A Data-Driven Rutting Depth Short-Time Prediction Model With Metaheuristic Optimization for Asphalt Pavements Based on RIOHTrack

Rutting of asphalt pavements is a crucial design criterion in various pavement design guides. A good road transportation base can provide security for the transportation of oil and gas in road transportation. This study attempts to develop a robust artificial intelligence model to estimate different asphalt pavements’ rutting depth clips, temperature, and load axes as primary characteristics. The experiment data were obtained from19 asphalt pavements with different crude oil sources on a 2.038km long full-scale field accelerated pavement test track(Road Track Institute, RIOHTrack) in Tongzhou, Beijing. In addition,this paper also proposes to build complex networks with different pavement rutting depths through complex network methods and the Louvain algorithm for community detection. The most critical structural elements can be selected from different asphalt pavement rutting data, and similar structural elements can be found. An extreme learning machine algorithm with residual correction(RELM) is designed and optimized using an independent adaptive particle swarm algorithm. The experimental results of the proposed method are compared with several classical machine learning algorithms, with predictions of average root mean squared error(MSE), average mean absolute error(MAE), and a verage mean absolute percentage error(MAPE) for 19 asphalt pavements reaching 1.742, 1.363, and 1.94% respectively. The experiments demonstrate that the RELM algorithm has an advantage over classical machine learning methods in dealing with non-linear problems in road engineering. Notably, the method ensures the adaptation of the simulated environment to different levels of abstraction through the cognitive analysis of the production environment parameters. It is a promising alternative method that facilitates the rapid assessment of pavement conditions and could be applied in the future to production processes in the oil and gas industry.

Instance-Specific Algorithm Selection via Multi-Output Learning

Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms：（1）multi-output regressor stacking;（2） multi-output extremely randomized trees; and（3） hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.

Feasibility of terahertz spectroscopy for hybrid purity verification of rice seeds

The purity of hybrid rice seeds reflects the typical consistency of seed varieties in characteristics.The accuracy and reliability of seed purity detecting are of great significance to ensure the quality of seeds.In this study,the feasibility of identifying the purity of hybrid rice seeds,Xinong 1A/89,by terahertz(THz)time-domain spectroscopy system combined with chemometrics was explored.Three quantitative identification models for testing the purity of Xinong 1A/89 hybrid rice seed were developed and compared by THz absorption spectroscopy with extreme learning algorithm(ELM),Principal cComponent Regression(PCR)and Partial Least Squares Regression(PLSR).Experimental results showed that comparing with classical PLSR and PCR models,ELM presents a better feasibility and stability.For the testing set,the quantitative prediction result of ELM(ELoo=2.005×10^(-5),R^(2)=96.75%)is significantly better than those of PCR(ELoo=7.346×10^(-5),R^(2)=88.10%)and PLSR(ELoo=8.007×10^(-5),R^(2)=87.03%).The results highlight the feasibility of THz spectroscopy combined with ELM as an efficient and reliable method for verification of hybrid rice seeds.