Filters

2016 - 201912020 - 20251
Reset filters

Settings

Subject: Data Mining

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Conference Object
    ANALYSIS OF NEUROONCOLOGICAL DATA TO PREDICT SUCCESS OF OPERATION THROUGH CLASSIFICATION
    (Assoc Computing Machinery, 2016) Bagherzadi, Negin; Borcek, Alp Ozgun; Tokdemir, Gul; Cagiltay, Nergiz; Maras, H. Hakan
    Data mining algorithms have been applied in various fields of medicine to get insights about diagnosis and treatment of certain diseases. This gives rise to more research on personalized medicine as patient data can be utilized to predict outcomes of certain treatment procedures. Accordingly, this study aims to create a model to provide decision support for surgeons in Neurooncology surgery. For this purpose, we have analyzed clinical pathology records of Neurooncology patients through various classification algorithms, namely Support Vector Machine, Multi Perceptron and Naive Bayes methods, and compared their performances with the aim of predicting surgery complication. A large number of factors have been considered to classify and predict percentage of patient's complication in surgery. Some of the factors found to be predictive were age, sex, clinical presentation, previous surgery type etc. For classification models built up using Support Vector Machine, Naive Bayes and Multi Perceptron, Classification trials for Support Vector Machine have shown %77.47 generalization accuracy, which was established by 5-fold cross-validation.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 1
    A Hybrid Data-Driven and Fuzzy MCDM Approach for Employee Selection
    (Institute of Electrical and Electronics Engineers Inc., 2025) Sadeghzadeh, K.; Bahreini, P.; Kao, Y.-L.; Yilmaz, I.; Erdebilli, B.; Aghsami, A.; Bahrini, A.
    Employee selection, a cornerstone of human resource management, critically shapes organizational performance and long-term effectiveness. While traditional approaches primarily rely on expert-based evaluations, this study proposes a novel hybrid framework that integrates Multi-Criteria Decision-Making methods with data mining techniques to reduce the dimensionality of the number of criteria or variables considered. By integrating backward regression with fuzzy Multi-Criteria Decision-Making methods, our framework reduces model complexity and captures criteria interdependencies, while fuzzy logic addresses ambiguity in expert judgment, a gap often overlooked in prior research. The methodology first uses backward regression modeling with the employee attrition rate as the response variable to identify core criteria. Subsequently, the fuzzy Decision-Making Trial and Evaluation Laboratory analyzes interrelationships between criteria, followed by the fuzzy Analytic Network Process for weighting criteria and ranking candidates. We validate our approach using real-world recruitment data - including expert interview scores and historical attrition - from a company specializing in electronic attendance systems. The AI-generated rankings are benchmarked against these expert-based evaluations to assess alignment with human judgment. Initially, 17 criteria were systematically reduced to 11 core factors, resulting in a streamlined yet robust evaluation system. Our findings emphasize that 'Time-of-service,' 'Requested-wage,' 'Teamwork,' and 'Leadership' are the most critical criteria influencing effective IT personnel selection. © 2025 IEEE.