Veni Vidi Dixi

• DOI: 10.1145/3359989.3365418
• Publication Date: 2019-12-05T14:07:37Z
• Authors: Serkut Ayvaşık; H. Murat Gürsu; Wolfgang Kellerer
• Keywords: Computer Science - Networking and Internet Architecture; Networking and Internet Architecture (cs.NI); FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Information Theory; Information Theory (cs.IT); Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Machine Learning (cs.LG)

The upcoming industrial revolution requires deployment of critical wireless sensor networks for automation and monitoring purposes. However, the reliability communication is rendered unpredictable by mobile elements in environment such as humans or robots which lead to dynamically changing radio environments. Changes channel can be monitored with frequent pilot transmission. that would stress battery life sensors. In this work a new estimation technique, Veni Vidi Dixi, VVD, proposed. VVD leverages redundant information depth images obtained from surveillance cameras utilizes Convolutional Neural Networks CNNs map complex estimations. increases without need transmission no additional complexity on receiver. proposed method tested conducting measurements an indoor single human. Up authors best knowledge our first obtain only any collected trace, codes are publicly available.