Browsing by Author "Turan C."

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    2D face recognition using PCA and triplet similarity embedding
    (Bulletin of Electrical Engineering and Informatics, 2023) Bazatbekov B.; Turan C.; Kadyrov Sh.; Aitimov A.
    The aim of this study is to propose a new robust face recognition algorithm by combining principal component analysis (PCA), Triplet Similarity Embedding based technique and Projection as a similarity metric at the different stages of the recognition processes. The main idea is to use PCA for feature extraction and dimensionality reduction, then train the triplet similarity embedding to accommodate changes in the facial poses, and finally use orthogonal projection as a similarity metric for classification. We use the open source ORL dataset to conduct the experiments to find the recognition rates of the proposed algorithm and compare them to the performance of one of the very well-known machine learning algorithms k-Nearest Neighbor classifier. Our experimental results show that the proposed model outperforms the kNN. Moreover, when the training set is smaller than the test set, the performance contribution of triplet similarity embedding during the learning phase becomes more visible compared to without it.
  • Thumbnail Image
    ItemOpen Access
    AN EVALUATION OF UNSUPERVISED OUTLIER DETECTION METHODS FOR UNIVARIATE TIME SERIES DATA IN FINANCIAL TRANSACTIONS
    (СДУ хабаршысы - 2023, 2023) Amankossova A.; Turan C.
    Abstract. An essential problem in finance application areas is identifying abnormal subsequences in time series data. Despite the wide range of outlier detection algorithms, no substantial research has been conducted to thoroughly investigate and assess the various methodologies, particularly in the financial industry. This study focuses on comparing and contrasting the outcomes of various unsupervised algorithms. The findings reveal that the Local Outlier Factor technique outperforms the other methods in terms of precision, recall, and Fl-score. The research provides valuable insights for financial institutions and businesses looking to improve their identification of abnormalities systems and highlights the importance of choosing the appropriate unsupervised outlier detection method for financial transaction data. The outcomes of this study can be used to inform future research and development in the area of financial unusual case detection.
  • Thumbnail Image
    ItemOpen Access
    IMPLEMENTATION OF A REAL-TIME ALERT-NOTIFICATION SYSTEM FOR DATA MONITORING IN THE FINANCIAL INDUSTRY
    (СДУ хабаршысы - 2023, 2023) Amankossova A. ; Turan C.
    Abstract. An alert notification system that operates in real-time is crucial for data monitoring, as it enables financial institutions to detect and address possible compliance issues promptly, preventing them from escalating into more significant problems. In the event that there are issues with the data, we may not realise that some parameter values are missing. In such instances, automatic alerts are unquestionably the most effective system. The use of an automated system to notify the responsible parties will benefit any organization's digitalization and reduce the burden on employees who must monitor manually. The article provides an examination and contrast of real-time alert automation techniques implemented through the programming languages of R and Python. The analysis encompasses the problems and limitations of the different methods. This study contributes to the field of automated notifications in the financial industry by evaluating different methods.
  • Thumbnail Image
    ItemOpen Access
    Plagiarism types and detection methods: a systematic survey of algorithms in text analysis
    (Frontiers in Computer Science, 2025) Makhmutova A.; Turan C.; Amirzhanov A.
    Plagiarism in academic and creative writing continues to be a significant challenge, driven by the exponential growth of digital content. This paper presents a systematic survey of various types of plagiarism and the detection algorithms employed in text analysis. We categorize plagiarism into distinct types, including verbatim, paraphrasing, translation, and idea-based plagiarism, discussing the nuances that make detection complex. This survey critically evaluates existing literature, contrasting traditional methods like string-matching with advanced machine learning, natural language processing, and deep learning approaches. We highlight notable works focusing on cross-language plagiarism detection, source code plagiarism, and intrinsic detection techniques, identifying their contributions and limitations. Additionally, this paper explores emerging challenges such as detecting cross-language plagiarism and AI-generated content. By synthesizing the current landscape and emphasizing recent advancements, we aim to guide future research directions and enhance the robustness of plagiarism detection systems across various domains.