Humans engage with a variety of symbols in daily life. Perhaps the most common symbol form is language where we represent myriad concepts, ideas, and notions through strings of sounds and letters. Human communication is also facilitated through other non-verbal symbol modalities ranging from body language/gestures (e.g., crossed arms, thumbs up) to objects (clothing as an indication of social status), and signs (red octagon means stop). Child language research has explored symbolic cognition and its emergence in development, but fundamental questions remain regarding symbolic thinking in adulthood and the impact a symbolic deficit can have on communication. A novel, neurologically-constrained model of symbolic representation is proposed and investigated which aims to addresses open challenges in exploring symbolic cognition. In Chapter 1, SymCog, a novel toolkit to evaluate symbolic representation is developed and normed in a series of three studies. This toolkit and its task, the Symbol Identification Task, are premised upon matching animated video depictions of abstract concepts to their corresponding verbal and non-verbal symbols. Results showed individuals can consistently match different symbol modalities (words, images) to shared concept animations. Chapter 2 assesses performance in the Symbol Identification Task in neurotypical adults receiving inhibitory brain stimulation [i.e., transcranial direct current stimulation (tDCS) of the temporoparietal junction]. Chapter 3 evaluates two cases of persons with aphasia (PWA) in the same task. The goal of these studies was to isolate the neurological-constraints of the model and identify how symbol processing can be impaired. Findings showed reduced performance in the inhibitory stimulation group; highlighting the role of the temporoparietal junction in symbol processing. Results from PWA revealed one case had poor performance across both word and image symbol modalities. Chapter 4 further investigates neurological constraints of the model in an EEG/ERP study. This study assessed N400 deflections during a modified Symbol Identification Task, where frontal-central electrodes were most active. Taken together, these chapter findings suggested two cortical regions potentially support symbolic cognition, including the temporoparietal junction and left central frontal cortex. The results also suggest that impairments in one symbol modality (e.g., words in aphasia) might also present in other modalities for shared concepts. These studies offer insights regarding the cognitive mechanisms involved in symbolic cognition and how they can be impaired. With the use of contemporary tools, such as the SymCog toolkit, future research can better recognize the human capacity to understand and use symbols. / Communication Sciences

Le traitement et l’analyse d’images angiographiques rotationnelles 3D (3DRA) de haute résolution spatiale pour l’aide à la planification d’interventions en neuroradiologie interventionnelle est un domaine de recherche récent et en plein essor. Les neuroradiologues ont besoin d’outils interactifs pour la planification des procédures d’embolisation et l’optimisation du guidage de microcathéters durant les interventions endovasculaires. L’exploitation des données d’imagerie pour l’aide au diagnostic et la thérapeutique requiert le développement d’algorithmes robustes et de méthodes efficaces. Ces méthodes permettent d’intégrer les informations contenues dans ces images pour en extraire des descripteurs anatomiques utiles durant les phases pre et per-opératoires.Cette thèse est dédiée au développement d’une chaine de traitement complète comprenant la segmentation, la reconstruction tridimensionnelle (3D) et la représentation symbolique de vaisseaux cérébraux à partir d’images 3DRA, pour faciliter la planification d’interventions d’embolisation pour le traitement de Malformations ArtérioVeineuses cérébrales (MAVs).La première partie du travail est consacrée à l’étude des différentes approches utilisées en segmentation des vaisseaux. Deux méthodes de segmentation sont ensuite proposées. Tout d’abord, une méthode de segmentation 2D coupe par coupe est développée ainsi qu’un technique robuste de suivi de vaisseaux permettant de détecter les bifurcations et de poursuivre le tracking de plusieurs branches du même vaisseau. Un maillage basé sur la triangulation Contrainte de Delaunay permet ensuite la reconstruction et la visualisation 3D des vaisseaux ainsi obtenus. Une méthode de segmentation 3D automatisée des images 3DRA est ensuite développée, elle présente l’avantage d’être plus rapide et de traiter le volume d’images entier en 3D. Cette méthode est basée sur la croissance de régions. Le processus 3D démarre à partir d’une coupe initiale pré-segmentée en utilisant la reconstruction géodésique et sur laquelle les germes sont placés de manière automatique. Finalement, une représentation du réseau vasculaire sur laquelle on distingue clairement les trois entités que sont les artères, les veines drainantes et le nidus est obtenue.La deuxième partie de la thèse est consacrée à la représentation symbolique des vaisseaux. L'étude hiérarchique du squelette permet de donner une description graphique du réseau vasculaire cérébral. A partir de cette description graphique, les vaisseaux et leurs branches sont labellisés et un ou plusieurs vaisseaux peuvent être isolés du reste du réseau pour