Behavioral analysis of macaques provides important experimental evidence in the field of neuroscience.In recent years,video-based automatic animal behavior analysis has received widespread attention.However,methods ca...Behavioral analysis of macaques provides important experimental evidence in the field of neuroscience.In recent years,video-based automatic animal behavior analysis has received widespread attention.However,methods capable of extracting and analyzing daily movement trajectories of macaques in their daily living cages remain underdeveloped,with previous approaches usually requiring specific environments to reduce interference from occlusion or environmental change.Here,we introduce a novel method,called MonkeyTrail,which satisfies the above requirements by frequently generating virtual empty backgrounds and using background subtraction to accurately obtain the foreground of moving animals.The empty background is generated by combining the frame difference method(FDM)and deep learning-based model(YOLOv5).The entire setup can be operated with low-cost hardware and can be applied to the daily living environments of individually caged macaques.To test MonkeyTrail performance,we labeled a dataset containing>8000 video frames with the bounding boxes of macaques under various conditions as ground-truth.Results showed that the tracking accuracy and stability of MonkeyTrail exceeded that of two deep learningbased methods(YOLOv5 and Single-Shot MultiBox Detector),traditional frame difference method,and na?ve background subtraction method.Using MonkeyTrail to analyze long-term surveillance video recordings,we successfully assessed changes in animal behavior in terms of movement amount and spatial preference.Thus,these findings demonstrate that MonkeyTrail enables low-cost,large-scale daily behavioral analysis of macaques.展开更多
The aim of this work is to establish the influence of the relative position of the alloy charge C-Cr-Mn in the structure of the coating of rutile electrodes for hardfacing,on the operational behavior(arc stability).Fo...The aim of this work is to establish the influence of the relative position of the alloy charge C-Cr-Mn in the structure of the coating of rutile electrodes for hardfacing,on the operational behavior(arc stability).For this,three variants of electrodes with similar chemical composition are elaborated in the metallic core and the coating,differentiating only in the relative position that occupies the alloy charge(C-Cr-Mn)in the structure of the coating:internal,external and homogeneous.For the development of the research,a completely random design is used.The operative characterization of the electrodes is performed in terms of the arc stability.In conclusion,it can be seen that the position of the alloy load influences the operation behavior(stability of the arc).The variant of internal alloy charge in the coating presents the better arc stability performance.展开更多
When the face of the inspected person and the photograph on their identification(ID)card cannot be clearly matched,the individual is undocumented,or the ID is forged,it is often difficult for the on‑site police to res...When the face of the inspected person and the photograph on their identification(ID)card cannot be clearly matched,the individual is undocumented,or the ID is forged,it is often difficult for the on‑site police to respond in time.This study proposes a number of key technologies for collecting fingerprints at mobile terminals for fast comparison using an automated fingerprint ID system(AFIS).These technologies ensure intelligent mobile fingerprint collection and allow the transmission of fingerprint information from the terminal to AFIS,over a wireless public security network for real‑time fingerprint comparison.This study also analyzes the feasibility and effectiveness of the proposed technologies for system design and the applicability of fingerprint ID algorithms.The system achieved good results in a test by the Shanghai Public Security Bureau Criminal Investigation Corps.展开更多
Using the spontaneously synchronized clapping in a concert hall as a special case, we build a nonlinear emergent model to characterize the collective behaviors of the complex multi-agent systems. Based on this model, ...Using the spontaneously synchronized clapping in a concert hall as a special case, we build a nonlinear emergent model to characterize the collective behaviors of the complex multi-agent systems. Based on this model, we develop an experimental platform for emergent computation, which only depends on the local interaction and reveals the uncertainty and diversity of emergent behaviors. By analyzing the data in the procedure of many hands clapping, we find that there exists an obvious critical region generated in the procedure from disorder to synchronization. More- over, we propose a fundamental synchronous criterion as follows： If the coupling coefficients c1 and c2 satisfy the condition 0.02≤c2=≤0.965c1＋0.018, then the clapping can realize synchronization.展开更多
