Submission Deadline: 30 January 2018
IEEE Access invites manuscript submissions in the area of Multimedia Analysis for Internet-of-Things.
Statistics reveal that the Internet traffic is shifting from non-multimedia data to multimedia data. This prevalent dominance signifies the importance and increase of multimedia usage in our day-to-day activities. Seamless integration, cooperative sensing, connectivity, and autonomy in the Internet-of-Multimedia-Things (IoMT) infrastructure opens doors to numerous opportunities to improve services and applications through efficient utilization of big multimedia data. However, the heterogeneous nature of big multimedia data demands scalable and customized recommendation frameworks for efficient analysis of big data collected in scenarios like surveillance, retail, telemedicine, traffic monitoring, and disaster management. Recommender systems are the technical response to the fact that we frequently rely on peoples’ experience, cultural norms and regional traditions when confronted with a new field of expertise, where we do not have a broad knowledge of all facts, or where such knowledge would exceed the amount of information humans can cognitively deal with. This observation in the real world suggests that recommender systems are an intuitive and valuable extension, allowing both end-users and multimedia service providers to take a much more active role in selecting semantically relevant content and providing valuable suggestions. For instance, in smart cities, multimedia sensors allow administrators to actively monitor assets and activities. Improvements in automatic interpretation of multimedia big data can enhance capacity of smart city administrators by autonomously reacting to emergency situations, and recommending effective actions, thereby reducing response times significantly. Furthermore, novel solutions for multimedia data processing and management in the IoMT ecosystem can enhance quality of life, urban environment, and smart city administration.
Big data processing includes both data management and data analytics. Data management step requires efficient cleaning, knowledge extraction, and integration and aggregation methods. Whereas, IoMT’s analysis is based on knowledge modelling, and interpretation which is more and more often performed by exploiting deep learning architectures. In couple of years, merging conventional and deep learning methodologies, have exhibited great promise in ingesting multimedia big data, exploring the paradigm of transfer learning, association rule mining, predictive analytics etc. Starting from the above considerations, this Special Section in IEEE Access aims to bring together researchers coming from both academia and industry, asking them to contribute in refining technologies and services aimed at personalization, monitoring, and recommendation in multimedia applications in the IoMT ecosystem based on deep architectures and conventional analysis methodologies, exploring their pros and cons in collaborative decision makings.
The topics of interest include, but are not limited to:
We also highly recommend the submission of multimedia with each article as it significantly increases the visibility, downloads, and citations of articles.
Associate Editor: Zhihan Lv, University College London, UK
Relevant IEEE Access Special Sections:
IEEE Access Editor-in-Chief: Michael Pecht, Professor and Director, CALCE, University of Maryland
Paper submission: Contact Associate Editor and submit manuscript to: