Distributed Face Recognition Based on Load Balancing and Dynamic Prediction
Source abstract
Abstract
With the dramatic expansion of large-scale videos, traditional centralized face recognition methods cannot meet the demands of time efficiency and expansibility, and thus distributed face recognition models were proposed. However, the number of tasks at the agent side is always dynamic, and unbalanced allocation will lead to time delay and a sharp increase of CPU utilization. To this end, a new distributed face recognition framework based on load balancing and dynamic prediction is proposed in this paper. The framework consists of a server and multiple agents. When performing face recognition, the server is used to recognize faces, and other operations are performed by the agents. Since the changes of the total number of videos and the number of pedestrians affect the task amount, we perform load balancing with an improved genetic algorithm. To ensure the accuracy of task allocation, we use extreme learning machine to predict the change of tasks. The server then performs task allocation based on the predicted results sent by the agents. The experimental results show that the proposed method can effectively solve the problem of unbalanced task allocation at the agent side, and meanwhile alleviate time delay and the sharp increase of CPU utilization.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and ELM · Face and Expression Recognition · Organizational and Employee Performance
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Engineering, Nanchang University, Nanchang 330031, China
School of Software, Nanchang University, Nanchang 330047, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Jiangxi Province
References (48)
Show source-provided references
1. A literature survey on face recognition techniques
2. Poli, G., Saito, J.H., Mari, J.F., and Zorzan, M.R. (November, January 29). Processing Neocognitron of Face Recognition on High Performance Environment Based on GPU with CUDA Architecture. Presented at the 20th International Symposium on Computer Architecture and High Performance Computing, Campo Grande, Brazil.
3. Recognition of pedestrian activity based on dropped-object detection10.1016/j.sigpro.2017.09.024 ↗
4. Jiang, C., Su, G., and Liu, X. (2003, January 29). A distributed parallel system for face recognition. Proceedings of the Fourth International Conference on Parallel and Distributed Computing, Applications and Technologies, Chengdu, China.
5. Distributed wireless face recognition system
6. Energy efficient distributed face recognition in wireless sensor network10.1007/s11277-011-0310-y ↗
7. A distributed face recognition framework based on data fusion10.14257/ijdta.2014.7.4.08 ↗
8. Ali, U., and Bilal, M. (2006, January 22–23). Video based parallel face recognition using gabor filter on homogeneous distributed systems. Presented at the 2006 IEEE International Conference on Engineering of Intelligent Systems, Islamabad, Pakistan.
9. Chetty, G., and Sharma, D. (2006, January 9–11). Distributed face recognition: A multiagent approach. Proceedings of the International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, Bournemouth, UK.10.1007/11893011_148 ↗
10. Genetic algorithms for task scheduling problem10.1016/j.jpdc.2009.09.009 ↗
11. A chaotic non-dominated sorting genetic algorithm for the multi-objective automatic test task scheduling problem10.1016/j.asoc.2012.10.001 ↗
12. Zhan, Z.H., Zhang, G.Y., Gong, Y.J., and Zhang, J. (2014, January 15–18). Load balance aware genetic algorithm for task scheduling in cloud computing. Proceedings of the Asia-Pacific Conference on Simulated Evolution and Learning, Dunedin, New Zealand.10.1007/978-3-319-13563-2_54 ↗
13. Makasarwala, H.A., and Hazari, P. (July, January 30). Using genetic algorithm for load balancing in cloud computing. Presented at the 2016 8th International Conference on Electronics, Computers and Artificial Intelligence, Ploiesti, Romania.10.1109/ECAI.2016.7861166 ↗
14. A combination of game theory and genetic algorithm for load balancing in distributed computer systems
15. Performance analysis of ant colony optimization and genetic algorithm for cloud load balancing
16. Min, W., Fan, M., Li, J., and Han, Q. (2018). Real-time face recognition based on face pre-identification detection and multi-scale classification. IET Comput. Vision.10.1049/iet-cvi.2018.5586 ↗
17. Improved the minimum squared error algorithm for face recognition by integrating original face images and the mirror images10.1016/j.ijleo.2015.10.182 ↗
