Sürdürülebilir Kalkınma Amaçları

• 1
• 1
• 1
• 1

• Derleme MakaleAçık Erişim2025/r/munzur/6183
  Deep learning: evolution, innovations, and applications in the last decade

  Yıldırım, Özal; Günay, Mıhrıban; Demir, Yakup

  Deep learning has become a popular method in the last ten years with its superior performance in many fields, especially in health. Although it is a sub-branch of machine learning, one of the most important reasons for researchers to use this method is that it automates the difficult processes of feature extraction stages in traditional machine learning methods. With the advancement of technology every year, it has become easier to create large data sets or to access large data sets that have been used before on the web. Researchers who want to work on large data sets use deep learning methods effectively because of their advantages instead of using traditional machine learning methods. The foundations of deep learning were laid with the deep belief networks method, which was first developed in 2006. Later, with the significant success of the Convolutional Neural Network (CNN) method developed in 2012 in image classification, deep learning methods have been used in many applications in other disciplines. The success of the deep reinforcement learning algorithm that defeated Alpha Go champion Lee Sedol in 2016, the remarkable success of the contentious generating networks in creating their own unique images, the success of the Siamese networks with the ability to learn from little data in signature verification and facial recognition systems, the success of the artificial intelligence chat bot ChatGPT, which was launched in the last months of 2022, attracted attention in a short time, and the ability of DALL-E, a similar language model, to create images from texts, shows that deep learning is in constant innovation and development. This study aims to give an idea to researchers who will work in this field in the future by talking about the basic concepts of deep learning and the innovative and popular approaches used.

  İncele
• MakaleAçık Erişim2025/r/munzur/6001
  A comparison of cnn and transformer-based models for algal species classification

  Ertarğın, Merve; Şimşek, Gökçe Kendirlioğlu

  In this study, the classification of Spirulina platensis, Tetraselmis suecica, and Porphyridium cruentum algal species was conducted using RegNetY-008, ConvNeXt-Tiny, and ViT-Tiny models. The experiments were performed on a small and imbalanced dataset, where all models achieved an accuracy of 100%. To assess model performance, training and validation losses were analyzed, confirming the absence of overfitting. Furthermore, Grad-CAM was applied to visualize the decision-making processes of the models. The results indicate that although all models demonstrated high accuracy, the ViT-Tiny model exhibited the most interpretable visualizations by effectively focusing on algal cells. This study highlights the capability of transformer-based models to achieve high performance even on small and imbalanced datasets, offering a promising alternative for biological image analysis.

  İncele
• MakaleAçık Erişim2025/r/munzur/5999
  Predicting daily energy consumption in ev charging stations using tree-based models

  Ertarğın, Merve

  Electric vehicles (EVs) have emerged as a cornerstone in the transition toward sustainable transportation, offering a cleaner alternative to conventional fossil fuel-based mobility. Their integration into modern transportation systems not only supports global decarbonization efforts but also requires robust energy management solutions to address the growing demands on charging infrastructure. Ensuring efficient energy consumption forecasting is vital for optimizing EV charging station operations and maintaining grid stability. This study aims to predict the daily energy consumption of an EV charging station using a public dataset. Key features such as charging duration, vehicle count, mean and median connection time were utilized for the prediction. Both the original dataset and its z-score-cleaned version were employed to evaluate the models' performance under different data conditions. Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) models were implemented, with hyperparameter optimization conducted via GridSearchCV. The results revealed that all four models achieved high accuracy in predicting daily energy consumption across both datasets, with R2 values exceeding 0.97. Specifically, for the z-score-cleaned dataset, LightGBM demonstrated the best performance with the lowest RMSE (37.35 kWh) and MAE (28.93 kWh), as well as the highest R2 value (0.9727) followed by XGBoost, RF and DT.

  • 
  • 
  • 
  • 
  AtıfOpenAlex1

  İncele