Edge Anomaly Detection
Edge Anomaly Detection is a computational framework within edge artificial intelligence that enables the localized identification of deviant patterns or behaviors in data streams at or near the data source, distinguishing itself from centralized approaches by leveraging real-time processing, reduced latency, and constrained resource adaptability inherent to edge computing environments.
94
Publications
4.3K
Citations
379
Authors
212
Institutions
Publications per year
2017–2026
84
Parents
94
AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN
Li Zheng, Zhenpeng Li, Jian Li et al. · 2019 · 239 citations · Full text
Edge AI: A Taxonomy, Systematic Review and Future Directions
Sukhpal Singh Gill, Muhammed Golec, Jianmin Hu et al. · Cluster Computing · 2024 · 147 citations
LightLog: A lightweight temporal convolutional network for log anomaly detection on the edge
Zumin Wang, Jiyu Tian, Hui Fang et al. · Computer Networks · 2021 · 98 citations · Full text
1–5 of 94
379
3
h-index
3
h-index
3
h-index
2
h-index
2
h-index
1–5 of 379
212

Chinese Academy of Sciences
Beijing, China
4 h-index
8 publications
587 citations
National University of Singapore
Singapore, Singapore
4 h-index
7 publications
273 citations
University of Chinese Academy of Sciences
Beijing, China
3 h-index
9 publications
174 citations
Tianjin University
Tianjin, China
3 h-index
4 publications
335 citations
Carnegie Mellon University
Pittsburgh, United States
3 h-index
6 publications
348 citations
Cardiff University
Cardiff, United Kingdom
3 h-index
5 publications
139 citations
University of Oxford
Oxford, United Kingdom
3 h-index
10 publications
278 citations
NTT (Japan)
Tokyo, Japan
2 h-index
6 publications
282 citations
1–8 of 212
7 publications · 736 citations
7
h-index
6 publications · 251 citations
6
h-index
2 publications · 175 citations
2
h-index
2 publications · 151 citations
2
h-index
2 publications · 59 citations
2
h-index
1–5