Enhancing Multimodal Silent Speech Interfaces With Feature Selection

In research on Silent Speech Interfaces (SSI), different sources of information (modalities) have been combined, aiming at obtaining better performance than the individual modalities. However, when combining these modalities, the dimensionality of the feature space rapidly increases, yielding the well-known "curse of dimensionality". As a consequence, in order to extract useful information from this data, one has to resort to feature selection (FS) techniques to lower the dimensionality of the learning space. In this paper, we assess the impact of FS techniques for silent speech data, in a dataset with 4 non-invasive and promising modalities, namely: video, depth, ultrasonic Doppler sensing, and surface electromyography. We consider two supervised (mutual information and Fisher's ratio) and two unsupervised (meanmedian and arithmetic mean geometric mean) FS filters. The evaluation was made by assessing the classification accuracy (word recognition error) of three well-known classifiers (knearest neighbors, support vector machines, and dynamic time warping). The key results of this study show that both unsupervised and supervised FS techniques improve on the classification accuracy on both individual and combined modalities. For instance, on the video component, we attain relative performance gains of 36.2% in error rates. FS is also useful as pre-processing for feature fusion. Copyright © 2014 ISCA.

Analysis of the domain of applicability of an algorithm for a resources system selection problem for Distributed/Agile/Virtual Enterprises integration

The process of resources systems selection takes an important part in Distributed/Agile/Virtual Enterprises (D/A/V Es) integration. However, the resources systems selection is still a difficult matter to solve in a D/A/VE, as it is pointed out in this paper. Globally, we can say that the selection problem has been equated from different aspects, originating different kinds of models/algorithms to solve it. In order to assist the development of a web prototype tool (broker tool), intelligent and flexible, that integrates all the selection model activities and tools, and with the capacity to adequate to each D/A/V E project or instance (this is the major goal of our final project), we intend in this paper to show: a formulation of a kind of resources selection problem and the limitations of the algorithms proposed to solve it. We formulate a particular case of the problem as an integer programming, which is solved using simplex and branch and bound algorithms, and identify their performance limitations (in terms of processing time) based on simulation results. These limitations depend on the number of processing tasks and on the number of pre-selected resources per processing tasks, defining the domain of applicability of the algorithms for the problem studied. The limitations detected open the necessity of the application of other kind of algorithms (approximate solution algorithms) outside the domain of applicability founded for the algorithms simulated. However, for a broker tool it is very important the knowledge of algorithms limitations, in order to, based on problem features, develop and select the most suitable algorithm that guarantees a good performance.

Enhancing the selection of a model-based clustering with external categorical variables

In cluster analysis, it can be useful to interpret the partition built from the data in the light of external categorical variables which are not directly involved to cluster the data. An approach is proposed in the model-based clustering context to select a number of clusters which both fits the data well and takes advantage of the potential illustrative ability of the external variables. This approach makes use of the integrated joint likelihood of the data and the partitions at hand, namely the model-based partition and the partitions associated to the external variables. It is noteworthy that each mixture model is fitted by the maximum likelihood methodology to the data, excluding the external variables which are used to select a relevant mixture model only. Numerical experiments illustrate the promising behaviour of the derived criterion. © 2014 Springer-Verlag Berlin Heidelberg.

An unsupervised approach to feature discretization and selection

Many learning problems require handling high dimensional datasets with a relatively small number of instances. Learning algorithms are thus confronted with the curse of dimensionality, and need to address it in order to be effective. Examples of these types of data include the bag-of-words representation in text classification problems and gene expression data for tumor detection/classification. Usually, among the high number of features characterizing the instances, many may be irrelevant (or even detrimental) for the learning tasks. It is thus clear that there is a need for adequate techniques for feature representation, reduction, and selection, to improve both the classification accuracy and the memory requirements. In this paper, we propose combined unsupervised feature discretization and feature selection techniques, suitable for medium and high-dimensional datasets. The experimental results on several standard datasets, with both sparse and dense features, show the efficiency of the proposed techniques as well as improvements over previous related techniques.

Efficient feature selection filters for high-dimensional data

Feature selection is a central problem in machine learning and pattern recognition. On large datasets (in terms of dimension and/or number of instances), using search-based or wrapper techniques can be cornputationally prohibitive. Moreover, many filter methods based on relevance/redundancy assessment also take a prohibitively long time on high-dimensional. datasets. In this paper, we propose efficient unsupervised and supervised feature selection/ranking filters for high-dimensional datasets. These methods use low-complexity relevance and redundancy criteria, applicable to supervised, semi-supervised, and unsupervised learning, being able to act as pre-processors for computationally intensive methods to focus their attention on smaller subsets of promising features. The experimental results, with up to 10(5) features, show the time efficiency of our methods, with lower generalization error than state-of-the-art techniques, while being dramatically simpler and faster.

