This dissertation's primary goal was to systematically study human activity recognition and enhance its performance by advancing human activities' sequential modeling based on HMM-based machine learning. Driven by these purposes, this dissertation has the following major contributions: The proposal of our HAR research pipeline that guides the building of a robust wearable end-to-end HAR system and the implementation of the recording and recognition software Activity Signal Kit (ASK) according to the pipeline; Collecting several datasets of multimodal biosignals from over 25 subjects using the self-implemented ASK software and implementing an easy mechanism to segment and annotate the data; The comprehensive research on the offline HAR system based on the recorded datasets and the implementation of an end-to-end real-time HAR system; A novel activity modeling method for HAR, which partitions the human activity into a sequence of shared, meaningful, and activity ...

This thesis contributes to motion characterization through inertial and physiological signals captured by wearable devices and analyzed using signal processing and deep learning techniques. This research leverages the possibilities of motion analysis for three main applications: to know what physical activity a person is performing (Human Activity Recognition), to identify who is performing that motion (user identification) or know how the movement is being performed (motor anomaly detection). Most previous research has addressed human motion modeling using invasive sensors in contact with the user or intrusive sensors that modify the user’s behavior while performing an action (cameras or microphones). In this sense, wearable devices such as smartphones and smartwatches can collect motion signals from users during their daily lives in a less invasive or intrusive way. Recently, there has been an exponential increase in research focused on inertial-signal processing to ...

Epilepsy is one of the most common neurological diseases that manifests in repetitive epileptic seizures as a result of an abnormal, synchronous activity of a large group of neurons. Depending on the affected brain regions, seizures produce various severe clinical symptoms. There is no cure for epilepsy and sometimes even medication and other therapies, like surgery, vagus nerve stimulation or ketogenic diet, do not control the number of seizures. In that case, long-term (home) monitoring and automatic seizure detection would enable the tracking of the evolution of the disease and improve objective insight in any responses to medical interventions or changes in medical treatment. Especially during the night, supervision is reduced; hence a large number of seizures is missed. In addition, an alarm should be integrated into the automated seizure detection algorithm for severe seizures in order to help the ...

Automatic analysis of head gestures and facial expressions is a challenging research area and it has significant applications for intelligent human-computer interfaces. An important task is the automatic classification of non-verbal messages composed of facial signals where both facial expressions and head rotations are observed. This is a challenging task, because there is no definite grammar or code-book for mapping the non-verbal facial signals into a corresponding mental state. Furthermore, non-verbal facial signals and the observed emotions have dependency on personality, society, state of the mood and also the context in which they are displayed or observed. This thesis mainly addresses the three desired tasks for an effective visual information based automatic face and head gesture (FHG) analyzer. First we develop a fully automatic, robust and accurate 17-point facial landmark localizer based on local appearance information and structural information of ...

When listening to music, some humans can easily recognize which instruments play at what time or when a new musical segment starts, but cannot describe exactly how they do this. To automatically describe particular aspects of a music piece – be it for an academic interest in emulating human perception, or for practical applications –, we can thus not directly replicate the steps taken by a human. We can, however, exploit that humans can easily annotate examples, and optimize a generic function to reproduce these annotations. In this thesis, I explore solving different music perception tasks with deep learning, a recent branch of machine learning that optimizes functions of many stacked nonlinear operations – referred to as deep neural networks – and promises to obtain better results or require less domain knowledge than more traditional techniques. In particular, I employ ...

Despite the outstanding progress made on automatic speech recognition (ASR) throughout the last decades, noise-robust ASR still poses a challenge. Tackling with acoustic noise in ASR systems is more important than ever before for a twofold reason: 1) ASR technology has begun to be extensively integrated in intelligent mobile devices (IMDs) such as smartphones to easily accomplish different tasks (e.g. search-by-voice), and 2) IMDs can be used anywhere at any time, that is, under many different acoustic (noisy) conditions. On the other hand, with the aim of enhancing noisy speech, IMDs have begun to embed small microphone arrays, i.e. microphone arrays comprised of a few sensors close each other. These multi-sensor IMDs often embed one microphone (usually at their rear) intended to capture the acoustic environment more than the speaker’s voice. This is the so-called secondary microphone. While classical microphone ...

This thesis focuses on the development of paradigms and techniques for the design and implementation of multimodal interactive systems, mainly for performing arts applications. The work addresses research issues in the fields of human-computer interaction, multimedia systems, and sound and music computing. The thesis is divided into two parts. In the first one, after a short review of the state-of-the-art, the focus moves on the definition of environments in which novel forms of technology-integrated artistic performances can take place. These are distributed active mixed reality environments in which information at different layers of abstraction is conveyed mainly non-verbally through expressive gestures. Expressive gesture is therefore defined and the internal structure of a virtual observer able to process it (and inhabiting the proposed environments) is described in a multimodal perspective. The definition of the structure of the environments, of the virtual ...

