Abstract
In data streams new classes can appear over time due to changes in the data statistical distribution. Consequently, models can become outdated, which requires the use of incremental learning algorithms capable of detecting and learning the changes over time. However, when a single classification model is used for novelty detection, there is a risk that its bias may not be suitable for new data distributions. A solution could be the combination of several models into an ensemble. Besides, because models can only be updated when labeled data arrives, we propose two unsupervised ensemble approaches: one combining clustering partitions using the same clustering technique; and other using different clustering techniques. We compare the performance of the proposed methods with well known novelty detection algorithms. The methods were tested on datasets commonly used in the novelty detection literature. The experimental results show that proposed ensembles have competitive performance for novelty detection in data streams. © Springer Nature Switzerland AG 2019.

Abstract
Time series data is composed of observations of one or more variables along a time period. By analyzing the variability of the variables we can reveal patterns that repeat or that are correlated, which helps to understand the behaviour of the variables over time. Our method finds frequent distributions of a target variable in time series data and discovers relationships between frequent distributions in consecutive time intervals. The frequent distributions are found using a new method, and relationships between them are found using association rules mining.

Abstract
This work proposes a mathematical programming model for jointly scheduling of production and transport in flexible manufacturing systems considering alternative job routing. Although production scheduling and transport scheduling have been vastly researched, most of the works address them independently. In addition, the few that consider their simultaneous scheduling assume job routes as an input, i.e., the machine -operation allocation is previously determined. However, in flexible manufacturing systems, this is an important source of flexibility that should not be ignored. The results show the model efficiency in solving small -sized instances.

Abstract
In the past few years, important supply chain decisions have captured managerial interest. One of these decisions is the design of the supply chain network incorporating financial considerations, based on the idea that establishment and operating costs have a direct effect on the company’s financial performance. However, works on supply chain network design (SCND) incorporating financial decisions are scarce. In this work, we address a SCND problem in which operational and investment decisions are made in order to maximize the company value, measured by the Economic Value Added, while respecting the usual operational constraints, as well as financial ratios and constraints. This work extends current research by considering debt repayments and new capital entries as decision variables, improving on the calculation of some financial values, as well as introducing infrastructure dynamics; which together lead to greater value creation. © 2019, Springer Nature Switzerland AG.

Abstract
This work proposes a multi-criteria decision making model to assist in the choice of a strategic plan for a world-class company. The Balanced Scorecard (BSC) is a support tool of Beyond Budgeting that translates a company’s vision and strategy into a coherent set of performance measures. However, it does not provide help in choosing a strategic plan. The selection of a strategic plan involves multiple goals and objectives that are often conflicting and incommensurable. This paper proposes an integrated Analytic Hierarchy Process-Goal Programming (AHP-GP) approach to select such a plan. This approach comprises two stages. In the first stage, the AHP is used to evaluate the relative importance of the initiatives with respect to financial indicators/KPIs; while in the second stage a GP model incorporating the AHP priority scores is developed. The GP model selects a set of initiatives that maximizes the earnings before interest and taxes (EBIT) and minimizes the Capital Employed (CE). The proposed method was evaluated through a case study. © 2019, Springer Nature Switzerland AG.

Abstract
This work proposes a biased random key genetic algorithm (BRKGA) for the integrated scheduling of manufacturing, transport, and storage/retrieval operations in flexible manufacturing systems (FMSs). Only recently, research on this problem has been reported; however, no heuristic approaches have yet been reported. The computational results show the BRKGA to be capable of finding good quality solutions quickly.