Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Utku, Anıl(3)
- Yildirim, Ozal(3)
- Acharya, U. Rajendra(2)
- Baloglu, Ulas Baran(2)
- Demir, Yakup(2)
- Talo, Muhammed(2)
- Akyol, Sinem(1)
- Alofaysan, Hind(1)
- Amoozegar, Azadeh(1)
- Ay Karakuş, Betül(1)
- Aydin, Galip(1)
- Barut, Abdulkadir(1)
- Benedicenti, L.(1)
- Ciaccio, Edward J.(1)
- Gunay, Mihriban(1)
- Hallaç, İbrahim Rıza(1)
- Henni, Mohamed Djafar(1)
- Kaya, Sema Kayapinar(1)
- Liu, Z.(1)
- Murat, Fatma(1)
- Tan, Ru-San(1)
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ2Federated agricultural yield forecasting under an Edge–Fog–Cloud framework: a multi-country privacy-preserving approach
Utku, Anıl; Barut, Abdulkadir; Alofaysan, Hind; Henni, Mohamed Djafar; Amoozegar, Azadeh
Predicting agricultural yields is crucial for ensuring global food security and adaptation to climate change. However, the centralized collection of agricultural data across countries might pose governance, privacy, and data sovereignty issues. This research presents a privacy-preserving model for predicting agricultural yields using federated learning within an edge-fog-cloud integrated architecture. The experiments have been performed on a European cereal production dataset for the period 1990–2022, using a time-aware forecasting scheme. Centralized, edge-only, federated, and hybrid learning techniques have been systematically compared to examine the influence of distributed optimization on forecasting performance. It can be seen that central classical machine learning algorithms have yielded the best predictive performance. Federated deep learning models, meanwhile, showed relatively poor forecasting accuracy compared to their centralized counterparts under a non-IID distribution of multi-country agricultural data. Edge-only learning, meanwhile, has yielded comparatively low generalization capabilities due to the absence of collaborative learning.
- BildiriAçık Erişim2025Deep Learning-Based Approaches for Short-Term Residential Electricity Consumption Prediction: A Comparative Study of LSTM, CNN-LSTM, and CNN-GRU Models
Gunay, Mihriban; Yildirim, Ozal; Demir, Yakup; Benedicenti, L.; Liu, Z.
The rapid increase in the world population has increased electricity consumption and demand for electricity. In order for electricity distribution companies to determine electricity demand, household electricity consumption must be predicted. In this study, an open access dataset was used to predict individual household electricity consumption. For this purpose, deep learning-based LSTM, CNN-LSTM and CNN-GRU models were developed and a comparative analysis was performed. The performance of the models was evaluated using four evaluation metrics commonly used in prediction model performance evaluation. According to the results obtained, it was seen that the models used in the study were successful in predicting short-term electricity consumption. In particular, the CNNLSTM model was found to have a lower error rate compared to the other two models.
- MakaleAçık Erişim2025Scopus SJRQ1Hybrid GA-ConvLSTM for data-driven prediction of climate variables: a case study of the most biodiverse cities in India
Utku, Anıl; Akyol, Sinem
Climate variables affect ecosystems’ structure, sustainability, and biodiversity. Monitoring and analysis of climate variables are essential for the management of ecosystems and the conservation of biodiversity. Temperature affects the distributions, habitats, and phonological events of living things in ecosystems. Humidity is essential for meeting plants’ water needs and the habitat’s quality and health. Dew point is essential for water quality, balance, plant health, and microclimate. Wind speed is essential for pollinating plants, microhabitats, and the health of living things. For such reasons, accurate prediction of climate variables using artificial intelligence methods can effectively predict the future of ecosystems and biodiversity and develop future strategic plans. This study aimed to predict the climate variables of temperature, humidity, dew point, and wind speed of Bhubaneshwar, Dehradun, Guwahati, Mysore, and Nagpur, among the cities with the highest biodiversity in India. It aimed to determine the long-term impacts of climate change on managing ecosystems and biodiversity protection. The hyperparameters of the ConvLSTM model, developed using CNN and LSTM, were optimized with a genetic algorithm, and the GA-ConvLSTM hybrid model was created. GA-ConvLSTM was tested with XGBoost, SVM, ANFIS, CNN, LSTM, and base ConvLSTM using approximately 15 years of hourly, up-to-date, and real-time climate variable data of cities. This work is one of the pioneering studies using GA to optimize deep learning hybrid models for multi-city climate prediction through extensive long-term high-resolution datasets. The experimental results reveal that GA-ConvLSTM outperforms conventional models, producing an R2 score exceeding 0.9 for each city across all climate variables. GA-ConvLSTM produced temperature predictions with 0.833 RMSE and 0.995 R2 for Bhubaneswar, humidity predictions with 3.461 RMSE and 0.990 R2, dew point predictions with 0.632 RMSE and 0.995 R2, and wind speed predictions with 2.278 RMSE and 0.993 R2. The experimental findings confirm the improved performance over conventional models due to SVM and XGBoost failing to achieve these R2 values and high RMSE scores. The research meets three principal obstacles because of the combination of stochastic climate datasets and complex nonlinear patterns, which also encounter limitations in conventional methods for managing scale-dependency relationships and manual parameter adjustments. This approach delivers three main strengths because it combines CNN and LSTM networks through genetic programming while tracking temporal and spatial relationships and processing noisy data automatically, leading to improved results compared to other methods. Unlike other published models in the field, the hybrid model GA-ConvLSTM combines optimized CNN and LSTM elements with genetic algorithm elements. The proposed model received its first application in this research for multi-city climate prediction through training with 15 years of hourly data. Standard methods encounter challenges when detecting long-term dependencies, but GA-ConvLSTM successfully addresses this issue.
