Text

Large-Scale Datastreams Surveillance via Pattern-Oriented-Sampling

Monitoring large-scale datastreams with limited resources has become increasingly important for real-time detection of abnormal activities in many applications. Despite the availability of large datasets, the challenges associated with designing an efficient change-detection when clustering or spatial pattern exists are not yet well addressed. In this article, a design-adaptive testing procedure is developed when only a limited number of streaming observations can be accessed at each time. We derive an optimal sampling strategy, the pattern-oriented-sampling, with which the proposed test possesses asymptotically and locally best power under alternatives. Then, a sequential change-detection procedure is proposed by integrating this test with generalized likelihood ratio approach. Benefiting from dynamically estimating the optimal sampling design, the proposed procedure is able to improve the sensitivity in detecting clustered changes compared with existing procedures. Its advantages are demonstrated in numerical simulations and a real data example. Ignoring the neighboring information of spatially structured data will tend to diminish the detection effectiveness of traditional detection procedures. Supplementary materials for this article are available online.

Ketersediaan

Informasi Detail

Judul Seri

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION (JASA); Vol.117 No.538 June 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 794-808

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

KERNEL SMOOTHING
OPTIMAL SAMPLING
GENERALIZED LIKELIHOOD RATIO METHOD
STATISTICAL MONITORING
DESIGN-ADAPTIVE TEST
SEQUENTIAL CHANGE DETECTION

Info Detail Spesifik

https://doi.org/10.1080/01621459.2020.1819295

Pernyataan Tanggungjawab

Haojie Ren, Changliang Zou, Nan Chen, Runze

Versi lain/terkait

Lampiran Berkas

Komentar