NAİM KARASEKRETER

Dr. NAİM KARASEKRETER

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2013 in Journal of Experimental & Theoretical Artificial Intelligence
Verified
Journal Article
Closed access
NKNAİM KARASEKRETER
NAİM KARASEKRETER
FBFatih Başçiftçi
Fatih Başçiftçi
UFUğur Fidan
Uğur Fidan
This study used artificial neural networks (ANNs) to propose a new system of irrigation ratios and time intervals. Data on soil moisture, soil type, product type and time interval were used as input parameters for the ANN and the network was trained through the Levenberg–Marquardt learning algorithm. The outputs of the model determined the water requirement of the plant and the irrigation time intervals. The aim of this study is to perform irrigation at night, to reduce water losses from evaporation and thereby promote water conservation. In addition, the study aimed to save on energy, as less irrigation would be provided compared to daytime irrigation. The system was tested in a strawberry orchard of 1000 m2 in the Serik district of Antalya, Turkey. The trial achieved a 20.46% water saving and 23.9% energy saving.

1 September 2020 in Emerging Materials Research
Verified
Journal Article
Closed access
NKNAİM KARASEKRETER
NAİM KARASEKRETER
Mehmet Akif ŞahmanMehmet Akif Şahman
Mehmet Akif Şahman
FBFatih Başçiftçi
Fatih Başçiftçi
UFUğur Fidan
Uğur Fidan
Wireless sensors (nodes) are devices with built-in batteries, sensors and communication units. Wireless sensor networks (WSNs) are structures that are formed by multiple nodes coming together to transmit the data they collect from each other to the base station. Significant work has been done on WSNs in recent years. One of the important issues that these studies have focused on is increasing the energy efficiency of the nodes forming the network and ensuring their survival for a longer time. In this paper, two-dimensional particle swarm optimization (PSO) is proposed to solve the problem of clustering in WSNs by inspiration from PSO modified by Fan to solve discrete problems such as the traveling salesman problem. The proposed algorithm was analyzed comparatively with the low-energy adaptive clustering hierarchy (Leach) protocol. As a result, an improvement of 4% compared with Leach was achieved in terms of the amount of energy left in the network. The data packets sent in 20 rounds increased by 2000 packets compared to Leach, and a 27% improvement was achieved. In addition, the number of surviving nodes increased by 22%.

1 September 2020 in Emerging Materials Research
Verified
Journal Article
Closed access
NKNAİM KARASEKRETER
NAİM KARASEKRETER
UFUğur Fidan
Uğur Fidan
FBFatih Başçiftçi
Fatih Başçiftçi
In this study, a new center-oriented clustering (CCP) algorithm that provides self-clustering of a network by using a method similar to the center-biased clustering method of the k-means algorithm is presented and differs from the literature in this respect. The proposed algorithm is compared with low-energy adaptive clustering hierarchy (Leach) because it uses similar techniques, as it aims to self-organize irregularly distributed networks. In the experimental study, CCP and Leach algorithms were run in randomly generated network models and the algorithms were compared in terms of the total amount of energy remaining in the network and the number of surviving nodes. The algorithms were run on 15 different wireless sensor network (WSN) models, each of which was irregularly distributed with 100 nodes, and the amount of energy remaining in the network after each trial was recorded and averaged. As a result, it was observed that the energy in the network was 9.4% more efficient in the CCP algorithm. In addition, when the number of surviving nodes was considered, it was observed that an average of 28.3 nodes in the CCP algorithm and 18 nodes in the Leach algorithm survived.

