Divit Kadi, Ayse; Gokalp, Ertan; Kadi, Fatih

Unmanned aerial vehicles, one of the technologies that aim to produce data in many scientific studies, has widespread use in many engineering applications, especially in cartography applications. UAV, which can meet the high accuracy required in many studies, offer users the opportunity to produce point cloud and maps for various aims. It is aimed to produce a high-resolution orthophoto map of the study area in this study. In addition, the accuracy of the orthophoto map produced for the areas classified according to topographic structures in the study area has been checked with GNSS measurements, and its compliance with the standards specified in the regulation has been examined. According to the results; Considering the root square mean error values of three axes, it has been searched whether the accuracy values of the products obtained are suitable according to the regulation and it has been determined that these values are within the limits. Then, the application of testing the accuracy of the orthophoto map has been started. When all checkpoints have been examined, the maximum error values in x, y, and h directions have been found to be 5.9, 4.5, and 4.9 cm, respectively.

AtıfScopus1·WoS1·OpenAlex1

İncele

Ay Karakuş, Betül; Talo, Muhammed; Hallaç, İbrahim Rıza; Aydin, Galip

Deep learning has emerged as an effective solution to various text mining problems such as document classification and clustering, document summarization, web mining, and sentiment analysis. In this paper, we describe our work on investigating several deep learning models for a binary sentiment classification problem. We used movie reviews in Turkish from the website www.beyazperde.com to train and test the deep learning models. We also report a detailed comparison of the models in terms of accuracy and time performances. Two major deep learning architectures used in this study are Convolutional Neural Networks and Long Short-Term Memory. We built several variants of these models by changing the number of layers, tuning the hyper-parameters, and combining models. Additionally, word embeddings were created by applying the word2vec algorithm with a skip-gram model on a large dataset (∼ 13 M words) composed of movie reviews. We investigate the effect of using the pre-word embeddings with these models. Experimental results have shown that the use of word embeddings with deep neural networks effectively yields performance improvements in terms of run time and accuracy.

AtıfScopus55·WoS40·OpenAlex64

İncele