Quick Search:

Predictive Analysis of Online Television Videos Using Machine Learning Algorithms

Jeyavadhanam, Rebecca B, Ramalingam, V. V., Sugumaran, V. and Rajkumar, D. (2022) Predictive Analysis of Online Television Videos Using Machine Learning Algorithms. In: Singh, Pradeep, (ed.) Fundamentals and Methods of Machine and Deep Learning. Scrivener Publishing, pp. 237-257

Full text not available from this repository.


In recent years, intelligent machine systems promote different disciplines and facilitate reasonable solutions in various domains. Machine learning offers higher-level services for organizations to build customized solutions. Machine learning algorithms are widely integrated with image, video analytics, and evolving technologies such as augmented and virtual reality. The advanced machine learning approach plays an essential key role in handling the huge volume of time-dependent data and modeling automatic detection systems. The data grows exponentially with varying sizes, formats, and complexity. Machine learning algorithms are developed to extract meaningful information from huge and complex datasets. Machine learning algorithms or models improve their efficiency by the training process. This chapter commences with machine learning fundamentals and focuses on the most prominent machine learning process of data collection, feature extraction, feature selection, and building model. The significance and functions of each method on the live streaming television video dataset are discussed. We addressed the dimensionality reduction and machine learning incremental learning process (online). Finally, we summarized the performance assessment of decision tree, J48 graft, LMT tree, REP tree, best first (BF), and random forest algorithms based on their classification performance to build a predictive model for automatic identification of advertisement videos.

Item Type: Book Section
Status: Published
DOI: https://doi.org/10.1002/9781119821908.ch10
School/Department: London Campus
URI: https://ray.yorksj.ac.uk/id/eprint/8266

University Staff: Request a correction | RaY Editors: Update this record