Deep Learning Hyper-Parameter Optimization for Video Analytics in Clouds

Muhammad Usman Yaseen, Ashiq Anjum, Omer Rana, Nikolaos Antonopoulos
2018 IEEE Transactions on Systems, Man & Cybernetics. Systems  
A system to perform video analytics is proposed using a dynamically tuned convolutional network. Videos are fetched from cloud storage, pre-processed and a model for supporting classification is developed on these video streams using cloud-based infrastructure. A key focus in this work is on tuning hyper-parameters associated with the deep learning algorithm used to construct the model. We further propose an automatic video object classification pipeline to validate the system. The mathematical
more » ... model used to support hyperparameter tuning improves performance of the proposed pipeline, and outcomes of various parameters on system's performance is compared. Subsequently, the parameters that contribute towards the most optimal performance are selected for the video object classification pipeline. Our experiment-based validation reveals an accuracy and precision of 97% and 96% respectively. The system proved to be scalable, robust and customizable for a variety of different applications.
doi:10.1109/tsmc.2018.2840341 fatcat:y6fp7xy6ufen5pae4qjctuc6au