پديد آورندگان :
بهرامي، ناهيد دانشگاه تهران - دانشكده جغرافيا , ارگاني، ميثم دانشگاه تهران - دانشكده جغرافيا , نيساني ساماني، نجمه دانشگاه تهران - دانشكده جغرافيا , وفائي نژاد، عليرضا دانشگاه شهيد بهشتي - دانشكده مهندسي عمران، آب و محيط زيست
كليدواژه :
سيستم توصيه‌گر , بافت آگاهي , بهينه سازي , امداد و نجات , الگوريتم كلوني مورچگان , زمين لرزه
چكيده فارسي :
بافت آگاهي منجر به شناخت بهتر محيط و اشيا و عوامل، و نحوه ارتباط و تعاملات بين آنها ميباشد. در نتيجه ميتواند تاثير به سزايي در ارائه راهكارهاي مناسب در حل مسائل جهان واقعي داشته باشد. از اين رو ميتوان در فرآيند امداد و نجات در بحرانها، نيز بافت آگاهي را وارد نمود و در راستاي بهبود و تطابق پذيري بيشتر راهكارها با محيط واقعي، گام برداشت. در ميان بحرانها و بلاياي طبيعي، زمينلرزه به دليل وجود گسلهاي لرزهخيز و فعال در ايران و بسياري از كشورها، يكي از بحرانهاي اساسي ميباشد. با توجه به اهميت شناسايي بافتها در واقعي و قابل اجرايي شدن پژوهشها، در اين پژوهش بافتهاي امدادگران، تيمها و محيط به عنوان بافتهاي اصلي در مسئله ي مذكور، بررسي و ارتباط آنها با يكديگر و اولويتهاي فعاليت ها و مكان ها با شناسايي تخصصها و شرايط جسماني و موقعيتي امدادگران مشخص شده است. در نهايت ساختار و راهكاري به كمك الگوريتم كلوني مورچگان و سيستم اطلاعات مكاني جهت بهينهسازي تخصيص امدادگران به محلهاي آسيب ديده و فعاليتهاي لازم در محدودهاي از منطقه 3 شهر تهران، طراحي و اجرا شده است؛ كه استفاده از بافتآگاهي و تركيب آن با الگوريتم هاي هوش مصنوعي جهت موضوع امداد و نجات در بحران زمين لرزه پژوهشي نوين ميباشد. نتايج حاصل شده از اين پژوهش در مقايسه با در نظر نگرفتن بافتهاي موجود در امداد و نجات و بدون استفاده از الگوريتم هاي هوش مصنوعي، بهبود 1/79 برابري راهكار پيشنهادي را نشان مي دهد.
چكيده لاتين :
One of the significant dangers to human life is crises and natural disasters worldwide every year. If such incidents are unpredictable, their risks and casualties will be much higher. Among disasters are floods, hurricanes, volcanoes, earthquakes, tsunamis. An earthquake is an event that is more prevalent than other disasters and is almost unpredictable. Respond structure to crises and disasters is called crisis management which deals with all issues before, during, and after crises and disasters and leads to activities in the field of planning, preparedness, prevention, response, and reconstruction.
One of the most basic and essential things that can reduce the casualties of various events is disaster relief and rescue, which respond to the crisis management structure. Also, the contextual information of the environment, rescuers, and activities created a context-aware recommending system that can facilitate the process of interaction with the environment. This study has checked the types of contexts, their relationship, and the structure of earthquake rescue in Iran, where there is a significant crisis due to geographical location and seismicity.
The whole problem space consists of three parts to provide a meaningful definition of the concept of "context" in the deployment of relief and rescue teams. The rescuer is the main context. Relief and rescue team as the object's environment, which includes team information of rescuers, consists of team members' position, distance, physical condition, and activity compared to other rescuers in the group. The physical environment is a collection of injured people, buildings, and relief and rescue teams in a specific area.
Contexts of rescuers and their relationships, teams, and the hypothetical earthquake were studied by studying related articles and books and interviewing experts in the field of research. The study of context-aware and optimization methods used for the actual structure of rescue teams are the innovations of this study. Contexts during relief and rescue include location, time, the extent of human and building injuries, rescuers' interactions with and with the environment, and activities, rescuers' specialties, and priorities. Interaction is necessary for optimal management of relief and rescue. To create a relationship between the various contexts and optimize the relief and rescue process by defining the mathematical function and using sensed information from contexts into the proposed optimized algorithm.
Finally, the solution has been designed and implemented with an ant colony algorithm and geospatial information system to optimize the allocation of rescuers to the affected areas and the necessary activities in the part of Tehran. The use of combination context-aware and artificial intelligence algorithms for the subject of relief and rescue in earthquake crisis is new research that Led to a 1.79-fold improvement of the proposed solution compared to not considering the existing contexts in relief and rescue without using artificial intelligence algorithms.
So can be created a context-aware system based on the appropriate optimization algorithm as a suitable solution to the problem of post-earthquake relief and rescue. Due to the context structure in this research in the individual's activity effectiveness on other individuals and groups, the ant colony algorithm is a collective intelligence base that can provide optimal positioning in a discrete environment. It allows more repetition in less time than other algorithms.
