Yes / Novel machine-learning and feature-selection algorithms have been developed to study: (i) the flare prediction capability of magnetic feature (MF) properties generated by the recently developed Solar Monitor Active Region Tracker (SMART); (ii) SMART's MF properties that are most significantly related to flare occurrence. Spatio-temporal association algorithms are developed to associate MFs with flares from April 1996 to December 2010 in order to differentiate flaring and non-flaring MFs and enable the application of machine learning and feature selection algorithms. A machine-learning algorithm is applied to the associated datasets to determine the flare prediction capability of all 21 SMART MF properties. The prediction performance is assessed using standard forecast verification measures and compared with the prediction measures of one of the industry's standard technologies for flare prediction that is also based on machine learning - Automated Solar Activity Prediction (ASAP). The comparison shows that the combination of SMART MFs with machine learning has the potential to achieve more accurate flare prediction than ASAP. Feature selection algorithms are then applied to determine the MF properties that are most related to flare occurrence. It is found that a reduced set of 6 MF properties can achieve a similar degree of prediction accuracy as the full set of 21 SMART MF properties.

Yes / There is an evolution in the demands of modern ophthalmology from descriptive findings to assessment of cellular level changes by using in vivo confocal microscopy. Confocal microscopy, by producing grey-scale images, enables a microstructural insight into the in vivo cornea in both health and disease, including epithelial changes, stromal degenerative or dystrophic diseases, endothelial pathologies, and corneal deposits and infections. Ophthalmologists use acquired confocal corneal images to identify health and disease states and then to diagnose which type of disease is affecting the cornea. This paper presents the main features of the healthy confocal corneal layers, and reviews the most common corneal diseases. It identifies the visual signature of each disease in the affected layer and extracts the main features of this disease in terms of intensity, certain regular shapes with both their size and diffusion, and some specific region of interest. These features will lead towards the development of a complete automatic corneal diagnostic system which predicts abnormalities in the confocal corneal data sets.

Yes / Face recognition is a very current subject of great interest in the area of visual computing. In the past, numerous face recognition and authentication approaches have been proposed, though the great majority of them use full frontal faces both for training machine learning algorithms and for measuring the recognition rates. In this paper, we discuss some novel experiments to test the performance of machine learning, especially the performance of deep learning, using partial faces as training and recognition cues. Thus, this study sharply differs from the common approaches of using the full face for recognition tasks. In particular, we study the rate of recognition subject to the various parts of the face such as the eyes, mouth, nose and the forehead. In this study, we use a convolutional neural network based architecture along with the pre-trained VGG-Face model to extract features for training. We then use two classifiers namely the cosine similarity and the linear support vector machine to test the recognition rates. We ran our experiments on the Brazilian FEI dataset consisting of 200 subjects. Our results show that the cheek of the face has the lowest recognition rate with 15% while the (top, bottom and right) half and the 3/4 of the face have near 100% recognition rates. / Supported in part by the European Union's Horizon 2020 Programme H2020-MSCA-RISE-2017, under the project PDE-GIR with grant number 778035.

The elderly population is growing at a rapid pace, and falls are a significant problem facing adults aged 65 and older in terms of both human suffering and economic losses. Falls are the leading cause of mortality among older adults, and non-fatal falls result in reduced function and poor quality of life for older adults. Although much is known about the mechanisms and contributing risk factors relevant to falls, falls still remain a significant problem associated with this age group. Therefore, new strategies and knowledge need to be introduced to understand and prevent falls. Studies show that early detection of impaired mobility is critical to the prevention of falls. In this study, the relationship between gait and postural parameters and falls among elderly participants using wearable inertial sensors was investigated. As such, the aim of this study is to investigate the critical gait and postural parameters contributing to falls, then further to classify fallers and non-fallers by utilizing gait and postural parameters and machine learning techniques, e.g. support vector machines (SVMs). Additionally, as the assessment of fall risk is linked to noisy environment, it is important to understand the capability of the SVM classifier to effectively address noisy data. Therefore, the robustness of the SVM classifier was also investigated in this study. In summary, the presented work addresses several challenges through research on the following three issues: 1) the significant differences in gait and pastoral parameters between fallers and non-fallers; 2) a machine learning based framework for classification of fallers and non-fallers by using only one IMU located at the sternum; and 3) robustness of SVM classifier to classify fallers and non-fallers in a noisy environment. The machine learning based framework developed in this dissertation contribute to advancing the state-of-art in fall risk assessment by 1) classifying fallers and non-fallers from a single IMU located at the sternum; 2) developing machine learning method for classification of fallers and non-fallers; and 3) investigating the robustness of SVM classifier in a noisy environment. / Ph. D.

