966 resultados para Functional Capacity Classification
Resumo:
Objectives: Assess the effect of re-expansive respiratory patterns associated to respiratory biofeedback (RBF) on pulmonary function, respiratory muscle strength and habits in individuals with functional mouth breathing (FMB). Methods: Sixty children with FMB were divided into experimental and control groups. The experimental group was submitted to 15 sessions of re-expansive respiratory patterns associated to RBF (biofeedback pletsmovent; MICROHARD (R) V1.0), which provided biofeedback of the thoracic and abdominal movements. The control group was submitted to 15 sessions using biofeedback alone. Spirometry, maximum static respiratory pressure measurements and questions regarding habits (answered by parents/guardians) were carried out before and after therapy. The Student`s t-test for paired data and non-parametric tests were employed for statistical analysis at a 5% Level of significance. Results: Significant changes were found in forced vital. capacity, Tiffeneau index scores, maximum expiratory pressure, maximum inspiratory pressure and habits assessed in FMB with the use of RBF associated to the re-expansive patterns. No significant differences were found comparing the experimental and control groups. Conclusions: The results allow the conclusion that RBF associated to re-expansive patterns improves forced vital capacity, Tiffeneau index scores, respiratory muscle strength and habits in FMB and can therefore be used as a form of therapy for such individuals. (C) 2008 Elsevier Ireland Ltd. All rights reserved.
Resumo:
Background Asbestosis is associated with lung cellular and immunological abnormalities. Induced sputum cytology and local and systemic markers of inflammation may be helpful to characterize disease status and progression in these patients. Methods Thirty-nine ex-workers with asbestosis on high-resolution CT (HRCT) and 21 non-exposed controls were evaluated. Sputum cytology and IL-8 in serum and sputum were related to lung function impairment. Results Subjects with asbestosis had reduced sputum cellularity but higher macrophagel neutrophil ratio and % macrophage as compared with controls. Sputum and serum IL-8 were also higher in patients with asbestosis (P < 0.05). In addition, evidence of lung architectural distorption on HRCT was associated with increased levels of serum IL-8. Interestingly, absolute macrophage number was negatively correlated with total lung capacity (r = -0.40; P = 0.04) and serum IL-8 to lung diffiusing capacity (r = -0.45; P = 0.01). Conclusions Occupationally exposed subjects with asbestosis on HRCT have cytologic abnormalities in induced sputum and increased local and systemic pro-inflammatory status which are correlated to functional impairment.
Resumo:
Introduction: Total knee arthroplasty (TKA) imposes many risks. TKA infection is not the most frequent complication, but is probably the most serious one. Two-step review is the procedure of choice in deep knee prosthesis infection. On the other hand, aseptic prosthesis detachment represents almost half of the primary arthroplasty review indications, Patient`s satisfaction level might diminish after reviews. Objective: The objective of this study was to compare the quality of life and final result of TKA review for septic and aseptic failures. Methods: The patients were assessed using the HSS and SF-36 scores. The patients were divided in two groups: one group submitted to two-step review (septic) and the other to one-step review (aseptic). The analysis of the data obtained shows better scores for the second group in HSS and in 06 of 08 domains of SF-36 classification. Conclusions: The on-step review of total knee arthroplasty leads to better functional outcomes.
Resumo:
Background and Aims: To test whether different degrees of immunologic and fibrotic airway remodeling processes occur in idiopathic interstitial pneumonias (IIPs), with impact on functional tests and survival, we studied the collagen/elastic system and immune cell density in the bronchiolar interstitium of lungs with the major types of IIPs. Materials and Methods: Histochemistry, immunohistochemistry and morphometric analysis were used to evaluate collagen/elastic fibers and immune cells in the bronchiolar interstitium of open lung biopsies of patients with cryptogenic organizing pneumonia [COP/organizing pneumonia (OP) = 10], acute interstitial pneumonia [AIP/diffuse alveolar damage (DAD) = 20], nonspecific interstitial pneumonia (NSIP/NSIP = 20) and idiopathic pulmonary fibrosis/usual interstitial pneumonia (UIP) = 20. Results: OP lungs presented a significant increase in collagenous/elastic fibers and in the total density of immune cells in the bronchiolar interstitium compared to controls, DAD, NSIP and UIP. We observed a significant increase in CD4, CD8 and CD20 lymphocytes, as well as in neutrophils, macrophages and plasma cells in OP. The increased amount of elastic fibers in the bronchiolar interstitium from OP lungs has a direct association with forced vital capacity (FVC) (r(s) = 0.99, P = 0.03). The most important survival predictor was CD20+ lymphocytes in the bronchiolar interstitium. In decreasing order, patients with UIP [Odds Ratio (OR) = 35.01], high forced expiratory volume in 1 s (FEV1)/FVC FVC (OR = 7.01), increased CD20+ lymphocytes (OR = 4.44) and collagenous/elastic fiber densities (OR = 2.03 and OR = 1.49, respectively) in the bronchiolar interstitium were those who had the greatest risk of death, followed by those with AIP, NSIP and COP. Conclusion: Different degrees of immunologic and fibroelastotic airway remodeling processes occur in the major types of IIPs with impact on physiological tests and survival.
