Mining Road Traffic Rules with Signal Temporal Logic and Grammar-Based Genetic Programming

Traffic systems, where human and autonomous drivers interact, are a very relevant instance of complex systems and produce behaviors that can be regarded as trajectories over time. Their monitoring can be achieved by means of carefully stated properties describing the expected behavior. Such properties can be expressed using Signal Temporal Logic (STL), a specification language for expressing temporal properties in a formal and human-readable way. However, manually authoring these properties is a hard task, since it requires mastering the language and knowing the system to be monitored. Moreover, in practical cases, the expected behavior is not known, but it has instead to be inferred from a set of trajectories obtained by observing the system. Often, those trajectories come devoid of human-assigned labels that can be used as an indication of compliance with expected behavior. As an alternative to manual authoring, automatic mining of STL specifications from unlabeled trajectories would enable the monitoring of autonomous agents without sacrificing human-readability. In this work, we propose a grammar-based evolutionary computation approach for mining the structure and the parameters of an STL specification from a set of unlabeled trajectories. We experimentally assess our approach on a real-world road traffic dataset consisting of thousands of vehicle trajectories. We show that our approach is effective at mining STL specifications that model the system at hand and are interpretable for humans. To the best of our knowledge, this is the first such study on a set of unlabeled real-world road traffic data. Being able to mine interpretable specifications from this kind of data may improve traffic safety, because mined specifications may be helpful for monitoring traffic and planning safety promotion strategies.

Transparent water quality model induction in a reservoir affected by the rainfall-runoff process using a grammar-based genetic programming

Building a reliable water quality prediction model in the catchment is of importance both for understanding the process of these natural systems and providing a basis for water quality management decisions. Due to a rapid change of river flow during a Typhoon season in South Korea, water quality parameters in reservoirs are affected significantly within a short-time period by a rainfall-runoff process. Integrated conceptual hydrological and water quality models seem to be complicated to produce a good model calibration and prediction with reasonable generalizations under these dynamic condition of heavy rainfall events. As an alternative, this paper proposes an evolutionary model induction system based on grammar-based genetic programming (GBGP) to derive the transparent mathematical model for estimating the dynamic change of water quality parameters within a short-time period in an agricultural reservoir affected by the rainfall-runoff process during a typical Typhoon summer period. Results showed that the GBGP system performed to evolve accurate water quality models, expressed in the form of explicit mathematical formulae which could predict the concentration and load of COD, SS, T-N, and T-P during the heavy rainfall event as a function of easily measurable rainfall, cumulative rainfall, and flow rate. The performance of the water quality models evolved by the GBGP was superior to ANN and optimized pollutant rating curve (PRC) model, showing that it has the lowest RMSE value. The transparent nature of water quality models evolved by the GBGP may allow inferences about underlying processes to be made. This work demonstrates that complex dynamic water quality change affected by the rainfall-runoff process in natural catchments can be successfully modelled through the use of GBGP system without costly or time-consuming tasks required in the conceptual modeling approach.

Probabilistic Contextual and Structural Dependencies Learning in Grammar-Based Genetic Programming

Genetic Programming is a method to automatically create computer programs based on the principles of evolution. The problem of deceptiveness caused by complex dependencies among components of programs is challenging. It is important because it can misguide Genetic Programming to create sub-optimal programs. Besides, a minor modification in the programs may lead to a notable change in the program behaviours and affect the final outputs. This paper presents Grammar-based Genetic Programming with Bayesian Classifiers (GBGPBC) in which the probabilistic dependencies among components of programs are captured using a set of Bayesian network classifiers. Our system was evaluated using a set of benchmark problems (the deceptive maximum problems, the royal tree problems, and the bipolar asymmetric royal tree problems). It was shown to be often more robust and more efficient in searching the best programs than other related Genetic Programming approaches in terms of the total number of fitness evaluation. We studied what factors affect the performance of GBGPBC and discovered that robust variants of GBGPBC were consistently weakly correlated with some complexity measures. Furthermore, our approach has been applied to learn a ranking program on a set of customers in direct marketing. Our suggested solutions help companies to earn significantly more when compared with other solutions produced by several well-known machine learning algorithms, such as neural networks, logistic regression, and Bayesian networks.

A Grammar-based Genetic Programming Approach to Optimize Convolutional Neural Network Architectures

Deep Learning is a research area under the spotlight in recent years due to its successful application to many domains, such as computer vision and image recognition. The most prominent technique derived from Deep Learning is Convolutional Neural Network, which allows the network to automatically learn representations needed for detection or classification tasks. However, Convolutional Neural Networks have some limitations, as designing these networks are not easy to master and require expertise and insight. In this work, we present the use of Genetic Algorithm associated to Grammar-based Genetic Programming to optimize Convolution Neural Network architectures. To evaluate our proposed approach, we adopted CIFAR-10 dataset to validate the evolution of the generated architectures, using the metric of accuracy to evaluate its classification performance in the test dataset. The results demonstrate that our method using Grammar-based Genetic Programming can easily produce optimized CNN architectures that are competitive and achieve high accuracy results.