Yazar "Atila, Umit" seçeneğine göre listele

Listeleniyor 1 - 11 / 11
  • Küçük Resim Yok
    Öğe
    Analyzing the performances of evolutionary multi-objective optimizers on design optimization of robot gripper configurations
    (Tubitak Scientific & Technological Research Council Turkey, 2021) Dorterler, Murat; Atila, Umit; Durgut, Rafet; Sahin, Ismail
    Robot grippers are widely used in a variety of areas requiring automation, precision, and safety. The performance of the grippers is directly associated with their design. In this study, four different multiobjective metaheuristic algorithms including particle swarm optimization (MOPSO), artificial algae algorithm (MOAAA), grey wolf optimizer (MOGWO) and nondominated sorting genetic algorithm (NSGA-II) were applied to two different configurations of highly nonlinear and multimodal robot gripper design problem including two objective functions and a certain number of constraints. The first objective is to minimize the difference between minimum and maximum forces for the assumed range in which the gripper ends are displaced. The second objective is force transmission rate that is the ratio of the actuator force to the minimum holding force obtained at the gripper ends. The performance of the optimizers was examined separately for each configuration by using pareto-front curves and hyper-volume (HV) metric. Performances of the optimizers on the specific problem were compared with results of previously proposed algorithms under equal conditions. With respect to these comparisons, the best-known results of the configurations were obtained. Furthermore, the pareto optimal solutions are thoroughly examined to present the relationship between design variables and objective functions.
  • Küçük Resim Yok
    Öğe
    Classification of DNA damages on segmented comet assay images using convolutional neural network
    (Elsevier Ireland Ltd, 2020) Atila, Umit; Baydilli, Yusuf Yargi; Sehirli, Eftal; Turan, Muhammed Kamil
    Background and Objective: Identification and quantification of DNA damage is a very significant subject in biomedical research area which still needs more robust and effective methods. One of the cheapest, easy to use and most successful method for DNA damage analyses is comet assay. In this study, performance of Convolutional Neural Network was examined on quantification of DNA damage using comet assay images and was compared to other methods in the literature. Methods: 796 single comet grayscale images with 170 x 170 resolution labeled by an expert and classified into 4 classes each having approximately 200 samples as G0 (healthy), G1 (poorly defective), G2 (defective) and G3 (very defective) were utilized. 120 samples were used as test dataset and the rest were used in data augmentation process to achieve better performance with training of Convolutional Neural Network. The augmented data having a total of 9995 images belonging to four classes were used as network training data set. Results: The proposed model, which was not dependent to pre-processing parameters of image processing for DNA damage classification, was able to classify comet images into 4 classes with an overall accuracy rate of 96.1%. Conclusions: This paper primarily focuses on features and usage of Convolutional Neural Network as a novel method to classify comet objects on segmented comet assay images. (C) 2019 Elsevier B.V. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Classification of white blood cells using capsule networks
    (Pergamon-Elsevier Science Ltd, 2020) Baydilli, Yusuf Yargi; Atila, Umit
    Background: While the number and structural features of white blood cells (WBC) can provide important information about the health status of human beings, the ratio of sub-types of these cells and the deformations that can be observed serve as a good indicator in the diagnosis process of some diseases. Hence, correct identification and classification of the WBC types is of great importance. In addition, the fact that the diagnostic process that is carried out manually is slow, and the success is directly proportional to the expert's skills makes this problem an excellent field of application for computer-aided diagnostic systems. Unfortunately, both the ethical reasons and the cost of image acquisition process is one of the biggest obstacles to the fact that researchers working with medical images are able to collect enough data to produce a stable model. For that reasons, researchers who want to perform a successful analysis with small data sets using classical machine learning methods need to undergo their data a long and error-prone pre-process, while those using deep learning methods need to increase the data size using augmentation techniques. As a result, there is a need for a model that does not need pre-processing and can perform a successful classification in small data sets. Methods: WBCs were classified under five categories using a small data set via capsule networks, a new deep learning method. We improved the model using many techniques and compared the results with the most known deep learning methods. Results: Both the above-mentioned problems were overcame and higher success rates were obtained compared to other deep learning models. While, convolutional neural networks (CNN) and transfer learning (TL) models suffered from over-fitting, capsule networks learned well training data and achieved a high accuracy on test data (96.86%). Conclusion: In this study, we briefly discussed the abilities of capsule networks in a case study. We showed that capsule networks are a quite successful alternative for deep learning and medical data analysis when the sample size is limited. (C) 2020 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    A comprehensive investigation into the performance of optimization methods in spur gear design
    (Taylor & Francis Ltd, 2020) Atila, Umit; Dorteder, Murat; Durgut, Rafet; Sahin, Ismail
    The design of gears with a minimum weight is an optimization problem that has been widely discussed in the literature. Various recent metaheuristic optimization methods, along with the conventional methods, have produced successful results for design optimization problems. In this study, a comprehensive investigation was conducted into the solution of the spur gear design problem in metaheuristic optimization methods. The artificial algae algorithm, artificial bee colony and whale optimization algorithm were applied to the problem for the first time. The grey wolf optimizer and particle swarm optimization were also applied. The results were compared with the performance of the genetic algorithm, simulating annealing and particle swarm optimization, applied in previous studies. A statistical evaluation of these methods applied under the same conditions was carried out in terms of stability. It was shown that the new methods demonstrated significantly improved performance in solving the gear design problem compared to existing methods.
