آمار
| تعداد نشریات | 29 |
| تعداد شماره‌ها | 431 |
| تعداد مقالات | 4,216 |
| تعداد مشاهده مقاله | 6,796,768 |
| تعداد دریافت فایل اصل مقاله | 5,043,844 |
ارائۀ مدل پیش‌بینی کنندۀ آسیب‌پذیری کالبدی محلات در برابر زلزله با استفاده از یادگیری ماشین (مطالعه‌ی موردی: منطقۀ 1 شهرداری تهران) | ||
| مطالعات ساختار و کارکرد شهری | ||
| مقاله 8، دوره 10، شماره 37، آذر 1402، صفحه 195-226 اصل مقاله (1.14 M) | ||
| نوع مقاله: مقالات مستقل پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22080/usfs.2023.25302.2350 | ||
| نویسندگان | ||
| مریم محمدی* 1؛ مرجان وثوقی نیا2 | ||
| 1دانشیار گروه طراحی شهری، دانشکده معماری و شهرسازی دانشگاه هنر، تهران، ایران. | ||
| 2گروه طراحی شهری، دانشکدۀ معماری و شهرسازی، دانشگاه هنر، تهران، ایران | ||
| تاریخ دریافت: 05 اردیبهشت 1402، تاریخ بازنگری: 05 شهریور 1402، تاریخ پذیرش: 09 مهر 1402 | ||
| چکیده | ||
| مدیریت بحران هوشمند (در سه مرحلۀ قبل، حین و پس‌ازآن)، با تأکید بر آمادگی و پیش‌بینی آسیب‌پذیری در برابر زلزله، امکان پیش‌بینی، کاهش آسیب‌پذیری و افزایش قدرت در تصمیم-سازی را فراهم می‌آورد. این مقاله بر آن است تا با استفاده از یادگیری ماشین، به ارائۀ مدل پیش-بینی‌کنندۀ آسیب‌پذیری کالبدی در برابر زلزله بپردازد. روش پژوهش کمی است. دادههای ارائه‌شده به ماشین برای آموزش و تست، مربوط به پهنه‌های محلات منطقۀ 1 شهرداری تهران بوده‌اند (که در محدودۀ خطر گسل شمال تهران قرار دارند). ویژگی‌های مورد تأکید که ماشین براساس آنها آموزش دیده تا مدل پیش‌بینی‌کننده را ارائه دهد، مشتمل بر موارد زیر هستند: ویژگی‌های الگوی قطعات و ساختار ابنیه، الگوی معبر، کاربری اراضی و موقعیت نسبت به گسل اصلی و فرعی بوده‌اند. مجموعۀ داده‌ها مشتمل بر 1997 سطر و 26 ستون بوده است. برخی از داده‌ها از جی.آی.اس. منطقه استخراج و بخش دیگری از داده‌ها از تحلیل نقشۀ پهنه‌ها به دست آمد. با توجه به بهره‌گیری از رویکرد یادگیری ماشین نظارت‌شده، برچسب‌گذاری توسط محققان در پنج طیف انجام شد. برای آموزش ماشین از الگوریتم درخت تصمیم، ماشین بردار پشتیبان و شبکۀ عصبی چندلایه استفاده شد. حجم دادههای آموزش به تست 70 به 30 در نظر گرفته شد. با بررسی دقت مدل توسط ماتریس درهم‌آمیختگی، مشخص شد که الگوریتم درخت تصمیم با دقت 99.50، حساسیت 99.42 و خطای 0.5 دارای عملکرد بهتری نسبت به دو الگوریتم دیگر است. شبکۀ عصبی نیز با دقت 97.85، حساسیت 97.57 و خطای 2.15، دارای عملکرد مناسبی است. بررسی میزان اعتمادپذیری مدل پیش‌بینی کننده با دادههای مربوط به محلۀ جوانمرد قصاب در منطقۀ 20 نیز نشان داد که ماشین آموزش‌دیده، با دقت بالای 97 درصد قابلیت پیش‌بینی پذیری دارد. بدین‌ترتیب ماشین آموزش‌دیده با دقت و سرعت بالا می‌تواند به پیش‌بینی میزان آسیب‌پذیری بافت‌های کالبدی در برابر زلزله بپردازد. | ||
| کلیدواژه‌ها | ||
| مدل پیش‌بینی کننده؛ آسیب پذیری؛ یادگیری ماشین؛ مورفولوژی؛ زلزله | ||
| عنوان مقاله [English] | ||
| Presenting a Predictive Model of the Physical Vulnerability of Neighborhoods against Earthquakes (Case Study: District 1 of Tehran Municipality) | ||
| نویسندگان [English] | ||
| Maryam Mohammadi1؛ Marjan Voosooghi Nia2 | ||
| 1Associate Professor, Department of Urban Design, Faculty of Urban Planning and Architecture, University of Art, Iran | ||
| 2M.A. in Urban Design, Department of Urban Design, Faculty of Urban Planning and Architecture, University of Art, Iran | ||
| چکیده [English] | ||
