Necla Bandirmali Erturk

Dr. Necla Bandirmali Erturk

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
23 April 2024 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
ASAdnan Sondas
Adnan Sondas
NENecla Bandirmali Erturk
Necla Bandirmali Erturk
Increasing data hiding capacity and making it difficult to detect presence of any confidential data in stego images are the key objectives in contemporary image steganography research ever-improving the embedding efficiency. With regard to these crucial and challenging points, a new Multi-Pixel-Pair (MPP)-based data hiding approach is proposed in this paper. It can dynamically increase data embedding capacity of the classical Hybrid Near Maximum Histogram (HNMH) image steganography method while well-maintaining the embedding efficiency. In the proposed MPP approach, the peak value as a reference point in the histogram distribution of a cover image is obtained, and accordingly the pixel-pairs of interest where secret data is to be embedded are determined. Then, the pixels of the cover image are scanned sequentially and data hiding is performed on the relevant pixels by using the Least Significant Bit (LSB) method. In an extensive experimental study of the proposed MPP approach, it is shown that the classical HNMH data hiding capacity is dynamically improved 4.74 to 37.48 times while the Peak Signal to Noise Ratio (PSNR) decreases between 6.62 and 13.75 dB, implying both a reasonable trade-off and 7.61% enhanced embedding efficiency performance. Moreover, using the well-known cover image partitioning technique, offering significant improvements in image steganography, and the proposed MPP approach together, can further extend the data hiding capacity about 7.05%.

1 May 2015
Verified
Conference Paper
Closed access
NENecla Bandirmali Erturk
Necla Bandirmali Erturk
MTMurat Torlak
Murat Torlak
This paper presents a BLUE-based (Best Linear Unbiased Estimator) real-time localization estimation approach using indoor Received Signal Strength Indicator (RSSI) measurements, its Android based mobile application and real experimental results. Location estimation and monitoring have recently become very popular research topics using WiFi networks for indoor environments. Differing from its counterparts in use, this presented approach does not require any calibration or hardware integration, discarding additional system overload and cost as an important contribution. Compared to its classical counterpart Least Square method, it achieves up to two times better location estimation especially for measurement points with none or very small signal received from some of the access points.

16 April 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
CTCeyda Gizem Topal
Ceyda Gizem Topal
OYOsman Yalcin
Osman Yalcin
HTHatice Tetik
Hatice Tetik
MÜMurat Ünal
Murat Ünal
NENecla Bandirmali Erturk
Necla Bandirmali Erturk
CÜCemile Özlem Üçok
Cemile Özlem Üçok
Background/Objectives: Intraoral radiographs acquired using photostimulable phosphor (PSP) plates are inherently susceptible to a wide spectrum of artifacts that can compromise diagnostic reliability and lead to unnecessary repeat exposures. Although structured taxonomies describing these artifacts have been proposed, automated methods capable of detecting and localizing multiple artifact types at the pixel level remain limited, particularly under realistic multi-class conditions. In this study, we address the problem of fine-grained, multi-class PSP artifact segmentation by systematically evaluating a deep learning-based framework and establishing a realistic baseline for this inherently challenging task. Methods: A retrospective, multi-center dataset comprising 1497 intraoral PSP radiographs (bitewing and periapical) collected from three institutions was analyzed. Pixel-level annotations were generated by expert oral and maxillofacial radiologists according to a standardized taxonomy consisting of four major artifact groups and 29 artifact classes, together with a background class. A 2D nnU-Net v2 architecture was employed as a baseline segmentation model. Model development was performed using 5-fold cross-validation, and performance was evaluated on an independent test set using Dice coefficient, Intersection over Union (IoU), Precision, and Recall. Results: Across all classes, the model achieved a mean Dice score of 0.0894 ± 0.0084 in cross-validation and 0.0952 on the independent test set, reflecting the intrinsic complexity of the task. Class-wise analysis revealed substantial variability, with higher performance in larger and visually distinctive artifacts, whereas small-scale, low-contrast, and underrepresented classes exhibited markedly reduced performance. Notably, several artifact categories were absent from the training data, resulting in a zero-shot scenario that directly constrained model generalization. Furthermore, segmentation performance demonstrated a strong dependency on class frequency, measured in terms of pixel distribution, underscoring the impact of severe class imbalance. Group-based evaluation showed relatively higher performance for pre-exposure and exposure-related artifacts compared to post-exposure and scanner-related categories. Conclusions: These findings demonstrate that large-scale, multi-class pixel-level segmentation of PSP artifacts represents a fundamentally challenging problem shaped by the combined effects of class imbalance, small object size, heterogeneous artifact morphology, and incomplete training representation. While the proposed framework confirms the feasibility of automated artifact localization, its current performance suggests greater immediate value as a quality control or screening support tool rather than a fully autonomous diagnostic system. By providing a comprehensive baseline and systematic analysis, this study establishes a benchmark for future research and highlights the critical need for imbalance-aware learning strategies, hierarchical modeling, and data-centric approaches to advance this field.

