[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been propo...[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been proposed for monitoring cow ruminant behavior,including video surveillance,sound recognition,and sensor monitoring methods.How‐ever,the application of edge device gives rise to the issue of inadequate real-time performance.To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior,a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.[Methods]Autono‐mously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time.Based on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time recognition of cow ruminant behavior.Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism.Additionally,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm.In the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through compara‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Score,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best recognition performance.[Conclusions]It is provided a real-time and effective method for monitoring cow ruminant behavior,and the proposed federated edge intelligence model can be ap‐plied in practical settings.展开更多
This paper computed the newest impact solutions of the potentially dangerous asteroid （99942） Apophis based on 4,138 optical observations from March 15.10789 UTC （Universal Time Coordinated）, 2004 to February 28.0...This paper computed the newest impact solutions of the potentially dangerous asteroid （99942） Apophis based on 4,138 optical observations from March 15.10789 UTC （Universal Time Coordinated）, 2004 to February 28.089569 UTC, 2014 and 20 radar observations from January 27, 2005 through March 15, 2013, as of June 20, 2014. Using the freely available the OrbFit software Package, this paper followed its orbit forward in the searching for close approaches with the Earth and possible impacts up to year 2116. With the different A2 non-gravitational parameter in the motion of the asteroid （99942） Apophis, this paper computed possible impact solutions using the JPL DE405 （Jet Propulsion Laboratory Development Ephemeris） and 25 additional massive perturbed asteroids. Additionally, this paper used weighing and selection methods adopted in the OrbFit software as prepared by the NEODyS （Near Earth Objects--Dynamical Side） Team. Moreover, this paper used method of computing the orbit of Apophis taking into account star catalog debiasing and an error model with assumed astrometric errors RMS （root mean square）, deduced from the observational material of the given observatories. JPL＇s Sentry and NEODyS＇s CLOMMON2, two automatic monitoring systems routinely scanning for possible impacts in the next hundred years. Only for several dangerous asteroids presented results are computed with the non-gravitational parameters. This paper detected possible impacts of the asteroid （99942） Apophis only with the non-gravitational parameter, A2 〉 0. It was appeared that impacts in 2068, 2087, 2105 and in 2111 were possible only when Apophis rotated in prograde direction.展开更多
This paper proposes an unprecedented systematic approach for real-time monitoring the temperature and flow of diesel engine by using embedded fiber Bragg grating(FBG). By virtue of FBG's temperature effect, we des...This paper proposes an unprecedented systematic approach for real-time monitoring the temperature and flow of diesel engine by using embedded fiber Bragg grating(FBG). By virtue of FBG's temperature effect, we design a novel sensitive FBG temperature sensing probe to measure the temperature of cylinder head and inlet flow of diesel engine. We also establish the corresponding software platform for intuitive data analysis. The experimental and complementary simulation results simultaneously demonstrate that the FBG-based optical fiber technique possesses extraordinary reproducibility and sensitivity, which makes it feasible to monitor the temperature and inlet flow of diesel engine. Our work can provide an effective way to evaluate the thermal load of cylinder head in diesel engine.展开更多
文摘[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been proposed for monitoring cow ruminant behavior,including video surveillance,sound recognition,and sensor monitoring methods.How‐ever,the application of edge device gives rise to the issue of inadequate real-time performance.To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior,a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.[Methods]Autono‐mously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time.Based on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time recognition of cow ruminant behavior.Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism.Additionally,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm.In the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through compara‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Score,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best recognition performance.[Conclusions]It is provided a real-time and effective method for monitoring cow ruminant behavior,and the proposed federated edge intelligence model can be ap‐plied in practical settings.
文摘This paper computed the newest impact solutions of the potentially dangerous asteroid （99942） Apophis based on 4,138 optical observations from March 15.10789 UTC （Universal Time Coordinated）, 2004 to February 28.089569 UTC, 2014 and 20 radar observations from January 27, 2005 through March 15, 2013, as of June 20, 2014. Using the freely available the OrbFit software Package, this paper followed its orbit forward in the searching for close approaches with the Earth and possible impacts up to year 2116. With the different A2 non-gravitational parameter in the motion of the asteroid （99942） Apophis, this paper computed possible impact solutions using the JPL DE405 （Jet Propulsion Laboratory Development Ephemeris） and 25 additional massive perturbed asteroids. Additionally, this paper used weighing and selection methods adopted in the OrbFit software as prepared by the NEODyS （Near Earth Objects--Dynamical Side） Team. Moreover, this paper used method of computing the orbit of Apophis taking into account star catalog debiasing and an error model with assumed astrometric errors RMS （root mean square）, deduced from the observational material of the given observatories. JPL＇s Sentry and NEODyS＇s CLOMMON2, two automatic monitoring systems routinely scanning for possible impacts in the next hundred years. Only for several dangerous asteroids presented results are computed with the non-gravitational parameters. This paper detected possible impacts of the asteroid （99942） Apophis only with the non-gravitational parameter, A2 〉 0. It was appeared that impacts in 2068, 2087, 2105 and in 2111 were possible only when Apophis rotated in prograde direction.
基金supported by the National Natural Science Foundation of China(Nos.61271073 and 61473175)the Fundamental Research Funds of Shandong University(No.2015JC040)
文摘This paper proposes an unprecedented systematic approach for real-time monitoring the temperature and flow of diesel engine by using embedded fiber Bragg grating(FBG). By virtue of FBG's temperature effect, we design a novel sensitive FBG temperature sensing probe to measure the temperature of cylinder head and inlet flow of diesel engine. We also establish the corresponding software platform for intuitive data analysis. The experimental and complementary simulation results simultaneously demonstrate that the FBG-based optical fiber technique possesses extraordinary reproducibility and sensitivity, which makes it feasible to monitor the temperature and inlet flow of diesel engine. Our work can provide an effective way to evaluate the thermal load of cylinder head in diesel engine.