30 May 2025 in Epilepsy Research
Verified
Journal Article
Closed access
ÖAÖzkan Aslan
Özkan Aslan
NKNAİM KARASEKRETER
NAİM KARASEKRETER
CBCaner BALIM
Caner BALIM
SYSuleyman Yaman
Suleyman Yaman
SŞSüleyman Şahin
Süleyman Şahin

28 October 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
SYSuleyman Yaman
Suleyman Yaman
NKNAİM KARASEKRETER
NAİM KARASEKRETER
RÇRabia ÇELİKÖZ
Rabia ÇELİKÖZ
EÖEsra Özgül
Esra Özgül
HGHasan Güler
Hasan Güler
Background/Objectives: Multiple sclerosis (MS) is a chronic demyelinating disease of the central nervous system, and magnetic resonance imaging (MRI) plays a central role in its diagnosis and monitoring. Because different MRI sequences provide complementary information about MS-related pathology, jointly exploiting multiple sequences may improve automated classification. However, many existing automated MS classification studies rely on limited sequence information, are not consistently evaluated under subject-independent protocols, and are constrained by the scarcity of publicly available multi-sequence datasets organized at the subject level. Methods: To address these gaps, we collected and publicly released a new multi-sequence brain MRI dataset and proposed DenseGated-MSNet, a novel end-to-end multi-input deep learning model for MS versus non-MS classification. DenseGated-MSNet processes each co-acquired MRI sequence in parallel through an independent sequence-specific DenseNet-121 branch and integrates the resulting representations through a proposed input-dependent gated feature-level fusion mechanism. Under a strict subject-independent evaluation protocol, the model configuration was determined on a subject-independent development set, and the performance of the final model was internally evaluated using five-fold subject-independent cross-validation on the same cohort at the image and subject levels. Results: In internal five-fold subject-independent cross-validation, DenseGated-MSNet achieved a pooled subject-level accuracy of 90.57% (95% CI: 86.44–93.53%) and an AUC of 0.947 (95% CI: 0.918–0.976). The learned gate values also provided sequence-level modulation information, indicating how strongly each MRI sequence was weighted during multi-sequence integration. Conclusions: Overall, these findings suggest that DenseGated-MSNet can effectively integrate complementary information from multiple MRI sequences for discriminating established MS from selected non-MS controls, while providing sequence-level modulation information. Together with the released dataset, the proposed framework provides a reproducible basis for future subject-independent MS classification studies.

15 September 2026 in Black Sea Journal of Engineering and Science
Verified
Journal Article
Closed access
NKNAİM KARASEKRETER
NAİM KARASEKRETER
CBCaner BALIM
Caner BALIM
ÖAÖzkan Aslan
Özkan Aslan
In this study, harmful content detection in Turkish texts is addressed as a three-class text classification problem comprising Harmless, Profanity and Sexist Discourse. For this purpose, open-access Turkish datasets and data compiled within the scope of the TÜBİTAK 1001 project were combined, and after removing cross-source duplicates and conflicting duplicates, a final dataset of 12051 texts was used. In the experimental process, traditional machine learning models and Transformer-based language models were compared under the same dataset, the same class structure and a 5-fold group-based stratified cross-validation protocol. For the traditional models, in addition to word- and character-level TF-IDF representations, Word2Vec- and FastText-based representations were used to evaluate Linear SVM, Logistic Regression, Decision Tree, Random Forest, Extra Trees and XGBoost algorithms. For the Transformer-based models, BERTurk, Electra-TR, ConvBERTurk and XLM-RoBERTa were adapted to the three-class classification task. Among the traditional models, the highest performance was obtained with Logistic Regression on TF-IDF representations (82.82% macro F1-score); Linear SVM produced very close results, while FastText- and Word2Vec-based representations remained comparatively lower. The obtained results showed that Transformer-based models offer higher and more balanced performance than traditional machine learning models. Among all models, the highest success was achieved with the ConvBERTurk model, which reached a 90.93% macro F1-score, 90.93% accuracy and a 98.09% ROC-AUC value. The BERTurk model exhibited a performance very close to ConvBERTurk with a 90.28% macro F1-score. A paired t-test over the five folds shows that this difference is not statistically significant (t(4) = 2.36, P=0.078). These findings indicate that contextual language representations are effective in Turkish harmful content classification. The study contributes to the literature by addressing Turkish harmful content detection as a multi-class problem that also includes the distinction between profanity and sexist discourse, and by comparing traditional models and Transformer-based models under the same leakage-controlled experimental protocol.