《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (1): 90-97.DOI: 10.11772/j.issn.1001-9081.2024010131
张思齐1,2, 张金俊1,2, 王天一1,2, 秦小林1,2()
收稿日期:
2024-02-05
修回日期:
2024-03-26
接受日期:
2024-03-26
发布日期:
2024-05-09
出版日期:
2025-01-10
通讯作者:
秦小林
作者简介:
张思齐(1995—),男,安徽淮南人,博士研究生,CCF会员,主要研究方向:时态逻辑、时间序列预测、时间序列分析;基金资助:
Siqi ZHANG1,2, Jinjun ZHANG1,2, Tianyi WANG1,2, Xiaolin QIN1,2()
Received:
2024-02-05
Revised:
2024-03-26
Accepted:
2024-03-26
Online:
2024-05-09
Published:
2025-01-10
Contact:
Xiaolin QIN
About author:
ZHANG Siqi, born in 1995, Ph. D. candidate. His research interests include temporal logic, time series forecasting, time series analysis.Supported by:
摘要:
针对深度事件检测模型对复杂时序事件检测准确性不足和忽略了不同事件间相关性的问题,提出一种基于信号时态逻辑的深度时序事件检测算法DSTL (Deep Signal Temporal Logic)。该算法一方面引入信号时态逻辑框架,并用信号时态逻辑(STL)公式建模时间序列中的事件来综合考虑时间序列上事件的逻辑性和时态性;另一方面采用基于神经网络的基础分类器来检测原子事件的发生情况,并通过STL公式结构和语义来辅助检测复杂事件。另外,使用神经网络模块替代相应的逻辑连接词和时态逻辑算子,从而提供可GPU加速和梯度下降的神经网络模块。通过对6个时间序列数据集的实验,验证了该算法在时序事件检测方面的有效性,并把使用DSTL算法的模型与不使用该算法而使用多层感知机(MLP)、长短期记忆(LSTM)网络和Transformer的深度时间序列分类模型进行比较。实验结果表明,使用DSTL算法的模型在5种事件上的平均F1分数提升了约12%,其中3种跨时间点事件上的平均F1分数提升了约14%,且具备更好的可解释性。
中图分类号:
张思齐, 张金俊, 王天一, 秦小林. 基于信号时态逻辑的深度时序事件检测算法[J]. 计算机应用, 2025, 45(1): 90-97.
Siqi ZHANG, Jinjun ZHANG, Tianyi WANG, Xiaolin QIN. Deep temporal event detection algorithm based on signal temporal logic[J]. Journal of Computer Applications, 2025, 45(1): 90-97.
类型 | 事件示例 | STL公式 |
---|---|---|
车流量高于阈值 | ||
电路电压高于阈值 | ||
6小时内降水量一直高于阈值 | ||
未来2小时内病人血压将升高至阈值 | ||
24小时内货币A汇率高于阈值 |
表1 时间序列中可被STL表示的一些事件示例
Tab. 1 Some examples of events in time series data that can be represented by STL
类型 | 事件示例 | STL公式 |
---|---|---|
车流量高于阈值 | ||
电路电压高于阈值 | ||
6小时内降水量一直高于阈值 | ||
未来2小时内病人血压将升高至阈值 | ||
24小时内货币A汇率高于阈值 |
数据集 | |||
---|---|---|---|
Exchange rate | 0.6 | 0.8 | 0.8 |
Electricity | 0.5 | 0.6 | 0.5 |
Traffic | 0.1 | 0.2 | 0.1 |
ETTh1 | 0.2 | 0.3 | 0.5 |
ETTh2 | 0.4 | 0.6 | 0.9 |
Weather | 0.6 | 0.7 | 0.4 |
表2 各数据集中的参数设置
Tab. 2 Parameter setting in each dataset
数据集 | |||
---|---|---|---|
Exchange rate | 0.6 | 0.8 | 0.8 |
Electricity | 0.5 | 0.6 | 0.5 |
Traffic | 0.1 | 0.2 | 0.1 |
ETTh1 | 0.2 | 0.3 | 0.5 |
ETTh2 | 0.4 | 0.6 | 0.9 |
Weather | 0.6 | 0.7 | 0.4 |
数据集 | 模型 | F1 | UpAll | UpTem | ||||
---|---|---|---|---|---|---|---|---|
E0 | E1 | E2 | E3 | E4 | ||||
Exchange rate | DTSC | 0.560 | 0.962 | 0.964 | 0.465 | 0.606 | 0.147 | 0.244 |
DSTL | 0.593 | 0.931 | 0.939 | 0.906 | 0.923 | |||
Electricity | DTSC | 0.541 | 0.772 | 0.929 | 0.848 | 0.846 | 0.046 | 0.001 |
DSTL | 0.709 | 0.833 | 0.924 | 0.836 | 0.865 | |||
Traffic | DTSC | 0.741 | 0.936 | 0.987 | 0.892 | 0.823 | 0.021 | 0.011 |
DSTL | 0.805 | 0.944 | 0.988 | 0.916 | 0.832 | |||
ETTh1 | DTSC | 0.009 | 0.869 | 0.539 | 0.811 | 0.505 | 0.170 | 0.091 |
DSTL | 0.582 | 0.873 | 0.707 | 0.805 | 0.615 | |||
ETTh2 | DTSC | 0.304 | 0.704 | 0.793 | 0.540 | 0.204 | 0.090 | 0.167 |
