https://hdl.handle.net/20.500.12294/442 Elektrik-Elektronik Mühendisliği Bölümüne ait bildiri ve sunumlar bu koleksiyonda listelenir. Tue, 09 Jun 2026 21:03:06 GMT 2026-06-09T21:03:06Z https://hdl.handle.net/20.500.12294/3899 Analysis of Deep Learning Sequence Models for Short Term Load Forecasting Dağ, Oben; Nefesoğlu, Oğuzhan Short Term Load Forecasting (STLF) is an essential part of generator scheduling in power plants. Better scheduling is crucial for both economic and environmental aspects. In this study, two different deep learning (DL) model architectures based on Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN) were tested and compared on load datasets from Spain and Turkey. In addition, a novel Long Short Term Memory (LSTM) model with embedding layer was proposed and compared with these two models. Optimum model design choices and practices were discussed for achieving reliable and robust results. It was showed that datasets with different characteristics require different model design choices. The simulations of the proposed DL method were carried out with Python and the performance parameters were also presented. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. Sun, 01 Jan 2023 00:00:00 GMT https://hdl.handle.net/20.500.12294/3899 2023-01-01T00:00:00Z https://hdl.handle.net/20.500.12294/3898 Multiband Microstrip Elliptical Monopole Antenna Design with Mushroom-Like Loadings for DCS, 5G and Ku-Band Applications Gürsoy, Gürtay Sezay; Uçar, Mustafa Hikmet Bilgehan In this study, a compact multiband, low-profile and low-cost microstrip antenna design covering DCS (Digital Cellular System, 1.7–1.8 GHz), mid-band 5G and Ku-band has been realized. The proposed monopole antenna consists of an elliptical patch element and mushroom-shaped metallic loadings placed on both sides of this patch. The elliptical patch element operates in the 3.3–3.8 GHz range for the mid-band 5G frequency band alone. In addition, the mushroom-shaped structures used on the front surface of the design enables the antenna to operate in the frequency ranges of 1.72–1.8 GHz DCS and 10–15 GHz Ku-band, as well as the 5G operating frequency. The proposed microstrip line fed antenna is 50 × 40 mm2 in size. The antenna has a bandwidth of 1.71 GHz and a maximum gain of 5.73 dBi at the 5G operating frequency. In addition, the designed antenna has a bandwidth of 80 MHz for the DCS band and 5 GHz for the Ku-band. The simulations of the proposed antenna were carried out in the CST Microwave Studio and the obtained performance parameters are presented in detail. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. Sun, 01 Jan 2023 00:00:00 GMT https://hdl.handle.net/20.500.12294/3898 2023-01-01T00:00:00Z https://hdl.handle.net/20.500.12294/3859 Synthesis of Thermoresponsive Hydrogel for Controlled Release of Quercetin Koca, Elif Isikci; Hatir, Pinar Cakir Thermoresponsive hydrogels are crosslinked hydrophilic polymers that absorb water and change their conformations depending on physiological conditions. As they swell/shrink according to environmental conditions, they are designed as stimuli responsive drug delivery/controlled release systems. Quercetin, with proven beneficial impact on health, is one of the phenolic flavonoids and the most potent antioxidants. In this study, quercetin loaded thermoresponsive hydrogel was synthesized and its release behavior with respect to temperature changes was investigated. Thermoresponsive hydrogels were synthesized via photopolymerization technique. Spectrophotometric measurements at room temperature (25 degrees C) and body temperature (37 degrees C) were performed. It is reported that the designed hydrogel released quercetin from polymer network to the aqueous medium at body temperature. Fri, 01 Jan 2016 00:00:00 GMT https://hdl.handle.net/20.500.12294/3859 2016-01-01T00:00:00Z https://hdl.handle.net/20.500.12294/3261 Spleen segmentation on CT using convolutional neural network Tulum, Gokalp; Aydinli, Bulent; Osman, Onur; Yilmaz, Vural Taner; Ergin, Tuncer; Cuce, Ferhat; Dandin, Ozgur; Kisaoglu, Abdullah; Demiryilmaz, Ismail; Yaprak, Muhittin The automated segmentation systems have been evolving from experimental to clinical applications in radiology. By taking advantage of these, radiologists can increase diagnostic accuracy in their interpretations. In this work we proposed a convolutional neural network based spleen segmentation system. Automatically segmented spleen had an 76.7% sensitivity, 99.8% specificity, 94.7% positive prediction value, 99.9% negative prediction value and 99.8% accuracy. © 2019 IEEE. Tue, 01 Jan 2019 00:00:00 GMT https://hdl.handle.net/20.500.12294/3261 2019-01-01T00:00:00Z