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.

The Internet of Things (IoT) is comprised of numerous devices that are connected through wired or wireless networks, including sensors and actuators. The number of IoT applications has recently increased dramatically, including Smart Homes, Internet of Vehicles (IoV), Internet of Medical Things (IoMT), Smart Cities, and Wearables. IoT Analytics has reported that the number of connected devices is expected to grow 18% to 14.4 billion in 2022 and will be 27 billion by 2025. Security is a critical issue in today's IoT, due to the nature of the architecture, the types of devices, the different methods of communication (mainly wireless), and the volume of data being transmitted over the network. Furthermore, security will become even more important as the number of devices connected to the IoT increases. However, devices can protect themselves and detect threats with the Intrusion Detection System (IDS). IDS typically use one of two approaches: anomaly-based or signature-based. In this thesis, we define the problems and the particular requirements of securing the IoT environments, and we have proposed a Deep Learning (DL) anomaly-based model with optimal features selection to detect the different potential attacks in IoT environments. We then compare the performance results with other works that have been used for similar tasks. We also employ the idea of reinforcement learning to combine the two different IDS approaches (i.e., anomaly-based and signature-based) to enable the model to detect known and unknown IoT attacks and classify the recognized attacked into five classes: Denial of Service (DDoS), Probe, User-to-Root (U2R), Remote-to-Local (R2L), and Normal traffic. We have also shown the effectiveness of two trending machine-learning techniques, Federated and Transfer learning (FL/TL), over using the traditional centralized Machine and Deep Learning (ML/DL) algorithms. Our proposed models improve the model's performance, increase the learning speed, reduce the amount of data that needs to be trained, and reserve user data privacy when compared with the traditional learning approaches. The proposed models are implemented using the three benchmark datasets generated by the Canadian Institute for Cybersecurity (CIC), NSL-KDD, CICIDS2017, and the CSE-CIC-IDS2018. The performance results were evaluated in different metrics, including Accuracy, Detection Rate (DR), False Alarm Rate (FAR), Sensitivity, Specificity, F-measure, and training and fine-tuning times.

Background: A problematic area in today’s large scale distributed systems is the exponential amount of growing log data. Finding anomalies by observing and monitoring this data with manual human inspection methods becomes progressively more challenging, complex and time consuming. This is vital for making these systems available around-the-clock. Aim: The main objective of this study is to determine which are the most suitable Machine Learning (ML) algorithms and if they can live up to needs and requirements regarding optimization and efficiency in the log data monitoring area. Including what specific steps of the overall problem can be improved by using these algorithms for anomaly detection and classification on different real provided data logs. Approach: Initial pre-study is conducted, logs are collected and then preprocessed with log parsing tool Drain and regular expressions. The approach consisted of a combination of K-Means + XGBoost and respectively Principal Component Analysis (PCA) + K-Means + XGBoost. These was trained, tested and with different metrics individually evaluated against two datasets, one being a Server data log and on a HTTP Access log. Results: The results showed that both approaches performed very well on both datasets. Able to with high accuracy, precision and low calculation time classify, detect and make predictions on log data events. It was further shown that when applied without dimensionality reduction, PCA, results of the prediction model is slightly better, by a few percent. As for the prediction time, there was marginally small to no difference for when comparing the prediction time with and without PCA. Conclusions: Overall there are very small differences when comparing the results for with and without PCA. But in essence, it is better to do not use PCA and instead apply the original data on the ML models. The models performance is generally very dependent on the data being applied, it the initial preprocessing steps, size and it is structure, especially affecting the calculation time the most.

Identification of novel cancer driver mutations is crucial for targeted cancer therapy, yet a difficult task especially for low frequency drivers. To identify cancer driver mutations, we developed a machine learning (ML) model to predict cancer hotspots. Here, we applied the ML program to 32 non-receptor tyrosine kinases (NRTKs) and identified 36 potential cancer driver mutations, with high probability mutations in 10 genes, including ABL1, ABL2, JAK1, JAK3, and ACK1. ACK1 is a member of the poorly understood ACK family of NRTKs that also includes TNK1. Although ACK1 is an established oncogene and high-interest therapeutic target, the exact mechanism of ACK1 regulation is largely unknown and there is still no ACK1 inhibitor in clinical use. The ACK kinase family has a unique domain arrangement with most notably, a predicted ubiquitin association (UBA) domain at its C-terminus. While the presence of a functional UBA domain on a kinase is unique to the ACK family, but the role of the UBA domain on ACK1 is unknown. Interestingly, the ML program identified the ACK1 Mig6 homology region (MHR) and UBA domains truncating mutation p633fs* as a cancer driver mutation. Our data suggest that the ACK1 UBA domain helps activate full-length ACK1 through induced proximity. It also acts as a mechanism of negative feedback by tethering ACK1 to ubiquitinated cargo that is ultimately degraded. Indeed, our preliminary data suggest that truncation of the ACK1 UBA stabilizes ACK1 protein levels, which results in spontaneous ACK1 oligomerization and activation. Furthermore, our data suggests removal of the MHR domain hyper activates ACK1. Thus, our data provide a model to explain how human mutations in ACK1 convert the kinase into an oncogenic driver. In conclusion, our data reveal a mechanism of ACK1 activation and potential strategies to target the kinase in cancer.