DSTL | 0.251 | 0.704 | 0.797 | 0.551 | 0.691 | |||
Weather | DTSC | 0.176 | 0.807 | 0.589 | 0.961 | 0.256 | 0.033 | 0.046 |
DSTL | 0.201 | 0.809 | 0.593 | 0.959 | 0.392 |
表3 MLP骨干网络下模型在各数据集上的分类结果
Tab. 3 Classification results of models with MLP backbone on each datasets
数据集 | 模型 | F1 | UpAll | UpTem | ||||
---|---|---|---|---|---|---|---|---|
E0 | E1 | E2 | E3 | E4 | ||||
Exchange rate | DTSC | 0.560 | 0.962 | 0.964 | 0.465 | 0.606 | 0.147 | 0.244 |
DSTL | 0.593 | 0.931 | 0.939 | 0.906 | 0.923 | |||
Electricity | DTSC | 0.541 | 0.772 | 0.929 | 0.848 | 0.846 | 0.046 | 0.001 |
DSTL | 0.709 | 0.833 | 0.924 | 0.836 | 0.865 | |||
Traffic | DTSC | 0.741 | 0.936 | 0.987 | 0.892 | 0.823 | 0.021 | 0.011 |
DSTL | 0.805 | 0.944 | 0.988 | 0.916 | 0.832 | |||
ETTh1 | DTSC | 0.009 | 0.869 | 0.539 | 0.811 | 0.505 | 0.170 | 0.091 |
DSTL | 0.582 | 0.873 | 0.707 | 0.805 | 0.615 | |||
ETTh2 | DTSC | 0.304 | 0.704 | 0.793 | 0.540 | 0.204 | 0.090 | 0.167 |
DSTL | 0.251 | 0.704 | 0.797 | 0.551 | 0.691 | |||
Weather | DTSC | 0.176 | 0.807 | 0.589 | 0.961 | 0.256 | 0.033 | 0.046 |
DSTL | 0.201 | 0.809 | 0.593 | 0.959 | 0.392 |
数据集 | 模型 | F1 | UpAll | UpTem | ||||
---|---|---|---|---|---|---|---|---|
E0 | E1 | E2 | E3 | E4 | ||||
Exchange rate | DTSC | 0.198 | 0.827 | 0.830 | 0.372 | 0.459 | 0.279 | 0.352 |
DSTL | 0.500 | 0.864 | 0.885 | 0.890 | 0.942 | |||
Electricity | DTSC | 0.669 | 0.797 | 0.907 | 0.855 | 0.807 | 0.011 | 0.013 |
DSTL | 0.672 | 0.812 | 0.926 | 0.836 | 0.845 | |||
Traffic | DTSC | 0.734 | 0.926 | 0.977 | 0.880 | 0.825 | 0.010 | 0.013 |
DSTL | 0.736 | 0.934 | 0.982 | 0.904 | 0.835 | |||
ETTh1 | DTSC | 0.000 | 0.907 | 0.813 | 0.806 | 0.886 | 0.074 | 0.074 |
DSTL | 0.632 | 0.859 | 0.813 | 0.747 | 0.732 | |||
ETTh2 | DTSC | 0.198 | 0.667 | 0.371 | 0.599 | 0.110 | 0.108 | 0.148 |
DSTL | 0.215 | 0.747 | 0.596 | 0.701 | 0.228 | |||
Weather | DTSC | 0.334 | 0.479 | 0.682 | 0.894 | 0.000 | 0.122 | 0.140 |
DSTL | 0.451 | 0.552 | 0.674 | 0.856 | 0.466 |
表4 LSTM骨干网络下模型在各数据集上的分类结果
Tab. 4 Classification results of models with LSTM backbone network on each datasets
数据集 | 模型 | F1 | UpAll | UpTem | ||||
---|---|---|---|---|---|---|---|---|
E0 | E1 | E2 | E3 | E4 | ||||
Exchange rate | DTSC | 0.198 | 0.827 | 0.830 | 0.372 | 0.459 | 0.279 | 0.352 |
DSTL | 0.500 | 0.864 | 0.885 | 0.890 | 0.942 | |||
Electricity | DTSC | 0.669 | 0.797 | 0.907 | 0.855 | 0.807 | 0.011 | 0.013 |
DSTL | 0.672 | 0.812 | 0.926 | 0.836 | 0.845 | |||
Traffic | DTSC | 0.734 | 0.926 | 0.977 | 0.880 | 0.825 | 0.010 | 0.013 |
DSTL | 0.736 | 0.934 | 0.982 | 0.904 | 0.835 | |||
ETTh1 | DTSC | 0.000 | 0.907 | 0.813 | 0.806 | 0.886 | 0.074 | 0.074 |
DSTL | 0.632 | 0.859 | 0.813 | 0.747 | 0.732 | |||
ETTh2 | DTSC | 0.198 | 0.667 | 0.371 | 0.599 | 0.110 | 0.108 | 0.148 |
DSTL | 0.215 | 0.747 | 0.596 | 0.701 | 0.228 | |||