Resumo:
Intense lifestyle modifications can change the high-density lipoprotein (HDL) cholesterol concentration. The aim of the present study was to analyze the early effects of short-term exercise training, without any specific diet, on the HDL cholesterol plasma levels and HDL functional characteristics in patients with the metabolic syndrome (MS). We studied 30 sedentary subjects, 20 with and 10 without the MS. The patients with the MS underwent moderate intensity exercise training for 3 months on bicycle ergometers. Blood was sampled before and after training for biochemical analysis, paraoxonase-1 activity, and HDL subfraction composition and antioxidative capacity. Lipid transfer to HDL was assayed in vitro using a labeled nanoemulsion as the lipid donor. At baseline, the MS group had greater triglyceride levels and a lower HDL cholesterol concentration and lower paraoxonase-1 activity than did the controls. Training decreased the plasma triglycerides but did not change the low-density lipoprotein or HDL cholesterol levels. Nonetheless, exercise training increased the HDL subfractions` antioxidative capacity and paraoxonase-1 activity. After training, the MS group had compositional changes in the smallest HDL subfractions associated with increased free cholesterol and cholesterol ester transfers to HDL, reaching normal values. In conclusion, the present investigation has added relevant information about the dissociation between the quantitative and qualitative aspects of HDL after short-term exercise training without any specific diet in those with the MS, highlighting the importance of evaluating the functional aspects of the lipoproteins, in addition to their plasma levels. (C) 2011 Elsevier Inc. All rights reserved. (Am J Cardiol 2011;107:1168-1172)
Resumo:
The vascular and bryophyte floras of subantarctic Heard Island were classified using cluster analysis into six vegetation communities: Open Cushion Carpet, Mossy Feldmark, Wet Mixed Herbfield, Coastal Biotic Vegetation, Saltspray Vegetation, and Closed Cushion Carpet. Multidimensional scaling indicated that the vegetation communities were not well delineated but were continua. Discriminant analysis and a classification tree identified altitude, wind, peat depth, bryophyte cover and extent of bare ground, and particle size as discriminating variables. The combination of small area, glaciation, and harsh climate has resulted in reduced vegetation variety in comparison to those subantarctic islands north of the Antarctic Polar Front Zone. Some of the functional groups and vegetation communities found on warmer subantarctic islands are not present on Heard Island, notably ferns and sedges and fernbrakes and extensive mires, respectively.
Resumo:
A comparative study of carbon gasification with O-2 and CO2 was conducted by using density functional theory calculations. It was found that the activation energy and the number of active sites in carbon gasification reactions are significantly affected by both the capacity and manner of gas chemisorption. O-2 has a strong adsorption capacity and the dissociative chemisorption of O-2 is thermodynamically favorable on either bare carbon surface or even isolated edge sites. As a result, a large number of semiquinone and o-quinone oxygen can be formed indicating a significant increase in the number of active sites. Moreover, the weaker o-quinone C-C bonds can also drive the reaction forward at (ca. 30%) lower activation energy. Epoxy oxygen forms under relatively high O-2 pressure, and it can only increase the number of active sites, not further reduce the activation energy. CO2 has a lower adsorption capacity. Dissociative chemisorption of CO2 can only occur on two consecutive edge sites and o-quinone oxygen formed from CO2 chemisorption is negligible, let alone epoxy oxygen. Therefore, CO2-carbon reaction needs (ca 30%) higher activation energy. Furthermore, the effective active sites are also reduced by the manner Of CO2 chemisorption. A combination of the higher activation energy and the fewer active sites leads to the much lower reaction rate Of CO2-carbon.