基金supported by the National Key Research and Development Program of China(2017YFA0105203,2017YFA0105201)National Science Foundation of China(31771076,81925011)+2 种基金Strategic Priority Research Program of the Chinese Academy of Sciences(CAS)(XDB32040201)Beijing Academy of Artificial IntelligenceKey-Area Research and Development Program of Guangdong Province(2019B030335001)。
文摘Behavioral analysis of macaques provides important experimental evidence in the field of neuroscience.In recent years,video-based automatic animal behavior analysis has received widespread attention.However,methods capable of extracting and analyzing daily movement trajectories of macaques in their daily living cages remain underdeveloped,with previous approaches usually requiring specific environments to reduce interference from occlusion or environmental change.Here,we introduce a novel method,called MonkeyTrail,which satisfies the above requirements by frequently generating virtual empty backgrounds and using background subtraction to accurately obtain the foreground of moving animals.The empty background is generated by combining the frame difference method(FDM)and deep learning-based model(YOLOv5).The entire setup can be operated with low-cost hardware and can be applied to the daily living environments of individually caged macaques.To test MonkeyTrail performance,we labeled a dataset containing>8000 video frames with the bounding boxes of macaques under various conditions as ground-truth.Results showed that the tracking accuracy and stability of MonkeyTrail exceeded that of two deep learningbased methods(YOLOv5 and Single-Shot MultiBox Detector),traditional frame difference method,and na?ve background subtraction method.Using MonkeyTrail to analyze long-term surveillance video recordings,we successfully assessed changes in animal behavior in terms of movement amount and spatial preference.Thus,these findings demonstrate that MonkeyTrail enables low-cost,large-scale daily behavioral analysis of macaques.
文摘The aim of this work is to establish the influence of the relative position of the alloy charge C-Cr-Mn in the structure of the coating of rutile electrodes for hardfacing,on the operational behavior(arc stability).For this,three variants of electrodes with similar chemical composition are elaborated in the metallic core and the coating,differentiating only in the relative position that occupies the alloy charge(C-Cr-Mn)in the structure of the coating:internal,external and homogeneous.For the development of the research,a completely random design is used.The operative characterization of the electrodes is performed in terms of the arc stability.In conclusion,it can be seen that the position of the alloy load influences the operation behavior(stability of the arc).The variant of internal alloy charge in the coating presents the better arc stability performance.
文摘When the face of the inspected person and the photograph on their identification(ID)card cannot be clearly matched,the individual is undocumented,or the ID is forged,it is often difficult for the on‑site police to respond in time.This study proposes a number of key technologies for collecting fingerprints at mobile terminals for fast comparison using an automated fingerprint ID system(AFIS).These technologies ensure intelligent mobile fingerprint collection and allow the transmission of fingerprint information from the terminal to AFIS,over a wireless public security network for real‑time fingerprint comparison.This study also analyzes the feasibility and effectiveness of the proposed technologies for system design and the applicability of fingerprint ID algorithms.The system achieved good results in a test by the Shanghai Public Security Bureau Criminal Investigation Corps.
基金the National Basic Research Program of China (Grant No. 2007CB310800)the National Natural Science Foundation of China (Grant Nos. 60375016, 60496323 and 60675032)
文摘Using the spontaneously synchronized clapping in a concert hall as a special case, we build a nonlinear emergent model to characterize the collective behaviors of the complex multi-agent systems. Based on this model, we develop an experimental platform for emergent computation, which only depends on the local interaction and reveals the uncertainty and diversity of emergent behaviors. By analyzing the data in the procedure of many hands clapping, we find that there exists an obvious critical region generated in the procedure from disorder to synchronization. More- over, we propose a fundamental synchronous criterion as follows： If the coupling coefficients c1 and c2 satisfy the condition 0.02≤c2=≤0.965c1＋0.018, then the clapping can realize synchronization.
