Modelling tyre-road noise with data mining techniques

The research aimed to establish tyre-road noise models by using a Data Mining approach that allowed to build a predictive model and assess the importance of the tested input variables. The data modelling took into account three learning algorithms and three metrics to define the best predictive model. The variables tested included basic properties of pavement surfaces, macrotexture, megatexture, and uneven- ness and, for the first time, damping. Also, the importance of those variables was measured by using a sensitivity analysis procedure. Two types of models were set: one with basic variables and another with complex variables, such as megatexture and damping, all as a function of vehicles speed. More detailed models were additionally set by the speed level. As a result, several models with very good tyre-road noise predictive capacity were achieved. The most relevant variables were Speed, Temperature, Aggregate size, Mean Profile Depth, and Damping, which had the highest importance, even though influenced by speed. Megatexture and IRI had the lowest importance. The applicability of the models developed in this work is relevant for trucks tyre-noise prediction, represented by the AVON V4 test tyre, at the early stage of road pavements use. Therefore, the obtained models are highly useful for the design of pavements and for noise prediction by road authorities and contractors.

Optimization techniques to detect early ventilation extubation in intensive care units

The decision support models in intensive care units are developed to support medical staff in their decision making process. However, the optimization of these models is particularly difficult to apply due to dynamic, complex and multidisciplinary nature. Thus, there is a constant research and development of new algorithms capable of extracting knowledge from large volumes of data, in order to obtain better predictive results than the current algorithms. To test the optimization techniques a case study with real data provided by INTCare project was explored. This data is concerning to extubation cases. In this dataset, several models like Evolutionary Fuzzy Rule Learning, Lazy Learning, Decision Trees and many others were analysed in order to detect early extubation. The hydrids Decision Trees Genetic Algorithm, Supervised Classifier System and KNNAdaptive obtained the most accurate rate 93.2%, 93.1%, 92.97% respectively, thus showing their feasibility to work in a real environment.

Educating for sociability and learning for citizenship: developing communicational skills and mediation in educational contexts

This text concerns a program about the Promotion of Social and Communicational Skills and Mediation (PSCSM) developed with children aged between 10 and 13 years in a non-formal educational institution. The program of intervention had, as its purpose, the promotion of social and communicational competencies and mediation, thus enabling the children involved to have a healthy and responsible sociability in the different contexts in which they find themselves: family, school, peer group, amongst others. It was developed over 13 sessions with objectives and activities intentionally planned with the view of promoting competencies of communication, co-operation, responsibility, a critical spirit, solidarity, autonomy, respect, integration, inclusion and the recognition of rights and duties. This work was carried out with an action-research methodology that resorted to various techniques and instruments to gather and record information. The results obtained showed the impact and benefits of the program and they also revealed the necessity of educational institutions investing in the promotion of an ethical literacy and the empowerment of the children and young people for healthy sociability and active citizenship.

Using active learning for monitoring networks design: The example of wind power plants sites evaluation

Locating new wind farms is of crucial importance for energy policies of the next decade. To select the new location, an accurate picture of the wind fields is necessary. However, characterizing wind fields is a difficult task, since the phenomenon is highly nonlinear and related to complex topographical features. In this paper, we propose both a nonparametric model to estimate wind speed at different time instants and a procedure to discover underrepresented topographic conditions, where new measuring stations could be added. Compared to space filling techniques, this last approach privileges optimization of the output space, thus locating new potential measuring sites through the uncertainty of the model itself.

Advanced mapping of environmental data: Geostatistics, Machine Learning and Bayesian Maximum Entropy

This book combines geostatistics and global mapping systems to present an up-to-the-minute study of environmental data. Featuring numerous case studies, the reference covers model dependent (geostatistics) and data driven (machine learning algorithms) analysis techniques such as risk mapping, conditional stochastic simulations, descriptions of spatial uncertainty and variability, artificial neural networks (ANN) for spatial data, Bayesian maximum entropy (BME), and more.

