Ebru Akçapınar Sezer

ORCID: 0000-0002-9287-2679
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Landslides and related hazards
  • Advanced Text Analysis Techniques
  • Sentiment Analysis and Opinion Mining
  • Software Engineering Research
  • Software Reliability and Analysis Research
  • Topic Modeling
  • Text and Document Classification Technologies
  • Spam and Phishing Detection
  • Flood Risk Assessment and Management
  • Natural Language Processing Techniques
  • Geotechnical Engineering and Analysis
  • Software System Performance and Reliability
  • Mineral Processing and Grinding
  • Web Data Mining and Analysis
  • Fuzzy Logic and Control Systems
  • Drilling and Well Engineering
  • Video Surveillance and Tracking Methods
  • Rock Mechanics and Modeling
  • Neural Networks and Applications
  • Authorship Attribution and Profiling
  • Tunneling and Rock Mechanics
  • Imbalanced Data Classification Techniques
  • Tree Root and Stability Studies
  • Educational Methods and Analysis
  • Fire effects on ecosystems

Hacettepe University
2015-2024

Scientific and Technological Research Council of Turkey
2016

Bilkent University
1991-2004

This paper presents the results of neuro-fuzzy model using remote-sensing data and geographic information system for landslide susceptibility analysis in a part Cameron Highlands areas Malaysia. Landslide locations study area were identified by interpreting aerial photographs satellite images, supported extensive field surveys. Landsat TM imagery was used to map vegetation index. Maps topography, lineaments, Normalized Difference Vegetation Index (NDVI), land cover constructed from spatial...

10.1109/tgrs.2010.2050328 article EN IEEE Transactions on Geoscience and Remote Sensing 2010-07-08

The main purpose of the present study is to investigate possible application decision tree in landslide susceptibility assessment. area having a surface 174.8 km 2 locates at northern coast Sea Marmara and western part Istanbul metropolitan area. When applying data mining extracting tree, geological formations, altitude, slope, plan curvature, profile heat load stream power index parameters are taken into consideration as conditioning factors. Using predicted values, map produced. AUC value...

10.1155/2010/901095 article EN cc-by Mathematical Problems in Engineering 2010-01-01

SUMMARY Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, analytical approaches. Because that, some prediction techniques, like artificial neural networks (ANN) nonlinear regression can utilized to solve those problems. The purpose this study is examine the effects cycling integer slake durability index test on intact behavior estimate...

10.1002/nag.1066 article EN International Journal for Numerical and Analytical Methods in Geomechanics 2011-07-08

Natural hazards have a great number of influencing factors. Machine-learning approaches been employed to understand the individual and joint relations these However, it is challenging process for machine learning algorithm learn large parameter space. In this circumstance, success model highly dependent on applied reduction procedure. As state-of-the-art neural network model, representative assumes full responsibility from feature extraction prediction. study, technique, recurrent (RNN), was...

10.3390/ijgi8120578 article EN cc-by ISPRS International Journal of Geo-Information 2019-12-11

Fluctuations and unpredictability in food demand generally cause problems economic point of view public courts. In this study, to overcome problem predict actual consumption for a specified menu selected date, three decision tree methods (CART, CHAID Microsoft Decision Trees) are utilized. A two year period dataset which is gathered from courts Hacettepe University Turkey used during the analyses. As result, prediction accuracies up 0.83 R2 achieved. By it's shown that methodology suitable...

10.1016/j.procs.2010.12.125 article EN Procedia Computer Science 2011-01-01
Coming Soon ...