Abstract

Abstract
For the predicted growth of e-commerce, supply chains need to adapt to new conditions, so that delivery can be fast, cheap and reliable. The key to success is the last-mile product delivery (LMD) - the last stage of the supply chain, where the ordered product is delivered to the final consumer's location. One innovative proposal puts foundations in a new delivery model where a professional delivery fleet (PF) is supplemented partially or fully with crowdshipping. The main idea of crowdshipping is to involve ordinary people - in our case in-store shoppers - in the delivery of packages to other customers. In return, occasional couriers (OC) are offered a small compensation. In hitherto formulated problems it was assumed that OCs always accept delivery tasks assigned to them. In this paper we consider OCs as independent agents, which are free to reject assignments. The main contribution of the paper is an original bi-level methodology for matching and routing problem in LMD with OCs and the PF. The goal is to use crowdshipping to reduce the total delivery cost in a same-day last-mile delivery system with respect to occasional couriers' freedom to accept or reject the assigned delivery. We introduce probability to represent each OC's willingness to perform the delivery to a given final customer. We study the OCs' willingness to accept or reject delivery tasks assigned to them and the influence of their decision on the total delivery cost associated to both the OCs' compensation fees and the delivery cost generated by the PF used for the delivery of remaining parcels. © 2018 The Author(s).

Abstract

Abstract
Neural networks have been applied as a machine learning tool in many different areas. Recently, they have gained increased attention with what is now called deep learning. Neural networks algorithms have several parameters that need to be tuned in order to maximize performance. The definition of these parameters can be a difficult, extensive and time consuming task, even for expert users. One approach that has been successfully used for algorithm and parameter selection is metalearning. Metalearning consists in using machine learning algorithm on (meta)data from machine learning experiments to map the characteristics of the data with the performance of the algorithms. In this paper we study how a metalearning approach can be used to obtain a good set of parameters to learn a neural network for a given new dataset. Our results indicate that with metalearning we can successfully learn classifiers from past learning tasks that are able to define appropriate parameters.

Abstract
An holistic approach to decision support systems for intelligent public lighting control, must address both energy efficiency and maintenance. Currently, it is possible to remotely control and adjust luminaries behaviour, which poses new challenges at the maintenance level. The luminary efficiency depends on several efficiency factors, either related to the luminaries or the surrounding conditions. Those factors are hard to measure without understanding the luminary operating boundaries in a real context. For this early stage on preventive maintenance design, we propose an approach based on the combination of two models of the network, wherein each is representing a different but complementary perspective on the classifying of the operating conditions of the luminary as normal or abnormal. The results show that, despite the expected and normal differences, both models have a high degree of concordance in their predictions.

Abstract
LED-based technology is transforming public lighting networks, favouring smart city innovations. Beyond energy efficiency benefits, LED-based luminaries provide real time stateful data. However, most of the municipalities manage all their luminaries equally, independently of its state or the environmental conditions. Some existing approaches to street lighting management are already considering elementary features such as on-off control and individual dimming based on movement or ambient light. Nevertheless, our vision on public (street) lighting management, goes beyond basic consumption monitoring and dimming control, encompassing: a) adaptive lighting, by considering other potential influence factors such as work temperature of the luminaries or the arrangement of the luminaries on the street; b) Colour tuning, for public safety purposes and; c) emergency behaviour control. This paper addresses the first component (adaptive lighting) influence factors, in the scope of a real scenario in a Portuguese municipality.