{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T09:10:28Z","timestamp":1769764228291,"version":"3.49.0"},"reference-count":52,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T00:00:00Z","timestamp":1744070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>This paper presents the development and evaluation of a distributed system employing low-latency embedded field-programmable gate arrays (FPGAs) to optimize scheduling for deep learning (DL) workloads and to configure multiple deep learning accelerator (DLA) architectures. Aimed at advancing FPGA applications in real-time edge computing, this study focuses on achieving optimal latency for a distributed computing system. A novel methodology was adopted, using configurable hardware to examine clusters of DLAs, varying in architecture and scheduling techniques. The system demonstrated its capability to parallel-process diverse neural network (NN) models, manage compute graphs in a pipelined sequence, and allocate computational resources efficiently to intensive NN layers. We examined five configurable DLAs\u2014Versatile Tensor Accelerator (VTA), Nvidia DLA (NVDLA), Xilinx Deep Processing Unit (DPU), Tensil Compute Unit (CU), and Pipelined Convolutional Neural Network (PipeCNN)\u2014across two FPGA cluster types consisting of Zynq-7000 and Zynq UltraScale+ System-on-Chip (SoC) processors, respectively. Four deep neural network (DNN) workloads were tested: Scatter-Gather, AI Core Assignment, Pipeline Scheduling, and Fused Scheduling. These methods revealed an exponential decay in processing time up to 90% speedup, although deviations were noted depending on the workload and cluster configuration. This research substantiates FPGAs\u2019 utility in adaptable, efficient DL deployment, setting a precedent for future experimental configurations and performance benchmarks.<\/jats:p>","DOI":"10.3390\/info16040298","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T11:05:02Z","timestamp":1744110302000},"page":"298","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning Scheduling on a Field-Programmable Gate Array Cluster Using Configurable Deep Learning Accelerators"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8741-0473","authenticated-orcid":false,"given":"Tianyang","family":"Fang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA"}]},{"given":"Alejandro","family":"Perez-Vicente","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9153-921X","authenticated-orcid":false,"given":"Hans","family":"Johnson","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2655-6950","authenticated-orcid":false,"given":"Jafar","family":"Saniie","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"7823","DOI":"10.1109\/ACCESS.2018.2890150","article-title":"FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review","volume":"7","author":"Shawahna","year":"2019","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sentieys, O., Filip, S., Briand, D., Novo, D., Dupuis, E., O\u2019Connor, I., and Bosio, A. (2021, January 7\u20139). AdequateDL: Approximating Deep Learning Accelerators. Proceedings of the 2021 24th International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS), Vienna, Austria.","DOI":"10.1109\/DDECS52668.2021.9417026"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pal, S., Venkataramani, S., Srinivasan, V., and Gopalakrishnan, K. (2021, January 28\u201330). Efficient Management of Scratch-Pad Memories in Deep Learning Accelerators. Proceedings of the 2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Stony Brook, NY, USA.","DOI":"10.1109\/ISPASS51385.2021.00046"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yang, A. (2019, January 18\u201320). Deep Learning Training At Scale Spring Crest Deep Learning Accelerator (Intel\u00ae Nervana\u2122 NNP-T). Proceedings of the 2019 IEEE Hot Chips 31 Symposium (HCS), Cupertino, CA, USA.","DOI":"10.1109\/HOTCHIPS.2019.8875643"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Song, L., Chen, F., Chen, Y., and Li, H. (2020, January 13\u201316). Parallelism in Deep Learning Accelerators. Proceedings of the 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), Beijing, China.","DOI":"10.1109\/ASP-DAC47756.2020.9045206"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Choubey, A., and Choubey, S.B. (2021, January 18\u201319). Efficient Design of Adaptable Deep Learning Accelerator. Proceedings of the 2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), Bhopal, India.","DOI":"10.1109\/CSNT51715.2021.9509692"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Faber, C.J., Harris, S.D., Xiac, Z., Chamberlain, R.D., and Cabrera, A.M. (2022, January 19\u201323). Challenges Designing for FPGAs Using High-Level