Dursun Zafer Şeker

A Framework for Enhancing Real-Time Social Media Data to Improve the Disaster Management Process

Social Media datasets are playing a vital role providing information that can support decision-making in nearly all domains. This is due to the fact that social media is a quick and economical approach for collecting data. It has already been proved that in case of disaster (natural or man-made) the information extracted from Social Media sites is very critical to Disaster Management Systems for response and reconstruction. This study comprises of two parts: The first proposes a framework that provides updated and filtered real time input data for the disaster management system through social media, and the second consists of a designed web user API for a structured and defined real time data input process. The aim of this study is to propose a framework that can filter and organize data from the unstructured social media sources through recognized methods and bring this retrieved data to the same level as that acquired through structured and predefined mechanisms, such as a web API. Both components are designed such that they can potentially collaborate and produce updated information for a disaster management system to carry out accurate and effective decision-making.

The Role of Spatial Data in Building Information Modelling

Bilgi teknolojilerindeki gelismeler insaat sektorunu hizli sekilde degistirmekte, ulastirma altyapilarinin, binalarin planlama, tasarim, insa ve yonetimini, kisaca yasam dongusunu farklilastirmaktadir. Bu yeni yaklasim, insaat projesi yasam dongusu boyunca karar almaya destek olmakta ve performansin onemli olcude artirilmasini saglamaktadir. Cok disiplinli olarak gerceklestirilen insaat projesi yasam dongusunun geregi farkli kaynaklardan gelen veri, yontem ve is modellerinin butunlestirilmesi gerekmektedir. Planlama asamasinda hazirlanan cizimlerin iki boyutlu olmasi, yapinin son halini gosteren uc boyutlu cizimlerin bulunmamasi, yapilarda zaman icerisinde yasanan degisimlerin tespit edilememesi, yapi elemanlarina ait ozniteliklerin dijital ortamda tutulmamasi gibi sorunlar maliyetleri arttirmaktadir. Bu kapsamda yaklasik 25 yillik bir tarihi bulunan ve Yapi Bilgi Modellemesi (YBM) olarak adlandirilan teknoloji, gunumuzde oldukca etkin olarak kullanilmakta olup pek cok ulkede kanun ve yonetmeliklerle belirlenerek zorunlu olarak uygulanmasi gereken standart haline donusmustur. Ulkemizde henuz kullanilmaya baslanan YBM modellerinin temeli uc boyutlu mekansal veri modelleridir. Bu calisma kapsaminda mekansal verilerin YBM’deki rolunu degerlendirmek uzere secilen ornek yapi icin bir YBM modeli olusturulmustur. Secilen yapinin guncel uc boyutlu bina modelinin uretilmesi icin yersel tarayicilar kullanilarak uc boyutlu nokta verileri elde edilmis, yapi modellenmis ve daha once 2006 yilinda olcme yontemleri ile elde edilen iki boyutlu modeller yine YBM ile modellenerek karsilastirilmistir. Gelistirilen yazilim ile yillar icinde yapida olusan farklar otomatik olarak belirlenmistir. Calisma kapsaminda elde edilen sonuclar, karsilasilan problemler ve cozum onerileri sunulmaktadir.

Dimension reduction methods applied to coastline extraction on hyperspectral imagery

Abstract In this study, dimensionality reduction (DR) methods on a hyperspectral dataset to explore the influence on the process of extraction of coastlines were examined and performance of different DR algorithms on the detection of coastline in Bosphorus, Istanbul was investigated. Among these methods, principal component (PC) analysis, maximum noise fraction and independent component (IC) analysis were used in the experiments with the aim of comparing. The study was carried out using these well-known DR techniques on a real hyperspectral image, an Hyperion data set with 161 bands, in the course of the experiments. Three different classifiers (i.e. ML, SVM and neural network) were used for the classification of dimensionally reduced and original images to detect coastline in the region. The DR results were evaluated quantitatively and visually in order to determine the reduced dimensions of the image subsets. Findings show that there is no significant influence of using DR methods on the dataset on the detection of coastline.