This thesis deals with design and implementation of laboratory microcontroller system, based on ARM architecture. Purpose of this thesis is to teach programming. This system allows the user to work with the internal and external peripherals of the microcontroller, which are equipped with the system. This thesis includes creating a concept its peripheral solution and realization itself. A suitable development environment is determined for the system and the thesis includes sample solutions for the proposed tasks.

Work done at Luleå Technical University regarding the RTIC RTOS framework is expanded upon to yield a convenient toolset for event-based instrumentation by exploiting debug peripherals available on the ARMv7-M platform. By parsing the source of an RTIC application and recovering instrumentation metadata from user-supplied information, the target-emitted trace stream is decoded and mapped to RTIC task events, yielding a timeline of events that can be analyzed live and postmortem by help of a recording host-side daemon. Relevant sections of the ARMv7-M standard are covered, and peripheral configuration covered in detail. An instrumentation result of a trivial RTIC application is presented and graphically plotted to exemplify the value of the toolset, and topics of future work to improve the toolset are outlined.

The goal of this thesis is to firstly design and implement an application for embeddedsystems which will classify MNIST numbers and secondly optimize energy and memoryrequirements of this network. The basics of neural networks, Cortex-M processor cores andembedded devices are described in the theoretical part. Followed by implementation details.Networks learning is done with Python and Theano library on a PC. The network is thenconverted to C for a board STM32F429 Discovery. Last part consist of network optimization,which focuses on convolution, dot product and number representation of weights and biasesof the network.

The aim of the work is the design and implementation of two circuit boards delivering learning platforms, which will consist of two separate circuit boards with ARM MCU and a programmable FPGA gate array that will be interconnectable and appropriately complemented by peripherals. These platforms will be developed by analysing current teaching and development platform solutions and then demonstrating on practical examples. The main benefit of this work should be update and simplification of existing equipment. At the same time, there is an emphasis on greater transparency of the whole solution, so that it is not too complicated for an aspiring student to familiarise himself with modern micro-controllers and programmable gate arrays and can link the simpler units into more complex ones, where the individual boards can be used as separate working units and their interconnection will provide a computationaly stronger yet more complex device.

With an increased amount of connected devices and the recent surge of artificial intelligence, the two technologies need more attention to fully bloom as a useful tool for creating new and exciting products. As machine learning traditionally is implemented on computers and online servers this thesis explores the possibility to extend machine learning to an embedded environment. This evaluation of existing machine learning in embedded systems with limited processing capa-bilities has been carried out in the specific context of an application involving classification of basic human movements. Previous research and implementations indicate that it is possible with some limitations, this thesis aims to answer which hardware limitation is affecting clas-sification and what classification accuracy the system can reach on an embedded device. The tests included human motion data from an existing dataset and included four different machine learning algorithms on three devices. Support Vector Machine (SVM) are found to be performing best com-pared to CART, Random Forest and AdaBoost. It reached a classification accuracy of 84,69% between six different included motions with a clas-sification time of 16,88 ms per classification on a Cortex M4 processor. This is the same classification accuracy as the one obtained on the host computer with more computational capabilities. Other hardware and machine learning algorithm combinations had a slight decrease in clas-sification accuracy and an increase in classification time. Conclusions could be drawn that memory on the embedded device affect which al-gorithms could be run and the complexity of data that can be extracted in form of features. Processing speed is mostly affecting classification time. Additionally the performance of the machine learning system is connected to the type of data that is to be observed, which means that the performance of different setups differ depending on the use case. / Antalet uppkopplade enheter ökar och det senaste uppsvinget av ar-tificiell intelligens driver forskningen framåt till att kombinera de två teknologierna för att både förbättra existerande produkter och utveckla nya. Maskininlärning är traditionellt sett implementerat på kraftfulla system så därför undersöker den här masteruppsatsen potentialen i att utvidga maskininlärning till att köras på inbyggda system. Den här undersökningen av existerande maskinlärningsalgoritmer, implemen-terade på begränsad hårdvara, har utförts med fokus på att klassificera grundläggande mänskliga rörelser. Tidigare forskning och implemen-tation visar på att det ska vara möjligt med vissa begränsningar. Den här uppsatsen vill svara på vilken hårvarubegränsning som påverkar klassificering mest samt vilken klassificeringsgrad systemet kan nå på den begränsande hårdvaran. Testerna inkluderade mänsklig rörelsedata från ett existerande dataset och inkluderade fyra olika maskininlärningsalgoritmer på tre olika system. SVM presterade bäst i jämförelse med CART, Random Forest och AdaBoost. Den nådde en klassifikationsgrad på 84,69% på de sex inkluderade rörelsetyperna med en klassifikationstid på 16,88 ms per klassificering på en Cortex M processor. Detta är samma klassifikations-grad som en vanlig persondator når med betydligt mer beräknings-resurserresurser. Andra hårdvaru- och algoritm-kombinationer visar en liten minskning i klassificeringsgrad och ökning i klassificeringstid. Slutsatser kan dras att minnet på det inbyggda systemet påverkar vilka algoritmer som kunde köras samt komplexiteten i datan som kunde extraheras i form av attribut (features). Processeringshastighet påverkar mest klassificeringstid. Slutligen är prestandan för maskininlärningsy-stemet bunden till typen av data som ska klassificeras, vilket betyder att olika uppsättningar av algoritmer och hårdvara påverkar prestandan olika beroende på användningsområde.