@article{liu_fragment_2017,
	title = {Fragment {Anomaly} {Detection} {With} {Prediction} and {Statistical} {Analysis} for {Satellite} {Telemetry}},
	volume = {5},
	doi = {10/gdf4sp},
	abstract = {In aerospace engineering, condition monitoring is an important reference for evaluating the performance of complex systems. Especially, effective anomaly detection, based on telemetry data, plays an important role for the system health management of a spacecraft. With the advantages of easy-to-use, high efficiency, and data-driven, the predicted model has been applied for anomalous point detection for monitoring data. However, compared with the point abnormal mode, fragment anomaly is more attractive and meaningful for the system identification. Therefore, the detection strategy of fragment anomaly is proposed based on the uncertainty estimation of least square support vector machine and statistical analysis. Moreover, some effective estimation indicators are presented to evaluate the performance of the detection method. Experimental validations are also carried out for some typical simulation data sets and open source data sets. In particular, relied on the analysis of fragment anomaly modes, experiments are conducted with the real satellite telemetry data and different anomaly modes are injected to examine the applicability of the proposed framework.},
	journal = {IEEE Access},
	author = {Liu, D. and Pang, J. and Song, G. and Xie, W. and Peng, Y. and Peng, X.},
	year = {2017},
	note = {00001},
	keywords = {Anomaly detection, Computational modeling, Data models, LS-SVM, Predictive models, Satellite, Support vector machines, Telemetry, Training, aerospace computing, aerospace engineering, anomalous point detection, anomaly detection, condition monitoring, fragment anomaly, fragment anomaly detection, fragment anomaly modes, least squares approximations, open source data sets, point abnormal mode, satellite telemetry, satellite telemetry data, square support vector machine, statistical analysis, support vector machines, system health management, system identification, telemetry, uncertainty},
	pages = {19269--19281}
}

{"_id":"vYGYpQTegFBaxuMoZ","bibbaseid":"liu-pang-song-xie-peng-peng-fragmentanomalydetectionwithpredictionandstatisticalanalysisforsatellitetelemetry-2017","downloads":0,"creationDate":"2018-05-16T15:04:02.591Z","title":"Fragment Anomaly Detection With Prediction and Statistical Analysis for Satellite Telemetry","author_short":["Liu, D.","Pang, J.","Song, G.","Xie, W.","Peng, Y.","Peng, X."],"year":2017,"bibtype":"article","biburl":"https://api.zotero.org/users/4282079/collections/QVXPDHMF/items?key=U62aeImfuN78X1koIwEbW1J0&format=bibtex&limit=100","bibdata":{"bibtype":"article","type":"article","title":"Fragment Anomaly Detection With Prediction and Statistical Analysis for Satellite Telemetry","volume":"5","doi":"10/gdf4sp","abstract":"In aerospace engineering, condition monitoring is an important reference for evaluating the performance of complex systems. Especially, effective anomaly detection, based on telemetry data, plays an important role for the system health management of a spacecraft. With the advantages of easy-to-use, high efficiency, and data-driven, the predicted model has been applied for anomalous point detection for monitoring data. However, compared with the point abnormal mode, fragment anomaly is more attractive and meaningful for the system identification. Therefore, the detection strategy of fragment anomaly is proposed based on the uncertainty estimation of least square support vector machine and statistical analysis. Moreover, some effective estimation indicators are presented to evaluate the performance of the detection method. Experimental validations are also carried out for some typical simulation data sets and open source data sets. In particular, relied on the analysis of fragment anomaly modes, experiments are conducted with the real satellite telemetry data and different anomaly modes are injected to examine the applicability of the proposed framework.","journal":"IEEE Access","author":[{"propositions":[],"lastnames":["Liu"],"firstnames":["D."],"suffixes":[]},{"propositions":[],"lastnames":["Pang"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Song"],"firstnames":["G."],"suffixes":[]},{"propositions":[],"lastnames":["Xie"],"firstnames":["W."],"suffixes":[]},{"propositions":[],"lastnames":["Peng"],"firstnames":["Y."],"suffixes":[]},{"propositions":[],"lastnames":["Peng"],"firstnames":["X."],"suffixes":[]}],"year":"2017","note":"00001","keywords":"Anomaly