|
Mariella Dimiccoli. (2016). Fundamentals of cone regression. Journal of Statistics Surveys, 53–99.
Abstract: Cone regression is a particular case of quadratic programming that minimizes a weighted sum of squared residuals under a set of linear inequality constraints. Several important statistical problems such as isotonic, concave regression or ANOVA under partial orderings, just to name a few, can be considered as particular instances of the cone regression problem. Given its relevance in Statistics, this paper aims to address the fundamentals of cone regression from a theoretical and practical point of view. Several formulations of the cone regression problem are considered and, focusing on the particular case of concave regression as an example, several algorithms are analyzed and compared both qualitatively and quantitatively through numerical simulations. Several improvements to enhance numerical stability and bound the computational cost are proposed. For each analyzed algorithm, the pseudo-code and its corresponding code in Matlab are provided. The results from this study demonstrate that the choice of the optimization approach strongly impacts the numerical performances. It is also shown that methods are not currently available to solve efficiently cone regression problems with large dimension (more than many thousands of points). We suggest further research to fill this gap by exploiting and adapting classical multi-scale strategy to compute an approximate solution.
Keywords: cone regression; linear complementarity problems; proximal operators.
|
|
|
Maria Salamo, Inmaculada Rodriguez, Maite Lopez, Anna Puig, Simone Balocco, & Mariona Taule. (2016). Recurso docente para la atención de la diversidad en el aula mediante la predicción de notas. ReVision.
Abstract: Desde la implantación del Espacio Europeo de Educación Superior (EEES) en los diferentes grados, se ha puesto de manifiesto la necesidad de utilizar diversos mecanismos que permitan tratar la diversidad en el aula, evaluando automáticamente y proporcionando una retroalimentación rápida tanto al alumnado como al profesorado sobre la evolución de los alumnos en una asignatura. En este artículo se presenta la evaluación de la exactitud en las predicciones de GRADEFORESEER, un recurso docente para la predicción de notas basado en técnicas de aprendizaje automático que permite evaluar la evolución del alumnado y estimar su nota final al terminar el curso. Este recurso se ha complementado con una interfaz de usuario para el profesorado que puede ser usada en diferentes plataformas software (sistemas operativos) y en cualquier asignatura de un grado en la que se utilice evaluación continuada. Además de la descripción del recurso, este artículo presenta los resultados obtenidos al aplicar el sistema de predicción en cuatro asignaturas de disciplinas distintas: Programación I (PI), Diseño de Software (DSW) del grado de Ingeniería Informática, Tecnologías de la Información y la Comunicación (TIC) del grado de Lingüística y la asignatura Fundamentos de Tecnología (FDT) del grado de Información y Documentación, todas ellas impartidas en la Universidad de Barcelona.
La capacidad predictiva se ha evaluado de forma binaria (aprueba o no) y según un criterio de rango (suspenso, aprobado, notable o sobresaliente), obteniendo mejores predicciones en los resultados evaluados de forma binaria.
Keywords: Aprendizaje automatico; Sistema de prediccion de notas; Herramienta docente
|
|
|
Marc Sunset Perez, Marc Comino Trinidad, Dimosthenis Karatzas, Antonio Chica Calaf, & Pere Pau Vazquez Alcocer. (2016). Development of general‐purpose projection‐based augmented reality systems. IADIs - IADIs international journal on computer science and information systems, 1–18.
Abstract: Despite the large amount of methods and applications of augmented reality, there is little homogenizatio n on the software platforms that support them. An exception may be the low level control software that is provided by some high profile vendors such as Qualcomm and Metaio. However, these provide fine grain modules for e.g. element tracking. We are more co ncerned on the application framework, that includes the control of the devices working together for the development of the AR experience. In this paper we describe the development of a software framework for AR setups. We concentrate on the modular design of the framework, but also on some hard problems such as the calibration stage, crucial for projection – based AR. The developed framework is suitable and has been tested in AR applications using camera – projector pairs, for both fixed and nomadic setups
|
|
|
Alicia Fornes, Josep Llados, Oriol Ramos Terrades, & Marçal Rusiñol. (2016). La Visió per Computador com a Eina per a la Interpretació Automàtica de Fonts Documentals. Lligall, Revista Catalana d'Arxivística, 20–46.
|
|
|
Mireia Sole, Joan Blanco, Debora Gil, G. Fonseka, Richard Frodsham, Francesca Vidal, et al. (2017). Noves perspectives en l estudi de la territorialitat cromosomica de cel·lules germinals masculines: estudis tridimensionals. JBR - Biologia de la Reproduccio, 73–78.
