Pharmacovigilance, also referred to as drug safety, is an important science for identifying risks related to medicine intake. Side effects of medicine can be caused by for example interactions, high dosage and misuse. In order to find patterns in what causes the unwanted effects, information needs to be gathered and mapped to predefined terms. This mapping is today done manually by experts which can be a very difficult and time consuming task. In this thesis the aim is to automate the process of mapping side effects by using machine learning techniques. The model was developed using information from preexisting mappings of verbatim expressions of side effects. The final model that was constructed made use of the pre-trained language model BERT, which has received state-of-the-art results within the NLP field. When evaluating on the test set the final model performed an accuracy of 80.21%. It was found that some verbatims were very difficult for our model to classify mainly because of ambiguity or lack of information contained in the verbatim. As it is very important for the mappings to be done correctly, a threshold was introduced which left for manual mapping the verbatims that were most difficult to classify. This process could however still be improved as suggested terms were generated from the model, which could be used as support for the specialist responsible for the manual mapping.

This study investigates whether code-switching practices among Sesotho-English bilinguals promote convergence between Sesotho and English. First, the study identifies different types and patterns of code-switching between Sesotho and English and analyses them using Myers-Scotton’s (1993) Matrix Language Frame model and Myers-Scotton and Jake’s (2000) 4-M model. Second, it applies the ML turnover in order to detect convergence in Sesotho-English code-switching data and to observe which direction it takes. The study also explores other factors contributing to change in the structure of Sesotho, which are not necessarily influenced by convergence. In conducting this study, data was collected through interviews that were held with younger bilingual speakers from different tertiary institutions in and around Maseru (Lesotho) and through recorded youth-centred phone-in radio programmes. Findings from the analysis of data reveal simple to complex Sesotho-English code-switching performance of various types and strategies. Findings also show through the existence of composite language in Sesotho-English code-switching that there is a turnover in the ML, which indicates a development of an asymmetrical convergence between Sesotho and English. It was also discovered that, although other changes in the Sesotho structure are not English influenced, they are enhanced mostly by younger urban bilingual speakers’ frequent “looser” approach to Sesotho. This is an indication that Sesotho’s susceptibility to change correlates strongly with age; that is, both the length of time contact between Sesotho and English has existed, and the generation in which change is mostly found. This thesis adds and documents a different perspective to the previously recorded changes on Sesotho-English contact in Lesotho.

Background: The usage of AI is becoming increasingly necessary in almost every industry, including marketing and branding. AI can help managers, marketers and designers in the marketing and branding sectors to overcome realistic and practical challenges by providing data-driven results. These results could be used in making decisions. Nevertheless, implementing AI systems and the acceptance of it varies widely across different industries, with building brands is still behind.  Purpose: This research aims to develop a deeper understanding of why AI systems are not yet commonly used in the branding industry with emphasis on how it could be useful. As a result, the main opportunities and threats to the usage of AI in branding as seen by branding- and IT specialists are explored and expressed.  Method: To achieve the purpose of this study, a qualitative study was conducted. Semi-structured interviews were used as means to collect primary data and in total 15 interviews with branding and IT specialists were carried out. The data was transcribed and analyzed according to thematic analysis which emerged in four main themes.  Conclusion: The results show that AI is capable of creating brand elements, with limitations to mostly non-visual brand elements due to the lack of creativity and emotions in AI solutions. The findings indicate that the perceived possibilities of implementing AI in branding mostly are cost- and time-related since AI tends to be capable of solving tasks which are cost- and time-consuming. Furthermore, the perceived threats mainly involve i) losing a job or ii) intrude on the roles of branding professionals.

In computer games, one use case for artificial intelligence is used to create interesting problems for the player. To do this new techniques such as reinforcement learning allows game developers to create artificial intelligence agents with human-like or superhuman abilities. The Unity ML-agents toolkit is a plugin that provides game developers with access to reinforcement algorithms without expertise in machine learning. In this paper, we compare reinforcement learning methods and provide empirical training data from two different environments. First, we describe the chosen reinforcement methods and then explain the design of both training environments. We compared the benefits in both dense and sparse rewards environments. The reinforcement learning methods were evaluated by comparing the training speed and cumulative rewards of the agents. The goal was to evaluate how much the combination of extrinsic and intrinsic rewards accelerated the training process in the sparse rewards environment. We hope this study helps game developers utilize reinforcement learning more effectively, saving time during the training process by choosing the most fitting training method for their video game environment. The results show that when training reinforcement agents in sparse rewards environments the agents trained faster with the combination of extrinsic and intrinsic rewards. And when training an agent in a sparse reward environment with only extrinsic rewards the agent failed to learn to complete the task.

