Machine learning is a growing area of artificial intelligence that is widely used in our world today. Training machine learning models requires knowledge and computing power. Machine Learning as a Service (MLaaS) tries to solve these issues. By storing the datasets and using virtual computing instances in the cloud, one can create machine learning models without writing a single line of code. When selecting an MLaaS platform to use, the natural question of which one to use arises. This thesis conducts controlled experiments to compare the image classification capabilities of Microsoft Azure ML, Amazon Web Services SageMaker, and Google Cloud Platform Vertex AI. The prediction accuracy, training time, and cost will be measured with three different datasets. Some subjective comments about the user experience while conducting these experiments will also be provided. The results of these experiments will be used to make recommendations as to which MLaaS platform to use depending on which metric is most suitable. This thesis found that Microsoft Azure ML performed best in terms of prediction accuracy, and training cost, across all datasets. Amazon Web Services SageMaker had the shortest time to train but performed the worst in terms of accuracy and had trouble with two of the three datasets. Google Cloud Platform Vertex AI did achieve the second-bestprediction accuracy but was the most expensive platform by far as it had the largest time to train. It did, however, provide the smoothest user experience.Overall, Azure ML would be the platform of choice for image classification tasks after weighing together the results of the experiments as well as the subjective user experience.

Making predictions nowadays is of high importance for any company, whether small or large, as thanks to the possibility to analyze the data available, new market opportunities can be found, risks and costs can be reduced, among others. Machine learning algorithms for time series can be used for predicting future values of interest. However, choosing the appropriate algorithm and tuning its metaparameters require a great level of expertise. This creates an adoption barrier for small and medium enterprises which could not afford hiring a machine learning expert to their IT team. For these reasons, this project studies different possibilities to make good predictions based on machine learning algorithms, but without requiring great theoretical knowledge from the users. Moreover, a software package that implements the prediction process has been developed. The software is an ensemble method that first predicts a value taking into account different algorithms at the same time, and then it combines their results considering also the previous performance of each algorithm to obtain a final prediction of the value. Moreover, the solution proposed and implemented in this project can also predict according to a concrete objective (e.g., optimize the prediction, or do not exceed the real value) because not every prediction problem is subject to the same constraints. We have experimented and validated the implementation with three different cases. In all of them, a better performance has been obtained in comparison with each of the algorithms involved, reaching improvements of 45 to 95%.

Network attacks remain a constant threat to organizations around the globe. Intrusion detection systems provide a vital piece of the protection needed in order to fend off these attacks. Machine learning has become a popular method for developing new anomaly-based intrusion detection systems, and in recent years, deep learning has followed suit. Additionally, data fusion is often applied to intrusion detection systems in research, most often in the form of feature reduction, which can improve the accuracy and training times of classifiers. Another less common form of data fusion is decision fusion, where the outputs of multipe classifiers are fused into a more reliable result. Recent research has produced some contradictory results regarding the efficiency of traditional machine learning algorithms compared to deep learning algorithms. This study aims to investigate this problemand provide some clarity about the relative performance of a selection of classifier algorithms, namely artificial neural network, long short-term memory and random forest. Furthermore, two feature selection methods, namely correlation coefficient method and principal component analysis, as well as one decision fusion method in D-S evidence theory are tested. The majority of the feature selection methods fail to increase the accuracy of the implemented models, although the accuracy is not drastically reduced. Among the individual classifiers, random forest shows the best performance, obtaining an accuracy of 87,87%. Fusing the results with D-S evidence theory further improves this result, obtaining an accuracy of 88,56%, and proves particularly useful for reducing the number of false positives.

Negation is a complex phenomenon present in all human languages, allowing for the uniquely human capacities of denial, contradiction, misrepresentation, lying, and irony. It is in the first place a phenomenon of semantical opposition. Sentences containing negation are generally (a) less informative than affirmative ones, (b) morphosyntactically more marked—all languages have negative markers while only a few have affirmative markers, and (c) psychologically more complex and harder to process. Negation often conveys positive meaning. This meaning ranges from implicatures to entailments. In this dissertation, I develop a system to reveal the underlying positive interpretation of negation. I first identify which words are intended to be negated (i.e, the focus of negation) and second, I rewrite those tokens to generate an actual positive interpretation. I identify the focus of negation by scoring probable foci along a continuous scale. One of the obstacles to exploring foci scoring is that no public datasets exist for this task. Thus, to study this problem I create new corpora. The corpora contain verbal, nominal and adjectival negations and their potential positive interpretations along with their scores ranging from 1 to 5. Then, I use supervised learning models for scoring the focus of negation. In order to rewrite the focus of negation with its positive interpretation, I work with negations from Simple Wikipedia, automatically generate potential positive interpretations, and then collect manual annotations that effectively rewrite the negation in positive terms. This procedure yields positive interpretations for approximately 77% of negations, and the final corpus includes over 5,700 negations and over 5,900 positive interpretations. I then use sequence-to-sequence neural models and provide baseline results.

