Eliana Costa e Silva | Instituto Politecnico do Porto (original) (raw)
Uploads
Papers by Eliana Costa e Silva
International Journal of Advanced Robotic Systems, 2021
As robots are starting to become part of our daily lives, they must be able to cooperate in a nat... more As robots are starting to become part of our daily lives, they must be able to cooperate in a natural and efficient manner with humans to be socially accepted. Human-like morphology and motion are often considered key features for intuitive human-robot interactions because they allow human peers to easily predict the final intention of a robotic movement. Here, we present a novel motion planning algorithm, the Human-like Upper-limb Motion Planner, for the upper limb of anthropomorphic robots, that generates collision-free trajectories with human-like characteristics. Mainly inspired from established theories of human motor control, the planning process takes into account a task-dependent hierarchy of spatial and postural constraints modelled as cost functions. For experimental validation, we generate arm-hand trajec-tories in a series of tasks including simple point-to-point reaching movements and sequential object-manipulation paradigms. Being a major contribution to the current literature, specific focus is on the kinematics of naturalistic arm movements during the avoidance of obstacles. To evaluate human-likeness, we observe kinematic regularities and adopt smoothness measures that are applied in human motor control studies to distinguish between well-coordinated and impaired movements. The results of this study show that the proposed algorithm is capable of planning arm-hand movements with human-like kinematic features at a computational cost that allows fluent and efficient human-robot interactions.
Journal of Applied Statistics
Neural Computing and Applications
This study focus on the twelve indicators of the entrepreneurial ecosystem, defined by the Global... more This study focus on the twelve indicators of the entrepreneurial ecosystem, defined by the Global Entrepreneurship Monitor (GEM) project -the Entrepreneurial Framework Conditions (EFCs). EFCs are relate more specifically to the quality of the entrepreneurial ecosystem. The present study analyses how experts' perceptions have changed in Portugal between 2010 and 2016 by establishing a comparative analysis between the Portuguese reality and the reality in other European countries. Based on the economic performance's similarities across countries before 2010, this study is mainly concerned with the evolution of experts' perceptions on the EFCs in Portugal and how do they differ in comparison with Italy, Greece and Spain. To achieve this goal the present study uses multivariate cluster analysis to group the European economies according to the experts' perceptions on the EFCs of their home country.
Journal of Applied Statistics
In this work we present a Factor Analysis of chemical and environmental variables of the water co... more In this work we present a Factor Analysis of chemical and environmental variables of the water column and hydromorphological features of several Portuguese reservoirs. The objective is to reduce the initial number of variables, keeping their common characteristics. Using the Factor Analysis, the environmental variables measured in the epilimnion and in the hypolimnion, together with the hydromorphological characteristics of the dams were reduced from 63 variables to only 13 factors, which explained a total of 83.348% of the variance in the original data. After performing rotation using the Varimax method, the relations between the factors and the original variables got clearer and more explainable, which provided a Factor Analysis model for these environmental variables using 13 varifactors: Water quality and distance to the source, Hypolimnion chemical composition, Sulfite-reducing bacteria and nutrients, Coliforms and faecal streptococci, Reservoir depth, Temperature, Location, among other factors.
Global Entrepreneurship Monitor is a large scale database for internationally comparative entrepr... more Global Entrepreneurship Monitor is a large scale database for internationally comparative entrepreneurship that includes information about many aspects of entrepreneurship activities, perceptions, conditions, national and regional policy, among others, of a large number of countries. This project has two main sources of primary data: the Adult Population Survey and the National Expert Survey. In this work the 2011 and 2012 National Expert Survey datasets are studied. Our goal is to analyze the effects of the different type of entrepreneurship expert specialization on the perceptions about the Entrepreneurial Framework Conditions. For this purpose the multivariate analysis of variance is used. Some similarities between the results obtained for the 2011 and 2012 datasets were found, however the differences between experts still exist.
Credit scoring is an application of financial risk forecasting to consumer lending. In this study... more Credit scoring is an application of financial risk forecasting to consumer lending. In this study, statistical analysis is applied to credit scoring data from a financial institution to evaluate the default risk of consumer loans. The default risk was found to be influenced by the spread, the age of the consumer, the number of credit cards owned by the consumer. A lower spread, a higher number of credit cards and a younger age of the borrower are factors that decrease the risk of default. Clients receiving the salary in the same banking institution of the loan have less chances of default than clients receiving their salary in another institution. We also found that clients in the lowest income tax echelon have more propensity to default.
Superquadric are mathematically quite simple and have the ability to obtain a variety of shapes u... more Superquadric are mathematically quite simple and have the ability to obtain a variety of shapes using low order parameterization. Furthermore they present closed-form equations and therefore can be used in the formulation of robotic movement planning problems, in particular in obstacle-avoidance and grasping constraints. In this paper we explore the modeling of objects using superquadrics. The classical nonlinear optimization problem for fitting shapes is extended by adding nonlinear constraints. The numerical results obtained by two different optimization methods are presented and a comparison of the volume of the superquadrics to the volume of simple ellipsoids is made.
In this paper a comparison between using global and local optimization techniques for solving the... more In this paper a comparison between using global and local optimization techniques for solving the problem of generating human-like arm and hand movements for an anthropomorphic dual arm robot is made. Although the objective function involved in each optimization problem is convex, there is no evidence that the admissible regions of these problems are convex sets. For the sequence of movements for which the numerical tests were done there were no significant differences between the optimal solutions obtained using the global and the local techniques. This suggests that the optimal solution obtained using the local solver is indeed a global solution.