No / Ethnicity is one of the most salient clues to face identity. Analysis of ethnicity-specific facial data is a challenging problem and predominantly carried out using computer-based algorithms. Current published literature focusses on the use of frontal face images. We addressed the challenge of binary (British Pakistani or other ethnicity) ethnicity classification using profile facial images. The proposed framework is based on the extraction of geometric features using 10 anthropometric facial landmarks, within a purpose-built, novel database of 135 multi-ethnic and multi-racial subjects and a total of 675 face images. Image dimensionality was reduced using Principle Component Analysis and Partial Least Square Regression. Classification was performed using Linear Support Vector Machine. The results of this framework are promising with 71.11% ethnic classification accuracy using a PCA algorithm + SVM as a classifier, and 76.03% using PLS algorithm + SVM as a classifier.

No / We propose a hybrid scheme to implement an object driven, block based algorithm to achieve low bit-rate compression of stereo image pairs. The algorithm effectively combines the simplicity and adaptability of the existing block based stereo image compression techniques with an edge/contour based object extraction technique to determine appropriate compression strategy for various areas of the right image. Unlike the existing object-based coding such as MPEG-4 developed in the video compression community, the proposed scheme does not require any additional shape coding. Instead, the arbitrary shape is reconstructed by the matching object inside the left frame, which has been encoded by standard JPEG algorithm and hence made available at the decoding end for those shapes in right frames. Yet the shape reconstruction for right objects incurs no distortion due to the unique correlation between left and right frames inside stereo image pairs and the nature of the proposed hybrid scheme. Extensive experiments carried out support that significant improvements of up to 20% in compression ratios are achieved by the proposed algorithm in comparison with the existing block-based technique, while the reconstructed image quality is maintained at a competitive level in terms of both PSNR values and visual inspections

This thesis investigates the integration of transfer learning with ResNet-101 and compares its performance with VGG-19 for 3D object detection in autonomous vehicles. ResNet-101 is a deep Convolutional Neural Network with 101 layers and VGG-19 is a one with 19 layers. The research emphasizes the fusion of camera and lidar outputs to enhance the accuracy of 3D bounding box estimation, which is critical in occluded environments. Selecting an appropriate backbone for feature extraction is pivotal for achieving high detection accuracy. To address this challenge, we propose a method leveraging transfer learning with ResNet- 101, pretrained on large-scale image datasets, to improve feature extraction capabilities. The averaging technique is used on output of these sensors to get the final bounding box. The experimental results demonstrate that the ResNet-101 based model outperforms the VGG-19 based model in terms of accuracy and robustness. This study provides valuable insights into the effectiveness of transfer learning and multi-sensor fusion in advancing the innovation in 3D object detection for autonomous driving. / Master of Science / In the realm of computer vision, the quest for more accurate and robust 3D object detection pipelines remains an ongoing pursuit. This thesis investigates advanced techniques to im- prove 3D object detection by comparing two popular deep learning models, ResNet-101 and VGG-19. The study focuses on enhancing detection accuracy by combining the outputs from two distinct methods: one that uses a monocular camera to estimate 3D bounding boxes and another that employs lidar's bird's-eye view (BEV) data, converting it to image-based 3D bounding boxes. This fusion of outputs is critical in environments where objects may be partially obscured. By leveraging transfer learning, a method where models that are pre-trained on bigger datasets are finetuned for certain application, the research shows that ResNet-101 significantly outperforms VGG-19 in terms of accuracy and robustness. The approach involves averaging the outputs from both methods to refine the final 3D bound- ing box estimation. This work highlights the effectiveness of combining different detection methodologies and using advanced machine learning techniques to advance 3D object detec- tion technology.

