Special Issue of IEEE Network Magazine Extended

IEEE Network Special Issue on "Exploring Deep Learning for Efficient and Reliable Mobile Sensing" has extended to Dec. 10, 2017.

Introduction:

Sensor-equipped smart devices such as smartphones and wearables are enabling a diverse set of mobile applications, ranging from user behavior perception such as gesture recognition and health monitoring to context inference such as driving detection and hazard warning. However, reliably inferring high-value user behavior and context information from noisy and highly heterogeneous sensor data using mobile devices remains an open issue. To combat against constraints of a mobile device, one conventional approach is to upload raw sensor data to the cloud and run complex inference algorithms remotely. This leads to inefficiency in terms of network overhead and large latency for mobile applications. Recently, deep learning techniques have made significant breakthrough in achieving the state-of-art inference performance in a variety of applications such as computer vision and natural language processing. In general, data modeling challenges found in mobile sensing can often be seen in deep-learning-based inference. Promisingly, with the ever-increasing computational capability of today’s smart devices as well as the new edge computing architecture where data processing is performed at the edge of the network, it is possible to apply the latest development in deep learning to mobile sensing from the cloud towards the edge or/and mobile devices. However, a set of new challenges rise, such as computational overhead associated with deep learning, training models requiring large data sets, and mobile devices being short of battery power etc. These challenges need to be carefully investigated in the near future before robust mobile inference can be fulfilled at no efficiency cost.

This feature topic aims at presenting the most relevant scenarios, prominent research outcomes and state-of-the-art advances of deep learning for mobile sensing (DLMS). Only technical papers describing previously unpublished, original, state-of-the-art research, and not currently under review by a conference or a journal will be considered. This SI solicits papers in a variety of topics presenting the current development and addressing the challenges in DLMS.

Submissions:
Submitted papers should not be under consideration elsewhere for publication and the authors must follow the IEEE Network guidelines regarding manuscript content and format for preparation of the manuscripts. For details, please refer to the “Author Guidelines” at the IEEE Network Web site at http://www.comsoc.org/netmag/author-guidelines. Authors must submit their manuscripts via the IEEE Network manuscript submission system at http://mc.manuscriptcentral.com/network-ieee.