Features Fusion Framework for Multimodal Irregular Time-series Events

被引:1
|
作者
Tang, Peiwang [1 ,2 ]
Zhang, Xianchao [3 ,4 ]
机构
[1] Univ Sci & Technol China, Inst Adv Technol, Hefei 230026, Peoples R China
[2] Jiaxing Univ, G60 STI Valley Ind Innovat Inst, Jiaxing 314001, Peoples R China
[3] Jiaxing Univ, Key Lab Med Elect & Digital Hlth Zhejiang Prov, Jiaxing 314001, Peoples R China
[4] Jiaxing Univ, Engn Res Ctr Intelligent Human Hlth Situat Awaren, Jiaxing 314001, Peoples R China
关键词
Features fusion; LSTM; Multimodal; Time-series;
D O I
10.1007/978-3-031-20862-1_27
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Some data from multiple sources can be modeled as multimodal time-series events which have different sampling frequencies, data compositions, temporal relations and characteristics. Different types of events have complex nonlinear relationships, and the time of each event is irregular. Neither the classical Recurrent Neural Network (RNN) model nor the current state-of-the-art Transformer model can deal with these features well. In this paper, a features fusion framework for multimodal irregular time-series events is proposed based on the Long Short-Term Memory networks (LSTM). Firstly, the complex features are extracted according to the irregular patterns of different events. Secondly, the nonlinear correlation and complex temporal dependencies relationship between complex features are captured and fused into a tensor. Finally, a feature gate are used to control the access frequency of different tensors. Extensive experiments on MIMIC-III dataset demonstrate that the proposed framework significantly outperforms to the existing methods in terms of AUC (the area under Receiver Operating Characteristic curve) and AP (Average Precision).
引用
收藏
页码:366 / 379
页数:14
相关论文
共 50 条
  • [1] Time-Series Classification Based on Fusion Features of Sequence and Visualization
    Wang, Baoquan
    Jiang, Tonghai
    Zhou, Xi
    Ma, Bo
    Zhao, Fan
    Wang, Yi
    APPLIED SCIENCES-BASEL, 2020, 10 (12):
  • [2] An LLVM-Inspired Framework for Unified Processing of Multimodal Time-Series Data
    Hinkle, Lee B.
    Metsis, Vangelis
    PROCEEDINGS OF THE 16TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2023, 2023, : 91 - 94
  • [3] MULTIVARIATE ARIMA FORECASTING OF IRREGULAR TIME-SERIES
    CHOLETTE, PA
    LAMY, R
    INTERNATIONAL JOURNAL OF FORECASTING, 1986, 2 (02) : 201 - 216
  • [4] A Framework for Time-Series Analysis
    Kurbalija, Vladimir
    Radovanovic, Milos
    Geler, Zoltan
    Ivanovic, Mirjana
    ARTIFICIAL INTELLIGENCE: METHODOLOGY, SYSTEMS, AND APPLICATIONS, AIMSA 2010, 2010, 6304 : 42 - 51
  • [5] ANNOTE: Annotation of time-series events
    Groh, Rene
    Li, Jie Yu
    Li-Jessen, Nicole Y. K.
    Kist, Andreas M.
    SOFTWARE IMPACTS, 2024, 21
  • [6] Identification of Optimal Data Augmentation Techniques for Multimodal Time-Series Sensory Data: A Framework
    Ashfaq, Nazish
    Khan, Muhammad Hassan
    Nisar, Muhammad Adeel
    INFORMATION, 2024, 15 (06)
  • [8] Isolating cyclical patterns in irregular time-series data
    Hurn, AS
    McDonald, AD
    MATHEMATICS AND COMPUTERS IN SIMULATION, 1997, 43 (3-6) : 405 - 412
  • [9] An analysis of time-aggregated and time-series features for scoring different aspects of multimodal presentation data
    Ramanarayanan, Vikram
    Chen, Lei
    Leong, Chee Wee
    Feng, Gary
    Suendermann-Oeft, David
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1373 - 1377
  • [10] Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features
    Belkhouja, Taha
    Doppa, Janardhan Rao
    JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2022, 73 : 1435 - 1471