Dear Colleagues, *** Apologies for Cross-Postings *** MobiSys is a premier venue for researchers working in the area of mobile and wireless systems, middleware, services, and applications. Workshop papers will be included with the MobiSys proceedings and published in the ACM Digital Library.
The following workshops will take place in conjunction with this year's MobiSys conference: • 5th International Workshop on Embedded and Mobile Deep Learning -- https://emdl21.github.io/index.html • Internet of Lights -- https://enlightem.eu/results/workshops/iol-workshop/ • MobileServerless ‘21 -- https://www.it.uc3m.es/mbsvless21/ • 1st Workshop on Zero Interaction Pairing and Authentication -- http://zipa.cs.luc.edu/mbsvless21/ • HealthDL: Deep Learning for Wellbeing Applications Leveraging Mobile Devices and Edge Computing -- https://cis.temple.edu/~yanwang/healthdl2021/ • BodySys 2021 (previously called WearSys): Workshop on Body-Centric Computing Systems -- http://bodysys-acm.com/ • DroNet 2021 - Workshop on Micro Aerial Vehicle Networks, Systems, and Applications -- http://wsslab.org/dronet21/ • Security and Privacy for Mobile AI (MAISP) -- http://maisp.gitlab.io/ • Future of Digital Biomarkers (DigiBiom) -- https://digi-biomarkers.github.io/ More information and the CFP of each workshop is available below: ##################################################################### EMDL: 5th International Workshop on Embedded and Mobile Deep Learning https://emdl21.github.io ##################################################################### In recent years, breakthroughs from the field of deep learning have transformed how sensor data (e.g., images, audio, and even accelerometers and GPS) can be interpreted to extract the high-level information needed by bleeding-edge sensor-driven systems like smartphone apps and wearable devices. Today, the state-of-the-art in computational models that, for example, recognize a face, track user emotions, or monitor physical activities are increasingly based on deep learning principles and algorithms. Unfortunately, deep models typically exert severe demands on local device resources and this conventionally limits their adoption within mobile and embedded platforms. As a result, in far too many cases existing systems process sensor data with machine learning methods that have been superseded by deep learning years ago. Because the robustness and quality of sensory perception and reasoning are so critical to mobile computing, it is critical for this community to begin the careful study of two core technical questions. First, how should deep learning principles and algorithms be applied to sensor inference problems that are central to this class of computing? This includes a combination of applications of learning some of which are familiar to other domains (such as the processing image and audio), in addition to those more uniquely tied to wearable and mobile systems (e.g., activity recognition). Second, what is required for current -- and future -- deep learning innovations to be either simplified or efficiently integrated into a variety of mobile resource-constrained systems? At heart, this MobiSys 2021 co-located workshop aims to consider these two broad themes. This year we place special focus on the emerging areas of i) resource allocation and scheduling for applying Federated Learning over embedded and mobile devices and ii) Edge-centric Learning that leverages the radical progress in Mobile Edge Computing (MEC) technologies. As such, we particularly encourage submissions on these two topics. More specific topics of interest, include, but are not limited to: • Resource-efficient Federated and Edge-centric Learning • Compression of Deep Model Architectures • Neural-based Approaches for Modeling User Activities and Behavior • Quantized and Low-precision Neural Networks (including Binary Networks) • Resource-efficient Federated Learning • Mobile Vision/AR/VR supported by Convolutional and Deep Networks • Audio Analysis and Understanding through Recurrent and Deep Architectures • Optimizing Commodity Processors (GPUs, DSPs, NPUs, etc.) for Deep Models • Hardware Accelerators for Deep Neural Networks • Distributed Deep Model Training Approaches • Applications of Deep Neural Networks with Real-time Requirements • Deep Models of Speech and Dialog Interaction or Mobile Devices • Partitioned Networks for Improved Cloud and Edge Offloading • OS Support for Resource Management at Inference Time FULL PAPER SUBMISSIONS Solicited submissions include both full technical workshop papers and white position papers. The maximum length of such submissions is 6 pages including references, and if accepted they will be published by ACM and appear in the ACM Digital Library. • Submission Deadline: April 9th, 2021 – 11:59 pm AOE • Author Notification: May 10th, 2021 – 11:59 pm AOE WORK-IN-PROGRESS AND DEMO SUBMISSIONS Abstracts describing work-in-progress and demonstrations are also welcome and warmly encouraged. Submissions are limited to 2 pages, and if accepted, included in the program as a short oral presentation – but will only be published on the workshop website (not the ACM