Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Utku, Anıl(12)
- Can, Umit(6)
- Yıldırım, Özal(4)
- Çelik, Yusuf(4)
- Artuger, Firat(3)
- Doğan, Gürkan(3)
- Ergen, Burhan(3)
- Sengur, Abdulkadir(3)
- Uyanik, Hakan(3)
- Özçelik, Salih Taha Alperen(3)
- Akcayol, M. Ali(2)
- Akyol, Sinem(2)
- Ertarğın, Merve(2)
- Acar, Ramazan(1)
- Akın, M Faysal(1)
- Alatas, Bilal(1)
- Algur, Özlem(1)
- Aycin, Ejder(1)
- Aydın, Yılmaz(1)
- Baykara, Muhammet(1)
- Bürhan, Yücel(1)
- Can, Ümit(1)
- Cevher, Muhammed Fatih(1)
- Demir, Yakup(1)
- Durmuş, Beyzanur(1)
- Eteman, Fatma Sert(1)
- Gültekın, Saıt Ugur(1)
- Gülter, Erkan(1)
- Günay, Mıhrıban(1)
- Imak, Andac(1)
- Karakaş, Buğra(1)
- Karakuş, Songül(1)
- Kaya, Sema Kayapinar(1)
- Kaya, Ömer(1)
- Kutlu, Banu(1)
- Kızıloluk, Soner(1)
- Metin, Zülfiye Beyza(1)
- Orhan, Ahmet(1)
- Saplioglu, Kemal(1)
- Sevinç, Ali(1)
Yayınlar
- MakaleAçık Erişim2026Dikkat Tabanlı Görsel–İşitsel Akış Füzyonu ile Sahne Sınıflandırma
Çelik, Yusuf
Bu çalışmada, sahne sınıflandırma görevlerinde görsel ve işitsel verilerin birlikte kullanılmasına yönelik, Gated Cross-Modal Attention Fusion Network (GCM-AFN) adı verilen çok modlu bir derin öğrenme mimarisi önerilmektedir. Önerilen yapıda, görsel akıştan EfficientNetV2 omurgası kullanılarak derin özellikler çıkarılırken, işitsel akışta MFCC tabanlı zaman-frekans temsilleri kullanılmaktadır. Her iki akıştan elde edilen özellik temsilleri, kapılı dikkat mekanizması aracılığıyla birleştirilmektedir. Model, çok kipli bilgilerin etkin biçimde bir araya getirilmesini sağlamak amacıyla yardımcı akış çıktıları ve dikkat tabanlı bir füzyon stratejisi içermektedir. Çapraz doğrulamaya dayalı deneysel sonuçlar, önerilen yaklaşımın tek akışlı modeller ve geleneksel füzyon yöntemlerine kıyasla daha yüksek doğruluk, daha düşük varyans ve sınıf bazında daha tutarlı bir performans sergilediğini göstermektedir. Elde edilen bulgular, dikkat tabanlı füzyonun görsel–işitsel sahne sınıflandırma görevlerinde etkili bir bilgi birleştirme yaklaşımı sunduğunu ortaya koymaktadır.
- MakaleAçık Erişim2026Sentiment Analysis of Monkeypox Tweets Using a Hybrid CNN-BiGRU Based Deep Learning Model
Can, Umit
Recently, epidemics have disrupted people's lives. Following the COVID-19 pandemic, cases of monkeypox, a rare disease, began to appear worldwide. These incidents raised societal tension and anxiety. Understanding public attitudes, sentiments, and perceptions regarding the epidemic is essential for developing and implementing effective policies and countermeasures. Online social media platforms are essential venues for expressing feelings and views. In particular, Twitter provides valuable information for measuring societal sentiment. Machine learning and deep learning methods have recently been widely used in social network analysis. Deep learning models, which deliver strong performance, particularly on complex and nonlinear problems, are used in natural language processing and text mining. In this study, a Convolutional Neural Network Bidirectional Gated Recurrent Unit (CNN-BiGRU) hybrid deep learning model was developed by combining a CNN and a BiGRU and applied for the monkeypox sentiment analysis. The dataset was labeled as positive, negative, or neutral with Valence Aware Dictionary and sEntiment Reasoner (VADER). In addition, FastText and Term Frequency-Inverse Document Frequency (TF-IDF) word-embedding methods were used for feature extraction, and the performance of machine-learning and deep-learning methods was evaluated separately. As a result of the experimental studies, the FastText-CNN-BiGRU model obtained the highest results with 0.9382 accuracy, 0.9347 macro precision, 0.9367 macro recall, 0.9355 macro F-score, and 0.9875 macro ROC-AUC. The FastText-CNN model was the second most successful, achieving 0.9303 accuracy, 0.9268 macro precision, 0.9280 macro recall, 0.9271 macro F-score, and 0.9862 macro ROC-AUC. The FastText-BiGRU model was the third most successful, achieving 0.9262 accuracy, 0.9224 macro precision, 0.9255 macro recall, 9236 macro F-score, and 0.9838 macro ROC-AUC.
