Abstract
Pectus Excavatum (PE) is the most common congenital chest wall deformity, affecting 1 in 400 live births. This deformity is commonly corrected using the minimally invasive Nuss procedure, where a bar is positioned under the sternum. Although recent procedure advances based on patientspecific prosthesis were proposed, correct bar placement is still challenging. In this work, we propose a novel augmented reality system to guide the surgeon during PE bar placement. This system combines a 3D sensor with a projector to superimpose the thoracic ribs cage on the chest wall of the patient, thus indicating the optimal insertion and bar placement points. This system was validated in three different scenarios: 1) simulated chest surface models; 2) 3D printed phantom; and 3) 3D commercial thoracic phantom. An error of 3.93 ± 3.44 mm, and 3.08 ± 1.57 mm were obtained in the first and second experiments, respectively. In the final experiment, visual assessment of the result proved that a high similarity was obtained between the projected model and the real ribs cage position. Overall, the proposed system showed high feasibility with low error, proving that 3D projection of the ribs on the patient’s chest wall may facilitate PE bar insertion and ultimately provide useful information to guide Nuss procedure. © 2016 Taylor & Francis Group, London.

Abstract

Abstract
Current technological and market challenges increase the need for development of intelligent systems to support decision making, allowing managers to concentrate on high-level tasks while improving decision response and effectiveness. A Racing based learning module is proposed to increase the effectiveness and efficiency of a Multi-Agent System used to model the decision-making process on scheduling problems. A computational study is put forward showing that the proposed Racing learning module is an important enhancement to the developed Multi-Agent Scheduling System since it can provide more effective and efficient recommendations in most cases.

Abstract
Meta-heuristics have been applied for a long time to the Travelling Salesman Problem (TSP) but information is still lacking in the determination of the parameters with the best performance. This paper examines the impact of the Simulated Annealing (SA) and Discrete Artificial Bee Colony (DABC) parameters in the TSP. One special consideration of this paper is how the Neighborhood Structure (NS) interact with the other parameters and impacts the performance of the meta-heuristics. NS performance has been the topic of much research, with NS proposed for the best-known problems, which seem to imply that the NS influences the performance of meta-heuristics, more that other parameters. Moreover, a comparative analysis of distinct meta-heuristics is carried out to demonstrate a non-proportional increase in the performance of the NS.

Abstract
The ability to adjust itself to users' profile is imperative in modern system, given that many people interact with a lot of information in different ways. The creation of adaptive systems is a complex domain that requires very specific methods and the integration of several intelligent techniques, from an intelligent systems development perspective. Designing an adaptive system requires planning and training of user modelling techniques combined with existing system components. Based on the architecture for user modelling on Intelligent and Adaptive Scheduling Systems, this paper presents an analysis of using the mentioned architecture to characterize user's behaviours and a case study comparing the employment of different user classifiers. Bayesian and Artificial Neural Networks were selected as the elements of the computational study and this paper presents a description on how to prepare them to deal with user information.

Abstract
Meta-heuristics have been applied for a long time to the Travelling Salesman Problem (TSP) but information is still lacking in the determination of the parameters with the best performance. This paper examines the impact of the Simulated Annealing (SA) and Discrete Artificial Bee Colony (DABC) parameters in the TSP. One special consideration of this paper is how the Neighborhood Structure (NS) interact with the other parameters and impacts the performance of the meta-heuristics. NS performance has been the topic of much research, with NS proposed for the best-known problems, which seem to imply that the NS influences the performance of meta-heuristics, more that other parameters. Moreover, a comparative analysis of distinct meta-heuristics is carried out to demonstrate a non-proportional increase in the performance of the NS.