Human activity recognition for an intelligent knee orthosis

Dissertação para obtenção do Grau de Mestre em Engenharia Biomédica

Displasia Fibrosa Crânio-Facial a Propósito de Dois Casos Clínicos

Dependendo da localização e do número de ossos envolvidos, a Displasia Fibrosa (D.F.) crânio-facial pode ser responsável por síndromes dismórficos e por sintomatologia otológica, oftalmológica ou rinológica. Este artigo tem por objectivo i1ustrar dois casos clínicos de D. F. Poliostótica com envolvimento predominante dos ossos temporal a etmóide. No primeiro caso clínico o envolvimento do osso temporal é responsável por síndrome vertiginoso resultante de hipofunção vestibular esquerda e da obliteração do aqueduto vestibular homolateral. Neste coso o doente foi submetido a neurectomia dos nervos vestibulares, por via retrosigmóide. O segundo caso clínico é um caso de D.F. predominantemente do osso etmóide, acompanhado de proptose e obstrução nasal, em que se procedeu à excisão total por via paralateronasal sob controlo endoscópico. Os autores fazem uma revisão da literatura sobre a clínica, o diagnóstico, e a terapêutica do da doença a nível crânio-facial.

Intention recognition, commitment and their roles in the evolution of cooperation

Dissertação para obtenção do Grau de Doutor em Informática

Bacterial peptidoglycan biosynthesis and recognition by the innate immune system

Dissertation presented to obtain the Ph.D degree in Biology

Facial nerve palsy associated with leptospirosis

This case report describes the findings of a 27-year-old black male from Bahia, Brazil, who developed facial palsy during the convalescence phase of leptospirosis. The patient recovered without neurological sequel. This work calls attention to a possible association between leptospirosis and facial palsy.

Software for pattern recognition of the larvae of Aedes aegypti and Aedes albopictus

Software for pattern recognition of the larvae of mosquitoes Aedes aegypti and Aedes albopictus, biological vectors of dengue and yellow fever, has been developed. Rapid field identification of larva using a digital camera linked to a laptop computer equipped with this software may greatly help prevention campaigns.

Avatars and the «Imitation Game» – can machines smile?

Considering Alan Turing’s challenge in «Computing Machinery and Intelligence» (1950) – can machines play the «imitation game»? – it is proposed that the requirements of the Turing test are already implicitly being used for checking the credibility of virtual characters and avatars. Like characters, Avatars aim to visually express emotions (the exterior signs of the existence of feeling) and its creators have to resort to emotion codes. Traditional arts have profusely contributed for this field and, together with the science of anatomy, shaped the grounds for current Facial Action Coding System (FACS) and their databases. However, FACS researchers have to improve their «instruction tables» so that the machines will be able, in a near future, to be programmed to carry out the operation of recognizing human expressions (face and body) and classify them adequately. For the moment, the reproductions have to resort to the copy of real life expressions, and the presente smile of avatars comes from mirroring their human users.

Human activity recognition with accelerometry: novel time and frequency features

Human Activity Recognition systems require objective and reliable methods that can be used in the daily routine and must offer consistent results according with the performed activities. These systems are under development and offer objective and personalized support for several applications such as the healthcare area. This thesis aims to create a framework for human activities recognition based on accelerometry signals. Some new features and techniques inspired in the audio recognition methodology are introduced in this work, namely Log Scale Power Bandwidth and the Markov Models application. The Forward Feature Selection was adopted as the feature selection algorithm in order to improve the clustering performances and limit the computational demands. This method selects the most suitable set of features for activities recognition in accelerometry from a 423th dimensional feature vector. Several Machine Learning algorithms were applied to the used accelerometry databases – FCHA and PAMAP databases - and these showed promising results in activities recognition. The developed algorithm set constitutes a mighty contribution for the development of reliable evaluation methods of movement disorders for diagnosis and treatment applications.

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

Dental and facial characteristics of patients with juvenile idiopathic arthritis

OBJECTIVE: It has been shown that the temporomandibular joint is frequently affected by juvenile idiopathic arthritis, and this degenerative disease, which may occur during facial growth, results in severe mandibular dysfunction. However, there are no studies that correlate oral health (tooth decay and gingival diseases) and temporomandibular joint dysfunction in patients with juvenile idiopathic arthritis. The aim of this study is to evaluate the oral and facial characteristics of the patients with juvenile idiopathic arthritis treated in a large teaching hospital. METHOD: Thirty-six patients with juvenile idiopathic arthritis (26 female and 10 male) underwent a systematic clinical evaluation of their dental, oral, and facial structures (DMFT index, plaque and gingival bleeding index, dental relationship, facial profile, and Helkimo's index). The control group was composed of 13 healthy children. RESULTS: The mean age of the patients with juvenile idiopathic arthritis was 10.8 years; convex facial profile was present in 12 juvenile idiopathic arthritis patients, and class II molar relation was present in 12 (P = .032). The indexes of plaque and gingival bleeding were significant in juvenile idiopathic arthritis patients with a higher number of superior limbs joints involved (P = .055). Anterior open bite (5) and temporomandibular joint noise (8) were present in the juvenile idiopathic arthritis group. Of the group in this sample, 94% (P = .017) had temporomandibular joint dysfunction, 80% had decreased mandibular opening (P = 0.0002), and mandibular mobility was severely impaired in 33% (P = .015). CONCLUSION: This study confirms that patients with juvenile idiopathic arthritis a) have a high incidence of mandibular dysfunction that can be attributed to the direct effect of the disease in the temporomandibular joint and b) have a higher incidence of gingival disease that can be considered a secondary effect of juvenile idiopathic arthritis on oral health.

Hand gesture recognition for human computer interaction : a comparative study of different image features

Hand gesture recognition for human computer interaction, being a natural way of human computer interaction, is an area of active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them to convey information or for device control. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. In this study we try to identify hand features that, isolated, respond better in various situations in human-computer interaction. The extracted features are used to train a set of classifiers with the help of RapidMiner in order to find the best learner. A dataset with our own gesture vocabulary consisted of 10 gestures, recorded from 20 users was created for later processing. Experimental results show that the radial signature and the centroid distance are the features that when used separately obtain better results, with an accuracy of 91% and 90,1% respectively obtained with a Neural Network classifier. These to methods have also the advantage of being simple in terms of computational complexity, which make them good candidates for real-time hand gesture recognition.

Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"