Yazar "Sert, Onur Can" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Analysis and prediction in sparse and high dimensional text data: The case of Dow Jones stock market
    (Elsevier B.V., 2020) Sert, Onur Can; Şahin, Salih Doruk; Özyer, Tansel; Alhajj, Reda
    In this research, we proposed a text analysis system to predict stock market movements using news and social media data. It is a scalable prediction system for sparse and high dimensional feature sets. Using the developed system, we collected 12,560 articles from New York Times covering one year time period, and 2,854,333 tweets from Twitter covering 4 months time period. We analysed the collected data using entity extraction, sentiment analysis and topic modelling techniques. We applied our feature set creation and elastic net regression based training method. The analyses have been used to train different prediction models. Using these trained prediction models, we predicted stock market movements for Dow Jones Index and showed that the proposed method can make promising predictions. In different sets of experiments, highly accurate (up to 70.90% accuracy) predictions are made by the proposed approach. These predicted values also correlated (up to 0.2315 correlation coefficient value) with real Dow Jones Index values. Further, we report performance comparison results for various prediction models that we trained with different set of features to analyse the importance of time interval and feature space size. Our test results show that it is possible to make reasonable stock movement prediction by integrating news and related social media data, analysing them using named entity extraction, sentiment analysis and topic modelling techniques together with prediction models which use features that are created from these analysis results.
  • Küçük Resim
    Öğe
    Fuzzy classification methods based diagnosis of Parkinson’s disease from speech test cases
    (Bentham Science Publishers, 2019) Dastjerd, Niousha Karimi; Sert, Onur Can; Özyer, Tansel; Alhajj, Reda
    Background: Together with the Alzheimer’s disease, Parkinson’s disease is considered as one of the two serious known neurodegenerative diseases. Physicians find it hard to predict whether a given patient has already developed or is expected to develop the Parkinson’s disease in the future. To overcome this difficulty, it is possible to develop a computing model, which analyzes the data related to a given patient and predicts with acceptable accuracy when he/she is anticipated to develop the Parkinson’s disease. Objectives: This paper contributes an attractive prediction framework based on some machine learning approaches for distinguishing people with Parkinsonism from healthy individuals. Methods: Several fuzzy classifiers such as Inductive Fuzzy Classifier, Fuzzy Rough Classifier and two types of neuro-fuzzy classifiers have been employed. Results: The fuzzy classifiers utilized in this study have been tested using the “Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set” of 40 subjects available on the UCI repository. Conclusion: The results achieved show that FURIA, MLP-Bagging-SGD, genfis2 and scg1 performed the best among the fuzzy rough, WEKA, adaptive neuro-fuzzy and neuro-fuzzy classifiers, respectively. The worst performance belongs to nearest neighborhood, IBK, genfis3 and scg3 among the formerly mentioned classifiers. The results reported in this paper are better in comparison to the results reported in Sakar et al., where the same dataset was used, with utilization of different classifiers. This demonstrates the applicability and effectiveness of the fuzzy classifiers used in this study as compared to the non-fuzzy classifiers used by Sakar et al.