-
Fakülteler10
-
Bilgisayar Mühendisliği Bölümü9
-
Mühendislik Fakültesi9
-
Bilgisayar Bilimleri Anabilim Dalı8
-
Bilgisayar Donanımı Anabilim Dalı8
-
Bilgisayar Mühendisliği8
-
Bilgisayar Yazılımı Anabilim Dalı8
-
Klinik Bilimler Bölümü1
-
Ağız Diş ve Çene Radyolojisi Anabilim Dalı1
-
Diş Hekimliği Fakültesi1
-
Deep learning1
-
K-means1
-
MRI1
-
Residual network+Melanoma detection+Lesion segmentation+Deep CNN+Batch mode+Oversampling strategies1
-
Support vector machine+Ensemble of classifiers+Kernel learning+K-means clustering+Class imbalance+Logistic regression1
-
Text Mining+Unbalanced Dataset+Classifiers+Nace1
-
Thresholding algorithms1
-
YOLOv8 state-of-the-art networks+ hyperparameter optimization+agricultural images+object detection1
-
Yapay zeka1
-
derin öğrenme;anlamsal bölütleme1
-
APPLIED SCIENCES-BASEL1
-
BMC Oral Health1
-
Biomedical Signal Processing and Control1
-
ICONTECH INTERNATIONAL JOURNAL1
-
Information Sciences1
-
International Journal of Business Intelligence and Data Mining1
-
International Journal of Computational Science and Engineering1
-
Journal of Engineering Science and Technology1
Evaluation of YOLOv8 Model Series with HOP for Object Detection in Complex Agriculture Domains
Bektaş, Jale
In recent years, many studies have been conducted in-depth investigating YOLO Models for object detection in the field of agriculture. For this reason, this study focused on four datasets containing different agricultural scenarios, and 20 dif-ferent trainings were carried out with the objectives of understanding the detec-tion capabilities of YOLOv8 and HPO (optimization of hyperparameters). While Weed/Crop and Pineapple datasets reached the most accurate measurements with YOLOv8n in mAP score of 0.8507 and 0.9466 respectively, the prominent model for Grapes and Pear datasets was YOLOv8l in mAP score of 0.6510 and 0.9641. This situation shows that multiple-species or in different developmental stages of a single species object YOLO training highlights YOLOv8n, while only object detection ...
Integrating a novel SRCRN network for segmentation with representative batch-mode experiments for detecting melanoma
Bektaş, Jale | Bektaş, Yasin | Kangal, Evrim Ersin
Melanoma is a type of skin cancer that tends to spread to other parts of the body and can be fatal if not detected at an early stage. This paper proposes an automated and non-invasive methodology to assist clinicians to detect melanoma. A two-stage framework was suggested in the study. In the first stage, the Resnet 50-based novel SRCRN Network was designed, which extracts high-dimensional distinctive features for skin lesion segmentation, and uses the advantage of stride regulation effectively. In the framework of SRCRN, pixel maps of different sizes were obtained by upsampling and downsampling methods between block layers, and the performance of segmentation was improved by selecting the most appropriate pixel map. In the second stage, the Resnet-50 network was used again for melanoma de...
Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
Bektaş, Jale
Numerous methods have been proposed for semantic segmentation and the state-of-the-art part is likely to be incorporated by deep learning-based methods which show a salient performance. This study addresses the challenge of semantic segmentation in low-contrast imbalanced under water images. Moreover, it employs nine model fusions as a downstream workflow task using encoder–decoder architectures with Dice Loss and Focal Loss training focusing on the imbalance data. Afterwards, the most effective two encoder–decoder fusion models, Res34+Unet and VGG19+FPN, by 0.592%, 0.590% mIoU on average and by 0.510%, 0.491% F1-score yielded better performance, respectively, than other models. Using a weight-optimization algorithm, the ensemble model with recreated IoU results improves the accuracy for b...
Enhanced diagnostic pipeline for maxillary sinus-maxillary molars relationships: a novel implementation of Detectron2 with faster R-CNN R50 FPN 3x on CBCT images
özemre,mehmet özgür | Bektaş, Jale | yanık,hüseyin | baysal,lütfiye
Background The anatomical relationship between the maxillary sinus and maxillary molars is critical for planning dental procedures such as tooth extraction, implant placement and periodontal surgery. Methods This study presents a novel artificial intelligence-based approach for the detection and classification of these anatomical relationships in cone beam computed tomography (CBCT) images. The model, developed using advanced image recognition technology, can automatically detect the relationship between the maxillary sinus and adjacent molars with high accuracy. Results The artificial intelligence algorithm used in our study provided faster and more consistent results compared to traditional manual evaluations, reaching 89% accuracy in the classification of anatomical structures....
