Yazar "Dokuz, Yesim" seçeneğine göre listele

Listeleniyor 1 - 8 / 8
  • Küçük Resim Yok
    Öğe
    Anomaly Detection in Region Mobility Utilization Using Daily Taxi Trajectory Dataset
    (Springer International Publishing Ag, 2022) Dokuz, Yesim; Dokuz, Ahmet Sakir
    Anomaly detection in urban big datasets is getting wide attention with the presence of different and various urban big data sources. Urban anomaly detection is an important application area because discovered anomalies in urban areas would provide essential information about urban areas and their utilization, especially human mobility analytics and traffic condition monitoring. In the literature, there are several studies performed for urban anomaly detection using taxi trajectory datasets, such as events detection, regional urban anomaly detection and traffic incident detection. In this study, anomaly detection in regional mobility utilization of daily taxi trajectory datasets is performed based on DBSCAN clustering algorithm. A new algorithm and a threshold value are proposed to detect taxi regions as normal and anomalous for both incoming and outgoing taxi trip records. Experiments are performed on New York taxi trajectory big dataset and the experimental results show that proposed algorithm is efficient on detecting regions as normal or anomalous based on daily taxi trip record counts.
  • Küçük Resim Yok
    Öğe
    Data-driven energy consumption prediction of a university office building using machine learning algorithms
    (Pergamon-Elsevier Science Ltd, 2024) Yesilyurt, Hasan; Dokuz, Yesim; Dokuz, Ahmet Sakir
    Redundant consumption of energy in buildings is an important issue that causes increasing problems of climate change and global warming in the world. Therefore, it is necessary to develop efficient energy management approaches in buildings. Accurate prediction of energy consumption plays an important role to obtain energyefficient buildings. Data-driven methods gained attention for estimation of energy consumption in buildings which would provide more accurate prediction results. In this study, hourly energy consumption prediction is performed on a university office building to increase energy efficiency in the building using machine learning algorithms. A new parameter is proposed, air conditioning demand, to improve accuracy of the algorithms. Moreover, temporal parameters, i.e. day of week, month of year, and hour of day, were used along with meteorological parameters to improve prediction performance of the algorithms. Experimental results show that hourly energy consumption of the building could be predicted using machine learning algorithms with high performance. When the results were analysed, Deep Neural Network (DNN) achieved better performance among other alternative algorithms. The average values of R2, RMSE and MAPE for DNN were 0.959, 4.796 kWh, and 5.738 %, respectively. Also, the addition of proposed air conditioning demand parameter provided improved performance to the algorithms.
  • Küçük Resim Yok
    Öğe
    Discovering popular and persistent tags from YouTube trending video big dataset
    (Springer, 2024) Dokuz, Yesim
    YouTube is the most popular video content platform which provides easy and fast accessibility, huge number of videos, qualified and large number of content producers, and wide range of users. Based on these advantages, YouTube datasets have a big data nature in terms of data analytics. Analyzing YouTube big datasets is essential for discovering user-video relations, video recommendation, semantic analysis of video comments and trending videos analysis. However, YouTube big data analysis has several challenges, such as video content issues, textual and semantic challenges, different metadata information about videos, and big data nature of YouTube datasets. In the literature, several studies are performed for sentiment analysis of YouTube video comments, video recommendation methods, and trending video analyses approaches. In this study, a new method is proposed for popular and persistent tags discovery which uses YouTube trending video dataset of United States for the year of 2021. A new algorithm is proposed, named as Popular and Persistent Tag Discovery algorithm (PPTagD algorithm), which uses proposed method. The proposed algorithm is experimentally evaluated on the dataset. The experimental results show the effectiveness of the proposed algorithm on discovering popular and persistent tags. The results reveal the tendency of United States YouTube users in terms of video tag popularity.
  • Küçük Resim Yok
    Öğe
    Feature-based hybrid strategies for gradient descent optimization in end-to-end speech recognition
    (Springer, 2022) Dokuz, Yesim; Tufekci, Zekeriya
    With the increasing popularity of deep learning, deep learning architectures are being utilized in speech recognition. Deep learning based speech recognition became the state-of-the-art method for speech recognition tasks due to their outstanding performance over other methods. Generally, deep learning architectures are trained with a variant of gradient descent optimization. Mini-batch gradient descent is a variant of gradient descent optimization which updates network parameters after traversing a number of training instances. One limitation of mini-batch gradient descent is the random selection of mini-batch samples from training set. This situation is not preferred in speech recognition which requires training features to collapse all possible variations in speech databases. In this study, to overcome this limitation, hybrid mini-batch sample selection strategies are proposed. The proposed hybrid strategies use gender and accent features of speech databases in a hybrid way to select mini-batch samples when training deep learning architectures. Experimental results justify that using hybrid of gender and accent features is more successful in terms of speech recognition performance than using only one feature. The proposed hybrid mini-batch sample selection strategies would benefit other application areas that have metadata information, including image recognition and machine vision.