Weather | DTSC | 0.334 | 0.479 | 0.682 | 0.894 | 0.000 | 0.122 | 0.140 |
DSTL | 0.451 | 0.552 | 0.674 | 0.856 | 0.466 |
数据集 | 模型 | F1 | UpAll | UpTem | ||||
---|---|---|---|---|---|---|---|---|
E0 | E1 | E2 | E3 | E4 | ||||
Exchange rate | DTSC | 0.082 | 0.864 | 0.860 | 0.141 | 0.170 | 0.382 | 0.544 |
DSTL | 0.371 | 0.855 | 0.883 | 0.972 | 0.948 | |||
Electricity | DTSC | 0.514 | 0.682 | 0.883 | 0.623 | 0.743 | 0.155 | 0.155 |
DSTL | 0.679 | 0.826 | 0.920 | 0.960 | 0.833 | |||
Traffic | DTSC | 0.576 | 0.867 | 0.958 | 0.772 | 0.732 | 0.098 | 0.076 |
DSTL | 0.782 | 0.924 | 0.987 | 0.845 | 0.860 | |||
ETTh1 | DTSC | 0.356 | 0.733 | 0.650 | 0.576 | 0.186 | 0.109 | 0.103 |
DSTL | 0.503 | 0.821 | 0.753 | 0.546 | 0.423 | |||
ETTh2 | DTSC | 0.300 | 0.550 | 0.791 | 0.053 | 0.044 | 0.160 | 0.217 |
DSTL | 0.336 | 0.661 | 0.821 | 0.214 | 0.505 | |||
Weather | DTSC | 0.105 | 0.356 | 0.150 | 0.966 | 0.278 | 0.150 | 0.162 |
DSTL | 0.282 | 0.446 | 0.468 | 0.937 | 0.475 |
表5 Transformer骨干网络下模型在各数据集上的分类结果
Tab. 5 Classification results of models with Transformer backbone network on each datasets
数据集 | 模型 | F1 | UpAll | UpTem | ||||
---|---|---|---|---|---|---|---|---|
E0 | E1 | E2 | E3 | E4 | ||||
Exchange rate | DTSC | 0.082 | 0.864 | 0.860 | 0.141 | 0.170 | 0.382 | 0.544 |
DSTL | 0.371 | 0.855 | 0.883 | 0.972 | 0.948 | |||
Electricity | DTSC | 0.514 | 0.682 | 0.883 | 0.623 | 0.743 | 0.155 | 0.155 |
DSTL | 0.679 | 0.826 | 0.920 | 0.960 | 0.833 | |||
Traffic | DTSC | 0.576 | 0.867 | 0.958 | 0.772 | 0.732 | 0.098 | 0.076 |
DSTL | 0.782 | 0.924 | 0.987 | 0.845 | 0.860 | |||
ETTh1 | DTSC | 0.356 | 0.733 | 0.650 | 0.576 | 0.186 | 0.109 | 0.103 |
DSTL | 0.503 | 0.821 | 0.753 | 0.546 | 0.423 | |||
ETTh2 | DTSC | 0.300 | 0.550 | 0.791 | 0.053 | 0.044 | 0.160 | 0.217 |
DSTL | 0.336 | 0.661 | 0.821 | 0.214 | 0.505 | |||
Weather | DTSC | 0.105 | 0.356 | 0.150 | 0.966 | 0.278 | 0.150 | 0.162 |
DSTL | 0.282 | 0.446 | 0.468 | 0.937 | 0.475 |
1 | SEZER O B, GUDELEK M U, OZBAYOGLU A M. Financial time series forecasting with deep learning: a systematic literature review: 2005-2019 [J]. Applied Soft Computing, 2020, 90: No.106181. |
2 | LI J, WU B, SUN X, et al. Causal hidden Markov model for time series disease forecasting [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 12100-12109. |
3 | 夏进, 王正群, 朱世明. 基于时间序列分解的交通流量预测模型 [J]. 计算机应用, 2023, 43 (4): 1129-1135. |
XIA J, WANG Z Q, ZHU S M. Traffic flow prediction model based on time series decomposition [J]. Journal of Computer Applications, 2023, 43 (4): 1129-1135. | |
4 | 朱怡蒙, 贺可太, 姜肖依, 等. 基于周期基准孤立森林的服装供应异常监测算法 [J]. 计算机应用, 2023, 43 (S2): 268-275. |
ZHU Y M, HE K T, JIANG X Y, et al. Anomaly detection algorithm for clothing supply based on isolated forest with periodic reference [J]. Journal of Computer Applications, 2023, 43 (S2): 268-275. | |
