166 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 166
Yayın Reviewing the effects of spatial features on price prediction for real estate market: Istanbul case(IEEE, 2022-09-16) Ecevit, Mert İlhan; Erdem, Zeki; Dağ, HasanIn the real estate market, spatial features play a crucial role in determining property appraisals and prices. When spatial features are considered, classification techniques have been rarely studied compared to regression, which is commonly used for price prediction. This study reviews spatial features' effects on predicting the house price ranges for real estate in Istanbul, Turkey, in the classification context. Spatial features are generated and extracted by geocoding the address information from the original data set. This geocoding and feature extraction is another challenge in this research. The experiments compare the performance of Decision Trees (DT), Random Forests (RF), and Logistic Regression (LR) classifier models on the data set with and without spatial features. The prediction models are evaluated based on classification metrics such as accuracy, precision, recall, and F1-Score. We additionally examine the ROC curve of each classifier. The test results show that the RF model outperforms the DT and LR models. It is observed that spatial features, when incorporated with non-spatial features, significantly improve the prediction performance of the models for the house price ranges. It is considered that the results can contribute to making decisions more accurately for the appraisal in the real estate industry.Yayın Optimum torque distribution during regenerative braking in a fully electrical vehicle via dynamic programming(IEEE, 2023-10-28) Ergün, Ömer; Çaycı, N. Okan; Dinçmen, Erkin; İstif, İlyasIn electric vehicles, it is important to maximize their regenerative braking performances for obtaining longer driving distances. In this study, for an electric vehicle having motors on the front and rear axles, an optimum torque distribution algorithm based on dynamic programming method is proposed for maximizing the regenerative braking energy. Electric motor limits, efficiency maps, battery model and braking force constraints given in the European regulations are considered in the proposed algorithm. The dynamic programming algorithm code and simulation studies for different braking scenarios are carried out via MATLAB. Simulation studies show that via the proposed torque distribution algorithm, significant improvements in the regenerated braking energy are obtained with respect to the fixed-rate torque distribution algorithm.Yayın Comparative performance evaluation of VLC, LTE and WLAN technologies in indoor environments(IEEE, 2021-05-24) Zeshan, Arooba; Karbalayghareh, Mehdi; Miramirkhani, Farshad; Uysal, Murat; Baykaş, TunçerRecent years have seen an exponential rise in the demand for indoor wireless connections that have driven future generation networks to aim for higher data rates with extended coverage and affordable rates. The two most prominent technologies for providing indoor wireless connections, WLAN and LTE, have their limitations and they can not coexist in a single band to form heterogeneous networks (HetNets). Visible light communication (VLC) has seen rapid growth in recent years as it has the capability to seamlessly merge with the existing technologies and provide wireless connections with high data rates. VLC based hybrid indoor network effectively combines the preferences of an end-user with the practicality of implementation. In this work, we investigate specific VLC/WLAN and VLC/LTE hybrid scenarios to perform a detailed analysis on the effect of user mobility on the performance of the system and how the performance of the network (in terms of throughput) can be maximized. The study aims to show how different technologies complement each other in the best and even the worst-case scenarios.Yayın GIS aided vulnerability assessment for roads(Springer Science and Business Media B.V., 2022-04-21) Çalışkan, Berna; Atahan, Ali Osman; Kesten, Ali SercanRoad networks are vulnerable to natural disasters such as floods, earthquakes and forest fires which can adversely affect the travel on the network. However, not all road links equally affect the travel conditions in a given network; typically some links are more critical to the network functioning than the others. The first stage of study involves the investigation of geological conditions. Image classification used for extracting information classes from ‘Geological Map of Istanbul area’ image file. The resulting raster layer used to create thematic map. A reclassification was performed for lithologic types. The second stage involves analyzing topological situation. A slope map prepared and classified according to percentage of slope values. The third phase is the analysis and interpretation of the accumulated data to establish suitable