanism of TP is also discussed in depth,emphasizing the hydroxyl and carbonyl reaction pathways strongly influenced by pH and electrode materials.These mechanisms guide the selection of the appropriate electrode ma-terial for a particular application.The main contribution of this article is to identify superior modifying materials that can improve the performance of non-enzymatic electrochemical sensors.In a recent study,the combination of multi-element nanocomposites based on titanium dioxide(TiO_(2)),CNTs,and gold nanoparticles(AuNPs)resulted in the lowest detection limit of 3×10^(-5)μmol·L^(-1),reflecting the great potential of these materials for developing high-performance electrochemical sensors.The main conclusion of this article is the importance of a multidisciplinary approach in electrode material design to support the sensitivity and selectivity of TP detection.In addition,there is still a research gap in understanding TP’s more detailed oxidation mechanism,especially under pH variations and complex environments.Therefore,further research on electrode modification and analysis of the TP oxidation mechanism are urgently needed to improve the accuracy and sta-bility of the sensor while expanding its applications in pharmaceutical monitoring and medical diagnostics.By integrating various innovative materials and technical approaches,this review is expected to be an essential reference for developing efficient and affordable non-enzymatic electrochemical sensors.展开更多
In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal...In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.展开更多
4-Nonylphenol(NP)is a kind of estrogen belonging to the endocrine disrupter,widely used in various agricultural and industrial goods.However,extensive use of NP with direct release to environment poses high risks to b...4-Nonylphenol(NP)is a kind of estrogen belonging to the endocrine disrupter,widely used in various agricultural and industrial goods.However,extensive use of NP with direct release to environment poses high risks to both human health and ecosystems.Herein,for the first time,we developed near-infrared(NIR)responsive upconversion luminescence nanosensor for NP detection.The Förster resonance energy transfer based upconversion nanoparticles(UCNPs)-graphene oxide sensor offers highly selective and sensitive detection of NP in linear ranges of 5−200 ng/mL and 200−1000 ng/mL under 980 nm and 808 nm excitation,respectively,with LOD at 4.2 ng/mL.The sensors were successfully tested for NP detection in real liquid milk samples with excellent recovery results.The rare-earth fluoride based upconversion luminescence nanosensor with NIR excitation wavelength,holds promise for sensing food,environmental,and biological samples due to their high sensitivity,specific recognition,low LOD,negligible autofluorescence,along with the deep penetration of NIR excitation sources.展开更多
Acrylamide(AA)is a neurotoxin and carcinogen that formed during the thermal food processing.Conventional quantification techniques are difficult to realize on-site detection of AA.Herein,a flower-like bimetallic FeCu ...Acrylamide(AA)is a neurotoxin and carcinogen that formed during the thermal food processing.Conventional quantification techniques are difficult to realize on-site detection of AA.Herein,a flower-like bimetallic FeCu nanozyme(FeCuzyme)sensor and portable platform were developed for naked-eye and on-site detection of AA.The FeCuzyme was successfully prepared and exhibited flower-like structure with 3D catalytic centers.Fe/Cu atoms were considered as active center and ligand frameworks were used as cofactor,resulting in collaborative substrate-binding features and remarkably peroxidase-like activity.During the catalytic process,the 3,3′,5,5′-tetrame-thylbenzidine(TMB)oxidation can be quenched by glutathione(GSH),and then restored after thiolene Michael addition reaction between GSH and AA.Given the“on–off–on”effect for TMB oxidation and high PODlike activity,FeCuzyme sensor exhibited a wide linear relationship from 0.50 to 18.00μM(R^(2)=0.9987)and high sensitivity(LOD=0.2360μM)with high stability.The practical application of FeCuzyme sensor was successfully validated by HPLC method.Furthermore,a FeCuzyme portable platform was designed with smartphone/laptop,and which can be used for naked-eye and on-site quantitative determination of AA in real food samples.This research provides a way for rational design of a novel nanozyme-based sensing platform for AA detection.展开更多
Intrusion detection systems play a vital role in cyberspace security.In this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusio...Intrusion detection systems play a vital role in cyberspace security.In this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusion of a recursive feature elimination(RFE)algorithm and a bidirectional gated recurrent unit(BGRU).Particularly,the RFE algorithm is employed to select features from high-dimensional data to reduce weak correlations between features and remove redundant features in the numerical feature space.Then,a neural network that combines the BGRU and multilayer perceptron(MLP)is adopted to extract deep intrusion behavior features.Finally,a support vector machine(SVM)classifier is used to classify intrusion behaviors.The proposed model is verified by experiments on the NSL-KDD dataset.The results indicate that the proposed model achieves a 90.25%accuracy and a 97.51%detection rate in binary classification and outperforms other machine learning and deep learning models in intrusion classification.The proposed method can provide new insight into network intrusion detection.展开更多
This paper concerns the exponential attitude-orbit coordinated control problems for gravitational-wave detection formation spacecraft systems.Notably,the large-scale communication delays resulting from oversized inter...This paper concerns the exponential attitude-orbit coordinated control problems for gravitational-wave detection formation spacecraft systems.Notably,the large-scale communication delays resulting from oversized inter-satellite distance of space-based laser interferometers are first modeled.Subject to the delayed communication behaviors,a new delay-dependent attitude-orbit coordinated controller is designed.Moreover,by reconstructing the less conservative Lyapunov-Krasovskii functional and free-weight matrices,sufficient criteria are derived to ensure the exponential stability of the closed-loop relative translation and attitude error system.Finally,a simulation example is employed to illustrate the numerical validity of the proposed controller for in-orbit detection missions.展开更多