5 | GURALNIK V, SRIVASTAVA J. Event detection from time series data [C]// Proceedings of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 1999: 33-42. |
6 | BATAL I, FRADKIN D, HARRISON J, et al. Mining recent temporal patterns for event detection in multivariate time series data [C]// Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2012: 280-288. |
7 | ZHOU Y, ARGHANDEH R, ZOU H, et al. Nonparametric event detection in multiple time series for power distribution networks [J]. IEEE Transactions on Industrial Electronics, 2019, 66 (2): 1619-1628. |
8 | 胡文斌, 王欢, 严丽平, 等. 面向节点演化波动的社会网络事件检测方法 [J]. 软件学报, 2017, 28 (10): 2693-2703. |
HU W B, WANG H, YAN L P, et al. Event detection method for social networks based on node evolution fluctuations [J]. Journal of Software, 2017, 28 (10): 2693-2703. | |
9 | 王雪颖, 杨文忠, 张志豪, 等. 基于多特征的微博突发事件检测算法 [J]. 计算机应用, 2019, 39 (11): 3263-3267. |
WANG X Y, YANG W Z, ZHANG Z H, et al. Microblog bursty events detection algorithm based on multi-feature [J]. Journal of Computer Applications, 2019, 39 (11): 3263-3267. | |
10 | EL-SAPPAGH S, ABUHMED T, ISLAM S M R, et al. Multimodal multitask deep learning model for Alzheimer’s disease progression detection based on time series data [J]. Neurocomputing, 2020, 412: 197-215. |
11 | PORUMB M, STRANGES S, PESCAPÈ A, et al. Precision medicine and artificial intelligence: a pilot study on deep learning for hypoglycemic events detection based on ECG [J]. Scientific Reports, 2020, 10: No.170. |
12 | ZHANG X, GAO Y, LIN J, et al. TapNet: multivariate time series classification with attentional prototypical network [C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020: 6845-6852. |
13 | GOSCHENHOFER J. Deep semi-supervised learning for time-series classification [M]// WANI M A, PALADE V. Deep learning applications, Volume 4. Singapore: Springer, 2022: 361-384. |
14 | ELDELE E, RAGAB M, CHEN Z, et al. Self-supervised contrastive representation learning for semi-supervised time-series classification [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (2): 15604-15618. |
15 | SUN L, ZHANG M, WANG B, et al. Few-shot class-incremental learning for medical time series classification [J]. IEEE Journal of Biomedical and Health Informatics, 2023, 28 (4): 1872-1882. |
16 | GE T, WEI F, ZHOU M. Reaching human-level performance in automatic grammatical error correction: an empirical study [EB/OL]. [2023-03-14]. . |
17 | GEIRHOS R, NARAYANAPPA K, MITZKUS B, et al. Partial success in closing the gap between human and machine vision [C]// Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 23885-23899. |
18 | BLÁZQUEZ-GARCÍA A, CONDE A, MORI U, et al. A review on outlier/anomaly detection in time series data [J]. ACM Computing Surveys, 2022, 54 (3): No.56. |
19 | 玄英律, 万源, 陈嘉慧. 基于多尺度卷积和注意力机制的LSTM时间序列分类 [J]. 计算机应用, 2022, 42 (8): 2343-2352. |
XUAN Y L, WAN Y, CHEN J H. Time series classification by LSTM based on multi-scale convolution and attention mechanism [J]. Journal of Computer Applications, 2022, 42 (8): 2343-2352. | |
20 | CARREIRA J, ZISSERMAN A. Quo vadis, action recognition? a new model and the kinetics dataset [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 4724-4733. |
21 | ZHANG Y C, LI Y, REHG J M. First-person action decomposition and zero-shot learning [C]// Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2017: 121-129. |
22 | GÖKCE Z, PEHLIVAN S. Temporal modelling of first-person actions using hand-centric verb and object streams [J]. Signal Processing: Image Communication, 2021, 99: No.116436. |
23 | YOO C, BELTA C. Rich time series classification using temporal logic [C/OL]// Proceedings of Robotics: Science and Systems XIII. [2024-08-11]. . |
24 | MA M, GAO J, FENG L, et al. STLnet: signal temporal logic enforced multivariate recurrent neural networks [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 14604-14614. |
25 | ZHOU Y, YAN Y, HAN R, et al. Clinical temporal relation extraction with probabilistic soft logic regularization and global inference [C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 14647-14655. |
26 | MALER O, NICKOVIC D. Monitoring temporal properties of continuous signals [C]// Proceedings of the 2004 Joint International Conference on Formal Modeling and Analysis of Timed Systems and Formal Techniques in Real-Time and Fault-Tolerant Systems, LNCS 3253. Berlin: Springer, 2004: 152-166. |
27 | BUZHINSKY I. Formalization of natural language requirements into temporal logics: a survey [C]// Proceedings of the IEEE 17th International Conference on Industrial Informatics. Piscataway: IEEE, 2019: 400-406. |
28 | COSLER M, HAHN C, MENDOZA D, et al. nl2spec: interactively translating unstructured natural language to temporal logics with large language models [C]// Proceedings of the 2023 International Conference on Computer Aided Verification, LNCS 13965. Cham: Springer, 2023: 383-396. |
29 | BOMBIERI M, MELI D, DALL’ALBA D, et al. Mapping natural language procedures descriptions to linear temporal logic templates: an application in the surgical robotic domain [J]. Applied Intelligence, 2023, 53 (22): 26351-26363. |
30 | 段喜龙, 陆智伟, 郑巍, 等. 面向模型检测的LTL语句自动生成方法 [J]. 计算机工程与设计, 2023, 44 (8): 2337-2344. |
DUAN X L, LU Z W, ZHENG W, et al. Automatic generation of LTL statements for model checking [J]. Computer Engineering and Design, 2023, 44 (8): 2337-2344. | |
31 | PITERMAN N, PNUELI A, SA’AR Y. Synthesis of reactive (1) designs [C]// Proceedings of the 2006 International Conference on Verification, Model Checking, and Abstract Interpretation, LNCS 3855. Berlin: Springer, 2006: 364-380. |
32 | PLAKU E, KARAMAN S. Motion planning with temporal-logic specifications: progress and challenges [J]. AI Communications, 2016, 29 (1): 151-162. |
