The current COVID-19 pandemic urges the extremely sensitive and prompt detection of SARS-CoV-2 virus.Here,we present a Human Angiotensin-converting-enzyme 2(ACE2)-functionalized gold“virus traps”nanostructure as an ...The current COVID-19 pandemic urges the extremely sensitive and prompt detection of SARS-CoV-2 virus.Here,we present a Human Angiotensin-converting-enzyme 2(ACE2)-functionalized gold“virus traps”nanostructure as an extremely sensitive SERS biosensor,to selectively capture and rapidly detect S-protein expressed coronavirus,such as the current SARS-CoV-2 in the contaminated water,down to the single-virus level.Such a SERS sensor features extraordinary 106-fold virus enrichment originating from high-affinity of ACE2 with S protein as well as“virus-traps”composed of oblique gold nanoneedles,and 109-fold enhancement of Raman signals originating from multi-component SERS effects.Furthermore,the identification standard of virus signals is established by machine-learning and identification techniques,resulting in an especially low detection limit of 80 copies mL^(−1) for the simulated contaminated water by SARS-CoV-2 virus with complex circumstance as short as 5 min,which is of great significance for achieving real-time monitoring and early warning of coronavirus.Moreover,here-developed method can be used to establish the identification standard for future unknown coronavirus,and immediately enable extremely sensitive and rapid detection of novel virus.展开更多
Target detection in low light background is one of the main tasks of night patrol robots for airport terminal.However,if some algorithms can run on a robot platform with limited computing resources,it is difficult for...Target detection in low light background is one of the main tasks of night patrol robots for airport terminal.However,if some algorithms can run on a robot platform with limited computing resources,it is difficult for these algorithms to ensure the detection accuracy of human body in the airport terminal. A novel thermal infrared salient human detection model combined with thermal features called TFSHD is proposed. The TFSHD model is still based on U-Net,but the decoder module structure and model lightweight have been redesigned. In order to improve the detection accuracy of the algorithm in complex scenes,a fusion module composed of thermal branch and saliency branch is added to the decoder of the TFSHD model. Furthermore,a predictive loss function that is more sensitive to high temperature regions of the image is designed. Additionally,for the sake of reducing the computing resource requirements of the algorithm,a model lightweight scheme that includes simplifying the encoder network structure and controlling the number of decoder channels is adopted. The experimental results on four data sets show that the proposed method can not only ensure high detection accuracy and robustness of the algorithm,but also meet the needs of real-time detection of patrol robots with detection speed above 40 f/s.展开更多
A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper.In this method,the original image sequence data i...A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper.In this method,the original image sequence data is first separated from the foreground and background.Then,the free anchor frame detection method is used in the foreground image to detect the personnel and correct their direction.Finally,human posture nodes are extracted from each frame of the image sequence,which are then used to identify the abnormal behavior of the human.Simulation experiment results demonstrate that the proposed algorithm has significant advantages in terms of the accuracy of human posture node detection and risk behavior identification.展开更多
One particular challenge for large‑scale software systems is anomaly detection.System logs are a straightforward and common source of information for anomaly detection.Existing log‑based anomaly detectors are unusable...One particular challenge for large‑scale software systems is anomaly detection.System logs are a straightforward and common source of information for anomaly detection.Existing log‑based anomaly detectors are unusable in real‑world industrial systems due to high false‑positive rates.In this paper,we incorporate human feedback to adjust the detection model structure to reduce false positives.We apply our approach to two industrial large‑scale systems.Results have shown that our approach performs much better than state‑of‑the-art works with 50%higher accuracy.Besides,human feedback can reduce more than 70%of false positives and greatly improve detection precision.展开更多
In order to monitor dangerous areas in coal mines automatically,we propose to detect helmets from underground coal mine videos for detecting miners.This method can overcome the impact of similarity between the targets...In order to monitor dangerous areas in coal mines automatically,we propose to detect helmets from underground coal mine videos for detecting miners.This method can overcome the impact of similarity between the targets and their background.We constructed standard images of helmets,extracted four directional features,modeled the distribution of these features using a Gaussian function and separated local images of frames into helmet and non-helmet classes.Out experimental results show that this method can detect helmets effectively.The detection rate was 83.7%.展开更多
基金the National Natural Science Foundation of China(No.51471182)this work is also supported by Shanghai international science and Technology Cooperation Fund(No.17520711700)the National Key Research and Development Project(No.2017YFB0310600).
