Periodic Reporting for period 1 - A-WEAR (A network for dynamic WEarable Applications with pRivacy constraints)
Reporting period: 2019-01-01 to 2020-12-31
As a response to the wearable technology development, the H2020 MSCA EJD/ITN A-WEAR project is aiming at both societal and research goals: to educate 15 Early Stage Researchers (ESRs) as well as to bring new benefits to the general public being among the end-users. The project's main two target groups in wearables applications are: the social applications, such as eHealth and social networking, and the industrial applications, such as automation halls, industrial robotics, and the automotive industry. Such applications are chosen because they have different requirements in terms of computational costs, communications latency, precision, security, and privacy of both communication and localization and related tradeoffs. All of the A-WEAR ESRs have already passed the first-year mark of their three-year research career and formalized their first research results in the field of wearable technology.
To summarize, enabling efficient operation of wearable technology is already being enabled by a series of existing communications and computing technologies, including edge/fog and cloud computing, forth-coming 5G/6G networks, and standardized security solutions. However, nothing has been devoted in existing literature so far to addressing the combination of the technologies mentioned above, considering wearable devices with stringent requirements compared to, e.g. smartphones, and this is where A-WEAR brings its contributions. Namely, in a broader sense, the A-WEAR main objective are:
1. To provide the society with general knowledge of dynamic wearable networks in terms of localization, connectivity, privacy, and security;
2. To identify vulnerabilities and offer innovative solutions in crowdsourced-, cloud-, edge-, and fog-based wearable architectures in the telecommunications area;
3. To design and develop privacy-enhanced and location-aware wearable technologies;
4. To improve the communications between wearable devices, their smartphone gateways and the infrastructure networks;
5. To develop new open-source software for wearables in social/eHealth/industrial applications.
The main topics of research addressed in the research papers include the following directions (the related objectives are shown in brackets, as O1-O5):
• Analysis of applications of wearables to Parkinson’s disease and neurocognitive disorder (eHealth); (O5)
• Utilization of wearables for public safety scenarios; (O1, O5)
• Various applications of wearables for COVID-19 localization and detection; (O3, O5)
• Evaluation of the wearable data impact on future wireless networks; (O1, O2)
• Testing modern information security for the use on wearable devices; (O3, O4)
• Forming various datasets for future use in indoor positioning domain; (O2)
• Analyzed how modern compression methods may impact wearable devices; (O2)
• Looked into the opportunities of wearable devices for crowdsourced data collection; (O2,O4)
• Studied tradeoffs of privacy and location accuracy in opportunistic wearable networks.(O3)
• Studying multicast transmissions in GHz ranges (O4)
• Developing machine learning solutions for wearable computing (O1, O4, O5)
On average, every ESR has so far around 2 published papers, excluding the submitted ones. After just one year, the project is exactly 30% on the way to the promised target of 90 research papers.
• Developed a fractional order model for exoskeleton hand control (O5);
• A novel machine-learning algorithms for posture identification of Obstructive Sleep Apnea patients (O5);
• A robust technique to detect COVID-19 using chest X-ray images (O5);
• A decision support algorithm based on the concentrations of air pollutants visualization (O5);
• An algorithm for optimal placement of social Digital Twins in edge IoT networks (O2);
• An improvement for indoor positioning algorithms based on Wi-Fi radio maps (O3);
• Developed a testbed for the use of HTC Vive as a ground-truth system for anchor-based indoor localization (O3);
• A deep learning-based localization and handover optimization for 5G NR networks (O4);
• A model for the analysis of system-level dynamics of direct extended reality sessions over mmWave links (O1).
Besides, the project has already collected four datasets and provided access to three open software code related to information security on wearables.
In terms of societal impact, the A-WEAR Twitter channel currently has 461 followers (as of 22.2.2021). YouTube A-WEAR channel currently has 123 subscribers and 25 videos. Facebook, ResearchGate, and LinkedIn activities fit the corresponding venues. A-WEAR currently has 7 press releases (in English, Czech, Romanian, Italian, and Spanish). The A-WEAR project representatives organized 4 outreach events in schools and other universities, including one A-WEAR Open Days, one lecture for MSc and BSc students, and one lecture in high school. Finally, the ESRs prepared a joint survey paper on wearable technology, which is currently submitted to Computer Networks journal. Moreover, the supervisors were involved in organizing 4 special sessions at conferences and 5 special issues in journals on the project topic. Additionally, 3 lectures for general audience and one public survey were executed.