Handling Label Noise in Air Traffic Complexity Evaluation Based on Confident Learning and XGBoost

Air traffic complexity is a critical indicator for air traffic operation,and plays an important role in air traffic management(ATM),such as airspace reconfiguration,air traffic flow management and allocation of air traffic controllers(ATCos).Recently,many machine learning techniques have been used to evaluate air traffic complexity by constructing a mapping from complexity related factors to air traffic complexity labels.However,the low quality of complexity labels,which is named as label noise,has often been neglected and caused unsatisfactory performance in air traffic complexity evaluation.This paper aims at label noise in air traffic complexity samples,and proposes a confident learning and XGBoost-based approach to evaluate air traffic complexity under label noise.The confident learning process is applied to filter out noisy samples with various label probability distributions,and XGBoost is used to train a robust and high-performance air traffic complexity evaluation model on the different label noise filtered ratio datasets.Experiments are carried out on a real dataset from the Guangzhou airspace sector in China,and the results prove that the appropriate label noise removal strategy and XGBoost algorithm can effectively mitigate the label noise problem and achieve better performance in air traffic complexity evaluation.

Analysis and evaluation of structural complexity of circular economy system＇s industrial chain

This paper examined the method to evaluate structural complexity of circular economy system＇s industrial chain, which applied entropy information and hierarchical metrics to produce complexity degrees according to the theory of complex system. We developed an evaluation model to make a general metrics for circular economy system of industrial chains. The development of the evaluation tree drew upon five factors to identify the structural complexity. The evaluation model generated unitive entropy information from six data definition （node, level of community, metabolic span, degree of node, number of relation and connectivity of node） according to the evaluation tree. The industrial chains of Tashan circular economy park of Datong Coal Mine Group and Gujiao circular economy park of Xishan Coal-Electricity Group were evaluated by the proposed method. The key factors stunted by the decline of structural complexity were identified and the unitive metrics of entropy information of the industrial chain was shown for realigning the circular economy systems.

MAIN FUNCTIONS AND EVALUATION OF CUTI'S COMPLEX——Simulated Saturation Diving Chamber

The 300 msw Simulated Saturation Diving Chamber Complex was designed and built by ourselves. It was completed at the end of 1985. A 300 msw trimixed saturation diving experiment was successfully conducted in the complex by Chinese Underwater Technology Institute(CUTI) from May 22 to June 12 of 1987. During the experiment, 4 divers habitated in the complex for 20 days, and they performed 16 person-time excursion dives and 8 other tests. The result of the experiment indicates that the complex is well designed, suitably configurated, wholly integrated and steadily run, as well as of low leakage. The main functions of the complex have approached to those of the same kind in the world. The complex can be used as a basic facility for serving the nation's saturation diving technology, underwater operation, personnel training, etc.

A man-made object detection algorithm based on contour complexity evaluation

Man-made object detection is of great significance in both military and civil areas, such as search-and-rescue missions at sea, traffic signs recognition during visual navigation, and targets location in a military strike. Contours of man-made objects usually consist of straight lines, corner points, and simple curves. Motivated by this observation, a man-made object detection method is proposed based on complexity evaluation of object contours. After salient contours which keep the crucial information of objects are accurately extracted using an improved mean-shift clustering algorithm, a novel approach is presented to evaluate the complexity of contours. By comparing the entropy values of contours before/after sampling and linear interpolation, it is easy to distinguish between man-made objects and natural ones according to the complexity of their contours.Experimental results show that the presented method can effectively detect man-made objects when compared to the existing ones.