Brain Computer Interface by Use of Single Trial EEG on Recalling of Several Images


YAMANOİ T., Toyoshima H., Otsuki M., Ohnishi S., Yamazaki T., Sugeno M.

15th International Conference on Information Processing and Management of Uncertainty in Knowledge-based Systems, IPMU 2014, Montpellier, France, 15 - 19 July 2014, vol.444 CCIS, pp.508-517, (Full Text) identifier

  • Nəşrin Növü: Conference Paper / Full Text
  • Cild: 444 CCIS
  • Doi nömrəsi: 10.1007/978-3-319-08852-5_52
  • Çap olunduğu şəhər: Montpellier
  • Ölkə: France
  • Səhifə sayı: pp.508-517
  • Açar sözlər: Brain computer interface, Canonical discriminant analysis, Image recognition, Single trial Electroencephalogram
  • Açıq Arxiv Kolleksiyası: Konfrans Materialı
  • Adres: Bəli

Qısa məlumat

In order to develop a brain computer interface (BCI), the present authors investigated the brain activity during recognizing or recalling some images of line drawings. The middle frontal robe is known to be related to the function of central executive system on working memory. It is supposed to be so called headquarters of the higher order function of the human brain.Taking into account these facts, the authors recorded Electroencephalogram (EEG) from subjects looking and recalling four types of line drawings of body part, tetra pod, and further ten types of tetra pods, home appliances and fruits that were presented on a CRT. They investigated a single trial EEGs of the subjects precisely after the latency at 400ms, and determined effective sampling latencies for the discriminant analysis to some types of images. They sampled EEG data at latencies from 400ms to 900ms at 25ms intervals by the four channels such as Fp2, F4, C4 and F8. Data were resampled -1 ms and -2 ms backward. Results of the discriminant analysis with the jack knife (cross validation) method for four type objective variates, the discriminant rates for two subjects were more than 95%, and for ten objective variates were almost 80%. © Springer International Publishing Switzerland 2014.