Optimisations of four imputation frameworks for performance exploring based on decision tree algorithms in big data analysis problems
Bektaş, Jale
The phenomenon of how to treat missing values is a problem confronted in big data analysis. Therefore, various applications have been developed on imputation strategies. This study focused on four imputation frameworks proposing novel perspectives based on expectation-maximisation (EM), self-organising map (SOM), K-means and multilayer perceptron (MLP). Initially, several transformation steps such as normalised, standardised, interquartile range and wavelet were applied. Then, imputed datasets were analysed using decision tree algorithms (DTAs) by optimising their parameters. These analyses showed that DTAs had not been strikingly affected by any data transformation techniques except interquartile range. Even though the dataset contains a missing value ratio of 33.73%, the EM imputation fr...
EKSL: An effective novel dynamic ensemble model for unbalanced datasets based on LR and SVM hyperplane-distances
Bektaş, Jale
Unbalanced data is considered in many real-world classification problems, where it is often costly in practice to sample and establish a homogeneous class distribution for a minority class. The choice of methods, diversity of datasets used for structuring, and the correct kernel decision are quite decisive in the success of the system. This study develops a powerful classifier algorithm that provides an alternative solution to kernel experiments with the choice of a general-purpose, fast, automatic linear kernel. Principally based on SVM, k-means clustering in partitions is used, and logistic regression is integrated into the ensemble system. To increase the success rate and deal with the maximum convergence problem, the soft margin value of the standard SVM is changed in an adaptive struc...
EVALUATING THE EFFECT OF LESION SEGMENTATION ON THE DETECTION OF SKIN CANCER BY PRE-TRAINED CNN MODELS
Bektaş, Jale | Bektaş, Yasin | Kangal, Evrim Ersin
Early diagnosis of melanoma, which is considered to be one of the deadliest skin cancers, via medical imaging can significantly improve the course of the disease. However, expert assessments are subjective and open to errors due to large variations in dermoscopy images. To cope with this problem, a two-stage framework is proposed for the detection of melanoma in dermoscopic images. Firstly, by eliminating the presence of natural structures such as veins or hair and the variations in the pattern region, segmented images are obtained from raw image data with the help of pixel-wise image processing techniques. The second part of this framework is the recognition stage of the skin lesions by Pre-Trained Deep Networks (PTN). By using segmented input images, the PTN classifiers are optimized wit...
Segmentation of brain region of MRIs and omparisons between autistic and healthy adolescent
Bektaş, Jale
One of the most important subject in the processing MR image is segmentation, especially extraction of the brain regions, which is part of the decision of urgent operation on brain.This type medical operations need speed up process with maximum accuracy. In this study, brain is segmented by using k-means algorithm. A combination of global, adaptive thresholding techniques and at the next stage morphological operations were used for preprocessing. Moreover after this stage the main aim was setting out in the regional different of specified brain disorders to detect autism disease. Neuroimages which belong to 5 female patients in 17 years old who are diagnosed with autism and 10 female adolescents averaging 17 years old who have Typical Development were used. The parameters were slices consi...
A unified workflow strategy for analysing large-scale TripAdvisor reviews with BOW model
Bektaş, Jale
Nowadays, firms need to transform customer online reviews data properly into information to achieve goals such as having a competitive edge and improving the quality of service. This paper presents a unified workflow to solve the problems of analysing large-scale data with 710,450 reviews for 1,134 hotels by using text mining methods among the different touristic regions of Turkey. Firstly, a star schema dimensional data mart is built that includes one fact table and two dimensional tables. Then, a series of text mining processes which includes data cleaning, tokenisation, and analysis are applied. Text mining is implemented through standard BOW and the extended BON model. The results show significant findings through this workflow. We propose to build a dimensional model dataset before pe...
An Overview of the Classification Problem in Unbalanced Datasets Using the Statistical Construction of European Community Economic Activities
Bektaş, Jale | Bektaş, Yasin
The use of classical classifiers in unbalanced and multi-class data sets has always been a problem. In this study, a text mining work has been applied with well-known classifiers on the definitions of Statistical Construction of Economic Activities (NACE) codes in the European Community. In the study, first of all, the application was made on the unbalanced structure of the original data, then the performance measurement was performed by retesting the result data by making it balanced by weighting on a class basis. Common classifiers such as Decision Trees, Naiv Bayes, Support Vector Machines, Diametric Based Functions and Random Forest algorithms were used in the tests. The study showed us that as a result of data balancing of Decision Trees, the F-score value increased from 17.43% to 92%...