OSOmer Galip Saracoglu

Omer Galip Saracoglu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Omer Galip Saracoglu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Continuous UV level estimation using photochromic PLA surfaces: A transformer-based heterogeneous deep ensemble approach

    by Eşref Erdoğan, Serkan Keser, Sekip Esat Hayber, Omer Galip Saracoglu

    This study presents a high-precision, continuous machine vision system for estimating ultraviolet (UV) radiation levels using low-cost, 3D-printable polylactic acid-based photochromic material (PLA-PCM) surfaces. Filament color transitions under different UV intensities were recorded at eight ambient color temperatures, and a zero-padding spatial arrangement protocol was applied to the 252×56 images that underwent color changes to extract stable temporal features. The methodology employs a deep transformer encoder (DTE) with multi-head self-attention (MSA), computing global temporal dependencies in parallel within 222 milliseconds and ensuring edge-AI compatibility. Multi-spectral feature vectors from the RGB, HSV, and CIELAB color spaces, augmented with ambient color temperature and DCT components, were constructed for 59,000 frames derived from 236 video sessions at 10 Hz. A strict zero-data-leakage protocol was enforced through video-level holdout and stratified temporal splits. Each fold equally represented the fast-onset and slow-decay phases of the photochromic reaction within a five-fold cross-validation. The resulting transformer-based heterogeneous deep ensemble (T-HDE), integrating Transformer, SVR, CatBoost, LightGBM, ExtraTrees, and MLP regressors with Nelder-Mead optimized weights, achieved R 2 = 0.9938 on the held-out test set with a homoscedastic error distribution, indicating that prediction accuracy remains equally reliable across low and high UV exposure levels. In single-frame snapshot mode, R 2 = 0.9811 was attained, confirming that even without temporal sequence information, the zero-padding-based spatial features alone provide robust UV estimation. These findings demonstrate that PLA-PCM surfaces, coupled with the T-HDE architecture, can serve as precise, continuous, and cost-effective UV dosimeters for IoT-based environmental monitoring and edge-AI sensing platforms.

  • Open Access

    Distance-Aware Optimization of Fractional Bandwidth in SOA-Based Photonic UWB Systems Across the S-, C-, and L-Bands

    by M. Filiz, O. G. Saracoglu

    This study investigates distance-dependent optimization of fractional bandwidth (FBW) while ensuring compliance with the Federal Communications Commission (FCC) spectral mask in a semiconductor optical amplifier (SOA)-based photonic ultra-wideband (UWB) pulse generation system. Fiber lengths of 40, 80, and 100 km across the S-, C-, and L-bands are analyzed to evaluate distance-induced spectral variations. FBW is adopted as the primary optimization metric, while FCC mask compliance is considered as a regulatory constraint. The simulation results demonstrate high spectral efficiency, with FBW values ranging from 88–100% in the S-band, 92–100% in the C-band, and 96–100% in the L-band. Although FBW gradually decreases with increasing fiber length due to nonlinear SOA dynamics and fiber dispersion, the level of degradation is strongly band-dependent. In particular, the L-band exhibits superior long-distance robustness, maintaining near-maximum FBW values (96–97%) even at a fiber length of 100 km, whereas the S-band shows higher sensitivity to propagation distance. The C-band provides balanced intermediate performance. Accordingly, this study provides a practical framework for distance-aware band selection in long-distance UWB-over-fiber communication systems.

  • An innovative application of CNN-based real-time temperature monitoring in electronics using thermochromic PLA

    by Egemen Nazife Yazlık, Ömer Galip Saraçoğlu

    The growing demand for more powerful electronic equipment forces the operator to use active control systems such as temperature monitoring. Real-time temperature monitoring is critical for ensuring the longevity and operational reliability of electronic components. This study presents a contactless, cost-effective, and user-independent monitoring system. In an innovative approach, thermochromic Polylactic Acid (PLA) is utilized as a passive temperature sensor. The proposed methodology employs a Convolutional Neural Network (CNN) to determine the temperature gradients of a Gigabyte GA-EQ45M-S2 motherboard and an Intel Core 2 Duo E8500 processor. Experimental results demonstrate that the system achieves 96% accuracy in image-based temperature detection. Measurements were compared with data obtained from a thermal camera and an infrared (IR) thermometer to validate the proposed method, under the same conditions. The findings suggest that this CNN-based system provides a viable, low-cost alternative to expensive thermal imaging equipment and traditional sensors for electronic component real-time temperature monitoring.

  • Open Access

    Performance Analysis of SOA and BPF Integration for S-, C-, and L-Band Photonic UWB Pulse Generation

    by Meryem Filiz, Ömer Galip Saraçoğlu

    In this study, a simulation-based investigation of the variations of the bit error rate (BER) and the maximum quality factor are presented for short- (S-), conventional- (C-), and long- (L-) band wavelengths in a photonic ultra-wideband (UWB) circuit using a semiconductor optical amplifier (SOA) with different bias currents and a bandpass filter (BPF). Gaussian quadruplet UWB pulses are generated at the S-, C-, and L-band wavelengths, which are commonly used in fiber transmission lines. An analysis of the temporal and spectral features of the generated pulses is carried out. The highest maximum quality factor and the lowest minimum BER are obtained in the C-band at an SOA bias current of 150 mA. This study simultaneously investigates both UWB pulse generation and transmission performance. The proposed circuit has a simple design and high applicability, as it employs a SOA, a Gaussian optical filter, a low-pass filter (LPF) and a single BPF.

