Comparative Analysis of Signal Denoising Methods for Object Selection in Gaze-Based Interactive Applications
Penulis/Author
SUATMI MURNANI (1); Dr.Eng. Ir. Sunu Wibirama, S.T., M.Eng., IPM. (2); Ir. Noor Akhmad Setiawan, S.T., M.T., Ph.D., IPM. (3)
Tanggal/Date
30 2019
Kata Kunci/Keyword
Abstrak/Abstract
Extracted data from an eye tracker generally contain inaccurate and noisy signals of spatial gaze position. The noise can affect performance of object selection in gaze-based interactive applications that implement smooth pursuit eye movement to control digital contents. Some signal denoising methods—such as Moving Average Filter, Kalman Filter, and Particle Filter—have been used in a smooth-pursuit-based interactive application to denoise the signal. There is another signal denoising method named Naive Segmented Linear Regression (NSLR) that is able to denoise gaze position signal by segmenting the signal and performing linear regression. Unfortunately, the use of NSLR in a smooth-pursuit-based interactive application is yet to be considered. To fill this research gap, we apply the NSLR sig- nal denoising method and compare its performance on gaze- based object selection against the above-mentioned filters. Experimental results show that gaze-based object selection with Euclidean Distance and Moving Average Filter obtains the best accuracy of 92.37±5.63%, whereas, object selection with Pearson Product Moment Coefficient and Kalman Filter yields the best accuracy of 23.57±2.08%. In future, our results can be used as guidance in the development of smooth- pursuit-based interactive applications.
Level
Internasional
Status
Dokumen Karya
No
Judul
Tipe Dokumen
Aksi
1
28 Similarity Comparative Analysis of Signal Denoising Methods for Object Selection in Gaze-Based Interactive App.pdf
Cek Similarity
2
ICST 2019 FULL - Comparative Analysis of Signal Denoising Methods for Object Selection in Gaze-Based Interactive Applications.pdf
