Abstract
This paper aims at presenting the main results of an energy audit performed to a gypsum production plant, in Portugal, which due to the amount of energy consumed must comply with the Portuguese program SGCIE (Intensive Energy Consumption Management System). The program was created in 2008 to promote energy efficiency and energy consumption monitoring in intensive energy consuming facilities (energy consumption higher than 500 toe per year). Facilities operators are required to perform energy audits and take actions to draw up an action plan for energy efficiency, establishing targets for energy consumption reduction and greenhouse gases emissions indexes. An energy audit was carried out to identify potential energy conservation measures for improving energy efficiency, and also typical energy consumption patterns, sector/equipment load profiles and thermal equipment performance. This tool gives managers the information to support decision making on improving energy performance and reducing greenhouse gas emissions. A number of tangible targets and measures were devised and set to be implemented in the next few years. Results show that there is a considerable potential for reduction in the energy consumption and greenhouse gases emissions of gypsum manufacturing plants. Here, as elsewhere in the industrial sector, energy efficiency can only be achieved through a continuous energy monitoring and management system.

Abstract
This paper discusses the problem of learning a global model from local information. We consider ubiquitous streaming data sources, such as sensor networks, and discuss efficient learning distributed algorithms. We present the generic framework of distributed sources of data, an illustrative algorithm to monitor the global state of the network using limited communication between peers, and an efficient distributed clustering algorithm.

Abstract
BackgroundSeveral studies link the seamless fit of implant-supported prosthesis with the accuracy of the dental impression technique obtained during acquisition. In addition, factors such as implant angulation and coping shape contribute to implant misfit. PurposeThe aim of this study was to identify the most accurate impression technique and factors affecting the impression accuracy. Material and MethodsA systematic review of peer-reviewed literature was conducted analyzing articles published between 2009 and 2013. The following search terms were used: implant impression, impression accuracy, and implant misfit. A total of 417 articles were identified; 32 were selected for review. ResultsAll 32 selected studies refer to in vitro studies. Fourteen articles compare open and closed impression technique, 8 advocate the open technique, and 6 report similar results. Other 14 articles evaluate splinted and non-splinted techniques; all advocating the splinted technique. Polyether material usage was reported in nine; six studies tested vinyl polysiloxane and one study used irreversible hydrocolloid. Eight studies evaluated different copings designs. Intraoral optical devices were compared in four studies. ConclusionsThe most accurate results were achieved with two configurations: (1) the optical intraoral system with powder and (2) the open technique with splinted squared transfer copings, using polyether as impression material.

Abstract
This paper is about long-term travel time prediction in public transportation. However, it can be useful for a wider area of applications. It follows a heterogeneous ensemble approach with dynamic selection. A vast set of experiments with a pool of 128 tuples of algorithms and parameter sets (a&ps) has been conducted for each of the six studied routes. Three different algorithms, namely, random forest, projection pursuit regression and support vector machines, were used. Then, ensembles of different sizes were obtained after a pruning step. The best approach to combine the outputs is also addressed. Finally, the best ensemble approach for each of the six routes is compared with the best individual a&ps. The results confirm that heterogeneous ensembles are adequate for long-term travel time prediction. Namely, they achieve both higher accuracy and robustness along time than state-of-the-art learners.

Abstract
This paper presents the results of an experimental study of the popular Bag-of-Features (BoF) model for the application of unsupervised learning of images, or image clustering. Although this method has been extensively applied for image classification and scene recognition, there has been few works which employ it in an unsupervised way. Also, due to the fact that the BoF model requires a great amount of steps, algorithms and parameter settings, we felt like there was a lack of detailed studies about the subject. We implemented testing routines in Python which we made publicly available in GitHub. In order to assess the performance of the model, three image datasets were used, namely, Coil-20 dataset, Natural and Urban dataset and Event dataset. The results obtained indicate that the BoF method provides a good representation of simple image collections for the purpose of clustering. However, it requires fine tunning of the parameters and algorithms for each dataset and obtains poor results for more complex scene datasets. We can therefore conclude that more advanced techniques are required in order to be able to effectively extract information from large image collections.

Abstract
In this paper we describe a method for packing tubes and boxes in containers. Each container is divided into parts (holders) which are allocated to subsets of objects. The method consists of a recursive procedure which, based on a predefined order for dealing with tubes and boxes, determines the dimensions and position of each holder. Characteristics of the objects to pack and rules limiting their placement make this problem unique. The method devised provides timely and practical solutions.