Coral snake venoms: mode of action and pathophysiology of experimental envenomation

Coral snakes, the New World Elapidae, are included in the genera Micniroides and Micrurus. The genus Mlcrurus comprises nearly all coral snake species and those which are responsible for human snake-bite accidents. The following generalizations concerning the effects induced by their venoms, and their venom-properties can be made. Coral snake venoms are neurotoxic, producing loss of muscle strenght and death by respiratory paralysis. Local edema and necrosis are not induced nor blood coagulation or hemorrhages. Proteolysis activity is absent or of very low grade. They display phospholipase A2 activity. Nephrotoxic effects are not evoked. The main toxins from elapid venoms are postsynaptic and presynaptic neurotoxins and cardiotoxins. Phospholipases A2 endowed with myonecrotic or cardiotoxin-like properties are important toxic components from some elapid venoms. The mode of action of Micrurus frontalis, M. lemniscatus, M. corallinus and M. fulvius venoms has been investigated in isolated muscle preparations and is here discussed. It is shown that while M. frontalis and M. lemniscatus venoms must contain only neurotoxins that act at the cholinergic end-plate receptor (postsynaptic neurotoxins), M. corallinus venom also inhibits evoked acetylcholine release by the motor nerve endings (presynaptic neurotoxin-like effect) and M. fulvius induces muscle fiber membrane depolarization (cardiotoxin-like effect). The effects produced by M. corallinus and M. fulvius venoms in vivo in dogs and M. frontalis venom in dogs and monkeys are also reported.

Conceiving modern engineers within the framework of the sustainability action plan (PASUS) of ISEP: sustainability matters!

Engineering education practices have evolved not only due to the natural changes in the contents of the curricula and skills but also, and more recently, due to the requirements imposed by the Bologna revision process. In addition, industry is becoming more demanding, as society is becoming more and more aware of the global needs and consequences of industrial practices. Under this scope, higher education needs not only to follow but also to lead these trends. Therefore, the School of Engineering of the Polytechnic Institute of Porto (ISEP), a Global Reporting Initiative (GRI) training partner in Portugal, prepared and presented its Sustainability Action Plan (PASUS), with the main objective of creating a new kind of engineers, with Sustainable Development at the core of their graduation and MsC degrees. In this paper, the main strategies and activities of the referred plan along with the strategic approach, which guided its development and implementation, will be presented in detail. Additionally, a reflection about the above mentioned bridge between concept and application will be established and justified, in the framework of the action plan. Although in most of the situations, there was no prior discussion or specific request, many of the graduation and post-graduation programmes offered by ISEP already include courses that attend to PASUS philosophy. As a consequence, the number of Master thesis, Graduation projects and R&D projects that address sustainability problems has grown substantially, a proof that for ISEP community, sustainability really matters!

Porto Polytechnical Engineering School sustainable development action plan

Porto Polytechnical Engineering School (ISEP), a Global Reporting Initiative training partner in Portugal, has just presented its Sustainable Development Action Plan (PASUS), which main objective is the formation of a new kind of engineers, with a Sustainable Development (SD) philosophy in the core of their academic curricula courses.

Fuzzy Boolean nets investigation of the alteration of some physical forest soil properties due to a prescribed fire action

Portuguese northern forests are often and severely affected by wildfires during the summer season. Some preventive actions, such as prescribed (or controlled) burnings and clear-cut logging, are often used as a measure to reduce the occurrences of wildfires. In the particular case of Serra da Cabreira forest, due to extremely difficulties in operational field work, the prescribed (or controlled) burning technique is the the most common preventive action used to reduce the existing fuel load amount. This paper focuses on a Fuzzy Boolean Nets analysis of the changes in some forest soil properties, namely pH, moisture and organic matter content, after a controlled fire, and on the difficulties found during the sampling process and how they were overcome. The monitoring process was conducted during a three-month period in Anjos, Vieira do Minho, Portugal, an area located in a contact zone between a two-mica coarse-grained porphyritic granite and a biotite with plagioclase granite. The sampling sites were located in a spot dominated by quartzphyllite with quartz veins whose bedrock is partially altered and covered by slightly thick humus, which maintains low undergrowth vegetation.