Abstract: In somatic cells, chromosomes occupy specific nuclear regions called chromosome territories which are involved in the
maintenance and regulation of the genome. Preliminary data in male germ cells also suggest the importance of chromosome
territoriality in cell functionality. Nevertheless, the specific characteristics of testicular tissue (presence of different
cell types with different morphological characteristics, in different stages of development and with different ploidy)
makes difficult to achieve conclusive results. In this study we have developed a methodology to approach the threedimensional
study of all chromosome territories in male germ cells from C57BL/6J mice (Mus musculus). The method
includes the following steps: i) Optimized cell fixation to obtain an optimal preservation of the three-dimensionality cell
morphology, ii) Chromosome identification by FISH (Chromoprobe Multiprobe® OctoChrome™ Murine System; Cytocell)
and confocal microscopy (TCS-SP5, Leica Microsystems), iii) Cell type identification by immunofluorescence
iv) Image analysis using Matlab scripts, v) Numerical data extraction related to chromosome features, chromosome
radial position and chromosome relative position. This methodology allows the unequivocally identification and the
analysis of the chromosome territories of all spermatogenic stages. Results will provide information about the features
that determine chromosomal position, preferred associations between chromosomes, and the relationship between chromosome
positioning and genome regulation.
|
|
|
Jordi Esquirol, Cristina Palmero, Vanessa Bayo, Miquel Angel Cos, Sergio Escalera, David Sanchez, et al. (2017). Automatic RBG-depth-pressure anthropometric analysis and individualised sleep solution prescription. JMET - Journal of Medical Engineering & Technology, 486–497.
Abstract: INTRODUCTION:
Sleep surfaces must adapt to individual somatotypic features to maintain a comfortable, convenient and healthy sleep, preventing diseases and injuries. Individually determining the most adequate rest surface can often be a complex and subjective question.
OBJECTIVES:
To design and validate an automatic multimodal somatotype determination model to automatically recommend an individually designed mattress-topper-pillow combination.
METHODS:
Design and validation of an automated prescription model for an individualised sleep system is performed through a single-image 2 D-3 D analysis and body pressure distribution, to objectively determine optimal individual sleep surfaces combining five different mattress densities, three different toppers and three cervical pillows.
RESULTS:
A final study (n = 151) and re-analysis (n = 117) defined and validated the model, showing high correlations between calculated and real data (>85% in height and body circumferences, 89.9% in weight, 80.4% in body mass index and more than 70% in morphotype categorisation).
CONCLUSIONS:
Somatotype determination model can accurately prescribe an individualised sleep solution. This can be useful for healthy people and for health centres that need to adapt sleep surfaces to people with special needs. Next steps will increase model's accuracy and analise, if this prescribed individualised sleep solution can improve sleep quantity and quality; additionally, future studies will adapt the model to mattresses with technological improvements, tailor-made production and will define interfaces for people with special needs.
|
|
|
Mireia Sole, Joan Blanco, Debora Gil, G. Fonseka, Richard Frodsham, Oliver Valero, et al. (2017). Análisis 3d de la territorialidad cromosómica en células espermatogénicas: explorando la infertilidad desde un nuevo prisma. ASEBIR - Revista Asociación para el Estudio de la Biología de la Reproducción, 105.
|
|
|
Patrick Brandao, O. Zisimopoulos, E. Mazomenos, G. Ciutib, Jorge Bernal, M. Visentini-Scarzanell, et al. (2018). Towards a computed-aided diagnosis system in colonoscopy: Automatic polyp segmentation using convolution neural networks. JMRR - Journal of Medical Robotics Research.
