Abstract

Abstract
The industrial growth of the last decades created a need for intelligent and autonomous systems that can propose solutions to scheduling problems efficiently. The job shop scheduling problem (JSSP) is the most common formulation of these real-world scheduling problems and can be found in complex fields, such as transportation or industrial assemblies, where the ability to quickly adapt to unforeseen events is critical. Using the Markov decision process mathematical framework, this paper details a formulation of the JSSP as a reinforcement learning (RL) problem. The formulation is part of a proposal of a novel environment where RL agents can interact with JSSPs that is detailed on this paper, including a comprehensive explanation of the design process, the decisions that were made and the key lessons learnt. Considering the need for better scheduling approaches on modern manufacturing environments, the limitations that current techniques have and the major breakthroughs that are being made on the field of machine learning, the environment proposed on this paper intends to be a major contribution to the JSSP landscape, enabling academics from different areas to focus on the development of new algorithms and effortlessly test them on academic and real-world benchmarks. © 2020 MIR Labs.

Abstract

Abstract

Abstract

Abstract
Up to one third of the global food production depends on the pollination of honey bees, making them vital. This study defines a methodology to create a bee hive health monitoring system through image processing techniques. The approach consists of two models, where one performs the detection of bees in an image and the other classifies the detected bee’s health. The main contribution of the defined methodology is the increased efficacy of the models, whilst maintaining the same efficiency found in the state of the art. Two databases were used to create models based on Convolutional Neural Network (CNN). The best results consist of 95% accuracy for health classification of a bee and 82% accuracy in detecting the presence of bees in an image, higher than those found in the state-of-the-art.