This thesis summarizes our project in building and setting up a Beowulf cluster. The idea of the project was brought forward by the company CGI in Karlstad, Sweden. CGI’s wish is that the project will serve as a starting point for future research and development of a larger Beowulf cluster. The future work can be made by both employees at CGI and student exam projects from universities. The projects main purpose was to construct a cluster by using several credit card sized single board computers, in our case the Raspberry Pi 3. The process of installing, compiling and con- figuring software for the cluster is explained. The MPICH and TensorFlow software platforms are reviewed. A performance evaluation of the cluster with TensorFlow is given. A single Raspberry Pi 3 can perform neural network training at a rate of seven times slower than an Intel system (i5-5250U at 2.7 GHz and 8 GB RAM at 1600 MHz). The performance degraded significantly when the entire cluster was training. The precise cause of the performance degradation was not found, but is ruled out to be in software, either a programming error or a bug in TensorFlow.

This master´s degree project is carried out by Trafikverket and concerns machine learning and image detection of defective pantographs on trains.   Today, Trafikverket has a system for detecting damages of the coal rail located on the pantograph. This coal rail lies against the contact wire and may become worn in such a way that damages are formed in the coal rail, which results in a risk of demolition of the contact wire which causes major interference and high costs. Today, approximately 10 demolitions of contact wire occur annually due to missed detection. Today's system is called KIKA2, developed during the year 2011 and incorporates a 12 MP digital camera, a target radar and detection of a damaged pantographs is done using various famous imaging techniques. The shortcomings of today's system are that the proportion of false alarms is high and on these occasions, a person must manually review the pictures.   The purpose of this degree project is to propose improvements and explore the possibilities of working with TensorFlow machine learning.  I have used different image processing techniques on the KIKA2 images for optimizing the images for TensorFlow machine learning. I realized after some TensorFlow classification tests on the raw images that preprocessing the images is necessary to obtain realistic values for the classification part. My plan was to clean the pictures from noise, in other words crop the coal rail and improve the contrast to make the damages in the coal rail more visible.  I have used Fourier analyze and correlation techniques to crop the coal rail and the k-means classification algorithm to improve the contrast of the images. The Googles TensorFlow is an open source framework and to use pre-processed RGB images from today's system KIKA2 will give reasonable classification values. I have brought some IR images with an external heating camera (FLIR-E60) of the pantograph. I can see that the thermal camera provides very nice contours on the pantograph, which is very good for machine learning.  My recommendation is that for further studies is to further evaluate the IR technique and use IR-images taken from different angles, distances and with different backgrounds. The segmentation of the images can be done with either Hu´s moment or Fourier analysis with correlation and refined with for example classification techniques. IR images could be used to complement today's systems, or machine learning together with today's RGB images. A robust and proven pre-treatment technique is very important for obtaining good results in machine learning and requires further studies and real life tests to handle different types of pantographs, different light conditions and other differences in the images.

Edge computing is the idea of moving computations away from the cloud andinstead perform them at the edge of the network. The benefits of edge computing arereduced latency, increased integrity, and less strain on networks. Edge AI is the practiceof deploying machine learning algorithms to perform computations on the edge.In this project, a pre-trained model YAMNet is retrained and used to perform audioclassification in real-time to detect gunshots, glass shattering, and speech. The modelis deployed onto the edge device both as a full TensorFlow model and as TensorFlowLite models. Comparing results of accuracy, inference time, and memory allocationfor full TensorFlow and TensorFlow Lite models with and without optimization. Resultsfrom this research were that it was a valid option to use both TensorFlow andTensorFlow Lite but there was a lot of performance to gain by using TensorFlow Litewith little downside.

In recent years, the tech is moving towards a more automized and smarter software. To achieve smarter software the implementation of AI is a step towards that goal. The forest industry needs to become more automized and decrease the manual labor. Decreasing manual labor will both have a positive impact on both the cost and the environment. After doing a literature study the conclusion was to use Mask R-CNN to be able to make the AI learn about the pattern of the different stands. The different stands were extracted and masked for the Mask R-CNN. First there was a comparison between the usage of a computer versus Google Colab, and the results show that Google Colab did deliver the results a little faster than on the computer. Using a smaller area with fewer stands gave a better result and decreased the risk of the algorithm crashing. Using 42 areas with about 10 stands in each gave better results than using one big area with 3248 stands. Using 42 areas gave the result of an average IoU of 42%. Comparing this to 6 areas with about 10 stands each gave the result of 28% IoU. The result of increasing the data split to 70/30 did gave the best IoU with the value of 47%.

The thesis deals with methods for analysis of financial markets, focused on cryptocurrencies. The theoretical part, in a context of virtual currencies, describes block-chain technology, financial indicators and neural networks with recurrent architectures. Main goal is to create a system for giving a recommendation either for buy, or sell the currency. The system consists of designed financial strategy and predicted value of the currency, for which is used financial indicators and LSTM neural network. Tests were performed on Bitcoin, Litecoin and Ethereum historical data from year 2017.

This master thesis is dealing with application of an artificial neural network for calculating specific volume of steam. There is described type and construction of the needed neural network. The main outcome of this work is an executable programme, which calculates specific volume of steam for given pressure and temperature, using neural nets.

This master's thesis deals with the classification of the retinal blood vessels in retinal image data. The thesis contains a description of anatomy of the human eye with focus on the blood circulation, and imaging and diagnostic methods of the retina are briefly mentioned further. The thesis also summarizes methods of the blood circulation classification with emphasis on the deep learning. The practical section was implemented in Python programming language and describes the pre-processing of the data with determination of AV ratio. Based on a literature search, the U-net architecture was chosen for the classification of the retinal blood vessels. The architecture was modified using the open-source Keras library and tested on images from the experimental video-ophthalmoscope. The modified architecture was initially used for classification of vessels into the corresponding classes and because of unsatisfying results was modified another architecture segmenting retinal vessels, arteries or veins and a proposition of a method of the blood vessels classification.

The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ). NAS techniques are currently being researched more and more, as they speed up and simplify the lengthy and complicated process of designing artificial neural networks. These techniques are also able to search for unconventional architectures that would not be found by classic methods. The work also contains the design and implementation of software capable of automated development of convolutional neural networks using the open-source library TensorFlow. The program uses a multiobjective NSGA-II algorithm for designing accurate and compact CNNs.

Cílem této práce je vylepšit implementaci modulu pro mobilní aplikace pro výuku výslovnosti, najít místa vhodná pro optimalizaci a provést optimalizaci s cílem zvýšit přesnost, snížit čas zpracování a snížit paměťovou náročnost zpracování.

In this thesis, a proof of concept of a digital twin of a type of reheating furnace, the walking beam furnace, is presented. It is created by using a machine learning concept called a neural network. The digital twin is trained using real data from a walking beam furnace located in Swerim AB, Luleå, and is taught to predict the temperature in the furnace using air, fuel and pressure as inputs. The machine learning technique used is an artifical neural network in the form of a multilayer perceptron model. The resulting model consists of 3 layers, input, hidden and output layer. The hyperparameters is decided by using grid search cross validation. The hyperparameters chosen to use in this thesis was amount of epochs, optimizer, learning rate, batch size, activation function, regularizer and amount of neurons in the hidden layer. The final settings for these can be found in table. The digital twin is then evaluated comparing predicted temperatures and actual temperatures from the measured data. The end result shows that the twin performs reasonably well. The predictions differs from measured temperature with a percentage around 0.5% to 1.5%.