BISE Dataset-Balinese Script for Imaginary Spelling using Electroencephalogram Signals

Balinese Script for Imaginary Spelling using Electroencephalogram (BISE dataset) is a collection of data related to pronunciation/spelling and imagination of Balinese script based on electroencephalogram (EEG) signals. This dataset consists of character spelling (CS) and character imagination (CI) datasets. Providing CS and CI datasets is very important to ensure that the EEG signal pattern for the spoken script matches the imagined script. So, this dataset would actually need to be provided. In addition, previous researchers have yet to collect a Balinese script imagination dataset. The participants used as samples in this study were 31 healthy people, 8 males and 23 females, from students of the Balinese language education study program at Universitas Pendidikan Ganesha. The participants' EEG signals were recorded using Contec KT 88 with 16 channels. This dataset consists of 7 types of data, namely: (1) Raw data from the 1st experiment, (2) Raw data from the 2nd experiment, (3) Data analysis of character spelling (CS) in 1st experiment, (4) Data analysis of character imagination (CI) in 1st experiment, (5) Data analysis of character spelling (CS) in 2nd experiment, (6) Data analysis of character imagination (CI) in 2nd experiment, and (7) Raw data from calm conditions. The first experimental data contains EEG signal data from participants experimenting with pronouncing and imagining 18 Balinese scripts sequentially and randomly. Furthermore, the raw data of the second experiment contains EEG signal data from participants who performed the spelling (CS) and imagining (CI) of 6 Balinese vowel scripts sequentially and randomly.
Furthermore, from the raw data, a data analysis process was carried out for the raw data in the 1st and 2nd experiments. In the first experiment's raw data, two analysis data were produced for 18 Balinese scripts spelling and 18 Balinese scripts imagined. Furthermore, for the raw data in the 2nd experiment, two analysis data were produced for 6 Balinese vowel scripts that were spelling and 6 Balinese vowel scripts that were imagined.
Finally, the raw data of the calm condition contains EEG signal data from participants in a quiet condition before starting the experiment.

巴厘文拼写与想象数据集（BISE数据集）系基于脑电图（EEG）信号对巴厘文拼写与想象相关数据的集合。该数据集包括字符拼写（CS）与字符想象（CI）两大子集，提供CS和CI子集至关重要，以确保所记录的脑电图信号模式与实际发音与想象中的文本相匹配。因此，该数据集的提供实属必要。此前，学界尚无针对巴厘文想象数据集的收集。本研究之样本参与者为31名健康个体，其中男性8名，女性23名，均来自加纳沙大学巴厘语教育研究项目。参与者的脑电图信号由Contec KT 88设备以16通道记录。本数据集包含七种类型的数据，包括：（1）第一次实验的原始数据，（2）第二次实验的原始数据，（3）第一次实验中字符拼写（CS）的数据分析，（4）第一次实验中字符想象（CI）的数据分析，（5）第二次实验中字符拼写（CS）的数据分析，（6）第二次实验中字符想象（CI）的数据分析，以及（7）平静状态下的原始数据。第一次实验的数据包含参与者依次随机发音和想象18个巴厘文字符的脑电图信号数据。此外，第二次实验的原始数据包含参与者依次随机拼写和想象6个巴厘文元音字符的脑电图信号数据。进一步地，从原始数据中进行了数据分析过程。在第一次实验的原始数据中，针对18个巴厘文字符的拼写和想象分别产生了两个分析数据集。同样，对于第二次实验的原始数据，针对6个巴厘文元音字符的拼写和想象也分别产生了两个分析数据集。最终，平静状态下的原始数据包含了实验开始前处于安静状态下的参与者的脑电图信号数据。