Abstract
In this paper, we present and discuss an innovative approach to solve Job Shop scheduling problems based on machine learning techniques. Traditionally, when choosing how to solve Job Shop scheduling problems, there are two main options: either use an efficient heuristic that provides a solution quickly, or use classic optimization approaches (e.g., metaheuristics) that take more time but will output better solutions, closer to their optimal value. In this work, we aim to create a novel architecture that incorporates reinforcement learning into scheduling systems in order to improve their overall performance and overcome the limitations that current approaches present. It is also intended to investigate the development of a learning environment for reinforcement learning agents to be able to solve the Job Shop scheduling problem. The reported experimental results and the conducted statistical analysis conclude about the benefits of using an intelligent agent created with reinforcement learning techniques. The main contribution of this work is proving that reinforcement learning has the potential to become the standard method whenever a solution is necessary quickly, since it solves any problem in very few seconds with high quality, approximate to the optimal methods.

Abstract

Abstract

Abstract
In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitting that has witnessed significant success in various classification applications. Recently, many efforts have been made to improve the Standard dropout using an unsupervised merit-based semantic selection of neurons in the latent space. However, these studies do not consider the task-relevant information quality and quantity and the diversity of the latent kernels. To solve the challenge of dropping less informative neurons in deep learning, we propose an efficient end-to-end dropout algorithm that selects the most informative neurons with the highest correlation with the target output considering the sparsity in its selection procedure. First, to promote activation diversity, we devise an approach to select the most diverse set of neurons by making use of determinantal point process (DPP) sampling. Furthermore, to incorporate task specificity into deep latent features, a mutual information (MI)-based merit function is developed. Leveraging the proposed MI with DPP sampling, we introduce the novel DPPMI dropout that adaptively adjusts the retention rate of neurons based on their contribution to the neural network task. Empirical studies on real-world classification benchmarks including, MNIST, SVHN, CIFAR10, CIFAR100, demonstrate the superiority of our proposed method over recent state-of-the-art dropout algorithms in the literature.

Abstract
In a precision agriculture context, the amount of geospatial data available can be difficult to interpret in order to understand the crop variability within a given terrain parcel, raising the need for specific tools for data processing and analysis. This is the case for data acquired from Unmanned Aerial Vehicles (UAV), in which the high spatial resolution along with data from several spectral wavelengths makes data interpretation a complex process regarding vegetation monitoring. Vegetation Indices (VIs) are usually computed, helping in the vegetation monitoring process. However, a crop plot is generally composed of several non-crop elements, which can bias the data analysis and interpretation. By discarding non-crop data, it is possible to compute the vigour distribution for a specific crop within the area under analysis. This article presents QVigourMaps, a new open source application developed to generate useful outputs for precision agriculture purposes. The application was developed in the form of a QGIS plugin, allowing the creation of vigour maps, vegetation distribution maps and prescription maps based on the combination of different VIs and height information. Multi-temporal data from a vineyard plot and a maize field were used as case studies in order to demonstrate the potential and effectiveness of the QVigourMaps tool. The presented application can contribute to making the right management decisions by providing indicators of crop variability, and the outcomes can be used in the field to apply site-specific treatments according to the levels of vigour.

Abstract
Changing mobility behaviors in academia - such as encouraging the use of bicycles - can help to reduce CO2 emissions since trips made by car or motorbikes tend to effectively reduce. Additionally, by obtaining mobility-related data we can infer patterns, optimize mobility and strengthen more sustainable habits within academia. In this paper, we propose a secure LoRa-based tracking system for the BIRA bicycle. The BIRA bicycle is an initiative of Instituto Politecnico de Viana do Castelo (IPVC) that aims to promote bicycle usage on campus, by encouraging the adoption of more sustainable mobility habits within the institution. The proposed system consists of BIRA bicycles equipped with low-cost GPS trackers. The collected data is then transmitted using a LoRaWAN infrastructure to an application server, which is responsible for storing and serving the client application with several contextual information, such as location, route, speed, and battery level. The results have shown that the proposed system is a viable low-cost solution for tracking bicycles and users' habits at a campus or even a city level.