Semantic communication(SemCom)aims to achieve high-fidelity information delivery under low communication consumption by only guaranteeing semantic accuracy.Nevertheless,semantic communication still suffers from unexpe...Semantic communication(SemCom)aims to achieve high-fidelity information delivery under low communication consumption by only guaranteeing semantic accuracy.Nevertheless,semantic communication still suffers from unexpected channel volatility and thus developing a re-transmission mechanism(e.g.,hybrid automatic repeat request[HARQ])becomes indispensable.In that regard,instead of discarding previously transmitted information,the incremental knowledge-based HARQ(IK-HARQ)is deemed as a more effective mechanism that could sufficiently utilize the information semantics.However,considering the possible existence of semantic ambiguity in image transmission,a simple bit-level cyclic redundancy check(CRC)might compromise the performance of IK-HARQ.Therefore,there emerges a strong incentive to revolutionize the CRC mechanism,thus more effectively reaping the benefits of both SemCom and HARQ.In this paper,built on top of swin transformer-based joint source-channel coding(JSCC)and IK-HARQ,we propose a semantic image transmission framework SC-TDA-HARQ.In particular,different from the conventional CRC,we introduce a topological data analysis(TDA)-based error detection method,which capably digs out the inner topological and geometric information of images,to capture semantic information and determine the necessity for re-transmission.Extensive numerical results validate the effectiveness and efficiency of the proposed SC-TDA-HARQ framework,especially under the limited bandwidth condition,and manifest the superiority of TDA-based error detection method in image transmission.展开更多
We present the experimental demonstration of nondestructive detection of ^(171)Yb atoms in a magneto-optical trap(MOT) based on phase shift measurement induced by the atoms on a weak off-resonant laser beam. After loa...We present the experimental demonstration of nondestructive detection of ^(171)Yb atoms in a magneto-optical trap(MOT) based on phase shift measurement induced by the atoms on a weak off-resonant laser beam. After loading a green MOT of ^(171)Yb atoms, the phase shift is obtained with a two-color Mach–Zehnder interferometer by means of ±45 MHz detuning with respect to the ^(1)S_(0)–^(1)P_(1) transition. We measured a phase shift of about 100 mrad corresponding to an atom count of around 5 × 10^(5). This demonstrates that it is possible to obtain the number of atoms without direct destructive measurement compared with the absorption imaging method. This scheme could be an important approach towards a high-precision lattice clock for clock operation through suppression of the impact of the Dick effect.展开更多
Complex-valued double-sideband direct detection(DD)can reconstruct the optical field and achieve a high electrical spectral efficiency(ESE)comparable to that of a coherent homodyne receiver,and DD does not require a c...Complex-valued double-sideband direct detection(DD)can reconstruct the optical field and achieve a high electrical spectral efficiency(ESE)comparable to that of a coherent homodyne receiver,and DD does not require a costly local oscillator laser.However,a fundamental question remains if there is an optimal DD receiver structure with the simplest design to approach the performance of the coherent homodyne detection.This study derives the optimal DD receiver structure with an optimal transfer function to recover a quadrature amplitude modulation(QAM)signal with a near-zero guard band at the central frequency of the signal.We derive the theoretical ESE limit for various detection schemes by invoking Shannon’s formula.Our proposed scheme is closest to coherent homodyne detection in terms of the theoretical ESE limit.By leveraging a WaveShaper to construct the optimal transfer function,we conduct a proof-of-concept experiment to transmit a net 228.85-Gb/s 64-QAM signal over an 80-km single-mode fiber with a net ESE of 8.76 b/s/Hz.To the best of our knowledge,this study reports the highest net ESE per polarization per wavelength for DD transmission beyond 40-km single-mode fiber.For a comprehensive metric,denoted as 2ESE×Reach,we achieve the highest 2ESE×Reach per polarization per wavelength for DD transmission.展开更多
This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-t...This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-term memory(LSTM)neural network model is proposed to monitor the operational state of the converter and accurately detect faults as they occur.By sampling and processing a large number of thyristor converter operation data,the LSTM model is trained to identify and detect abnormal state,and the power supply health status is monitored.Compared with traditional methods,LSTM model shows higher accuracy and abnormal state detection ability.The experimental results show that this method can effectively improve the reliability and safety of the thyristor converter,and provide a strong guarantee for the stable operation of the nuclear fusion reactor.展开更多
To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection...To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection method.Hence,we proposed an intrusion detection algorithm based on convolutional neural network(CNN)and AdaBoost algorithm.This algorithm uses CNN to extract the characteristics of network traffic data,which is particularly suitable for the analysis of continuous and classified attack data.The AdaBoost algorithm is used to classify network attack data that improved the detection effect of unbalanced data classification.We adopt the UNSW-NB15 dataset to test of this algorithm in the PyCharm environment.The results show that the detection rate of algorithm is99.27%and the false positive rate is lower than 0.98%.Comparative analysis shows that this algorithm has advantages over existing methods in terms of detection rate and false positive rate for small proportion of attack data.展开更多