Background: Traffic Sign Recognition (TSR) is particularly useful for novice driversand self-driving cars. Driver Assistance Systems(DAS) involves automatic trafficsign recognition. Efficient classification of the traffic signs is required in DAS andunmanned vehicles for safe navigation. Convolutional Neural Networks(CNN) isknown for establishing promising results in the field of image classification, whichinspired us to employ this technique in our thesis. Computer vision is a process thatis used to understand the images and retrieve data from them. OpenCV is a Pythonlibrary used to detect traffic sign images in real-time. Objectives: This study deals with an experiment to build a CNN model which canclassify the traffic signs in real-time effectively using OpenCV. The model is builtwith low computational cost. The study also includes an experiment where variouscombinations of parameters are tuned to improve the model’s performance. Methods: The experimentation method involve building a CNN model based onmodified LeNet architecture with four convolutional layers, two max-pooling layersand two dense layers. The model is trained and tested with the German Traffic SignRecognition Benchmark (GTSRB) dataset. Parameter tuning with different combinationsof learning rate and epochs is done to improve the model’s performance.Later this model is used to classify the images introduced to the camera in real-time. Results: The graphs depicting the accuracy and loss of the model before and afterparameter tuning are presented. An experiment is done to classify the traffic signimage introduced to the camera by using the CNN model. High probability scoresare achieved during the process which is presented. Conclusions: The results show that the proposed model achieved 95% model accuracywith an optimum number of epochs, i.e., 30 and default optimum value oflearning rate, i.e., 0.001. High probabilities, i.e., above 75%, were achieved when themodel was tested using new real-time data.

Deep learning has become ubiquitous in science and industry for classifying images or identifying patterns in data. The most widely used approach to training convolutional neural networks is supervised learning, which requires a large set of annotated data. To elude the high cost of collecting and annotating datasets, selfsupervised learning methods represent a promising way to learn the common functions of images and videos from large-scale unlabeled data without using humanannotated labels. This thesis provides the results of using self-supervised learning and explainable AI to localise objects in images from electron microscopes. The work used a synthetic geometric dataset and a synthetic pollen dataset. The classification was used as a pretext task. Different methods of explainable AI were applied: Grad-CAM and backpropagation-based approaches showed the lack of prospects; at the same time, the Extremal Perturbation function has shown efficiency. As a result of the downstream localisation task, the objects of interest were detected with competitive accuracy for one-class images. The advantages and limitations of the approach have been analysed. Directions for further work are proposed.