DL). Deadlines for this informal track remain open even past the early registration deadline of MobiSys 2021; author notifications will be rolling (i.e., max. of 4 days after submission) to enable early authors to take advantage of available discounts. Workshop Organizers PC Chairs • Ahmed M. Abdelmoniem (KAUST, Saudi Arabia) • Shaohuai Shi (HKUST, Hong Kong) • Stylianos I. Venieris (Samsung AI Center, Cambridge) • Shiqiang Wang (IBM Research, USA) Steering Committee • Nicholas D. Lane (Univ. of Cambridge & Samsung AI, UK) • Christos Bouganis (Imperial College London, UK) • Ilias Leontiadis (Samsung AI, Cambridge, UK) • Brahim Bensaou (HKUST, Hong Kong) ##################################################################### "Internet of Lights" https://enlightem.eu/results/workshops/iol-workshop/ ##################################################################### LEDs have become ubiquitous owing to their superior energy efficiency. Their potential for Visible Light Communication remains largely untapped, but the emergence of Li-Fi and its convergence with the Internet of Things can effectively change that, allowing the world’s virtually unlimited supply of LEDs to be harnessed for data communication as well as illumination. The intersection of the Internet of Things and Li-Fi technology holds great promise and poses formidable challenges, for instance with respect to energy-efficient operation. The objective of this workshop is to provide a forum for researchers and practitioners to share early-stage ideas and results on how to leverage the huge potential of Li-Fi and the underlying Visible Light Communication technology in the Internet of Things. Papers describing prototype implementations and deployment of such applications and systems are particularly welcome. The submission of informative surveys of the state of the art as well as position papers on controversial issues is also encouraged. The topics of interest include, but are not limited to: • Energy efficiency in LiFi • Spectrum efficiency in LiFi • Low-power VLC systems • Simultaneous Data and Power Transfer • Passive Communication and Sensing • Resource-constrained VLC • Resilient LiFi for IoT applications • LiFi systems for home automation • LiFi systems for smart buildings • Interplay of LiFi and smart lighting • Indoor Positioning Systems based on LiFi/VLC • Integration of VLC/LiFi and mm-Wave technologies • Power-efficient underwater optical communications • Applications of LiFi to smart energy systems • Applications of LiFi to smart vehicles and smart transportation • Applications of LiFi to smart manufacturing Program Chairs: • Daniele Puccinelli, University of Applied Sciences of Southern Switzerland • Frank Lochmann, Tridonic GmbH & Co KG, Austria Keynote speaker: Prof. Harald Haas: Director of the LiFi Research and Development Centre (University of Strathclyde, UK) Authors of accepted papers are expected to present their work at the workshop. Key Dates: • Papers submission deadline: May 7, 2021 • Camera ready deadline: TBD in June, 2021 • Workshop date: TBD in July, 2021 For more details, please visit the workshop homepage: https://enlightem.eu/results/workshops/iol-workshop/ and/or contact the Program Chair Daniele Puccinelli (daniele.puccine...@supsi.ch) ##################################################################### Mobile Serverless Workshop https://www.it.uc3m.es/mbsvless21/ ##################################################################### Spurred by a growing need for programmability and flexibility, serverless computing is rapidly gaining the attention of mobile network stakeholders. The introduction of serverless architectures, also known as Function as a Service (FaaS), enables programmers to decompose network operations into atomic building blocks. This new paradigm represents the natural evolution of current cloud-native architectures, and a first glimpse into an actual fluid resource control that breaks current quantization and reaches ultimate flexibility. The advantages are evident and include: no service management, boosted resource multiplexing, liquid scalability, and high customization. The challenges to realizing a complete serverless approach in mobile networks are however important: software needs to be re-developed for this purpose, the scalability of routing traffic interconnecting functions must be explored, and resource orchestration becomes daunting. MobileServerless will facilitate discussions and novel contributions on the emerging topic of serverless networking for future mobile communications. MobileServerless welcomes both theoretical and more applied contributions, tools and methodologies, works-in-progress, demos and experience papers. Specific topics of interest include but are not limited to: • Application of cloud-native and serverless concept to network function design • Performance evaluation of cloud-native network deployment • Simulation and theoretical evaluation of highly modular network functions • New software architectures for network function design • Management and orchestration solutions for cloud-native network functions • Technical enablers for scalable packet forwarding