Urban image classification with semisupervised multiscale cluster kernels

This paper presents a semisupervised support vector machine (SVM) that integrates the information of both labeled and unlabeled pixels efficiently. Method's performance is illustrated in the relevant problem of very high resolution image classification of urban areas. The SVM is trained with the linear combination of two kernels: a base kernel working only with labeled examples is deformed by a likelihood kernel encoding similarities between labeled and unlabeled examples. Results obtained on very high resolution (VHR) multispectral and hyperspectral images show the relevance of the method in the context of urban image classification. Also, its simplicity and the few parameters involved make the method versatile and workable by unexperienced users.

Caracterització d'oscil·ladors basats en CMOS-M/NEMS i la seva aplicació com a sensors de massa

El present projecte tracta sobre la caracterització d'oscil·ladors basats en ressonadors micro/nanoelectromecànics (M/NEMS) i la seva aplicació com a sensors de massa. Els oscil·ladors utilitzats es basen en un pont i una palanca ressoants M/NEMS, integrats en tecnologia CMOS. En primer lloc s'ha fet una introducció teòrica als conceptes utilitzats per a entendre el funcionament i la caracterització dels dispositius. A continuació s'han realitzat proves per tal de caracteritzar els paràmetres importants per a l'ús dels oscil·ladors com a sensors de massa, com la seva estabilitat en freqüència. Per acabar s'han aplicat aquests sensors en la caracterització i modelització del flux de massa a través d'obertures de dimensions micromètriques.

A gene knockout approach in mice to identify glucose sensors controlling glucose homeostasis.

A key aspect of glucose homeostasis is the constant monitoring of blood glucose concentrations by specific glucose sensing units. These sensors, via stimulation of hormone secretion and activation of the autonomic nervous system (ANS), regulate tissue glucose uptake, utilization or production. The best described glucose detection system is that of the pancreatic beta-cells which controls insulin secretion. Secretion of other hormones, in particular glucagon, and activation of the ANS, are regulated by glucose through sensing mechanisms which are much less well characterized. Here I review some of the studies we have performed over the recent years on a mouse model of impaired glucose sensing generated by inactivation of the gene for the glucose transporter GLUT2. This transporter catalyzes glucose uptake by pancreatic beta-cells, the first step in the signaling cascade leading to glucose-stimulated insulin secretion. Inactivation of its gene leads to a loss of glucose sensing and impaired insulin secretion. Transgenic reexpression of the transporter in GLUT2/beta-cells restores their normal secretory function and rescues the mice from early death. As GLUT2 is also expressed in other tissues, these mice were then studied for the presence of other physiological defects due to absence of this transporter. These studies led to the identification of extra-pancreatic, GLUT2-dependent, glucose sensors controlling glucagon secretion and glucose utilization by peripheral tissues, in part through a control of the autonomic nervous system.

Desenvolupament d'una xarxa de sensors i actuadors sense fils de propòsit industrial

Aquesta memòria de projecte final de carrera és un estudi i implementació bàsica de l’estat actual en quant a les tecnologies/protocols sense fils existents, en particular centrat en ZigBee sobre la plataforma CC2430 de Texas Instruments, per a una aplicació industrial amb una taxa de transferència de dades baixa, que no presenta un alt grau de complexitat, però que requereix gran versatilitat i fiabilitat.

Plataforma per a la simulació de xarxes de sensors

Aquest projecte descriu una plataforma de simulació per a xarxes de sensors des de la perspectiva dels sistemes multi-agents. La plataforma s'ha dissenyat per facilitar la simulació de diferents aplicacions concretes de xarxes de sensors. A més, s'ha entregat com a artefacte del projecte IEA (Institucions Electròniques Autònomes, TIN2006-15662-C02-0) de l'IIIACSIC. Dins l'entorn de l'IEA, aquesta és l'eina que aporta les capacitats de simulació per donar suport al disseny d'algorismes adaptatius per a xarxes de sensors.