  • Küçük Resim Yok
    Öğe
    Mini-batch sample selection strategies for deep learning based speech recognition
    (Elsevier Sci Ltd, 2021) Dokuz, Yesim; Tufekci, Zekeriya
    With the use of deep learning technologies, speech recognition systems gained more success and human-computer interactions became more prevalent. Deep learning based speech recognition systems are getting more attention and are having tremendous success in all areas of speech recognition, such as voice search, mobile communication, and personal digital assistance. However, speech recognition is still challenging due to hardness of adapting new languages, difficulty in handling variations in speech datasets, and overcoming distorting factors. Deep learning systems have the ability to overcome these challenges using high-level abstractions in the datasets by using a deep graph with multiple processing layers using training algorithms, such as gradient descent optimization. In this study, a variant of gradient descent optimization, mini-batch gradient descent is used. We proposed four strategies for selecting mini-batch samples to represent variations of each feature in the dataset for speech recognition tasks to increase model performance of deep learning based speech recognition. For this purpose, gender and accent adjusted strategies are proposed for selecting mini-batch samples. The experiments show that proposed strategies perform better in comparison with standard mini-batch sample selection strategy. (C) 2020 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Spatial prediction of PM10 concentration using machine learning algorithms in Ankara, Turkey
    (Elsevier Sci Ltd, 2020) Bozdag, Asli; Dokuz, Yesim; Gokcek, Oznur Begum
    With the increase in population and industrialization, air pollution has become one of the global problems nowadays. Therefore, air pollutant parameters should be measured at regular intervals, and the necessary measures should be taken by evaluating the results of measurements. In order to prevent air pollution, pollutant parameters must be evaluated within the framework of a model. Recently, in order to obtain objective and more sensitive results with regard to air pollution nowadays, studies, which use machine learning algorithms in artificial intelligence technologies, have been carried out. In this study, PM10 concentrations, which are obtained from 7 stations in Ankara province in Turkey, were trained with machine learning algorithms (LASSO, SVR, RF, kNN, xGBoost, ANN). The PM10 concentrations of the years 2009-2017 of 6 stations in Ankara were given as input, and the PM10 concentrations of the seventh station for the year 2018 were predicted. The model development stage was repeated for each station, and the performance and error rates of the algorithms were determined by comparing the results produced by the algorithms with the actual results. The best results were provided with ANN (R-2 = 0.58, RMSE = 20.8, MAE = 14.4). The spatial distribution of the estimated concentration results was provided through Geographic Information System (GIS), and spatial strategies for improving air pollution over land use were established. (c) 2020 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Time-persistent regions discovery of taxi trajectory big datasets based on regional spatio-temporal velocity
    (Elsevier, 2023) Dokuz, Yesim; Dokuz, Ahmet Sakir
    With the increasing number of residents and motor vehicles in urban areas, traffic-related problems have emerged. Traffic analysis and prediction systems provide in-formation about the city dynamics and traffic estimation on a regional basis. Several studies are performed for traffic analysis and prediction in urban datasets, including taxi trajectory datasets, however, these studies do not focus on regional traffic analysis and time-persistent regions discovery. Time-persistent regions refer to the regions that have a stable utilization and relatively stationary velocity in terms of traffic activities. In this study, a novel method is proposed to discover time-persistent regions based on regional daily velocity values using taxi trajectory big datasets. A new algorithm, namely Time-Persistent Regions Discovery algorithm (TPRD algorithm), is proposed based on the proposed method. The proposed TPRD algorithm is experimentally evaluated on TLC Taxi Trip Records big dataset of New York City and the results show that the proposed algorithm could discover time-persistent regions based on proposed interest measures and threshold values. & COPY; 2023 Elsevier B.V. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Using machine learning algorithms for predicting real estate values in tourism centers
    (Springer, 2023) Alkan, Tansu; Dokuz, Yesim; Ecemis, Alper; Bozdas, Asli; Durduran, S. Savas
    Along with the development of technology in recent years, artificial intelligence (machine learning) techniques that perform operations, such as learning, classification, association, optimization, and prediction, have started to be used on data on real estate according to the criteria affecting the value. Using artificial intelligence (machine learning) techniques, valuation processes are performed objectively and scientifically. In this study, machine learning techniques were employed to balance the real estate market, affected by the tourism sector in Alanya district of Antalya province, Turkey, and examine changes in value objectively and scientifically. First, the criteria affecting the real estate value were determined as structural and spatial, and data on real estate were obtained from the online real estate website. Then, the values of the real estate in the selected application area were predicted using machine learning algorithms (k-nearest neighbors, random forest, and support vector machines). Unlike studies in the literature, algorithm-based valuation using machine learning algorithms was performed instead of mathematical modeling. When analyzed for performance metrics, the best result was achieved with the support vector machines algorithm (0.73). Objective methods should be used to balance the exorbitant differences between real estate values, to regulate market conditions and to carry out a real estate valuation process free from speculative effects in coastal areas where tourism factor is effective. This study indicated the applicability of algorithm-based machine learning techniques in real estate valuation.