This thesis presents a deep learning tool able to identify ice in radar images fromthe sea-ice environment of the Twhaites glacier outlet. The project is motivatedby the threatening situation of the Thwaites glacier that has been increasingits mass loss rate during the last decade. This is of concern considering thelarge mass of ice held by the glacier, that in case of melting, could increasethe mean sea level by more than +65 cm [1]. The algorithm generated alongthis work is intended to help in the generation of navigation charts and identificationof icebergs in future stages of the project, outside of the scope of this thesis.The data used for this task are ICEYE’s X-band radar images from the Thwaitessea-ice environment, the target area to be studied. The corresponding groundtruth for each of the samples has been manually generated identifying the iceand icebergs present in each image. Additional data processing includes tiling,to increment the number of samples, and augmentation, done by horizontal andvertical flips of a random number of tiles.The proposed tool performs semantic segmentation on radar images classifyingthe class "Ice". It is developed by a deep learning Convolutional Neural Network(CNN) model, trained with prepared ICEYE’s radar images. The model reachesvalues of F1 metric higher than 89% in the images of the target area (Thwaitessea-ice environment) and is able to generalize to different regions of Antarctica,reaching values of F1 = 80 %. A potential alternative version of the algorithm isproposed and discussed. This alternative score F1 values higher than F1 > 95 %for images of the target environment and F1 = 87 % for the image of the differentregion. However, it must not be confirmed as the final algorithm due to the needfor further verification.

Spielt Ihr Gehirn Ihre letzten Lebenserfahrungen ab, während Sie sich ausruhen? Eine offene Frage in den Neurowissenschaften ist, welche Ereignisse unser Gehirn wiederholt und gibt es eine Korrelation zwischen der Wiederholung und der Dauer des Ereignisses? In dieser Studie habe ich versucht, dieser Frage nachzugehen, indem ich Magnetenzephalographie-Daten aus einem Experiment zum aktiven Hören verwendet habe. Die Magnetenzephalographie (MEG) ist ein nicht-invasives Neuroimaging-Verfahren, das verwendet wird, um die Gehirnaktivität zu untersuchen und die Gehirndynamik bei Wahrnehmungs- und kognitiven Aufgaben insbesondere in den Bereichen Sprache und Hören zu verstehen. Es zeichnet das in unserem Gehirn erzeugte Magnetfeld auf, um die Gehirnaktivität zu erkennen. Ich baue eine Pipeline für maschinelles Lernen, die einen Teil der Experimentdaten verwendet, um die Klangmuster zu lernen und dann das Vorhandensein von Geräuschen im späteren Teil der Aufnahmen vorhersagt, in denen die Teilnehmer untätig sitzen mussten und kein Ton zugeführt wurde. Das Ziel der Untersuchung der Testwiedergabe von gelernten Klangsequenzen in der Nachhörphase. Ich habe ein Klassifikationsschema verwendet, um Muster zu identifizieren, wenn MEG auf verschiedene Tonsequenzen in der Zeit nach der Aufgabe reagiert. Die Studie kam zu dem Schluss, dass die Lautfolgen über dem theoretischen Zufallsniveau identifiziert und unterschieden werden können und bewies damit die Gültigkeit unseres Klassifikators. Darüber hinaus könnte der Klassifikator die Geräuschsequenzen in der Nachhörzeit mit sehr hoher Wahrscheinlichkeit vorhersagen, aber um die Modellergebnisse über die Nachhörzeit zu validieren, sind mehr Beweise erforderlich. / Does your brain replay your recent life experiences while you are resting? An open question in neuroscience is which events does our brain replay and is there any correlation between the replay and duration of the event? In this study I tried to investigate this question by using Magnetoencephalography data from an active listening experiment. Magnetoencephalography (MEG) is a non-invasive neuroimaging technique used to study the brain activity and understand brain dynamics in perception and cognitive tasks particularly in the fields of speech and hearing. It records the magnetic field generated in our brains to detect the brain activity. I build a machine learning pipeline which uses part of the experiment data to learn the sound patterns and then predicts the presence of sound in the later part of the recordings in which the participants were made to sit idle and no sound was fed. The aim of the study of test replay of learned sound sequences in the post listening period. I have used classification scheme to identify patterns if MEG responses to different sound sequences in the post task period. The study concluded that the sound sequences can be identified and distinguished above theoretical chance level and hence proved the validity of our classifier. Further, the classifier could predict the sound sequences in the post-listening period with very high probability but in order to validate the model results on post listening period, more evidence is needed.