Techniques for CT and MR, post-processing, radiation

Brain perfusion can be assessed by CT and MR. For CT, two major techniques are used. First, Xenon CT is an equilibrium technique based on a freely diffusible tracer. First pass of iodinated contrast injected intravenously is a second method, more widely available. Both methods are proven to be robust and quantitative, thanks to the linear relationship between contrast concentration and x-ray attenuation. For the CT methods, concern regarding x-ray doses delivered to the patients need to be addressed. MR is also able to assess brain perfusion using the first pass of gadolinium based contrast agent injected intravenously. This method has to be considered as a semi-quantitative because of the non linear relationship between contrast concentration and MR signal changes. Arterial spin labeling is another MR method assessing brain perfusion without injection of contrast. In such case, the blood flow in the carotids is magnetically labelled by an external radiofrequency pulse and observed during its first pass through the brain. Each of this various CT and MR techniques have advantages and limits that will be illustrated and summarized.Learning Objectives:1. To understand and compare the different techniques for brain perfusion imaging.2. To learn about the methods of acquisition and post-processing of brain perfusion by first pass of contrast agent for CT and MR.3. To learn about non contrast MR methods (arterial spin labelling).

Curriculum sequencing for an e-learning system based on learning styles

This work shows the use of adaptation techniques involved in an e-learning system that considers students' learning styles and students' knowledge states. The mentioned e-learning system is built on a multiagent framework designed to examine opportunities to improve the teaching and to motivate the students to learn what they want in a user-friendly and assisted environment

Collage, a Collaborative Learning Design Editor Based on Patterns

This paper introduces Collage, a high-level IMS-LD compliant authoring tool that is specialized for CSCL (Computer-Supported Collaborative Learning). Nowadays CSCL is a key trend in elearning since it highlights the importance of social interactions as an essential element of learning. CSCL is an interdisciplinary domain, which demands participatory design techniques that allow teachers to get directly involved in design activities. Developing CSCL designs using LD is a difficult task for teachers since LD is a complex technical specification and modelling collaborative characteristics can be tricky. Collage helps teachers in the process of creating their own potentially effective collaborative Learning Designs by reusing and customizing patterns, according to the requirements of a particular learning situation. These patterns, called Collaborative Learning Flow Patterns (CLFPs), represent best practices that are repetitively used by practitioners when structuring the flow of (collaborative) learning activities. An example of an LD that can be created using Collage is illustrated in the paper. Preliminary evaluation results show that teachers, with experience in CL but without LD knowledge, can successfully design real collaborative learning experiences using Collage.

Reusing IMS-LD formalized best practices in collaborative learning structuring

Designs of CSCL (Computer Supported Collaborative Learning)activities should be flexible, effective and customizable toparticular learning situations. On the other hand, structureddesigns aim to create favourable conditions for learning. Thus,this paper proposes the collection of representative and broadlyaccepted (best practices) structuring techniques in collaborative learning. With the aim of establishing a conceptual common ground among collaborative learning practitioners and softwaredevelopers, and reusing the expertise that best practicesrepresent, the paper also proposes the formulation of these techniques as patterns: the so-called CLFPs (CollaborativeLearning Flow Patterns). To formalize these patterns, we havechosen the educational modelling language IMS Learning Design (IMS-LD). IMS-LD has the capability to specify many of the collaborative characteristics of the CLFPs. Nevertheless, the language bears limited capability for describing the services that mediate interactions within a learning activity and the specification of temporal or rotated roles. This analysis isdiscussed in the paper, as well as our approaches towards thedevelopment of a system capable of integrating tools using IMSLDscripts and a CLFP-based Learning Design authoring tool.

An Automatic Approach for Learning and Tuning Gaussian Interval Type-2 Fuzzy Membership Functions Applied to Lung CAD Classification System

The potential of type-2 fuzzy sets for managing high levels of uncertainty in the subjective knowledge of experts or of numerical information has focused on control and pattern classification systems in recent years. One of the main challenges in designing a type-2 fuzzy logic system is how to estimate the parameters of type-2 fuzzy membership function (T2MF) and the Footprint of Uncertainty (FOU) from imperfect and noisy datasets. This paper presents an automatic approach for learning and tuning Gaussian interval type-2 membership functions (IT2MFs) with application to multi-dimensional pattern classification problems. T2MFs and their FOUs are tuned according to the uncertainties in the training dataset by a combination of genetic algorithm (GA) and crossvalidation techniques. In our GA-based approach, the structure of the chromosome has fewer genes than other GA methods and chromosome initialization is more precise. The proposed approach addresses the application of the interval type-2 fuzzy logic system (IT2FLS) for the problem of nodule classification in a lung Computer Aided Detection (CAD) system. The designed IT2FLS is compared with its type-1 fuzzy logic system (T1FLS) counterpart. The results demonstrate that the IT2FLS outperforms the T1FLS by more than 30% in terms of classification accuracy.