Resumo:
The growing importance and influence of new resources connected to the power systems has caused many changes in their operation. Environmental policies and several well know advantages have been made renewable based energy resources largely disseminated. These resources, including Distributed Generation (DG), are being connected to lower voltage levels where Demand Response (DR) must be considered too. These changes increase the complexity of the system operation due to both new operational constraints and amounts of data to be processed. Virtual Power Players (VPP) are entities able to manage these resources. Addressing these issues, this paper proposes a methodology to support VPP actions when these act as a Curtailment Service Provider (CSP) that provides DR capacity to a DR program declared by the Independent System Operator (ISO) or by the VPP itself. The amount of DR capacity that the CSP can assure is determined using data mining techniques applied to a database which is obtained for a large set of operation scenarios. The paper includes a case study based on 27,000 scenarios considering a diversity of distributed resources in a 33 bus distribution network.
Resumo:
OBJECTIVE: To evaluate musculoskeletal disorders among active industrial workers. METHODS: The study was carried out in São Carlos, Southeastern Brazil, in 2005. One hundred and thirty-four female workers were physically evaluated and answered questions about their physical symptoms, filled out a pain scale and gave responses in the Oswestry Disability Questionnaire, and the Work Ability Index questionnaire. The data were analyzed descriptively, and in correlation tests and through applying logistic regression. The outcome was evaluated in relation to the perceptions of pain, symptoms, physical assessment, ability to work and disability. RESULTS: Clinical evaluations and sick leave presented positive correlations with the subjective variables. The Work Ability Index presented a negative correlation with the physical disability index (r=-0.69). Symptoms reported at the time of the assessment presented a good correlation with the results from the pain scale and the clinical findings. Previous sick leave showed an association with disability (OR=1.13; 95% CI:1.08;1.18). CONCLUSION: Symptom reports and pain scales may be useful for assessing current conditions at the time of evaluating individuals with work-related musculoskeletal disorders, as they are easier to apply. In more severe cases of such injuries, clinical and functional evaluations and questionnaires such as those relating to ability to work and disability are preferable. Precise and specific evaluations of these disorders may contribute towards fairer legal and administrative decisions.
Resumo:
Introdução: A sequência de movimento de sentado para de pé (SPP) exige um elevado controlo postural (CP). Em indivíduos com doença de Parkinson (DP), os circuitos que envolvem os ajustes posturais antecipatórios (APA’s) parecem estar afetados, refletindo-se numa diminuição do CP com repercussões nesta sequência de movimento. Objetivo: Avaliar o comportamento dos APA’s na tibio-társica na sequência de movimento SPP em indivíduos com DP. Métodos: Recorreu-se ao estudo de 4 casos com DP, com tempo de evolução entre os 3 e 17 anos, objeto de uma intervenção de fisioterapia baseada nos princípios do Conceito de Bobath durante 12 semanas. Antes (M0) e após (M1) a intervenção procedeu-se ao registo eletromiográfico dos músculos tibial anterior (TA) e solear (SOL) bilateralmente e durante a sequência de SPP. Adicionalmente foram também utilizadas a Escala de Equilíbrio de Berg, a Modified Falls Efficacy Scale (MFES) e a Classificação Internacional de Funcionalidade (CIF), para, indiretamente, averiguar o impacto funcional da reorganização dos APA’s. Resultados: Em M0 os resultados sugerem uma diminuição APA’s, uma vez que se observou: 1) diferentes tempos de ativação do TA e do SOL entre membros e 2) uma ativação prévia do SOL ao TA para os participantes A, C e D. Em M1, observou-se uma aproximação ao comtemplado para os APA’s para a maioria dos indivíduos. Os resultados na escala de Berg e MFES, de M0 para M1, sugerem um aumento do equilíbrio e da capacidade de confiança na maioria dos participantes (A, 21/42 pontos, B manteve a pontuação final 31 pontos, C, 50/54 pontos e D 45/53 pontos na escala de Berg; A, 30/43 pontos, B, 21/18 pontos, C, 70/68 pontos e D, 40/64 pontos na MFES;). Também se observaram melhorias nas atividades e participação da CIF. Conclusão: nos indivíduos em estudo verificou-se, de uma forma geral, uma modificação no sentido da aproximação do período comtemplado para os APA’s, em M1. Nos sujeitos A, C, e D verificou-se uma modificação do tempo de activação do SOL em função da actividade do TA em M1. No individuo B, à esquerda não se verificou o mesmo comportamento, verificou-se a activação inversa do SOL ao TA.