Abstract: Early diagnosis is essential for the successful treatment of bowel cancers including colorectal cancer (CRC) and capsule endoscopic imaging with robotic actuation can be a valuable diagnostic tool when combined with automated image analysis. We present a deep learning rooted detection and segmentation framework for recognizing lesions in colonoscopy and capsule endoscopy images. We restructure established convolution architectures, such as VGG and ResNets, by converting them into fully-connected convolution networks (FCNs), ne-tune them and study their capabilities for polyp segmentation and detection. We additionally use Shape-from-Shading (SfS) to recover depth and provide a richer representation of the tissue's structure in colonoscopy images. Depth is
incorporated into our network models as an additional input channel to the RGB information and we demonstrate that the resulting network yields improved performance. Our networks are tested on publicly available datasets and the most accurate segmentation model achieved a mean segmentation IU of 47.78% and 56.95% on the ETIS-Larib and CVC-Colon datasets, respectively. For polyp
detection, the top performing models we propose surpass the current state of the art with detection recalls superior to 90% for all datasets tested. To our knowledge, we present the rst work to use FCNs for polyp segmentation in addition to proposing a novel combination of SfS and RGB that boosts performance.
Keywords: convolutional neural networks; colonoscopy; computer aided diagnosis
|
|
|
Esmitt Ramirez, Carles Sanchez, Agnes Borras, Marta Diez-Ferrer, Antoni Rosell, & Debora Gil. (2018). BronchoX: bronchoscopy exploration software for biopsy intervention planning. HTL - Healthcare Technology Letters, 177–182.
Abstract: Virtual bronchoscopy (VB) is a non-invasive exploration tool for intervention planning and navigation of possible pulmonary lesions (PLs). A VB software involves the location of a PL and the calculation of a route, starting from the trachea, to reach it. The selection of a VB software might be a complex process, and there is no consensus in the community of medical software developers in which is the best-suited system to use or framework to choose. The authors present Bronchoscopy Exploration (BronchoX), a VB software to plan biopsy interventions that generate physician-readable instructions to reach the PLs. The authors’ solution is open source, multiplatform, and extensible for future functionalities, designed by their multidisciplinary research and development group. BronchoX is a compound of different algorithms for segmentation, visualisation, and navigation of the respiratory tract. Performed results are a focus on the test the effectiveness of their proposal as an exploration software, also to measure its accuracy as a guiding system to reach PLs. Then, 40 different virtual planning paths were created to guide physicians until distal bronchioles. These results provide a functional software for BronchoX and demonstrate how following simple instructions is possible to reach distal lesions from the trachea.
|
|
|
Fernando Vilariño, Dimosthenis Karatzas, & Alberto Valcarce. (2018). The Library Living Lab Barcelona: A participative approach to technology as an enabling factor for innovation in cultural spaces. Technology Innovation Management Review.
|
|
|
Ester Fornells, Manuel De Armas, Maria Teresa Anguera, Sergio Escalera, Marcos Antonio Catalán, & Josep Moya. (2018). Desarrollo del proyecto del Consell Comarcal del Baix Llobregat “Buen Trato a las personas mayores y aquellas en situación de fragilidad con sufrimiento emocional: Hacia un envejecimiento saludable”. Informaciones Psiquiatricas, 47–59.
|
|
|
Marçal Rusiñol, & Lluis Gomez. (2018). Avances en clasificación de imágenes en los últimos diez años. Perspectivas y limitaciones en el ámbito de archivos fotográficos históricos. Revista anual de la Asociación de Archiveros de Castilla y León, 161–174.
|
|
|
Lasse Martensson, Ekta Vats, Anders Hast, & Alicia Fornes. (2019). In Search of the Scribe: Letter Spotting as a Tool for Identifying Scribes in Large Handwritten Text Corpora. HUMAN IT - Journal for Information Technology Studies as a Human Science, 95–120.