  • A Novel Method for UV Measurement Using PLA-Based Photochromic Material and Machine Learning Models

    by Eşref Erdoğan, Şekip Esat Hayber, Ömer Galip Saraçoğlu

    A new method has been developed that can accurately measure the relationship between color change under ultraviolet (UV) light and the amount of UV using a mobile phone camera to observe the color changes of a polylactic acid-based photochromic material (PLA-PM). Videos of the color change of the PLA-PM were recorded using a mobile phone camera. The obtained data were used for machine learning, and the amount of UV light causing the color change was predicted using machine learning models. The target variable in the models is the voltage values read from the UV sensor via Arduino. Data set preparations process different high-resolution and fps images through six image processing stages. Image processing stages end with the normalization of values for the final image’s three-color space channels. This work, which enhances traditional colorimetric measurements with artificial intelligence technologies, demonstrates potential applicability in studies such as UV index measurement, medical measurements, and UV-sensitive textile products. The study experimentally shows the feasibility of measuring UV with mobile phones without relying on expensive devices.


  • The Experimental Validation of Designed Fiber Optic Pressure Sensors With EPDM Diaphragm

    by Sekip Esat Hayber, Umut Aydemir, Timucin Emre Tabaru, Omer Galip Saracoglu

    This study focused on the experimental validation of diaphragm-based Fabry-Perot fiber optic pressure sensors (D-FP-FOPS) with ethylene propylene diene terpolymers (EPDM) diaphragm as designed and analyzed sensor tip theoretically. We also used self-adhesive EPDM rubber as a diaphragm for the first time in the literature. Analytical calculation and finite element method (FEM) analysis were carried out to obtain values of fundamental resonance frequency (f0) and deflection (d) with diaphragm specific values of Young’s modulus and Poisson’s ratio measured by tensile tests. We produced D-FP-FOPS tip with EPDM diaphragm and obtained experimental f0 between 250-400 Hz from extended signal to noise ratio (SNR) plot which figured out with the help of theoretical values of f0. We also analyzed minimum detectable pressure (MDP) mapping which is used to confirm SNR mapping for D-FP-FOPS. We noticed that our sensor could be operated up to 1.6 Pa pressure which confirms the mechanical limit given in the literature. Before production of D-FP-FOPS, a pioneering way which includes design, analytical calculation, FEM analysis, and experimental validation was demonstrated as a novel. Moreover, since we used self-adhesive EPDM tape as a diaphragm material, our sensor tip cost is less than 50whichcapabletocompetewithcommercialsensors.


  • A Simple, High Sensitive Fiber Optic Microphone Based on Cellulose Triacetate Diaphragm

    by Sekip Esat Hayber, Timucin Emre Tabaru, Serkan Keser, Omer Galip Saracoglu

    We present a high sensitive Fiber-Optic Microphone (FOM) with a wide measuring range based on a cellulose triacetate diaphragm in this work. The average Signal to Noise Ratio (SNR) of the proposed FOM is measured 50.86 dB in at the frequency range of 100 Hz-20 kHz. In the same spectrum range, the highest SNR for the 2 kHz frequency under 103.16 mPa acoustic pressure is measured at 72.20 dB with 2 Hz resolution bandwidth, which corresponds to a noise-limited minimum detectable acoustic pressure level of 17.91 μPa/ $\sqrt$ Hz. The proposed sensor has advantages of high sensitivity, low cost, and easy fabrication. According to the assessments based on the obtained results, the FOM can be used for medical spectroscopy, imaging applications and for long-distance listening and voice recognition in the military-public security.


  • Open Access

    Bent Fiber Sensor for Preservative Detection in Milk

    by Omer Galip Saracoglu, Sekip Esat Hayber

    A fiber optic sensor sensitive to refractive index changes of the outer region of the fiber cladding is presented. The sensor uses bent plastic optical fibers in different bending lengths to increase sensitivity. Measurements were made for low-fat milk, the refractive index of which is altered by some preservatives such as formaldehyde, hydrogen peroxide, and sodium carbonate. Concentrations of the preservatives in the milk were changed between 0% and 14.3% while the refractive indices occurred between 1.34550 and 1.35093 for the minimum (0%) and maximum (14.286%) concentrations of sodium carbonate, respectively. Due to bending-induced sensitivity, the sensor is able to detect refractive index changes less of than 0.4%. The results show that there is excellent linearity between the concentration and normalized response of the sensor.


  • Open Access

    Color Regeneration from Reflective Color Sensor Using an Artificial Intelligent Technique

    by Ömer Galip Saracoglu, Hayriye Altural

    A low-cost optical sensor based on reflective color sensing is presented. Artificial neural network models are used to improve the color regeneration from the sensor signals. Analog voltages of the sensor are successfully converted to RGB colors. The artificial intelligent models presented in this work enable color regeneration from analog outputs of the color sensor. Besides, inverse modeling supported by an intelligent technique enables the sensor probe for use of a colorimetric sensor that relates color changes to analog voltages.