| The issue of the physical vulnerability of neighborhoods against earthquakes is the subject of this research. Crisis management and smart crisis management are generally considered in three stages: before, during, and after the crisis. The management of a smart crisis in all three stages, with emphasis on preparedness and anticipation of vulnerability against disasters such as earthquakes, can provide a way to predict vulnerability and increase power in decision-making. The purpose of this research is to present a predictive model for the vulnerability of the physical context against earthquakes in District 1 of Tehran municipality using machine learning. The research method is analytical and quantitative. Some of the data was collected from GIS and some were extracted from the map analysis. According to the use of a supervised learning approach in this research, labeling was performed by researchers in five different spectrums. Decision tree algorithm, support vector machine (SVM), and multilayer neural network (MLP) were used as machine learning algorithms. The portion of training data for the test was considered to be 70 to 30. By examining the accuracy of the model by the confusion matrix, it was found that the decision tree algorithm with an accuracy of 99.50, sensitivity of 99.42, and error of 0.5 has better performance than the other two algorithms. Moreover, the neural network with an accuracy of 97.85, sensitivity of 97.57, and error of 2.15 showed better performance than support vector machine. | ||
| کلیدواژه‌ها [English] | ||
| Predictive model, Vulnerability, Machine learning, Morphology, Earthquake | ||
| مراجع | ||
|
Ahmadi, M. et al. (2018). Data Mining with RapidMiner: Data Access, Combination and Cleansing. Qom: Elham Noor Publication. [in Persian]
Akerkar, R. (2018). Processing Big Data for Emergency Management. (Eds. Zhi Liu & Kaoru Ota) Smart Technologies for Emergency Response and Disaster Management. USA: IGI Publication.
Alazawi, Z. et al. (2014). A Smart Disaster Management System for Future Cities. In Proceedings of the 2014 ACM International Workshop on Wireless and Mobile Technologies for Smart Cities (pp. 1-10).
Alizadeh, M. et al., (2018). A Hybrid Analytic Network Process and Artificial Neural Network (ANP-ANN) Model for Urban Earthquake Vulnerability Assessment. Remote Sens, 10(6), 975, 1-34.
Avvenuti, M. et al., (2014). EARS (Earthquake Alert and Report System): a Real Time Decision Support System for Earthquake Crisis Management, Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1749-1758. https://doi.org/10.1145/2623330.2623358.
Baft Shahr Consulting Engineers. (2007). Preparation of Development Model and Detailed Plan of District 1 of Tehran Municipality. [in Persian]
Bagheri N., Motamedi M. & Mafi E. (2022). Assessing the resilience of Shirvan city in the face of earthquakes. Journal of Applied researches in Geographical Sciences, 22 (64), 329-347. [in Persian]
Benaben, F. et al., (2017). A Conceptual Framework and a Suite of Tools to Support Crisis Management. Proceedings of the 50th Hawaii International Conference on System Sciences, 237-246.
Carmona, M., Tiesdell, S. Heath, T. & Oc, T. (2012). Public Places Urban Spaces, The Dimensions of Urban Design. Routledge, Taylor & Francis Group.
Chambelland, J.C., et al., (2011). SIMFOR: Towards a Collaborative Software Platform for Urban Crisis Management. MCSIS CGVCVIP.
