OPTIMIZED MODEL FOR PREDICTING THE AVAILABILITY OF OBJECTS BASED ON DEEP LEARNING AND GEOSPATIAL FEATURES
DOI:
https://doi.org/10.15588/1607-3274-2025-4-14Keywords:
deep learning, forecasting, object availability, geospatial data, RNN optimization, intelligent systemsAbstract
Context. Today, predicting the availability of objects in spatially distributed systems remains one of the areas of computer science that constantly attracts the attention of researchers. There are many reasons for this. There is an increase in the amount of spatial information. New types of infrastructure networks are emerging, as well as the need for rapid decision-making in changing conditions. At the same time, traditional analysis methods do not always cope with the tasks of processing multidimensional data. This is especially true when it comes to complex or unstable environments. This opens up opportunities for applying deep learning methods that demonstrate high efficiency where classical approaches fail.
Objective. The study aims to optimize the model for predicting the availability of objects in spatially distributed systems by defining an efficient deep learning architecture that uses spatial and other infrastructure features to improve prediction accuracy and generalizability.
Method. To achieve this goal, deep learning architectures were used, including feed-forward models (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN, GRU, LSTM). During the modeling, methods of data normalization, training regularization, and a comprehensive system for evaluating the accuracy of forecasts using the mean square error, mean absolute error, and coefficient of determination were used.
Results. An optimized architecture of a recurrent neural network was built for the study, which includes a combination of two recurrent layers, Dropout regularization layers, and a fully connected layer. The analysis has shown that the proposed model provides high accuracy in predicting the availability of objects, demonstrating stability over a wide range of spatial data. Comparison of actual and predicted values confirmed the effectiveness of the proposed solution.
Conclusions. The proposed approach to building an optimized deep learning model for predicting the availability of objects provides a high level of generalization and accuracy, which creates prerequisites for its use in systems of intelligent decision support in spatially distributed environments.
References
Siriwardena A.N., Patel G., Botan V., Rowan E., Spaight R. Community First Responders’ role in the current and future rural health and care workforce: a mixed-methods study, Health and Social Care Delivery Research, 2024, Vol. 12(18), pp. 1–101. Mode of access:
https://doi.org/10.3310/JYRT8674.
Ratushny R., Horodetskyy I., Molchak Y., Grabovets V. The configurations coordination of the projects products of development of the community fire extinguishing systems with the project environment, CEUR Workshop Proceedings, 2021, Vol. 2851, pp. 238–248, Mode of access: http://ceur-ws.org/Vol-2851/paper22.pdf.
Hou C., Wu H. Rescuer, decision maker, and breadwinner: Women’s predominant leadership across the post-Wenchuan earthquake efforts in rural areas, Sichuan, China. Safety Science, 2020, Vol. 125, 104623, Mode of access: https://doi.org/10.1016/j.ssci.2020.104623.
Sarmadi K., Amiri-Aref M. A distributionally robust optimisation with joint chance constraints approach for location-routing problem in urban search and rescue operations. Computers and Operations Research, 2025, Vol. 180, 107051, Mode of access:
https://doi.org/10.1016/j.cor.2025.107051
Tryhuba A., Ratushny R., Tryhuba I., Koval N., Androshchuk I. The model of projects creation of the fire extinguishing systems in community territories. Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, 2020, Vol. 68(2), pp. 419–431, Mode of access: https://doi.org/10.11118/actaun202068020419
Makino H., Hatanaka M., Abe S., Takahashi M., Kinoshita H. Web-GIS-based emergency rescue to track triage information – System configuration and experimental results. 2012 Ubiquitous Positioning, Indoor Navigation, and Location Based Service, UPINLBS 2012, 2012, 6409773, Mode of access: https://doi.org/10.1109/UPINLBS.2012.6409773
Jaljolie R., Dror T., Siriba D.N., Dalyot S. Evaluating current ethical values of OpenStreetMap using value sensitive design, Geo-Spatial Information Science, 2023, Vol. 26(3), pp. 362–378, Mode of access: https://doi.org/10.1080/10095020.2022.2087048