Synthesis. Proceedings of the 2022 IEEE High Performance Extreme Computing Conference (HPEC), Waltham, MA, USA.","DOI":"10.1109\/HPEC55821.2022.9926398"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/TPDS.2020.3030548","article-title":"The Deep Learning Compiler: A Comprehensive Survey","volume":"32","author":"Li","year":"2021","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Gonzalez-Carabarin, L., Schmid, A., and Sloun, R.J.v. (June, January 27). Structured and tiled-based pruning of Deep Learning models targeting FPGA implementations. Proceedings of the 2022 IEEE International Symposium on Circuits and Systems (ISCAS), Austin, TX, USA.","DOI":"10.1109\/ISCAS48785.2022.9937748"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, Z., Ge, F., Zhou, F., and Wu, N. (2022, January 11\u201314). An A3C Deep Reinforcement Learning FPGA Accelerator based on Heterogeneous Compute Units. Proceedings of the 2022 IEEE 22nd International Conference on Communication Technology (ICCT), Nanjing, China.","DOI":"10.1109\/ICCT56141.2022.10073229"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Soltani, S., Sagduyu, Y.E., Hasan, R., Davaslioglu, K., Deng, H., and Erpek, T. (2019, January 11\u201314). Real-Time Experimentation of Deep Learning-based RF Signal Classifier on FPGA. Proceedings of the 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Newark, NJ, USA.","DOI":"10.1109\/DySPAN.2019.8935784"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yin, H., Hong, H., and Liu, J. (2021, January 15\u201319). FPGA-based Deep Learning Acceleration for Visual Grasping Control of Manipulator. Proceedings of the 2021 IEEE International Conference on Real-time Computing and Robotics (RCAR), Xining, China.","DOI":"10.1109\/RCAR52367.2021.9517666"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lu, Y., Zhai, X., Saha, S., Ehsan, S., and McDonald-Maier, K.D. (2021, January 20\u201323). FPGA based Adaptive Hardware Acceleration for Multiple Deep Learning Tasks. Proceedings of the 2021 IEEE 14th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSoC), Singapore.","DOI":"10.1109\/MCSoC51149.2021.00038"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rupanetti, D., Nepal, K., Salamy, H., and Min, C.H. (2020, January 6\u20138). Cost-Effective, Re-Configurable Cluster Approach for Resource Constricted FPGA Based Machine Learning and AI Applications. Proceedings of the 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.","DOI":"10.1109\/CCWC47524.2020.9031161"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kan, H., Li, R., Su, D., Wang, Y., Shen, Y., and Liu, W. (2020, January 20\u201322). Trusted Edge Cloud Computing Mechanism Based on FPGA Cluster. Proceedings of the 2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China.","DOI":"10.1109\/ICCSNT50940.2020.9304996"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wu, C.B., Hsiao, Y.K., and Chang, W.H. (2022, January 13\u201315). Extensible and Modularized Processing Unit Design and Implementation for AI Accelerator. Proceedings of the 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS), Incheon, Republic of Korea.","DOI":"10.1109\/AICAS54282.2022.9869949"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lin, X., Yin, S., Tu, F., Liu, L., Li, X., and Wei, S. (2018, January 24\u201328). LCP: A Layer Clusters Paralleling mapping method for accelerating Inception and Residual networks on FPGA. Proceedings of the 2018 55th ACM\/ESDA\/IEEE Design Automation Conference (DAC), San Francisco, CA, USA.","DOI":"10.1109\/DAC.2018.8465777"},{"key":"ref_18","first-page":"2142","article-title":"A Memory-Efficient CNN Accelerator Using Segmented Logarithmic Quantization and Multi-Cluster Architecture","volume":"68","author":"Xu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Johnson, H., Fang, T., Perez-Vicente, A., and Saniie, J. (2023, January 18\u201320). Reconfigurable Distributed FPGA Cluster Design for Deep Learning Accelerators. Proceedings of the 2023 IEEE International Conference on Electro Information Technology (eIT), Romeoville, IL, USA.","DOI":"10.1109\/eIT57321.2023.10187228"},{"key":"ref_20","unstructured":"Apache.org (2024, December 19). Overview\u2014tvm 0.19.dev0 Documentation. Available online: https:\/\/tvm.apache.org\/docs\/get_started\/overview.html."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Farshchi, F., Huang, Q., and Yun, H. (2019, January 17). Integrating NVIDIA Deep Learning Accelerator (NVDLA) with RISC-V SoC on FireSim. Proceedings of the 2019 2nd Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2), Washington, DC, USA.","DOI":"10.1109\/EMC249363.2019.00012"},{"key":"ref_22","unstructured":"Tensil (2024, December 19). Hardware Architecture and Implementation Details. Available online: https:\/\/www.tensil.ai\/docs\/reference\/hardware\/."