Publication:
Human activities classification based on ?-OTDR system by utilizing gammatone filter cepstrum coefficient envelope using support vector machine

Simple item page
dc.citedby3
dc.contributor.authorSaleh N.L.en_US
dc.contributor.authorFaisal B.en_US
dc.contributor.authorYusri M.S.en_US
dc.contributor.authorSulaiman A.H.en_US
dc.contributor.authorIsmail M.F.en_US
dc.contributor.authorNik Zulkefli N.A.H.A.en_US
dc.contributor.authorMuhamud-Kayat S.en_US
dc.contributor.authorIsmail A.en_US
dc.contributor.authorAbdullah F.en_US
dc.contributor.authorJamaludin M.Z.en_US
dc.contributor.authorAripin N.M.en_US
dc.contributor.authorid57198797134en_US
dc.contributor.authorid57209973264en_US
dc.contributor.authorid57480859600en_US
dc.contributor.authorid36810678100en_US
dc.contributor.authorid57211721986en_US
dc.contributor.authorid58191841700en_US
dc.contributor.authorid55027311200en_US
dc.contributor.authorid36023817800en_US
dc.contributor.authorid56613644500en_US
dc.contributor.authorid58071849900en_US
dc.contributor.authorid35092180800en_US
dc.date.accessioned2024-10-14T03:17:53Z
dc.date.available2024-10-14T03:17:53Z
dc.date.issued2023
dc.description.abstractIntrusion into the critical energy assets area is a serious problem that may cause essential operations to be disrupted. Besides using closed-circuit television to detect early intrusion, perimeter fencing using fiber optic distributed acoustic sensing is becoming popular. This paper proposes a phase-sensitive optical time-domain reflectometry system-based classification of human activities using a coexisting support vector machine which the Gammatone filter cepstrum coefficient envelope as input features. The detection and classification campaign consists of four phases: detection, feature extraction, classification, and evaluation. A combination of wavelet and normalized differential methods is used for detection to improve the signal-to-noise ratio. Simple dataset management methods that use envelope-wrapped, local maxima, averaging, truncation, rearrangement, and random permutation are beneficial for reducing the dimensionality of problems with lower computational power. The classification performance was considered good, which is higher than 95 %. Despite using the legacy classifier algorithm, an improvement in dataset management presented in this paper proves that it is still realistic to implement and does not require demanding computational power to achieve a good classification result. Also, the way datasets are managed in this paper is made to be flexible enough to work with other legacy classifiers. � 2023 Elsevier Ltden_US
dc.description.natureFinalen_US
dc.identifier.ArtNo109417
dc.identifier.doi10.1016/j.optlastec.2023.109417
dc.identifier.scopus2-s2.0-85153316700
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85153316700&doi=10.1016%2fj.optlastec.2023.109417&partnerID=40&md5=95795227857eb1f3f2e3745feead305f
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/34081
dc.identifier.volume164
dc.publisherElsevier Ltden_US
dc.sourceScopus
dc.sourcetitleOptics and Laser Technology
dc.subjectDistributed acoustic sensor
dc.subjectEnergy infrastructure
dc.subjectGammatone filter cepstral coefficient
dc.subjectPhase optical time-domain reflectometry
dc.subjectSupport vector machine
dc.subjectClassification (of information)
dc.subjectFeature extraction
dc.subjectPermittivity measurement
dc.subjectReflection
dc.subjectReflectometers
dc.subjectSignal to noise ratio
dc.subjectTime domain analysis
dc.subjectAcoustic Sensors
dc.subjectCepstral coefficients
dc.subjectDistributed acoustic sensor
dc.subjectEnergy infrastructures
dc.subjectGammatone filter cepstral coefficient
dc.subjectGammatone filters
dc.subjectHuman activities
dc.subjectOptical time domain reflectometry
dc.subjectPhase optical time-domain reflectometry
dc.subjectSupport vectors machine
dc.subjectSupport vector machines
dc.titleHuman activities classification based on ?-OTDR system by utilizing gammatone filter cepstrum coefficient envelope using support vector machineen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS