Semi-supervised Anomaly Detection
Semi-Supervised Anomaly Detection is a methodological framework within anomaly detection that leverages a subset of labeled data—typically only normal instances—combined with unlabeled data to learn a model that distinguishes anomalous from normal behavior by assuming most training data are normal while identifying deviations in time series observations.
295
Publications
16.2K
Citations
1K
Authors
418
Institutions
Publications per year
2017–2026
247
295
A survey on anomaly detection for technical systems using LSTM networks
B. Lindemann, Benjamin Maschler, Nada Sahlab et al. · Computers in Industry · 2021 · 425 citations · Full text
1–5 of 295
1K
4
h-index
3
h-index
3
h-index
3
h-index
3
h-index
1–5 of 1K
418

Chinese Academy of Sciences
Beijing, China
5 h-index
17 publications
1.3K citations

Sun Yat-sen University
Guangzhou, China
5 h-index
15 publications
584 citations
Tsinghua University
Beijing, China
5 h-index
10 publications
519 citations
KU Leuven
Leuven, Belgium
4 h-index
13 publications
834 citations

Huazhong University of Science and Technology
Wuhan, China
4 h-index
11 publications
309 citations
RWTH Aachen University
Aachen, Germany
4 h-index
17 publications
1.4K citations
State Key Laboratory of Industrial Control Technology
Hangzhou, China
4 h-index
11 publications
315 citations
Tencent (China)
Shenzhen, China
4 h-index
6 publications
337 citations
1–8 of 418
Repository · 19 publications · 446 citations
14
h-index
13 publications · 784 citations
12
h-index
7 publications · 980 citations
7
h-index
5 publications · 726 citations
5
h-index
5 publications · 102 citations
5
h-index
1–5