TY - JOUR
T1 - Degree-Based WCL for Video Endoscopic Capsule Localization
AU - Hany, Umma
AU - Akter, Lutfa
AU - Hossain, Farhad
N1 - Publisher Copyright:
© 2001-2012 IEEE.
PY - 2017/5/1
Y1 - 2017/5/1
N2 - Wireless video capsule endoscope (VCE) is used to diagnose lesions along digestive tracts. For proper diagnosis, it is necessary to know the exact location of the lesions which may be estimated by localizing the VCE. In this paper, we propose a simple VCE localization approach using static and dynamic degree-based weighted centroid localization (WCL). In our proposed approach, a sensor array of eight receivers is used to estimate the distance of the moving capsule. The estimated distance is then raised to a higher degree to reduce the weight of the remote sensors marginally lower. We propose a suboptimal method of both static and dynamic degree calculation using the estimated distances. We also analytically compute the optimal values of the degree to set benchmark to compare the performance of our proposed suboptimal methods. We develop a 3 D simulation platform using MATLAB to show the results and to verify the accuracy. We use indices named localization error (LE), average localization error (ALE), standard deviation (STD) and the normalized error to evaluate the performance. Using static optimal degree, the ALE is 5.19 mm where ALE of 6.55 mm is reachable using the suboptimal method. For dynamic degree, ALE using optimal degree is 3.8 mm, while the ALE using suboptimal degree is 6.27 mm. Thus, our proposed algorithms approach benchmark accuracy even if we change the dimension of the sensor network. The performance is also compared to the existing algorithms in the literature which shows better performance using our proposed algorithms.
AB - Wireless video capsule endoscope (VCE) is used to diagnose lesions along digestive tracts. For proper diagnosis, it is necessary to know the exact location of the lesions which may be estimated by localizing the VCE. In this paper, we propose a simple VCE localization approach using static and dynamic degree-based weighted centroid localization (WCL). In our proposed approach, a sensor array of eight receivers is used to estimate the distance of the moving capsule. The estimated distance is then raised to a higher degree to reduce the weight of the remote sensors marginally lower. We propose a suboptimal method of both static and dynamic degree calculation using the estimated distances. We also analytically compute the optimal values of the degree to set benchmark to compare the performance of our proposed suboptimal methods. We develop a 3 D simulation platform using MATLAB to show the results and to verify the accuracy. We use indices named localization error (LE), average localization error (ALE), standard deviation (STD) and the normalized error to evaluate the performance. Using static optimal degree, the ALE is 5.19 mm where ALE of 6.55 mm is reachable using the suboptimal method. For dynamic degree, ALE using optimal degree is 3.8 mm, while the ALE using suboptimal degree is 6.27 mm. Thus, our proposed algorithms approach benchmark accuracy even if we change the dimension of the sensor network. The performance is also compared to the existing algorithms in the literature which shows better performance using our proposed algorithms.
KW - least mean square methods
KW - received signal strength indicator
KW - sensor arrays
KW - Wireless sensor networks
UR - http://www.scopus.com/inward/record.url?scp=85018939701&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2017.2672699
DO - 10.1109/JSEN.2017.2672699
M3 - Article
AN - SCOPUS:85018939701
SN - 1530-437X
VL - 17
SP - 2904
EP - 2916
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 9
M1 - 7862130
ER -