18. Dang, K., and Sharma, S. (2017, January 12–13). Review and comparison of face detection algorithms. Presented at the 2017 7th International Conference on Cloud Computing, Data Science & Engineering-Confluence, Noida, India.10.1109/CONFLUENCE.2017.7943228 ↗
19. Dynamic texture comparison using derivative sparse representation: Application to video-based face recognition10.1109/THMS.2017.2681425 ↗
20. Opitz, A., and Kriechbaumzabini, A. (2015, January 25–28). Evaluation of face recognition technologies for identity verification in an eGate based on operational data of an airport. Presented at 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance, Karlsruhe, Germany.10.1109/AVSS.2015.7301747 ↗
21. Intruder recognition system
22. Siswanto, A.R.S., Nugroho, A.S., and Galinium, M. (2014, January 24–25). Implementation of face recognition algorithm for biometrics based time attendance system. Presented at the 2014 International Conference on ICT For Smart Society (ICISS), Bandung, Indonesia.10.1109/ICTSS.2014.7013165 ↗
23. Yu, L., and Li, K. (2017, January 8–9). Application of Face Recognition Technology in the Exam Identity Authentication System. Proceedings of the 3rd International Conference on Social Science and Management, Xi’an, China.10.12783/dtssehs/icssm2017/10431 ↗
24. Identity Verification of Ticket Holders at Large-scale Events Using Face Recognition
25. First: Face identity recognition in smart bank10.1142/S1793351X16400213 ↗
26. Gaynor, P., and Coore, D. (2015, January 9–12). Distributed face recognition using collaborative judgement aggregation in a swarm of tiny wireless sensor nodes. Proceedings of the Southeast Con 2015, Fort Lauderdale, FL, USA.10.1109/SECON.2015.7133046 ↗
27. Monteiro, C.E., and Trevelin, L.C. (2015, January 17–20). Studies of computing techniques for performing face recognition with a focus in the crowds: A distributed architecture based on cloud computing. Presented at 2015 IEEE/ACS 12th International Conference of Computer Systems and Applications, Marrakech, Morocco.10.1109/AICCSA.2015.7507131 ↗
28. Distributed Face Recognition Using Multiple Kernel Discriminant Analysis in Wireless Sensor Networks
29. Design of a Parallel Face Detection Algorithm for Distributed Low Cost IP-based Surveillance Systems
30. Hinojos, G., and Leon, P.L.D. (2014, January 4–9). Face recognition using distributed, mobile computing. Presented at the 2014 IEEE International Conference on Acoustic, Speech and Signal Processing, Florence, Italy.10.1109/ICASSP.2014.6853985 ↗
31. Face recognition in video systems on homogeneous distributed systems
32. A genetic algorithm for static load balancing in parallel heterogeneous systems10.1016/j.sbspro.2014.03.688 ↗
33. A genetic algorithm (ga) based load balancing strategy for cloud computing10.1016/j.protcy.2013.12.369 ↗
34. A genetic-fuzzy algorithm for load balancing in multiprocessor systems
35. Dynamic genetic algorithms for the dynamic load balanced clustering problem in mobile ad hoc networks10.1016/j.eswa.2012.08.050 ↗
36. Enhancing energy efficiency and load balancing in mobile ad hoc network using dynamic genetic algorithms10.1016/j.jnca.2016.07.003 ↗
37. Extreme learning machine: Theory and applications10.1016/j.neucom.2005.12.126 ↗
38. Extreme learning machine: Algorithm, theory and applications10.1007/s10462-013-9405-z ↗
39. Extreme learning machines: New trends and applications
40. Application of extreme learning machine for estimation of wind speed distribution10.1007/s00382-015-2730-y ↗
41. Application of extreme learning machine for underground cable fault location10.1002/etep.2032 ↗
42. Application of extreme learning machine to gas flow measurement with multipath acoustic transducers10.1016/j.flowmeasinst.2016.03.003 ↗
43. Rational and self-adaptive evolutionary extreme learning machine for electricity price forecast10.1007/s12293-016-0195-0 ↗
44. A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecasting10.1016/j.engappai.2015.04.016 ↗
45. Selective ensemble based on extreme learning machine and improved discrete artificial fish swarm algorithm for haze forecast10.1007/s10489-017-1027-8 ↗
46. Entropy method combined with extreme learning machine method for the short-term photovoltaic power generation forecasting10.1016/j.chaos.2015.11.008 ↗
47. Multimodal Biometric System Using Face-Iris Fusion Feature10.4304/jcp.6.5.931-938 ↗
48. Wang, K. (2013, January 9–11). Implementation of face cartoon maker system based on android. Presented at the 2013 Fourth International Conference on Intelligent Control & Information Processing, Beijing, China.10.1109/ICICIP.2013.6568066 ↗