Human activity recognition by inertial signals obtained from a smartphone

Human Activity Recognition (HAR) is an emerging research field with the aim to identify the actions carried out by a person given a set of observations and the surrounding environment. The wide growth in this research field inside the scientific community is mainly explained by the high number of applications that are arising in the last years. A great part of the most promising applications are related to the healthcare field, where it is possible to track the mobility of patients with motor dysfunction as also the physical activity in patients with cardiovascular risk. Until a few years ago, by using distinct kind of sensors, a patient follow-up was possible. However, far from being a long-term solution and with the smartphone irruption, that monitoring can be achieved in a non-invasive way by using the embedded smartphone’s sensors. For these reasons this Final Degree Project arises with the main target to evaluate new feature extraction techniques in order to carry out an activity and user recognition, and also an activity segmentation. The recognition is done thanks to the inertial signals integration obtained by two widespread sensors in the greater part of smartphones: accelerometer and gyroscope. In particular, six different activities are evaluated walking, walking-upstairs, walking-downstairs, sitting, standing and lying. Furthermore, a segmentation task is carried out taking into account the activities performed by thirty users. This can be done by using Hidden Markov Models and also a set of tools tested satisfactory in speech recognition: HTK (Hidden Markov Model Toolkit).

Towards a new proposal to evaluate the learning objects quality in learning strategies for education (QEES)

In Computer Science world several proposals have been developed for the assessment of the quality of the digital objects, based on the capabilities and facilities offered by current technologies and the available resources. Years ago researchers and specialists from both educational and technological areas have been committed to the development of strategies that improve the quality of education. At present, in the field of teaching-learning, another important aspect is the need to improve the manner of gaining knowledge and learning in education, which the use of learning strategies is a major advance in the teaching-learning process in institutions of higher education. This paper presents QEES, a proposal for evaluating the quality of the learning objects employed on learning strategies to support students during their education processes by using information extraction techniques and ontologies.

Improving 3D Keypoint Detection from Noisy Data Using Growing Neural Gas

3D sensors provides valuable information for mobile robotic tasks like scene classification or object recognition, but these sensors often produce noisy data that makes impossible applying classical keypoint detection and feature extraction techniques. Therefore, noise removal and downsampling have become essential steps in 3D data processing. In this work, we propose the use of a 3D filtering and down-sampling technique based on a Growing Neural Gas (GNG) network. GNG method is able to deal with outliers presents in the input data. These features allows to represent 3D spaces, obtaining an induced Delaunay Triangulation of the input space. Experiments show how the state-of-the-art keypoint detectors improve their performance using GNG output representation as input data. Descriptors extracted on improved keypoints perform better matching in robotics applications as 3D scene registration.

A comparative evaluation of term recognition algorithms

Automatic Term Recognition (ATR) is a fundamental processing step preceding more complex tasks such as semantic search and ontology learning. From a large number of methodologies available in the literature only a few are able to handle both single and multi-word terms. In this paper we present a comparison of five such algorithms and propose a combined approach using a voting mechanism. We evaluated the six approaches using two different corpora and show how the voting algorithm performs best on one corpus (a collection of texts from Wikipedia) and less well using the Genia corpus (a standard life science corpus). This indicates that choice and design of corpus has a major impact on the evaluation of term recognition algorithms. Our experiments also showed that single-word terms can be equally important and occupy a fairly large proportion in certain domains. As a result, algorithms that ignore single-word terms may cause problems to tasks built on top of ATR. Effective ATR systems also need to take into account both the unstructured text and the structured aspects and this means information extraction techniques need to be integrated into the term recognition process.

