Abstract
The design of computer-assisted decision (CAD) systems for different biomedical imaging scenarios is a challenging task in computer vision. Sometimes, this challenge can be attributed to the image acquisition mechanisms since the lack of control on the cameras can create different visualizations of the same imaging site under different rotation, scaling, and illumination parameters, with a requirement to get a consistent diagnosis by the CAD systems. Moreover, the images acquired from different sites have specific colors, making the use of standard color spaces highly redundant. In this paper, we propose to tackle these issues by introducing novel region-based texture, and color descriptors. The proposed texture features are based on the usage of analytic Gabor filters (for compensation of illumination variations) followed by the calculation of first-and second-order statistics of the filter responses and making them invariant using some trivial mathematical operators. The proposed color features are obtained by compensating for the illumination variations in the images using homomorphic filtering followed by a bag-of-words approach to obtain the most typical colors in the images. The proposed features are used for the identification of cancer in images from two distinct imaging modalities, i.e., gastroenterology and dermoscopy. Experiments demonstrate that the proposed descriptors compares favorably to several other state-of-the-art methods, elucidating on the effectiveness of adapted features for image characterization.

Abstract
One of the most challenging tasks for energy domain stakeholders is to have a better preview of the electricity consumption. Having a more trustable expectation of electricity consumption can help minimizing the cost of electricity and also enable a better control on the electricity tariff. This paper presents a study using a Methodology to Obtain Genetic fuzzy rule-based systems Under the iterative rule Learning approach (MOGUL) methodology in order to have a better profile of the electricity consumption of the following hours. The proposed approach uses the electricity consumption of the past hours to forecast the consumption value for the following hours. Results from this study are compared to those of previous approaches, namely two fuzzy based systems: and several different approaches based on artificial neural networks. The comparison of the achieved results with those achieved by the previous approaches shows that this approach can calculate a more reliable value for the electricity consumption in the following hours, as it is able to achieve lower forecasting errors, and a less standard deviation of the forecasting error results. © 2017 IEEE.

Abstract
This work aims to study a new energy harvesting device to be anchored on the ocean floor and convert any type of currents, tides or oscillation movement into electrical energy using linear electromagnetic generators. The final application is to supply energy to a set of moored monitoring sensors that collects data and allowing the system to be energetically autonomous. The proposed setup is a spherical buoy with no external moving parts, to be more biofouling proof. The maximum output power measured for a 4 Hz movement was 9.9 mW with only one linear electromagnetic generator.

Abstract
A system identification approach is used estimate linear time invariant models from the data of physical activity gathered in the Just Walk intervention conducted by the Designing Health Lab and the Control Systems Laboratory at Arizona State University A class of identification algorithms proposed elsewhere by one of the authors, denoted as MoliZoft, was reformulated and adapted to estimate models from data gathered in this experience. In this paper, the identification algorithms are described and the best models estimated for a particular participant are analysed and used to improve the results in future experiments.

Abstract
With recent advances in high-throughput cell biology, the amount of cellular biological data has grown drastically. Such data is often modeled as graphs (also called networks) and studying them can lead to new insights intomolecule-level organization. A possible way to understand their structure is by analyzing the smaller components that constitute them, namely network motifs and graphlets. Graphlets are particularly well suited to compare networks and to assess their level of similarity due to the rich topological information that they offer but are almost always used as small undirected graphs of up to five nodes, thus limiting their applicability in directed networks. However, a large set of interesting biological networks such asmetabolic, cell signaling, or transcriptional regulatory networks are intrinsically directional, and using metrics that ignore edge direction may gravely hinder information extraction. Our main purpose in this work is to extend the applicability of graphlets to directed networks by considering their edge direction, thus providing a powerful basis for the analysis of directed biological networks. We tested our approach on two network sets, one composed of synthetic graphs and another of real directed biological networks, and verified that they were more accurately grouped using directed graphlets than undirected graphlets. It is also evident that directed graphlets offer substantially more topological information than simple graph metrics such as degree distribution or reciprocity. However, enumerating graphlets in large networks is a computationally demanding task. Our implementation addresses this concern by using a state-of-the-art data structure, the g-trie, which is able to greatly reduce the necessary computation. We compared our tool to other state-of-the art methods and verified that it is the fastest general tool for graphlet counting.

Abstract
Real world optimization problems like Scheduling are generally complex, large scaled, and constrained in nature. Thereby, classical operational research methods are often inadequate to efficiently solve them. Metaheuristics (MH) are used to obtain near-optimal solutions in an efficient way, but have different numerical and/or categorical parameters which make the tuning process a very time-consuming and tedious task. Learning methods can be used to aid with the parameter tuning process. Racing techniques have been used to evaluate, in a refined and efficient way, a set of candidates and discard those that appear to be less promising during the evaluation process. Case-based Reasoning (CBR) aims to solve new problems by using information about solutions to previous similar problems. A novel Racing+CBR approach is proposed and brings together the better of the two techniques. A computational study for the resolution of the scheduling problem is presented, concluding about the effectiveness of the proposed approach.