une analyse visuelle plus précise, ce qui n’est pas possible avec les reconstructions 3D du constructeur. De plus, cette représentation améliore la détermination des chemins optimaux pour l’embolisation de la MAV et réduit la complexité due à l’enchevêtrement des vaisseaux malformés.La chaine de traitement complète ainsi développée aboutit à une description 3D précise des vaisseaux. Elle permet une meilleure compréhension structurelle du réseau vasculaire cérébral et offre aux neuroradiologues la possibilité d’extraire des descripteurs anatomiques, et géométriques (taille, diamètre…) des vaisseaux. Enfin, une étape de vérification des résultats par un expert neuroradiologue a permis la validation clinique des résultats de segmentation et de reconstruction 3D. L’intégration des algorithmes développés dans une interface graphique intuitive et facile d’utilisation devra être faite pour permettre l’exploitation de nos résultats en routine clinique / The processing and analysis of 3D Rotational Angiographic images (3DRA) of high spatial resolution to facilitate intervention planning in interventional neuroradiology is a new and booming research area. Neuroradiologists need interactive tools for the planning of embolization procedures and the optimization of the guidance of micro-catheters during endovascular interventions. The exploitation of imaging data to help in diagnosis and treatment requires the development of robust algorithms and efficient methods. These methods allow integrating information included in these images in order to extract useful anatomical descriptors during preoperative and peroperative phases.This thesis is dedicated to the development of a complete processing pipeline including segmentation, three-dimensional (3D) reconstruction and symbolic representation of cerebral vessels from 3DRA images, aiming to facilitate the embolization intervention planning for the treatment of cerebral ArterioVenous Malformations (AVMs).The first part of the work is devoted to the study of the different approaches used for the segmentation of vessels. Two segmentation methods are then proposed. First, a 2D slice-by-slice segmentation method is developed, followed by a robust vessel tracking process that enables detecting bifurcations and further following several branches of the same vessel. A mesh based on the Constrained Delaunay triangulation allows then the 3D reconstruction and visualization of the obtained vessels. An automated 3D segmentation method of 3DRA images is then developed, which presents the advantage of being faster and processing the whole 3D volume of images. This method is region growing based. The 3D process starts from an initial pre-segmented slice using the geodesic reconstruction, where the seeds are automatically placed. Finally, a representation of the vasculature is obtained, in which these three entities are clearly visible: the feeding arteries, the draining veins and the nidus.The second part of the thesis is devoted to the symbolic representation of the vessels. The hierarchical study of the skeleton allows giving a graphic description of the cerebral vascular network. From this graphic description, the vessels and their branches are labeled and one or more vessels can be isolated from the rest of network for a more accurate visual analysis, which is not possible with the original 3D reconstructions. Moreover, this improves the determination of the optimal paths for the AVM embolization and reduces the complexity due to the entanglement of the malformed vessels.The complete processing pipeline thus developed leads to a precise 3D description of the vessels. It allows a better understanding of the cerebral vascular network structure and provides the possibility to neuroradiologists of extracting anatomical and geometric descriptors (size, diameter...) of the vessels. Finally, a verification step of the results by a neuroradiology expert enabled clinical validation of the 3D segmentation and reconstruction results. The integration of the developed algorithms in a user-friendly graphical interface should be achieved to allow the exploitation of our results in clinical routine

With the highest representation of female parliamentarians in the world, Rwanda is a frequently reoccurring case when studying the impact of increased female representation. In this debate, little attention has been given to symbolic representation and particularly to the concept of the Role Model Effect. To bridge this gap, the purpose is to provide insights to how the Role Model Effect operates in a rural, non-quota context, separated from high politics. Consequently, the thesis seeks to examine how female board members in Rwandan agricultural cooperatives affect the willingness of female members to obtain board positions. The data was collected through a qualitative field study where 44 respondents in three different cooperatives in Rwanda were interviewed. Respondents were chosen through a combination of strategic selection and snowball sampling. The thesis found that the Role Model Effect required two conditions to be fulfilled before it could be manifested: geographical proximity and trust. If these criteria were met, both female board members and female leaders of lower ranks were found to explicitly and implicitly increase the willingness to obtain leading positions among female members, thus altering ruling gender roles.

