2019 IEEE Bombay Section Signature Conference (IBSSC) 2019
DOI: 10.1109/ibssc47189.2019.8973004
|View full text |Cite
|
Sign up to set email alerts
|

Wireless Body Area Network Sensor Faults and Anomalous Data Detection and Classification using Machine Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
10
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 13 publications
(11 citation statements)
references
References 13 publications
1
10
0
Order By: Relevance
“…Figure 2 presents the performance of the SFD algorithm for Dataset 1 in terms of TPR and TNR. One can clearly see that the anomaly detection rate of the proposed scheme is 100%, which matches the results of existing schemes [12–17]. Figure 3 presents the performance of the SFD algorithm for Dataset 1 in terms of FPR and FNR.…”
Section: Resultssupporting
confidence: 73%
See 3 more Smart Citations
“…Figure 2 presents the performance of the SFD algorithm for Dataset 1 in terms of TPR and TNR. One can clearly see that the anomaly detection rate of the proposed scheme is 100%, which matches the results of existing schemes [12–17]. Figure 3 presents the performance of the SFD algorithm for Dataset 1 in terms of FPR and FNR.…”
Section: Resultssupporting
confidence: 73%
“…The proposed SFD algorithm significantly reduces FPR by 91.22%, 84.20%, 37.80%, 26.17%, 28.02%, 32.33%, 29.78%, and 45.80% compared to the existing schemes from Ref. [11–18], respectively. The proposed scheme for Dataset 1 achieves high accuracy, precision, and F 1 score based on its high detection rate and low FPR.…”
Section: Resultsmentioning
confidence: 95%
See 2 more Smart Citations
“…Nevertheless, with an increase in the number of colluding sensors, the detection efficiency degrades to a point that the detection fails when most of the sensors are colluding. Furthermore, researchers (Nagdeo & Mahapatro 2019) have implemented an ML model to separate anomalous data from legitimate sensed data. This research used a combination of ANN with Ensemble LinReg as a detection technique for abnormalities in WBAN sensors.…”
Section: Computer Sciencementioning
confidence: 99%