33 | 骆翔宇, 黄欣玥, 古天龙, 等. 基于时态测试器的实时分支时态逻辑模型检测 [J]. 软件学报, 2022, 33 (8): 2930-2946. |
LUO X Y, HUANG X Y, GU T L, et al. Model checking for real-time branching-time temporal logic based on temporal testers [J]. Journal of Software, 2022, 33 (8): 2930-2946. | |
34 | RAMAN V, DONZÉ A, SADIGH D, et al. Reactive synthesis from signal temporal logic specifications [C]// Proceedings of the 18th International Conference on Hybrid Systems: Computation and Control. New York: ACM, 2015: 239-248. |
35 | BARTOCCI E, BORTOLUSSI L, NENZI L, et al. System design of stochastic models using robustness of temporal properties [J]. Theoretical Computer Science, 2015, 587: 3-25. |
36 | GHOSH S, SADIGH D, NUZZO P, et al. Diagnosis and repair for synthesis from signal temporal logic specifications [C]// Proceedings of the 19th International Conference on Hybrid Systems: Computation and Control. New York: ACM, 2016: 31-40. |
37 | ALQAHTANI S, TAYLOR S, RILEY I, et al. Predictive path planning algorithm using Kalman filters and MTL robustness [C]// Proceedings of the 2018 IEEE International Symposium on Safety, Security, and Rescue Robotics. Piscataway: IEEE, 2018: 1-7. |
38 | QIN X, DESHMUKH J V. Clairvoyant monitoring for signal temporal logic [C]// Proceedings of the 2020 International Conference on Formal Modeling and Analysis of Timed Systems, LNCS 12288. Cham: Springer, 2020: 178-195. |
39 | LI X, ROSMAN G, GILITSCHENSKI I, et al. Vehicle trajectory prediction using generative adversarial network with temporal logic syntax tree features [J]. IEEE Robotics and Automation Letters, 2021, 6 (2): 3459-3466. |
40 | TIGER M, HEINTZ F. Stream reasoning using temporal logic and predictive probabilistic state models [C]// Proceedings of the 23rd International Symposium on Temporal Representation and Reasoning. Piscataway: IEEE, 2016: 196-205. |
41 | ALUR R, FEDER T, HENZINGER T A. The benefits of relaxing punctuality [J]. Journal of the ACM, 1996, 43 (1): 116-146. |
42 | SADIGH D, KAPOOR A. Safe control under uncertainty with probabilistic signal temporal logic [C/OL]// Proceedings of the 2016 Robotics: Science and Systems XII. [2024-08-11]. . |
43 | TIGER M, HEINTZ F. Incremental reasoning in probabilistic Signal Temporal Logic [J]. International Journal of Approximate Reasoning, 2020, 119: 325-352. |
44 | MEHDIPOUR N, VASILE C I, BELTA C. Specifying user preferences using weighted signal temporal logic [J]. IEEE Control Systems Letters, 2021, 5 (6): 2006-2011. |
45 | LEUNG K, ARÉCHIGA N, PAVONE M. Backpropagation for parametric STL [C]// Proceedings of the 2019 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE, 2019: 185-192. |
46 | DONZÉ A, FERRÉRE T, MALER O. Efficient robust monitoring for STL [C]// Proceedings of the 2013 International Conference on Computer Aided Verification, LNCS 8044. Berlin: Springer, 2013: 264-279. |