in a cloud-native environment • Security and privacy in serverless environments Important Dates: • Submission due: May 7th, 2021 • Notification of acceptance: June 4th, 2021 • Camera ready due: June 11th, 2021 • Workshop date: TBD (Mid July 2021) ##################################################################### 1st Workshop on Zero Interaction Pairing and Authentication http://zipa.cs.luc.edu/ ##################################################################### Zero-interaction pairing (ZIP), zero interaction authentication (ZIA) and continuous authentication are emerging techniques that enable users and devices to form self-organizing networks and mutually verify their identities without the use of passwords. Two devices that want to authenticate with one another both measure environmental noise signals and, using ZIP, can convert their measurements to authentication keys. In a scenario where both devices have already established a shared key, they can use ZIA to mutually verify their proximity to one another, for example as a second authentication factor. Network formation with ZIA and ZIP offers the advantage of being both secure and transparent to the user in the sense that no user involvement is required to configure a network. ZIA and ZIP have tremendous potential as an alternative to passwords, particularly in unattended systems like those in the Internet of Things. But ZIA and ZIP also represent a relatively new form of authentication, and we lack a comprehensive understanding of many of their practical and theoretical properties. This workshop aims to serve as a forum for researchers who are interested in ZIA to discuss unsolved problems and formulate new research directions with the goal of making ZIA a practical, secure, and user-friendly form of authentication. Submissions should be no more than 6 U.S. letter pages in PDF format, including all references, figures, and tables. Topics of interest include: • Information-theoretic fundamentals and limitations of ZIA • New key reconciliation techniques • New key generation techniques • Applications of ZIA • Real-world deployment experiences with ZIA systems • Methods of sampling or extracting environmental noise signals • Methods for distinguishing legitimate users from imposters on ZIA networks • Techniques for compromising security of ZIA authentication systems • Microcontroller-friendly techniques for evaluating key quality in real time ##################################################################### HealthDL: Deep Learning for Wellbeing Applications Leveraging Mobile Devices and Edge Computing https://cis.temple.edu/~yanwang/healthdl2021/ ##################################################################### The availability of affordable wearable Internet of Things (wIoT) and edge devices with embedded sensors has revolutionized intelligent health and wellness applications. Users often use wIoT and smartphones to collect medical data and send them to the cloud for further analysis. Edge-based solutions, where analysis and inference of such data are carried out on edge devices, have been proposed to address users' security and privacy concerns since users' sensitive data is not transferred to untrusted cloud servers for inferencing. However, resource constraints on the edge devices also pose challenges in using deep learning solutions. Research needs to be conducted to produce efficient system designs, algorithms, and deep learning models that can be deployed in edge devices. Such outcomes will enable better personalization of health-related solutions and enhance users' experience. Furthermore, thanks to the ever-improving voice recognition and synthesis schemes, many wearables and smartphone applications now rely on voice assistants to interact with users. Existing work has shown that such interactions can significantly improve users' experience but incur significant security and privacy issues. This workshop aims to fill the gap between deep learning for intelligent healthcare and power-constrained wIoT and edge and create impactful solutions to help in the well beings of users. This workshop invites researchers from academia and industry to submit their current research for fostering academic-industry collaboration. The scope of this workshop includes but not limited to the following topics: • E2E deep learning for smart health applications. • Deep learning for sensing, analysis and interpretation of wIoT healthcare data. • Resource constrained deep learning schemes for smartphones and wIoT • Edge-based Deep learning & AI models (e.g. sensor-based, visual-based or NLP-based) for mental health or other illnesses • Transfer learning and model compression for smart health applications • Context-aware ubiquitous healthcare systems based on wearables, edge machine learning • Emerging applications or sensors for personalized health and fitness Submission Specifications The papers are limited to 6 pages including references. The formatting should adhere to the formatting requirements of ACM Mobisys submissions. The papers should be submitted to the workshop submission site. Any questions regarding submission issues should be directed to y.w...