Resumo:
A Sequência de Movimento de Sentado para de Pé (SMSP) é um marco importante na independência funcional da criança, sendo a sua qualidade afetada em casos de alteração do controlo postural do tronco. É por isso motivo de especial foco neste estudo, como elemento avaliativo e interventivo. Este estudo tem como objetivo a análise da modificação de componentes motores relacionados com o controlo postural, durante a SMSP, em 5 crianças com alterações neuromotoras, face à aplicação de um programa de intervenção baseado no Tratamento de Neuro Desenvolvimento (TND). Foi para tal utilizada a análise cinemática da SMSP - nomeadamente as variáveis “variação do deslocamento dos segmentos cabeça e tronco” e “variação do ângulo perna-pé” entre o momento inicial e o seat-off – complementada com a aplicação do Teste de Medida da Função Motora 88 (TMFM-88) e a Classificação Internacional da Funcionalidade Incapacidade e Saúde-Versão Crianças e Jovens (CIF-CJ), bem como a avaliação de componentes de movimento com recurso a registo de imagem. A análise cinemática demonstrou uma diminuição do deslocamento dos segmentos cabeça e tronco na maioria dos casos, bem como uma maior mobilidade da tíbia sobre pé. Verificou-se um aumento do score final do TMFM-88, em todos os casos. A CIF-CJ não evidenciou alterações entre o início e o término do período de intervenção. O registo de imagem demonstrou alterações positivas visíveis no alinhamento de segmentos, nível de atividade, controlo postural, e recurso a estratégias compensatórias no conjunto postural sentado e na SMSP. Após o período de intervenção as crianças deste estudo evidenciaram modificações positivas nas variáveis em estudo, nomeadamente 1) diminuição do deslocamento dos segmentos cabeça e tronco na fase inicial da SMSP, 2) aumento da variação do ângulo perna-pé na fase inicial da SMSP, 3) aumento do score total da TMFM-88, 4) alteração positiva dos componentes de movimento alinhamento de segmentos e nível de atividade e 5) redução do recurso a estratégias compensatórias de movimento na SMSP. Estas modificações sugerem um controlo postural mais eficiente.
Resumo:
To cope with permanent fluctuations in demand, organizations are challenged to organize their manpower capacity in a flexible way. Different strategies of manpower planning are being used for this purpose. Using data from the 2002 Panel Survey of Organisations Flanders, we first verify to what extent temporal, contractual and functional flexibility strategies are applied in Flemish organizations. Subsequently, logistic regression is used to analyse the link between these flexible work strategies and a ‘fitting manpower capacity’. While the results show a negative association between the use of temporal or contractual flexibility measures and a balanced manpower capacity, functional flexibility seems to be positively related. The different logics in which numerical and functional flexibility proceed can be labeled as ‘curative’ versus ‘preventive’ strategies of flexibility. Further analyses discern between various interpretations of functional flexibility and assess whether different team types make a contribution to a fitting manpower capacity.
Resumo:
This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds. NMR-based classification of photochemical and enzymatic reactions. Photochemical and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen SOMs) and Random Forests (RFs) taking as input the difference between the 1H NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data. A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases was able to correctly classify 75% of an independent test set in terms of the EC number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used. This study was performed with NMR data simulated from the molecular structure by the SPINUS program. In the design of one test set, simulated data was combined with experimental data. The results support the proposal of linking databases of chemical reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions. Genome-scale classification of enzymatic reactions from their reaction equation. The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken, changed, and made during a chemical reaction. The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods should be available to automatically compare metabolic reactions and for the automatic assignment of EC numbers to reactions still not officially classified. In this study, the genome-scale data set of enzymatic reactions available in the KEGG database was encoded by the MOLMAP descriptors, and was submitted to Kohonen SOMs to compare the resulting map with the official EC number classification, to explore the possibility of predicting EC numbers from the reaction equation, and to assess the internal consistency of the EC classification at the class level. A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions. RFs were also used to assign the four levels of the EC hierarchy from the reaction equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases (for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively. In the course of the experiments with metabolic reactions we suggested that the MOLMAP / SOM concept could be extended to the representation of other levels of metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different types of metabolism and pathways that do not share similarities in terms of EC numbers. Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function. The results indicated that for LJ-type potentials, NNs can be trained to generate accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown. The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo, the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes. Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task. The data consisted of energy values, from Density Functional Theory (DFT) calculations, at different distances, for several molecular orientations and three electrode adsorption sites. The results indicate that NNs require a data set large enough to cover well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions. Therefore, they can be used in molecular simulations, particularly for the ethanol/Au (111) interface which is the case studied in the present Thesis. Once properly trained, the networks are able to produce, as output, any required number of energy points for accurate interpolations.