Evidence for sensitisation of DNA to oxidative damage during isolation

The oxidative base lesion 8-oxo-deoxyguanosine (8-oxo-dG) has been identified in DNA isolated from normal tissue and may occur at elevated levels during disease. However, the use of phenol during DNA extraction may artificially elevate the detected levels of this lesion. Herein, we have performed a comparative methodological study using both pronase E and phenol extraction techniques; native or oxidatively stressed DNA was isolated to determine the validity of each extraction technique for the subsequent determination of 8-oxo-dG. Whilst the yields of DNA were comparable, after pronase E extraction there was no detectable induction of 8-oxo-dG in reextracted naked DNA or peripheral blood mononuclear cell DNA that had been oxidatively stressed. However, phenol extraction enhanced the basal levels of 8-oxo-dG detected, and also induced a significant increase in levels of the modified base after exposure to oxidative stress. The latter was dependent on the presence of foetal calf serum in the extracellular medium. We have confirmed that phenol extraction sensitises native DNA to subsequent oxidative damage. In addition, this work shows that the extent of sensitisation occurring during phenol extraction varies with the degree of oxidative damage already incurred and infers that labile guanine sites generated during oxidative stress may be detected as 8-oxo-dG residues after phenol extraction.

Sensitivity and reliability of objective image analysis compared to subjective grading of bulbar hyperaemia

Aims: To establish the sensitivity and reliability of objective image analysis in direct comparison with subjective grading of bulbar hyperaemia. Methods: Images of the same eyes were captured with a range of bulbar hyperaemia caused by vasodilation. The progression was recorded and 45 images extracted. The images were objectively analysed on 14 occasions using previously validated edge-detection and colour-extraction techniques. They were also graded by 14 eye-care practitioners (ECPs) and 14 non-clinicians (NCb) using the Efron scale. Six ECPs repeated the grading on three separate occasions Results: Subjective grading was only able to differentiate images with differences in grade of 0.70-1.03 Efron units (sensitivity of 0.30-0.53), compared to 0,02-0.09 Efron units with objective techniques (sensitivity of 0.94-0.99). Significant differences were found between ECPs and individual repeats were also inconsistent (p<0.001). Objective analysis was 16x more reliable than subjective analysis. The NCLs used wider ranges of the scale but were more variable than ECPs, implying that training may have an effect on grading. Conclusions: Objective analysis may offer a new gold standard in anterior ocular examination, and should be developed further as a clinical research tool to allow more highly powered analysis, and to enhance the clinical monitoring of anterior eye disease.

The effect of digital image resolution and compression on anterior eye imaging

Aim: To determine the theoretical and clinical minimum image pixel resolution and maximum compression appropriate for anterior eye image storage. Methods: Clinical images of the bulbar conjunctiva, palpebral conjunctiva, and corneal staining were taken at the maximum resolution of Nikon:CoolPix990 (2048 × 1360 pixels), DVC:1312C (1280 × 811), and JAI:CV-S3200 (767 × 569) single chip cameras and the JVC:KYF58 (767 × 569) three chip camera. The images were stored in TIFF format and further copies created with reduced resolution or compressed. The images were then ranked for clarity on a 15 inch monitor (resolution 1280 × 1024) by 20 optometrists and analysed by objective image analysis grading. Theoretical calculation of the resolution necessary to detect the smallest objects of clinical interest was also conducted. Results: Theoretical calculation suggested that the minimum resolution should be ≥579 horizontal pixels at 25 × magnification. Image quality was perceived subjectively as being reduced when the pixel resolution was lower than 767 × 569 (p<0.005) or the image was compressed as a BMP or <50% quality JPEG (p<0.005). Objective image analysis techniques were less susceptible to changes in image quality, particularly when using colour extraction techniques. Conclusion: It is appropriate to store anterior eye images at between 1280 × 811 and 767 × 569 pixel resolution and at up to 1:70 JPEG compression.

Accent Recognition for Noisy Audio Signals

It is well established that accent recognition can be as accurate as up to 95% when the signals are noise-free, using feature extraction techniques such as mel-frequency cepstral coefficients and binary classifiers such as discriminant analysis, support vector machine and k-nearest neighbors. In this paper, we demonstrate that the predictive performance can be reduced by as much as 15% when the signals are noisy. Specifically, in this paper we perturb the signals with different levels of white noise, and as the noise become stronger, the out-of-sample predictive performance deteriorates from 95% to 80%, although the in-sample prediction gives overly-optimistic results. ACM Computing Classification System (1998): C.3, C.5.1, H.1.2, H.2.4., G.3.

Obtenção de concentrado proteico do farelo de arroz e avaliação das propriedades químicas e funcionais

Esta dissertação é composta por 5 artigos.

