Yazar "Bulut, Faruk" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    Data-Driven Analysis of Short- and Long-Term Outcomes of Simulation, Nasal Hump Reduction, and Rasping in Open Rhinoplasty for Nasal Dorsum Correction
    (SAGE PUBLICATIONS INC, 2025) Bulut, Fuat; Bulut, Faruk
    Purpose: This study aims to highlight the significance of performing simulations, nasal hump reduction, and rasping in open-technique rhinoplasty for the nasal dorsum. The research utilizes data science methodologies for a thorough examination of the collected survey data.Methods: A comprehensive survey comprising 29 questions was presented to surgeons participating in the Eastern Trakya ENT Association Training Meetings-I. This survey, specifically designed to investigate the nuances of open and closed rhinoplasty approaches to nasal dorsum intervention, collected responses from 132 physicians. The collected dataset was thoroughly reviewed and analyzed. The responses were not only graphically represented but also transformed into a dataset primed for data science analysis. Significant results were derived using both association rule-mining algorithms from machine learning and basic statistical analysis.Results: The raw data underwent thorough analysis using fundamental statistical methods and association rules within the field of data science. The discerned data patterns revealed significant insights into the behavioral tendencies and approaches adopted by physicians in rhinoplasty. The survey analysis emphasized the widespread acceptance of the open technique for nasal dorsum procedures, even though it may not be the preferred choice for all rhinoplasty cases. A notable 74.6% of rhinoplasty surgeons employing the open technique indicated that the primary long-term challenge during nasal dorsum interventions was irregularity. In addition, among the 132 participating surgeons, 25.8% were found to frequently engage in facial plastic surgery, while 55.4% reported abstaining from simulations. Notably, rhinoplasty surgeons who opted out of simulations, despite exclusively applying the open technique, reported encountering irregularities and requiring more adjustments.Conclusion: Rhinoplasty surgeons who do not use simulations in open nasal dorsum approaches reported facing irregularities and performing more revisions. Furthermore, they noted encountering irregularities in both the short and long term following nasal hump reduction and rasping procedures.
  • [ X ]
    Öğe
    Enhancement of eye socket recognition performance using inverse histogram fusion images and the Gabor transform
    (Wiley, 2025) Shehu, Harisu Abdullahi; Ince, Ibrahim Furkan; Bulut, Faruk
    The eye socket is a cavity in the skull that encloses the eyeball and its surrounding muscles. It has unique shapes in individuals. This study proposes a new recognition method that relies on the eye socket shape and region. This method involves the utilization of an inverse histogram fusion image to generate Gabor features from the identified eye socket regions. These Gabor features are subsequently transformed into Gabor images and employed for recognition by utilizing both traditional methods and deep-learning models. Four distinct benchmark datasets (Flickr30, BioID, Masked AT & T, and CK+) were used to evaluate the method's performance. These datasets encompass a range of perspectives, including variations in eye shape, covering, and angles. Experimental results and comparative studies indicate that the proposed method achieved a significantly (p<0.001) higher accuracy (average value greater than 92.18%) than that of the relevant identity recognition method and state-of-the-art deep networks (average value less than 78%). We conclude that this improved generalization has significant implications for advancing the methodologies employed for identity recognition.
  • [ X ]
    Öğe
    MACHINE LEARNING FOR ENHANCED CLASSROOM HOMOGENEITY IN PRIMARY EDUCATION
    (2024) Bulut, Faruk; Donmez, Ilknur; Ince, Ibrahim Furkan; Petrov, Pavel
    A homogeneous distribution of students in a class is accepted as a key factor for overall success in primary education. A class of students with similar attributes normally increases academic success. It is also a fact that general academic success might be lower in some classes where students have different intelligence and academic levels. In this study, a class distribution model is proposed by using some data science algorithms over a small number of students’ dataset. With unsupervised and semi supervised learning methods in machine learning and data mining, a group of students is equally distributed to classes, taking into account some criteria. This model divides a group of students into clusters by the considering students’ different qualitative and quantitative characteristics. A draft study is carried out by predicting the effectiveness and efficiency of the presented approaches. In addition, some process elements such as quantitative and qualitative characteristics of a student, data acquisition style, digitalization of attributes, and creating a future prediction are also included in this study. Satisfactory and promising experimental results are received using a set of algorithms over collected datasets for classroom scenarios. As expected, a clear and concrete evaluation between balanced and unbalanced class distributions cannot be performed since these two scenarios for the class distributions cannot be applicable at the same time.