An improved artificial dendrite cell algorithm for abnormal signal detection

Mohamad Farhan Mohamad Mohsin, Azuraliza Abu Bakar, Abdul Razak Hamdan, Mohd Helmy Abdul Wahab

Research output: Contribution to journalArticle

Abstract

In dendrite cell algorithm (DCA), the abnormality of a data point is determined by comparing the multi-context antigen value (MCAV) with anomaly threshold. The limitation of the existing threshold is that the value needs to be determined before mining based on previous information and the existing MCAV is inefficient when exposed to extreme values. This causes the DCA fails to detect new data points if the pattern has distinct behavior from previous information and affects detection accuracy. This paper proposed an improved anomaly threshold solution for DCA using the statistical cumulative sum (CUSUM) with the aim to improve its detection capability. In the proposed approach, the MCAV were normalized with upper CUSUM and the new anomaly threshold was calculated during run time by considering the acceptance value and min MCAV. From the experiments towards 12 benchmark and two outbreak datasets, the improved DCA is proven to have a better detection result than its previous version in terms of sensitivity, specificity, false detection rate and accuracy.

Original languageEnglish
Pages (from-to)33-54
Number of pages22
JournalJournal of Information and Communication Technology
Volume17
Issue number1
Publication statusPublished - 1 Jan 2018

Fingerprint

Dendrite
Signal Detection
Signal detection
Antigens
Anomaly
Cumulative Sum
Cell
Extreme Values
Specificity
Mining
Benchmark
Distinct
Context
Experiment
Experiments

Keywords

  • Anomaly threshold
  • Dendrite cell algorithm
  • Multi-context antigen value

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Cite this

An improved artificial dendrite cell algorithm for abnormal signal detection. / Mohsin, Mohamad Farhan Mohamad; Abu Bakar, Azuraliza; Hamdan, Abdul Razak; Wahab, Mohd Helmy Abdul.

In: Journal of Information and Communication Technology, Vol. 17, No. 1, 01.01.2018, p. 33-54.

Research output: Contribution to journalArticle

@article{037d2b818e254403b35d88003a540782,
title = "An improved artificial dendrite cell algorithm for abnormal signal detection",
abstract = "In dendrite cell algorithm (DCA), the abnormality of a data point is determined by comparing the multi-context antigen value (MCAV) with anomaly threshold. The limitation of the existing threshold is that the value needs to be determined before mining based on previous information and the existing MCAV is inefficient when exposed to extreme values. This causes the DCA fails to detect new data points if the pattern has distinct behavior from previous information and affects detection accuracy. This paper proposed an improved anomaly threshold solution for DCA using the statistical cumulative sum (CUSUM) with the aim to improve its detection capability. In the proposed approach, the MCAV were normalized with upper CUSUM and the new anomaly threshold was calculated during run time by considering the acceptance value and min MCAV. From the experiments towards 12 benchmark and two outbreak datasets, the improved DCA is proven to have a better detection result than its previous version in terms of sensitivity, specificity, false detection rate and accuracy.",
keywords = "Anomaly threshold, Dendrite cell algorithm, Multi-context antigen value",
author = "Mohsin, {Mohamad Farhan Mohamad} and {Abu Bakar}, Azuraliza and Hamdan, {Abdul Razak} and Wahab, {Mohd Helmy Abdul}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "17",
pages = "33--54",
journal = "Journal of Information and Communication Technology",
issn = "1675-414X",
publisher = "Universiti Utara Malaysia Press",
number = "1",

}

TY - JOUR

T1 - An improved artificial dendrite cell algorithm for abnormal signal detection

AU - Mohsin, Mohamad Farhan Mohamad

AU - Abu Bakar, Azuraliza

AU - Hamdan, Abdul Razak

AU - Wahab, Mohd Helmy Abdul

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In dendrite cell algorithm (DCA), the abnormality of a data point is determined by comparing the multi-context antigen value (MCAV) with anomaly threshold. The limitation of the existing threshold is that the value needs to be determined before mining based on previous information and the existing MCAV is inefficient when exposed to extreme values. This causes the DCA fails to detect new data points if the pattern has distinct behavior from previous information and affects detection accuracy. This paper proposed an improved anomaly threshold solution for DCA using the statistical cumulative sum (CUSUM) with the aim to improve its detection capability. In the proposed approach, the MCAV were normalized with upper CUSUM and the new anomaly threshold was calculated during run time by considering the acceptance value and min MCAV. From the experiments towards 12 benchmark and two outbreak datasets, the improved DCA is proven to have a better detection result than its previous version in terms of sensitivity, specificity, false detection rate and accuracy.

AB - In dendrite cell algorithm (DCA), the abnormality of a data point is determined by comparing the multi-context antigen value (MCAV) with anomaly threshold. The limitation of the existing threshold is that the value needs to be determined before mining based on previous information and the existing MCAV is inefficient when exposed to extreme values. This causes the DCA fails to detect new data points if the pattern has distinct behavior from previous information and affects detection accuracy. This paper proposed an improved anomaly threshold solution for DCA using the statistical cumulative sum (CUSUM) with the aim to improve its detection capability. In the proposed approach, the MCAV were normalized with upper CUSUM and the new anomaly threshold was calculated during run time by considering the acceptance value and min MCAV. From the experiments towards 12 benchmark and two outbreak datasets, the improved DCA is proven to have a better detection result than its previous version in terms of sensitivity, specificity, false detection rate and accuracy.

KW - Anomaly threshold

KW - Dendrite cell algorithm

KW - Multi-context antigen value

UR - http://www.scopus.com/inward/record.url?scp=85037596349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037596349&partnerID=8YFLogxK

M3 - Article

VL - 17

SP - 33

EP - 54

JO - Journal of Information and Communication Technology

JF - Journal of Information and Communication Technology

SN - 1675-414X

IS - 1

ER -