Tryhuba A., Zachko O., Grabovets V., Pavlova I., Rudynets M. Examining the effect of production conditions at territorial logistic systems of milk harvesting on the parameters of a fleet of specialized road tanks, EasternEuropean Journal of Enterprise Technologies, 2018,
Vol. 5(3–95), pp. 59–69, Mode of access: https://doi.org/10.15587/1729-4061.2018.142227
Böckling M., Paulheim H., Detzler S. A Planet Scale Spatial-Temporal Knowledge Graph Based On OpenStreetMap And H3 Grid. CEUR Workshop Proceedings, 2024, Vol. 3743, pp. 60–72, Mode of access: http://ceur-ws.org/Vol-3743/paper6.pdf
Protaziuk G., Piątkowski R., Bembenik R. Modelling OpenStreetMap Data for Determination of the Fastest Route Under Varying Driving Conditions. Studies in Big Data, 2019, Vol. 40, pp. 53–71, Mode of access: https://doi.org/10.1007/978-3-319-77604-0_5
Tryhuba A., Ratushny R., Bashynsky O., Chubyk R., Bordun I. Planning of territorial location of fire-rescue formations in administrative territory development projects, CEUR Workshop Proceedings, 2020, Vol. 2565, pp. 93–105, Mode of access: http://ceur-ws.org/Vol 2565/paper9.pdf
Rani G., Siddiqui N. A., Yadav M., Ansari S. Hierarchical integrated spatial risk assessment model of fire hazard for the core city areas in India. Land Use Policy, 2023, Vol. 126, 106536, Mode of access: https://doi.org/10.1016/j.landusepol.2023.106536
Shahparvari S., Fadaki M., Chhetri P. Spatial accessibility of fire stations for enhancing operational response in Melbourne, Fire Safety Journal, 2020, Vol. 117, 103149, Mode of access: https://doi.org/10.1016/j.firesaf.2020.103149
Mao K., Chen Y., Wu G., Huang J., Yang W., Xia Z. Measuring spatial accessibility of urban fire services using historical fire incidents in Nanjing, China, ISPRS International Journal of Geo-Information, 2020, Vol. 9(10), 585, Mode of access: https://doi.org/10.3390/ijgi9100585
Tao Z., Cheng Y., Liu J. Hierarchical two-step floating catchment area (2SFCA) method: Measuring the spatial accessibility to hierarchical healthcare facilities in Shenzhen, China, International Journal for Equity in Health, 2020, Vol. 19(1), 164, Mode of access:
https://doi.org/10.1186/s12939-020-01280-7
Tryhuba A., Tryhuba I., Ftoma O., Boyarchuk O. Method of quantitative evaluation of the risk of benefits for investors of fodder-producing cooperatives, International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2019, Vol. 3, pp. 55–58, Mode of access: https://doi.org/10.1109/STC-CSIT.2019.8929788
Koval N., Kondysiuk I., Grabovets V., Onyshchuk V. Forecasting the fund of time for performance of works in hybrid projects using machine training technologies. CEUR Workshop Proceedings, 2021, Vol. 2917, pp. 196–206, Mode of access: http://ceur-ws.org/Vol-2917/paper18.pdf
Xu Y., Zhou C., Hu B. Measuring the accessibility of emergency shelters based on an improved two-step floating catchment area model, International Journal of Digital Earth, 2025, Vol. 18(1), Mode of access: https://doi.org/10.1080/17538947.2025.2479864
Chen Z., Tang L., Guo X., Zheng G. A self-supervised detection method for mixed urban functions based on trajectory temporal image. Computers, Environment and Urban Systems, 2024, Vol. 110, 102113, Mode of access: https://doi.org/10.1016/j.compenvurbsys.2024.102113
Chen H., Lan C., Song J., Xia J., Yokoya N. ObjFormer: Learning land-cover changes from paired OSM data and optical high-resolution imagery via object-guided transformer, IEEE Transactions on Geoscience and Remote Sensing, 2024, Vol. 62, 4408522, Mode of access:
https://doi.org/10.1109/TGRS.2024.3410389
Liu Z. Identifying urban land use social functional units: a case study using OSM data, International Journal of Digital Earth, 2021, Vol. 14(12), pp. 1798–1817, Mode of access: https://doi.org/10.1080/17538947.2021.1988161
Tryhuba A., Hutsol T., Tryhuba I., Tabor S., Kwasniewski D. Risk assessment of investments in projects of production of raw materials for bioethanol, Processes, 2020, Vol. 9(1), pp. 1–12. Mode of access: https://doi.org/10.3390/pr9010012
Jayapriya J., Vinay M. Deep learning algorithms comparison for multiple biological sequences alignment. Lecture Notes in Networks and Systems, 2023, Vol. 720, P. 563–575, Mode of access: https://doi.org/10.1007/978-981-99-3761-5_50
Chen D. Research on network information security applications based on deep learning algorithms. 2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL), 2024, pp. 1160–1163, Mode of access: https://doi.org/10.1109/CVIDL62147.2024.10603692