Testing low-altitude infrared digital photography from a mini-UAV to retrieve information for biological conservation

Satellite remote sensing imagery is used for forestry, conservation and environmental applications, but insufficient spatial resolution, and, in particular, unavailability of images at the precise timing required for a given application, often prevent achieving a fully operational stage. Airborne remote sensing has the advantage of custom-tuned sensors, resolution and timing, but its price prevents using it as a routine technique for the mentioned fields. Some Unmanned Aerial Vehicles might provide a “third way” solution as low-cost techniques for acquiring remotely sensed information, under close control of the end-user, albeit at the expense of lower quality instrumentation and instability. This report evaluates a light remote sensing system based on a remotely-controlled mini-UAV (ATMOS-3) equipped with a color infra-red camera (VEGCAM-1) designed and operated by CATUAV. We conducted a testing mission over a Mediterranean landscape dominated by an evergreen woodland of Aleppo pine (Pinus halepensis) and (Holm) oak (Quercus ilex) in the Montseny National Park (Catalonia, NE Spain). We took advantage of state-of-the-art ortho-rectified digital aerial imagery (acquired by the Institut Cartogràfic de Catalunya over the area during the previous year) and used it as quality reference. In particular, we paid attention to: 1) Operationality of flight and image acquisition according to a previously defined plan; 2) Radiometric and geometric quality of the images; and 3) Operational use of the images in the context of applications. We conclude that the system has achieved an operational stage regarding flight activities, although with meteorological limits set by wind speed and turbulence. Appropriate landing areas can be sometimes limiting also, but the system is able to land on small and relatively rough terrains such as patches of grassland or short matorral, and we have operated the UAV as far as 7 km from the control unit. Radiometric quality is sufficient for interactive analysis, but probably insufficient for automated processing. A forthcoming camera is supposed to greatly improve radiometric quality and consistency. Conventional GPS positioning through time synchronization provides coarse orientation of the images, with no roll information.

Some variational problems from image processing

"Vegeu el resum a l'inici del document del fitxer adjunt."

Generating controlled image sets in cognitive neuroscience research.

The investigation of perceptual and cognitive functions with non-invasive brain imaging methods critically depends on the careful selection of stimuli for use in experiments. For example, it must be verified that any observed effects follow from the parameter of interest (e.g. semantic category) rather than other low-level physical features (e.g. luminance, or spectral properties). Otherwise, interpretation of results is confounded. Often, researchers circumvent this issue by including additional control conditions or tasks, both of which are flawed and also prolong experiments. Here, we present some new approaches for controlling classes of stimuli intended for use in cognitive neuroscience, however these methods can be readily extrapolated to other applications and stimulus modalities. Our approach is comprised of two levels. The first level aims at equalizing individual stimuli in terms of their mean luminance. Each data point in the stimulus is adjusted to a standardized value based on a standard value across the stimulus battery. The second level analyzes two populations of stimuli along their spectral properties (i.e. spatial frequency) using a dissimilarity metric that equals the root mean square of the distance between two populations of objects as a function of spatial frequency along x- and y-dimensions of the image. Randomized permutations are used to obtain a minimal value between the populations to minimize, in a completely data-driven manner, the spectral differences between image sets. While another paper in this issue applies these methods in the case of acoustic stimuli (Aeschlimann et al., Brain Topogr 2008), we illustrate this approach here in detail for complex visual stimuli.

A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

MSight: an image analysis software for liquid chromatography-mass spectrometry.

Images obtained from high-throughput mass spectrometry (MS) contain information that remains hidden when looking at a single spectrum at a time. Image processing of liquid chromatography-MS datasets can be extremely useful for quality control, experimental monitoring and knowledge extraction. The importance of imaging in differential analysis of proteomic experiments has already been established through two-dimensional gels and can now be foreseen with MS images. We present MSight, a new software designed to construct and manipulate MS images, as well as to facilitate their analysis and comparison.