| | SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Iskanje po katalogu digitalne knjižnice Pomoč

Iskalni niz: išči po
išči po
išči po
išči po
* po starem in bolonjskem študiju


1 - 5 / 5
Na začetekNa prejšnjo stran1Na naslednjo stranNa konec
Deep Learning on Low Power Embedded Devices Using RISC-V Cores with an Extended Instruction Set
Jure Vreča, 2020, magistrsko delo

Opis: This thesis explores the possibility of running neural networks on microcontrollers and how to optimize their performance using instruction set extensions. Microcontrollers are seen as too weak to run neural networks. We challenge this view and show that stripped-down neural networks can run and be useful for some applications. We used an open-source microcontroller called PULPino to run our neural network. The benefit of various instructions and optimizations for minimizing energy consumption to run deep learning algorithms was evaluated. Hardware loops, loop unrolling, and the dot-product unit were implemented and tested. We developed an FPGA-based testing system to evaluate our hardware. We also developed a deep learning library and a test neural network for our hardware. We wrote two versions of the deep learning library. One version is the reference code, and the other is the optimized code that uses the dot product unit. Using the testing system, we tested the performance of the two versions. The synthesis was run to determine the power and energy consumption. We also tried out various optimizations to see if the performance could be improved. Using instruction set extensions and algorithmic optimizations we reduced the clock cycle count by 72% for the convolutional layers and by 78% for fully-connected layers. This reduced power consumption by 73%. We compare our results with related research.
Ključne besede: deep learning, embedded system, instruction set, RISC-V
Objavljeno: 03.11.2020; Ogledov: 416; Prenosov: 82
.pdf Celotno besedilo (2,69 MB)

Design of an Embedded Position Sensor with Sub-mm Accuracy
Matej Nogić, 2019, magistrsko delo

Opis: This master’s thesis presents the development of a machine-vision based localization unit developed at Robert Bosch GmbH, Corporate Sector Research and Advance Engineering in Renningen, Germany. The localization unit was developed primarily for position detection purposes with three degrees of freedom in highly versatile manufacturing systems but has an immense potential to be used anywhere where a precise, low-cost localization method on a two-dimensional surface is required. The complete product development cycle was carried out, from the components selection, schematic and optical system design, to the development of machine vision algorithms, four-layer Printed Circuit Board design and evaluation using an industrial robot. Thanks to the use of a patented two-dimensional code pattern, the localization unit can cover a surface area of 49 km2. The size and speed optimized, self-developed machine-vision algorithms running on a Cortex-M7 microcontroller allow achieving an accuracy of 100 µm and 60 Hz refresh rate.
Ključne besede: localization, machine-vision, code pattern, image sensor, embedded system
Objavljeno: 14.01.2020; Ogledov: 336; Prenosov: 0

Development of RFID/NFC based access control system
Darko Topić, 2018, magistrsko delo

Opis: The master thesis describes the development of NFC/RFID access control system based on the ARM platform. The access control system is widely used in different applications. The goal of this thesis is to develop a smart NFC access control system used for accessing an elevator, where users could use only NFC tags to access a specific floor. The design of the proposed NFC access control system is based on the ARM platform, while the developed NFC antenna guarantees wide scanning range. At the end of the thesis the results are presented.
Ključne besede: access control system, RFID, NFC, MIFARE, ARM processor, embedded system, short-range communication, contactless communication, ISO/IEC 14443
Objavljeno: 23.05.2018; Ogledov: 2415; Prenosov: 363
.pdf Celotno besedilo (7,51 MB)

The Internet of Things Communication Protocol for Devices with Low Memory Footprint
Sašo Vinkovič, Milan Ojsteršek, izvirni znanstveni članek

Opis: This paper describes a new communication protocol named XMC which is designed for the transmission of messages between an embedded device and a remote system. A new markup language called XMDD has also been developed and is used to describe the functional profile of the embedded device. The main advantage of the XMC communication protocol is its flexibility and independence from the device type. It is suitable for communication with devices that have a curtailed amount of working memory (a few kB) and limited computing power, i.e. 8-bit or 16-bit microcontrollers. Messaging between the embedded device and the remote systems is done without any interference with the basic source code of the embedded device, thus allowing access to all functionalities and features of the connectable embedded device and is based on the functionality dictionary and built-in features of an embedded device. It also maintains a low production price for the embedded device and from the programming point of view provides a transparent and flexible upgrade of the hardware and software without any redundancy input.
Ključne besede: communication protocol, internet of things, home automation, functional profile, smart appliance, code generation, embedded system, framework
Objavljeno: 21.12.2014; Ogledov: 1607; Prenosov: 88
URL Povezava na datoteko

Iskanje izvedeno v 0.14 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici