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
  • [21] Quantification of irregular circadian cycles using time-series methods
    Marisol Garcia-Iglesias, Lorena
    Rivera, Ana Leonor
    Claudio Toledo-Roy, Juan
    Fossion, Ruben
    XV MEXICAN SYMPOSIUM ON MEDICAL PHYSICS, 2019, 2090
  • [22] MERITS: Medication Recommendation for Chronic Disease with Irregular Time-Series
    Zhang, Shuai
    Li, Jianxin
    Zhou, Haoyi
    Zhu, Qishan
    Zhang, Shanghang
    Wang, Danding
    2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021), 2021, : 1481 - 1486
  • [23] Application of grammar framework to time-series prediction
    De Silva, Anthony Mihirana
    Leong, Philip H. W.
    SpringerBriefs in Applied Sciences and Technology, 2015, 0 (9789812874108): : 51 - 62
  • [24] A framework for predictive compression of time-series data
    Mukherjee, S
    Zobel, J
    PROCEEDINGS OF THE 21ST AUSTRALASIAN COMPUTER SCIENCE CONFERENCE, ACSC'98, 1998, 20 (01): : 95 - 105
  • [25] Evaluating Speech, Face, Emotion and Body Movement Time-series Features for Automated Multimodal Presentation Scoring
    Ramanarayanan, Vikram
    Leong, Chee Wee
    Chen, Lei
    Feng, Gary
    Suendermann-Oeft, David
    ICMI'15: PROCEEDINGS OF THE 2015 ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2015, : 23 - 30
  • [26] MULTIMODAL PUBLIC TRANSPORT DEMAND: A COINTEGRATION TIME-SERIES APPROACH
    Milioti, Christina P.
    Karlaftis, Matthew G.
    INTERNATIONAL JOURNAL OF TRANSPORT ECONOMICS, 2014, 41 (03) : 361 - 382
  • [27] Explainable Sleep Stage Classification with Multimodal Electrophysiology Time-series
    Ellis, Charles A.
    Zhang, Rongen
    Carbajal, Darwin A.
    Miller, Robyn L.
    Calhoun, Vince D.
    Wang, May D.
    2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), 2021, : 2363 - 2366
  • [28] Identification Method of the Time-Series Properties of the Aviation Events
    Zenchenko T.A.
    Gorshkov V.A.
    Sirotin N.N.
    Frolkov A.I.
    Pleshakov A.I.
    Russian Aeronautics, 2019, 62 (02): : 175 - 183
  • [29] Optimizing Metro Passenger Flow Prediction: Integrating Machine Learning and Time-Series Analysis with Multimodal Data Fusion
    Wan, Li
    Cheng, Wenzhi
    Yang, Jie
    IET CIRCUITS DEVICES & SYSTEMS, 2024, 2024
  • [30] CUTS: NEURAL CAUSAL DISCOVERY FROM IRREGULAR TIME-SERIES DATA
    Cheng, Yuxiao
    Yang, Runzhao
    Xiao, Tingxiong
    Li, Zongren
    Suo, Jinli
    He, Kunlun
    Dai, Qionghai
    arXiv, 2023,