Title | ||
---|---|---|
A Heterogeneous Fault-Resilient Architecture for Mining Anomalous Activity Patterns in Smart Homes |
Abstract | ||
---|---|---|
We are presenting a massively parallel heterogeneous cloud-based architecture oriented towards anomalous activity detection in smart homes. The architecture has very high resilience to both hardware and software faults, it is capable of collecting activity from various data sources and performing anomaly detection in real-time. We corroborate the approach with an efficient checkpointing mechanism for data processing which allows the implementation of hybrid (CPU/GPU) fault-resilience and anomaly detection through pattern mining techniques, at the same time offering high throughput. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-19713-5_12 | INTERNATIONAL JOINT CONFERENCE: CISIS'15 AND ICEUTE'15 |
Keywords | Field | DocType |
Anomaly detection,Pattern mining,Smart home,Fault resiliency,Heterogeneous architecture,Graphics processing unit | Anomaly detection,Data mining,Data processing,Massively parallel,Computer science,Home automation,Software,Throughput,Graphics processing unit,Cloud computing,Distributed computing | Conference |
Volume | ISSN | Citations |
369 | 2194-5357 | 0 |
PageRank | References | Authors |
0.34 | 7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ciprian Pungila | 1 | 11 | 4.51 |
Bogdan Manate | 2 | 20 | 3.44 |
Viorel Negru | 3 | 311 | 47.71 |