- MakaleAçık Erişim2026Deep learning-based short-term cryptocurrency price forecasting using LSTM models enhanced with technical indicators
Çelik, Yusuf; İnce, İrem Sevda
This study investigates short-term cryptocurrency price forecasting using deep learning methods. Minute-level price and volume data for BTC/USDT and ETH/USDT trading pairs were obtained through the Binance API and analyzed under different temporal resolutions, including hourly and 15-minute forecasting scenarios. Recurrent neural network architectures, including LSTM, GRU, and BiLSTM, were evaluated using different loss functions to identify effective configurations for short-term forecasting. Experimental results show that deep learning models can achieve high forecasting accuracy for high-frequency cryptocurrency data. In particular, the LSTM model trained with a weighted loss function demonstrated strong and stable prediction performance. In addition, incorporating technical indicators as auxiliary features enriched the feature space and improved forecasting capability. The results also suggest that aligning the temporal resolution of technical indicators with the prediction frequency can further enhance model performance. Overall, the proposed framework provides an effective deep learning–based approach for short-term cryptocurrency price forecasting in high-frequency financial markets.
- MakaleAçık Erişim2026Application of machine learning techniques for multi-class classification performance on mental disorders
Can, Umit
The contemporary social framework is predicated on a fiercely competitive system, which amplifies individual pressure and subsequently elevates the incidence of mental diseases, significantly affecting public health. Consequently, governmental and non-governmental groups allocate considerable resources to tackle these concerns. The precise identification of such illnesses via artificial intelligence techniques has become critically significant. These methodologies, widely used across several healthcare sectors, have been increasingly adopted in psychiatry. Evaluating psychiatric data to forecast disease accurately enables doctors to make better decisions and establishes a robust decision-support framework. This work employed prevalent machine learning techniques to identify mental illnesses utilizing a dataset with labels for seven distinct mental states—six disorders and one normative condition. The approaches were initially evaluated on an imbalanced dataset and subsequently on a balanced dataset, facilitating comparison of the outcomes. Among Categorical Boosting, Gradient Boosting, Extreme Gradient Boosting, Support Vector Machine, and Logistic Regression, the Support Vector Machine method demonstrated superior performance on both balanced and imbalanced datasets.
- MakaleAçık Erişim2025Artificial Intelligence Applications in the Aquaculture Industry: Sustainability, Efficiency and Innovative Solutions
Kutlu, Banu; Utku, Esen Damla Balo
Artificial Intelligence (AI) is becoming increasingly important to increase efficiency and sustainability by organizing processes and providing significant improvements in different sectors. AI is reshaping the aquaculture sector. AI is being used to help solve optimization problems in aquaculture, reduce costs, and find sustainable solutions. These scenarios guided the evaluation of the future role of AI in aquaculture and the benefits that AI brings to the aquaculture sector in this study. AI is improving the way fish stocks are monitored, live stocks are assessed, diseases among plants and animals are recognized, water quality is tested, and production lines are controlled. Aquaculture uses AI technologies to help detect diseases early, monitor environmental conditions affecting production, and improve both efficiency and sustainability. In addition, AI is examining and providing solutions to environmental issues such as global warming and water resource management.
AtıfOpenAlex5
İncele - Derleme MakaleAçık Erişim2025Deep 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.