International Journal of Advanced Robotic Systems, 2021
As robots are starting to become part of our daily lives, they must be able to cooperate in a nat... more As robots are starting to become part of our daily lives, they must be able to cooperate in a natural and efficient manner with humans to be socially accepted. Human-like morphology and motion are often considered key features for intuitive human-robot interactions because they allow human peers to easily predict the final intention of a robotic movement. Here, we present a novel motion planning algorithm, the Human-like Upper-limb Motion Planner, for the upper limb of anthropomorphic robots, that generates collision-free trajectories with human-like characteristics. Mainly inspired from established theories of human motor control, the planning process takes into account a task-dependent hierarchy of spatial and postural constraints modelled as cost functions. For experimental validation, we generate arm-hand trajec-tories in a series of tasks including simple point-to-point reaching movements and sequential object-manipulation paradigms. Being a major contribution to the current literature, specific focus is on the kinematics of naturalistic arm movements during the avoidance of obstacles. To evaluate human-likeness, we observe kinematic regularities and adopt smoothness measures that are applied in human motor control studies to distinguish between well-coordinated and impaired movements. The results of this study show that the proposed algorithm is capable of planning arm-hand movements with human-like kinematic features at a computational cost that allows fluent and efficient human-robot interactions.
Journal of Applied Statistics
Neural Computing and Applications
This study focus on the twelve indicators of the entrepreneurial ecosystem, defined by the Global... more This study focus on the twelve indicators of the entrepreneurial ecosystem, defined by the Global Entrepreneurship Monitor (GEM) project -the Entrepreneurial Framework Conditions (EFCs). EFCs are relate more specifically to the quality of the entrepreneurial ecosystem. The present study analyses how experts' perceptions have changed in Portugal between 2010 and 2016 by establishing a comparative analysis between the Portuguese reality and the reality in other European countries. Based on the economic performance's similarities across countries before 2010, this study is mainly concerned with the evolution of experts' perceptions on the EFCs in Portugal and how do they differ in comparison with Italy, Greece and Spain. To achieve this goal the present study uses multivariate cluster analysis to group the European economies according to the experts' perceptions on the EFCs of their home country.
Journal of Applied Statistics
In this work we present a Factor Analysis of chemical and environmental variables of the water co... more In this work we present a Factor Analysis of chemical and environmental variables of the water column and hydromorphological features of several Portuguese reservoirs. The objective is to reduce the initial number of variables, keeping their common characteristics. Using the Factor Analysis, the environmental variables measured in the epilimnion and in the hypolimnion, together with the hydromorphological characteristics of the dams were reduced from 63 variables to only 13 factors, which explained a total of 83.348% of the variance in the original data. After performing rotation using the Varimax method, the relations between the factors and the original variables got clearer and more explainable, which provided a Factor Analysis model for these environmental variables using 13 varifactors: Water quality and distance to the source, Hypolimnion chemical composition, Sulfite-reducing bacteria and nutrients, Coliforms and faecal streptococci, Reservoir depth, Temperature, Location, among other factors.
Global Entrepreneurship Monitor is a large scale database for internationally comparative entrepr... more Global Entrepreneurship Monitor is a large scale database for internationally comparative entrepreneurship that includes information about many aspects of entrepreneurship activities, perceptions, conditions, national and regional policy, among others, of a large number of countries. This project has two main sources of primary data: the Adult Population Survey and the National Expert Survey. In this work the 2011 and 2012 National Expert Survey datasets are studied. Our goal is to analyze the effects of the different type of entrepreneurship expert specialization on the perceptions about the Entrepreneurial Framework Conditions. For this purpose the multivariate analysis of variance is used. Some similarities between the results obtained for the 2011 and 2012 datasets were found, however the differences between experts still exist.
Credit scoring is an application of financial risk forecasting to consumer lending. In this study... more Credit scoring is an application of financial risk forecasting to consumer lending. In this study, statistical analysis is applied to credit scoring data from a financial institution to evaluate the default risk of consumer loans. The default risk was found to be influenced by the spread, the age of the consumer, the number of credit cards owned by the consumer. A lower spread, a higher number of credit cards and a younger age of the borrower are factors that decrease the risk of default. Clients receiving the salary in the same banking institution of the loan have less chances of default than clients receiving their salary in another institution. We also found that clients in the lowest income tax echelon have more propensity to default.
Superquadric are mathematically quite simple and have the ability to obtain a variety of shapes u... more Superquadric are mathematically quite simple and have the ability to obtain a variety of shapes using low order parameterization. Furthermore they present closed-form equations and therefore can be used in the formulation of robotic movement planning problems, in particular in obstacle-avoidance and grasping constraints. In this paper we explore the modeling of objects using superquadrics. The classical nonlinear optimization problem for fitting shapes is extended by adding nonlinear constraints. The numerical results obtained by two different optimization methods are presented and a comparison of the volume of the superquadrics to the volume of simple ellipsoids is made.
In this paper a comparison between using global and local optimization techniques for solving the... more In this paper a comparison between using global and local optimization techniques for solving the problem of generating human-like arm and hand movements for an anthropomorphic dual arm robot is made. Although the objective function involved in each optimization problem is convex, there is no evidence that the admissible regions of these problems are convex sets. For the sequence of movements for which the numerical tests were done there were no significant differences between the optimal solutions obtained using the global and the local techniques. This suggests that the optimal solution obtained using the local solver is indeed a global solution.