Adaptive modeling and high quality spectral estimation for speech enhancement

In this work an adaptive modeling and spectral estimation scheme based on a dual Discrete Kalman Filtering (DKF) is proposed for speech enhancement. Both speech and noise signals are modeled by an autoregressive structure which provides an underlying time frame dependency and improves time-frequency resolution. The model parameters are arranged to obtain a combined state-space model and are also used to calculate instantaneous power spectral density estimates. The speech enhancement is performed by a dual discrete Kalman filter that simultaneously gives estimates for the models and the signals. This approach is particularly useful as a pre-processing module for parametric based speech recognition systems that rely on spectral time dependent models. The system performance has been evaluated by a set of human listeners and by spectral distances. In both cases the use of this pre-processing module has led to improved results.

A novel framework for modeling value for the customer, an essay on negotiation

This paper proposes a novel framework for modelling the Value for the Customer, the so-called the Conceptual Model for Decomposing Value for the Customer (CMDVC). This conceptual model is first validated through an exploratory case study where the authors validate both the proposed constructs of the model and their relations. In a second step the authors propose a mathematical formulation for the CMDVC as well as a computational method. This has enabled the final quantitative discussion of how the CMDVC can be applied and used in the enterprise environment, and the final validation by the people in the enterprise. Along this research, we were able to confirm that the results of this novel quantitative approach to model the Value for the Customer is consistent with the company's empirical experience. The paper further discusses the merits and limitations of this approach, proposing that the model is likely to bring value to support not only the contract preparation at an Ex-Ante Negotiation Phase, as demonstrated, but also along the actual negotiation process, as finally confirmed by an enterprise testimonial.

Self-optimization module for scheduling using case-based reasoning

Metaheuristics performance is highly dependent of the respective parameters which need to be tuned. Parameter tuning may allow a larger flexibility and robustness but requires a careful initialization. The process of defining which parameters setting should be used is not obvious. The values for parameters depend mainly on the problem, the instance to be solved, the search time available to spend in solving the problem, and the required quality of solution. This paper presents a learning module proposal for an autonomous parameterization of Metaheuristics, integrated on a Multi-Agent System for the resolution of Dynamic Scheduling problems. The proposed learning module is inspired on Autonomic Computing Self-Optimization concept, defining that systems must continuously and proactively improve their performance. For the learning implementation it is used Case-based Reasoning, which uses previous similar data to solve new cases. In the use of Case-based Reasoning it is assumed that similar cases have similar solutions. After a literature review on topics used, both AutoDynAgents system and Self-Optimization module are described. Finally, a computational study is presented where the proposed module is evaluated, obtained results are compared with previous ones, some conclusions are reached, and some future work is referred. It is expected that this proposal can be a great contribution for the self-parameterization of Metaheuristics and for the resolution of scheduling problems on dynamic environments.

Increase of the delivered energy probability in DES using a fuzzy probabilistic modeling

The paper proposes a methodology to increase the probability of delivering power to any load point by identifying new investments in distribution energy systems. The proposed methodology is based on statistical failure and repair data of distribution components and it uses a fuzzy-probabilistic modeling for the components outage parameters. The fuzzy membership functions of the outage parameters of each component are based on statistical records. A mixed integer nonlinear programming optimization model is developed in order to identify the adequate investments in distribution energy system components which allow increasing the probability of delivering power to any customer in the distribution system at the minimum possible cost for the system operator. To illustrate the application of the proposed methodology, the paper includes a case study that considers a 180 bus distribution network.

Contextual intelligent load management with ANN adaptive learning module

With the current increase of energy resources prices and environmental concerns intelligent load management systems are gaining more and more importance. This paper concerns a SCADA House Intelligent Management (SHIM) system that includes an optimization module using deterministic and genetic algorithm approaches. SHIM undertakes contextual load management based on the characterization of each situation. SHIM considers available generation resources, load demand, supplier/market electricity price, and consumers’ constraints and preferences. The paper focus on the recently developed learning module which is based on artificial neural networks (ANN). The learning module allows the adjustment of users’ profiles along SHIM lifetime. A case study considering a system with fourteen discrete and four variable loads managed by a SHIM system during five consecutive similar weekends is presented.

Lightweight user modeling – a case study

In the context of previous publications, we propose a new lightweight UM process, intended to work as a tourism recommender system in a commercial environment. The new process tackles issues like cold start, gray sheep and over specialization through a rich user model and the application of a gradual forgetting function to the collected user action history. Also, significant performance improvements were achieved regarding the previously proposed UM process.

