Thesis Title: Multi-modal IoT Sensing using Edge Computing and Machine Learning
Description of the Unit
The Networked Embedded Systems (NES) group at RISE SICS is a part of the Computer Systems Laboratory. The current research focus is on the Internet of Things. Among the group's key technologies are the Contiki operating system, uIP stack, ContikiRPL, SICSLoWPAN, and lightweight implementation of IPsec and DTLS. The NES group conduct projects together with industry and academic partners from Sweden and across the world.
Modern Internet of Things sensing devices come with a plethora of different sensors and actuators. Making sense out of the sensed values is often a non-trivial task and hence often impossible on resource-constrained sensing devices. The edge, on the other hand, has enough computing resources to execute modern machine learning tasks such as object or activity recognition and classification.
The task of this thesis is to implement a framework for combining edge computing with multi-model and possibly large-scale IoT sensing. The work includes the implementation of one or more applications that are enabled by the combination of IoT sensing and edge computing on a compute capable gateway such as Nvidia Jetson Nano or Google Coral. The evaluation will investigate different resource allocation strategies.
We expect the student to have good programming skills in Python and (embedded) C. Basic knowledge or a strong interest in machine learning and in particular deep learning is also a prerequisite.
Applications should include a brief personal letter, CV, and recent grades. Candidates are encouraged to send in their application as soon as possible. Suitable applicants will be interviewed as applications are received.
Start TimeAs soon as possible
LocationRISE SICS Kista, Stockholm
Joakim Eriksson firstname.lastname@example.org
Thiemo Voigt email@example.com