{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T03:10:19Z","timestamp":1769569819246,"version":"3.49.0"},"reference-count":29,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Telekom Malaysia Research and Development","award":["RDTC\/221036"],"award-info":[{"award-number":["RDTC\/221036"]}]},{"name":"Telekom Malaysia Research and Development","award":["MMUE\/220003"],"award-info":[{"award-number":["MMUE\/220003"]}]},{"name":"Telekom Malaysia Research and Development","award":["MMUI\/210028"],"award-info":[{"award-number":["MMUI\/210028"]}]},{"name":"Multimedia University IR Fund","award":["RDTC\/221036"],"award-info":[{"award-number":["RDTC\/221036"]}]},{"name":"Multimedia University IR Fund","award":["MMUE\/220003"],"award-info":[{"award-number":["MMUE\/220003"]}]},{"name":"Multimedia University IR Fund","award":["MMUI\/210028"],"award-info":[{"award-number":["MMUI\/210028"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Raspberry Pi (Pi) is a versatile general-purpose embedded computing device that can be used for both machine learning (ML) and deep learning (DL) inference applications such as face detection. This study trials the use of a Pi Spark cluster for distributed inference in TensorFlow. Specifically, it investigates the performance difference between a 2-node Pi 4B Spark cluster and other systems, including a single Pi 4B and a mid-end desktop computer. Enhancements for the Pi 4B were studied and compared against the Spark cluster to identify the more effective method in increasing the Pi 4B\u2019s DL performance. Three experiments involving DL inference, which in turn involve image classification and face detection tasks, were carried out. Results showed that enhancing the Pi 4B was faster than using a cluster as there was no significant performance difference between using the cluster and a single Pi 4B. The difference between the mid-end computer and a single Pi 4B was between 6 and 15 times in the experiments. In the meantime, enhancing the Pi 4B is the more effective approach for increasing the DL performance, and more work needs to be done for scalable distributed DL inference to eventuate.<\/jats:p>","DOI":"10.3390\/fi14080220","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T21:20:59Z","timestamp":1658784059000},"page":"220","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Exploring Distributed Deep Learning Inference Using Raspberry Pi Spark Cluster"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2538-1519","authenticated-orcid":false,"given":"Nicholas","family":"James","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4749-3490","authenticated-orcid":false,"given":"Lee-Yeng","family":"Ong","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6327-0735","authenticated-orcid":false,"given":"Meng-Chew","family":"Leow","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shinde, P.P., and Shah, S. (2018, January 16\u201318). A review of machine learning and deep learning applications. Proceedings of the 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India.","DOI":"10.1109\/ICCUBEA.2018.8697857"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Dey, N., Ashour, A.S., and Borra, S. (2018). Deep learning for medical image processing: Overview, challenges and the future. Classification in BioApps, Springer.","DOI":"10.1007\/978-3-319-65981-7"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1109\/TRPMS.2019.2899538","article-title":"Machine (deep) learning methods for image processing and radiomics","volume":"3","author":"Hatt","year":"2019","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"ref_4","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., and Zheng, X. (2016, January 2\u20134). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Gupta, A., Gandhi, C., Katara, V., and Brar, S. (2020, January 10\u201312). Real-time video monitoring of vehicular traffic and adaptive signal change using Raspberry Pi. Proceedings of the 2020 IEEE Students Conference on Engineering & Systems (SCES), Prayagraj, India.","DOI":"10.1109\/SCES50439.2020.9236731"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Gupta, I., Patil, V., Kadam, C., and Dumbre, S. (2016, January 19\u201321). Face detection and recognition using Raspberry Pi. Proceedings of the 2016 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), Pune, India.","DOI":"10.1109\/WIECON-ECE.2016.8009092"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Patel, K., and Patel, M. (2021, January 1\u20133). Smart Surveillance System using Deep Learning and RaspberryPi. Proceedings of the 2021 8th International Conference on Smart Computing and Communications (ICSCC), Kochi, India.","DOI":"10.1109\/ICSCC51209.2021.9528194"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Anh, P.T., and Duc, H.T.M. (2021, January 14\u201316). A Benchmark of Deep Learning Models for Multi-leaf Diseases for Edge Devices. Proceedings of the 2021 International Conference on Advanced Technologies for Communications (ATC), Ho Chi Minh City, Vietnam.","DOI":"10.1109\/ATC52653.2021.9598196"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cloutier, M., Paradis, C., and Weaver, V. (2016). A Raspberry Pi Cluster Instrumented for Fine-Grained Power Measurement. Electronics, 