Abstract: In this article, a form of the so-called word spotting-method is used on a large set of handwritten documents in order to identify those that contain script of similar execution. The point of departure for the investigation is the mediaeval Swedish manuscript Cod. Holm. D 3. The main scribe of this manuscript has yet not been identified in other documents. The current attempt aims at localising other documents that display a large degree of similarity in the characteristics of the script, these being possible candidates for being executed by the same hand. For this purpose, the method of word spotting has been employed, focusing on individual letters, and therefore the process is referred to as letter spotting in the article. In this process, a set of ‘g’:s, ‘h’:s and ‘k’:s have been selected as templates, and then a search has been made for close matches among the mediaeval Swedish charters. The search resulted in a number of charters that displayed great similarities with the manuscript D 3. The used letter spotting method thus proofed to be a very efficient sorting tool localising similar script samples.
Keywords: Scribal attribution/ writer identification; digital palaeography; word spotting; mediaeval charters; mediaeval manuscripts
|
|
|
Marçal Rusiñol. (2019). Classificació semàntica i visual de documents digitals. Revista de biblioteconomia i documentacio, 75–86.
Abstract: Se analizan los sistemas de procesamiento automático que trabajan sobre documentos digitalizados con el objetivo de describir los contenidos. De esta forma contribuyen a facilitar el acceso, permitir la indización automática y hacer accesibles los documentos a los motores de búsqueda. El objetivo de estas tecnologías es poder entrenar modelos computacionales que sean capaces de clasificar, agrupar o realizar búsquedas sobre documentos digitales. Así, se describen las tareas de clasificación, agrupamiento y búsqueda. Cuando utilizamos tecnologías de inteligencia artificial en los sistemas de
clasificación esperamos que la herramienta nos devuelva etiquetas semánticas; en sistemas de agrupamiento que nos devuelva documentos agrupados en clusters significativos; y en sistemas de búsqueda esperamos que dada una consulta, nos devuelva una lista ordenada de documentos en función de la relevancia. A continuación se da una visión de conjunto de los métodos que nos permiten describir los documentos digitales, tanto de manera visual (cuál es su apariencia), como a partir de sus contenidos semánticos (de qué hablan). En cuanto a la descripción visual de documentos se aborda el estado de la cuestión de las representaciones numéricas de documentos digitalizados
tanto por métodos clásicos como por métodos basados en el aprendizaje profundo (deep learning). Respecto de la descripción semántica de los contenidos se analizan técnicas como el reconocimiento óptico de caracteres (OCR); el cálculo de estadísticas básicas sobre la aparición de las diferentes palabras en un texto (bag-of-words model); y los métodos basados en aprendizaje profundo como el método word2vec, basado en una red neuronal que, dadas unas cuantas palabras de un texto, debe predecir cuál será la
siguiente palabra. Desde el campo de las ingenierías se están transfiriendo conocimientos que se han integrado en productos o servicios en los ámbitos de la archivística, la biblioteconomía, la documentación y las plataformas de gran consumo, sin embargo los algoritmos deben ser lo suficientemente eficientes no sólo para el reconocimiento y transcripción literal sino también para la capacidad de interpretación de los contenidos.
|
|
|
Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, & Xavier Roca. (2019). Integrating Vision and Language in Social Networks for Identifying Visual Patterns of Personality Traits. IJSSH - International Journal of Social Science and Humanity, 6–12.
Abstract: Social media, as a major platform for communication and information exchange, is a rich repository of the opinions and sentiments of 2.3 billion users about a vast spectrum of topics. In this sense, user text interactions are widely used to sense the whys of certain social user’s demands and cultural- driven interests. However, the knowledge embedded in the 1.8 billion pictures which are uploaded daily in public profiles has just started to be exploited. Following this trend on visual-based social analysis, we present a novel methodology based on neural networks to build a combined image-and-text based personality trait model, trained with images posted together with words found highly correlated to specific personality traits. So, the key contribution in this work is to explore whether OCEAN personality trait modeling can be addressed based on images, here called MindPics, appearing with certain tags with psychological insights. We found that there is a correlation between posted images and the personality estimated from their accompanying texts. Thus, the experimental results are consistent with previous cyber-psychology results based on texts, suggesting that images could also be used for personality estimation: classification results on some personality traits show that specific and characteristic visual patterns emerge, in essence representing abstract concepts. These results open new avenues of research for further refining the proposed personality model under the supervision of psychology experts, and to further substitute current textual personality questionnaires by image-based ones.
|
|