Modeling group decision meeting participants with an Agent-based approach

This paper aims to present a multi-agent model for a simulation, whose goal is to help one specific participant of multi-criteria group decision making process.This model has five main intervenient types: the human participant, who is using the simulation and argumentation support system; the participant agents, one associated to the human participant and the others simulating the others human members of the decision meeting group; the directory agent; the proposal agents, representing the different alternatives for a decision (the alternatives are evaluated based on criteria); and the voting agent responsiblefor all voting machanisms.At this stage it is proposed a two phse algorithm. In the first phase each participantagent makes his own evaluation of the proposals under discussion, and the voting agent proposes a simulation of a voting process.In the second phase, after the dissemination of the voting results,each one ofthe partcipan agents will argue to convince the others to choose one of the possible alternatives. The arguments used to convince a specific participant are dependent on agent knowledge about that participant. This two-phase algorithm is applied iteratively.

User modeling and recommendation strategies for tourism

Mestrado em Engenharia Informática

User modeling In adaptive hypermedia educational systems

This document is a survey in the research area of User Modeling (UM) for the specific field of Adaptive Learning. The aims of this document are: To define what it is a User Model; To present existing and well known User Models; To analyze the existent standards related with UM; To compare existing systems. In the scientific area of User Modeling (UM), numerous research and developed systems already seem to promise good results, but some experimentation and implementation are still necessary to conclude about the utility of the UM. That is, the experimentation and implementation of these systems are still very scarce to determine the utility of some of the referred applications. At present, the Student Modeling research goes in the direction to make possible reuse a student model in different systems. The standards are more and more relevant for this effect, allowing systems communicate and to share data, components and structures, at syntax and semantic level, even if most of them still only allow syntax integration.

Sistema de recomendação para plataformas de e-learning

O aumento do número de recursos digitais disponíveis dificulta a tarefa de pesquisa dos recursos mais relevantes, no sentido de se obter o que é mais relevante. Assim sendo, um novo tipo de ferramentas, capaz de recomendar os recursos mais apropriados às necessidades do utilizador, torna-se cada vez mais necessário. O objetivo deste trabalho de I&D é o de implementar um módulo de recomendação inteligente para plataformas de e-learning. As recomendações baseiam-se, por um lado, no perfil do utilizador durante o processo de formação e, por outro lado, nos pedidos efetuados pelo utilizador, através de pesquisas [Tavares, Faria e Martins, 2012]. O e-learning 3.0 é um projeto QREN desenvolvido por um conjunto de organizações e tem com objetivo principal implementar uma plataforma de e-learning. Este trabalho encontra-se inserido no projeto e-learning 3.0 e consiste no desenvolvimento de um módulo de recomendação inteligente (MRI). O MRI utiliza diferentes técnicas de recomendação já aplicadas noutros sistemas de recomendação. Estas técnicas são utilizadas para criar um sistema de recomendação híbrido direcionado para a plataforma de e-learning. Para representar a informação relevante, sobre cada utilizador, foi construído um modelo de utilizador. Toda a informação necessária para efetuar a recomendação será representada no modelo do utilizador, sendo este modelo atualizado sempre que necessário. Os dados existentes no modelo de utilizador serão utilizados para personalizar as recomendações produzidas. As recomendações estão divididas em dois tipos, a formal e a não formal. Na recomendação formal o objetivo é fazer sugestões relacionadas a um curso específico. Na recomendação não-formal, o objetivo é fazer sugestões mais abrangentes onde as recomendações não estão associadas a nenhum curso. O sistema proposto é capaz de sugerir recursos de aprendizagem, com base no perfil do utilizador, através da combinação de técnicas de similaridade de palavras, um algoritmo de clustering e técnicas de filtragem [Tavares, Faria e Martins, 2012].

Biomechanical modeling and simulation of the spider crab (maja brachydactyla)

Uma linha de pesquisa e desenvolvimento na área da robótica, que tem recebido atenção crescente nos últimos anos, é o desenvolvimento de robôs biologicamente inspirados. A ideia é adquirir conhecimento de seres biológicos, cuja evolução ocorreu ao longo de milhões de anos, e aproveitar o conhecimento assim adquirido para implementar a locomoção pelos mesmos métodos (ou pelo menos usar a inspiração biológica) nas máquinas que se constroem. Acredita-se que desta forma é possível desenvolver máquinas com capacidades semelhantes às dos seres biológicos em termos de capacidade e eficiência energética de locomoção. Uma forma de compreender melhor o funcionamento destes sistemas, sem a necessidade de desenvolver protótipos dispendiosos e com longos tempos de desenvolvimento é usar modelos de simulação. Com base nestas ideias, o objectivo deste trabalho passa por efectuar um estudo da biomecânica da santola (Maja brachydactyla), uma espécie de caranguejo comestível pertencente à família Majidae de artrópodes decápodes, usando a biblioteca de ferramentas SimMechanics da aplicação Matlab / Simulink. Esta tese descreve a anatomia e locomoção da santola, a sua modelação biomecânica e a simulação do seu movimento no ambiente Matlab / SimMechanics e SolidWorks.