Maskininlärning har blivit allt vanligare inom näringslivet. Informationsinsamling med Data mining (DM) har expanderats och DM-utövare använder en mängd tumregler för att effektivisera tillvägagångssättet genom att undvika en anständig tid att ställa in hyperparametrarna för en given ML-algoritm för nå bästa träffsäkerhet. Förslaget i denna rapport är att införa ett tillvägagångssätt som systematiskt optimerar ML-algoritmerna med hjälp av genetiska algoritmer (GA), utvärderar om och hur modellen ska konstrueras för att hitta globala lösningar för en specifik datamängd. Genom att implementera genetiska algoritmer på två utvalda ML-algoritmer, K-nearest neighbors och Random forest, med två numeriska datamängder, Iris-datauppsättning och Wisconsin-bröstcancerdatamängd. Modellen utvärderas med träffsäkerhet och beräkningstid som sedan jämförs med sökmetoden exhaustive search. Resultatet har visat att GA fungerar bra för att hitta bra träffsäkerhetspoäng på en rimlig tid. Det finns vissa begränsningar eftersom parameterns betydelse varierar för olika ML-algoritmer. / As machine learning (ML) is being more and more frequent in the business world, information gathering through Data mining (DM) is on the rise, and DM-practitioners are generally using several thumb rules to avoid having to spend a decent amount of time to tune the hyperparameters (parameters that control the learning process) of an ML algorithm to gain a high accuracy score. The proposal in this report is to conduct an approach that systematically optimizes the ML algorithms using genetic algorithms (GA) and to evaluate if and how the model should be constructed to find global solutions for a specific data set. By implementing a GA approach on two ML-algorithms, K-nearest neighbors, and Random Forest, on two numerical data sets, Iris data set and Wisconsin breast cancer data set, the model is evaluated by its accuracy scores as well as the computational time which then is compared towards a search method, specifically exhaustive search. The results have shown that it is assumed that GA works well in finding great accuracy scores in a reasonable amount of time. There are some limitations as the parameter’s significance towards an ML algorithm may vary.

This thesis investigates the use of Maximum Likelihood Sequence Estimation (MLSE) in the presence of unknown channel parameters. MLSE is a fundamental problem that is closely related to many modern research areas like Space-Time Coding, Overloaded Array Processing and Multi-User Detection. Per-Survivor Processing (PSP) is a technique for approximating MLSE for unknown channels by embedding channel estimation into the structure of the Viterbi Algorithm (VA). In the case of successful acquisition, the convergence rate of PSP is comparable to that of the pilot-aided RLS algorithm. However, the performance of PSP degrades when certain sequences are transmitted. In this thesis, the blind acquisition characteristics of PSP are discussed. The problematic sequences for any joint ML data and channel estimator are discussed from an analytic perspective. Based on the theory of indistinguishable sequences, modifications to conventional PSP are suggested that improve its acquisition performance significantly. The effect of tree search and list-based algorithms on PSP is also discussed. Proposed improvement techniques are compared for different channels. For higher order channels, complexity issues dominate the choice of algorithms, so PSP with state reduction techniques is considered. Typical misacquisition conditions, transients, and initialization issues are reported. / Master of Science

Machine learning has been widely used in computer games for a long time. This is something that has been proven to create a better experience and well-balanced challenges for players. In 2017, the game engine Unity released the ML-agents toolkit that provides several machine learning algorithms together with examples and a user-friendly development environment for free to the public. This has made it simpler for developers to explore what is possible in the world of machine learning in games. In many cases, a developer has spent a lot of time on a specific place in a game and would like a player to visit that area. The location can also be important for the gameplay, but the developer wants to steer the player there without the player feeling forced. This thesis investigates if it is possible to create a smart agent in a modern game engine like Unity that can affect the route taken by a player through a level. The results show that this is fully possible with a high success rate for a simple environment, but that it requires much time and effort to make it work on an advanced environment with several agents. Experiments with a randomized environment to create an agent that is general and can be used in many situations were also done, but a successful agent could not be produced in this way within the timeframe of the work.