In this dissertation, we introduce a novel text representation method mainly used for text classification purpose. The presented representation method is initially based on a variety of closeness relationships between pairs of words in text passages within the entire corpus. This representation is then used as the basis for our multi-level lightweight ontological representation method (TOR-FUSE), in which documents are represented based on their contexts and the goal of the learning task. The method is unlike the traditional representation methods, in which all the documents are represented solely based on the constituent words of the documents, and are totally isolated from the goal that they are represented for. We believe choosing the correct granularity of representation features is an important aspect of text classification. Interpreting data in a more general dimensional space, with fewer dimensions, can convey more discriminative knowledge and decrease the level of learning perplexity. The multi-level model allows data interpretation in a more conceptual space, rather than only containing scattered words occurring in texts. It aims to perform the extraction of the knowledge tailored for the classification task by automatic creation of a lightweight ontological hierarchy of representations. In the last step, we will train a tailored ensemble learner over a stack of representations at different conceptual granularities. The final result is a mapping and a weighting of the targeted concept of the original learning task, over a stack of representations and granular conceptual elements of its different levels (hierarchical mapping instead of linear mapping over a vector). Finally the entire algorithm is applied to a variety of general text classification tasks, and the performance is evaluated in comparison with well-known algorithms.

In this dissertation, we introduce a novel text representation method mainly used for text classification purpose. The presented representation method is initially based on a variety of closeness relationships between pairs of words in text passages within the entire corpus. This representation is then used as the basis for our multi-level lightweight ontological representation method (TOR-FUSE), in which documents are represented based on their contexts and the goal of the learning task. The method is unlike the traditional representation methods, in which all the documents are represented solely based on the constituent words of the documents, and are totally isolated from the goal that they are represented for. We believe choosing the correct granularity of representation features is an important aspect of text classification. Interpreting data in a more general dimensional space, with fewer dimensions, can convey more discriminative knowledge and decrease the level of learning perplexity. The multi-level model allows data interpretation in a more conceptual space, rather than only containing scattered words occurring in texts. It aims to perform the extraction of the knowledge tailored for the classification task by automatic creation of a lightweight ontological hierarchy of representations. In the last step, we will train a tailored ensemble learner over a stack of representations at different conceptual granularities. The final result is a mapping and a weighting of the targeted concept of the original learning task, over a stack of representations and granular conceptual elements of its different levels (hierarchical mapping instead of linear mapping over a vector). Finally the entire algorithm is applied to a variety of general text classification tasks, and the performance is evaluated in comparison with well-known algorithms.

In this dissertation, we introduce a novel text representation method mainly used for text classification purpose. The presented representation method is initially based on a variety of closeness relationships between pairs of words in text passages within the entire corpus. This representation is then used as the basis for our multi-level lightweight ontological representation method (TOR-FUSE), in which documents are represented based on their contexts and the goal of the learning task. The method is unlike the traditional representation methods, in which all the documents are represented solely based on the constituent words of the documents, and are totally isolated from the goal that they are represented for. We believe choosing the correct granularity of representation features is an important aspect of text classification. Interpreting data in a more general dimensional space, with fewer dimensions, can convey more discriminative knowledge and decrease the level of learning perplexity. The multi-level model allows data interpretation in a more conceptual space, rather than only containing scattered words occurring in texts. It aims to perform the extraction of the knowledge tailored for the classification task by automatic creation of a lightweight ontological hierarchy of representations. In the last step, we will train a tailored ensemble learner over a stack of representations at different conceptual granularities. The final result is a mapping and a weighting of the targeted concept of the original learning task, over a stack of representations and granular conceptual elements of its different levels (hierarchical mapping instead of linear mapping over a vector). Finally the entire algorithm is applied to a variety of general text classification tasks, and the performance is evaluated in comparison with well-known algorithms.

Purpose – Artificial Intelligence has seen important growth in the digital area in recent years. Our aim is to explore possible guidelines that make use of AI advances to design good user experiences for digital products. Method – The proposed methods to gather the necessary qualitative data to support our claim involve open-ended interviews with UX/UI Designers working in the industry, in order to gain a deeper understanding of their thoughts and experiences. In addition, a literature review is conducted to identify the knowledge gap and build the base of our new theory. Findings – Our findings suggest a need to embrace new technological developments in favour of enhancing UX designers’ workflow. Additionally, basic AI and ML knowledge is needed to utilise these capabilities to their full potential. Indeed, a crucial area of impact where AI can augment a designer’s reach is personalization. Together with smart algorithms, designers may target their creations to specific user needs and demands. UX designers even have the opportunity for innovation as mundane tasks are automated by intelligent assistants, which broadens the possibility of acquiring further skills to enhance their work. One result, that is both innovative and unexpected, is the notion that AI and ML can augment a designer’s creativity by taking over mundane tasks, as well as, providing assistance with certain graphics and inputs. Implications – These results indicate that AI and ML may potentially impact the UX industry in a positive manner, as long as designers make use of the technology for the benefit of the user in true human-centred practice. Limitations – Nevertheless, our study presents its own unique limitations due to the scope and time frame of this dissertation, we are bound to the knowledge gathered from a small sample of professionals in Sweden. Presented guidelines are a suggestion based on our research and not a definitive workflow.