Quality of Service through Path Selecting Algorithm in Pervasive and IoT Computing

Authors: , ,

Abstract: The direction of arrival (DoA) estimation is thecrucial aspect of the radar technologies for detecting and dividingseveral signal sources. In this scenario, the antenna array outputmodeling involves numerous parameters including noise samples,signal waveform, signal directions, signal number, and signal to noiseratio (SNR), and thereby the methods of the DoA estimation relyheavily on the generalization characteristic for establishing a largenumber of the training data sets. Hence, we have analogouslyrepresented the two different optimization models of the DoAestimation; (1) the implementation of the decision directed acyclicgraph (DDAG) for the multiclass least-squares support vectormachine (LS-SVM), and (2) the optimization method of the deepneural network (DNN) radial basis function (RBF). We haverigorously verified that the LS-SVM DDAG algorithm is capable ofaccurately classifying DoAs for the three classes. However, theaccuracy and robustness of the DoA estimation are still highlysensitive to technological imperfections of the antenna arrays such asnon-ideal array design and manufacture, array implementation,mutual coupling effect, and background radiation and thereby themethod may fail in representing high precision for the DoAestimation. Therefore, this work has a further contribution ondeveloping the DNN-RBF model for the DoA estimation forovercoming the limitations of the non-parametric and data-drivenmethods in terms of array imperfection and generalization. Thenumerical results of implementing the DNN-RBF model haveconfirmed the better performance of the DoA estimation comparedwith the LS-SVM algorithm. Consequently, we have analogouslyevaluated the performance of utilizing the two aforementionedoptimization methods for the DoA estimation using the concept of themean squared error (MSE).

International Journal of Electrical Engineering and Computer Science, E-ISSN: 2769-2507, Volume 3, 2021, Art. #12

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
Padmanabhan P., Sampath Kumar K., John A, "Quality of Service through Path Selecting Algorithm in Pervasive and IoT Computing," International Journal of Electrical Engineering and Computer Science, vol. 3, pp. 83-91, 2021, DOI:
Padmanabhan P., Sampath Kumar K., John A. Quality of Service through Path Selecting Algorithm in Pervasive and IoT Computing. International Journal of Electrical Engineering and Computer Science. 2021;3:83-91.
Copy to Clipboard
Citation copied to Clipboard

Certification

---