我們的目標是對自2010年至今的鹿林光度觀測數據集進行分類。在進行這項工作之前， 我們使用了主成分分析並應用了顏色-顏色指數來編目近地小行星（NEAs）。然而，由 於它們的顏色數值相似，有時很難區分S型和Q型NEAs的相對反射率。為了使預測結果 更準確，我們應用了機器學習技術。我們使用了幾種算法，包括決策樹、隨機森林、 邏輯回歸、支持向量機和神經網絡;We aim to classify the dataset of Lulin photometry observations from 2010 to the present. Prior to this study, we utilized Principle Component Analysis and applied a color-color index to catalog near-Earth Asteroids (NEAs). However, distinguishing between the rel ative reflectance of S-type and Q-type NEAs proved challenging due to the similarity in their color values. To enhance the accuracy of our predictions, we incorporated machine learning techniques. We employed several algorithms, including decision trees, random forests, logistic regression, support vector machines, and neural networks.