@temple.edu. ##################################################################### BodySys 2021 (previously called WearSys): Workshop on Body-Centric Computing Systems http://bodysys-acm.com/ ##################################################################### BodySys workshop focuses on advances and discussions on how body-centric (human/animals) computing technologies can shape mobile computing, systems, and applications research. The goal of the workshop is to provide a forum to bring together researchers and de-sign experts to discuss how wearable, body-centric, and user-in-the-loop technologies have, and can, complement mobile systems research, and vice-versa. It also aims to provide a launchpad for bold and visionary ideas for systems research in this space. We solicit papers of six or fewer pages that present preliminary research in areas of body-centric computing, including efforts on prototyping a system, experiences in designing a novel technology, or survey of useful tools for designing inter-disciplinary systems and applications. We also encourage position papers that propose new directions for research or advocate disruptive design ideas and project applications. We also encourage sub-missions that can help bootstrap exploration of the body-centric computing space by the broader mobile systems community. Important Dates: • Submission deadline: May 1, 2021 (11.59pm EDT) • Notification of acceptance: May 19, 2021 • Camera-ready workshop papers: May 31, 2021 • Workshop date: June 24, 2021 or July 2, 2021 (to be finalised soon) ##################################################################### DroNet 2021 - Workshop on Micro Aerial Vehicle Networks, Systems, and Applications http://wsslab.org/dronet21/ ##################################################################### Robot vehicle platforms, often called “drones”, offer exciting new opportunities for mobile computing. Autonomous cooperative systems, made of intelligent devices (such as drones), may deploy and optimize the network to improve its coverage, build routes and fix network partition to ensure the best communication performance, reduce energy consumption, and dynamically respond to detected network problems. Innovative solutions are built upon these drone networking primitives to accomplish cost-effective and wide-ranging mission-critical applications, including search and rescue, surveillance, 3D-mapping, farmland and construction monitoring, delivery of light-weight objects and products, and video production. DroNet welcomes contributions dealing with all facets of drones as mobile computing platforms, including system aspects, theoretical studies, algorithm and protocol design, as well as requirements, constraints, dependability, and regulations. We are particularly looking for papers reporting on experimental results of deployed systems, summaries of challenges or advancements, measurements, and innovative applications. We welcome in particular also contributions from interdisciplinary teams to present robotic work or applications focusing on the communication networks enabling the efficient control and context-awareness of teams of unmanned autonomous vehicles/systems with an emphasis on civilian and aerial applications, while related work on unmanned systems working underwater, in space or on the ground is also invited. Topics of interest include, but are not limited to: • Novel applications of drones • Drone system design and deployment • Drone ad-hoc networks • Micro flying systems • Aerial communication protocol design • Drone operating systems • Programming systems • MAC and routing protocols for drone fleets • Theoretical analysis and models for drone networks • Solutions for sparse and dense fleets of drones • Spectrum and regulatory issues • Mission and context-aware solutions • Drone coordination • Mobility-aware and 3D communication • Delay-tolerant networks and ferrying • Energy-efficient operation and harvesting • Integration of drones with backend systems • Drone-based sensor networks • Positioning and passive/active localization • Swarm movement, coordination, and behavior • Autonomous flight • Artificial intelligence techniques for drones • Vision and object tracking • Human drone interaction • Cooperative surveillance, smart cameras and sensors • Acceptance, security, and privacy aspects • Experimental results of aerial communication • Results from prototypes and demonstrations • Drone testbeds • Identification and Authentication of Drones • Applications with non-conventional drones including underwater or ground drones DroNet invites submission of original work not previously published or under review at another conference or journal. Accepted papers will be published by ACM and considered for the Best Paper Award and/or a Best Presentation Award. Best Paper Award: All papers will be considered for the Best Paper Award. The program committee will select a number of candidates for the award among accepted papers, and select one or more award papers prior to the conference. Important Dates: • Paper Submission: April 25, 2021 (AoE) • Camera Ready Deadline: June 4, 2021 (AoE) • Workshop