  • Küçük Resim Yok
    Öğe
    A genetic algorithm approach for finding the shortest driving time on mobile devices
    (Academic Journals, 2011) Karas, Ismail Rakip; Atila, Umit
    Recently, with the increasing interest in using handheld devices, the application of navigation systems that provide driving information to the drivers has become widespread in daily life. An efficient route guidance system should consider the influential factors of traffic flow such as traffic density and allowable velocity limits of the roads. As the number of influential factors and amount of nodes in road network increase, the computational cost increases. On navigation systems, using handheld devices with limited processing speed and memory capacity, it is not feasible to find the exact optimal solution in real-time for the road networks with excessive number of nodes using deterministic methods such as Dijkstra algorithm. This paper proposes a Genetic Algorithm approach applied to a route guidance system to find the shortest driving time. Constant length chromosomes have been used for encoding the problem. It was found that the mutation operator proposed in this algorithm provided great contribution to achieve optimum solution by maintaining the genetic diversity. The efficiency of the genetic algorithm was tested by applying it on the networks with different sizes.
  • Küçük Resim Yok
    Öğe
    Integration of CityGML and Oracle Spatial for implementing 3D network analysis solutions and routing simulation within 3D-GIS environment
    (Taylor & Francis Ltd, 2013) Atila, Umit; Karas, Ismail Rakip; Abdul-Rahman, Alias
    3D navigation within a 3D-GIS environment is increasingly getting more popular and spreading to various fields. In the last decade, especially after the 9/11 disaster, evacuating the complex and tall buildings of today in case of emergency has been an important research area for scientists. Most of the current navigation systems are still in the 2D environment and that is insufficient to visualize 3D objects and to obtain satisfactory solutions for the 3D environment. Therefore, there is currently still a lack of implementation of 3D network analysis and navigation for indoor spaces in respect to evacuation. The objective of this paper is to investigate and implement 3D visualization and navigation techniques and solutions for indoor spaces within 3D-GIS. For realizing this, we have proposed a GIS implementation that is capable of carrying out 3D visualization of a building model stored in the CityGML format and perform analysis on a network model stored in Oracle Spatial. The proposed GUI also provides routing simulation on the calculated shortest paths with voice commands and visual instructions.
  • Küçük Resim Yok
    Öğe
    A Knowledge Based Decision Support System: 3D GIS Implementation for Indoor Visualisation and Routing Simulation
    (Univ Utari Malaysia-Uum, 2014) Atila, Umit; Karas, Ismail Rakip; Rahman, Alias Abdul
    In this study, a knowledge management based Decision Support System has been suggested. By collecting the data of people, event and properties of building, a 3D navigation system has been developed to support building management and users during the extraordinary circumtances. Most of the current navigation systems are still in the 2D environment and that is insufficient to visualize 3D objects and to obtain satisfactory solutions for the 3D environment. Therefore, there is currently still a lack of implementation of 3D network analysis and navigation for indoor spaces in respect to evacuation. 3D navigation within a 3D-GIS environment (Three Dimensional Geographical Information Systems) is increasingly getting more popular and spreading to various fields. In the last decade, especially after the 9/11 disaster; evacuating the complex and tall buildings of today in case of emergency has been an important research area for scientists. The objective of this paper is to implement 3D visualization and navigation techniques and solutions for indoor spaces within 3D-GIS. For realizing this, we have proposed a GIS implementation that is capable of carrying out 3D visualization of a building model stored in the CityGML format and perform analysis on a network model stored in Oracle Spatial. The proposed GUI also provides routing simulation on the calculated shortest paths with voice commands and visual instructions.
  • Küçük Resim Yok
    Öğe
    Learn from one data set to classify all - A multi-target domain adaptation approach for white blood cell classification
    (Elsevier Ireland Ltd, 2020) Baydilli, Yusuf Yargi; Atila, Umit; Elen, Abdullah
    Background and objective: Traditional machine learning methods assume that both training and test data come from the same distribution. In this way, it becomes possible to achieve high successes when modelling on the same domain. Unfortunately, in real-world problems, direct transfer between domains is adversely affected due to differences in the data collection process and the internal dynamics of the data. In order to cope with such drawbacks, researchers use a method called domain adaptation, which enables the successful transfer of information learned in one domain to other domains. In this study, a model that can be used in the classification of white blood cells (WBC) and is not affected by domain differences was proposed. Methods: Only one data set was used as source domain, and an adaptation process was created that made possible the learned knowledge to be used effectively in other domains (multi-target domain adaptation). While constructing the model, we employed data augmentation, data generation and fine-tuning processes, respectively. Results: The proposed model has been able to extract domain-invariant features and achieved high success rates in the tests performed on nine different data sets. Multi-target domain adaptation accuracy was measured as %98.09. Conclusions: At the end of the study, it has been observed that the proposed model ignores the domain differences and it can adapt in a successful way to target domains. In this way, it becomes possible to classify unlabeled samples rapidly by using only a few number of labeled ones. (C) 2020 Elsevier B.V. All rights reserved.
