-
SDC.cpp is the C++ implementation of the algorithm in the paper of "Analyzing and Visualizing Web Opinion Development and Social Interactions With Density-Based Clustering". (Yang C C, Ng T D. Analyzing and Visualizing Web Opinion Development and Social Interactions With Density-Based Clustering[J]. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2011, 41(6):1144-1155.)
-
The folder of '2016泰迪杯数据挖掘' is the data processing code for a data mining contest.
-
The folder of Experiments-of-Caltech-Pedestrian-Dataset is several basic experiments of SVM, K-NN, Decsion Trees and Random Forests with respect to direct experiments on normalized dataset, direct experiments on sampling training datasets and cross-validation experiments on normalized sampling datasets.
Caltech Pedestrian dataset consists of 11 subsets of videos, the first 6 for training and the last 5 for testing. The videos are taken from a vehicle driving in urban areas, and very 30 th frame is used. The data of the course project is obtained from the Caltech pedestrian dataset including a training set (3605 positive samples and 10055 negative samples) and a test set (2043 positive samples and 4832 negative samples). A 2330-dimensional Haar-like feature was extracted from each image patch. The purpose of the project is to to develop classifiers, which take input features and predict the labels, compute the precision and recall values of the classifier and find out the best result. In this project, I have carried out both direct experiments and cross-validation experiments to find out best result. Besides, I have experimented K-NN, Decision Trees, Random Forest and SVM to find out the best algorithm with best parameters.