Abstract
Machine learning processes consist in collecting data, obtaining a model and applying it to a given task. Given a new task, the standard approach is to restart the learning process and obtain a new model. However, previous learning experience can be exploited to assist the new learning process. The two most studied approaches for this are meta-learning and transfer learning. Metalearning can be used for selecting the predictive model to use on a new dataset. Transfer learning allows the reuse of knowledge from previous tasks. However, when multiple heterogeneous tasks are available as potential sources for transfer, the question is which one to use. One approach to address this problem is metalearning. In this paper we investigate the feasibility of this approach. We propose a method to transfer weights from a source trained neural network to initialize a network that models a potentially very different target dataset. Our experiments with 14 datasets indicate that this method enables faster convergence without significant difference in accuracy provided that the source task is adequately chosen. This means that there is potential for applying metalearning to support transfer between heterogeneous datasets.

Abstract
Eyesight is an important sense that helps humans to avoid dangers and navigate in our world. Blind people usually have enhanced accuracy and sensibility of their other natural senses in order to sense their surroundings. But sometimes this is not enough because the human senses can be affected by external sources of noise or disease. That is why technology has been used to develop many assistive tools. Artifacts like white canes or braille compasses help blind people moving around in the environment. In this article, the use of a system that detects and recognize nearby objects or obstacles is proposed, giving an audible feedback to the user. It is designed as a wireless system in order to be comfortable to be carried by the user. The system helps visual impaired people to move around in indoor or outdoor scenarios. The goals of this blind guide system is to detect obstacles that white canes or dogs cannot, extending its detection range. © 2016 ACM.

Abstract
The emergence of complex supply chains is one of the most important consequences of globalization. The management of these supply chains requires increased efforts by organizations that, on one hand, are increasingly pressured by customers in terms of service levels, on the other hand, must manage their suppliers from various locations and with different local requirements. In this context, an appropriate management of information flows is needed to create the adequate visibility level for managing supply chain risk. This chapter presents an overview on the concepts of risk management, visibility and information management in supply chains. This study proposes a conceptual framework for the selection of risk mitigation strategies in the supply chain and characterizes the external and internal information flows decision makers need to implement two categories of risk mitigation strategies: redundancy and flexibility. © 2017, IGI Global.

Abstract
This paper describes a control technique for control of voltage source converters (VSCs) in the multi-terminal high voltage direct current (HVDC) transmission systems. The proposed control technique is based on a multi-loop current and voltage control scheme for tracking the reference value of the DC link voltage in the rectifier side to achieve a proper performance during the irregular circumstances of wind farm operation. In addition, the proposed control scheme is able to transmit the maximum power to the consumption sectors. Moreover, the proposed control method on the grid side converter guarantees least amount of current harmonics injection into the AC power grid. The MATLAB simulation results are presented to confirm the effectiveness of the proposed control technique for variation in AC voltage amplitude and frequency of wind turbines output voltage.

Abstract
The current vehicle stability control techniques relies on an accurate sensor information and a complete system definition, such information is not easily obtained and requires expensive sensor technology. In this work it is presented a fusion algorithm for estimating the vehicle handling dynamic states, using inertial measurements combined with Global Positioning System (GPS) information, based on the Extended Kalman Filter algorithm (EKF). The proposed method will be able to track the state of the variable vector that includes the yaw rate, lateral velocity and longitudinal velocity of the vehicle using the information of the available sensors combined with the non-linear model of the system. In order to validate the proposed sensor fusion algorithm a simulation with a high-fidelity CarSim model is carried out and its sensors are compared with Extended Kalman Filter state variables.

Abstract