Person:
AYRANCI, AHMET AYTUĞ

Profile Picture

Email Address

Birth Date

Research Projects

Organizational Units

Job Title

Arş.Gör.

Last Name

AYRANCI

First Name

AHMET AYTUĞ

Name

Filters

2021 - 20223
Reset filters

Settings

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Publication
    Capacity Loss Analysis Using Machine Learning Regression Algorithms
    (IEEE, 2022) Atay, Sergen; AYRANCI, AHMET AYTUĞ; Erkmen, Burcu
    In this study, time dependent measurements of the power capacitor, which is the main equipment of a compensation unit, are given. The power capacitor is actively working in an industrial facility. Six months of the data from this capacitor were recorded and tests were carried out using Machine Learning (ML) algorithms for its remaining useful life. ML algorithms were selected from the algorithms that used for regression problems. In the study, Support Vector Machine (SVM), Linear Regression (LR) and Regression Trees (RT) algorithms were used. The rated powers of the analyzed capacitor are 50kVAR and 25kVAR from the active plant. The data set was created by running the capacitor continuously for 6 months and the capacity loss was examined with using ML algorithms. The algorithm that gives the best result in the regression analyzes is the LR algorithm. With the results obtained, it is possible to analyze how long the useful life of capacitors with the same characteristics have under the same stress.
  • Thumbnail Image
    Publication
    Speaker Accent Recognition Using MFCC Feature Extraction and Machine Learning Algorithms
    (Marmara Üniversitesi, Fen Bilimleri Enstitüsü, 2021) AYRANCI, AHMET AYTUĞ; Atay, Sergen; Yıldırım, Tülay
    Speech and speaker recognition systems aim to analyze parametric information contained in the human voice and recognize it at the highest possible rate. One of the most important features in the audio signal for the speaker to be recognized successfully by the system is the speaker's accent. Speaker accent recognition systems are based on the analysis of patterns such as the way the speaker speaks and the word choice he uses while speaking. In this study, the data obtained by the MFCC feature extraction technique from voice signals of 367 speakers with 7 different accents were used. The data of 330 speakers in the data set were taken from the "Speaker Accent Recognition" data set in the UC Irvine Machine Learning (ML) open data source. The data of the other 37 speakers were obtained by converting the voice recordings in the "Speaker Accent Archive" data set created by George Mason University into data using the MFCC feature extraction technique. 9 ML classification algorithms were used for the designed speaker accent recognition system. Also, the k-fold cross-validation technique was used to test the data set independently. In this way, the performance of ML algorithms is shown when the data set is divided into a k number of parts. Information about the classification algorithms used in the designed system and the hyperparameter optimizations made in these algorithms are also given. The success performances of the classification algorithms are shown with performance metrics.
  • Thumbnail Image
    Publication
    Decentral Smart Grid Control System Stability Analysis Using Machine Learning
    (Institute of Electrical and Electronics Engineers Inc., 2022) AYRANCI, AHMET AYTUĞ; İlhan, Hacı
    Electrical Grid Systems transmit power produced from various facilities to end-users. Supply and demand must be in balance to achieve secure and stable use in the power grid. To ensure this stability, the amount of electricity fed into the system must always be the same as the amount of demand. High demand makes electrical grid systems' stability more important than ever. Current electrical infrastructures are hard to adapt to these needs. A smart grid system enables two-way electricity flow according to the demand from end-users. Digital communication in smart grid systems enables the system to detect demands, problems, and changes. Also collects information to ensure stability in the system. This study is using the Electrical Grid Stability data set shared at UC Irvine (UCI) Machine Learning repository. Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) Network, K-Nearest Neighbors (K-NN), and Naïve Bayes (NB) Machine Learning (ML) algorithms were used to examine the stability performance of the Smart Grid system. Acquired performance metrics compared using Accuracy, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and F-Score. According to the results obtained, the system and its performance are interpreted. © 2022 IEEE.