Opis: Efficient encoding of data is an important part of projects in
the Internet of Things space. Communication packets must be kept
as small as possible in order to minimize the power consumption of
In this thesis, an automatic code generation tool, irpack, is proposed
that will unify the way packets are defined across all future
projects at Institute IRNAS.
Using a schema, this tool generates source code of encoders and
decoders in target programming languages. A schema evolution system
is also defined, by which changes to packets can be compatible
across multiple versions.
The tool is then applied to a selection of past projects to gauge
its usefulness. It is determined that irpack is able to encode the same
data into a similar or smaller size packet, while also providing
additional versioning information.Ključne besede: encoding/decoding, schema, schema evolution, bit packing, code generationObjavljeno v DKUM: 31.01.2022; Ogledov: 165; Prenosov: 37 Celotno besedilo (2,58 MB)
Opis: Human-Elephant Conflicts are a major problem in terms of elephant conservation.
According to WILDLABS, an average of 400 people and 100 elephants are killed every year in India alone because of them.
Early warning systems replace the role of human watchers and warn local communities of nearby, potentially life threatening, elephants, thus minimising the Human-Elephant Conflicts.
In this Master's thesis we present the structure of an early warning system, which consists of several low-power embedded systems equipped with thermal cameras and a single gateway.
To detect elephants from captured thermal images we used Machine Learning methods, specifically Convolutional Neural Networks.
The main focus of this thesis was the design, implementation and evaluation of Machine Learning models running on microcontrollers under low-power conditions.
We designed and trained several accurate image classification models, optimised them for on-device deployment and compared them against models trained with commercial software in terms of accuracy, inference speed and size.
While writing firmware, we ported a part of the TensorFlow library and created our own build system, suitable for the libopencm3 platform.
We also implemented reporting of inference results over the LoRaWAN network and described a possible server-size solution.
We finally a constructed fully functional embedded system from various development and evaluation boards, and evaluated its performance in terms of power consumption.
We show that embedded systems with Machine Learning capabilities are a viable solution to many real life problems.Ključne besede: machine learning, microcontroller, on-device inference, thermal camera, low-power systemObjavljeno v DKUM: 06.01.2021; Ogledov: 442; Prenosov: 88 Celotno besedilo (13,35 MB)