Self Intelligence with Human Activities Recognition Based in CNN

  • R. Angeline, V. Tharun, D. Maheswar Reddy, A. U. Mani Vinay


Deep Learning is a subset collection of Machine Learning concerned where neural network algorithms inspired by human brain (what occurs spontaneously to human) learn from large amount of data through several layers for nonlinear transformation. The deep learning can process large number of features to increase the outcome accuracy. Real world applications on Deep Learning are Face Recognition, Hand Writing Recognition, Speech Recognition, Translate from one human language to another human language, Control Robots like self driving cars. The existing system is based on sensors and devices collect time collection indicators which can be generated in each time and frequency area. To gather the  quickening  data,  each  subject  carries a smart device for a few hours and plays several activities. In the projected application,  five kinds of common activities will be implemented, including walking, hobbling, exercising, walking upstairs, and walking downstairs. Human Activity Recognition has increased a great deal in research field particularly context-aware computing and multimedia - for the most part on the record of it's ubiquity in human-life and furthermore on our consistently expanding computational capacity. It is as a rule effectively sought after for a wide range of uses like keen homes, human conduct analysis, sports and even security frameworks.The proposed application Human Activity Recognition is based on Deep Learning which is used to identify and verify the human activities from the images. Deep Learning Algorithms leverage large datasets of elderly human activities and learn from rich set of features and train the models and eventually outperform the human activities. The proposed application included Feature Detection, Feature Alignment, Feature Extraction, Feature Detection.

How to Cite
R. Angeline, V. Tharun, D. Maheswar Reddy, A. U. Mani Vinay. (2020). Self Intelligence with Human Activities Recognition Based in CNN. International Journal of Advanced Science and Technology, 29(3), 12433 - 12439. Retrieved from