Noisy values detection and correction of traffic accident data

A strategy for predicting waste production and planning recycling paths in e-logistics based on improved EMD-LSTM

With the rapid development of e-commerce, express delivery has been chosen and accepted by consumers, and a large number of express packages have resulted in serious waste of resources and environmental pollution. Because of the irregularity of online goods purchases by users in real life, logistics parks are unable to accurately judge the recycling needs of various regions. In order to solve this problem, we propose an improved empirical mode decomposition (IEMD) algorithm combined with a long-short-term memory (LSTM) network to deal with the addresses and categories in logistics data, analyze the distribution of recyclable logistics waste in the logistics park service area and in the express recycling station within the logistics park, judge the value of recyclable logistics waste, optimize the best path for recycling vehicles and improve the success rate of logistics waste recycling. In order to better research and verify the IEMD-LSTM prediction model, we model and simulate the algorithm behavior of the express waste packaging recycling prediction model system, and compare it with other classification methods through specific logistics data experiments. The prediction accuracy, stability and advantages of the four algorithms are analyzed and compared, and the application reliability of the algorithm proposed in this paper to the logistics waste recycling process is verified. The application in the actual express logistics packaging recycling case shows the feasibility and effectiveness of the waste recycling scheme proposed in this paper.

Using the scanners and drone for comparison of point cloud accuracy at traffic accident analysis

The purpose of the paper is to describe, compare and analyse the instruments used, time needed and accuracy of gathered data, sketches, 3D models and to enhance the extracted information about the accident. Simple sketches and tape measurements were performed. Also complex 3D measurements and 3D modelling of the scene with Terrestrial Laser Scanners (TLS) and Unmanned Aerial Vehicle (UAV) technology were used. A classical police work dealing with a simulated traffic accident was compared to sketches obtained from 3D models from Riegl VZ-400i 3D, Faro Focus S70, Geoslam ZebRevo 3D TLS and Topcon Falcon 8 drone. For 3D modelling an orthophoto from drone photos and point clouds were obtained. 3D models were graphically compared in CloudCompare software. Sketches were made for each measuring method and their accuracies were also compared one to each other. The graphical distance accuracy in scene measurements ranged up to 17 cm in comparison to police measurement but in the most course point cloud. Average absolute difference in compared distances amounts up to 6 cm. As expected, more points in the cloud means better 3D model and easier analysis. There is considerable reduction of time needed for collecting the accident scene data. The obtained 3D model is a permanent archive of the scene of a traffic accident. From the cadre, both visual and dimensional information subsequently can be obtained.