Enhancing Anomaly Detection for Cultural Heritage via Long Short-Term Memory with Attention Mechanism

被引:2
作者
Wu, Yuhan [1 ]
Dong, Yabo [1 ]
Shan, Zeyang [1 ]
Meng, Xiyu [1 ]
He, Yang [1 ]
Jia, Ping [2 ]
Lu, Dongming [1 ]
机构
[1] Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310027, Peoples R China
[2] China Mobile Grp Zhejiang Co Ltd, Hangzhou 311100, Peoples R China
关键词
cultural heritage; anomaly warning; LSTM; attention mechanism; timber structure; DETERIORATION; PREDICTION; RISK;
D O I
10.3390/electronics13071254
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Cultural heritages are invaluable and non-renewable resources. Existing warning mechanisms usually rely on degradation analysis to assess environmental risk factors. However, they have limitations such as complex research, poor generalization, and inadequate warnings. To address these issues, we propose a hybrid model that combines the long short-term memory network (LSTM) and attention mechanisms with environmental factors to detect anomalies in cultural heritage. The attention mechanism extracts temporal dependencies, while LSTM captures global long-term patterns, enhancing the reconstruction capability. Additionally, we introduce the seasonal, trend, shapelet, and mixed anomalies to enrich the positive and negative samples and propose a novel threshold extraction method to reduce the reliance on prior knowledge. Extensive experiments demonstrate that LSTM-Attention outperforms previous methods, with a root mean square error (RMSE) of 34.328, mean absolute error (MAE) of 27.060, and the largest area under the receiver operating characteristic curve (AUC) value, highlighting the superiority and effectiveness of our method. The ablation study proves the contribution of the attention mechanism, and the reconstruction step can be flexibly adjusted according to practical needs. Finally, the algorithm has been successfully implemented in engineering and employed in practice, providing valuable guidelines for the preservation of ancient buildings worldwide.
引用
收藏
页数:21
相关论文
共 53 条
[11]  
Fan LP, 2019, 2019 4TH INTERNATIONAL CONFERENCE ON INTELLIGENT GREEN BUILDING AND SMART GRID (IGBSG 2019), P645, DOI [10.1109/IGBSG.2019.8886291, 10.1109/igbsg.2019.8886291]
[12]   Self-attention neural architecture search for semantic image segmentation [J].
Fan, Zhenkun ;
Hu, Guosheng ;
Sun, Xin ;
Wang, Gaige ;
Dong, Junyu ;
Su, Chi .
KNOWLEDGE-BASED SYSTEMS, 2022, 239
[13]   Sequential Recommendation via Stochastic Self-Attention [J].
Fan, Ziwei ;
Liu, Zhiwei ;
Wang, Yu ;
Wang, Alice ;
Nazari, Zahra ;
Zheng, Lei ;
Peng, Hao ;
Yu, Philip S. .
PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, :2036-2047
[14]  
Fanti R., 2013, Landslide Science and Practice, P467
[15]   Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection [J].
Feng, Xinyang ;
Song, Dongjin ;
Chen, Yuncong ;
Chen, Zhengzhang ;
Ni, Jingchao ;
Chen, Haifeng .
PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, :5546-5554
[16]   Integration of advanced monitoring and numerical modeling techniques for the complete risk scenario analysis of rockslides: The case of Mt. Beni (Florence, Italy) [J].
Gigli, Giovanni ;
Fanti, Riccardo ;
Canuti, Paolo ;
Casagli, Nicola .
ENGINEERING GEOLOGY, 2011, 120 (1-4) :48-59
[17]   Intelligent detection of deterioration in cultural stone heritage [J].
Hatir, M. Ergun ;
Ince, Ismail ;
Korkanc, Mustafa .
JOURNAL OF BUILDING ENGINEERING, 2021, 44
[18]  
Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1007/978-3-642-24797-2, 10.1162/neco.1997.9.1.1]
[19]   Assessment of Flooding Risk to Cultural Heritage in Historic Sites [J].
Holicky, Milan ;
Sykora, Miroslav .
JOURNAL OF PERFORMANCE OF CONSTRUCTED FACILITIES, 2010, 24 (05) :432-438
[20]   Network self attention for forecasting time series. [J].
Hu, Yuntong ;
Xiao, Fuyuan .
APPLIED SOFT COMPUTING, 2022, 124