Murat Ekici

Dr. Murat Ekici

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
21 December 2022 in Drones
Verified
Journal Article
Open access
PDF file
MEMurat Ekici
Murat Ekici
ASAhmet Çağdaş Seçkin
Ahmet Çağdaş Seçkin
AÖAhmet Özek
Ahmet Özek
CKCeyhun Karpuz
Ceyhun Karpuz
The use of robotic systems in logistics has increased the importance of precise positioning, especially in warehouses. The paper presents a system that uses virtual fiducial markers to accurately predict the position of a drone in a warehouse and count items on the rack. A warehouse scenario is created in the simulation environment to determine the success rate of positioning. A total of 27 racks are lined up in the warehouse and in the center of the space, and a 6 × 6 ArUco type fiducial marker is used on each rack. The position of the vehicle is predicted by supervised learning. The inputs are the virtual fiducial marker features from the drone. The output data are the cartesian position and yaw angle. All input and output data required for supervised learning in the simulation environment were collected along different random routes. An image processing algorithm was prepared by making use of fiducial markers to perform rack counting after the positioning process. Among the regression algorithms used, the AdaBoost algorithm showed the highest performance. The R2 values obtained in the position prediction were 0.991 for the x-axis, 0.976 for the y-axis, 0.979 for the z-axis, and 0.816 for the γ-angle rotation.

13 September 2026 in Pamukkale University Journal of Engineering Sciences
Verified
Journal Article
Open access
MEMurat Ekici
Murat Ekici
Context—Global navigation satellite system signals are strongly attenuated indoors, where multipath, non-line-of-sight propagation, device heterogeneity, and changing occupancy limit outdoor positioning methods. The diversity of indoor technologies and inconsistent accuracy metrics also complicate direct, application-oriented comparison.Objective—This structured narrative review connects measurement observables, estimation algorithms, protocol capabilities, validation design, artificial intelligence, governance, and life-cycle requirements to an auditable technology-selection decision.Method—IEEE Xplore, the ACM Digital Library, ScienceDirect, SpringerLink, Web of Science, and Scopus were searched together with official ISO/IEC, IEEE, Bluetooth SIG, 3GPP, ETSI, CEPT, and national regulatory documents. The search was updated on 22 July 2026. The final evidence map comprised 103 unique sources prioritized as recent reviews, standards and official technical documents, and representative experiments.Results—Received signal strength, channel state information, time-of-flight, round-trip time, time-difference-of-arrival, and angle measurements support proximity, geometric estimation, fingerprinting, and sensor fusion. Performance depends on hardware, anchor geometry, calibration, line-of-sight ratio, and test design. Wi-Fi and Bluetooth commonly provide environment-dependent metre-level positioning or robust room/zone awareness, whereas ultra-wideband can reach centimetre-to-decimetre accuracy in favourable deployments. Visible-light, acoustic, geomagnetic, artificial-magnetic, and device-free systems add complementary capabilities but also introduce visibility, reverberation, map-maintenance, privacy, or hardware constraints. Learning-based methods can improve nonlinear mapping and NLOS mitigation, but packet-random or same-session validation may overstate generalizability.Conclusion—No technology is universally superior. Selection should use output type, error percentiles, coverage, latency, update rate, device model, environment, maintenance, cybersecurity, privacy, and life-cycle cost, followed by a context-matched site pilot. Hybrid systems are preferable when continuity and reliability are more important than isolated laboratory accuracy.

30 December 2021 in European Neuropsychopharmacology
Verified
Journal Article
Closed access
DCDeniz Ceylan
Deniz Ceylan
FÖF. Özel
F. Özel
BVB. Verim
B. Verim
İKİ. Kalaycı
İ. Kalaycı
MEMurat Ekici
Murat Ekici
AÖA. Özerdem
A. Özerdem

