摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-调查人员发布了关于人工智能的新报告。根据NewsRx Edi Tors对山东大学的新闻报道，研究表明：“轨迹重建是对撞机实验离线数据处理中最重要和最关键的任务之一。”新闻记者从山东大学的研究中获得了一句话：“对于工作在桃色能量区的BESIII探测器，以前曾用模板匹配和Hough变换等传统方法来提高跟踪性能，但对于跟踪困难的任务，如跟踪低动量轨道，本文提出了一种新的基于机器学习的跟踪算法,该算法利用大量的MC样本建立了表示漂移单元连通度的命中模式图,并在此基础上设计了一种最优的图构造方法。最后，提出了一种基于DBSCAN和RANSAC的聚类方法，对多个航迹进行聚类，研究了基于GENFIT2的航迹拟合算法，得到航迹参数，并采用确定性退火滤波器处理模糊度和潜在噪声。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Investigators publish new report on artificial in telligence. According to news reporting out of Shandong University by NewsRx edi tors, research stated, “Track reconstruction is one of the most important and ch allenging tasks in the offline data processing of collider experiments.” The news journalists obtained a quote from the research from Shandong University : “For the BESIII detector working in the tau-charm energy region, plenty of eff orts were made previously to improve the tracking performance with traditional m ethods, such as template matching and Hough transform etc. However, for difficul t tracking tasks, such as the tracking of low momentum tracks, tracks from secon dary vertices and tracks with high noise level, there is still large room for im provement. In this contribution, we demonstrate a novel tracking algorithm based on machine learning method. In this method, a hit pattern map representing the connectivity between drift cells is established using an enormous MC sample, bas ed on which we design an optimal method of graph construction, then an edgeclass ifying Graph Neural Network is trained to distinguish the hit-on-track from nois e hits. Finally, a clustering method based on DBSCAN and RANSAC is developed to cluster hits from multiple tracks. Track fitting algorithm based on GENFIT2 is a lso studied to obtain the track parameters, where deterministic annealing filter are implemented to deal with ambiguities and potential noises.”
NETL
NSTL