In the field of remote sensing,the rapid and accurate acquisition of the category and location of airplanes has emerged as a prominent research.However,remote sensing fuzzy imaging and complex environmental interferen...In the field of remote sensing,the rapid and accurate acquisition of the category and location of airplanes has emerged as a prominent research.However,remote sensing fuzzy imaging and complex environmental interference affect airplane detection.Besides,the inconsistency in the size of remote sensing images and the low accuracy of small target detection are crucial challenges that need to be addressed.To tackle these issues,we propose a novel network SDaDCS(SAHI-data augmentation-dilation-channel and spatial attention)based on YOLOX model and the slicing aided hyper inference(SAHI)framework,a new data augmentation technique and dilation-channel and spatial(DCS)attention mechanism.Initially,we create a remote sensing dataset for airplane targets and introduce a new data augmentation technique based on the Rotate-Mixup and mixed data augmentation to enhance data diversity.The DCS attention mechanism,which comprises the dilated convolution block,channel attention and spatial attention,is designed to bolster the feature extraction and discrimination of the network.To address the challenges arised by the difficulties of detecting small targets,we integrate the YOLOX model with the SAHI framework.Experiment results show that,when compared to the original YOLOX model,the proposed SDaDCS remote sensing target detection algorithm enhances overall accuracy by 13.6%.The experimental results validate the effectiveness of the proposed algorithm.展开更多
In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have differ...In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.展开更多
The specific detection of tumor markers is crucial in early tumor screening and subsequent treatment processes.To ac-curately distinguish the signal response caused by trace markers,the high demodulation resolution of...The specific detection of tumor markers is crucial in early tumor screening and subsequent treatment processes.To ac-curately distinguish the signal response caused by trace markers,the high demodulation resolution of the sensor is necessary.In this paper,we propose a dual-wavelength fiber laser sensing system enhanced with microwave photonics de-modulation technology to achieve high-resolution tumor marker detection.This sensing system can simultaneously perform spectral wavelength-domain and frequency-domain analyses.Experimental results demonstrate that this system's refractive index(RI)sensitivity reaches 1083 nm/RIU by wavelength analysis and-1902 GHz/RIU by frequency analysis,with ideal detection resolutions of 1.85×10^(-5)RIU and 5.26×10^(-8)RIU,respectively.Compared with traditional wavelength domain analysis,the demodulation resolution is improved by three orders of magnitude,based on the same sensing structure.To validate its biosensing performance,carcinoembryonic antigen-related cell adhesion molecule 5(CEACAM5)is selected as the detection target.Experimental results show that the improved sensing system has a limit of detection(LOD)of 0.076 ng/mL and a detection resolution of 0.008 ng/mL.Experimental results obtained from human serum samples are consistent with clinical data,highlighting the strong clinical application potential of the proposed sens-ing system and analysis method.展开更多
Recently,anomaly detection(AD)in streaming data gained significant attention among research communities due to its applicability in finance,business,healthcare,education,etc.The recent developments of deep learning(DL...Recently,anomaly detection(AD)in streaming data gained significant attention among research communities due to its applicability in finance,business,healthcare,education,etc.The recent developments of deep learning(DL)models find helpful in the detection and classification of anomalies.This article designs an oversampling with an optimal deep learning-based streaming data classification(OS-ODLSDC)model.The aim of the OSODLSDC model is to recognize and classify the presence of anomalies in the streaming data.The proposed OS-ODLSDC model initially undergoes preprocessing step.Since streaming data is unbalanced,support vector machine(SVM)-Synthetic Minority Over-sampling Technique(SVM-SMOTE)is applied for oversampling process.Besides,the OS-ODLSDC model employs bidirectional long short-term memory(Bi LSTM)for AD and classification.Finally,the root means square propagation(RMSProp)optimizer is applied for optimal hyperparameter tuning of the Bi LSTM model.For ensuring the promising performance of the OS-ODLSDC model,a wide-ranging experimental analysis is performed using three benchmark datasets such as CICIDS 2018,KDD-Cup 1999,and NSL-KDD datasets.展开更多
The advent of pandemics such as COVID-19 significantly impacts human behaviour and lives every day.Therefore,it is essential to make medical services connected to internet,available in every remote location during the...The advent of pandemics such as COVID-19 significantly impacts human behaviour and lives every day.Therefore,it is essential to make medical services connected to internet,available in every remote location during these situations.Also,the security issues in the Internet of Medical Things(IoMT)used in these service,make the situation even more critical because cyberattacks on the medical devices might cause treatment delays or clinical failures.Hence,services in the healthcare ecosystem need rapid,uninterrupted,and secure facilities.The solution provided in this research addresses security concerns and services availability for patients with critical health in remote areas.This research aims to develop an intelligent Software Defined Networks(SDNs)enabled secure framework for IoT healthcare ecosystem.We propose a hybrid of machine learning and deep learning techniques(DNN+SVM)to identify network intrusions in the sensor-based healthcare data.In addition,this system can efficiently monitor connected devices and suspicious behaviours.Finally,we evaluate the performance of our proposed framework using various performance metrics based on the healthcare application scenarios.the experimental results show that the proposed approach effectively detects and mitigates attacks in the SDN-enabled IoT networks and performs better that other state-of-art-approaches.展开更多
