Yazar "Seker, Abdulkadir" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • Küçük Resim Yok
    Öğe
    A New Cloud Service for Interpreting Taxi Trajectories via Crowdsensing Approach
    (IEEE, 2018) Seker, Abdulkadir; Guvensan, M. Amac
    In recent years, with the development of IoT, particularly vehicle mobility, a wide range of studies have been conducted on smart city concept. As monitoring a city's traffic conditions have a significant impact on city planning and environmental monitoring. In fact, with the aid of smart systems, it can be both generated mobility maps for cities, and saved gas consumption of vehicles in traffic. This study aims at analyzing the efficient usage of taxis that follow perpetual and non-stationary roads in a city. Following the obtained results, a new cloud-based architecture which enables taxis to find passengers easier via knowledge extracted from the past trips of taxis is designed. The most frequently routes followed by taxis, the starting points of short and long trips, the areas with a high-demand filtered by time/day and the common areas where passengers are get in/drop in, are determined as main parameters in this architecture. The introduced model makes possible to direct taxi drivers worthwhile areas. Meanwhile it will reduce the amount of traffic jam caused by taxis and make it easier for passengers to find a taxi.
  • Küçük Resim Yok
    Öğe
    A novel alignment-free DNA sequence similarity analysis approach based on top-k n-gram match-up
    (Elsevier Science Inc, 2020) Delibas, Emre; Arslan, Ahmet; Seker, Abdulkadir; Diri, Banu
    DNA sequence similarity analysis is an essential task in computational biology and bioinformatics. In nearly all research that explores evolutionary relationships, gene function analysis, protein structure prediction and sequence retrieving, it is necessary to perform similarity calculations. As an alternative to alignment-based sequence comparison methods, which result in high computational cost, alignment-free methods have emerged that calculate similarity by digitizing the sequence in a different space. In this paper, we proposed an alignment-free DNA sequence similarity analysis method based on top-k n-gram matches, with the prediction that common repeating DNA subsections indicate high similarity between DNA sequences. In our method, we determined DNA sequence similarities by measuring similarity among feature vectors created according to top-k n-gram match-up scores without the use of similarity functions. We applied the similarity calculation for three different DNA data sets of different lengths. The phylogenetic relationships revealed by our method show that our trees coincide almost completely with the results of the MEGA software, which is based on sequence alignment. Our findings show that a certain number of frequently recurring common sequence patterns have the power to characterize DNA sequences. (C) 2020 Elsevier Inc. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Determination of Photonuclear Reaction Cross-Sections on Stable P-shell Nuclei by Using Deep Neural Networks
    (Springer, 2023) Akkoyun, Serkan; Kaya, Huseyin; Seker, Abdulkadir; Yesilyurt, Saliha
    Photonuclear reactions are widely used in investigations of nuclear structure. Thus, the determination of the cross-sections are essential for the experimental studies. In the present work, (gamma, n) photonuclear reaction cross-sections for stable p-shell nuclei have been estimated by using the neural network method. The main purpose of this study is to find neural network structures that give the best estimations for the cross-sections, and to compare them with the available data. These comparisons indicate the deep neural network structures that are convenient for this task. Through this procedure, we have found that the shallow NN models, tanh activation function is better than the ReLU. However, as our models become deeper, the difference between tanh and ReLU decreases considerably. In this context, we think that the crucial hyperparameters are the size of the hidden layer and neuron numbers of each layer.
  • Küçük Resim Yok
    Öğe
    DNA Sequence Compression within Traditional Text Compression Algorithms
    (IEEE, 2017) Seker, Abdulkadir; Delibas, Emre; Diri, Banu
    It aimed that traditional text compression methods are using on compression of DNA sequence in this study. It has seen that the random short repeats are vital and it has examined their posivite impact for compression. A pipelined system with multiple algorithms running sequentially for compression. How the contribution of the algorithm to the system was investigated and especially the effect of the BWT on compression was shown. Results show that the pipeline system was found unable to catch the compression success of the Huffman coding alone.
  • Küçük Resim Yok
    Öğe
    Evaluation of Fabric Defect Detection Based on Transfer Learning with Pre-trained AlexNet
    (IEEE, 2018) Seker, Abdulkadir
    Deep learning methods are successful in many different domains such as image, natural language and signal processing. However, the number of samples affects success of deep learning algorithms significantly. Therefore, it is seen as a big challenge to obtain or produce lots of labeled data. A transfer learning method has been proposed to overcome this problem. Transfer learning aimed that using a pre-trained network instead of training it from scratch as the basis for new problem. In this paper, it is looked for a solution to fabric defect detection problem through transfer learning. The sale of defective fabrics damages both producers and customers. Accurate and rapid detection of fabric defects is a crucial problem for the textile industry. Since fabric has the features of unique own textures, it is a matter of curiosity how the transfer learning method will result in determining the fabric defect. In this study, using the AlexNet model trained with millions of images, the success rate of training from stratch to 75% was increased to 98% with transfer learning.
  • Küçük Resim Yok
    Öğe
    Fabric Defect Detection using Deep Learning
    (IEEE, 2016) Seker, Abdulkadir; Peker, Kadir Askin; Yuksek, Ahmet Gurkan; Delibas, Emre
    Fabric defect detection have importance in terms of sectoral quality. Automatic systems are developed on the defect detection, in this regard many methods are tried to obtain high precision with image processing studies. In this study, deep learning which distinguishes with multi-layer architectures and reveals high achievement is applied to fabric defect detection. Autoencoder - a deep learning algorithm-that aimed to represent input data via compression or decompression is tried to detect defect of fabrics and it gains acceptable success. The vital goal of this study is to increase achievement of feature extraction by tuning up the autoencoder's input value and hyper parameters.
  • Küçük Resim Yok
    Öğe
    Open Source Software Development Challenges: A Systematic Literature Review on GitHub
    (IGI Global, 2021) Seker, Abdulkadir; Diri, Banu; Arslan, Halil; Amasyalı, Mehmet Fatih
    GitHub is the most common code hosting and repository service for open-source software (OSS) projects. Thanks to the great variety of features, researchers benefit from GitHub to solve a wide range of OSS development challenges. In this context, the authors thought that was important to conduct a literature review on studies that used GitHub data. To reach these studies, they conducted this literature review based on a GitHub dataset source study instead of a keyword-based search in digital libraries. Since GHTorrent is the most widely known GitHub dataset according to the literature, they considered the studies that cite this dataset for the systematic literature review. In this study, they reviewed the selected 172 studies according to some criteria that used the dataset as a data source. They classified them within the scope of OSS development challenges thanks to the information they extract from the metadata of studies. They put forward some issues about the dataset and they offered the focused and attention-grabbing fields and open challenges that we encourage the researchers to study on them. © 2021 by IGI Global. All rights reserved.