文摘The current COVID-19 pandemic urges the extremely sensitive and prompt detection of SARS-CoV-2 virus.Here,we present a Human Angiotensin-converting-enzyme 2(ACE2)-functionalized gold“virus traps”nanostructure as an extremely sensitive SERS biosensor,to selectively capture and rapidly detect S-protein expressed coronavirus,such as the current SARS-CoV-2 in the contaminated water,down to the single-virus level.Such a SERS sensor features extraordinary 106-fold virus enrichment originating from high-affinity of ACE2 with S protein as well as“virus-traps”composed of oblique gold nanoneedles,and 109-fold enhancement of Raman signals originating from multi-component SERS effects.Furthermore,the identification standard of virus signals is established by machine-learning and identification techniques,resulting in an especially low detection limit of 80 copies mL^(−1) for the simulated contaminated water by SARS-CoV-2 virus with complex circumstance as short as 5 min,which is of great significance for achieving real-time monitoring and early warning of coronavirus.Moreover,here-developed method can be used to establish the identification standard for future unknown coronavirus,and immediately enable extremely sensitive and rapid detection of novel virus.
基金supported in part by the National Key Research and Development Program of China(No. 2018YFC0309104)the Construction System Science and Technology Project of Jiangsu Province (No.2021JH03)。
文摘Target detection in low light background is one of the main tasks of night patrol robots for airport terminal.However,if some algorithms can run on a robot platform with limited computing resources,it is difficult for these algorithms to ensure the detection accuracy of human body in the airport terminal. A novel thermal infrared salient human detection model combined with thermal features called TFSHD is proposed. The TFSHD model is still based on U-Net,but the decoder module structure and model lightweight have been redesigned. In order to improve the detection accuracy of the algorithm in complex scenes,a fusion module composed of thermal branch and saliency branch is added to the decoder of the TFSHD model. Furthermore,a predictive loss function that is more sensitive to high temperature regions of the image is designed. Additionally,for the sake of reducing the computing resource requirements of the algorithm,a model lightweight scheme that includes simplifying the encoder network structure and controlling the number of decoder channels is adopted. The experimental results on four data sets show that the proposed method can not only ensure high detection accuracy and robustness of the algorithm,but also meet the needs of real-time detection of patrol robots with detection speed above 40 f/s.
基金supported by the project“Research and application of key technologies of safe production management and control of substation operation and maintenance based on video semantic analysis”(5700-202133259A-0-0-00)of the State Grid Corporation of China.
文摘A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper.In this method,the original image sequence data is first separated from the foreground and background.Then,the free anchor frame detection method is used in the foreground image to detect the personnel and correct their direction.Finally,human posture nodes are extracted from each frame of the image sequence,which are then used to identify the abnormal behavior of the human.Simulation experiment results demonstrate that the proposed algorithm has significant advantages in terms of the accuracy of human posture node detection and risk behavior identification.
基金ZTE Industry-University-Institute Cooperation Funds under Grant No.20200492.
文摘One particular challenge for large‑scale software systems is anomaly detection.System logs are a straightforward and common source of information for anomaly detection.Existing log‑based anomaly detectors are unusable in real‑world industrial systems due to high false‑positive rates.In this paper,we incorporate human feedback to adjust the detection model structure to reduce false positives.We apply our approach to two industrial large‑scale systems.Results have shown that our approach performs much better than state‑of‑the-art works with 50%higher accuracy.Besides,human feedback can reduce more than 70%of false positives and greatly improve detection precision.
基金provided by the National High Technology Research and Development Program of China (No.2008AA062202)
文摘In order to monitor dangerous areas in coal mines automatically,we propose to detect helmets from underground coal mine videos for detecting miners.This method can overcome the impact of similarity between the targets and their background.We constructed standard images of helmets,extracted four directional features,modeled the distribution of these features using a Gaussian function and separated local images of frames into helmet and non-helmet classes.Out experimental results show that this method can detect helmets effectively.The detection rate was 83.7%.