BIO-INSPIRED COMPUTATIONAL TECHNIQUES APPLIED TO THE CLUSTERING AND VISUALIZATION OF SPATIO-TEMPORAL GEOSPATIAL DATA

The coverage and volume of geo-referenced datasets are extensive and incessantly¦growing. The systematic capture of geo-referenced information generates large volumes¦of spatio-temporal data to be analyzed. Clustering and visualization play a key¦role in the exploratory data analysis and the extraction of knowledge embedded in¦these data. However, new challenges in visualization and clustering are posed when¦dealing with the special characteristics of this data. For instance, its complex structures,¦large quantity of samples, variables involved in a temporal context, high dimensionality¦and large variability in cluster shapes.¦The central aim of my thesis is to propose new algorithms and methodologies for¦clustering and visualization, in order to assist the knowledge extraction from spatiotemporal¦geo-referenced data, thus improving making decision processes.¦I present two original algorithms, one for clustering: the Fuzzy Growing Hierarchical¦Self-Organizing Networks (FGHSON), and the second for exploratory visual data analysis:¦the Tree-structured Self-organizing Maps Component Planes. In addition, I present¦methodologies that combined with FGHSON and the Tree-structured SOM Component¦Planes allow the integration of space and time seamlessly and simultaneously in¦order to extract knowledge embedded in a temporal context.¦The originality of the FGHSON lies in its capability to reflect the underlying structure¦of a dataset in a hierarchical fuzzy way. A hierarchical fuzzy representation of¦clusters is crucial when data include complex structures with large variability of cluster¦shapes, variances, densities and number of clusters. The most important characteristics¦of the FGHSON include: (1) It does not require an a-priori setup of the number¦of clusters. (2) The algorithm executes several self-organizing processes in parallel.¦Hence, when dealing with large datasets the processes can be distributed reducing the¦computational cost. (3) Only three parameters are necessary to set up the algorithm.¦In the case of the Tree-structured SOM Component Planes, the novelty of this algorithm¦lies in its ability to create a structure that allows the visual exploratory data analysis¦of large high-dimensional datasets. This algorithm creates a hierarchical structure¦of Self-Organizing Map Component Planes, arranging similar variables' projections in¦the same branches of the tree. Hence, similarities on variables' behavior can be easily¦detected (e.g. local correlations, maximal and minimal values and outliers).¦Both FGHSON and the Tree-structured SOM Component Planes were applied in¦several agroecological problems proving to be very efficient in the exploratory analysis¦and clustering of spatio-temporal datasets.¦In this thesis I also tested three soft competitive learning algorithms. Two of them¦well-known non supervised soft competitive algorithms, namely the Self-Organizing¦Maps (SOMs) and the Growing Hierarchical Self-Organizing Maps (GHSOMs); and the¦third was our original contribution, the FGHSON. Although the algorithms presented¦here have been used in several areas, to my knowledge there is not any work applying¦and comparing the performance of those techniques when dealing with spatiotemporal¦geospatial data, as it is presented in this thesis.¦I propose original methodologies to explore spatio-temporal geo-referenced datasets¦through time. Our approach uses time windows to capture temporal similarities and¦variations by using the FGHSON clustering algorithm. The developed methodologies¦are used in two case studies. In the first, the objective was to find similar agroecozones¦through time and in the second one it was to find similar environmental patterns¦shifted in time.¦Several results presented in this thesis have led to new contributions to agroecological¦knowledge, for instance, in sugar cane, and blackberry production.¦Finally, in the framework of this thesis we developed several software tools: (1)¦a Matlab toolbox that implements the FGHSON algorithm, and (2) a program called¦BIS (Bio-inspired Identification of Similar agroecozones) an interactive graphical user¦interface tool which integrates the FGHSON algorithm with Google Earth in order to¦show zones with similar agroecological characteristics.