and applicable road vulnerability scores. The information in the source data for each vulnerability factor are classified into three different vulnerability scores: +2 (considerably increases vulnerability), +1 (increases vulnerability) and 0 (does not increase vulnerability) by using a vulnerability score table. The study area was categorized into three different traffic analysis zones as: (1) least favorable area; (2) favorable area; (3) most favorable area. Vulnerability values obtained to measure serviceability of critical links in dense urban road networks and applies them to the case of ‘Beyoğlu’ region. Thematic layers were prepared using the Geographic Information System (GIS), and they were then combined to produce the serviceability of road links in the ‘Beyoğlu’ region. Consequently, A site specific vulnerability index is proposed, considering the serviceability of road links. A conceptual flowchart of the GIS processing steps taken to obtain the vulnerability index is illustrated.Yayın Path loss and RMS delay spread model for VLC-based patient health monitoring system(Institute of Electrical and Electronics Engineers Inc., 2022-05-13) Dönmez, Barış; Miramirkhani, FarshadVisible Light Communication (VLC) emerges as a supplementary technology to ubiquitous Radio Frequency (RF) since VLC meets the very high data rate, very high reliability, and ultra-low latency requirements driven by the trends in beyond-5G communication systems. Since VLC offers a solution to Electromagnetic Interference (EMI) and security problems in hospital environments, it becomes a better alternative for Medical Body Sensor Networks (MBSNs). Nonetheless, user mobility in a 3D environment causes a degradation in channel DC gain that leads to an optical path loss and also affects the time dispersive properties of multipath channels. In our paper, we adopt a ray tracing-based site-specific channel modeling method to characterize VLC-based MBSNs channel parameters. Based on the channel characteristics, we propose statistical models for path loss and Root Mean Square (RMS) delay spread in realistic Intensive Care Unit (ICU) ward and Family-Type Patient Room (FTPR) where user upon which three MBSNs nodes placed walks over extensive realistic random trajectories. The simulation results indicate that both path loss and RMS delay spread follow a log-normal distribution.Yayın Çizge evrişim ağı kullanarak patojen-konak ağlarında protein etkileşim tahmini(IEEE, 2021-06-09) Koca, Mehmet Burak; Karadeniz, İlknur; Nourani, Esmaeil; Sevilgen, Fatih ErdoğanProteinler yaşamsal faaliyetlerin gerçekleşmesinde kritik rol oynayan biyolojik moleküllerdir. Konak canlı proteinleri ile patojen proteinleri arasındaki etkileşimler patojenkonak etkileşim (PHI) ağlarını oluşturmaktadır. Bu iki parçalı etkileşim ağları patojenin hangi yaşamsal faaliyetleri etkilediğini belirlemede ve dolayısıyla sebep olabileceği hastalıkların tespitinde büyük öneme sahiptir. Proteinler arası etkileşimlerin laboratuvar ortamında tespiti hem zaman alıcı hem de maliyetlidir. Deneysel olarak saptanabilen etkileşim sayısının kısıtlı olması ve bazı etkileşimlerin gözden kaçması hesaplamalı tahmin yöntemlerinin geliştirilmesine önayak olmaktadır. Bu çalışmada PHI ağlarında protein etkileşim tahmini yapmayı sağlayan çizge evrişim ağı (GCN) tabanlı bir yöntem sunulmaktadır. Gözetimsiz olarak eğitilen GCN modeli (GraphSAGE) topolojik bilginin yanı sıra temel öznitelik olarak amino asit dizilimlerini kullanmaktadır. Bu çalışma bildiğimiz kadarıyla PHI ağlarında GCN tabanlı etkileşim tahmini sağlayan ilk çalışmadır. Deneysel sonuçlar geliştirilen modelin kıyaslama için kullanılan PHI veri seti üzerinde yüksek performanslı algoritmalardan %10 daha iyi performans göstererek %96 oranında doğrulukla etkileşim tahmini yaptığını göstermektedir.Yayın Design trade-offs and considerations for improving the PCB current carrying capacity in high power density power electronics applications(IEEE, 2022-03-24) Büyükdeğirmenci, Veysel Tutku; Kozarva, Ömer F.; Milletsever, Özgür C.; Hava, Ahmet MasumThis paper investigates printed circuit board (PCB) design trade-offs and considerations to maximize the current carrying capacity of traces in PCB-based power electronics applications. Many existing designs rely on methodologies through empirical data presented by the outdated IPC-2152 standard. A design methodology to maximize the utilized PCB area and improve thermal performance is introduced. To assess this methodology, lumped parameter (LP) and finite element (FE) models are developed and computational fluid dynamics (CFD) simulations are carried out. Thermal via placement strategies are investigated and maximum allowable power dissipation on the PCB traces is calculated. Simulations and analyses are experimentally validated on a PCB-based 100kW three-phase three-level inverter. The that results show that the thermal and