Abstract
Many computers in companies and universities have old operating systems. These computers cannot perform high-load calculations because their processing power is deteriorated over the time due to the degradation of components such as CPU and memory. Therefore, by clustering deteriorated computers, a single computing resource can be created enabling both effective use of resources and the construction of an environment for deep learning, which requires a heavy computational load. In this paper, we propose an intelligent cluster construction method based on Fuzzy control, which uses computers with low performance specifications. We also present a distributed processing method, which uses a Distributed Convolutional Neural Network (Distributed CNN). Experimental results show that the proposed approach is able to determine the appropriate Cluster-Head (CH) and has good classification results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ramirez-Gargallo, G., et al.: TensorFlow on state-of-the-art HPC clusters: a machine learning use case. In: Proceedings of the IEEE/ACM 19-th International Symposium on Cluster, Cloud and Grid Computing (IEEE/ACM CCGRID), pp. 526–533 (2019)
Mantovani, F., et al.: Performance and power analysis of HPC workloads on heterogeneous multi-node clusters. J. Low Power Electron. Appl. 8(2), 13 (2018)
Mantovani, F., et al.: Performance and energy consumption of HPC workloads on a cluster based on Arm ThunderX2 CPU. Futur. Gener. Comput. Syst. 112, 800–818 (2020)
Chien, S., et al.: TensorFlow doing HPC. In: Proceedings of the IEEE 33rd International Parallel and Distributed Processing Symposium Workshops (IEEE IPDPSW), pp. 509–518 (2019)
EffatParvar, M., et al.: Improved algorithms for leader election in distributed systems. In: Proceedings of the 2nd International Conference on Computer Engineering and Technology (ICCET), Vol. 2, pp. 2–6 (2010)
Biswas, A., et al.: Frlle: a failure rate and load-based leader election algorithm for a bidirectional ring in distributed systems. J. Supercomput. 77(1), 751–779 (2021)
Favier, A., et al.: Centrality-based eventual leader election in dynamic networks. In: Proceedings of the IEEE 20-th International Symposium on Network Computing and Applications (IEEE NCA), pp. 1–8 (2021)
Ingram, R., et al.: An asynchronous leader election algorithm for dynamic networks. In: Proceedings of the IEEE 23-th International Symposium on Parallel & Distributed Processing (IEEE IPDPS), pp. 1–12 (2009)
Saito, N., et al.: Approach of fuzzy theory and hill climbing based recommender for schedule of life. In: Proceedings of the IEEE 2nd Global Conference on Life Sciences and Technologies (IEEE LifeTech), pp. 368–369 (2020)
Matsui, T., et al.: FPGA implementation of a fuzzy inference based quadrotor attitude control system. In: Proceedings of the IEEE 10-th Global Conference on Consumer Electronics (IEEE GCCE), pp. 691–692 (2021)
Yukawa, C., et al.: Design of a robot vision system for microconvex recognition. In: Barolli, L., Kulla, E., Ikeda, M. (eds.) EIDWT 2022. Lecture Notes on Data Engineering and Communications Technologies, vol. 118, pp. 366–374. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-95903-6_39
Lata, S., et al.: Fuzzy clustering algorithm for enhancing reliability and network lifetime of wireless sensor networks. IEEE Access 8, 66013–66024 (2020)
Gm, H., et al.: Pneumonia detection using CNN through chest X-ray. J. Eng. Sci. Technol. (JESTEC) 16, 861–876 (2021)
Kayalibay, B., et al.: CNN-based segmentation of medical imaging data. arXiv preprint arXiv:1701.03056 (2017)
Kore, P., Khoje, S.: Obstacle detection for auto-driving using convolutional neural network. In: Kulkarni, A.J., Satapathy, S.C., Kang, T., Kashan, A.H. (eds.) Proceedings of the 2nd International Conference on Data Engineering and Communication Technology. AISC, vol. 828, pp. 269–278. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-1610-4_28
Wei, J., et al.: Enhanced object detection with deep convolutional neural networks for advanced driving assistance. IEEE Trans. Intell. Transp. Syst. (IEEE TITS) 21(4), 1572–1583 (2019)
Štepec, D., et al.: Video-based ski jump style scoring from pose trajectory. In: Proceedings of the IEEE/CVF 22-th Winter Conference on Applications of Computer Vision Workshop (IEEE/CVF WACVW), pp. 682–690 (2022)
Felsen, P., et al.: What will happen next? Forecasting player moves in sports videos. In: Proceedings of the IEEE 16-th International Conference on Computer Vision (IEEE ICCV), pp. 3342–3351 (2017)
Hershey, S., et al.: CNN architectures for large-scale audio classification. In: Proceedings of the IEEE 42nd International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), pp. 131–135 (2017)
Kamilaris, A., et al.: A review of the use of convolutional neural networks in agriculture. J. Agric. Sci. 156(3), 312–322 (2018)
Acknowledgement
This work was supported by JSPS KAKENHI Grant Number JP20K19793.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hayashi, K. et al. (2023). A Fuzzy Control Based Cluster-Head Selection and CNN Distributed Processing System for Improving Performance of Computers with Limited Resources. In: Barolli, L. (eds) Advances on P2P, Parallel, Grid, Cloud and Internet Computing. 3PGCIC 2022. Lecture Notes in Networks and Systems, vol 571. Springer, Cham. https://doi.org/10.1007/978-3-031-19945-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-19945-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19944-8
Online ISBN: 978-3-031-19945-5
eBook Packages: EngineeringEngineering (R0)