Soft-computing techniques applied to artificial tissue temperature estimation

Tese dout., Engenharia electrónica e computação - Processamento de sinal, Universidade do Algarve, 2008

Small area estimation using linear mixed models with heterogeneous covariance structures of random effects

The problem of Small Area Estimation is about how to produce reliable estimates of domain characteristics when the sample sizes within the domain is very small ou even zero.

Small Area Estimation of the Mean Price of the Habitation Transaction in Portugal: Methodological and Practical Issues

The Portuguese National Statistical Institute intends to produce estimations for the mean price of the habitation transation.

Small area estimation for the price of habitation transaction: comparison of different uncertainty measures of temporal EBLUP

Local level planning requires statistics for small areas, but normally due to cost or logistic constraints, sample surveys are often planned to provide reliable estimates only for large geographical regions and large subgroups of a population.

Estimation of unemployment rates in small areas of Portugal: a best linear unbiased prediction approach versus a hierarchical Bayes approach

The high level of unemployment is one of the major problems in most European countries nowadays. Hence, the demand for small area labor market statistics has rapidly increased over the past few years. The Labour Force Survey (LFS) conducted by the Portuguese Statistical Office is the main source of official statistics on the labour market at the macro level (e.g. NUTS2 and national level). However, the LFS was not designed to produce reliable statistics at the micro level (e.g. NUTS3, municipalities or further disaggregate level) due to small sample sizes. Consequently, traditional design-based estimators are not appropriate. A solution to this problem is to consider model-based estimators that "borrow information" from related areas or past samples by using auxiliary information. This paper reviews, under the model-based approach, Best Linear Unbiased Predictors and an estimator based on the posterior predictive distribution of a Hierarchical Bayesian model. The goal of this paper is to analyze the possibility to produce accurate unemployment rate statistics at micro level from the Portuguese LFS using these kinds of stimators. This paper discusses the advantages of using each approach and the viability of its implementation.

Patient´s knowledge about radiation and radiological protection

Purpose: To obtain and analyse patient´s knowledge and perceptions regarding radiation exposure, from both natural and man-made radiation of medical procedures and interventions. Verify if patients worry about their exposure when undergoing medical exams, are aware of associated risks and means of radiological protection and if their knowledge on medical radiation exposure affects their own decisions. Methods and Materials: On a medical environment a self-applied questionnaire was used as instrument and assigned to patients who would undergo medical imaging exams involving ionising radiation. A total of 300 valid questionnaires were interpreted and statistically analysed through descriptive statistics and Phi & Cramer´s V correlation tests. Results: 44.3% of patients believe most of their exposure derives from electronic appliances and 25% from medical imaging exams, while patient´s with higher education levels tend to consider is comes from the environment. The great majority of patients (95%) consider that only certified personnel should operate medical imaging equipment, but 74% never ask for their qualifications. 66.3% of patients claim that Technologists have more education on radiological protection and about 60% of patients rarely or never worry about radiation exposure when undergoing medical imaging exams. Conclusion: Patients overestimate the risks of industrial radiation exposure while they underestimate the associated risks of medical radiation exposure and the Technologist´s ability to reduce the inherent radiation exposure of medical imaging exams. Patient´s knowledge on radiation and radiological protection is based more on perceptions and beliefs, rather than factual knowledge.

The estimation and improvement of the selectivity in crustacean and fish trawls

Tese de dout., Ciências e Tecnologias das Pescas, Faculdade de Ciências do Mar e do Ambiente, Univ. do Algarve, 2003

Multilayered non-invasive temperature estimation from backscattered ultrasound

Roughly one in four breast cancer survivors report some degree of arm oedema. Lymphoedema is a build-up of excess lymph fluids in the tissues. Persistent lymphoedema leads to pain, diminished limb function, increased risk of infection, soft tissue fibrosis, and severe cases can be grossly disfiguring. From a mechanics perspective, the lymphoedemous tissue may be thought of as a two phase composite, consisting of both fluid and solid phases. Here we discuss the use of composites mixture theory to model the mechanics of lymphoedemous tissues. By treating the tissue as a fluid-solid composite, rules-of-mixtures may be used to estimate the effective moduli in terms of the properties of the individual components and their respective volume fractions in these two states.

