Department of Knowledge Engineering, University of Economics in Katowice, Bogucicka 3 Str., 40-226 Katowice, Poland.
Pattern Recognition Group, University of Siegen, Hoelderlinstr. 3, 57076 Siegen, Germany.
Comput Biol Med. 2018 Apr 1;95:277-287. doi: 10.1016/j.compbiomed.2017.10.026. Epub 2017 Oct 28.
With the advancement in mobile/wearable technology, people started to use a variety of sensing devices to track their daily activities as well as health and fitness conditions in order to improve the quality of life. This work addresses an idea of eye movement analysis, which due to the strong correlation with cognitive tasks can be successfully utilized in activity recognition. Eye movements are recorded using an electrooculographic (EOG) system built into the frames of glasses, which can be worn more unobtrusively and comfortably than other devices. Since the obtained information is low-level sensor data expressed as a sequence representing values in constant intervals (100 Hz), the cognitive activity recognition problem is formulated as sequence classification. However, it is unclear what kind of features are useful for accurate cognitive activity recognition. Thus, a machine learning algorithm like a codebook approach is applied, which instead of focusing on feature engineering is using a distribution of characteristic subsequences (codewords) to describe sequences of recorded EOG data, where the codewords are obtained by clustering a large number of subsequences. Further, statistical analysis of the codeword distribution results in discovering features which are characteristic to a certain activity class. Experimental results demonstrate good accuracy of the codebook-based cognitive activity recognition reflecting the effective usage of the codewords.
随着移动/可穿戴技术的进步，人们开始使用各种感测设备来跟踪他们的日常活动以及健康和健身状况，以提高生活质量。这项工作提出了一种眼动分析的想法，由于与认知任务具有很强的相关性，因此可以成功地用于活动识别。眼动是使用内置在眼镜架中的眼电图 (EOG) 系统记录的，与其他设备相比，这种系统更不引人注目，更舒适。由于获得的信息是低水平的传感器数据，表示为以恒定间隔（100 Hz）表示值的序列，因此认知活动识别问题被表述为序列分类。然而，尚不清楚哪些特征对于准确的认知活动识别有用。因此，应用了机器学习算法（如码本方法），该方法不是专注于特征工程，而是使用特征子序列（码字）的分布来描述记录的 EOG 数据的序列，其中码字是通过聚类大量子序列获得的。此外，对码字分布的统计分析导致发现了对特定活动类具有特征的特征。实验结果表明，基于码本的认知活动识别具有很好的准确性，反映了码字的有效使用。