In recent years, there has been an exponential growth in sequencing projects due to accelerated technological advances, leading to a significant increase in the amount of data and resulting in new challenges for biological sequence analysis. Consequently, the use of techniques capable of analyzing large amounts of data has been explored, such as machine learning (ML) algorithms. ML algorithms are being used to analyze and classify biological sequences, despite the intrinsic difficulty in extracting and finding representative biological sequence methods suitable for them. Thereby, extracting numerical features to represent sequences makes it statistically feasible to use universal concepts from Information Theory, such as Tsallis and Shannon entropy. In this study, we propose a novel Tsallis entropy-based feature extractor to provide useful information to classify biological sequences. To assess its relevance, we prepared five case studies: (1) an analysis of the entropic index q; (2) performance testing of the best entropic indices on new datasets; (3) a comparison made with Shannon entropy and (4) generalized entropies; (5) an investigation of the Tsallis entropy in the context of dimensionality reduction. As a result, our proposal proved to be effective, being superior to Shannon entropy and robust in terms of generalization, and also potentially representative for collecting information in fewer dimensions compared with methods such as Singular Value Decomposition and Uniform Manifold Approximation and Projection.

Facade cracks are a common problem in the north of Sweden due to shifting temperatures creating frost in the facades which ultimately damages the facades, often in the form of cracks. To fix these cracks, workers must visually inspect the facades to find them which is a difficult and time-consuming task. This project explores the possibilities of creating an algorithm that can classify cracks on facades with the help of deep learning models. The idea is that in the future, an algorithm like this could be implemented on a drone that hoovers around buildings, filming the facade, and reporting back if there are any damages to the facade. The work in this project is exploratory and the path of convolutional neural networks has been explored, as well as the possibility to simulate training data due to the lack of real-world data. The experimental work in this project led to some interesting conclusions for further work. The relatively small amount of data used in this project points towards the possibility of using simulated data as a complement to real data, as well as the possibility of using convolutional neural networks as a means of classifying facades for crack recognition. The data and conclusions collected in this report can be used as a preparatory work for a working prototype algorithm.

Just-In-Time Software Defect Prediction (JIT-DP) focuses on predicting errors in software at change-level with the objective of helping developers identify defects while the development process is still ongoing, and improving the quality of software applications. This work studies deep learning techniques by applying attention mechanisms that have been successful in, among others, Natural Language Processing (NLP) tasks. We introduce two networks named Convolutional Neural Network with Bidirectional Attention (BACNN) and Bidirectional Attention Code Network (BACoN) that employ a bi-directional attention mechanism between the code and message of a software change. Furthermore, we examine BERT [17] and RoBERTa [57] attention architectures for JIT-DP. More specifically, we study the effectiveness of the aforementioned attention-based models to predict defective commits compared to the current state of the art, DeepJIT [37] and TLEL [101]. Our experiments evaluate the models by using software changes from the OpenStack open source project. The results showed that attention-based networks outperformed the baseline models in terms of accuracy in the different evaluation settings. The attention-based models, particularly BERT and RoBERTa architectures, demonstrated promising results in identifying defective software changes and proved to be effective in predicting defects in changes of new software releases. / Just-In-Time Defect Prediction (JIT-DP) fokuserar på att förutspå fel i mjukvara vid ändringar i koden, med målet att hjälpa utvecklare att identifiera defekter medan utvecklingsprocessen fortfarande är pågående, och att förbättra kvaliteten hos applikationsprogramvara. Detta arbete studerar djupinlärningstekniker genom att tillämpa attentionmekanismer som har varit framgångsrika inom, bland annat, språkteknologi (NLP). Vi introducerar två nätverk vid namn Convolutional Neural Network with Bidirectional Attention (BACNN), och Bidirectional Attention Code Network (BACoN), som använder en tvåriktad attentionmekanism mellan koden och meddelandet om en mjukvaruändring. Dessutom undersöker vi BERT [17] och RoBERTa [57], attentionarkitekturer för JIT-DP. Mer specifikt studerar vi hur effektivt dessa attentionbaserade modeller kan förutspå defekta ändringar, och jämför dem med de bästa tillgängliga arkitekturerna DeePJIT [37] och TLEL [101]. Våra experiment utvärderar modellerna genom att använda mjukvaruändringar från det öppna källkodsprojektet OpenStack. Våra resultat visar att attentionbaserade nätverk överträffar referensmodellen sett till träffsäkerheten i de olika scenarierna. De attentionbaserade modellerna, framför allt BERT och RoBERTa, demonstrerade lovade resultat när det kommer till att identifiera defekta mjukvaruändringar och visade sig vara effektiva på att förutspå defekter i ändringar av nya mjukvaruversioner.