Viabilidade do biodiesel de microalgas: otimização de técnicas de extração

Os problemas relacionados com o consumo energético e as emissões de poluentes relativas ao setor dos transportes representam seguramente a maior preocupação ao nível Europeu no que respeita aos gases com efeito de estufa e à poluição atmosférica. Uma das formas de resolver/minimizar estes problemas é através da aposta em combustíveis alternativos. Em particular, os biocombustíveis poderão ser uma alternativa interessante aos combustíveis convencionais. As microalgas, como matéria-prima para produção de biodiesel, apresentam-se com excelentes perspetivas de futuro e com vantagens competitivas no campo das energias renováveis. É nesta perspetiva que se enquadra o presente trabalho, cujos objetivos consistiram na extração de biodiesel a partir de microalgas secas (Nannochloropsis gaditana e Scenedesmus sp.) e na otimização das respetivas técnicas de extração lipídica. Verificou-se que, em função dos métodos e condições utilizadas, a espécie Nannochloropsis gaditana apresenta um potencial de produção de biodiesel superior à espécie Scenedesmus sp. (eficiências de extração de 24,6 (wt.%) e 9,4 (wt.%) respetivamente). Um método de rotura celular conjugado com o processo de extração lipídica via solvente orgânico é essencial, pois conseguiu-se um acréscimo de 42% no rendimento de extração, sendo 10 minutos o tempo ideal de operação. Solventes como o metanol e sistema de solventes diclorometano/metanol mostraram ser mais eficazes quando se pretende extrair lípidos de microalgas, com valores de eficiência de remoção de 30,9 (wt.%) e 23,2 (wt.%) respetivamente. De forma a valorizar os resultados obtidos no processo de extração recorreu-se à sua conversão em biodiesel através da transesterificação catalítica ácida, onde se obteve uma eficiência de conversão de 17,8 (wt.%) para a espécie Nannochloropsis gaditana.

Investigation of properties affecting controlled release of macromolecules from PLGA microspheres

Poly(lactide-co-glycolide), or PLGA, microspheres offer a widely-studied biodegradable option for controlled release of therapeutics. An array of fabrication methodologies have been developed to produce these microspheres with the capacity to encapsulate therapeutics of various types; and produce microspheres of a wide range of sizes for different methods of delivery. The encapsulation, stability, and release profiles of therapeutic release based on physical and thermodynamic properties has also been studied and modeled to an extent. Much research has been devoted to tailoring formulations for improved therapeutic encapsulation and stability as well as selective release profiles. Despite the breadth of available research on PLGA microspheres, further analysis of fundamental principles regarding the microsphere degradation, formation, and therapeutic encapsulation is necessary. This work aims to examine additional fundamental principles related to PLGA microsphere formation and degradation from solvent-evaporation of preformed polymer. In particular, mapping the development of the acidic microenvironment inside the microsphere during degradation and erosion is discussed. Also, the effect of macromolecule size and conformation is examined with respect to microsphere diameter and PLGA molecular weight. Lastly, the effects of mechanical shearing and protein exposure to aqueous media during microsphere formation are examined. In an effort to better understand the acidic microenvironment development across the microsphere diameter, pH sensitive dye conjugated to protein that undergoes conformational change at different acidic pH values was encapsulated in PLGA microspheres of diameters ranging from 40 µm to 80 µm, and used in conjunction with fluorescence resonance energy transfer to measure the radial pH change in the microspheres. Qualitative analysis of confocal micrographs was used to correlate fluorescence intensity with pH value, and obtain the radial pH across the center of the microsphere. Therapeutic encapsulation and release from polymeric microspheres is governed by an interconnected variety of factors, including the therapeutic itself. The globular protein bovine serum albumin, and the elongated and significantly smaller enzyme, lysozyme, were encapsulated in PLGA microspheres ranging from 40 µm to 80 µm in diameter. The initial surface morphology upon microsphere formation, release profiles, and microsphere erosion characteristics were explored in an effort to better understand the effect of protein size, conformation, and known PLGA interaction on the formation and degradation of PLGA microspheres and macromolecule release, with respect to PLGA molecular weight and microsphere diameter. In addition to PLGA behavior and macromolecule behavior, the effect of mechanical stresses during fabrication was examined. Two similar solvent extraction techniques were compared for the fabrication of albumin loaded microspheres. In particular, the homogeneity of the microspheres as well as capacity to retain encapsulated albumin were compared. This preliminary study paves the way for a more rigorous treatment of the effect of mechanical forces present in popular microsphere fabrication. Several factors affecting protein release from PLGA microspheres are examined herein. The technique explored for spatial resolution of the pH inside the microsphere proved mildly effective in producing a reliable method of mapping microsphere pH changes. However, notable trends with respect to microsphere size, PLGA molecular weight, and microsphere porosity were observed. Proposed methods of improving spatial resolution of the acidic microenvironment are also provided. With respect to microsphere formation, studies showed that albumin and lysozyme had little effect on the internal homogeneity of the microsphere. Rather, ionic interactions with PLGA played a more significant role in the encapsulation and release of each macromolecule. Studies also showed that higher instances of mechanical stress led to less homogeneous microspheres with lower protein encapsulation. This suggests that perhaps instead of or in addition to modifying the microsphere formation formulation, the fabrication technique itself should be more closely considered in achieving homogeneous microspheres with desired loading.

