本文選題：酒后駕駛　切入點：駕駛行為　出處：《中國安全科學(xué)學(xué)報》2017年07期 　論文類型：期刊論文

【摘要】：為準(zhǔn)確辨識駕駛員酒駕行為以及酒駕狀態(tài)水平,提高酒駕治理效率,通過人因工程試驗和駕駛模擬試驗,采集并預(yù)處理駕駛員在正常、飲酒、醉酒3種駕駛狀態(tài)下的駕駛行為數(shù)據(jù)(包括駕駛員的人、車、環(huán)境數(shù)據(jù));對原始參數(shù)進行因子分析,提取特征參數(shù)并將其作為多層神經(jīng)網(wǎng)絡(luò)的輸入向量,訓(xùn)練多層神經(jīng)網(wǎng)絡(luò),建立基于因子分析和多層神經(jīng)網(wǎng)絡(luò)的酒駕行為辨識模型;選取75組測試樣本數(shù)據(jù)輸入模型,將模型的輸出結(jié)果與實際情況比較,驗證模型的有效性。研究表明:該模型的訓(xùn)練時間為0.905 s,最優(yōu)驗證均方誤差(MSE)為0.034,識別準(zhǔn)確率達92.41%,用該模型能較為快速、準(zhǔn)確地識別酒后駕駛行為。
[Abstract]:In order to accurately identify the driver's behavior and the level of drinking driving, and to improve the efficiency of drinking driving, the drivers were collected and pretreated by human engineering test and driving simulation test. Driving behavior data (including driver's person, vehicle, environment data) under three driving states, factor analysis of original parameters, extracting characteristic parameters and using them as input vectors of multi-layer neural network, training multi-layer neural network, Based on factor analysis and multi-layer neural network, the identification model of drinking driving behavior is established, 75 groups of test sample data input model are selected, and the output results of the model are compared with the actual situation. The results show that the training time of the model is 0.905 s, the optimal mean square error (MSE) is 0.034, and the recognition accuracy is 92.41%. The model can be used to identify drunk driving behavior quickly and accurately.
【作者單位】： 山東理工大學(xué)交通與車輛工程學(xué)院;
【基金】：國家自然科學(xué)基金資助(61573009) 山東省自然科學(xué)基金資助(ZR2014FM027) 山東省高等學(xué)�？萍加媱�(J15LB07) 汽車安全與節(jié)能國家重點實驗室開放基金資助(KF16232)
【分類號】：U492.8
，

本文編號：1557272