@article{oai:ipsj.ixsq.nii.ac.jp:00182271,
 author = {Pitoyo, Hartono and Kayo, Ogawa and Pitoyo, Hartono and Kayo, Ogawa},
 issue = {2},
 journal = {情報処理学会論文誌教育とコンピュータ（TCE）},
 month = {Jun},
 note = {In the last few years learning management systems have been widely introduced in many educational institutions with the primary objectives of supporting students with more flexible learning environments and also importantly acquiring learning pattern data from students and extracting meaningful contents from the data to be used to improve the learning quality. However, often due to the complexity and the multidimensionality of the data, the extraction of meaningful information from them is difficult. So far many methods for mining useful information from complex data have been proposed, and one of the most powerful is visualization that allows intuitive understanding on the underlying properties of the data. In this paper, visualization of E-learning data using a newly introduced context-oriented self-organizing map is introduced and compared against some traditional visualization methods., In the last few years learning management systems have been widely introduced in many educational institutions with the primary objectives of supporting students with more flexible learning environments and also importantly acquiring learning pattern data from students and extracting meaningful contents from the data to be used to improve the learning quality. However, often due to the complexity and the multidimensionality of the data, the extraction of meaningful information from them is difficult. So far many methods for mining useful information from complex data have been proposed, and one of the most powerful is visualization that allows intuitive understanding on the underlying properties of the data. In this paper, visualization of E-learning data using a newly introduced context-oriented self-organizing map is introduced and compared against some traditional visualization methods.},
 pages = {20--27},
 title = {Intuitive Analysis by Visualizing Context Relevant E-learning Data},
 volume = {3},
 year = {2017}
}