- MakaleYalnız künye2025The Position of Metaheuristic Optimization Methods in Psychiatric Practice: A Bibliometric Analysis
Tuğrul, Feride; Can, Umit
Mental diseases affect billions of people worldwide to varying degrees. This poses a risk to public health. Although the levels and effects of diseases vary, in general, mental diseases prevent people from having a healthy relationship with themselves and their environment and prevent them from living their daily lives efficiently. Individuals who move away from the comfort of daily life face many difficulties in their social and professional lives. People with long-term mental disorders may also experience physiological disorders due to stress. When this situation is not treated and prevented, it becomes a public health problem. Therefore, centers such as health institutions, research centers, and universities operating in the field of health carry out many studies to detect and treat mental disorders. These methods include traditional methods, but today, they also include artificial intelligence-supported methods. AI-powered methods are used for early diagnosis and treatment of mental illnesses by analyzing large amounts of mental illness data of various types. Researchers are also using metaheuristic optimization algorithms to improve the performance of these methods. These optimization methods, which seek fast and high-performance solutions to very complex nonlinear problems, are increasing the success of machine learning and deep learning methods. Nonetheless, there is no distinct bibliometric analysis demonstrating the quantity and quality of research in this domain for scholars. This study aims to fill this gap in this field and to be a preliminary guide for researchers.
AtıfTR Dizin1İncele - MakaleYalnız künye2025Artificial Intelligence-Driven Risk Assessment in Civil Engineering Projects: A Comparative Analysis of Machine Learning Models
Utku, Anıl
Successful completion of civil engineering projects involves complex interactions among various components such as managing costs, maintaining schedules, ensuring structural stability, and minimizing environmental impacts. Accurate risk prediction at the project level is important to support efficient resource planning and prevent potential delays or disruptions. Since traditional risk assessment methods based on expert judgments involve lengthy and subjective procedures, the development of data-driven and automated estimation systems is at the forefront. In this study, a comparative analysis of various machine learning methods such as RF, SVM, XGBoost, CatBoost, and LGBM for project risk assessments in civil engineering is presented. The dataset used in the study includes information on project type, cost change records and planning, and real-time history, as well as environmental data and safety documentation, and structural health measurements. Precision, accuracy, sensitivity, and F-score metrics were used to evaluate the models along with ROC-AUC measurements. Experimental studies showed that CatBoost and LGBM outperform the compared models with 95.5% accuracy.
AtıfTR Dizin1İncele - MakaleAçık Erişim2025Evolution of digital marketing campaigns with artificial intelligence and machine learning: Analysing success prediction capabilities
Cevher, Muhammed Fatih; Gülter, Erkan
This study aims to investigate the predictive capabilities of machine learning algorithms in forecasting the success of digital marketing campaigns. In addition, the study aims to evaluate the performance of machine learning algorithm classification models and to determine which classification model is more effective in making this prediction. In this direction, a classification analysis was performed with machine learning algorithms using a dataset of 10,001 digital marketing campaigns obtained from the Kaggle platform. The study's theoretical background is based on Attribution Modelling, the Technology Acceptance Model, Incremental Response Modelling, and the Diffusion of Innovations Theory. As a result of the analysis, it was revealed that the success prediction capabilities of machine learning algorithms for marketing campaigns are pretty high. In the study comparing the success prediction abilities of machine learning models, the Gradient Boosting model demonstrated the highest success prediction ability (93.31%). In comparison, the Logistic Regression model has the lowest predictive success rate (53.36%). The findings revealed that machine learning algorithms should be more widely incorporated into the marketing literature and that businesses can run more successful and efficient campaigns by utilising machine learning models in their marketing efforts.
AtıfOpenAlex1İncele - MakaleAçık Erişim2025A 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.
- MakaleAçık Erişim2025Tek değişkenli tahminde tahmin yöntemlerinin karşılaştırılması: Türkiye çimento endüstrisi örneği
Tüzüntürk, Selim; Eteman, Fatma Sert
Bu çalışma, Türk çimento imalat sanayinde çimento üretimini tahmin etmek için bir yöntem bulmayı ve bu yöntemle çimento üretimini tahmin ederek gelecekteki üretim gelişimi hakkında bazı sonuçlar çıkarmayı amaçlamaktadır. Bu çalışmada kullanılan veri, Türk çimento sanayinin toplam aylık çimento üretimidir. Veriler, Ocak 2017'den Eylül 2024'e kadar 93 ayı kapsamaktadır. Oluşturulan modele yapay sinir ağı modelleme prosedürleri uygulanmış ve derin öğrenme araçları yardımıyla tahmin yapılmıştır. Tahminlerin performansı oldukça iyi olup, ağın genelleştirilebilir olduğu sonucuna varılmıştır. Sonuçlar, eğitilen ağdan elde edilen eşik değerleri ve ağırlıklar kullanılarak geliştirilen model ile aylık üretimlerin tahmin edilebileceğini göstermiştir. Aylık çimento tahminleri Aralık 2026'ya kadar yapılmıştır. Tek değişkenli zaman serisi verilerinin YSA'lar ile modellenmesinin başarısı, MAPE istatistikleri kullanılarak Winters ve SARIMA yöntemleri ile karşılaştırılarak doğrulanmıştır. En uygun tahmin yönteminin YSA olduğu bulunmuş ve bulgular tartışılmıştır.
