Browsing by Author "Unluturk, Mehmet S."

Now showing 1 - 6 of 6

Citation - WoS: 2
Citation - Scopus: 6
A robotic system to prepare IV solutions
(Elsevier Ireland Ltd, 2018) Mehmet Suleyman Ünlütürk; Özgür Tamer; Semih Utku; Unluturk, Mehmet S.; Tamer, Ozgur; Utku, Semih
Drugs need to be used regularly and correctly in order to be effective. When medicines are used correctly negativities that threaten human health and life can be avoided but they can cause unwanted situations that can occur until the end of life when they are used incorrectly. The most common drug administration errors in hospitals are: The wrong dosage of the drug given to the patient the timing and / or the method of administration the wrong drug given to the patient the drug given to the wrong patient or even not given. Furthermore the information about the drug that is administered to the patient may not be registered at all. In this research a robotic drug preparation system and a communication server accepting prescription orders have been developed. Component engineering methodology is further utilized in the design of the Drug Preparation System to maximize reuse increase product reliability reduce design code and test efforts. The IV Robotic Drug Preparation Robot is composed of a robotic work station and a Cartesian carrier to carry the work station to the desired location. The robotic work station has several grippers to handle syringes to pull the piston of the syringe and to lock the closed system connector to the vial. The IV Robotic Drug Preparation System and communication server are developed and being used in the hospitals. Due to this system medicines left unused in vials can be used and a great amount of savings is obtained from the drug purchases. © 2018 Elsevier B.V. All rights reserved.
Automated Detection and Quantification of Honey Adulteration Using Thermal Imaging and Convolutional Neural Networks
(Pergamon-Elsevier Science Ltd, 2026) Unluturk, Mehmet S.; Unluturk, Sevcan; Berk, Berkay
Honey is a valuable natural food rich in bioactive substances beneficial to health. Despite strict regulations prohibiting adulteration, honey remains one of the most frequently adulterated foods, often with low-cost commercial syrups. Conventional detection methods require expensive instruments, expert operators, and lengthy analysis times, limiting their practical use. This study introduces a rapid and automated method for detecting and quantifying honey adulteration using thermal image analysis combined with a tailored Convolutional Neural Network (CNN) architecture. Thirty-six pure honey samples (blossom and honeydew) from different regions of Türkiye were adulterated with inverted sugar, maltose, and glucose syrups at varying levels (3 %-60 % weight/weight (w/w)). Samples were heated to 60 degrees C and thermal images were captured during cooling using a custom image-capturing unit. The CNN model employed a multi-layer structure, starting with a shallow network for binary classification (pure vs adulterated honey) achieving 100 % accuracy, followed by specialized deeper CNN regressors to quantify adulterant levels with mean squared errors of 0.0003, 0.001, and 0.0002 for glucose, maltose, and inverted sugar, respectively. This layered CNN approach leverages thermal patterns linked to adulteration, enabling sensitive, rapid, and non-destructive quality control. Furthermore, the method is integrated into a user-friendly hardware-software system called Compact Adulteration Testing Cabinet on Honey (CATCH), requiring no specialized expertise, demonstrating strong potential for automated honey authenticity verification in practical settings.
Citation - WoS: 4
Citation - Scopus: 4
Classification of organic and conventional olives using convolutional neural networks
(Springer Science and Business Media Deutschland GmbH, 2021) Mehmet Suleyman Ünlütürk; Seçil Küçükyaşar; Fikret Pazir; Unluturk, Mehmet S.; Pazir, Fikret; Kucukyasar, Secil
This paper presents a convolutional neural network (CNN) to classify between the conventionally and organically cultivated Memecik varieties of green olives. The image forming method called the rising paper chromatography is utilized in preparing the images of Memecik varieties of green olives for CNN. In the rising chromatography method 20 30 and 40% sample concentrations were determined as the suitable concentrations for both organic and conventional olives. The concentrations of AgNO3 and FeSO4 were determined as 0.25 0.5 0.75 and 1% for both conventional and organic samples. The visual differences used for differentiation of different types of Memecik green olives are usually determined according to the regional color differences the vivid color occurrence the width and the frequency of bowl occurrence the thin line and the picks at drop zone by the expert assessors. The testing results in this study verified the effectiveness of the CNN methodology in differentiating between the organically and conventionally cultivated Memecik green olives. The newly designed neural network achieved 100% accuracy. Furthermore this high accuracy achieved by CNN might suggest that it can be effectively used in place of the expert assessors. © 2021 Elsevier B.V. All rights reserved.