Acquisition and data analysis related to changes in some forest soils properties after prescribed fire action

Controlled fires in forest areas are frequently used in most Mediterranean countries as a preventive technique to avoid severe wildfires in summer season. In Portugal, this forest management method of fuel mass availability is also used and has shown to be beneficial as annual statistical reports confirm that the decrease of wildfires occurrence have a direct relationship with the controlled fire practice. However prescribed fire can have serious side effects in some forest soil properties. This work shows the changes that occurred in some forest soils properties after a prescribed fire action. The experiments were carried out in soil cover over a natural site of Andaluzitic schist, in Gramelas, Caminha, Portugal, that had not been burn for four years. The composed soil samples were collected from five plots at three different layers (0-3cm, 3-6cm and 6-18cm) during a three-year monitoring period after the prescribed burning. Principal Component Analysis was used to reach the presented conclusions.

Sustainable Development Action Plan at ISEP - From Concept to Engineering Practice

Some of the main challenges in Incorporating Sustainable Development practices into Engineering Education reside in establishing the bridge between concept and application. In particular the relation between value creation and the knowledge economy, innovation and entrepreneurship, as the main vehicles to a relevant application of the sustainable development concept, is not yet part of the majority of the engineering curricula in schools. Porto Polytechnical Engineering School (ISEP), a Global Reporting Initiative training partner in Portugal, as just presented its Sustainable Development Action Plan, with the main objective of creating a new kind of engineers, with Sustainable Development at the core of their degrees. The plan has several issues like publish an annual sustainability report, sustainable buildings, minimization of energy consumption and water policy, waste management, sustainable mobility, green procurement, EMAS certification, research and postgraduate activity and promotion of lectures and seminars in Sustainable Development.

In vitro action of some disinfectants on Paracoccidioides brasiliensis yeast forms

The fungicidal action of sodium hypochlorite (0.3, 1, 2.5, 5 and 10%); formaldehyde (2, 5, and 10%); and ethyl alcohol (70%) on yeast forms of Paracoccidioides brasiliensis Pb 18 and a newly-isolated Goiana strain was described. Contact between the fungus and the disinfectants was maintained for 1, 2, 24, 48 and 72 hours at room temperature. Viability was evaluated by the fluorescein diacetate-ethidium bromide treatment, culture in solid and liquid media (36ºC and 26ºC); yeast to mycelial germination at room temperature; and radiometric study of metabolic activity. All concentrations of disinfectants were found to be effective in inactivating Pb 18 and Goiana strains, except for the 1-hour contact with 2% formaldehyde, in which fluorescein diacetate-ethidium bromide treatment was found to reveal 40 and 27% of viable cells, respectively. The yeast to mycelial germination method was considered to reveal faster and similar results as compared to culture in solid and liquid media.

Conceptual analogy for modelling entrapped air action in hydraulic systems

Hydraulic systems are dynamically susceptible in the presence of entrapped air pockets, leading to amplified transient reactions. In order to model the dynamic action of an entrapped air pocket in a confined system, a heuristic mathematical formulation based on a conceptual analogy to a mechanical spring-damper system is proposed. The formulation is based on the polytropic relationship of an ideal gas and includes an additional term, which encompasses the combined damping effects associated with the thermodynamic deviations from the theoretical transformation, as well as those arising from the transient vorticity developed in both fluid domains (air and water). These effects represent the key factors that account for flow energy dissipation and pressure damping. Model validation was completed via numerical simulation of experimental measurements.

Enhancing the selection of a model-based clustering with external categorical variables

In cluster analysis, it can be useful to interpret the partition built from the data in the light of external categorical variables which are not directly involved to cluster the data. An approach is proposed in the model-based clustering context to select a number of clusters which both fits the data well and takes advantage of the potential illustrative ability of the external variables. This approach makes use of the integrated joint likelihood of the data and the partitions at hand, namely the model-based partition and the partitions associated to the external variables. It is noteworthy that each mixture model is fitted by the maximum likelihood methodology to the data, excluding the external variables which are used to select a relevant mixture model only. Numerical experiments illustrate the promising behaviour of the derived criterion.

Materials selection for a set of multiple parts considering manufacturing costs and weight reduction with structural isoperformance using direct multisearch optimization

Materials selection is a matter of great importance to engineering design and software tools are valuable to inform decisions in the early stages of product development. However, when a set of alternative materials is available for the different parts a product is made of, the question of what optimal material mix to choose for a group of parts is not trivial. The engineer/designer therefore goes about this in a part-by-part procedure. Optimizing each part per se can lead to a global sub-optimal solution from the product point of view. An optimization procedure to deal with products with multiple parts, each with discrete design variables, and able to determine the optimal solution assuming different objectives is therefore needed. To solve this multiobjective optimization problem, a new routine based on Direct MultiSearch (DMS) algorithm is created. Results from the Pareto front can help the designer to align his/hers materials selection for a complete set of materials with product attribute objectives, depending on the relative importance of each objective.