Ebrahimzaeh, I., Kashefi, D., & Hosseini, S. A. (2015). Evaluating the Vulnerability of Urban Regions Against Earthquake, Case Study: the City of Piranshahr. Saptial Planning, 5(1), 1-26. [in Persian]
Eliasian, I. (2021). Artificial Intelligence and Machine Learning. Tehran: Ketab-e Sabz Publication. [in Persian]
Faraji, A. & Qarakhlo, M. (2009). Earthquake and Urban Crisis Management (Case Study: Babol City). Journal of Geography. 8(25), 143-164. [in Persian]
Farzadenia, A. and Monsefi, D. (2018). The Impact of Smart Cities on Crisis Management, Case Study: Japan. Conference on Civil Engineering, Architecture and Urban Planning of the Islamic world. Azerbaijan-e Sharghi: Tabriz University. [in Persian]
Golrokh, S. (2012). Rethinking Fabric ‘Deterioration’ Based on Place Deterioration. Soffeh, 2(2), 79-94. [in Persian]
Habibi, Q. et al., (2013). Developing a Model to Assess Seismic Instability against Earthquake using Fuzzy & IHPW and GIS. Scientifc Quartely Journal of Geosciences, 22(87), 83-92. [in Persian]
Hayati, S. et al., (2017). Predicting the Location of a Possible Earthquake in Khorasan Razavi Province by Using Artificial Neural Network. Journal of Geography and Environmental Hazards, 5(20), 1-19. [in Persian]
Hosseini, A. & Omidari, F. (2017). Analyzing the Role of Urban Design in the Crisis Management Cycle. Memarishenasi, 1(2), 1-8. [in Persian]
Hosseini, R. (2015). Establishing Indices of Underground Space Development in Terms of Urban Crisis Management Criteria. Bagh-e Nazar, 12(35), 53-64. [in Persian]
Hosseinpour, A., Shamshirband, M. & Tavakoli, A. (2009). Investigating the Process of Reducing Urban Open Spaces in the Process of Urban Development with an Emphasis on Crisis Management, a Case Study of Tehran Metropolis. Geography, (5), 141-154. [in Persian]
Ibrahim, I., Abdullah, A., Ibrahim, M. & Farhana, F. (2018). Historical Urban Form: A Case Study of Melaka. Journal of the Malaysian Institute of Planners, 16(2), 153-163.
Jung, D. et al., (2020). Conceptual Framework of an Intelligent Decision Support System for Smart City Disaster Management, Applied Sciences, 10(2) (666), 1-13. https://doi.org/10.3390/app10020666
Karimi, S. & Nasr, A. R. (2013).The Methods of Analyzing Interview Data. Ayar-e Pajohesh Dar Oloom-e Ensani, 4(1), 71-94.[in Persian]
Lee, S. et al., (2019). SEVUCAS: A Novel GIS-Based Machine Learning Software for Seismic Vulnerability Assessment. Applied Science, 9 (3495), 1-21.
Linardos.V., et al., (2022) Machine Learning in Disaster Management: Recent Developments in Methods and Applications. Machine Learning and Knowledge Extraction, 4(2), 446-473. https://doi.org/10.3390/make4020020.
Liu. Y. et al., (2019). Seismic Vulnerability Assessment at Urban Scale Using Data Mining and GIS Science Technology: Application to Urumqi (China). Geomatics, Natural Hazards and Risk, 10(1), 958-985. https://doi.org/10.1080/19475705.2018.1524400.
Mohammad Shafiei, M. R. & Mohammad Shafiei, A. H. (2014). Crisis and its Management Solutions. The Second International Research Conference in Science and Technology, Sarmad Hamyesh Karin Institute, March 24. [in Persian]
Mohemed, A.S., Harun, N.Z. & Abdullah, A. (2018). Urban Morphological Analysis Framework for Conservation Planning and Management. Journal of the Malaysian Institute of Planners. 16(1), 360-371.
Nadeem, M., et al. (2021). Scaling the Potential of Compact City Development: The Case of Lahore, Pakistan. Sustainability, 13 (5257), 1-22.
