Doğu İlmak's repositories
Drone-Detection-YOLOv7
Introducing a curated dataset for drone detection and a state-of-the-art YOLOv7 model, enabling real-time and accurate identification of drones in complex environments.
Drone-Detection-YOLOv8x
This repository provides a dataset and model for real-time drone detection using YOLOv8, contributing to enhanced security and privacy protection. Join us in advancing drone detection technology for safer environments.
Wildfire-Prediction-from-Satellite-Imagery
Building models that can predict whether an area is at risk of a wildfire or not on satellite images.
Classify-Trees-from-Satellite-Imagery
Satellite photographs taken by the Sentinel-2 were classified with pre-trained ResNet-50 and VGG16 models. In addition made CAM model.
Game-Theory
In this project, you will be able to access the games and codes that I made which are shown to us in the Game Theory lecture.
Predict-Heating-and-Cooling-Load
The aim is to use the eight features to predict each of the two responses (heating and cooling loads) with multi-output architecture.
TACO-Trash-Annotations-in-Context-YOLOv7x
TACO: Precise trash detection with YOLOv7x. Detect and classify trash items for a cleaner environment. Easy-to-use and customizable.
Concrete-Classification-Computer-Vision-CoE
In the project, within the scope of the Computer Vision course with the code 02010012 given by the Faculty of Computer Engineering, crack and no crack classification was made with the VGG-16 and ResNet-50 architecture.
Image-Segmentation-with-Mask-R-CNN
In this repository, we are going to use photos that I took in the cities I visited for image segmentation with Mask R-CNN.
Predicting-Solar-Flares
Multi-output and XGBoost models have been created which can estimate numbers of the solar flares production in specific region on sun in the following 24 hours.
Cat-Dog-Classification-with-VGG-16
In the project, within the scope of the Computer Vision course with the code 02010012 given by the Faculty of Computer Engineering, cat and dog classification was made with the VGG-16 architecture.
Clus-Hierarchical-Credit-Card
Hierarchical clustering analysis on Credit Card customers dataset.
Clustering-Earthquakes-in-Turkey
The magnitude of the earthquakes in Turkey was clustered by DBSCAN. Datas taken from Kandilli Observatory and Earthquake Research Instıtute (KOERI) and AFAD Event Catalog.
Leaf-Detection-YOLOv7x
YOLOv7-based leaf object detection for agriculture. Accurate crop management and weed control.
Restaurant-and-Cafe-API
This project aims to streamline the operations of a restaurant, making it easier for restaurant owners and staff to manage menus, bookings, and customer information efficiently.
Rock-Paper-Scissors-with-Thompson-Sampling
The aim of this project is to achieve maximum success by the algorithm in the rock-paper-scissors game with the reinforcement learning.
Shopping-with-Association-Rules-Analysis
Create relation between the people who buy the products and the products they might buy with the association rules analysis.
Temp-Forecast-RNN
Enhance Turkey's weather forecasting with RNNs for precise climate insights and informed decision-making.
Cozy-Cafe-Website
A delightful website showcasing a fusion of modern desserts and exceptional coffees. Built with Django and powered by SQLite for efficient data management.
InferenceVision
Provide geographic coordinates from bounding boxes.
Analysis-of-Algorithms
In this repository, the solutions of the problems given in the Analysis of Algorithms course will be shown. Problems are solved with Python, Java and MATLAB.
Book-Recommendation-with-Collaborative-Filtering
In this project, with Pearson correlation, book recommendation algorithm builded to make recommendation between users by their ratings.
FineTune-DiaSum-PEFT-LoRA
PEFT and LoRA to fine-tune large language models for dialogue summarization, reducing computational resources for broader application.
GeoAdvances-EQ-Scene-Classification-2023-Kahramanmaras
This repository houses a comprehensive deep learning-based system for the scene classification of very high-resolution satellite imagery, focusing on post-earthquake damage assessment. The primary case study involves the devastating earthquakes that occurred in Kahramanmaraş province, Türkiye, in 2023.
HRPlanes
A benchmark dataset for deep learning-based airplane detection: HRPlanes
MAGIC-Gamma-Telescope-Particle-Classification
The purpose of this study is to predict the particle classes of the telescope observation. Classes consists of the gamma (signal) or hadron (background) particle.
Nearest-Earth-Objects-Classification
Explore NEOs with our AI-powered model. Predict hazardous NEOs using Artificial Neural Networks (ANNs). Join us in safeguarding our planet.
Sunspot-RNN-Forecast
Advancing sunspot forecasting with Recurrent Neural Networks for precise predictions in space weather research and monitoring.
Text-Analysis-TF-IDF
Text Analysis and Information Retrieval with TF-IDF provides tools for TF-IDF vectorization, Bayesian probabilistic retrieval, word frequency analysis, and inner product scoring for information retrieval.