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, D., Xu, K., and Jiang, D. (2017, January 11\u201313). PipeCNN: An OpenCL-based open-source FPGA accelerator for convolution neural networks. Proceedings of the 2017 International Conference on Field Programmable Technology (ICFPT), Melbourne, VIC, Australia.","DOI":"10.1109\/FPT.2017.8280160"},{"key":"ref_24","unstructured":"Taylor, A. (2024, December 19). MicroZed Chronicles: The Deep Learning Processing Unit. Available online: https:\/\/www.hackster.io\/news\/microzed-chronicles-the-deep-learning-processing-unit-659221f58883."},{"key":"ref_25","unstructured":"AMD (2024, December 19). DPU for Convolutional Neural Network. Available online: https:\/\/www.xilinx.com\/products\/intellectual-property\/dpu.html#overview."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ramagond, S., Yellampalli, S., and Kanagasabapathi, C. (2017, January 17\u201319). A review and analysis of communication logic between PL and PS in ZYNQ AP SoC. Proceedings of the 2017 International Conference On Smart Technologies For Smart Nation (SmartTechCon), Bengaluru, India.","DOI":"10.1109\/SmartTechCon.2017.8358511"},{"key":"ref_27","unstructured":"Ferguson, D. (2024, December 19). Clusterssh, 2018. Copyright 1999\u20132018 Duncan Ferguson. Licensed under the GNU GPL or Artistic License. Available online: https:\/\/github.com\/duncs\/clusterssh."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, Z. (2023, January 29\u201331). The Analysis of Distributed Computing Systems with Machine Learning. Proceedings of the 2023 International Conference on Networking, Informatics and Computing (ICNETIC), Palermo, Italy.","DOI":"10.1109\/ICNETIC59568.2023.00020"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gavankar, T., Joshi, A., and Sharma, S. (2018, January 13\u201314). Distributed Computing and Image Processing for Autonomous Driving Systems. Proceedings of the 2018 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER), Mangalore, India.","DOI":"10.1109\/DISCOVER.2018.8673972"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, B., Zhao, Y., and Shi, W. (2022, January 5\u20138). Towards Edge-enabled Distributed Computing Framework for Heterogeneous Android-based Devices. Proceedings of the 2022 IEEE\/ACM 7th Symposium on Edge Computing (SEC), Seattle, WA, USA.","DOI":"10.1109\/SEC54971.2022.00082"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, H., and Wu, Y. (2021, January 11\u201315). Coded Computing for Master-Aided Distributed Computing Systems. Proceedings of the 2020 IEEE Information Theory Workshop (ITW), Riva del Garda, Italy.","DOI":"10.1109\/ITW46852.2021.9457580"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wen, J., and Zhang, W. (2020, January 6\u20138). Billing System in Distributed Computing Environment. Proceedings of the 2020 International Conference on Computer Engineering and Intelligent Control (ICCEIC), Chongqing, China.","DOI":"10.1109\/ICCEIC51584.2020.00066"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"D\u0131ker, A. (2021, January 6\u20138). A Performance Comparison of Pre-trained Deep Learning Models to Classify Brain Tumor. Proceedings of the IEEE EUROCON 2021\u201419th International Conference on Smart Technologies, Lviv, Ukraine.","DOI":"10.1109\/EUROCON52738.2021.9535636"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Khan, S.U., Mynuddin, M., Ahad, D.M.A., Hossain, M.I., Islam, M.J., and Kabir, M.F. (2023, January 7\u201310). A Comparative Analysis of Deep Learning Models for Power Quality Disturbance Classification. Proceedings of the 2023 IEEE World AI IoT Congress (AIIoT), Seattle, WA, USA.","DOI":"10.1109\/AIIoT58121.2023.10174320"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Poomrittigul, S., Chomkwah, W., Tanpatanan, T., Sakorntanant, S., and Treebupachatsakul, T. (2022, January 5\u20138). A Comparison of Deep Learning CNN Architecture Models for Classifying Bacteria. Proceedings of the 2022 37th International Technical Conference on Circuits\/Systems, Computers and Communications (ITC-CSCC), Phuket, Thailand.","DOI":"10.1109\/ITC-CSCC55581.2022.9894986"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Gan, H.S., Ramlee, M.H., Wahab, A.A., Mahmud, W.M.H.W., and Setiadi, D.R.I.M. (2022, January 7\u20139). Image-to-Graph Transformation via Superpixel Clustering to Build Nodes in Deep Learning for Graph. Proceedings of the 2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Kuala Lumpur, Malaysia.","DOI":"10.1109\/IECBES54088.2022.10079411"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, R., Gopinath, K., Desrosiers, C., and Lombaert, H. (2020, January 3\u20137). Spectral