CycleFootprint: A Fully Automated Method for Extracting Operation Cycles from Historical Raw Data of Multiple Sensors

CycleFootprint: A Fully Automated Method for Extracting Operation Cycles from Historical Raw Data of Multiple Sensors. Fanaee-T, H., Bouguelia, M., Rahat, M., Blixt, J., & Singh, H. In Gama, J., Pashami, S., Bifet, A., Sayed-Mouchawe, M., Fröning, H., Pernkopf, F., Schiele, G., & Blott, M., editors, IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning, of Communications in Computer and Information Science, pages 30–44, Cham, 2020. Springer International Publishing.
doi abstract bibtex

Extracting operation cycles from the historical reading of sensors is an essential step in IoT data analytics. For instance, we can exploit the obtained cycles for learning the normal states to feed into semi-supervised models or dictionaries for efficient real-time anomaly detection on the sensors. However, this is a difficult problem due to this fact that we may have different types of cycles, each of which with varying lengths. Current approaches are highly dependent on manual efforts by the aid of visualization and knowledge of domain experts, which is not feasible on a large scale. We propose a fully automated method called CycleFootprint that can: 1) identify the most relevant signal that has the most obvious recurring patterns among multiple signals; and 2) automatically find the cycles from the selected signal. The main idea behind CycleFootprint is mining footprints in the cycles. We assume that there should be a unique pattern in each cycle that shows up repeatedly in each cycle. By mining those footprints, we can identify cycles. We evaluate our method with existing labeled ground truth data of a real separator in marine application equipped with multiple health monitoring sensors. 86% of cycles extracted by our method match fully or with at least 99% overlap with true cycles, which sounds promising given its unsupervised and fully automated nature.

@inproceedings{fanaee-t_cyclefootprint_2020,
	address = {Cham},
	series = {Communications in {Computer} and {Information} {Science}},
	title = {{CycleFootprint}: {A} {Fully} {Automated} {Method} for {Extracting} {Operation} {Cycles} from {Historical} {Raw} {Data} of {Multiple} {Sensors}},
	isbn = {978-3-030-66770-2},
	shorttitle = {{CycleFootprint}},
	doi = {10.1007/978-3-030-66770-2_3},
	abstract = {Extracting operation cycles from the historical reading of sensors is an essential step in IoT data analytics. For instance, we can exploit the obtained cycles for learning the normal states to feed into semi-supervised models or dictionaries for efficient real-time anomaly detection on the sensors. However, this is a difficult problem due to this fact that we may have different types of cycles, each of which with varying lengths. Current approaches are highly dependent on manual efforts by the aid of visualization and knowledge of domain experts, which is not feasible on a large scale. We propose a fully automated method called CycleFootprint that can: 1) identify the most relevant signal that has the most obvious recurring patterns among multiple signals; and 2) automatically find the cycles from the selected signal. The main idea behind CycleFootprint is mining footprints in the cycles. We assume that there should be a unique pattern in each cycle that shows up repeatedly in each cycle. By mining those footprints, we can identify cycles. We evaluate our method with existing labeled ground truth data of a real separator in marine application equipped with multiple health monitoring sensors. 86\% of cycles extracted by our method match fully or with at least 99\% overlap with true cycles, which sounds promising given its unsupervised and fully automated nature.},
	language = {en},
	booktitle = {{IoT} {Streams} for {Data}-{Driven} {Predictive} {Maintenance} and {IoT}, {Edge}, and {Mobile} for {Embedded} {Machine} {Learning}},
	publisher = {Springer International Publishing},
	author = {Fanaee-T, Hadi and Bouguelia, Mohamed-Rafik and Rahat, Mahmoud and Blixt, Jonathan and Singh, Harpal},
	editor = {Gama, Joao and Pashami, Sepideh and Bifet, Albert and Sayed-Mouchawe, Moamar and Fröning, Holger and Pernkopf, Franz and Schiele, Gregor and Blott, Michaela},
	year = {2020},
	keywords = {Cycle detection, IoT, Sensors},
	pages = {30--44},
}