The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields.Cryptographic algorithms and smart contracts are critical components of blockchain security.De...The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields.Cryptographic algorithms and smart contracts are critical components of blockchain security.Despite the benefits of virtual currency,vulnerabilities in smart contracts have resulted in substantial losses to users.While researchers have identified these vulnerabilities and developed tools for detecting them,the accuracy of these tools is still far from satisfactory,with high false positive and false negative rates.In this paper,we propose a new method for detecting vulnerabilities in smart contracts using the BERT pre-training model,which can quickly and effectively process and detect smart contracts.More specifically,we preprocess and make symbol substitution in the contract,which can make the pre-training model better obtain contract features.We evaluate our method on four datasets and compare its performance with other deep learning models and vulnerability detection tools,demonstrating its superior accuracy.展开更多
Timely inspection of defects on the surfaces of wind turbine blades can effectively prevent unpredictable accidents.To this end,this study proposes a semi-supervised object-detection network based on You Only Looking ...Timely inspection of defects on the surfaces of wind turbine blades can effectively prevent unpredictable accidents.To this end,this study proposes a semi-supervised object-detection network based on You Only Looking Once version 4(YOLOv4).A semi-supervised structure comprising a generative adversarial network(GAN)was designed to overcome the difficulty in obtaining sufficient samples and sample labeling.In a GAN,the generator is realized by an encoder-decoder network,where the backbone of the encoder is YOLOv4 and the decoder comprises inverse convolutional layers.Partial features from the generator are passed to the defect detection network.Deploying several unlabeled images can significantly improve the generalization and recognition capabilities of defect-detection models.The small-scale object detection capacity of the network can be improved by enhancing essential features in the feature map by adding the concurrent spatial and channel squeeze and excitation(scSE)attention module to the three parts of the YOLOv4 network.A balancing improvement was made to the loss function of YOLOv4 to overcome the imbalance problem of the defective species.The results for both the single-and multi-category defect datasets show that the improved model can make good use of the features of the unlabeled images.The accuracy of wind turbine blade defect detection also has a significant advantage over classical object detection algorithms,including faster R-CNN and DETR.展开更多
文摘A measurement system for the scattering characteristics of warhead fragments based on high-speed imaging systems offers advantages such as simple deployment,flexible maneuverability,and high spatiotemporal resolution,enabling the acquisition of full-process data of the fragment scattering process.However,mismatches between camera frame rates and target velocities can lead to long motion blur tails of high-speed fragment targets,resulting in low signal-to-noise ratios and rendering conventional detection algorithms ineffective in dynamic strong interference testing environments.In this study,we propose a detection framework centered on dynamic strong interference disturbance signal separation and suppression.We introduce a mixture Gaussian model constrained under a joint spatialtemporal-transform domain Dirichlet process,combined with total variation regularization to achieve disturbance signal suppression.Experimental results demonstrate that the proposed disturbance suppression method can be integrated with certain conventional motion target detection tasks,enabling adaptation to real-world data to a certain extent.Moreover,we provide a specific implementation of this process,which achieves a detection rate close to 100%with an approximate 0%false alarm rate in multiple sets of real target field test data.This research effectively advances the development of the field of damage parameter testing.
基金supported by National Natural Science Foundation of China(Nos.62171042,62102033,U24A20331)the R&D Program of Beijing Municipal Education Commission(No.KZ202211417048)+2 种基金the Project of Construction and Support for High-Level Innovative Teams of Beijing Municipal Institutions(No.BPHR20220121)Beijing Natural Science Foundation(Nos.4232026,4242020)the Academic Research Projects of Beijing Union University(Nos.ZKZD202302,ZK20202403)。
文摘Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view,but their unique imaging characteristics pose challenges like distortion,complex scenes,scale variations,and small objects near image edges.To tackle these,we proposed peripheral focus you only look once(PF-YOLO),an enhanced YOLOv8n-based method.Firstly,we introduced a cutting-patch data augmentation strategy to mitigate the problem of insufficient small-object samples in various scenes.Secondly,to enhance the model's focus on small objects near the edges,we designed the peripheral focus loss,which uses dynamic focus coefficients to provide greater gradient gains for these objects,improving their regression accuracy.Finally,we designed the three dimensional(3D)spatial-channel coordinate attention C2f module,enhancing spatial and channel perception,suppressing noise,and improving personnel detection.Experimental results demonstrate that PF-YOLO achieves strong performance on the challenging events for person detection from overhead fisheye images(CEPDTOF)and in-the-wild events for people detection and tracking from overhead fisheye cameras(WEPDTOF)datasets.Compared to the original YOLOv8n model,PFYOLO achieves improvements on CEPDTOF with increases of 2.1%,1.7%and 2.9%in mean average precision 50(mAP 50),mAP 50-95,and tively.On WEPDTOF,PF-YOLO achieves substantial improvements with increases of 31.4%,14.9%,61.1%and 21.0%in 91.2%and 57.2%,respectively.