This dissertation is a study of methods to automatedly detect and produce approximations of eddy current differential coil defect signatures in terms of a summed collection of Gaussian functions (SoG). Datasets consisting of varying material, defect size, inspection frequency, and coil diameter were investigated. Dimensionally reduced representations of the defect responses were obtained utilizing common existing reduction methods and novel enhancements to them utilizing SoG Representations. Efficacy of the SoG enhanced representations were studied utilizing common Machine Learning (ML) interpretable classifier designs with the SoG representations indicating significant improvement of common analysis metrics.

Mathematics textbooks are by far the most commonly used didactic tool in classroom teaching. Currently, there is very limited research into how teacher guides, accompanying these textbooks, support the teacher’s work in the classroom. The purpose of the study was to examine to what extent teacher guides support and guide teacher in teaching mathematics. Question raised by the study was – how are variation and concretization addressed in the teacher guides? Variation theory directs focus to critical aspects of the object of learning and can be used as basis to evaluate teacher guides. Concepts like variation and concretization have been useful tools when analysing the teacher guides. To support the study’s phenomenographical approach, a coding system was developed and used as a tool in analysis. Developing the coding system was critical in order to compare the four teacher guides, as well as for the reliability and validity of the study. Data were collected from four, first grade teacher guides in mathematics. An analysis covering an overall perspective has been performed. Several specific topics have also been analysed in a more inductive approach. The results indicate that teacher guides, anchored in the Swedish curricula in mathematics, do not support teachers in how to move from concrete learning to abstract learning. Critical details are being omitted which might affect the goal of abstract thinking.

Cette thèse appréhende des questions scientifiques d'un point de vue de la data science, dans le cadre de l'analyse des séries temporelles issues de la locomotion en fauteuil roulant manuel (FRM). Compression et classification des séries temporelles à l'aide de DTW : l'algorithme Dynamic Time Warping (DTW) est souvent utilisé car il permet d'éviter de petites distorsions entre les séries temporelles au cours de leur alignement. Cependant, DTW produit parfois des alignements pathologiques qui se produisent, lorsque au cours de la comparaison de deux séries temporelles X et Y, un point de données de la série temporelle X est comparé à une grande sous-séquence de Y. Nous démontrons que la compression de séries temporelles à l'aide de l'approximation par morceaux (Piecewise Aggregate Approximation) (PAA) augmente considérablement la qualité de l'alignement avec DTW. Classification non supervisée de séries temporelles basée sur la distance Frobenius : Un shapelet non supervisé (U-shapelet) est une sous-séquence d'une série temporelle utilisée pour segmenter un jeu de données. Notre but est de découvrir des u-shapelets sur des séries temporelles incertaines. Pour ce faire, nous proposons un score de dissimilarité robuste à l'incertitude appelé FOTS dont le calcul est basé sur la décomposition en vecteurs propres et la comparaison des matrices d'autocorrélation de la série temporelle. Ce score est robuste à la présence d'incertitude ; il n'est pas très sensible aux changements transitoires ; il permet de saisir des relations complexes entre des séries temporelles telles que les oscillations et les tendances, et il est également