Anda belum login :: 23 Nov 2024 05:23 WIB
Detail
ArtikelA semi-supervised attributes-weighting clustering method for inattention prediction in human-machine interaction systems  
Oleh: Choi, Yerim ; Kwon, Namyeon ; Yoon, Jooshik ; Jeon, Sungwook ; Paeng, Bo-Hyung ; Park, Jonghun ; Shin, Dongmin
Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-8.
Topik: EEG-signal; Human-machine interaction system; Semi-supervised approach; Attributes-weighting clustering
Fulltext: 1088.pdf (297.11KB)
Isi artikelAs the operator’s inattention is known as one of the main reasons for accidents in many human-machine interaction systems, developing a method for the inattention prediction becomes an important research issue. Several inattention prediction methods based on EEG-signal by adopting supervised learning models have been proposed with promising results. However, obtaining accurate labeled data for supervised learning is almost impossible due to the absence of a standardized measure for inattention and the inexactitude of alternative measures. In this paper, we present a semi-supervised attributes-weighting clustering method which can predict inattention by incorporating small size of labeled data and different weighting for each frequency band, where both the labeled data and the weighting scheme can be acquired from prior knowledge. The effectiveness of the proposed method is demonstrated with real-world dataset collected from subjects during maneuvering a flight simulator.
Opini AndaKlik untuk menuliskan opini Anda tentang koleksi ini!

Kembali
design
 
Process time: 0 second(s)