基金the funding from Lembaga Penelitian dan Pengabdian Masyarakat(LPPM)Universitas Indonesia,by Riset Kolaborasi Indonesia(RKI)-World Class University(WCU)Program with grant number NKB-1067/UN2-RST/HKP.05.00/2023 and NKB-781/UN2.RST/HKP.05.00/2024.
文摘Detection of target analytes at low concentrations is significant in various fields,including pharmaceuticals,healthcare,and environmental protection.Theophylline(TP),a natural alkaloid used as a bronchodilator to treat respiratory disorders such as asthma,bronchitis,and emphysema,has a narrow therapeutic window with a safe plasma concentration ranging from 55.5-111.0μmol·L^(-1)in adults.Accurate monitoring of TP levels is essential because too low or too high can cause se-rious side effects.In this regard,non-enzymatic electrochemical sensors offer a practical solution with rapidity,portability,and high sensitivity.This article aims to provide a comprehensive review of the recent developments of non-enzymatic electrochemical sensors for TP detection,highlighting the basic principles,electro-oxidation mechanisms,catalytic effects,and the role of modifying materials on electrode performance.Carbon-based electrodes such as glassy carbon electrodes(GCEs),carbon paste electrodes(CPEs),and carbon screen-printed electrodes(SPCEs)have become the primary choices for non-enzymatic sensors due to their chemical stability,low cost,and flexibility in modification.This article identifies the sig-nificant contribution of various modifying materials,including nanomaterials such as carbon nanotubes(CNTs),graphene,metal oxides,and multi-element nanocomposites.These modifications enhance sensors’electron transfer,sensitivity,and selectivity in detecting TP at low concentrations in complex media such as blood plasma and pharmaceutical samples.The electro-oxidation mechanism of TP is also discussed in depth,emphasizing the hydroxyl and carbonyl reaction pathways strongly influenced by pH and electrode materials.These mechanisms guide the selection of the appropriate electrode ma-terial for a particular application.The main contribution of this article is to identify superior modifying materials that can improve the performance of non-enzymatic electrochemical sensors.In a recent study,the combination of multi-element nanocomposites based on titanium dioxide(TiO_(2)),CNTs,and gold nanoparticles(AuNPs)resulted in the lowest detection limit of 3×10^(-5)μmol·L^(-1),reflecting the great potential of these materials for developing high-performance electrochemical sensors.The main conclusion of this article is the importance of a multidisciplinary approach in electrode material design to support the sensitivity and selectivity of TP detection.In addition,there is still a research gap in understanding TP’s more detailed oxidation mechanism,especially under pH variations and complex environments.Therefore,further research on electrode modification and analysis of the TP oxidation mechanism are urgently needed to improve the accuracy and sta-bility of the sensor while expanding its applications in pharmaceutical monitoring and medical diagnostics.By integrating various innovative materials and technical approaches,this review is expected to be an essential reference for developing efficient and affordable non-enzymatic electrochemical sensors.
文摘In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.
文摘4-Nonylphenol(NP)is a kind of estrogen belonging to the endocrine disrupter,widely used in various agricultural and industrial goods.However,extensive use of NP with direct release to environment poses high risks to both human health and ecosystems.Herein,for the first time,we developed near-infrared(NIR)responsive upconversion luminescence nanosensor for NP detection.The Förster resonance energy transfer based upconversion nanoparticles(UCNPs)-graphene oxide sensor offers highly selective and sensitive detection of NP in linear ranges of 5−200 ng/mL and 200−1000 ng/mL under 980 nm and 808 nm excitation,respectively,with LOD at 4.2 ng/mL.The sensors were successfully tested for NP detection in real liquid milk samples with excellent recovery results.The rare-earth fluoride based upconversion luminescence nanosensor with NIR excitation wavelength,holds promise for sensing food,environmental,and biological samples due to their high sensitivity,specific recognition,low LOD,negligible autofluorescence,along with the deep penetration of NIR excitation sources.
基金supported by the National Natural Science Foundation of China(32060577 and 32360619)Natural Science Foundation of Jiangxi Province(20224ACB203016 and 20212BAB203034)the Open Project of China Food Flavor and Nutrition Health Innovation Center(CFC2023B-013).
文摘Acrylamide(AA)is a neurotoxin and carcinogen that formed during the thermal food processing.Conventional quantification techniques are difficult to realize on-site detection of AA.Herein,a flower-like bimetallic FeCu nanozyme(FeCuzyme)sensor and portable platform were developed for naked-eye and on-site detection of AA.The FeCuzyme was successfully prepared and exhibited flower-like structure with 3D catalytic centers.Fe/Cu atoms were considered as active center and ligand frameworks were used as cofactor,resulting in collaborative substrate-binding features and remarkably peroxidase-like activity.During the catalytic process,the 3,3′,5,5′-tetrame-thylbenzidine(TMB)oxidation can be quenched by glutathione(GSH),and then restored after thiolene Michael addition reaction between GSH and AA.Given the“on–off–on”effect for TMB oxidation and high PODlike activity,FeCuzyme sensor exhibited a wide linear relationship from 0.50 to 18.00μM(R^(2)=0.9987)and high sensitivity(LOD=0.2360μM)with high stability.The practical application of FeCuzyme sensor was successfully validated by HPLC method.Furthermore,a FeCuzyme portable platform was designed with smartphone/laptop,and which can be used for naked-eye and on-site quantitative determination of AA in real food samples.This research provides a way for rational design of a novel nanozyme-based sensing platform for AA detection.