bien adapté à la comparaison de séries temporelles courtes. Le score FOTS a été utilisé avec l'algorithme Scalable Unsupervised Shapelet Discovery pour le clustering de 17 jeux de données, et il a montré une amélioration substantielle de la qualité du clustering par rapport à l'indice Rand. Représentation symbolique de série temporelles cycliques basée sur les propriétés des cycliques : L'analyse des séries temporelles cycliques de la biomécanique est basée sur la comparaison des propriétés de leurs cycles. En général, les algorithmes de fouille de données ignorent cette particularité, nous proposons une représentation symbolique des séries temporelles cycliques basées sur les propriétés de cycles, appelés SAX-P. Les chaînes de caractères résultantes peuvent être comparées en utilisant la distance de distorsion temporelle dynamique (DTW). L'application de SAX-P aux moments propulsifs de trois sujets (S1, S2, S3) se déplaçant en FRM a mis en évidence de caractère asymétrique de leur propulsion. La représentation symbolique SAX-P facilite l'interprétation clinique des résultats de classification. / This thesis addresses scientific issues from a data science perspective as part of the analysis of time series from manual wheelchair locomotion (FRM).Compression and classification with Dynamic Time Warping: Dyna- mic Time Warping (DTW) is a time series alignment algorithm that is often used because it considers that it exits small distortions between time series during their alignment. However, DTW sometimes produces pathological alignments that occur when, during the comparison of two time series X and Y, one data point of the time series X is compared to a large subsequence of data points of Y. In this chapter, we demonstrate that compressing time series using Piecewise Aggregate Approximation (PAA) is a simple strategy that greatly increases the quality of the alignment with DTW. This result is particularly true for synthetic data sets.Frobenius correlation based u-shapelets discovery for time series clustering: An unsupervised shapelet (u-shapelet) is a sub-sequence of a time series used for clustering a time series dataset. The purpose of this chapter is to discover u-shapelets on uncertain time series. To achieve this goal, we propose a dissimilarity score robust to uncertainty called FOTS whose computation is based on the eigen- vector decomposition and the comparison of the autocorrelation matrices of the time series. This score is robust to the presence of uncertainty; it is not very sensitive to transient changes; it allows capturing complex relationships between time series such as oscillations and trends, and it is also well adapted to the comparison of short time series. The FOTS score has been used with the Scalable Unsupervised Shapelet Discovery algorithm for the clustering of 17 datasets, and it has shown a substantial improvement in the quality of clustering with respect to the Rand Index. This work defines a novel framework for clustering of uncertain time series.Symbolic representation of cyclic time series based on properties of cycles: The analysis of cyclic time series from bio-mechanics is based on the comparison of the properties of their cycles. As usual algorithms of time series classification ignore this particularity, we propose a symbolic representation of cyclic time series based on the properties of cycles, named SAX-P. The resulting character strings can be compared using the Dynamic Time Warping distance. The application of SAX-P to propulsive moments of three subjects (S1, S2, S3) moving in Manual Wheelchair highlight the asymmetry of their propulsion. The symbolic representation SAX-P facilitates the reading of the cyclic time series and the clinical interpretation of the classification results.