Resumo:
In practice the robotic manipulators present some degree of unwanted vibrations. The advent of lightweight arm manipulators, mainly in the aerospace industry, where weight is an important issue, leads to the problem of intense vibrations. On the other hand, robots interacting with the environment often generate impacts that propagate through the mechanical structure and produce also vibrations. In order to analyze these phenomena a robot signal acquisition system was developed. The manipulator motion produces vibrations, either from the structural modes or from endeffector impacts. The instrumentation system acquires signals from several sensors that capture the joint positions, mass accelerations, forces and moments, and electrical currents in the motors. Afterwards, an analysis package, running off-line, reads the data recorded by the acquisition system and extracts the signal characteristics. Due to the multiplicity of sensors, the data obtained can be redundant because the same type of information may be seen by two or more sensors. Because of the price of the sensors, this aspect can be considered in order to reduce the cost of the system. On the other hand, the placement of the sensors is an important issue in order to obtain the suitable signals of the vibration phenomenon. Moreover, the study of these issues can help in the design optimization of the acquisition system. In this line of thought a sensor classification scheme is presented. Several authors have addressed the subject of the sensor classification scheme. White (White, 1987) presents a flexible and comprehensive categorizing scheme that is useful for describing and comparing sensors. The author organizes the sensors according to several aspects: measurands, technological aspects, detection means, conversion phenomena, sensor materials and fields of application. Michahelles and Schiele (Michahelles & Schiele, 2003) systematize the use of sensor technology. They identified several dimensions of sensing that represent the sensing goals for physical interaction. A conceptual framework is introduced that allows categorizing existing sensors and evaluates their utility in various applications. This framework not only guides application designers for choosing meaningful sensor subsets, but also can inspire new systems and leads to the evaluation of existing applications. Today’s technology offers a wide variety of sensors. In order to use all the data from the diversity of sensors a framework of integration is needed. Sensor fusion, fuzzy logic, and neural networks are often mentioned when dealing with problem of combing information from several sensors to get a more general picture of a given situation. The study of data fusion has been receiving considerable attention (Esteban et al., 2005; Luo & Kay, 1990). A survey of the state of the art in sensor fusion for robotics can be found in (Hackett & Shah, 1990). Henderson and Shilcrat (Henderson & Shilcrat, 1984) introduced the concept of logic sensor that defines an abstract specification of the sensors to integrate in a multisensor system. The recent developments of micro electro mechanical sensors (MEMS) with unwired communication capabilities allow a sensor network with interesting capacity. This technology was applied in several applications (Arampatzis & Manesis, 2005), including robotics. Cheekiralla and Engels (Cheekiralla & Engels, 2005) propose a classification of the unwired sensor networks according to its functionalities and properties. This paper presents a development of a sensor classification scheme based on the frequency spectrum of the signals and on a statistical metrics. Bearing these ideas in mind, this paper is organized as follows. Section 2 describes briefly the robotic system enhanced with the instrumentation setup. Section 3 presents the experimental results. Finally, section 4 draws the main conclusions and points out future work.
Resumo:
In the present paper we assess the performance of information-theoretic inspired risks functionals in multilayer perceptrons with reference to the two most popular ones, Mean Square Error and Cross-Entropy. The information-theoretic inspired risks, recently proposed, are: HS and HR2 are, respectively, the Shannon and quadratic Rényi entropies of the error; ZED is a risk reflecting the error density at zero errors; EXP is a generalized exponential risk, able to mimic a wide variety of risk functionals, including the information-thoeretic ones. The experiments were carried out with multilayer perceptrons on 35 public real-world datasets. All experiments were performed according to the same protocol. The statistical tests applied to the experimental results showed that the ubiquitous mean square error was the less interesting risk functional to be used by multilayer perceptrons. Namely, mean square error never achieved a significantly better classification performance than competing risks. Cross-entropy and EXP were the risks found by several tests to be significantly better than their competitors. Counts of significantly better and worse risks have also shown the usefulness of HS and HR2 for some datasets.