基金supported in part by the National Natural Science Foundation of China(No.62001333)the Scientific Research Project of Education Department of Hubei Province(No.D20221702).
文摘Intrusion detection systems play a vital role in cyberspace security.In this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusion of a recursive feature elimination(RFE)algorithm and a bidirectional gated recurrent unit(BGRU).Particularly,the RFE algorithm is employed to select features from high-dimensional data to reduce weak correlations between features and remove redundant features in the numerical feature space.Then,a neural network that combines the BGRU and multilayer perceptron(MLP)is adopted to extract deep intrusion behavior features.Finally,a support vector machine(SVM)classifier is used to classify intrusion behaviors.The proposed model is verified by experiments on the NSL-KDD dataset.The results indicate that the proposed model achieves a 90.25%accuracy and a 97.51%detection rate in binary classification and outperforms other machine learning and deep learning models in intrusion classification.The proposed method can provide new insight into network intrusion detection.
基金supported by the Na⁃tional Key R&D Program of China(No.2022YFC2204800)the Graduate Student Independent Exploration and Innovation Program of Central South University(No.2024ZZTS 0767).
文摘This paper concerns the exponential attitude-orbit coordinated control problems for gravitational-wave detection formation spacecraft systems.Notably,the large-scale communication delays resulting from oversized inter-satellite distance of space-based laser interferometers are first modeled.Subject to the delayed communication behaviors,a new delay-dependent attitude-orbit coordinated controller is designed.Moreover,by reconstructing the less conservative Lyapunov-Krasovskii functional and free-weight matrices,sufficient criteria are derived to ensure the exponential stability of the closed-loop relative translation and attitude error system.Finally,a simulation example is employed to illustrate the numerical validity of the proposed controller for in-orbit detection missions.
基金supported in part by the National Key Research and Development Program of China under Grant 2024YFE0200600in part by the National Natural Science Foundation of China under Grant 62071425+3 种基金in part by the Zhejiang Key Research and Development Plan under Grant 2022C01093in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LR23F010005in part by the National Key Laboratory of Wireless Communications Foundation under Grant 2023KP01601in part by the Big Data and Intelligent Computing Key Lab of CQUPT under Grant BDIC-2023-B-001.
文摘Semantic communication(SemCom)aims to achieve high-fidelity information delivery under low communication consumption by only guaranteeing semantic accuracy.Nevertheless,semantic communication still suffers from unexpected channel volatility and thus developing a re-transmission mechanism(e.g.,hybrid automatic repeat request[HARQ])becomes indispensable.In that regard,instead of discarding previously transmitted information,the incremental knowledge-based HARQ(IK-HARQ)is deemed as a more effective mechanism that could sufficiently utilize the information semantics.However,considering the possible existence of semantic ambiguity in image transmission,a simple bit-level cyclic redundancy check(CRC)might compromise the performance of IK-HARQ.Therefore,there emerges a strong incentive to revolutionize the CRC mechanism,thus more effectively reaping the benefits of both SemCom and HARQ.In this paper,built on top of swin transformer-based joint source-channel coding(JSCC)and IK-HARQ,we propose a semantic image transmission framework SC-TDA-HARQ.In particular,different from the conventional CRC,we introduce a topological data analysis(TDA)-based error detection method,which capably digs out the inner topological and geometric information of images,to capture semantic information and determine the necessity for re-transmission.Extensive numerical results validate the effectiveness and efficiency of the proposed SC-TDA-HARQ framework,especially under the limited bandwidth condition,and manifest the superiority of TDA-based error detection method in image transmission.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. U20A2075,11803072,and 12374467)the Innovation Program for Quantum Science and Technology (Grant No. 2021ZD0300902)the Hubei Provincial Science and Technology Major Project (Grant No. ZDZX2022000004)。
文摘We present the experimental demonstration of nondestructive detection of ^(171)Yb atoms in a magneto-optical trap(MOT) based on phase shift measurement induced by the atoms on a weak off-resonant laser beam. After loading a green MOT of ^(171)Yb atoms, the phase shift is obtained with a two-color Mach–Zehnder interferometer by means of ±45 MHz detuning with respect to the ^(1)S_(0)–^(1)P_(1) transition. We measured a phase shift of about 100 mrad corresponding to an atom count of around 5 × 10^(5). This demonstrates that it is possible to obtain the number of atoms without direct destructive measurement compared with the absorption imaging method. This scheme could be an important approach towards a high-precision lattice clock for clock operation through suppression of the impact of the Dick effect.
基金supported by the National Natural Science Foundation of China(62341508).