Submitted by Maike Costa (maiksebas@gmail.com) on 2016-02-16T14:06:13Z No. of bitstreams: 1 arquivototal.pdf: 3923588 bytes, checksum: decb7a3c36ae3a6e9488321eb846455a (MD5) / Made available in DSpace on 2016-02-16T14:06:13Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 3923588 bytes, checksum: decb7a3c36ae3a6e9488321eb846455a (MD5) Previous issue date: 2015-06-26 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Prior to the invention of writing, the image was a means of communication which contributed to the expression of social relations, to the culture and ideology of the age. With the „development‟ of civilization, the image lost its natural character, which led to the configuration of a new system of symbols, from the ideogram to the rise of the alphabet, bringing about a break in the communication through images. However, with the advent of post-modernity and the advance of media culture a new concept has been established in society, a concept marked by the symbolic and by the proliferation of the image. Given the range of the theme „image‟ in the various fields of science, we delimit our analysis in terms of the religious imagination and the images contained in Teaching Manuals used in Religious Education (TMRE) from the platform of Gilbert Durand‟s symbolical hermeneutics. In this vein the research concentrated, initially, on enumerating certain theoretical presuppositions which guide and sustain the analysis undertaken with a view to strengthening its relevance in relation to the triad of the „religious imagination‟, the visual image and the teaching manual. The aim is to consolidate and collaborate with the development of research on religious symbolic representation, bearing in mind the thematic issue of the visual image in TMRE, in order to use it critically and creatively in educative spaces in schools. The findings of this research point to the guaranteed presence of the visual image in TMRE, above all in the genres of drawing, painting, photography and info-imagery, with the hegemony of photography. While the treatment of the image as an object of knowledge is outlined, therefore, as a codifier of religious symbolic representations, the predominant pedagogical use is illustrative. The general configuration of TMRE was structured on the basis of imaginary representation in the mystical-religious form, set within a theological and messianic conception of religion. / Antes do surgimento da escrita, a imagem era um meio de comunicação que contribuía para expressar as relações sociais, a cultura e a ideologia da época. Com o “desenvolvimento” da civilização, ela perdeu seu caráter natural, o que levou à configuração de um novo sistema de símbolos, desde o ideograma até o surgimento do alfabeto, que acarretou o rompimento com as comunicações de natureza imagética. Todavia, o advento da pós-modernidade e o avanço da cultura midiática estabeleceram um novo conceito de sociedade, marcado pelo simbólico e pela proliferação da imagem. Devido à abrangência do tema „imagem‟, nos vários campos do conhecimento, delimitamos nossa análise em torno do imaginário religioso nas imagens contidas nos livros didáticos de Ensino Religioso (LDER), a partir da hermenêutica simbólica de Gilberto Durand. Nesse sentido, a pesquisa concentrou-se, inicialmente, em explicitar alguns pressupostos teóricos que norteiam e dão sustentação à análise empreendida, fortalecer sua relevância sobre a tríade „imaginário religioso, imagem visual e livro didático‟ e consolidar e colaborar com o desenvolvimento de pesquisas sobre as representações simbólicas religiosas, tendo em vista refletir sobre a problemática da imagem visual no LDER, a fim de utilizá-la crítica e criativamente nos espaços educativos escolares e não escolares. Os achados de pesquisa apontaram para a presença garantida da imagem visual no LDER, sobretudo nos gêneros desenho, pintura fotografia e infoimagem, com a hegemonia da fotografia. Embora seja vislumbrado o tratamento da imagem como objeto de conhecimento, portanto, codificador de representações simbólicas religiosas, o uso pedagógico predominante é o ilustrativo. A configuração geral do LDER foi estruturada a partir de uma representação imaginária de viés místico-religioso, pautado numa concepção teológica e messiânica da religião.