5.","DOI":"10.3390\/electronics5040061"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hajji, W., and Tso, F. (2016). Understanding the Performance of Low Power Raspberry Pi Cloud for Big Data. Electronics, 5.","DOI":"10.3390\/electronics5020029"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rahmat, R.F., Saputra, T., Hizriadi, A., Lini, T.Z., and Nasution, M.K. (2019, January 16\u201317). Performance test of parallel image processing using open MPI on Raspberry PI cluster board. Proceedings of the 2019 3rd International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), Medan, Indonesia.","DOI":"10.1109\/ELTICOM47379.2019.8943848"},{"key":"ref_12","unstructured":"Komninos, A., Simou, I., Gkorgkolis, N., and Garofalakis, J.D. (2019, January 13\u201315). Performance of Raspberry Pi microclusters for Edge Machine Learning in Tourism. Proceedings of the European Conference on Ambient Intelligence 2019, Rome, Italy."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"S\u00fczen, A.A., Duman, B., and \u015een, B. (2020, January 26\u201328). Benchmark analysis of jetson tx2, jetson nano and raspberry pi using deep-cnn. Proceedings of the 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Ankara, Turkey.","DOI":"10.1109\/HORA49412.2020.9152915"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yoshimoto, J., Taniguchi, I., Tomiyama, H., and Onoye, T. (2020, January 21\u201324). An Evaluation of Edge Computing Platform for Reliable Automated Drones. Proceedings of the 2020 International SoC Design Conference (ISOCC), Yeosu, Korea.","DOI":"10.1109\/ISOCC50952.2020.9332925"},{"key":"ref_15","first-page":"21","article-title":"Benchmarking Raspberry Pi 2 Beowulf Cluster","volume":"179","author":"Papakyriakou","year":"2018","journal-title":"Int. J. Comput. Appl."},{"key":"ref_16","first-page":"989","article-title":"An efficient implementation of mobile raspberry Pi hadoop clusters for robust and augmented computing performance","volume":"14","author":"Srinivasan","year":"2018","journal-title":"J. Inf. Process. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Samadi, Y., Zbakh, M., and Tadonki, C. (2016, January 24\u201326). Comparative study between Hadoop and Spark based on Hibench benchmarks. Proceedings of the 2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech), Marrakech, Morocco.","DOI":"10.1109\/CloudTech.2016.7847709"},{"key":"ref_18","first-page":"1","article-title":"An empirical study of cross-platform mobile development in industry","volume":"2","year":"2019","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Mantowsky, S., Heuer, F., Bukhari, S., Keckeisen, M., and Schneider, G. (2021, January 11\u201317). ProAI: An Efficient Embedded AI Hardware for Automotive Applications-A Benchmark Study. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCVW54120.2021.00113"},{"key":"ref_20","unstructured":"Bordin, M.V. (2017). A Benchmark Suite for Distributed Stream Processing Systems. [Master\u2019s Thesis, Federal University of Rio Grande do Sul]."},{"key":"ref_21","unstructured":"Recht, B., Roelofs, R., Schmidt, L., and Shankar, V. (2019, January 9\u201315). Do imagenet classifiers generalize to imagenet?. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_22","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical Report TR-2009."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., and Tang, X. (2016, January 27\u201330). Wider face: A face detection benchmark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint face detection and alignment using multitask cascaded convolutional networks","volume":"23","author":"Zhang","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020, January 13\u201319). Retinaface: Single-shot multi-level face localisation in the wild. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.2991\/ijcis.d.200805.002","article-title":"YOLOv3: Face detection in complex environments","volume":"13","author":"Chun","year":"2022","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xiang, J., and Zhu, G. (2017, January 21\u201323). Joint face detection and facial expression recognition with MTCNN. Proceedings of the 2017 4th international conference on information science and control engineering (ICISCE), Changsha, China.","DOI":"10.1109\/ICISCE.2017.95"},{"key":"ref_28","unstructured":"Li, M., Andersen, D.G., Park, J.W., Smola, A.J., Ahmed, A., Josifovski, V., Long, J., Shekita, E.J., and Su, B.Y. (2014, January 6\u20138). Scaling distributed machine learning with the parameter server. Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14), Broomfield, CO, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.jss.2016.11.037","article-title":"Performance evaluation of cloud-based log file analysis with Apache Hadoop and Apache Spark","volume":"125","author":"Mavridis","year":"2017","journal-title":"J. Syst. Softw."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/14\/8\/220\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:56:01Z","timestamp":1760140561000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/14\/8\/220"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,25]]},"references-count":29,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["fi14080220"],"URL":"https:\/\/doi.org\/10.3390\/fi14080220","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,25]]}}}