Show simple item record

dc.contributor.authorNakip, M.
dc.contributor.authorGuzelis, C.
dc.contributor.authorYildiz, O.
dc.date.accessioned2021-12-14T11:04:56Z
dc.date.available2021-12-14T11:04:56Z
dc.date.issued2021
dc.identifier.issn2169-3536
dc.identifier.urihttps://dspace.yasar.edu.tr/xmlui/handle/20.500.12742/18504
dc.description.abstractWe propose a Recurrent Trend Predictive Neural Network (rTPNN) for multi-sensor fire detection based on the trend as well as level prediction and fusion of sensor readings. The rTPNN model significantly differs from the existing methods due to recurrent sensor data processing employed in its architecture. rTPNN performs trend prediction and level prediction for the time series of each sensor reading and captures trends on multivariate time series data produced by multi-sensor detector. We compare the performance of the rTPNN model with that of each of the Linear Regression (LR), Nonlinear Perceptron (NP), Multi-Layer Perceptron (MLP), Kendall- \tau combined with MLP, Probabilistic Bayesian Neural Network (PBNN), Long-Short Term Memory (LSTM), and Support Vector Machine (SVM) on a publicly available fire data set. Our results show that rTPNN model significantly outperforms all of the other models (with 96% accuracy) while it is the only model that achieves high True Positive and True Negative rates (both above 92%) at the same time. rTPNN also triggers an alarm in only 11 s from the start of the fire, where this duration is 22 s for the second-best model. Moreover, we present that the execution time of rTPNN is acceptable for real-time applications.en_US
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectFire detectionen_US
dc.subjectTrend predictionen_US
dc.subjectMulti-sensoren_US
dc.titleRecurrent Trend Predictive Neural Network for Multi-Sensor Fire Detectionen_US
dc.typeArticleen_US
dc.relation.journalIEEE Accessen_US
dc.identifier.doi10.1109/ACCESS.2021.3087736en_US
dc.contributor.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.identifier.issue9en_US
dc.identifier.woshttps://www.webofscience.com/wos/woscc/full-record/WOS:000674098400001?AlertId=fc1c72a7-b080-4d60-92a3-edbe4aa40157&SID=E6Z5I2uRPq1sXeqbCdRen_US
dc.identifier.scopushttps://www.scopus.com/record/display.uri?eid=2-s2.0-85112169845&origin=resultslist&sort=plf-f&src=s&st1=Recurrent+Trend+Predictive+Neural+Network+for+Multi-Sensor+Fire+Detection&sid=60e0d962cae5fd2561e2bcef01820a32&sot=b&sdt=b&sl=88&s=TITLE-ABS-KEY%28Recurrent+Trend+Predictive+Neural+Network+for+Multi-Sensor+Fire+Detection%29&relpos=0&citeCnt=0&searchTerm=en_US
dc.contributor.yasarauthor0000-0001-5416-368X: Cüneyt Güzelişen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record