Citation - WoS: 5
Citation - Scopus: 5
Fluence (UV dose) distribution assessment of UV-C light at 254 nm on food surfaces using radiochromic film dosimetry integrated with image processing and convolutional neural network (CNN)
(Elsevier Ltd, 2023) Yadigar Seyfi Cankal; Mehmet Suleyman Ünlütürk; Sevcan Mehmet Unluturk; Cankal, Yadigar Seyfi; Unluturk, Mehmet S.; Unluturk, Sevcan
Uniform Fluence (UV Dose) distribution on food surfaces is essential for an effective UV process design. In this study the use of radiochromic films (RCFs) with a computer vision system (CVS) integrating image processing and Convolutional Neural Network (CNN) is proposed as an alternative method to assess Fluence distribution of UV-C light at 254 nm on food surfaces. The color difference of RCFs exposed to different UV irradiance and exposure times was correlated with Fluence. The validity of the developed methodology was proved by applying it to the surface of apple fruits of different shapes and sizes. A linear relationship was found between the color difference of RCF and Fluence. The maximum Fluence to be determined using RCFs was ∼60 mJ/cm2. The color of the films after UV irradiation remained stable for up to 15 days in darkness when stored at room and refrigeration temperatures. The results showed that RCF can be used as an alternative UV dosimeter. © 2023 Elsevier B.V. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 1
GPR Raw-Data Analysis to Detect Crack Using Order Statistic Filtering
(AMER SOC TESTING MATERIALS, 2016) Gokhan Kilic; Mehmet S. Unluturk; Unluturk, Mehmet S.; Kilic, Gokhan
Ground penetrating radar (GPR) uses data collected with the aid of electromagnetic waves transmitted into a structure by antenna to assess and monitor the structural health of many different kinds of civil infrastructure. With GPR technology promoting their system with promises of the achievement of in excess of 1000 sample points per scan this research demonstrated on the basis of the Nyquist theorem that 256 sample points per scan provided equally reliable inspection results. Furthermore 256 sample points per scan GPR data were further analyzed by order statistic filtering with neural networks to locate cracks within concrete materials. The results showed that the neural network order statistic filters are effective in their use of detecting cracks in noisy environments using 256 sample points per scan GPR data.
Citation - WoS: 6
Citation - Scopus: 6
Wavelet Analysis With Different Frequency GPR Antennas for Bridge Health Assessment
(AMER SOC TESTING MATERIALS, 2016) Gokhan Kilic; Mehmet S. Unluturk; Unluturk, Mehmet S.; Kilic, Gokhan
This study presents an examination and a presentation of ground-penetrating radar (GPR) on a heavily used high-speed railway bridge in Turkey. This study also considers GPR mapping using two different antennas (2 GHz and 500 MHz) and their reliability in terms of locating subsurface features such as rebar (lower and upper reinforcement) and the presence of moisture. Moreover GPR interesting results in terms of the structural crack locations by detecting discontinuities and breakdowns in the wavelets' travel with the incorporation of wavelet analysis into the process of the collected raw data of the highspeed railway bridge under survey. This study promotes the GPR and the wavelet analyses in the health monitoring and assessment of bridge structures. By increasing insight into the kinds of structural deterioration that can occur in structures such as high-speed railway bridges this study also has implications for the process of tool selection in structural inspection. The wavelet analysis can be used as an effective tool in analyzing and presenting the results of the GPR survey.