Nazemi, E. (2016). Examining Concepts and Theoretical Foundations of Worn Texture [website]. Retrieved on 30 May 2022, https://research.iaun.ac.ir/pd/nazemi/pdfs/UploadFile_8326.pdf [in Persian]
Nazmfar, H. & Alavi, S. (2019). Evaluating the vulnerability of urban buildings to various earthquake intensities Case study: District 9 of Tehran Municipality. Scientific-Research Quarterly of Geographical Data (SEPEHR), 27(108), 165-181. [in Persian]
Piper, W. (2018). Crisis Management Under the Control of New Technologies. Spectrum Analysis Scientific Group [website]. Retrieved on 21 May 2021, from https://teyf.ir/wp-content/uploads/2019/10/whitepaper_01.pdf [in Persian]
Pishgahi Fard, Z. et al. (2010). GIS Geographic Information System and Its Role in Locating Risky Urban Areas for Use in Crisis Management (Case Study: District 8 of Tabriz Municipality). Geographical Quarterly Journal of Environmental Based Territorial Planning, 4(13), 91-104. [in Persian]
Qadir, J. et al., (2016). Crisis Analytics: Big Data Driven Crisis Response. Journal of International Humanitarian Action, 1(1), 1-8.
Qanawati, E., Qalami, S. & Abdoli, A. (2008). Empowering Urban Crisis Management to Reduce Natural Disasters (Earthquake), Case Study: Khorramabad City. Journal of Natural Geography, 4, 15-24. [in Persian]
Sahoh, B. & Choksuriwong, A. (2017). Smart Emergency Management Based on Social Big Data Analytics: Research Trends and Future Directions. Proceedings of the 2017 International Conference on Information Technology, December, 1-6.
Salvatian, S. & Mehraban, F. (2016). Role of Social Media in Disaster Management of possible Earthquake in Tehran. Disaster Prevntion and Management Knowledge. 6 (1), 9-22. [in Persian]
Sanieizadeh, M., Mahmoudi, S. & Taher Parvar, M. (2012). Applied Data Mining. Tehran: Niaze-Danesh. [in Persian]
Shahi, S.A., Hameed, S. & Draheim, D. (2019). The Rising Role of Big Data Analytics and IoT in Disaster Management: Recent Advances, Taxonomy and Prospects. IEEE Journal, 7, 24595-45614. https://10.1109/ACCESS.2019.2913340
Sinafar, A. Partovi, P. & Shokouhi, M. (2015). Investigating the Role of Permeability in Promotion of Quality of Environment of Neighborhood Unit (Case Study: Tehran-Narmak). Hoviatshahr, 9(21), 91-100. [in Persian]
Stangl, P. (2018). Prospects for Urban Morphology in Resilience Assessment. (Eds.) In Lecture Notes in Energy, (PP. 181-193).
Taghvaei, M., Jozi Khamselouei (2012). Management and Planning of Crisis in Urban Spaces with Passive Defense Approach and SWOT Model. Case Study: Marching Routes of Isfahan City. Geographical Planning of Space Quarterly Journal, 2(6), 57-74. [in Persian]
Talebpour, A. & Mojaheddini, M. (2019). The Role of Integrated Urban Management in Improving Crisis Management and Improving the Quality of Public Services to Citizens (Case Study: Tehran Province). Socio-Cultural Development Studies, 7(4), 67-92. [in Persian]
Vazan, M. (2021). Machine Learning and Data Science: Fundamentals, Concepts, Algorithms and Tools. Tehran: Miaad-e Andisheh. [in Persian]
Yarahmadi, M., Nikpour, A. & Lotfi, S. (2020). Evaluating the physical resilience of cities against earthquakes: A case study of Noorabad Mamassani. The Journal of Geographical Research on Desert Areas, 7(2), 147-171. [in Persian]
Yariyan, P. et al., (2020). Earthquake Vulnerability Mapping Using Different Hybrid Models. Symmetry Journal, 12(3), 405. https://doi.org/10.3390/sym12030405.
Yu, M., Yang, C.H. & Li. Y. (2018). Big Data in Natural Disaster Management: A Review. Geosciences Journal, 8(5), 1-26. https://doi.org/10.3390/geosciences8050165.
Zare, M. (2015). The Faults of Tehran, Crisis Management and Earthquake Risk in Tehran [website]. Retrieved on August 1, 2022, from http://iranethics.ir/files/site1/files/khordad95.pdf [in Persian]
| ||
|
آمار تعداد مشاهده مقاله: 114 تعداد دریافت فایل اصل مقاله: 92 |
||