文摘Complex-valued double-sideband direct detection(DD)can reconstruct the optical field and achieve a high electrical spectral efficiency(ESE)comparable to that of a coherent homodyne receiver,and DD does not require a costly local oscillator laser.However,a fundamental question remains if there is an optimal DD receiver structure with the simplest design to approach the performance of the coherent homodyne detection.This study derives the optimal DD receiver structure with an optimal transfer function to recover a quadrature amplitude modulation(QAM)signal with a near-zero guard band at the central frequency of the signal.We derive the theoretical ESE limit for various detection schemes by invoking Shannon’s formula.Our proposed scheme is closest to coherent homodyne detection in terms of the theoretical ESE limit.By leveraging a WaveShaper to construct the optimal transfer function,we conduct a proof-of-concept experiment to transmit a net 228.85-Gb/s 64-QAM signal over an 80-km single-mode fiber with a net ESE of 8.76 b/s/Hz.To the best of our knowledge,this study reports the highest net ESE per polarization per wavelength for DD transmission beyond 40-km single-mode fiber.For a comprehensive metric,denoted as 2ESE×Reach,we achieve the highest 2ESE×Reach per polarization per wavelength for DD transmission.
基金supported by the Open Fund of Magnetic Confinement Fusion Laboratory of Anhui Province(No.2024AMF04003)the Natural Science Foundation of Anhui Province(No.228085ME142)Comprehensive Research Facility for Fusion Technology(No.20180000527301001228)。
文摘This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-term memory(LSTM)neural network model is proposed to monitor the operational state of the converter and accurately detect faults as they occur.By sampling and processing a large number of thyristor converter operation data,the LSTM model is trained to identify and detect abnormal state,and the power supply health status is monitored.Compared with traditional methods,LSTM model shows higher accuracy and abnormal state detection ability.The experimental results show that this method can effectively improve the reliability and safety of the thyristor converter,and provide a strong guarantee for the stable operation of the nuclear fusion reactor.
基金supported in part by the National Key R&D Program of China(No.2022YFB3904503)National Natural Science Foundation of China(No.62172418)。
文摘To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection method.Hence,we proposed an intrusion detection algorithm based on convolutional neural network(CNN)and AdaBoost algorithm.This algorithm uses CNN to extract the characteristics of network traffic data,which is particularly suitable for the analysis of continuous and classified attack data.The AdaBoost algorithm is used to classify network attack data that improved the detection effect of unbalanced data classification.We adopt the UNSW-NB15 dataset to test of this algorithm in the PyCharm environment.The results show that the detection rate of algorithm is99.27%and the false positive rate is lower than 0.98%.Comparative analysis shows that this algorithm has advantages over existing methods in terms of detection rate and false positive rate for small proportion of attack data.
基金supported in part by National Natural Science Foundation of China(No.62471034)Hebei Natural Science Foundation(No.F2023105001)。
文摘In the field of remote sensing,the rapid and accurate acquisition of the category and location of airplanes has emerged as a prominent research.However,remote sensing fuzzy imaging and complex environmental interference affect airplane detection.Besides,the inconsistency in the size of remote sensing images and the low accuracy of small target detection are crucial challenges that need to be addressed.To tackle these issues,we propose a novel network SDaDCS(SAHI-data augmentation-dilation-channel and spatial attention)based on YOLOX model and the slicing aided hyper inference(SAHI)framework,a new data augmentation technique and dilation-channel and spatial(DCS)attention mechanism.Initially,we create a remote sensing dataset for airplane targets and introduce a new data augmentation technique based on the Rotate-Mixup and mixed data augmentation to enhance data diversity.The DCS attention mechanism,which comprises the dilated convolution block,channel attention and spatial attention,is designed to bolster the feature extraction and discrimination of the network.To address the challenges arised by the difficulties of detecting small targets,we integrate the YOLOX model with the SAHI framework.Experiment results show that,when compared to the original YOLOX model,the proposed SDaDCS remote sensing target detection algorithm enhances overall accuracy by 13.6%.The experimental results validate the effectiveness of the proposed algorithm.
文摘In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.
基金supported in part by the Science and Technology Department of Guangdong Province(2021A0505080002)Department of Natural Resources of Guangdong Province(GDNRC[2022]No.22)+2 种基金Science,Technology and Innovation Commission of Shenzhen Municipality(20220815121807001)Hunan Provincial Natural Science Foundation of China(under Grant Nos.2023JJ30209)Hunan Provincial Education Department Science Research Fund of China(under Grant Nos.22B0862).
文摘The specific detection of tumor markers is crucial in early tumor screening and subsequent treatment processes.To ac-curately distinguish the signal response caused by trace markers,the high demodulation resolution of the sensor is necessary.In this paper,we propose a dual-wavelength fiber laser sensing system enhanced with microwave photonics de-modulation technology to achieve high-resolution tumor marker detection.This sensing system can simultaneously perform spectral wavelength-domain and frequency-domain analyses.Experimental results demonstrate that this system's refractive index(RI)sensitivity reaches 1083 nm/RIU by wavelength analysis and-1902 GHz/RIU by frequency analysis,with ideal detection resolutions of 1.85×10^(-5)RIU and 5.26×10^(-8)RIU,respectively.Compared with traditional wavelength domain analysis,the demodulation resolution is improved by three orders of magnitude,based on the same sensing structure.To validate its biosensing performance,carcinoembryonic antigen-related cell adhesion molecule 5(CEACAM5)is selected as the detection target.Experimental results show that the improved sensing system has a limit of detection(LOD)of 0.076 ng/mL and a detection resolution of 0.008 ng/mL.Experimental results obtained from human serum samples are consistent with clinical data,highlighting the strong clinical application potential of the proposed sens-ing system and analysis method.