Bashynsky O., Hutsol T., Rozkosz A., Prokopova O. Justification of parameters of the energy supply system of agricultural enterprises with using wind power installations, E3S Web of Conferences, 2020, Vol. 154, 06001, Mode of access: https://doi.org/10.1051/e3sconf/202015406001
Hutsol T., Kuboń M., Hohol T., Tomaszewska-Górecka W. Taxonomy and stakeholder risk management in integrated projects of the European Green Deal, Energies, 2022, Vol.15(6), 2015, Mode of access: https://doi.org/10.3390/en15062015
Korstanje J. Machine Learning on Geographical Data Using Python: Introduction into Geodata with Applications and Use Cases. 2022, P. 1–230, Mode of access: https://doi.org/10.1007/978-1-4842-8287-8
Bashynsky O., Garasymchuk I., Vilchinska D., Dubik V. Research of the variable natural potential of the wind and energy in the northern strip of the Ukrainian Carpathians. E3S Web of Conferences, 2020, Vol. 154, 06002, Mode of access: https://doi.org/10.1051/e3sconf/202015406002
Omarkhanova D., Oralbekova Z. Interpretation of georadar data based on machine learning technologies, EUREKA: Physics and Engineering, 2024, (4), pp. 193–204, Mode of access: https://doi.org/10.21303/2461-4262.2024.003289
Araujo A. S., de Queiroz A. P. Spatial Characterization and Mapping of Gated Communities, ISPRS International Journal of Geo-Information, 2018, Vol. 7(7), 248, Mode of access: https://doi.org/10.3390/ijgi7070248
Suchenwirth L., Forster M., Lang F., Kleinschmit B. Estimation and mapping of carbon stocks in riparian forests by using a machine learning approach with multiple geodata. Photogrammetrie, Fernerkundung, Geoinformation, 2013, (4), pp. 333–349, Mode of access:
https://doi.org/10.1127/1432-8364/2013/0181
Tryhuba A., Boyarchuk V., Tryhuba I., Pavlikha N., Kovalchuk N. Study of the impact of the volume of investments in agrarian projects on the risk of their value. CEUR Workshop Proceedings, 2021, Vol. 2851, P. 303–313, Mode of access: https://ceur-ws.org/Vol 2851/paper28.pdf
Tryhuba A., Boyarchuk V., Tryhuba I., Tymochko V., Bondarchuk S. Model of assessment of the risk of investing in the projects of production of biofuel raw materials. International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2020, Vol. 2, P. 151–154, Mode of access: https://doi.org/10.1109/CSIT49958.2020.9322024
Czarnecka K., Kuchcik M., Baranowski J. Spatial development indicators as a tool to determine thermal conditions in an urban environment. Sustainable Cities and Society, 2024, Vol. 100, 105014, Mode of access: https://doi.org/10.1016/j.scs.2023.105014
Nemchinov D.M. The assessment of the required level of road and street network development in localities and conurbations (city agglomeration). 6th Transport Research Arena, April 18–21, 2016, Mode of access: https://doi.org/10.1016/j.trpro.2016.05.135
Yuxin Y., Guangbin W., Yubin M., Haoxuan D. Data augmentation in training deep learning models for malware family classification. Proceedings – International Conference on Machine Learning and Cybernetics, 2021, December, Mode of access:
https://doi.org/10.1109/ICMLC54886.2021.9737271
Ouarab S., Boutteau R., Romeo K., Ragot N., Duval F. Industrial object detection: Leveraging synthetic data for training deep learning models. Lecture Notes in Business Information Processing, 2024, Vol. 507, pp. 200–212, Mode of access: https://doi.org/10.1007/978-3-031-58113-7_17
Park J.-H., Kim Y.-S., Seo H., Cho Y.-J. Analysis of training deep learning models for PCB defect detection. Sensors, 2023, Vol. 23(5), 2766, Mode of access: https://doi.org/10.3390/s23052766
Tryhuba A., Kondysiuk I., Tryhuba I., Boiarchuk O., Tatomyr A. Intellectual information system for formation of portfolio projects of motor transport enterprises. CEUR Workshop Proceedings, 2022, Vol. 3109, pp. 44–52, Mode of access: https://ceur-ws.org/Vol-3109/paper7.pdf
Basyuk T., Vasyliuk A., Lytvyn V., Vlasenko O. Features of designing and implementing an information system for studying and determining the level of foreign language proficiency. Proceedings of the 4th International Workshop on Modern Machine Learning Technologies and Data Science Workshop MoMLeT&DS 2022, 2022, pp. 212–225, Mode of access: https://ceur-ws.org/Vol-3312/paper18.pdf
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 A. M. Tryhuba, R. T. Ratushny, L. S. Koval, A. R. Ratushnyi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
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 CC BY-SA 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) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