date: TBD Technical Program Chairs: • Jun Han (National University of Singapore) • VP Nguyen (UT Arlington, USA) ##################################################################### Security and Privacy for Mobile AI (MAISP) http://maisp.gitlab.io/ ##################################################################### The S&P for Mobile AI workshop aims to bring together researchers in the areas of security and privacy with respect to mobile systems, networking, and AI, to discuss challenging topics, share new ideas, and exchange experiences across these areas, from both theoretical and experimental perspectives. In particular, we are interested in contributions that discuss what type of security and privacy problems (e.g., attacks, leaks, etc.) the mobile AI will raise in the near future, and what kind of algorithmic or practical solutions and adaptations must be employed at the application, operating system or network level to solve these challenges. We invite submissions of original, previously unpublished papers addressing key challenges in the intersection of the following (tentative) list of topics: • Secure / privacy-preserving distributed learning (P2P, FL, etc.) • Secure / privacy-preserving network functions at the edge • Security / privacy issues in FL systems (e.g., mobile / edge systems) • Security / privacy issues in FL scheduling algorithms • Security / privacy issues in on-device training, algorithms, analytics • Security / privacy issues in Biometrics/Fingerprinting in mobile systems • Security / privacy issues in mobile medical and health (MHealth) systems • Security / privacy issues in (Covid) mobile contact tracing technologies • Security / privacy issues in voice agents and local interactions • Trusted / attestable mobile / edge systems • Detection of automated / bot mobile users (e.g., mobile farms) We invite submissions which can be either full technical workshop papers, or position papers. Maximum length of such submissions is 6 pages (including references) in 2-column 10pt ACM format. All the submissions should be double-blind and will be peer-reviewed. For anonymity purposes, you must remove any author names and other uniquely identifying features in your submitted paper (e.g., references to your past work, links to data/code, etc). All submissions must be uploaded to the workshop submission site available here: https://maisp21.hotcrp.com. Any questions regarding submission issues should be directed to nicolas.kourtel...@telefonica.com. • Workshop Submission Deadline: May 7th, 2021 • Acceptance Notifications: May 28th, 2021 • Camera Ready Deadline: TBD in June, 2021 • Workshop Date: TBD in July, 2021 ##################################################################### Future of Digital Biomarkers (DigiBiom) https://digi-biomarkers.github.io/ ##################################################################### The Workshop on the Future of Digital Biomarkers will offer a unified forum that brings academics, industry researchers and medical practitioners together to explore the role of existing and future mobile technology for modeling, testing, and validating new digital biomarkers. The workshop aims to facilitate a systematic discussion among experts from different knowledge domains including mobile sensing, systems, machine learning, medicine, and health sciences. The workshop aims to (i) identify new digital biomarkers for capturing different physiological and behavioral health conditions and diseases, (ii) identify the key shortcomings of the existing research in terms of scalability, customizability, and sensing affordances, (iii) find realistic solutions by leveraging sensor data from a variety of mobile systems (e.g., smartphones, wearables, and IoT devices), (iv) identify key methodologies for validation and testing of the new biomarker evidence engine. Topics of interest (NOT an exhaustive list) • Predicting the incidence of disease, health conditions, effects of treatments, and interventions with digital biomarkers. • Design and implementation of mobile phone, wearable and/or novel embedded systems based computational platforms. • Integration of multimodal data from different sensor streams for digital biomarker modeling. • Using existing IoT infrastructure for new digital biomarker modeling. • Improved data collection, labeling, testing and validation methodologies for digital biomarker modeling. • Novel signal processing or machine learning techniques for digital biomarker modeling. • Developing robust biomarker models that can handle data sparsity and mis-labeling issues. • Energy and resource efficient implementation of biomarker models. • Designing and implementing data feedback and visualization for both participants and caregivers. • Development of smartphone based automated health interventions with digital biomarkers Important Dates: • Submission deadline: May 15, 2021 at 11:59 PM (EST) • Notification deadline: June 1, 2021 • Camera-ready workshop papers due: June 15, 2021 • Workshop Dates: July 24-25, 2021 _______________________________________________ uai mailing list uai@engr.orst.edu https://it.engineering.oregonstate.edu/mailman/listinfo/uai