  • Küçük Resim Yok
    Öğe
    A novel data clustering algorithm based on gravity center methodology
    (Pergamon-Elsevier Science Ltd, 2020) Kuwil, Farag Hamed; Atila, Umit; Abu-Issa, Radwan; Murtagh, Fionn
    The concept of clustering is to separate clusters based on the similarity which is greater within cluster than among clusters. The similarity consists of two principles, namely, connectivity and cohesion. However, in partitional clustering, while some algorithms such as K-means and K-medians divides the dataset points according to the first principle (connectivity) based on centroid clusters without any regard to the second principle (cohesion), some others like K-medoids partially consider cohesion in addition to connectivity. This prevents to discover clusters with convex shape and results are affected negatively by outliers. In this paper a new Gravity Center Clustering (GCC) algorithm is proposed which depends on critical distance (lambda) to define threshold among clusters. The algorithm falls under partition clustering and is based on gravity center which is a point within cluster that verifies both the connectivity and cohesion in determining the similarity of each point in the dataset. Therefore, the proposed algorithm deals with any shape of data better than K-means, K-medians and K-medoids. Furthermore, GCC algorithm does not need any parameters beforehand to perform clustering but can help user improving the control over clustering results and deal with overlapping and outliers providing two coefficients and an indicator. In this study, 22 experiments are conducted using different types of synthetic, and real healthcare datasets. The results show that the proposed algorithm satisfies the concept of clustering and provides great flexibility to get the optimal solution especially since clustering is considered as an optimization problem. (C) 2020 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Plant leaf disease classification using EfficientNet deep learning model
    (Elsevier, 2021) Atila, Umit; Ucar, Murat; Akyol, Kemal; Ucar, Emine
    Most plant diseases show visible symptoms, and the technique which is accepted today is that an experienced plant pathologist diagnoses the disease through optical observation of infected plant leaves. The fact that the disease diagnosis process is slow to perform manually and another fact that the success of the diagnosis is proportional to the pathologist's capabilities makes this problem an excellent application area for computer aided diagnostic systems. Instead of classical machine learning methods, in which manual feature extraction should be flawless to achieve successful results, there is a need for a model that does not need pre-processing and can perform a successful classification. In this study, EfficientNet deep learning architecture was proposed in plant leaf disease classification and the performance of this model was compared with other state-of-the-art deep learning models. The PlantVillage dataset was used to train models. All the models were trained with original and augmented datasets having 55,448 and 61,486 images, respectively. EfficientNet architecture and other deep learning models were trained using transfer learning approach. In the transfer learning, all layers of the models were set to be trainable. The results obtained in the test dataset showed that B5 and B4 models of EfficientNet architecture achieved the highest values compared to other deep learning models in original and augmented datasets with 99.91% and 99.97% respectively for accuracy and 98.42% and 99.39% respectively for precision.
  • Küçük Resim Yok
    Öğe
    SmartEscape: A Mobile Smart Individual Fire Evacuation System Based on 3D Spatial Model
    (Mdpi, 2018) Atila, Umit; Ortakci, Yasin; Ozacar, Kasim; Demiral, Emrullah; Karas, Ismail Rakip
    We propose SmartEscape, a real-time, dynamic, intelligent and user-specific evacuation system with a mobile interface for emergency cases such as fire. Unlike past work, we explore dynamically changing conditions and calculate a personal route for an evacuee by considering his/her individual features. SmartEscape, which is fast, low-cost, low resource-consuming and mobile supported, collects various environmental sensory data and takes evacuees' individual features into account, uses an artificial neural network (ANN) to calculate personal usage risk of each link in the building, eliminates the risky ones, and calculates an optimum escape route under existing circumstances. Then, our system guides the evacuee to the exit through the calculated route with vocal and visual instructions on the smartphone. While the position of the evacuee is detected by RFID (Radio-Frequency Identification) technology, the changing environmental conditions are measured by the various sensors in the building. Our ANN (Artificial Neural Network) predicts dynamically changing risk states of all links according to changing environmental conditions. Results show that SmartEscape, with its 98.1% accuracy for predicting risk levels of links for each individual evacuee in a building, is capable of evacuating a great number of people simultaneously, through the shortest and the safest route.