Open source data sensing software for ultrasonic non-invasive temperature estimation

In this paper, an open source solution for measurement of temperature and ultrasonic signals (RF-lines) is proposed. This software is an alternative to the expensive commercial data acquisition software, enabling the user to tune applications to particular acquisition architectures. The collected ultrasonic and temperature signals were used for non-invasive temperature estimation using neural networks. The existence of precise temperature estimators is an essential point aiming at the secure and effective applica tion of thermal therapies in humans. If such estimators exist then effective controllers could be developed for the therapeutic instrumentation. In previous works the time-shift between RF-lines echoes were extracted, and used for creation of neural networks estimators. The obtained estimators successfully represent the temperature in the time-space domain, achieving a maximum absolute error inferior to the threshold value defined for hyperthermia/diathermia applications.

Model comparison for temperature estimation inside buildings

This paper presents a comparison between a physical model and an artificial neural network model (NN) for temperature estimation inside a building room. Despite the obvious advantages of the physical model for structure optimisation purposes, this paper will test the performance of neural models for inside temperature estimation. The great advantage of the NN model is a big reduction of human effort time, because it is not needed to develop the structural geometry and structural thermal capacities and to simulate, which consumes a great human effort and great computation time. The NN model deals with this problem as a “black box” problem. We describe the use of the Radial Basis Function (RBF), the training method and a multi-objective genetic algorithm for optimisation/selection of the RBF neural network inputs and number of neurons.

Real-time parameter estimation of dynamic temperature and humidity models for greenhouse adaptive climate control

A real-time parameter estimator for the climate discrete-time dynamic models of a greenhouse located at the North of Portugal are presented. The experiments showed that the second order models identified for the air temperature and humidity achieve a close agreement between simulated and experimantal data.

Real-time parameter estimation of dynamic temperature models for greenhouse environmental control

For a greenhouse located at UTAD-University, the methods used to estimate in real-time the parameters of the inside air temperature model will be described. The structure and the parameters of the climate discrete-time dynamic model were previously identified using data acquired during two different periods of the year.

A soft-computing approach for non-invasive temperature estimation

The domain of thermal therapies applications can be improved with the development of accurate non-invasive timespatial temperature models. These models should represent the non-linear tissue thermal behaviour and be capable of tracking temperature at both time-instant and spatial position. If such estimators exist then efficient controllers for the therapeutic instrumentation could be developed, and the desired safety and effectiveness reached.

Prediction of the solar radiation using RBF neural networks and ground-to-sky images

In this study, Artificial Neural Networks are applied to multistep long term solar radiation prediction. The networks are trained as one-step-ahead predictors and iterated over time to obtain multi-step longer term predictions. Auto-regressive and Auto-regressive with exogenous inputs solar radiationmodels are compared, considering cloudiness indices as inputs in the latter case. These indices are obtained through pixel classification of ground-to-sky images. The input-output structure of the neural network models is selected using evolutionary computation methods.

Tissue temperature estimation with pulse-echo in blood flow presence

Aiming at time-spatial characterization of tissue temperature when ultrasound is applied for thermal therapeutic proposes two experiments were developed considering gel-based phantoms, one of them including an artificial blood vessel. The blood vessel was mimicking blood flow in a common carotid artery. For each experiment phantoms were heated by a therapeutic ultrasound (TU) device emitting different intensities (0.5, 1, 1.5, 1.8 W/cm2). Temperature was monitored by thermocouples and estimated through imaging ultrasound transducer's signals within specific special points inside the phantom. The temperature estimation procedure was based on temporal echo-shifts (TES), computed based on echo-shifts collected through image ultrasound (IU) transducer. Results show that TES is a reliable non-invasive method of temperature estimation, regardless the TU intensities applied. Presence of a pulsatile blood flow vessel in the focal point of TU transducer reduces thermal variation in more than 50%, also affecting the temperature variation in the surrounding area. In other words, vascularized tissues require longer ultrasound thermal therapeutic sessions or higher TU intensities and inclusion of IU in the therapeutic procedure enables non-invasive monitoring of temperature. © 2013 IEEE.