BCI cinematics – A pre-release analyser for movies using H2O deep learning platform. (March 2019)

• Record Type: Journal Article
• Authors: K.B, Sundhara Kumar; G, Krishna; N, Bhalaji; S, Chithra
• Is Part Of: Computers & electrical engineering. Volume 74(2019)
• Page Start: 547
• Page End: 556
• Publication Date: 2019-03
• Subjects: BCI cinematics -- Machine learning, Movie analysis -- Pre-release analysis -- Deep learning, H2O framework; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.03.015
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Entertainment industry has seen a phenomenal growth throughout the globe in recent times and movie industry enjoys a crucial role in the above emergence. A movie can capture the attention of a viewer and can trigger cognitive and emotional processes in the brain. In this article we assess the emotional outcome of the viewer while they watch the movie before its actual release that is, during its preview. Traditionally FMRI was used to assess the activity of brain but proved to be non-feasible and costly so we used EEG Sensors to monitor and record the functioning of the brain of movie viewer for further analysis. The collected data through EEG sensor were analysed using deep learning framework. H2 O package of deep learning was employed to find high and low of different brain waves mapping to the emotions depicted in the every scene of the movie. Our proposed system named BCI cinematics obtained 85% accuracy and results were validated by obtaining the feedback from the stake holders. The outcome of this work will assist the creators to understand the emotional impact of movie over a normal viewer impartially thus enable them to modify certain scenes or change sequence of scenes and so on. When deployed in real time our system prove to be a cost saver for movie makers.