Downloads: 0

{"_id":"dQE6KLMHbvuJxL5hT","bibbaseid":"fanaeet-bouguelia-rahat-blixt-singh-cyclefootprintafullyautomatedmethodforextractingoperationcyclesfromhistoricalrawdataofmultiplesensors-2020","author_short":["Fanaee-T, H.","Bouguelia, M.","Rahat, M.","Blixt, J.","Singh, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Cham","series":"Communications in Computer and Information Science","title":"CycleFootprint: A Fully Automated Method for Extracting Operation Cycles from Historical Raw Data of Multiple Sensors","isbn":"978-3-030-66770-2","shorttitle":"CycleFootprint","doi":"10.1007/978-3-030-66770-2_3","abstract":"Extracting operation cycles from the historical reading of sensors is an essential step in IoT data analytics. For instance, we can exploit the obtained cycles for learning the normal states to feed into semi-supervised models or dictionaries for efficient real-time anomaly detection on the sensors. However, this is a difficult problem due to this fact that we may have different types of cycles, each of which with varying lengths. Current approaches are highly dependent on manual efforts by the aid of visualization and knowledge of domain experts, which is not feasible on a large scale. We propose a fully automated method called CycleFootprint that can: 1) identify the most relevant signal that has the most obvious recurring patterns among multiple signals; and 2) automatically find the cycles from the selected signal. The main idea behind CycleFootprint is mining footprints in the cycles. We assume that there should be a unique pattern in each cycle that shows up repeatedly in each cycle. By mining those footprints, we can identify cycles. We evaluate our method with existing labeled ground truth data of a real separator in marine application equipped with multiple health monitoring sensors. 86% of cycles extracted by our method match fully or with at least 99% overlap with true cycles, which sounds promising given its unsupervised and fully automated nature.","language":"en","booktitle":"IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning","publisher":"Springer International Publishing","author":[{"propositions":[],"lastnames":["Fanaee-T"],"firstnames":["Hadi"],"suffixes":[]},{"propositions":[],"lastnames":["Bouguelia"],"firstnames":["Mohamed-Rafik"],"suffixes":[]},{"propositions":[],"lastnames":["Rahat"],"firstnames":["Mahmoud"],"suffixes":[]},{"propositions":[],"lastnames":["Blixt"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Singh"],"firstnames":["Harpal"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Gama"],"firstnames":["Joao"],"suffixes":[]},{"propositions":[],"lastnames":["Pashami"],"firstnames":["Sepideh"],"suffixes":[]},{"propositions":[],"lastnames":["Bifet"],"firstnames":["Albert"],"suffixes":[]},{"propositions":[],"lastnames":["Sayed-Mouchawe"],"firstnames":["Moamar"],"suffixes":[]},{"propositions":[],"lastnames":["Fröning"],"firstnames":["Holger"],"suffixes":[]},{"propositions":[],"lastnames":["Pernkopf"],"firstnames":["Franz"],"suffixes":[]},{"propositions":[],"lastnames":["Schiele"],"firstnames":["Gregor"],"suffixes":[]},{"propositions":[],"lastnames":["Blott"],"firstnames":["Michaela"],"suffixes":[]}],"year":"2020","keywords":"Cycle detection, IoT, Sensors","pages":"30–44","bibtex":"@inproceedings{fanaee-t_cyclefootprint_2020,\n\taddress = {Cham},\n\tseries = {Communications in {Computer} and {Information} {Science}},\n\ttitle = {{CycleFootprint}: {A} {Fully} {Automated} {Method} for {Extracting} {Operation} {Cycles} from {Historical} {Raw} {Data} of {Multiple} {Sensors}},\n\tisbn = {978-3-030-66770-2},\n\tshorttitle = {{CycleFootprint}},\n\tdoi = {10.1007/978-3-030-66770-2_3},\n\tabstract = {Extracting operation cycles from the historical reading of sensors is an essential step in IoT data analytics. For instance, we can exploit the obtained cycles for learning the normal states to feed into semi-supervised models or dictionaries for efficient real-time anomaly detection on the sensors. However, this is a difficult problem due to this fact that we may have different types of cycles, each of which with varying lengths. Current approaches are highly dependent on manual efforts by the aid of visualization and knowledge of domain experts, which is not feasible on a large scale. We propose a fully automated method called CycleFootprint that can: 1) identify the most relevant signal that has the most obvious recurring patterns among multiple signals; and 2) automatically find the cycles from the selected signal. The main idea behind CycleFootprint is mining footprints in the cycles. We assume that there should be a unique pattern in each cycle that shows up repeatedly in each cycle. By mining those footprints, we can identify cycles. We evaluate our method with existing labeled ground truth data of a real separator in marine application equipped with multiple health monitoring sensors. 86\\% of cycles extracted by our method match fully or with at least 99\\% overlap with true cycles, which sounds promising given its unsupervised and fully automated nature.},\n\tlanguage = {en},\n\tbooktitle = {{IoT} {Streams} for {Data}-{Driven} {Predictive} {Maintenance} and {IoT}, {Edge}, and {Mobile} for {Embedded} {Machine} {Learning}},\n\tpublisher = {Springer International Publishing},\n\tauthor = {Fanaee-T, Hadi and Bouguelia, Mohamed-Rafik and Rahat, Mahmoud and Blixt, Jonathan and Singh, Harpal},\n\teditor = {Gama, Joao and Pashami, Sepideh and Bifet, Albert and Sayed-Mouchawe, Moamar and Fröning, Holger and Pernkopf, Franz and Schiele, Gregor and Blott, Michaela},\n\tyear = {2020},\n\tkeywords = {Cycle detection, IoT, Sensors},\n\tpages = {30--44},\n}\n\n\n\n","author_short":["Fanaee-T, H.","Bouguelia, M.","Rahat, M.","Blixt, J.","Singh, H."],"editor_short":["Gama, J.","Pashami, S.","Bifet, A.","Sayed-Mouchawe, M.","Fröning, H.","Pernkopf, F.","Schiele, G.","Blott, M."],"key":"fanaee-t_cyclefootprint_2020","id":"fanaee-t_cyclefootprint_2020","bibbaseid":"fanaeet-bouguelia-rahat-blixt-singh-cyclefootprintafullyautomatedmethodforextractingoperationcyclesfromhistoricalrawdataofmultiplesensors-2020","role":"author","urls":{},"keyword":["Cycle detection","IoT","Sensors"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["PfM5iniYHEthCfQDH","RktFJE9cDa98BRLZF","yanwtMpCcFaHzRwWb","iwKepCrWBps7ojhDx"],"keywords":["cycle detection","iot","sensors"],"search_terms":["cyclefootprint","fully","automated","method","extracting","operation","cycles","historical","raw","data","multiple","sensors","fanaee-t","bouguelia","rahat","blixt","singh"],"title":"CycleFootprint: A Fully Automated Method for Extracting Operation Cycles from Historical Raw Data of Multiple Sensors","year":2020}