Abstract

Abstract
This study aimed to assess the motion and its deformation index (DI) of red blood cells (RBCs) flowing through a microchannel with a microstenosis using an image analysis-based method. For this purpose, a microchannel having a smooth contraction was used and the images were captured by a standard high-speed microscopy system. An automatic image-processing and analysing method was developed in a MATLAB environment to not only track the motion of RBCs but also measure the DI along the microchannel. The keyhole model, tested in this study, proved to be a promising technique to automatically track individual RBCs in microchannels.

Abstract
This work presents an autonomous system for marine integrated physical-chemical and biological monitoring - the MarinEye system. It comprises a set of sensors providing diverse and relevant information for oceanic environment characterization and marine biology studies. It is constituted by a physical-chemical water properties sensor suite, a water filtration and sampling system for DNA collection, a plankton imaging system and biomass assessment acoustic system. The MarinEye system has onboard computational and logging capabilities allowing it either for autonomous operation or for integration in other marine observing systems (such as Observatories or robotic vehicles. It was designed in order to collect integrated multi-trophic monitoring data. The validation in operational environment on 3 marine observatories: RAIA, BerlengasWatch and Cascais on the coast of Portugal is also discussed.

Abstract
Personnel scheduling problems are widely studied both by the scientific community and by the human resource managers of the companies. The financial impact of the decisions, the welfare of the employees, or more subjective concepts like "fairness" and "balance", turn this case into much more than just a routine problem. When it comes to medical personnel scheduling, additional difficulties can be found, such as uninterrupted work (24 hours per day, 7 days per week), or the quality of service that has to be ensured. The work presented in this paper was based on the rules defined in INRCII - Second International Nurse Rostering Competition - but always with the vision of creating the necessary basis for the future development of an automatic and optimized generic personnel scheduling software.

Abstract

Abstract
Dynamic selection or combination (DSC) methods allow to select one or more classifiers from an ensemble according to the characteristics of a given test instance x. Most methods proposed for this purpose are based on the nearest neighbours algorithm: it is assumed that if a classifier performed well on a set of instances similar to x, it will also perform well on x. We address the problem of dynamically combining a pool of classifiers by combining two approaches: metalearning and multi-label classification. Taking into account that diversity is a fundamental concept in ensemble learning and the interdependencies between the classifiers cannot be ignored, we solve the multi-label classification problem by using a widely known technique: Classifier Chains (CC). Additionally, we extend a typical metalearning approach by combining metafeatures characterizing the interdependencies between the classifiers with the base-level features.We executed experiments on 42 classification datasets and compared our method with several state-of-the-art DSC techniques, including another metalearning approach. Results show that our method allows an improvement over the other metalearning approach and is very competitive with the other four DSC methods. © Springer International Publishing AG 2016.