21 March 2021 in Bitlis Eren Üniversitesi Fen Bilimleri Dergisi
Verified
Journal Article
Closed access
NENecla Bandirmali Erturk
Necla Bandirmali Erturk
Bu makalede mobil uygulama etkileşimli entegre websitesi uygulama paradigması için etkileşimli tasarım, güvenlik ve ölçeklenebilirlik boyutları incelenmektedir. Geleneksel çözümlere kıyasla önemli avantajlara sahip olan bu sistem mimarisi ve yazılımlarıyla, yerel/küresel ağ üzerinden işlem ve iletişim gerektiren bankacılıktan sigortaya, e-ticaretten e-devlete, sağlıktan seyahate, eğitimden askeriyeye kadar tüm sektörler için hayatın her anında ve evresinde yüksek sunucu-istemci başarımı mümkün görülmektedir. Çalışma sonuçları, ciddi kullanıcı ya da anlık işlem sayısı artışlarını da beraberinde getiren mobil uygulamaların değişik isterleri karşılanırken, hem güvenlik hem de ölçeklenebilirlik boyutlarının birlikte ve öncelikle ele alınmasının zorunlu olduğunu göstermektedir.

5 November 2025 in International Journal of Computers Communications & Control
Verified
Journal Article
Open access
PDF file
SASedat Atmaca
Sedat Atmaca
NENecla Bandirmali Erturk
Necla Bandirmali Erturk
Cognitive Radio-based Internet of Things (CR-IoT) is an emerging paradigm that combines the strengths of CR and the IoT to address spectrum scarcity and enhance IoT connectivity. This paper introduces a new Priority-Based Channel Allocation (PBCA) scheme with integrated queueing and dynamic retrial mechanisms for CR-IoT applications. The scheme effectively mitigates connection drops for low priority IoT (IoT-LP) data traffic in the network, where heterogeneous real-time and non-real time nodes opportunistically share licensed spectrum with primary users (PUs). Unlike conventional approaches that often sacrifice low-priority traffic under heavy load, the proposed scheme ensures fair and reliable access while preserving priority for delay-sensitive traffic. Spectrum handoff, connection request queueing, and a new retrial process are jointly employed to enhance quality of service. The system is modeled using a multi-dimensional continuous-time Markov chain and validated through extensive simulations. Results show that the proposed PBCA scheme eliminates connection drops for IoT-LP nodes, increases total channel utilization by up to 4.65%, and reduces connection handoff probability by 50.05% compared with the baseline Random DSA scheme.

5 January 2022 in Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi
Verified
Journal Article
Closed access
PDF file
NENecla Bandirmali Erturk
Necla Bandirmali Erturk
YHYasemin Hocaoğlu
Yasemin Hocaoğlu
A scalable and microservices architecture-based system & specific software for a complete Global Trade - Import/Export Management (GTM) solution is presented in this paper. It has been developed by means of a modular web application approach, containing functionally different tools such as customer management, business process management, accounting & finance management and marketing & sales management components that all can be adapted to any other business sector. It allows for any user/system-required expansion through a cloud-based and flexible modular structure, proposing a framework for commercial solutions. Compared to its classical monolithic-based counterpart, it well offers above 10 times better delay results and remarkably decreases the system blocking ratio.