arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.09415cs.LGcs.HC
收藏

通过自由漫游眼动数据进行用户识别

User Identification via Free Roaming Eye Tracking Data

University of Bremen(不来梅大学)

Rishabh Vallabh Varsha Haria, Amin El Abed, Sebastian Maneth

AI总结:

本研究提出自由漫游与目标漫游眼动数据集,用RBFN分类器在非实验室场景实现用户识别,最高准确率分别达87.3%和89.4%,并分析轨迹截取位置及高阶速度导数的影响。

摘要:

我们提出了一个新的“自由漫游”(FR)和“目标漫游”(TR)数据集:一组41名参与者被要求步行绕行大学校园(FR),或被要求在图书馆内找到特定房间(TR)。使用商用可穿戴眼动仪(Pupil Labs Neon,200Hz)记录眼动。在此数据集上,我们使用先前已知的机器学习流程(以径向基函数网络(RBFN)作为分类器)研究了用户识别的准确性。我们的最高准确率在FR中为87.3%,在TR中为89.4%。这应与95.3%进行比较,这是我们所知的(相应的)最高准确率(在实验室环境中使用BioEye 2015竞赛数据集的“RAN”刺激实现)。据我们所知,我们的结果是首次在非实验室环境中研究用户识别;此类环境通常比实验室环境更可行,并且可能包含更多优势。每次记录的最短持续时间为FR的263秒和TR的154秒。我们的最佳准确率是在FR和TR分别限制为120秒和140秒时获得的,总是从轨迹的末端截取(训练和测试会话均如此)。如果从开头截取相同长度,则FR的准确率降低12.2%,TR的准确率降低约6.4%。在完整轨迹上,FR和TR的准确率分别降低5%和52%。我们还研究了包含更高阶速度导数(如加速度、加加速度或加加速度变化率)的影响。

英文摘要:

We present a new dataset of "free roaming" (FR) and "targeted roaming" (TR): a pool of 41 participants is asked to walk around a university campus (FR) or is asked to find a particular room within a library (TR). Eye movements are recorded using a commodity wearable eye tracker (Pupil Labs Neon at 200Hz). On this dataset we investigate the accuracy of user identification using a previously known machine learning pipeline where a Radial Basis Function Network (RBFN) is used as classifier. Our highest accuracies are 87.3% for FR and 89.4% for TR. This should be compared to 95.3% which is the (corresponding) highest accuracy we are aware of (achieved in a laboratory setting using the "RAN" stimulus of the BioEye 2015 competition dataset). To the best of our knowledge, our results are the first that study user identification in a non laboratory setting; such settings are often more feasible than laboratory settings and may include further advantages. The minimum duration of each recording is 263s for FR and 154s for TR. Our best accuracies are obtained when restricting to 120s and 140s for FR and TR respectively, always cut from the end of the trajectories (both for the training and testing sessions). If we cut the same length from the beginning, then accuracies are 12.2% lower for FR and around 6.4% lower for TR. On the full trajectories accuracies are lower by 5% and 52% for FR and TR. We also investigate the impact of including higher order velocity derivatives (such as acceleration, jerk, or jounce).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