- MakaleAçık Erişim2024Convmixer ve SDD Kullanılarak DEHB Hastalığının EEG Sinyalleri ile Otomatik Olarak Tespit Edilmesi
Sengur, Abdulkadir; Üzen, Hüseyin; Özçelik, Salih Taha Alperen; Uyanik, Hakan; Karakaş, Buğra
DEHB, çocuklarda dikkat eksikliği, davranış problemleri, eğitimle ilgili sorunlar ve düşük özgüven gibi problemler oluşturabilir. Bu çalışma, Dikkat Eksikliği Hiperaktivite Bozukluğu (DEHB) teşhisini elektroensefalografi (EEG) sinyalleriyle değerlendirmeyi hedefleyen bir araştırmayı özetlemektedir. Araştırma, 30 DEHB tanısı almış çocuk ve 30 sağlıklı kontrol grubunun EEG verilerini kullanmıştır. EEG verileri öncelikle gürültü azaltma amacıyla işlenmiş ve ardından ConvMixer, ResNet50 ve ResNet18 gibi derin öğrenme modelleri kullanılarak sınıflandırılmıştır. Bulgular, ConvMixer'in düşük hesaplama kaynaklarına ihtiyaç duyarak yüksek sınıflandırma başarısı elde ettiğini göstermektedir. Ayrıca, EEG sinyallerinin DEHB teşhisinde kullanılabilirliği konusunda farklı kanalların etkileri incelenmiş ve T8 kanalının özellikle etkili olduğu tespit edilmiştir. Bu çalışma, EEG tabanlı DEHB teşhisi için daha hafif modellerin kullanılabilirliğini ve EEG kanallarının önemini vurgulamaktadır.
AtıfOpenAlex1İncele - MakaleAçık Erişim2024Neural Network Based a Comparative Analysis for Customer Churn Prediction
Akcayol, M. Ali; Utku, Anıl
Customer churn refers to a customer's disconnection from a business. The expense associated with customer churn encompasses both the forfeited revenue and the marketing expenditures required to acquire new customers. Mitigating customer churn stands as the foremost objective for every business. Customer churn prediction will contribute to developing strategies enabling businesses to retain these customers by identifying customers with a high risk of loss. In the digital world, the importance of developing customer churn prediction models is increasing daily. In this study, MLP based artificial neural network model was developed for customer churn prediction using customer data from an anonymous telecommunications company. The developed model was compared with kNN, LR, NB, RF, and SVM. The prediction results of the applied models were discussed, and the experimental results showed that all the models compared had over 70% accuracy. Experimental results showed that the developed MLP-based artificial neural network model has the most successful classification performance compared to other models with approximately 95% accuracy.