Smart applications like speaker verification have become essential in verifying the user's identity for availing of personal assistants or online banking services based on the user's voice characteristics. However, far-field or distant speaker verification is constantly affected by surrounding noises which can severely distort the speech signal. Moreover, speech signals propagating in long-range get reflected by various objects in the surrounding area, which creates reverberation and further degrades the signal quality. This PhD thesis explores deep learning-based multichannel speech enhancement techniques to improve the performance of speaker verification systems in real conditions. Multichannel speech enhancement aims to enhance distorted speech using multiple microphones. It has become crucial to many smart devices, which are flexible and convenient for speech applications. Three novel approaches are proposed to improve the robustness of speaker verification systems in noisy and reverberated conditions. Firstly, we integrate ...

The term "spike" is used to describe a short-time event that is the result of the activity of its source. Spikes can be seen in different signal modalities. In these modalities, often more than one source generates spikes. Classification algorithms can be used to group similar spikes, ideally spikes from the same source. This work examines the classification of spikes generated from neurons and muscles. When each detected spike is assigned to its source, the spike trains of these sources can provide information on complex brain network functioning, muscle disorders, and other applications. During the past several decades, there were many attempts to create and improve spike classification algorithms. No matter how advanced these methods are today, errors in classification cannot be avoided. Therefore, methods that would determine and improve reliability of classification are very desirable. In this work, it ...

Current Human-Machine Interfaces (HMI) lack of “emotional intelligence”, i.e. they are not able to identify human emotional states and take this information into account to decide on the proper actions to execute. The goal of affective computing is to fill this lack by detecting emotional cues occurring during Human-Computer Interaction (HCI) and synthesizing emotional responses. In the last decades, most of the studies on emotion assessment have focused on the analysis of facial expressions and speech to determine the emotional state of a person. Physiological activity also includes emotional information that can be used for emotion assessment but has received less attention despite of its advantages (for instance it can be less easily faked than facial expressions). This thesis reports on the use of two types of physiological activities to assess emotions in the context of affective computing: the activity ...

In recent years Machine Learning and in particular Deep Learning have excelled in object recognition and classification tasks in computer vision. As these methods extract features from the data itself by learning features that are relevant for a particular task, a key aspect of this remarkable success is the amount of data on which these methods train. Biomedical applications face the problem that the amount of training data is limited. In particular, labels and annotations are usually scarce and expensive to obtain as they require biological or medical expertise. One way to overcome this issue is to use additional knowledge about the data at hand. This guidance can come from expert knowledge, which puts focus on specific, relevant characteristics in the images, or geometric priors which can be used to exploit the spatial relationships in the images. This thesis presents ...

Over the last few years, i-vectors have been the state-of-the-art technique in speaker and language recognition. Recent advances in Deep Learning (DL) technology have improved the quality of i-vectors but the DL techniques in use are computationally expensive and need speaker or/and phonetic labels for the background data, which are not easily accessible in practice. On the other hand, the lack of speaker-labeled background data makes a big performance gap, in speaker recognition, between two well-known cosine and Probabilistic Linear Discriminant Analysis (PLDA) i-vector scoring techniques. It has recently been a challenge how to fill this gap without speaker labels, which are expensive in practice. Although some unsupervised clustering techniques are proposed to estimate the speaker labels, they cannot accurately estimate the labels. This thesis tries to solve the problems above by using the DL technology in different ways, without ...

The unprecedented processing demand, posed by the explosion of big data, challenges researchers to design efficient and adaptive machine learning algorithms that do not require persistent retraining and avoid learning redundant information. Inspired from learning techniques of intelligent biological agents, identifying transferable knowledge across learning problems has been a significant research focus to improve machine learning algorithms. In this thesis, we address the challenges of knowledge transfer through embedding spaces that capture and store hierarchical knowledge. In the first part of the thesis, we focus on the problem of cross-domain knowledge transfer. We first address zero-shot image classification, where the goal is to identify images from unseen classes using semantic descriptions of these classes. We train two coupled dictionaries which align visual and semantic domains via an intermediate embedding space. We then extend this idea by training deep networks that ...

Obstructive sleep apnea (OSA) is among the most prevalent sleep disorders, which is estimated to affect 6 %−19 % of women and 13 %−33 % of men. Besides daytime sleepiness, impaired cognitive functioning and an increased risk for accidents, OSA may lead to obesity, diabetes and cardiovascular diseases (CVD) on the long term. Its prevalence is only expected to rise, as it is linked to aging and excessive body fat. Nevertheless, many patients remain undiagnosed and untreated due to the cumbersome clinical diagnostic procedures. For this, the patient is required to sleep with an extensive set of body attached sensors. In addition, the recordings only provide a single night perspective on the patient in an uncomfortable, and often unknown, environment. Thus, large scale monitoring at home is desired with comfortable sensors, which can stay in place for several nights. To ...

This thesis addresses the problem of vision based sign language recognition and focuses on three main tasks to design improved techniques that increase the performance of sign language recognition systems. We first attack the markerless tracking problem during natural and unrestricted signing in less restricted environments. We propose a joint particle filter approach for tracking multiple identical objects, in our case the two hands and the face, which is robust to situations including fast movement, interactions and occlusions. Our experiments show that the proposed approach has a robust tracking performance during the challenging situations and is suitable for tracking long durations of signing with its ability of fast recovery. Second, we attack the problem of the recognition of signs that include both manual (hand gestures) and non-manual (head/body gestures) components. We investigated multi-modal fusion techniques to model the different temporal ...