Anxiety is becoming more and more common, seeking help to evaluate your anxiety canfirst of all take a long time, secondly, many of the tests are self-report assessments that could cause incorrect results. It has been shown there are several voice characteristics that are affected in people with anxiety. Knowing this, we got the idea that an algorithm can be developed to classify the amount of anxiety based on a person's voice. Our goal is that the developed algorithm can be used in collaboration with today's evaluation methods to increase the validity of anxiety evaluation. The algorithm would, in our opinion, give a more objective result than self-report assessments. In this thesis we answer questions such as “Is it possible toclassify anxiety based on a speech recording?”, as well as if deep learning algorithms perform better than machine learning algorithms on such a task. To answer the research questions we compiled a data set containing samples of people speaking with a varying degree of anxiety applied to their voice. We then implemented two algorithms able to classify the samples from our data set. One of the algorithms was a machine learning algorithm (ANN) with manual feature extraction, and the other one was a deep learning model (CNN) with automatic feature extraction. The performance of the two models were compared, and it was concluded that ANN was the better algorithm. When evaluating the models a 5-fold cross validation was used with a data split of 80/20. Every fold contains 100 epochs meaning we train both the models for a total of 500 epochs. For every fold the accuracy, precision, and recall is calculated. From these metrics we have then calculated other metrics such as sensitivity and specificity to compare the models. The ANN model performed a lot better than the CNN model on every single metric that was measured: accuracy, sensitivity, precision, f1-score, recall andspecificity.

Indiana University-Purdue University Indianapolis (IUPUI) / Since its codified genesis in the 18th century, ballet training has largely been unchanged: it relies on tools that lack adequate support for both dancers and teachers. In particular, providing effective augmented feedback remains challenging as it can be limited, not always provided at the proper time, and highly subjective as it depends on the visual experience of an instructor. Designing a ballet assessment and learning tool with the aim of achieving a meaningful educational experience is an interdisciplinary challenge due to the fine motor movements and patterns of the art form. My work examines how we can effectively augment ballet learning in three phases using mixedmethod approaches. First, through my past professional experience as a ballet dancer, I explore how the design and in-lab evaluation of augmented visual and verbal feedback can improve the technical performance for novices and experts via remote learning. Second, I investigate the learning and teaching challenges that currently exist in traditional in-person training environments for dancers and teachers. Furthermore, I study the current technology use, reasons for non-use, and derive design requirements for future use. Lastly, I focus on how we can design aiDance, an AI-based feedback tool that attempts to represent an affordable and non-invasive approach that augments teachers’ abilities to facilitate assessment in the 21st century and pirouette towards the enhancement of learning. With this empirical work, I present insights that inform the HCI community at the intersection of dance and design in addressing the first steps towards the standardization of motor learning feedback. / 2023-12-28

Since mid to late 2010 image synthesizing using neural networks has become a trending research topic. And the framework mostly used for solving these tasks is the Generative adversarial network (GAN). GAN works by using two networks, a generator and a discriminator that trains and competes alongside each other. In today’s research regarding image synthesis, it is mostly about generating or altering images in any way which could be used in many fields, for example creating virtual environments. The topic is however still in quite an early stage of its development and there are fields where image synthesizing using Generative adversarial networks fails. In this work, we will answer one thesis question regarding the limitations and discuss for example the limitation causing GAN networks to get stuck during training. In addition to some limitations with existing GAN models, the research also lacks more experimental GAN variants. It exists today a lot of different variants, where GAN has been further developed and modified. But when it comes to GAN models where the discriminator has been changed to a different network, the number of existing works reduces drastically. In this work, we will experiment and compare an existing deep convolutional generative adversarial network (DCGAN), which is a GAN variant, with one that we have modified using a deep neuro-fuzzy system. We have created the first DCGAN model that uses a deep neuro-fuzzy system as a discriminator. When comparing these models, we concluded that the performance differences are not big. But we strongly believe that with some further improvements our model can outperform the DCGAN model. This work will therefore contribute to the research with the result and knowledge of a possible improvement to DCGAN models which in the future might cause similar research to be conducted on other GANmodels.