Edição gráfica de layout fabril no apoio ao planeamento e controlo da produção

O contributo da área de investigação Interacção Humano-Computador (HCI) está patente não só na qualidade da interacção, mas também na diversificação das formas de interacção. A HCI define-se como sendo uma disciplina que se dedica ao desenho, desenvolvimento e implementação de sistemas de computação interactivos para uso humano e estudo dos fenómenos relevantes que os rodeiam. Pretende-se, no âmbito desta tese de mestrado, o desenvolvimento de um Editor Gráfico de Layout Fabril a integrar num SAD para suporte ao Planeamento e Controlo da Produção. O sistema deve ser capaz de gerar um layout fabril do qual constam, entre outros objectos, as representações gráficas e as respectivas características/atributos do conjunto de recursos (máquinas/processadores) existentes no sistema de produção a modelar. O módulo desenvolvido será integrado no projecto de I&D ADSyS (Adaptative Decision Support System for Interactive Scheduling with MetaCognition and User Modeling Experience), melhorando aspectos de interacção referentes ao sistema AutoDynAgents, um dedicado ao escalonamento, planeamento e controlo de produção. Foi realizada a análise de usabilidade a este módulo com a qual se pretendeu realizar a respectiva avaliação, através da realização de um teste de eficiência e do preenchimento de um inquérito, da qual se identificaram um conjunto de melhorias e sugestões a serem consideradas no refinamento deste módulo.

Three-dimensional modeling of tongue during speech using MRI data

The tongue is the most important and dynamic articulator for speech formation, because of its anatomic aspects (particularly, the large volume of this muscular organ comparatively to the surrounding organs of the vocal tract) and also due to the wide range of movements and flexibility that are involved. In speech communication research, a variety of techniques have been used for measuring the three-dimensional vocal tract shapes. More recently, magnetic resonance imaging (MRI) becomes common; mainly, because this technique allows the collection of a set of static and dynamic images that can represent the entire vocal tract along any orientation. Over the years, different anatomical organs of the vocal tract have been modelled; namely, 2D and 3D tongue models, using parametric or statistical modelling procedures. Our aims are to present and describe some 3D reconstructed models from MRI data, for one subject uttering sustained articulations of some typical Portuguese sounds. Thus, we present a 3D database of the tongue obtained by stack combinations with the subject articulating Portuguese vowels. This 3D knowledge of the speech organs could be very important; especially, for clinical purposes (for example, for the assessment of articulatory impairments followed by tongue surgery in speech rehabilitation), and also for a better understanding of acoustic theory in speech formation.

Analysis of tongue shape and motion in speech production using statistical modeling

The mechanisms of speech production are complex and have been raising attention from researchers of both medical and computer vision fields. In the speech production mechanism, the articulator’s study is a complex issue, since they have a high level of freedom along this process, namely the tongue, which instigates a problem in its control and observation. In this work it is automatically characterized the tongues shape during the articulation of the oral vowels of Portuguese European by using statistical modeling on MR-images. A point distribution model is built from a set of images collected during artificially sustained articulations of Portuguese European sounds, which can extract the main characteristics of the motion of the tongue. The model built in this work allows under standing more clearly the dynamic speech events involved during sustained articulations. The tongue shape model built can also be useful for speech rehabilitation purposes, specifically to recognize the compensatory movements of the articulators during speech production.

Multimedia fate modeling and comparative impact on freshwater ecosystems of pharmaceuticals from biosolids-amended soils

This study modeled the impact on freshwater ecosystems of pharmaceuticals detected in biosolids following application on agricultural soils. The detected sulfonamides and hydrochlorothiazide displayed comparatively moderate retention in solid matrices and, therefore, higher transfer fractions from biosolids to the freshwater compartment. However, the residence times of these pharmaceuticals in freshwater were estimated to be short due to abiotic degradation processes. The non-steroidal anti-inflammatory mefenamic acid had the highest environmental impact on aquatic ecosystems and warrants further investigation. The estimation of the solid-water partitioning coefficient was generally the most influential parameter of the probabilistic comparative impact assessment. These results and the modeling approach used in this study serve to prioritize pharmaceuticals in the research effort to assess the risks and the environmental impacts on aquatic biota of these emerging pollutants.