AtıfOpenAlex3TR Dizin2İncele - MakaleYalnız künye2024Yapay zeka öz-yeterlilik ölçeğinin türkçe’ye uyarlanması: geçerlililik ve güvenirlik çalışması
Uyan, Umut; Gültekın, Saıt Ugur
Son dönemde geliştirilen ve geleneksel iş yapma pratiklerimize meydan okuyan yapay zeka (YZ) teknolojileri, otonom araçlardan tıbbi teşhise kadar birçok alanda kullanılmaya başlanmıştır. Bahsedilen teknolojiler hızlı ve bağlama uyarlanabilir çıktılar sunabilmesi bakımından kullanıcılarına etkinliklerini arttırmayı vadetmektedir. Diğer taraftan insan-benzeri etkileşim deneyimi sunabilen bu teknolojiler makine-insan ilişkisini benzersiz bir boyuta taşımaktadır. Ancak bahsedilen teknolojilerin bireysel düzeyde benimsenmesi ve kullanımına yönelik bilimsel çabaya ihtiyaç duyulmaktadır. Bu bağlamda Wang ve Chuang (2023) dört boyuttan oluşan yapay zeka öz yeterlilik (YZÖY) ölçeğini oluşturmuşlardır. Mevcut çalışmanın amacı yabancı dilde oluşturulan ve yazında öncü nitelikte olan bu ölçüm aracının Türkçeye uyarlanmasıdır. Uyarlama çalışması için Munzur Üniversitesinde görev yapan 156 akademik ve idari personelden online anketler vasıtasıyla veri toplanmıştır. Keşifsel ve doğrulayıcı analizlerin sonucunda elde edilen bulgular orijinal ölçeğin Türkçe formunun geçerli ve güvenilir olduğunu göstermektedir. Kültürel doğrulaması yapılan ölçüm aracının ileride bu alanda gerçekleştirilecek Türkçe çalışmalara katkı sunması beklenmektedir.
AtıfOpenAlex13TR Dizin4İncele - MakaleAçık Erişim2024Application of Deep Learning for Voice Command Classification in Turkish Language
Çelik, Yusuf
In this study, a deep learning model was developed for the recognition and classification of voice commands using the Turkish Speech Command Dataset. The division of training, validation, and test sets was carried out on an individual basis. This approach aims to prevent the model from memorizing and to enhance its generalization capability. The model was trained using Mel-Frequency Cepstral Coefficients (MFCC) features extracted from voice files, and its classification performance was evaluated in detail. The findings indicate that the model successfully classifies voice commands with a high accuracy rate, achieving an overall accuracy of 92.3% on the test set, highlighting the potential of deep learning approaches in voice recognition technologies
AtıfOpenAlex6İncele - MakaleAçık Erişim2024Blum Blum Shub Tabanlı Yeni Bir Kriptografik Anahtar Planlama Algoritması
Artuger, Firat; Karakuş, Songül
Blum Blum Shub (BBS) algoritması bilinen güçlü sözde rastgele sayı üreteçlerinden bir tanesidir. Bu algoritma anahtar üretiminde kullanılabilir. BBS temelde iki büyük asal sayının çarpımına ve bir tohum değerine dayanmaktadır. Bu değerlerin seçilmesi oldukça kritik bir konudur. Bu çalışmada bu problemin üstesinden gelmek için yeni bir yaklaşım önerilmiştir. Önerilen yaklaşımda öncelikle asal sayı havuzu oluşturulmaktadır. Bu noktada kullanıcı bir başlangıç ve bitiş değeri belirlemektedir. Belirlenen bu aralıktaki asal sayılar üretilerek bir diziye kaydedilir. Daha sonra bu asal sayı havuzundan kaotik haritalar ile rastgele iki asal sayı seçilir. Seçilen bu asal sayıların dizideki konumları kaydedilir. Tohum değeri ise bu iki asal sayının konumları toplamı olarak ele alınmıştır. Yani seçilecek olan parametreler o an kullanıcının gireceği aralıklarda rastgele bir şekilde seçilecektir. Bu çalışmada bu şekilde rastgele iki bit dizisi elde edilmiştir. Bu diziler 1 milyon bit uzunluğundadır. Elde edilen bu dizilere NIST SP 800-22 testleri uygulanmış olup diziler tüm testleri başarı ile tamamlamıştır.
AtıfOpenAlex2İncele - MakaleAçık Erişim2024Automatic Classification of Defective Photovoltaic Module Cells Based on a Novel CNN-PCA-SVM Deep Hybrid Model in Electroluminescence Images
Imak, Andac
In today’s world, the rapid development of photovoltaic (PV) power plants has facilitated sustainable energy production. Maintenance and defect detection play crucial roles in ensuring the continuity of energy production. The manual inspection of electroluminescence (EL) images of PV modules requires significant human power and time investment. This study presents a method for the automatic fault detection of PV cells in EL images using hybrid deep features optimized with a principal component analysis (PCA) feature selection algorithm. A lightweight and high-performance model that combines the strengths of convolutional neural network (CNN) architectures was proposed. First, data augmentation techniques were employed owing to the imbalance between the defective and functional classes in the dataset containing EL images. In experimental studies conducted by integrating the PCA algorithm into MobileNetV2, DenseNet201, and InceptionV3 CNN models, accuracy, precision, recall, and F1-score values of 92.19%, 92%, 90%, and 91%, respectively, were achieved. When the results were analyzed, it was observed that the proposed method was effective in detecting faults in PV panel cells.