Bioactive compounds through anaerobic digestion of heterotrophic microalgae residues

Several important biomolecules are available into anaerobically digested effluents that were obtained from the biodiesel production process using heterotrophically grown microalga Chlorella protothecoides. Defatted microalgae residues and crude glycerol may undergo anaerobic digestion, separately and in admixture, providing methane/hydrogen and a digestate exploitable for agriculture applications. Furthermore, industrial interesting bioactive compounds such as polyphenols provided with antioxidant activity can be obtained. Anaerobic process offers a promising chance and can be advantageously combined with algae lipid-extraction techniques in order to make it more sustainable.

Desenvolvimento de um aditivo natural à base de catequina: otimização da extração e estabilização a partir de frutos de Arbutus unedo L.

The common Mediterranean ornamental strawberry-tree (Arbutus unedo L.) produces an edible reddish sweet berry that is found to be bland and tasteless unless it is consumed overripe, otherwise it is discarded or used as basic agricultural sub residue. The bioactive properties of this fruit have been reported and related with phenolic compounds, mainly flavan-3-ols, such as catechin and procyanidins, which has opened the opportunity to exploit their extraction from alternative sources.The common Mediterranean ornamental strawberry-tree (Arbutus unedo L.) produces an edible reddish sweet berry that is found to be bland and tasteless unless it is consumed overripe, otherwise it is discarded or used as basic agricultural sub residue. The bioactive properties of this fruit have been reported and related with phenolic compounds, mainly flavan-3-ols, such as catechin and procyanidins, which has opened the opportunity to exploit their extraction from alternative sources. This study compares and optimizes the maceration, microwave and ultrasound extraction techniques in the recovery of a catechin extract from Arbutus unedo L. fruits and evaluate the stability of flavan-3-ols during storage and application processes. To obtain conditions that maximize the catechin extraction yield, a response surface methodology was used. Maceration and microwave extractions were found to be the most effective methods, capable of yielding 1.38±0.1 and 1.70±0.3 mg of catechin/g dry weight (dw) in the corresponding optimal extraction conditions. The optimal conditions for maceration were 93.2±3.7 min, 79.6±5.2 ºC and 23.1±3.7 % of ethanol, while for the microwave extraction were 42.2±4.1 min, 137.1±8.1 ºC and 12.1±1.1 % of ethanol. The microwave system was a quicker solution, conducting to slightly higher yields of catechin than maceration, but this one needed lower temperatures to reach similar yields. The ultrasound method was the least effective solution in terms of catechin yield extraction (0.71±0.1 mg/g at 42.4±3.6 min, 314.9±21.2 W and 40.3±3.8 %. ethanol). The stability was tested with of the catechin-enriched extract (60% flavan-3-ols and 22% catechin), obtained under the best maceration conditions, was tested. Therefore, catechin-enriched extracts were submitted to physical and chemical stability studies, considering the main affecting variables (time, temperature and pH): i) a stability study of the extracts during storage as powder system; and ii) a stability study of the extracts in simulated food environment (aqueous solution system). The measured responses were the flavan-3-ols and catechin contents, determined by HPLC-DAD, and the antioxidant activity of the extracts evaluated by hydrophilic assays. Mechanistic and phenomenological equations were used to describe the responses, and the optimal conditions for flavan-3-ols (including catechin) stability as powder extract during a month were pH= 5.4 and T= -20ºC; while its stability in aqueous solution remained during the 24 h of application at pH<4 and T<30ºC. This study compares and optimizes the maceration, microwave and ultrasound extraction techniques in the recovery of a catechin extract from Arbutus unedo L. fruits and evaluate the stability of flavan-3-ols during storage and application processes. To obtain conditions