Made available in DSpace on 2015-05-07T15:09:59Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 2561743 bytes, checksum: c1fad1cda34ed7a4d0fe6cc0b08477fe (MD5) Previous issue date: 2010-08-20 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The thesis presents an analysis of the relation between the contents transmitted by the SpongeBob animated series and the infantile subjectivity formation using the concepts of symbolic representation, internalization and resistance based on Piaget (1978) Vygotsky (2007) and Giroux (1986) respectively. In this investigation sixty-two children, between 03 and 05 years old, took part. They were students from the Basic Education School of the Federal University of Paraíba, enrolled in the morning and afternoon shifts in 2009. The ethnographic research used the direct observation, interviews with the students and dialogues in circle before and after they watched the SpongeBob series video. The data obtained and submitted to analyses indicate that the contents, of the mentioned cartoon, intervened in the subjectivity of the infantile spectators, between 03 and 04 years old, in a proportion higher than in those who were 05 years old. Such interference is demonstrated by the preference of being the main cartoon character, adopting standardized attitudes and behaviors. Nevertheless, this does not prevent the children from adding their own meaning to the cartoon s contents. The thesis still advocates that the school education has the potential to prepare the students as concerns educating them by means of the television media, specifically, the cartoons, through the dialogue and the critical analysis; procedures adopted by the critical pedagogy. We concluded that we should integrate to school the educational studies for the television media as both a pedagogical instrument and a study object so as to promote a critical behavior in the students in regard to the media. / A tese contém uma análise da relação entre os conteúdos transmitidos pelo desenho animado Bob Esponja e a formação da subjetividade infantil utilizando os conceitos de representação simbólica, internalização e resistência, baseados em Piaget (1978) Vygotsky (2007) e Giroux (1986), respectivamente. Nesta investigação, participaram 62 crianças de 03 a 05 anos, alunos da Escola de Educação Básica da Universidade Federal da Paraíba, matriculados nos turnos manhã e tarde em 2009. A pesquisa etnográfica utilizou a observação direta, entrevistas com os alunos e rodas de conversa antes e depois que os mesmos assistiram ao vídeo do desenho animado Bob Esponja. Os dados obtidos e submetidos a análise indicam que os conteúdos do referido desenho interferiram na subjetividade dos espectadores infantis de 03 e de 04 anos, em proporção maior do que naqueles de 05 anos. Esta interferência é demonstrada pela preferência em ser o personagem principal do desenho, adotando atitudes e comportamentos padronizados, no entanto, não os impedindo de acrescentar aos conteúdos do desenho animado um sentido próprio. A tese defende ainda que a educação escolar tem potencial para capacitar os alunos no sentido de educar para mídia televisiva, especificamente os desenhos animados, através do diálogo e análise crítica, procedimentos adotados pela pedagogia crítica. Concluímos que devemos integrar à escola os estudos de educação para a mídia televisiva, como instrumento pedagógico e como objeto de estudo para que se desenvolva nos alunos uma postura crítica diante dela.

abstract: Continuous monitoring of sensor data from smart phones to identify human activities and gestures, puts a heavy load on the smart phone's power consumption. In this research study, the non-Euclidean geometry of the rich sensor data obtained from the user's smart phone is utilized to perform compressive analysis and efficient classification of human activities by employing machine learning techniques. We are interested in the generalization of classical tools for signal approximation to newer spaces, such as rotation data, which is best studied in a non-Euclidean setting, and its application to activity analysis. Attributing to the non-linear nature of the rotation data space, which involve a heavy overload on the smart phone's processor and memory as opposed to feature extraction on the Euclidean space, indexing and compaction of the acquired sensor data is performed prior to feature extraction, to reduce CPU overhead and thereby increase the lifetime of the battery with a little loss in recognition accuracy of the activities. The sensor data represented as unit quaternions, is a more intrinsic representation of the orientation of smart phone compared to Euler angles (which suffers from Gimbal lock problem) or the computationally intensive rotation matrices. Classification algorithms are employed to classify these manifold sequences in the non-Euclidean space. By performing customized indexing (using K-means algorithm) of the evolved manifold sequences before feature extraction, considerable energy savings is achieved in terms of smart phone's battery life. / Dissertation/Thesis / M.S. Electrical Engineering 2014