47 | LAI G, CHANG W C, YANG Y, et al. Modeling long-and short-term temporal patterns with deep neural networks [C]// Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2018: 95-104. |
48 | WU H, XU J, WANG J, et al. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting [C]// Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 22419-22430. |
49 | ZHENG J, HUANG M. Traffic flow forecast through time series analysis based on deep learning [J]. IEEE Access, 2020, 8: 82562-82570. |
50 | ZHOU H, ZHANG S, PENG J, et al. Informer: beyond efficient transformer for long sequence time-series forecasting [C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 11106-11115. |
51 | Max-Planck-Institut fuer Biogeochemie. Documentation Weather Station [DB/OL]. [2023-12-30]. . |
52 | LAM C N, NICULESCU S, BENGOUFA S. Monitoring and mapping floods and floodable areas in the Mekong Delta (Vietnam) using time-series sentinel-1 images, convolutional neural Network, multi-layer perceptron, and random forest [J]. Remote Sensing, 2023, 15 (8): No.2001. |
53 | BELAGOUNE S, BALI N, BAKDI A, et al. Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems [J]. Measurement, 2021, 177: No.109330. |
54 | XIE J, ZHANG J, SUN J, et al. A transformer-based approach combining deep learning network and spatial-temporal information for raw EEG classification [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2126-2136. |
[1] | 胡健鹏, 张立臣. 面向多时间步风功率预测的深度时空网络模型[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 98-105. |
[2] | 郑宗生, 杜嘉, 成雨荷, 赵泽骋, 张月维, 王绪龙. 用于红外-可见光图像分类的跨模态双流交替交互网络[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 275-283. |
[3] | 徐欣然, 张绍兵, 成苗, 张洋, 曾尚. 基于多路层次化混合专家模型的轴承故障诊断方法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 59-68. |
[4] | 梁杰涛, 罗兵, 付兰慧, 常青玲, 李楠楠, 易宁波, 冯其, 何鑫, 邓辅秦. 基于坐标几何采样的点云配准方法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 214-222. |
[5] | 晏燕, 钱星颖, 闫鹏斌, 杨杰. 位置大数据的联邦学习统计预测与差分隐私保护方法[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 127-135. |
[6] | 黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969. |
[7] | 赵秦壮, 谭红叶. 基于自适应阈值学习的时序因果推断方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2660-2666. |
[8] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[9] | 王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918. |
[10] | 范黎林, 曹富康, 王琬婷, 杨凯, 宋钊瑜. 基于需求模式自适应匹配的间歇性需求预测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2747-2755. |
[11] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[12] | 李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703. |
[13] | 任烈弘, 黄铝文, 田旭, 段飞. 基于DFT的频率敏感双分支Transformer多变量长时间序列预测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2739-2746. |
[14] | 刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557. |
[15] | 顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||