Buscar
Mostrando ítems 1-10 de 13
Artículo
Boosting offline handwritten text recognition in historical documents with few labeled lines
(Institute of Electrical and Electronics Engineers Inc., 2021)
In this paper we address the problem of offline handwritten text recognition (HTR) in historical documents when few labeled samples are available and some of them contain errors in the train set. Our three main contributions ...
Artículo
A Sensor-Based mHealth Platform for Remote Monitoring and Intervention of Frailty Patients at Home
(MDPI, 2021-11)
Frailty syndrome is an independent risk factor for serious health episodes, disability, hospitalization, falls, loss of mobility, and cardiovascular disease. Its high reversibility demands personalized interventions among ...
Artículo
A bivariate volterra series model for the design of power amplifier digital predistorters
(MDPI, 2021)
The operation of the power amplifier (PA) in wireless transmitters presents a trade-off between linearity and power efficiency, being more efficient when the device exhibits the highest nonlinearity. Its modeling and ...
Artículo
Sparse identification of volterra models for power amplifiers without pseudoinverse computation
(Institute of Electrical and Electronics Engineers Inc., 2021)
We present a new formulation of the doubly orthogonal matching pursuit (DOMP) algorithm for the sparse recovery of Volterra series models. The proposal works over the covariance matrices by taking advantage of the orthogonal ...
Artículo
An Upgraded Dual-Band Digital Predistorter Model for Power Amplifiers Linearization
(IEEE, 2021-01)
Digital predistortion (DPD) based on Volterra models is commonly employed to counteract the nonlinear distortion of power amplifiers. However, when concurrent dual-band signals are transmitted, 2-D DPD models are required. ...
Artículo
L1-norm unsupervised Fukunaga-Koontz transform
(Elsevier, 2021)
The Fukunaga-Koontz transform (FKT) is a powerful supervised feature extraction method used in twoclass recognition problems, particularly when the classes have equal mean vectors but different covariance matrices. The ...
Tesis Doctoral
Sobre las propiedades discriminativas del análisisen componentes principales basado en la norma L1
(2021-09-30)
El análisis de componentes principales (PCA) basado en la norma L1 es una técnica cada vez más popular para el análisis de datos multivariantes. Como idea intuitiva se utiliza que, para las direcciones en las que la nube ...
Artículo
Desarrollo de un bioimpedancímetro portable para pacientes con enfermedad renal crónica y deportistas de alto rendimiento
(Instituto Tecnológico de Costa Rica, 2021)
El presente artículo da cuenta de la investigación para la innovación, diseño y desarrollo industrial de un dispositivo médico portable que obtiene datos relevantes de la bioimpedancia humana con precisión clínica, ...
Artículo
Internet of things in health: Requirements, issues, and gaps
(Elsevier, 2021-09)
Background and objectives: The Internet of Things (IoT) paradigm has been extensively applied to several sectors in the last years, ranging from industry to smart cities. In the health domain, IoT makes possible new scenarios ...
Artículo
A Low-Complexity Double EP-based Detector for Iterative Detection and Decoding in MIMO
(Institute of Electrical and Electronics Engineers Inc., 2021)
We propose a new iterative detection and decoding (IDD) algorithm for multiple-input multiple-output (MIMO) based on expectation propagation (EP) with application to massive MIMO scenarios. Two main results are ...