Online Anomaly Detection for Smartphone-Based Multivariate Behavioral Time Series Data.
Online Anomaly Detection for Smartphone-Based Multivariate Behavioral Time Series Data.
复制标题
DOI：
10.3390/s22062110
复制
发表时间：
2022-03-09
期刊：
影响因子：
--
通讯作者：
Onnela JP
中科院分区：
文献类型：
--
作者：
Liu G;Onnela JP
智能手机可用于在现实环境中长时间不引人注目地收集颗粒状行为数据。为了检测大量被动收集的智能手机数据中的异常行为，我们提出了一种使用Hotelling T平方检验的在线异常检测方法。在我们的方法中的检验统计量是一个加权平均值，当个人可用的数据量有限时，个体间分量的权重更大，当数据充足时，个体内分量的权重更大。该算法在每次更新中只占用一个运行时间，并且在预先指定的更新次数后，所需的内存使用量是固定的。根据个体数据的样本量，拟定方法在准确度、灵敏度和特异性方面的性能始终优于或等于其构建的离线方法。我们的方法的未来应用包括在恢复过程中早期发现手术并发症和可能预防严重精神疾病患者的复发。
Smartphones can be used to collect granular behavioral data unobtrusively, over long time periods, in real-world settings. To detect aberrant behaviors in large volumes of passively collected smartphone data, we propose an online anomaly detection method using Hotelling’s T-squared test. The test statistic in our method was a weighted average, with more weight on the between-individual component when the amount of data available for the individual was limited and more weight on the within-individual component when the data were adequate. The algorithm took only an runtime in each update, and the required memory usage was fixed after a pre-specified number of updates. The performance of the proposed method, in terms of accuracy, sensitivity, and specificity, was consistently better than or equal to the offline method that it was built upon, depending on the sample size of the individual data. Future applications of our method include early detection of surgical complications during recovery and the possible prevention of the relapse of patients with serious mental illness.
登录
查看更多内容
影响因子：
5.2
作者：
Torous J;Kiang MV;Lorme J;Onnela JP
通讯作者：
Onnela JP
影响因子：
3.8
作者：
Bickley, Harriet;Hunt, Isabelle M.;Kapur, Navneet
通讯作者：
Kapur, Navneet
影响因子：
8.5
作者：
Scaranti, Gustavo Frigo;Carvalho, Luiz Fernando;Proenca, Mario Lemes
通讯作者：
Proenca, Mario Lemes
影响因子：
7.6
作者：
Barnett, Ian;Torous, John;Onnela, Jukka-Pekka
通讯作者：
Onnela, Jukka-Pekka
影响因子：
25.8
作者：
Chung, Daniel Thomas;Ryan, Christopher James;Large, Matthew Michael
通讯作者：
Large, Matthew Michael