detection, Computational modeling, Data models, LS-SVM, Predictive models, Satellite, Support vector machines, Telemetry, Training, aerospace computing, aerospace engineering, anomalous point detection, anomaly detection, condition monitoring, fragment anomaly, fragment anomaly detection, fragment anomaly modes, least squares approximations, open source data sets, point abnormal mode, satellite telemetry, satellite telemetry data, square support vector machine, statistical analysis, support vector machines, system health management, system identification, telemetry, uncertainty","pages":"19269--19281","bibtex":"@article{liu_fragment_2017,\n\ttitle = {Fragment {Anomaly} {Detection} {With} {Prediction} and {Statistical} {Analysis} for {Satellite} {Telemetry}},\n\tvolume = {5},\n\tdoi = {10/gdf4sp},\n\tabstract = {In aerospace engineering, condition monitoring is an important reference for evaluating the performance of complex systems. Especially, effective anomaly detection, based on telemetry data, plays an important role for the system health management of a spacecraft. With the advantages of easy-to-use, high efficiency, and data-driven, the predicted model has been applied for anomalous point detection for monitoring data. However, compared with the point abnormal mode, fragment anomaly is more attractive and meaningful for the system identification. Therefore, the detection strategy of fragment anomaly is proposed based on the uncertainty estimation of least square support vector machine and statistical analysis. Moreover, some effective estimation indicators are presented to evaluate the performance of the detection method. Experimental validations are also carried out for some typical simulation data sets and open source data sets. In particular, relied on the analysis of fragment anomaly modes, experiments are conducted with the real satellite telemetry data and different anomaly modes are injected to examine the applicability of the proposed framework.},\n\tjournal = {IEEE Access},\n\tauthor = {Liu, D. and Pang, J. and Song, G. and Xie, W. and Peng, Y. and Peng, X.},\n\tyear = {2017},\n\tnote = {00001},\n\tkeywords = {Anomaly detection, Computational modeling, Data models, LS-SVM, Predictive models, Satellite, Support vector machines, Telemetry, Training, aerospace computing, aerospace engineering, anomalous point detection, anomaly detection, condition monitoring, fragment anomaly, fragment anomaly detection, fragment anomaly modes, least squares approximations, open source data sets, point abnormal mode, satellite telemetry, satellite telemetry data, square support vector machine, statistical analysis, support vector machines, system health management, system identification, telemetry, uncertainty},\n\tpages = {19269--19281}\n}\n\n","author_short":["Liu, D.","Pang, J.","Song, G.","Xie, W.","Peng, Y.","Peng, X."],"key":"liu_fragment_2017","id":"liu_fragment_2017","bibbaseid":"liu-pang-song-xie-peng-peng-fragmentanomalydetectionwithpredictionandstatisticalanalysisforsatellitetelemetry-2017","role":"author","urls":{},"keyword":["Anomaly detection","Computational modeling","Data models","LS-SVM","Predictive models","Satellite","Support vector machines","Telemetry","Training","aerospace computing","aerospace engineering","anomalous point detection","anomaly detection","condition monitoring","fragment anomaly","fragment anomaly detection","fragment anomaly modes","least squares approximations","open source data sets","point abnormal mode","satellite telemetry","satellite telemetry data","square support vector machine","statistical analysis","support vector machines","system health management","system identification","telemetry","uncertainty"],"downloads":0},"search_terms":["fragment","anomaly","detection","prediction","statistical","analysis","satellite","telemetry","liu","pang","song","xie","peng","peng"],"keywords":["anomaly detection","computational modeling","data models","ls-svm","predictive models","satellite","support vector machines","telemetry","training","aerospace computing","aerospace engineering","anomalous point detection","anomaly detection","condition monitoring","fragment anomaly","fragment anomaly detection","fragment anomaly modes","least squares approximations","open source data sets","point abnormal mode","satellite telemetry","satellite telemetry data","square support vector machine","statistical analysis","support vector machines","system health management","system identification","telemetry","uncertainty"],"authorIDs":[],"dataSources":["N3CMPD4uLFHe2aopm"]}