Lightweight Neural Network-Based Dynamic Monitoring Model for Community Human Settlement Environment Governance
Main Article Content
Abstract
Aiming at the problems of poor real-time performance, high equipment deployment cost and insufficient adaptability of big data models existing in current community human settlement environment monitoring, this paper constructs a dynamic monitoring model of human settlement environment based on lightweight neural networks oriented to refined community governance. Firstly, combined with the theory of human settlement environment science, an indicator system for community human settlement environment monitoring covering four dimensions of ecology, facilities, safety and humanity is established. Secondly, the lightweight neural network backbone network is optimized and improved, an attention mechanism and a multi-scale feature fusion module are embedded, and multi-task parallel monitoring branches are designed to realize real-time perception and dynamic analysis of multiple elements of the community environment. Finally, comparative experiments and empirical verification are carried out based on real community scene datasets. The results show that the parameter quantity of the lightweight monitoring model constructed in this paper is only 18.6% of that of the traditional convolutional neural network, and the inference speed is increased by 62.3%. On the premise of ensuring monitoring accuracy, the model is suitable for edge terminal deployment, can accurately capture temporal and spatial dynamic changes of the community human settlement environment, and provides technical support for intelligent and refined governance of the community human settlement environment.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
S. Li, “An AI-Enabled Multi-Stakeholder Participation Model and Decision Support System for Urban Community Environmental Governance,” J. Eng. Proj. Prod. Manage., 2026, DOI: 10.32738/JEPPM-2026-152.
C. Li, “Application of Digital Twin Technology in Urban Environmental Governance,” Procedia Comput. Sci., vol. 282, pp. 1519–1527, 2026, DOI: 10.1016/J.PROCS.2026.05.191.
Y. Chen, B. Hu, J. Tang, et al., “Dynamic Monitoring and Ecological Zoning Based on Eco-Environmental Quality and Landscape Ecological Risk in Dexing City, China,” Land Degrad. Dev., vol. 37, no. 8, pp. 3272–3289, 2025, DOI: 10.1002/LDR.70310.
X. Meng and S. Xiong, “Optimization and Implementation of a Lightweight Neural Network Architectures for Edge Computing,” J. Electron. Res. Appl., vol. 10, no. 4, pp. 132–138, 2026, DOI: 10.26689/JERA.V10I4.14905.
M. V. Fridous, A. Agar, B. K. Bhaskar, et al., “Optimization and Benchmarking of Lightweight Neural Networks for Efficient Embedded AI Deployment,” Eng. Rep., vol. 8, no. 5, p. e70814, 2026, DOI: 10.1002/ENG2.70814.
J. S. Walton, M. El-Haram, N. H. Castillo, et al., “Integrated assessment of urban sustainability,” Proc. Inst. Civ. Eng. Eng. Sustain., vol. 158, no. ES2, pp. 57–65, 2005, DOI: 10.1680/ensu.2005.158.2.57.
M. Bonnes, D. Uzzell, G. Carrus, et al., “Inhabitants’ and Experts’ Assessments of Environmental Quality for Urban Sustainability,” J. Soc. Issues, vol. 63, no. 1, 2010, DOI: 10.1111/j.1540-4560.2007.00496.x.
R. Guo, Y. Chen, Z. Wang, et al., “Design of Low-Carbon Community Based on the Science of Human Settlements,” J. Adv. Integr. Landsc. City Des., vol. 2020, p. 521, 2020, DOI: 10.69368/JAILCD.20200111.
S. Wang and H. Gong, “Research on the path of urban living environment quality evaluation from the perspective of high-quality development,” J. Inner Mongolia Univ. Finance Econ., vol. 24, no. 1, pp. 84–92, 2026, DOI: 10.13895/j.cnki.jimufe.2026.01.003.
U. Kulkarni, S. M. Meena, S. V. Gurlahosur, et al., “Quantization Friendly MobileNet (QF-MobileNet) Architecture for Vision Based Applications on Embedded Platforms,” Neural Netw., vol. 136, pp. 28–39, 2021, DOI: 10.1016/j.neunet.2020.12.022.
G. Yu, X. Zuo, X. Wang, et al., “ASPCCNet: A Lightweight Pavement Crack Classification Network Based on Augmented ShuffleNet,” Symmetry, vol. 17, no. 12, p. 2095, 2025, DOI: 10.3390/SYM17122095.
L. Zhang, N. Zhang, R. Shi, et al., “SG-Det: Shuffle-GhostNet-Based Detector for Real-Time Maritime Object Detection in UAV Images,” Remote Sens., vol. 15, no. 13, p. 3365, 2023, DOI: 10.3390/rs15133365.
A. Garcia, Y. Saez, I. Harris, et al., “Advancements in air quality monitoring: a systematic review of IoT-based air quality monitoring and AI technologies,” Artif. Intell. Rev., vol. 58, no. 9, pp. 275–275, 2025, DOI: 10.1007/S10462-025-11277-9.
W. Liu, Y. Li, S. Zhang, et al., “Towards smart city supervision: A detection pipeline for illegal buildings,” Eng. Appl. Artif. Intell., vol. 163, p. 113052, 2026, DOI: 10.1016/J.ENGAPPAI.2025.113052.
Y. Zhang, J. Dai, Z. Panfeng, et al., “Pavement distress detection using multimodal image fusion and enhanced convolutional neural network in complex scenarios,” Eng. Appl. Artif. Intell., vol. 179, p. 115292, 2026, DOI: 10.1016/J.ENGAPPAI.2026.115292.
M. Piponidis and T. Theocharides, “Dynamic convolutional neural networks for altitude aware UAV object detection,” Sci. Rep., 2026, DOI: 10.1038/S41598-026-58335-Y.