Embedded Electronics Laboratory focuses in its research on Internet of Things (IoT), new Parallel Architectures and Autonomous Embedded Electronics not to forget Engineering Education Research. In addition, the Embedded Electronics laboratory educates experts for design and engineering of contemporary and future systems in the context of IoT and Cyber Physical Systems (CPS).
The key application domain for the research is personal health, safety and well-being. These application domains are and will be important for society in Finland, Europe and world-wide. The focus is on application development and implementation tools for multiprocessor platforms developed within the laboratory and wireless sensor networks. Sensors for the network are developed in international cooperation with Royal Institute of Technology (KTH) (Stockholm, Sweden) and Fudan University (Shanghai, PRC). In addition to international collaboration, the Embedded Electronic laboratory cooperates with multiple disciplines within University of Turku to achieve real multidisciplinary research and education environment.
As described above, the research area is diverse and multidisciplinary, and therefore the laboratory personnel are a diverse and international group of researchers. The more fine grain research interests are gathered under the following themes.
Internet of Things / Cyber Physical Systems
One of the main objectives within Internet of Things research theme is to establish a methodology to construct heterogeneous embedded systems containing a mix of general purpose processors, application specific processors, special purpose computing engines and sensors. This includes the development of the actual embedded computing platform that controls the personal IoT framework. The ultimate goal is to establish a proactive health monitoring network. The current research area is pain management that is carried out in cooperation with nursing science.
Parallel Architectures (NoC)
Compact integrated computational and storage modules: System design problematics caused by integration of systems into a 3-dimensional structure with several integrated circuit chips, including both processor and memory array structures in a single stacked package. To create such a platform, we will have to find manageable and efficient mappings of the complex algorithms onto the distributed hardware architecture. The platform takes advantage of a dynamically configurable connectivity thereby achieving better qualitative performance while simultaneously maintaining high computational efficiency. Challenges are communication, distributed processing, dynamic control, and new class of processor-memory architectures which need to be addressed.
The majority of the activities have intertwined to the Network-on-Chip (NoC) paradigm in which computation is divided into two distinct elements, processing and communication. The knowledge gained from this research is generalised to the serve larger context as described above. In conclusion, the research areas covered by our laboratory are system modelling and verification, design methodologies, embedded programming, multiprocessor architectures and platforms, fault tolerance methods, reconfigurable computing, and implementation technologies including both ASIC and FPGA based approaches.
The used working environments range from high level, UML based developments to hardware description languages such as VHDL, with support from Modelsim and Matlab frameworks. The preferred employed technology is FPGA. In the projects associated with the lab we also develop tools to assist the execution of design methodologies at all the levels of the process, and integrate them with third party providers.
Autonomous Embedded Electronics
Dependability and reliability management: Different methods must be developed to ensure the continuous operation of the system, thus guaranteeing that a localized fault will not compromise the whole system. This must be done in different ways, such as controlling power and temperature distribution to avoid hot spots, run-time monitoring of task execution and communication correctness, dynamic task recovery, rescheduling and remapping.
Controllability is the third element of computation currently explored through hierarchical and distributed agent hardware and software architectures in order to ensure dependable operation of systems, even in the case of faulty subcomponents or large variability of their parameters.
Managing complexity: It is essential to enable designers to manage the complexity of massively parallel 3-D behaviour and structure, to reason about system reliability, and to produce precise mathematical documentation of system properties. Therefore, a novel framework for the specification and verification of systems based on 3-D platforms is needed. This can be achieved by extending and integrating existing formal methods of concurrent system design as well as exploiting non-formal state of the art design methodologies such as simulation at different abstraction levels.
- Energy efficient wearable sensor node for IoT-based fall detection systems
Tuan Nguyen Gia, Victor Kathan Sarker, Igor Tcarenko, Amir M. Rahmani, Tomi Westerlund, Pasi Liljeberg, Hannu Tenhunen
- Exploiting smart e-Health gateways at the edge of healthcare Internet-of-Things: A fog computing approach
Rahmani A., Gia T., Negash B., Anzanpour A., Azimi I., Jiang M., Liljeberg P.
- Autonomous Patient/Home Health Monitoring Powered by Energy Harvesting (2017)
Mai Ali, Tuan Nguyen Gia, Abd-Elhamid Taha, Amir M. Rahmani, Tomi Westerlund, Pasi Liljeberg, Hannu Tenhunen
- Leveraging fog computing for healthcare IoT (2017)
Negash B., Gia T., Anzanpour A., Azimi I., Jiang M., Westerlund T., Rahmani A., Liljeberg P., Tenhunen H.
- Energy-efficient IoT-enabled fall detection system with messenger-based notification (2017)
Tcarenko I., Gia T., Rahmani A., Westerlund T., Liljeberg P., Tenhunen H.
- Low-latency hardware architecture for cipher-based message authentication code (2017)
Ben Dhaou I., Gia T., Liljeberg P., Tenhunen H.
- IoT-based continuous glucose monitoring system: A feasibility study (2017)
Gia TN, Ali M, Ben Dhaou I, Rahmani AM, Westerlund T, Liljeberg P, Tenhunen H
- HiCH: Hierarchical Fog-Assisted Computing Architecture for Healthcare IoT (2017)
Azimi I, Anzanpour A, Rahmani AM, Pahikkala T, Levorato M, Liljeberg P, Dutt N
- Performance/Reliability-Aware Resource Management for Many-Cores in Dark Silicon Era (2017)
Haghbayan M, Miele A, Rahmani A, Liljeberg P, Tenhunen H
- Energy-Efficient and Reliable Computing in Dark Silicon Era (2017)