Arslan, Serdar
Loading...
Name Variants
Job Title
Dr. Öğr. Üyesi
Email Address
sarslan@cankaya.edu.tr
Main Affiliation
Bilgisayar Mühendisliği
Status
Current Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Files
Sustainable Development Goals Report Points
SDG data could not be loaded because of an error. Please refresh the page or try again later.
Scholarly Output
6
Articles
10
Citation Count
42
Supervised Theses
0
6 results
Scholarly Output Search Results
Now showing 1 - 6 of 6
Article Citation - WoS: 24Citation - Scopus: 35A hybrid forecasting model using LSTM and Prophet for energy consumption with decomposition of time series data(Peerj inc, 2022) Arslan, Serdar; Arslan, Serdar; Arslan, Serdar; 325411; Bilgisayar MühendisliğiFor decades, time series forecasting had many applications in various industries such as weather, financial, healthcare, business, retail, and energy consumption forecasting. An accurate prediction in these applications is a very important and also difficult task because of high sampling rates leading to monthly, daily, or even hourly data. This high-frequency property of time series data results in complexity and seasonality. Moreover, the time series data can have irregular fluctuations caused by various factors. Thus, using a single model does not result in good accuracy results. In this study, we propose an efficient forecasting framework by hybridizing the recurrent neural network model with Facebook's Prophet to improve the forecasting performance. Seasonal-trend decomposition based on the Loess (STL) algorithm is applied to the original time series and these decomposed components are used to train our recurrent neural network for reducing the impact of these irregular patterns on final predictions. Moreover, to preserve seasonality, the original time series data is modeled with Prophet, and the output of both sub-models are merged as final prediction values. In experiments, we compared our model with state-of-art methods for real-world energy consumption data of seven countries and the proposed hybrid method demonstrates competitive results to these state-of-art methods.Article Türkçe Kısa Metinlerde Duruş Tespiti: Rusya-ukrayna Savaşı Örneği(2024) Arslan, Serdar; Fırat, Eray; Bilgisayar MühendisliğiSon yıllarda sosyal medya, çeşitli konulardaki halkın görüşlerini anlamak için önemli bir bilgi kaynağı haline gelmiştir. Bu nedenle, bu verilerden otomatik bilgi çıkarmak öneminin arttığı bir alan haline gelmiştir. Doğal dil işleme alanının alt görevlerinden biri olan görüş belirleme, otomatik bilgi çıkarma için kritik bir konudur. Duruş tespiti, kullanıcının belirli bir konu, olay veya kişi hakkındaki tutumunu otomatik olarak belirler. Bu çalışmada, Rusya-Ukrayna Savaşı'na yönelik sosyal medya kullanıcılarının tutumlarını belirleme görevine odaklanan Türkçe etiketli bir veri kümesi oluşturulmuş ve bu veri kümesinde çeşitli makine öğrenimi yöntemleri değerlendirilmiştir. Bu çalışma için 8215 tweet Twitter'dan toplandı ve temizlendi. Veri kümesi daha sonra Rusya ve Ukrayna olmak üzere iki hedefle etiketlendi. Stance Detection görevi için GloVe ve FastText kelime gömme ile Support Vector Machines, Random Forest, k-Nearest Neighbor, XGBoost, Long-Short Term Memory (LSTM) ve Gated Recurrent Unit (GRU) modelleri kullanılmıştır. Ayrıca, duruş tespiti için transformer tabanlı bir yaklaşım da kullanılmıştır. Veri kümesinin hedefler arasındaki dengesizliği dikkate alındığında, bu algoritmalarla birlikte örnek azaltma ve örnek artırma yöntemleri de kullanılmıştır. Deney sonuçları, BERT tabanlı modellerin diğer tüm modelleri geride bıraktığını göstermektedir. Bu sonuçların yanı sıra, LSTM ve GRU da BERT tabanlı modelin sonuçlarına oldukça benzer sonuçlar üretmiştir. Yeni oluşturulan Türkçe veritabanı, bu araştırma alanı için değerli bir kaynak olarak kabul edilebilir ve gelecekte transformer tabanlı yaklaşımlarla birlikte kullanma potansiyeline sahiptir. Özetle, bu çalışma, Türkçe metin bağlamında duruş tespiti araştırma alanını ilerletmektedir.Article Citation - WoS: 8Citation - Scopus: 8Application of BiLSTM-CRF model with different embeddings for product name extraction in unstructured Turkish text(Springer London Ltd, 2024) Arslan, Serdar; Arslan, Serdar; 325411; Bilgisayar MühendisliğiNamed entity recognition (NER) plays a pivotal role in Natural Language Processing by identifying and classifying entities within textual data. While NER methodologies have seen significant advancements, driven by pretrained word embeddings and deep neural networks, the majority of these studies have focused on text with well-defined grammar and structure. A significant research gap exists concerning NER in informal or unstructured text, where traditional grammar rules and sentence structure are absent. This research addresses this crucial gap by focusing on the detection of product names within unstructured Turkish text. To accomplish this, we propose a deep learning-based NER model which combines a Bidirectional Long Short-Term Memory (BiLSTM) architecture with a Conditional Random Field (CRF) layer, further enhanced by FastText embeddings. To comprehensively evaluate and compare our model's performance, we explore different embedding approaches, including Word2Vec and Glove, in conjunction with the Bidirectional Long Short-Term Memory and Conditional Random Field (BiLSTM-CRF) model. Furthermore, we conduct comparisons against BERT to assess the efficacy of our