Salesian Journal on Information Systems

19-30

Authors: SANTOS, H. F. R. DOS, WEITZEL, L., SOBRAL, A. P. B.

Prognostics assesses and predicts future machine health, which includes detecting incipient failures and predicting remaining useful life. Several studies approached prognostics as a time series forecasting problem. The main goal of this study is to evaluate the performance of a set of methods in the prediction of future values from a dataset of time series collected from sensors installed on an industrial gas turbine. Methods tested include the use of ensembles of feedforward neural networks, ensembles of long short-term memory networks, exponential smoothing, and Auto Regressive Integrated Moving Average (ARIMA) models. Results show that the use of ARIMA models to forecast on the dataset is the best default method to apply, and is the only method that consistently beats a simple naïve no-change model.

39-54

Authors: MACHADO, L. D. P.; BERKENBROCK, C. D. M, FREITAS, L. E. R. de. et al.

This paper presents a collaborative learning approach that aims to contribute to the reduction of learning difficulties in programming classes. This approach is based on the concept of the flipped classroom and the practice of collaborative learning. In order to support the use of the approach a collaborative application was developed. This application implements fifteen requirements related to collaboration, learning and technical requirements on mobile devices. A case study was conducted with students of an Object-Oriented Programming class in a Computer Science undergraduate course to evaluate the approach and the application. The results indicate the potential of the approach to support student learning.

10-23

Authors: RODRIGUES, L. S., MACEDO, C. J. A., BORGES, V. C. M.

This work presents a flight path optimization model for drones that serve as a communication gateway or a data mule for IoT (Internet of Things) devices distributed on an Intelligent Campus. The results presented here consider a drone with limited energy autonomy (battery life), which causes the reduction of flight time and the number of covered devices in certain scenarios. This article proposes two approaches that ensure serving the maximum number of possible devices, considering the drones autonomy: the first using the Linear Programming, and the second through the Ant Colony Optimization Algorithm.

32-39

Authors: LIMA, E. A., ALVES, D. F.

When the organizational system is perceived by the inherent complexity, managing it has been a challenge for leaders in the world. On the one hand, there is a predilection for adopting models and approaches based on precepts of systematic vision, which guided the organizational development models at the second half of the twentieth century, on the other, the tendency to have levels of volatility, uncertainty, increasing ambiguity in the organizational environment exposes realities without well defined, amorphous, irregular and asymmetric contours, triggering new dimensions of analysis. In the midst of the challenges and paradoxes that exist in the corporate sphere, knowledge management is one of many prescriptive approaches that do not usually contemplate the contextual and organic relational precepts typically present in the systemic view. In this sense, the objective of this study is to specify multidimensional evaluation parameters that can parameterize GC maturity models, in order to facilitate the absorption of the complexity of the organizational system. For that, a narrative review work was developed that culminated in the specification of parameters of a multidimensional nature to evaluate the level of maturity of CG in complex scenarios.