Denna rapport utvärderar olika metoder för att klassificera och kategorisera email. Mångamail anländer hos människors inkorg varje dag. När tiden går och antalet email ökar blir detsvårare att hitta specifika email. På HDAB arbetar de som konsulter och vill dela upp email iolika mappar beroende på vilket projekt det tillhör. Idag fungerar det genom ett ord-regelbaseratsystem som sorterar email I olika mappar med en precision på cirka 85%. HDAB villta reda på om det går att använda maskininlärning för det nuvarande systemet. Denna rapportpresenterar fyra maskininlärningsalgorimer, beslutsträd, random forest beslutsträd, k-nearestneighbor och naive bayes, som användas för att utvärdera om det är möjligt att kategoriseraemailen.Datan som används till rapporten kommer från HDABs mailserver och är redan kategoriseradtill rätt kaegori. / This report will evaluate methods for classifying e-mails into different categories. A lot ofemails are received in peoples inboxes every day. When the time passes and the amount ofemails increases the ability to find specific emails gets harder. At HDAB they are workingwith consulting and want to separate different emails from different project into separate folders.This is achieved today by using a word based rule system that sorts emails into differentfolders and has a precision about 85%. HDAB wants to know if it is possible to use machinelearning to automatically sort the emails into different folders instead of the current solution.This report presents four machine learning algorithms, decision tree, random forest decisiontree, k-nearest neighbor and naive bayes, which are being used for evaluation of the possibilityto categorize the emails.The data used for the report will be data gathered from HDAB’s mail server and are alreadypre-labeled into their respectively categories.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第23540号 / 情博第770号 / 新制||情||131(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)准教授 吉井 和佳, 教授 河原 達也, 教授 西野 恒, 教授 鹿島 久嗣 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Research and experimentation in various scientific fields are based on the knowledge and ideas from scholarly literature. The advancement of research and development has, thus, strengthened the importance of literary analysis and understanding. However, in recent years, researchers have been facing massive scholarly documents published at an exponentially increasing rate. Analyzing this vast number of publications is far beyond the capability of individual researchers. This dissertation is motivated by the need for large scale analyses of the exploding number of scholarly literature for scientific knowledge discovery. In the first part of this dissertation, the interdependencies between scholarly literature are studied. First, I develop Delve – a data-driven search engine supported by our designed semi-supervised edge classification method. This system enables users to search and analyze the relationship between datasets and scholarly literature. Based on the Delve system, I propose to study information extraction as a node classification problem in attributed networks. Specifically, if we can learn the research topics of documents (nodes in a network), we can aggregate documents by topics and retrieve information specific to each topic (e.g., top-k popular datasets). Node classification in attributed networks has several challenges: a limited number of labeled nodes, effective fusion of topological structure and node/edge attributes, and the co-existence of multiple labels for one node. Existing node classification approaches can only address or partially address a few of these challenges. This dissertation addresses these challenges by proposing semi-supervised multi-class/multi-label node classification models to integrate node/edge attributes and topological relationships. The second part of this dissertation examines the problem of analyzing the interdependencies between terms in scholarly literature. I present two algorithms for the automatic hypothesis generation (HG) problem, which refers to the discovery of meaningful implicit connections between scientific terms, including but not limited to diseases, drugs, and genes extracted from databases of biomedical publications. The automatic hypothesis generation problem is modeled as a future connectivity prediction in a dynamic attributed graph. The key is to capture the temporal evolution of node-pair (term-pair) relations. Experiment results and case study analyses highlight the effectiveness of the proposed algorithms compared to the baselines’ extension.

L’objectif de la thèse est d’améliorer les différents traitements et de proposer une visualisation claire et intuitive à l’opérateur des données en sortie d’un géoradar (radargramme) afin de pouvoir localiser de manière précise les réseaux de canalisations enfouis. Notamment, nous souhaitons mettre en évidence les hyperboles présentes dans les radargrammes car celles-ci sont caractéristiques de la présence d'une canalisation. Dans un premier temps nous nous sommes intéressés à la suppression de l’information inutile (clutter) pouvant gêner la détection des hyperboles. Nous avons ainsi proposé une méthode de filtrage du clutter et du bruit des radargrammes. Ensuite, nous avons travaillé sur l’élaboration d’une méthode permettant de détecter automatiquement les hyperboles dans un radargramme ainsi qu’une estimation de sa fonction mathématique dans des conditions quasi-temps réel. Et enfin nous avons également proposé une méthode de séparation de source permettant de distinguer le clutter et le signal utile du radargramme tout en ayant un impact minimal sur les hyperboles. Ces derniers travaux ouvrent d’autres possibilités pour le filtrage, le rehaussement ou la détection automatique d’hyperboles. / The thesis objective is to improve the different processing in order to make the data acquired by ground penetrating radar (B-scan) more understandable for the operators. Consequently, it will facilitate the pipe localisation. More particularly, we wish to highlight the hyperbolas in the B-scan because they point out the presence of a pipe. First of all, we are interested in removing all the useless information which might hide the hyperbolas. We proposed a filtering method removing unwanted reflections and noise. Then, we worked on an automatic hyperbola detection method and an estimation of their mathematical functions in quasi real time. Finally, we proposed a source separation method to distinguish the unwanted reflections from the hyperbolas with a minimal impact on them. This last work opens interesting perspectives in filtering, hyperbolas enhancement and hyperbola detection.