approach. Our experimentation utilizes a Turkish e-commerce dataset gathered from the internet, where traditional grammatical and structural rules may not apply. The BiLSTM-CRF model with FastText embeddings achieved an F1 score value of 57.40%, a precision value of 55.78%, and a recall value of 59.12%. These results indicate promising performance in outperforming other baseline techniques. This research contributes to the field of NER by addressing the unique challenges posed by unstructured Turkish text and opens avenues for improved entity recognition in informal language settings, with potential applications across various domains.Article Gated Recurrent Unit Network-based Fuzzy Time Series Forecasting Model(2023) Arslan, Serdar; Arslan, Serdar; 325411; Bilgisayar MühendisliğiZaman serisi tahminleme hava durumu, iş dünyası, satış verileri ve enerji tüketimi tahminleme gibi bir çok alanda uygulama alanına sahiptir. Bu alanlarda tahminleme yaparken kesin sonuçlar elde etmek çok önemlidir ama aynı zamanda zaman serilerinin karmaşık ve de belirsizlik içeren veriler olması nedeniyle çok zordur. Günümüzde, derin öğrenme metotları bu alanda klasik metotlara göre daha iyi sonuçlar vermektedir. Fakat literatürde bulanık zaman serileri tahminleme konusunda çok az çalışma vardır. Bu çalışmada, zaman serilerindeki karmaşıklığın ve belirsizliğin doğurduğu problemleri yok etmek için Yinelemeli sinir Ağları ile bulanık time serilerini bir arada kullanan bir model ortaya konmuştur. Bu çalışmada, Kapılı Tekrarlayan Hücreler kullanarak geçmiş veriler ile bulanık verilerin üyelik değerleri birleştirilerek tahminleme değeri hesaplanmıştır. Ayrıca, bu çalışmadaki model ilk seviye bulanık ilişkileri ele alabildiği gibi, çoklu seviye bulanık ilişkileri de kapsamaktadır. Testlerde literatürde var olan çalışmalar ilgili model ile iki açık veri seti ile karşılaştırılmış olup bahsi geçen modelin daha iyi veya benzer sonuçlar verdiği gözlemlenmiştir. Ayrıca model Covid-19 verileri kullanılarak da test edilmiş ve Uzun-Kısa Süreli Bellek modellerinden daha iyi sonuç vermiştir.Article Citation - WoS: 0MM-FOOD: a high-dimensional index structure for efficiently querying content and concept of multimedia data(Ios Press, 2023) Arslan, Serdar; Arslan, Serdar; Yazici, Adnan; 325411; Bilgisayar MühendisliğiThe semantic query problem is commonly called the semantic gap and is one of the significant problems in multimedia data retrieval. In this study, we focus on multimedia data retrieval by combining semantic information with data content to solve the semantic gap problem effectively. The main idea behind the combination of low-level content descriptors and the concept of multimedia data is to represent the content information with the semantic information by adding a low-level content descriptor as a new dimension to the index structure. This new dimension is represented by constructing an array index structure that uses a fuzzy clustering algorithm. Thus, a new high-dimensional index structure, named MM-FOOD, supporting querying of multimedia data, including fuzzy querying, is presented in this paper. This proposed index structures construction and query algorithms are explained throughout this paper. Our experiments show that our indexing mechanism is considerably efficient compared to the basic indexing approach, which stores low-level content and semantic concept descriptors in separate structures when the data size is large.Article Citation - WoS: 3Citation - Scopus: 5Bitcoin Price Prediction Using Sentiment Analysis and Empirical Mode Decomposition(Springer, 2025) Arslan, S.; Arslan, Serdar; Bilgisayar MühendisliğiCryptocurrencies have garnered significant attention recently due to widespread investments. Additionally, researchers have increasingly turned to social media, particularly in the context of financial markets, to harness its predictive capabilities. Investors rely on platforms like Twitter to analyze investments and detect trends, which can directly impact the future price movements of Bitcoin. Understanding and analyzing Twitter sentiments can potentially provide insights into future Bitcoin price movements and can shed light on how investor sentiment affects cryptocurrency markets. In this study, we explore the correlation between Twitter activity and Bitcoin prices by examining tweets related to Bitcoin price sentiments. Our proposed model consists of two distinct networks. The first network exclusively utilizes historical price data, which is further decomposed into various components using the Empirical Mode Decomposition method. This decomposition helps mitigate the impact of irregular fluctuations on Bitcoin price predictions. Each of these components is then separately processed by Long Short-Term Memory (LSTM) networks. The second network focuses on modeling user sentiments and emotions in conjunction with Bitcoin market data. User opinions are categorized into positive and negative classes and are integrated with historical data to predict the next-day price using LSTM networks. Finally, the outputs of each network are combined to form the ultimate prediction values. Experimental results demonstrate that Twitter sentiment can effectively helps us predict Bitcoin price trends. Furthermore, to validate our proposed model, we compared it with several state-of-the-art methods. The results indicate that our approach outperforms these existing models in terms of accuracy. © The Author(s) 2024.
