Interdisciplinary landscape of connected health research demands researchers from different areas such as deep learning, machine learning, internet of things (IoT), wearable sensing, distributed computing, embedded systems, big data, and medical devices to collaborate for accurate, efficient and reliable systems for a wide array of health applications. Recent advancements in deep learning and model compression of deep models on wearables have created unique opportunities for connected health. The new opportunities also have associated challenges that need to be addressed to achieve the goal of accuracy, efficiency, privacy, reliability and security.

This workshop aims to bring together the collaboration between research groups in academia and industry. It compasses a wide array of techniques, methods, architectures and solutions in low-resource machine learning, model-compressed deep learning, secure, private and efficient fog computing for practical IoT use cases. The DL-EDGE-IOT workshop invite authors from both academia and industry to submit high quality papers containing original work.

DL-EDGE-IOT workshop includes (but not limited to) the following topics:

* Deep learning and low-resource machine learning for wearable IoT
* Machine learning for IoT signal processing on edge device
* Neural network model compression for wearables
* Information-theoretic signal learning on IoT devices
* Fog, edge and mist computing for DL in connected health
* Edge-based DL for wearable health solutions
* Novel emerging applications of IoT in biomedical signal processing on edge devices
* Fog computing for mobile-based location search; context-aware, information processing
* Scalability, privacy and usability aspects of DL-focused IoT
* Design, development and evaluation of fog architectures for data analysis, visualization and interoperability for connected health
* Big data storage in IoT and Edge Computing for healthcare applications
* Nano-CMOS and Post-CMOS based sensors, circuits, and controller
* Accelerators for IoT Health (e.g., neuromorphic and cognitive computing)
* End-to-End ML-driven privacy preserving and security approaches for IoT Health
* Brain‐inspired and neuromorphic components, circuits, and systems for Connected Health
* Case studies of IoT Health (e.g., Predictive analytics and population health management, risk prediction and patient subtyping, behavioral coaching, social network analysis for IoT Health)


Paper Submission: Prospective authors are invited to submit full-length papers (up to six pages plus 1 page with extra charge) for technical content including figures and references. Submitted manuscripts should be single-spaced double-column pages using 10-point size font on 8.5x11 inch pages (IEEE conference style - download the template). Manuscripts should be original (not submitted/published anywhere else). Papers will be accepted only by electronic submission via the CHASE 2018 conference website. Accepted workshop papers will be included in proceedings to be published by IEEE CPS and indexed by IEEE Explore.


Important Dates:

* Workshop Paper Submission: June 8, 2018
* Workshop Paper Acceptance: July 13, 2018
* Workshop Camera-Ready Paper: July 23, 2018
* Submission link: https://edas.info/newPaper.php?c=24762


Workshop Organizers:

* Kunal Mankodiya, University of Rhode Island, USA
* Harishchandra Dubey, University of Texas at Dallas, USA
* Farshad Firouzi, MSG Systems AG, Germany
* Amir M. Rahmani, University of California Irvine (USA) and TU Wien (Austria)
* Utsav Drolia, NEC Laboratories America Inc., USA