Class Binarization to NeuroEvolution for Multiclass Classification

Multiclass classification is a fundamental and challenging task in machine learning. The existing techniques of multiclass classification can be categorized as (i) decomposition into binary (ii) extension from binary and (iii) hierarchical classification. Decomposing multiclass classification into a set of binary classifications that can be efficiently solved by using binary classifiers, called class binarization, which is a popular technique for multiclass classification. Neuroevolution, a general and powerful technique for evolving the structure and weights of neural networks, has been successfully applied to binary classification. In this paper, we apply class binarization techniques to a neuroevolution algorithm, NeuroEvolution of Augmenting Topologies (NEAT), that is used to generate neural networks for multiclass classification. We propose a new method that applies Error-Correcting Output Codes (ECOC) to design the class binarization strategies on the neuroevolution for multiclass classification. The ECOC strategies are compared with the class binarization strategies of One-vs-One and One-vs-All on three well-known datasets Digit, Satellite, and Ecoli. We analyse their performance from four aspects of multiclass classification degradation, accuracy, evolutionary efficiency, and robustness. The results show that the NEAT with ECOC performs high accuracy with low variance. Specifically, it shows significant benefits in a flexible number of binary classifiers and strong robustness.

Aircraft Environmental Impact Segmentation via Metric Learning

Metric learning is the process of learning a tailored distance metric for a particular task. This advanced subfield of machine learning is useful to any machine learning or data mining task that relies on the computation of distances or similarities over objects. In recently years, machine learning techniques have been extensively used in aviation and aerospace engineering to make predictions, extract patterns, discover knowledge, etc. Nevertheless, metric learning, an element that can advance the performance of complex machine learning tasks, has so far been hardly utilized in relevant literature. In this study, we apply classic metric learning formulations with novel components on aviation environmental impact modeling. Through a weakly-supervised metric learning task, we achieve significant improvement in the newly emerged problem of aircraft characterization and segmentation for environmental impacts. The result will enable the more efficient and accurate modeling of aircraft environmental impacts, a focal topic in sustainable aviation. This work is also a demonstration that shows the potential and value of metric learning in a wide variety of similar studies in the transportation domain.

A Framework for Learning Predator-prey Agents from Simulation to Real World

In this paper, we propose an evolutionary predatorprey robot system which can be generally implemented from simulation to the real world. We design the closed-loop robot system with camera and infrared sensors as inputs of controller. Both the predators and prey are co-evolved by NeuroEvolution of Augmenting Topologies (NEAT) to learn the expected behaviours. We design a framework that integrate Gym of OpenAI, Robot Operating System (ROS), Gazebo. In such a framework, users only need to focus on algorithms without being worried about the detail of manipulating robots in both simulation and the real world. Combining simulations, real-world evolution, and robustness analysis, it can be applied to develop the solutions for the predator-prey tasks. For the convenience of users, the source code and videos of the simulated and real world are published on Github.