文摘Recently,anomaly detection(AD)in streaming data gained significant attention among research communities due to its applicability in finance,business,healthcare,education,etc.The recent developments of deep learning(DL)models find helpful in the detection and classification of anomalies.This article designs an oversampling with an optimal deep learning-based streaming data classification(OS-ODLSDC)model.The aim of the OSODLSDC model is to recognize and classify the presence of anomalies in the streaming data.The proposed OS-ODLSDC model initially undergoes preprocessing step.Since streaming data is unbalanced,support vector machine(SVM)-Synthetic Minority Over-sampling Technique(SVM-SMOTE)is applied for oversampling process.Besides,the OS-ODLSDC model employs bidirectional long short-term memory(Bi LSTM)for AD and classification.Finally,the root means square propagation(RMSProp)optimizer is applied for optimal hyperparameter tuning of the Bi LSTM model.For ensuring the promising performance of the OS-ODLSDC model,a wide-ranging experimental analysis is performed using three benchmark datasets such as CICIDS 2018,KDD-Cup 1999,and NSL-KDD datasets.
文摘The advent of pandemics such as COVID-19 significantly impacts human behaviour and lives every day.Therefore,it is essential to make medical services connected to internet,available in every remote location during these situations.Also,the security issues in the Internet of Medical Things(IoMT)used in these service,make the situation even more critical because cyberattacks on the medical devices might cause treatment delays or clinical failures.Hence,services in the healthcare ecosystem need rapid,uninterrupted,and secure facilities.The solution provided in this research addresses security concerns and services availability for patients with critical health in remote areas.This research aims to develop an intelligent Software Defined Networks(SDNs)enabled secure framework for IoT healthcare ecosystem.We propose a hybrid of machine learning and deep learning techniques(DNN+SVM)to identify network intrusions in the sensor-based healthcare data.In addition,this system can efficiently monitor connected devices and suspicious behaviours.Finally,we evaluate the performance of our proposed framework using various performance metrics based on the healthcare application scenarios.the experimental results show that the proposed approach effectively detects and mitigates attacks in the SDN-enabled IoT networks and performs better that other state-of-art-approaches.
基金supported by the National Key Research and Development Plan in China(Grant No.2020YFB1005500)。
文摘The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields.Cryptographic algorithms and smart contracts are critical components of blockchain security.Despite the benefits of virtual currency,vulnerabilities in smart contracts have resulted in substantial losses to users.While researchers have identified these vulnerabilities and developed tools for detecting them,the accuracy of these tools is still far from satisfactory,with high false positive and false negative rates.In this paper,we propose a new method for detecting vulnerabilities in smart contracts using the BERT pre-training model,which can quickly and effectively process and detect smart contracts.More specifically,we preprocess and make symbol substitution in the contract,which can make the pre-training model better obtain contract features.We evaluate our method on four datasets and compare its performance with other deep learning models and vulnerability detection tools,demonstrating its superior accuracy.
基金supported in part by the National Natural Science Foundation of China under grants 62202044 and 62372039Scientific and Technological Innovation Foundation of Foshan under grant BK22BF009+3 种基金Excellent Youth Team Project for the Central Universities under grant FRF-EYIT-23-01Fundamental Research Funds for the Central Universities under grants 06500103 and 06500078Guangdong Basic and Applied Basic Research Foundation under grant 2022A1515240044Beijing Natural Science Foundation under grant 4232040.
文摘Timely inspection of defects on the surfaces of wind turbine blades can effectively prevent unpredictable accidents.To this end,this study proposes a semi-supervised object-detection network based on You Only Looking Once version 4(YOLOv4).A semi-supervised structure comprising a generative adversarial network(GAN)was designed to overcome the difficulty in obtaining sufficient samples and sample labeling.In a GAN,the generator is realized by an encoder-decoder network,where the backbone of the encoder is YOLOv4 and the decoder comprises inverse convolutional layers.Partial features from the generator are passed to the defect detection network.Deploying several unlabeled images can significantly improve the generalization and recognition capabilities of defect-detection models.The small-scale object detection capacity of the network can be improved by enhancing essential features in the feature map by adding the concurrent spatial and channel squeeze and excitation(scSE)attention module to the three parts of the YOLOv4 network.A balancing improvement was made to the loss function of YOLOv4 to overcome the imbalance problem of the defective species.The results for both the single-and multi-category defect datasets show that the improved model can make good use of the features of the unlabeled images.The accuracy of wind turbine blade defect detection also has a significant advantage over classical object detection algorithms,including faster R-CNN and DETR.
