计算机技术与发展
計算機技術與髮展
계산궤기술여발전
COMPUTER TECHNOLOGY AND DEVELOPMENT
2015年
1期
57-61
,共5页
测谎%K-SVM%事件相关电位%P300%真实性识别
測謊%K-SVM%事件相關電位%P300%真實性識彆
측황%K-SVM%사건상관전위%P300%진실성식별
lie detection%K-SVM%ERP%P300%facticity identification
文中将支持向量机( SVM)和K近邻算法( KNN)相结合,提出一种基于K-SVM分类器的心理意识真实性识别新方法,获得了满意的结果。对15名受试者分别进行两组测试:模拟犯罪组和自传信息组。提取多通道ERP的P300幅值、波形面积和峰峰值组成特征向量,利用K-SVM算法分类,获得平均识别率分别为92.11%和97.37%,两组实验中分类精度都比单纯的SVM分类算法有明显的提高。因此文中的新算法可以为心理意识真实性检测提供一定的参考。
文中將支持嚮量機( SVM)和K近鄰算法( KNN)相結閤,提齣一種基于K-SVM分類器的心理意識真實性識彆新方法,穫得瞭滿意的結果。對15名受試者分彆進行兩組測試:模擬犯罪組和自傳信息組。提取多通道ERP的P300幅值、波形麵積和峰峰值組成特徵嚮量,利用K-SVM算法分類,穫得平均識彆率分彆為92.11%和97.37%,兩組實驗中分類精度都比單純的SVM分類算法有明顯的提高。因此文中的新算法可以為心理意識真實性檢測提供一定的參攷。
문중장지지향량궤( SVM)화K근린산법( KNN)상결합,제출일충기우K-SVM분류기적심리의식진실성식별신방법,획득료만의적결과。대15명수시자분별진행량조측시:모의범죄조화자전신식조。제취다통도ERP적P300폭치、파형면적화봉봉치조성특정향량,이용K-SVM산법분류,획득평균식별솔분별위92.11%화97.37%,량조실험중분류정도도비단순적SVM분류산법유명현적제고。인차문중적신산법가이위심리의식진실성검측제공일정적삼고。
K-SVM classification algorithm,combined SVM with KNN,which is adopted to identify mentality facticity,and the result is satisfactory. 15 subjects are tested respectively in mock-crime group and biographical information group. The multi-channel ERP P300 amplitude and P300 waveform area and peak to peak are used as the feature parameters and a K-SVM algorithm is applied to identify mentality facticity with the average accuracy rates are 92. 11% and 97. 37% separately. The results of both experiments show that the ac-curacy of K-SVM classification algorithm is better than pure SVM classification algorithm. Therefore,the new algorithm can provide cer-tain reference for identification of mentality facticity.