Cerebro: A Wearable Solution to Detect and Track User Preferences using Brainwaves
Cerebro: A Wearable Solution to Detect and Track User Preferences using Brainwaves
复制标题
Cerebro：使用脑电波检测和跟踪用户偏好的可穿戴解决方案
DOI：
10.1145/3325424.3329660
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Sivakumar, Raghupathy
中科院分区：
文献类型：
--
作者：
Agarwal, Mohit;Sivakumar, Raghupathy
在这项工作中，我们考虑使用他们的脑电波的用户偏好的检测和解释的问题。在这种情况下的具体目标是通过仅依赖于佩戴EEG耳机可穿戴设备的用户的大脑活动来确定一组对象的偏好排名。我们首先通过对EEG信号的基于试验和错误的分析来建立对象排名（基于EEG可穿戴设备）的可行性。然后，我们提出了一种机器学习算法Cerebro，它可以学习用户脑电波的特定细微差别，以准确地对对象进行排序。我们根据归一化贴现累积增益（NDCG）来衡量算法的准确性，并表明它在7个对象上训练时表现良好，并在14个用户的3个对象上进行评估。
In this work, we consider the problem of detection and interpretation of user preferences using their brainwaves. The specific goal in this context is to determine the preference ranking for a set of objects by solely relying on the brain activity of a user who is wearing an EEG headset wearable. We first establish the feasibility of object ranking (based on an EEG wearable) by a trial and error based analysis of the EEG signals. We then present a machine learning algorithm Cerebro, which can learn the specific nuances of the user's brainwaves for preferences to accurately rank the objects. We measure the accuracy of the algorithm in terms of the Normalized Discounted Cumulative Gain (NDCG), and show that it performs well when trained on 7 objects, and evaluated on 3 objects for the 14 users.
影响因子：
3.6
作者：
Yadava, Mahendra;Kumar, Pradeep;Dogra, Debi Prosad
通讯作者：
Dogra, Debi Prosad