AtıfScopus1OpenAlex1
İncele - MakaleYalnız künye2023Scopus SJRQ2New Deep Learning-Based Passenger Flow Prediction Model
Utku, Anıl; Kaya, Sema Kayapinar
The ability to predict passenger flow in transport networks is an important aspect of public transport management. It helps improve transport services, aids those responsible for management to obtain early warning signals of emergencies and unusual circumstances and, in general, makes cities smarter and safer. This paper develops a long short-term memory-based (LTSM-based) deep learning model to predict short-term transit passenger volume on transport routes in Istanbul. This prediction model has been created using a dataset that included the number of people who used different transit routes in Istanbul at one-hour intervals between January and December 2020. The proposed multilayer LSTM-based deep learning model has been compared with popular models such as random forest (RF), support vector machines, autoregressive integrated moving average, multilayer perceptron, and convolutional neural network. The experimental findings showed that the proposed multilayer LSTM-based deep learning model outperformed the other models with regard to prediction for each transfer route. Furthermore, RF, one of the machine learning models used, produced remarkably successful results.
AtıfScopus19WoS12OpenAlex16
İncele - Derleme MakaleYayıncıda açık erişim2020Scopus SJRQ1Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review
Murat, Fatma; Yildirim, Ozal; Talo, Muhammed; Baloglu, Ulas Baran; Demir, Yakup; Acharya, U. Rajendra
Deep learning models have become a popular mode to classify electrocardiogram (ECG) data. Investigators have used a variety of deep learning techniques for this application. Herein, a detailed examination of deep learning methods for ECG arrhythmia detection is provided. Approaches used by investigators are examined, and their contributions to the field are detailed. For this purpose, journal papers have been surveyed according to the methods used. In addition, various deep learning models and experimental studies are described and discussed. A five-class ECG dataset containing 100,022 beats was then utilized for further analysis of deep learning techniques. The constructed models were examined with this dataset, and results are presented. This study therefore provides information concerning deep learning approaches used for arrhythmia classification, and suggestions for further research in this area.
AtıfScopus318OpenAlex328
İncele - MakaleYalnız künye2019Scopus SJRQ1A new approach for arrhythmia classification using deep coded features and LSTM networks
Yildirim, Ozal; Baloglu, Ulas Baran; Tan, Ru-San; Ciaccio, Edward J.; Acharya, U. Rajendra
Background and objective: For diagnosis of arrhythmic heart problems, electrocardiogram (ECG)signals should be recorded and monitored. The long-term signal records obtained are analyzed by expert cardiologists. Devices such as the Holter monitor have limited hardware capabilities. For improved diagnostic capacity, it would be helpful to detect arrhythmic signals automatically. In this study, a novel approach is presented as a candidate solution for these issues. Methods: A convolutional auto-encoder (CAE)based nonlinear compression structure is implemented to reduce the signal size of arrhythmic beats. Long-short term memory (LSTM)classifiers are employed to automatically recognize arrhythmias using ECG features, which are deeply coded with the CAE network. Results: Based upon the coded ECG signals, both storage requirement and classification time were considerably reduced. In experimental studies conducted with the MIT-BIH arrhythmia database, ECG signals were compressed by an average 0.70% percentage root mean square difference (PRD)rate, and an accuracy of over 99.0% was observed. Conclusions: One of the significant contributions of this study is that the proposed approach can significantly reduce time duration when using LSTM networks for data analysis. Thus, a novel and effective approach was proposed for both ECG signal compression, and their high-performance automatic recognition, with very low computational cost.
AtıfScopus377OpenAlex388İncele - BildiriAçık Erişim2018Scopus SJRQ2Evaluating deep learning models for sentiment classification
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.
AtıfScopus55WoS40OpenAlex64İncele