Abstract
Inductive Logic Programming (ILP) systems have been largely applied to classification problems with a considerable success. The use of ILP systems in problems requiring numerical reasoning capabilities has been far less successful. Current systems have very limited numerical reasoning capabilities, which limits the range of domains where the ILP paradigm may be applied. This paper proposes improvements in numerical reasoning capabilities of ILP systems. It proposes the use of statistical-based techniques like Model Validation and Model Selection to improve noise handling and it introduces a new search stopping criterium based on the PAG method to evaluate learning performance. We have found these extensions essential to improve on results mer statistical-based algorithms for time series forecasting used in the empirical evaluation study.

Abstract
ILP systems have been largely applied to datamining classification tasks with a considerable success. The use of ILP systems in regression tasks has been far less successful. Current systems have very limited numerical reasoning capabilities, which limits the application of ILP to discovery of functional relationships of numeric nature. This paper proposes improvements in numerical reasoning capabilities of ILP systems for dealing with regression tasks. It proposes the use of statistical-based techniques like Model Validation and Model Selection to improve noise handling and it introduces a new search stopping criterium based on the PAC method to evaluate learning performance. We have found these extensions essential to improve on results over machine learning and statistical-based algorithms used in the empirical evaluation study.

Abstract
A sensing head for simultaneous measurement of temperature and strain is presented and analyzed. The proposed configuration is based on the combination of two Bragg gratings, written in different fibres and with different reflectivities, to form a single signature with a reflected step spectrum profile. By measuring the changes in the peak wavelength and spectral width of this signature, resolutions of 0.65 degreesC/rootHz and +/- 2.55 muepsilon/rootHz were achieved for temperature and strain measurements, respectively.

Abstract
This paper studies the performance of integer and fractional order controllers in a hexapod robot with joints at the legs having viscous friction and flexibility. For that objective the robot prescribed motion is characterized in terms of several locomotion variables. The walking performance is analysed through the Nyquist stability criterion and several indices that reflect the system dynamical properties. A set of model-based experiments reveals the influence of the different controller implementations upon the proposed metrics.

Abstract
An optical fiber sensor for the measurement of oxygen in gaseous environments, which is based on the quenching of the fluorescence of a ruthenium complex, is presented. The sensing chemistry is immobilized in a sol-gel based solid matrix that is coated on a tapered optical fiber probe. Oxygen measurement is performed both by phase and fluorescence intensity spectroscopy. Experimental results show that the fluorescence intensity and the lifetime depend both on oxygen and temperature. A scheme for simultaneous determination of the temperature and the oxygen concentration is proposed. Temperature measurement is performed using the excitation radiation and an absorption long pass filter. Preliminary results are presented which show a temperature measurement independent of oxygen and of optical power level.

Abstract
The development of fiber optical sensor in which the sensing head comprises a long period fiber grating (LPG) whose attenuation peak varies as function of its bending was investigated. Various arc-induced LPGs were fabricated in the spectral region of the optical source. The spectral power evolution was taken from a streched to a bending position with the optical spectrum analyzer. The developed fiber optical sensor demonstrated its capability of micro-displacement measurement.