electrical models discussed in this paper have superior accuracy compared to traditional formulations.Yayın Design of the near infrared camera DIRAC for East Anatolia Observatory(SPIE, 2022) Zhelem, Ross; Content, Robert; Churilov, Vladimir; Kripak, Yevgen; Waller, Lew; Case, Scott; Mali, Slavko; Muller, Rolf; Gonzalez, Mario; Adams, Dave; Binos, Nick; Chin, Timothy; Farrell, Tony; Klauser, Urs; Kondrat, Yuriy; Kunwar, Nirmala; Lawrence, Jon; Lorente, Nuria; Luo, Summer; McDonald, Erica; McGregor, Helen; Nichani, Vijay; Pai, Naveen; Vuong, Minh; Zahoor, Jahanzeb; Zheng, Jessica; Norris, Barnaby; Bryant, Julia; Vaccarella, Annino; Herrald, Nick; Gilbert, James; Yeşilyaprak, Cahit; Güçsav, Bülent; Coker, Deniz; Keskin, Onur; Jolissaint, LaurentThe 4m DAG telescope is under construction at East Anatolia Observatory in Turkey. DIRAC, the " DAG InfraRed Adaptive optics Camera", is one of the facility instruments. This paper describes the design of the camera to meet the performance specifications. Adaptive and auxiliary optics relay the telescope F/14 input 1:1 into DIRAC. The camera has an all refractive design for the wavelength range 0.9 - 2.4 micron. Lenses reimage the telescope focal plane 33 x 33 as (9 x 9 mm) on a 1k x 1k focal plane array. With magnification of 2x, the plate scale on the detector is 33 mas/pixel. There are 4 standard filters (Y, J, H, K) and 4 narrowband continuum filters. A 12 position filter wheel allows installation of 2 extra customer filters for specific needs; the filter wheel also deploys a pupil viewer lens. Optical tolerancing is carried out to deliver the required image quality at polychromatic Strehl ratio of 90% with focus compensator. This reveals some challenges in the precision assembly of optics for cryogenic environments. We require cells capable of maintaining precision alignment and keeping lenses stress free. The goal is achieved by a combination of flexures with special bonding epoxy matching closely the CTE of the lens cells and crystalline materials. The camera design is very compact with object to image distance <220 mm and lens diameters <25 mm. A standalone cryostat is LN2 cooled for vibration free operation with the bench mounted adaptive optics module (TROIA) and coronagraph (PLACID) at the Nasmyth focus of the DAG telescope.Yayın Implementing lightweight, dynamic hierarchical key assignment scheme for cloud computing(IEEE, 2024-03-25) Çelikbilek, İbrahim; Çeliktaş, Barış; Özdemir, EnverIn this paper, we propose the implementation and adaptation of a hierarchical key assignment scheme (HKAS) previously developed in our research to improve access control in cloud computing environments. The secret keys generated and managed by this scheme can be utilized for various purposes within the cloud computing, including data encryption, integrity checks, secure communications, and accessing critical infrastructures or services. Our implementation performs dynamic update operations with minimal computational cost and storage demands, as users within the hierarchical structure do not store any key components. Through security analysis, the scheme demonstrates strong key indistinguishability security (S-KI-security), effectively safeguarding keys against various cryptographic attacks. The scheme's flexibility allows it to be tailored to specific organizational needs, whether for securing sensitive data, ensuring compliance with regulatory standards, or facilitating secure data sharing and collaboration in cloud environments. Thus, we advocate for the practical implementation of the HKAS in transitioning to cloud environments.Yayın Hotel sales forecasting with LSTM and N-BEATS(IEEE, 2023-09-15) Özçelik, Şuayb Talha; Tek, Faik Boray; Şekerci, ErdalTime series forecasting aims to model the change in data points over time. It is applicable in many areas, such as energy consumption, solid waste generation, economic indicators (inflation, currency), global warming (heat, water level), and hotel sales forecasting. This paper focuses on hotel sales forecasting with machine learning and deep learning solutions. A simple forecast solution is to repeat the last observation (Naive method) or the average of the past observations (Average method). More sophisticated solutions have been developed over the years, such as machine learning methods that have linear (Linear Regression, ARIMA) and nonlinear (Polynomial Regression and Support Vector Regression) methods. Different kinds of neural networks are developed and used in time series forecasting problems, and two of the successful ones are Recurrent Neural Networks and N-BEATS. This paper presents a forecasting analysis of hotel sales from Türkiye and Cyprus. We showed that N-BEATS is a solid choice against LSTM, especially in long sequences. Moreover, N-BEATS has slightly better inference time results in long sequences, but LSTM is faster in short sequences.
