Wireless Sensing With Long Range Comminication (LoRa)
With the novel Internet-of-Things (IoT) connectivity standards such as LoRaWAN and NB-IoT, smart devices can be connected through a network that ensures seamless communication over the internet. These standards are low power and enable a modest coverage distance of more than 20km. This technology trends are transforming how we life and work in the near future. While most of sensor applications are typically build with a sensor and IoT communication interface to cover simple applications, advanced use cases preferably require computing power on the edge. Power efficient edge computation is challenging to be achieved in practice since low power microprocessors are weak in terms of computation power. High computation microprocessor are power hungry though. For these reasons, multi-core processors are providing new essential possibilities to enable advanced applications.
In this project,the student(s) will desing a how hardware/software low power embedded systesm, to connect a several sensor including a camera with a RISC-V based microprocessor to enable edge computation in the sensor for people counting. RISC-V has the advantage that it is open-source and avoids license fees. In this thesis, typical image processing or neural network algorithms needs to be evaluated to gather the key information from the taken pictures. While the image can be deleted after calculating the key information, the key information can be transferred using LoRaWAN to the cloud. Since most sensors are limited by the power consumption of the transceiver, LoRaWAN is the way to go for low bandwidth applications, assuming that only the calculated key information is transferred and not the image. The sensor is meant to run battery supplied and make clever use of the edge computation power. A battery lifetime of around 3-5 years should be targeted with the corresponding prototype. The desinged node will also include energy harvesting to allow a self-sustainig system.
The project will be done in collaboration with the company Miromico (http://www.miromico.ch/) based in Zurich.
Depending on the applicant's profile and project type, his tasks may involve some of the following:
- lab. testing/characterization of RF localization modules and embedded systems: verification of the prototype's characteristics w.r. design specification (simulations), measuring power-consumption, and assessing detection performance in lab. conditions
- High-level software programming, signal processing, machine learning, wireless communication
- programming the circuit for a specific application, field testing, data acquisition
- Machine Learning for microcontrollers.
- PCB design to build a working prototype which includes all the subsystems
-  Aoudia, F. A., Gautier, M., Magno, M., Le Gentil, M., Berder, O., & Benini, L. (2018). Long-short range communication network leveraging LoRa™ and wake-up receiver. Microprocessors and Microsystems, 56, 184-192.
Figure Source: ref 
- Looking for Semester and Master Project Students
- Supervisors: Michele Magno;
(not all need to be met by the single candidate)
- Experience using the laboratory instrumentation - signal generators, oscilloscopes, DAQ cards, Matlab etc..
- knowledge of microcontroller programming and PC programming (C/C++, preferably microcontroller with Bluetooth Low Energy but it is not mandatory)
- basic knowledge or interests on signal processing, wireless communication for localization and machine learning is a plus
- plus is also knowledge on printed circuit board (PCB) using Altium.
- 35% Theory
- 45% Implementation
- 20% Testing