Graph Transformer Networks for Brain Surface Parcellation. Proceedings of the 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, USA.","DOI":"10.1109\/ISBI45749.2020.9098737"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1109\/TMI.2020.3035789","article-title":"Combined Spiral Transformation and Model-Driven Multi-Modal Deep Learning Scheme for Automatic Prediction of TP53 Mutation in Pancreatic Cancer","volume":"40","author":"Chen","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Bertalani\u010d, B., Vnu\u010dec, M., and Fortuna, C. (2023, January 5\u20138). Graph Neural Networks Based Anomalous RSSI Detection. Proceedings of the 2023 International Balkan Conference on Communications and Networking (BalkanCom), \u0130stanbul, Turkey.","DOI":"10.1109\/BalkanCom58402.2023.10167910"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1109\/TPAMI.2022.3170559","article-title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","volume":"45","author":"Xie","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Lattner, C., Amini, M., Bondhugula, U., Cohen, A., Davis, A., Pienaar, J., Riddle, R., Shpeisman, T., Vasilache, N., and Zinenko, O. (March, January 27). MLIR: Scaling Compiler Infrastructure for Domain Specific Computation. Proceedings of the 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), Seoul, Republic of Korea.","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, Y., and Xie, F. (2022, January 26\u201330). Extending Tensor Virtual Machine to Support Deep-Learning Accelerators with Convolution Cores. Proceedings of the 2022 26th International Conference on Engineering of Complex Computer Systems (ICECCS), Hiroshima, Japan.","DOI":"10.1109\/ICECCS54210.2022.00031"},{"key":"ref_43","unstructured":"Xilinx (2024, December 19). Xilinx\/Vitis-AI. Available online: https:\/\/github.com\/Xilinx\/Vitis-AI."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Jadhav, S.S., Gloster, C., Naher, J., Doss, C., and Kim, Y. (2021, January 1\u20134). A Multi-Memory Field-Programmable Custom Computing Machine for Accelerating Compute-Intensive Applications. Proceedings of the 2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York, NY, USA.","DOI":"10.1109\/UEMCON53757.2021.9666601"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zou, C., Cui, X., Kuang, Y., Liu, K., Wang, Y., Wang, X., and Huang, R. (2021). A Scatter-and-Gather Spiking Convolutional Neural Network on a Reconfigurable Neuromorphic Hardware. Front. Neurosci., 15.","DOI":"10.3389\/fnins.2021.694170"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1145\/327070.327215","article-title":"Improvements in multiprocessor system design","volume":"13","author":"Rodgers","year":"1985","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Reddy, M. (2011). API Design for C++, Morgan Kaufmann Publishers.","DOI":"10.1016\/B978-0-12-385003-4.00004-X"},{"key":"ref_48","unstructured":"Bello, I., Fedus, L.B., Du, X., Cubuk, E.D., Srinivas, A., Lin, T.Y., Shlens, J., and Zoph, B.R. (2024, December 19). Revisiting ResNets: Improved Training Methodologies and Scaling Principles. Available online: https:\/\/research.google\/pubs\/revisiting-resnets-improved-training-methodologies-and-scaling-principles\/."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Bressem, K.K., Adams, L.C., Erxleben, C., Hamm, B., Niehues, S.M., and Vahldiek, J.L. (2020). Comparing Different Deep Learning Architectures for Classification of Chest Radiographs. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-70479-z"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Pandey, G.K., and Srivastava, S. (2023, January 26\u201328). ResNet-18 comparative analysis of various activation functions for image classification. Proceedings of the 2023 International Conference on Inventive Computation Technologies (ICICT), Lalitpur, Nepal.","DOI":"10.1109\/ICICT57646.2023.10134464"},{"key":"ref_51","unstructured":"AMD (2024, December 19). Aurora 64B\/66B. Available online: https:\/\/www.xilinx.com\/products\/intellectual-property\/aurora64b66b.html."},{"key":"ref_52","unstructured":"AMD (2024, December 19). Power Estimator. Available online: https:\/\/www.amd.com\/en\/products\/adaptive-socs-and-fpgas\/technologies\/power-efficiency\/power-estimator.html."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/4\/298\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:12:18Z","timestamp":1760029938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/4\/298"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,8]]},"references-count":52,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["info16040298"],"URL":"https:\/\/doi.org\/10.3390\/info16040298","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,8]]}}}