that maximize the catechin extraction yield, a response surface methodology was used. Maceration and microwave extractions were found to be the most effective methods, capable of yielding 1.38±0.1 and 1.70±0.3 mg of catechin/g dry weight (dw) in the corresponding optimal extraction conditions. The optimal conditions for maceration were 93.2±3.7 min, 79.6±5.2 ºC and 23.1±3.7 % of ethanol, while for the microwave extraction were 42.2±4.1 min, 137.1±8.1 ºC and 12.1±1.1 % of ethanol. The microwave system was a quicker solution, conducting to slightly higher yields of catechin than maceration, but this one needed lower temperatures to reach similar yields. The ultrasound method was the least effective solution in terms of catechin yield extraction (0.71±0.1 mg/g at 42.4±3.6 min, 314.9±21.2 W and 40.3±3.8 %. ethanol). The stability was tested with of the catechin-enriched extract (60% flavan-3-ols and 22% catechin), obtained under the best maceration conditions, was tested. Therefore, catechin-enriched extracts were submitted to physical and chemical stability studies, considering the main affecting variables (time, temperature and pH): i) a stability study of the extracts during storage as powder system; and ii) a stability study of the extracts in simulated food environment (aqueous solution system). The measured responses were the flavan-3-ols and catechin contents, determined by HPLC-DAD, and the antioxidant activity of the extracts evaluated by hydrophilic assays. Mechanistic and phenomenological equations were used to describe the responses, and the optimal conditions for flavan-3-ols (including catechin) stability as powder extract during a month were pH= 5.4 and T= -20ºC; while its stability in aqueous solution remained during the 24 h of application at pH<4 and T<30ºC.

Emerging technologies for recovery of value-added components from olive leaves and their applications in food/feed industries

Olive leaves are the most abundant agricultural waste source rich in polyphenolics. Due to the numerous health benefits associated with these compounds, the interest in recovering polyphenols from olive leaves has increased in the scientific community over the last decade. Recent studies have focused on improved extraction techniques and processing methods that are most suited for agro-biological industries involved in the development of nutraceutical and functional products. The major problems in olive leaves processing include bitter taste and the low stability of various phenolic compounds. Oleuropein and hydroxytyrosol are the most important phenolic compounds extracted from olive leaves. The present review highlights the importance of olive leaves, their composition, preparation methods, major phenolic compounds, and commercial applications. This review article focuses on integrating studies on olive leaf extract (OLE) pertinent to nutrition, health, and beauty. The different board categories of delivery systems available for the encapsulation of OLE are given. These novel delivery systems could improve fortification, supplementation, and dietary diversification in food and pharmaceutical products.

Mathematical model and rule extraction for tool wear monitoring problem using nature inspired techniques

In this paper, pattern classification problem in tool wear monitoring is solved using nature inspired techniques such as Genetic Programming(GP) and Ant-Miner (AM). The main advantage of GP and AM is their ability to learn the underlying data relationships and express them in the form of mathematical equation or simple rules. The extraction of knowledge from the training data set using GP and AM are in the form of Genetic Programming Classifier Expression (GPCE) and rules respectively. The GPCE and AM extracted rules are then applied to set of data in the testing/validation set to obtain the classification accuracy. A major attraction in GP evolved GPCE and AM based classification is the possibility of obtaining an expert system like rules that can be directly applied subsequently by the user in his/her application. The performance of the data classification using GP and AM is as good as the classification accuracy obtained in the earlier study.