Intraoperative training on the techniques of sentinel node biopsy in breast cancer

Principles: Surgeon's experience is crucial for proper application of sentinel node biopsy (SNB) in patients with breast cancer. A 20-30 cases learning curve of sentinel node (SN) and axillary lymph node dissection (ALND) was widely practiced. In order to speed up this learning curve, surgeons may be trained intraoperative by an experienced surgeon. The purpose of this report is to evaluate the results of this procedure. Methods: Patients with one primary invasive breast cancer (cT1-T2[<3 cm]cN0) underwent SNB based on lymphoscintigraphy using technetium Tc 99m colloid, intraoperative gamma probe detection, with or without blue dye mapping. This was followed by completion ALND when SN was positive or not found. SNB was performed by one experienced surgeon (teacher) or by 10 junior surgeons trained by the experienced surgeon (trainees). Four groups were defined: (i) SNB with immediate ALND for the teacher's learning curve, (ii) SNB by the teacher, (iii) SNB by the trainees under the teacher's supervision, and (iv) SNB by the trainees alone. Results: Between May 1999 and December 2007, a total of 808 évaluable patients underwent SNB. The SN identification rate was 98% in the teacher's group, and 99% in the trainees' group (p = 0.196). SN were positive in respectively 28% and 29% of patients (p = 0.196). The distribution of isolated tumor cells, micrometastases and metastases was not statistically different between the teacher's and the trainees' groups (p = 0.163). Conclusion: These comparable results confirm the success with which the SNB was taught. This strategy avoided the 20-30 SNB followed by immediate ALND early required per surgeon.

Applying machine learning methods to avalanche forecasting

Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work.

Techniques for CT and MR, post-processing, radiation.

Brain perfusion can be assessed by CT and MR. For CT, two major techniquesare used. First, Xenon CT is an equilibrium technique based on a freely diffusibletracer. First pass of iodinated contrast injected intravenously is a second method,more widely available. Both methods are proven to be robust and quantitative,thanks to the linear relationship between contrast concentration and x-ray attenuation.For the CT methods, concern regarding x-ray doses delivered to the patientsneed to be addressed. MR is also able to assess brain perfusion using the firstpass of gadolinium based contrast agent injected intravenously. This method hasto be considered as a semi-quantitative because of the non linear relationshipbetween contrast concentration and MR signal changes. Arterial spin labelingis another MR method assessing brain perfusion without injection of contrast. Insuch case, the blood flow in the carotids is magnetically labelled by an externalradiofrequency pulse and observed during its first pass through the brain. Eachof this various CT and MR techniques have advantages and limits that will be illustratedand summarised.Learning Objectives:1. To understand and compare the different techniques for brain perfusionimaging.2. To learn about the methods of acquisition and post-processing of brainperfusion by first pass of contrast agent for CT and MR.3. To learn about non contrast MR methods (arterial spin labelling).

Similarity in food cleaning techniques within matrilines in wild vervet monkeys.

Social learning and the formation of traditions rely on the ability and willingness to copy one another. A central question is under which conditions individuals adapt behaviour to social influences. Here, we demonstrate that similarities in food processing techniques emerge on the level of matrilines (mother-offspring) but not on the group level in an experiment on six groups of wild vervet monkeys that involved grapes covered with sand. Monkeys regularly ate unclean grapes but also used four cleaning techniques more similarly within matrilines: rubbing in hands, rubbing on substrate, open with mouth, and open with hands. Individual cleaning techniques evolved over time as they converged within matrilines, stabilised at the end and remained stable in a follow-up session more than one year later. The similarity within matrilines persisted when we analyzed only foraging events of individuals in the absence of other matriline members and matriline members used more similar methods than adult full sisters. Thus, momentary conversion or purely genetic causation are unlikely explanations, favouring social learning as mechanism for within matriline similarities. The restriction of traditions to matriline membership rather than to the group level may restrict the development of culture in monkeys relative to apes or humans.