AtıfOpenAlex8TR Dizin2İncele - MakaleYalnız künye2024Deprem seviye sınıflandırması için hibrit bir convlstm modeli: karşılaştırmalı bir analiz
Utku, Anıl
Deprem, yer kabuğunda depolanan enerjinin açığa çıkması sonucu yer yüzeyinin aniden sarsılmasıdır. Depremler genellikle yer altı kayalarının aniden kırılması ve bir fay boyunca hızlı etmesi nedeniyle meydana gelir. Binaların ve altyapının düzgün inşa edilmediği ve nüfusun hazırlıklı olmadığı bir ortamda, orta şiddette bile olsa bir deprem yıkıcı olabilir. Yapay zekâ yöntemleri, deprem tahmini gibi doğal afetlerin öngörülmesinde önemli bir rol oynamaktadır. Bu amaçla geliştirilen hibrit ConvLSTM modeli ile yer kabuğundaki karmaşık enerji dinamikleri ve hareketleri, büyük miktardaki jeolojik verilerden analiz edilerek deprem olasılıklarının tahmin edilmesi amaçlandı. ConvLSTM, LR, RF, SVM, XGBoost, MLP, CNN ve LSTM gibi popüler yöntemlerle USGS tarafından sunulan gerçek zamanlı deprem verileri kullanılarak karşılaştırıldı. Deneysel sonuçlar, ConvLSTM’in 0,9951 doğruluk ve 0,9993 AUC ile karşılaştırılan modellerden daha başarılı olduğunu göstermiştir
- MakaleAçık Erişim2024Hybrid ConvLSTM Model for Wind Speed Prediction: A Case Study for India's Highest Wind Speed Cities
Utku, Anıl; Akyol, Sinem
Wind speed prediction is very important for logistics, energy production and renewable energy sources, aviation and maritime, agriculture, disaster management, environmental monitoring, construction, life planning and economic activities. In this study, it was aimed to predict the wind speeds of Jaisalmer, Kochi, Mangalore, Puri and Rameswaram, which are among the cities with the highest wind speeds in India. ConvLSTM hybrid model was developed by taking advantage of the effective features of CNN and LSTM models for wind speed prediction. With ConvLSTM, it is aimed to better determine the dynamics of wind speed by processing spatial and temporal data simultaneously. ConvLSTM has been extensively tested using an approximately 15-year hourly dataset consisting of RF, SVM, ANFIS, CNN and LSTM and wind speed measurements at 10 meters and 100 meters’ altitudes. Experimental results show that ConvLSTM has R2 values above 0.9 for almost all of the city and wind speed parameters, and outperforms the compared models with the lowest error values in terms of RMSE and MAE error metrics.
AtıfOpenAlex1TR Dizin1İncele - MakaleYalnız künye2024Hybrid CNN-LSTM Model for Accurate Long-Term and Short-Term Temperature Prediction: A Case Study for Bingöl and Tunceli
Utku, Anıl
Extreme and sudden weather events experienced with global warming and climate change reveal the importance of accurate air temperature prediction. For this reason, it can be used to optimize decision-making processes for a wide range of applications from health and agricultural planning to energy consumption strategies. Artificial intelligence methods are successfully applied in many application areas due to their flexibility and efficiency. Traditional weather forecasting models are inefficient in detecting sudden fluctuations and complex, irregular patterns in data. Artificial in-telligence methods overcome these limitations thanks to their ability to process big data and capture long-term temporal dependencies. In this study, the aim is to predict future temperature changes more accurately by capturing patterns in past data with the developed CNN-LSTM hybrid model. The developed hybrid model is compared in detail with RF, SVM, CNN, and LSTM. The compared models were tested using daily average temperature data between 1961-2024 and hourly temperature data between 2020-2024. Experiments have shown that CNN-LSTM outperforms the compared models with R2 value above 0.97 in all scenarios.
AtıfOpenAlex2TR Dizin1İncele