Submitted by Kevin Quispe (kgmq@icomp.ufam.edu.br) on 2018-10-26T19:02:31Z No. of bitstreams: 1 dissertação-kevin-quispe-final.pdf: 2744401 bytes, checksum: cf4d3337afb0d9fa244abbd4ec3d1a5a (MD5) / Approved for entry into archive by Secretaria PPGI (secretariappgi@icomp.ufam.edu.br) on 2018-10-26T19:07:43Z (GMT) No. of bitstreams: 1 dissertação-kevin-quispe-final.pdf: 2744401 bytes, checksum: cf4d3337afb0d9fa244abbd4ec3d1a5a (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-10-26T19:15:25Z (GMT) No. of bitstreams: 1 dissertação-kevin-quispe-final.pdf: 2744401 bytes, checksum: cf4d3337afb0d9fa244abbd4ec3d1a5a (MD5) / Made available in DSpace on 2018-10-26T19:15:25Z (GMT). No. of bitstreams: 1 dissertação-kevin-quispe-final.pdf: 2744401 bytes, checksum: cf4d3337afb0d9fa244abbd4ec3d1a5a (MD5) Previous issue date: 2018-08-14 / Human activity recognition (RAH) through sensors embedded in wearable devices such as smartphones has allowed the development of solutions capable of monitoring human behavior. However, such solutions have presented limitations in terms of efficiency in the consumption of computational resources and generalization for different application or data domain configurations. These limitations are explored in this work in the feature extraction process, in which existing solutions use a manual approach to extract the characteristics of the sensor data. To overcome the problem, this work presents an automatic approach to feature extraction based on the symbolic representation of time series --- representation defined by sets of discrete symbols (words). In this context, this work presents an extension of the symbolic representation of the Bag-Of-SFA-Symbols (BOSS) method to handle the processing of multiple time series, reduce data dimensionality and generate compact and efficient classification models. The proposed method, called Multivariate Bag-Of-SFA-Symbols (MBOSS), is evaluated for the classification of physical activities from data of inertial sensors. Experiments are conducted in three public databases and for different experimental configurations. In addition, the efficiency of the method is evaluated in aspects such as computing time and data space. The results, in general, show an efficiency of classification equivalent to the solutions based on the traditional approach of manual extraction, highlighting the results obtained in the database with nine classes of activities (UniMib SHAR), where MBOSS obtained an accuracy of 99% and 87% for the custom and generalized template, respectively. The efficiency results of MBOSS demonstrate the low computational cost of the solution and show the feasibility of application in smartphones. / O reconhecimento de atividade humanas (RAH) por meio de sensores embutidos em dispositivos vestíveis como, por exemplo, smartphones tem permitido o desenvolvimento de soluções capazes de monitorar o comportamento humano. No entanto, tais soluções têm apresentado limitações em termos de eficiência no consumo dos recursos computacionais e na generalização para diferentes configurações de aplicação ou domínio de dados. Essas limitações são exploradas neste trabalho no processo de extração de características, na qual as soluções existentes utilizam uma abordagem manual para extrair as características dos dados de sensores. Para superar o problema, este trabalho apresenta uma abordagem automática de extração de características baseada na representação simbólica de séries temporais --- representação definida por conjuntos de símbolos discretos (palavras). Nesse contexto, este trabalho apresenta uma extensão do método de representação simbólica Bag-Of-SFA-Symbols (BOSS) para lidar com o processamento de múltiplas séries temporais, reduzir a dimensionalidade dos dados e gerar modelos de classificação compactos e eficiêntes. O método proposto, denominado Multivariate Bag-Of-SFA-Symbols (MBOSS), é avaliado para a classificação de atividades físicas a partir de dados de sensores inerciais. Experimentos são conduzidos em três bases de dados públicas e para diferentes configurações experimentais. Além disso, avalia-se a eficiência do método em aspectos como tempo de computação e espaço de dados. Os resultados, em geral, demostram uma eficácia de classificação equivalente as soluções baseadas na abordagem comun de extração manual de características, destacando os resultados obtidos na base de dados com nove classes de atividades (UniMib SHAR), onde o MBOSS obteve uma acurácia de 99% e 87% para o modelo personalizado e generalizado, respectivamente. Os resultados de eficiência do MBOSS demostram o baixo custo computacional da solução e mostram a viabilidade de aplicação em smartphones.