20 October 2026
Verified
Book
Closed access
EÜEmir Üşenmezsoylu
Emir Üşenmezsoylu
FHFatma HEPSAĞ
Fatma HEPSAĞ
MEMurat Ekici
Murat Ekici
TATolga Akcan
Tolga Akcan
ZKZeynep Gürbüz Kaçan
Zeynep Gürbüz Kaçan
RSRıdvan Saraçoğlu
Rıdvan Saraçoğlu
Gıda mühendisliği, yapay zekâ ve veri temelli teknolojilerin etkisiyle yeni bir dönüşüm sürecinden geçiyor. Karmaşık verilerin analizinden üretim süreçlerinin modellenmesine, gıda güvenliğinin değerlendirilmesinden yenilikçi ürün ve ambalaj tasarımına kadar uzanan bu dönüşüm, gıda endüstrisinin geleceğini şekillendiren önemli fırsatlar sunuyor. Yapay Zekâ Destekli Gıda Mühendisliği, yapay zekânın gıda bilimi ve mühendisliğindeki kullanım alanlarını kapsamlı ve disiplinler arası bir bakış açısıyla ele alıyor. Spektroskopik ve kemometrik verilerin analizinden makine öğrenmesi tabanlı proses modellemeye; gıda güvenliği ve risk değerlendirmesinden yer fıstığında oksidasyon ve depolama koşullarının incelenmesine kadar farklı uygulamaları bir araya getiriyor. Eser ayrıca yapay zekânın fonksiyonel gıda geliştirme, biyoaktif bileşen seçimi, formülasyon optimizasyonu ve kişiselleştirilmiş beslenmedeki rolünü inceliyor. Nanoteknolojiyle bütünleştirilmiş akıllı ambalaj sistemleri, elektronik burun uygulamaları ve ambalaj tasarımının görsel ve göstergebilimsel analiziyle teknolojik dönüşümün farklı boyutlarını ortaya koyuyor. Geleneksel gıda mühendisliği yaklaşımlarını yenilikçi dijital çözümlerle buluşturan bu kitap; akademisyenler, araştırmacılar, lisansüstü öğrenciler ve gıda sektöründeki profesyoneller için güncel bir başvuru kaynağı olmayı amaçlıyor. Gıdanın geleceğini anlamak, veriyi anlamakla başlar. Yapay zekâ ise bu veriyi bilgiye ve daha bilinçli kararlara dönüştürmenin yeni yollarını sunar.

27 April 2026 in Biosensors
Verified
Journal Article
Open access
PDF file
ASAhmet Çağdaş Seçkin
Ahmet Çağdaş Seçkin
MEMurat Ekici
Murat Ekici
TATolga Akcan
Tolga Akcan
FSFatih Soygazi
Fatih Soygazi
HDHabibe Gürsoy Demir
Habibe Gürsoy Demir
In this study, a low-cost AS7265x-based multispectral electronic tongue system was developed for estimating milk composition and adulteration indicators and supported with an explainable artificial intelligence (XAI) framework. Experimental analyses were conducted on 190 augmented commercial milk samples, where fat, protein, solids-not-fat (SNF), density, freezing point, and added water ratio were treated as target variables. Sensor data were modeled as RAW, DERIVED, and FUSION feature sets, and regression performance was compared using Random Forest, Gradient Boosting, AdaBoost, KNN, and XGBoost. Model validation was carried out with both five-fold cross-validation and Leave-One-Out (LOO) strategies to assess field-level generalizability. Results showed that a narrow-band, low-cost optical sensor platform can estimate not only fat and protein but also SNF, density, and freezing point with high accuracy. Within the XAI framework, permutation-based importance analysis and SHAP were used to identify critical spectral bands for each target parameter, enabling data-driven recommendations for band-oriented sensor design optimization. The study presents a scalable methodology that integrates low-cost sensor design, multi-parameter quality estimation, and explainable modeling beyond traditional fat–protein-focused approaches. Across all six targets, the XAI analysis consistently identified the near-infrared channel at 860 nm (asIR_3) as the most informative band, reflecting the combined effect of water absorption and Mie scattering by fat globules; the visible channel at 680 nm (asVIS_4) emerged as a secondary band, reflecting dissolved-matter scattering. These bands are therefore the natural starting point for cost-reduced versions of the sensor. Among the compared feature sets (RAW, DERIVED, FUSION), the 18-band RAW configuration provided the most balanced performance across all six targets.

28 December 2025 in International Journal of 3D Printing Technologies and Digital Industry
Verified
Journal Article
Open access
HÖHüseyin Öztürksoy
Hüseyin Öztürksoy
AÖAhmet Özek
Ahmet Özek
MEMurat Ekici
Murat Ekici
ASAhmet Çağdaş Seçkin
Ahmet Çağdaş Seçkin
This paper presents a smart insole that combines flexible TPU optical fiber sensors with force-sensitive resistors (FSRs) on a 3D-printed TPU base to estimate plantar forces during walking. Three thermoplastic polyurethane optical fibers, illuminated by red lasers and read by light-dependent resistors, were routed in a non-anatomical, irregular (‘random’) layout and compared against six FSR channels taken as reference targets. Signals were sampled and streamed via an ESP32 microcontroller over Bluetooth. Using a sliding-window approach (20 samples), simple statistical features from the three optical channels were used to train supervised regressors—Gradient Boosting, Adaptive Boosting, and a shallow artificial neural network—to predict each FSR output. Across sensors, models achieved R² between 0.865 and 0.951 and mean absolute error (MAE) between 29.0 and 48.9. Adaptive Boosting gave the lowest average MAE and stable R², while the artificial neural network reached the highest R² for several regions. Results show that accurate force estimation is possible without anatomically precise sensor placement, reducing hardware complexity and cost while keeping performance suitable for gait analysis and wearable health applications.