DSpace@ATÜ (Adana Alparslan Türkeş Bilim ve Teknoloji Universiti)
Not a member yet
3463 research outputs found
Sort by
Artificial intelligence algorithms for recurrence risk score prediction in early-stage breast cancer: A multicenter study of 437 cases
No full textSpecial Clinical Science Symposia -- MAY 29-29, 2024 -- ELECTR NETWORK[Abstract Not Available
Transfer Learning with Fuzzy for Breast Cancer
No full textDeep learning methods have been used to reduce the number of unnecessary breast biopsies. In this study, an accurate hybrid rule-based fuzzy system with transfer learning is developed to classify breast abnormalities as malignant or benign by calculating breast cancer risk from digital mammogram images. Our system consists of three phases: (i) data augmentation methods (e.g., traditional methods, Generative Adversarial Networks (GANs)); (ii) classification of the breast abnormalities on the BCDR-D02 and mini-MIAS databases by fine-tuning transfer learning methods with the deep learning base model Convolutional Neural Network (CNN); and (iii) calculation of breast cancer risk with a rule-based fuzzy system using the results of the second phase to improve the classification of breast abnormality results. Using our CNN baseline model and traditional extension methods, we achieve 64% and 82% accuracy for mini-MIAS and BCDR-D02, respectively. With fine-tuning the transfer learning methods, we obtain 80% and 83% with VGG-16 for mini- MIAS and BCDR-D02, respectively. Using the rule-based fuzzy system, called the risk method, we achieve the highest results for mini-MIAS (93%) and BCDR-D02 (94%). The classification results of our risk method are compared with the other transfer learning and baseline methods, and it is found that the accuracy of breast abnormality classification is improved by using a hybrid rule-based fuzzy system with transfer learning. Our study can serve as a guide that provides useful tips to researchers in the field of breast cancer classification to develop more effective and reliable studies
Optimizing parameters for additive manufacturing: a study on the vibrational performance of 3D printed cantilever beams using material extrusion
No full textPurposeThis study aims to investigate the impact of different printing parameters on the free vibration characteristics of 3D printed cantilever beams. Through a comprehensive analysis of material extrusion (ME) variables such as extrusion rate, printing pattern and layer thickness, the study seeks to enhance the understanding of how these parameters influence the vibrational properties, particularly the natural frequency, of printed components.Design/methodology/approachThe experimental design involves conducting a series of experiments using a central composite design approach to gather data on the vibrational response of ABS cantilever beams under diverse ME parameters. These parameters are systematically varied across different levels, facilitating a thorough exploration of their effects on the vibrational behavior of the printed specimens. The collected data are then used to develop a predictive model leveraging a hybrid artificial neural network (ANN)/ particle swarm optimization (PSO) approach, which combines the strengths of ANN in modeling complex relationships and PSO in optimizing model parameters.FindingsThe developed ANN/PSO hybrid model demonstrates high accuracy in predicting the natural frequency of 3D printed cantilever beams, with a correlation ratio (R) of 0.9846 when tested against experimental data. Through iterative fine-tuning with PSO, the model achieves a low mean square error (MSE) of 1.1353e-5, underscoring its precision in estimating the vibrational characteristics of printed specimens. Furthermore, the model's transformation into a regression model enables the derivation of surface response characteristics governing the vibration properties of 3D printed objects in response to input parameters, facilitating the identification of optimal parameter configurations for maximizing vibration characteristics in 3D printed products.Originality/valueThis study introduces a novel predictive model that combines ANNs with PSO to analyze the vibrational behavior of 3D printed ABS cantilever beams produced under various ME parameters. By integrating these advanced methodologies, the research offers a pioneering approach to precisely estimating the natural frequency of 3D printed objects, contributing to the advancement of predictive modeling in additive manufacturing
The effect of the COVID-19 pandemic on accrual-based earnings management: Evidence from four most affected European countries
No full textThis study aims to investigate the effect of the COVID-19 pandemic on accrual-based earnings management (EM) based upon a sampling of 938 listed firms from four selected European countries (United Kingdom, Italy, Spain, and T & uuml;rkiye) during 2016-2020. We find that firms engage more in accrual-based EM through income-increasing and income-decreasing accruals in the year of the COVID-19 pandemic relative to the period before the pandemic. These findings imply that financial reporting reliability and usefulness decreased in the period of the pandemic. Our results are robust to some sensitivity checks.We thank the editors and anonymous referees for their constructive and valuable comments, which improved our manuscript
Vibration Analysis of a Hybrid Polymer Ball Bearing with 3D-Printed Races
No full textBackgroundThe use of polymer bearings in some industries has increased in recent years because of their advantages, such as resistance to dirt and dust, no need for maintenance and lubrication, and chemical resistance, especially in hygienic areas. Additive manufacturing (AD) or 3D printing is also a popular method that makes complex geometric shapes easily produced using polymer material, layer by layer, of the defined component.PurposeThe study aims to investigate the applicability of producing polymer ball bearing with additive manufacturing techniques by experimentally observing the bearing's vibrations, temperature, and rolling resistance.MethodsA set of ball-bearing races-inner and outer-are produced with the stereolithography (SLA) method using polymeric resin and tested under a certain load.ResultsVibrations and load cell data for rolling resistance are analyzed through its lifetime to investigate the evolution of the bearing under the test.ConclusionThe additive manufacturing method could be preferred to produce a ball bearing with limited life.Gazi niversitesi [06/2018-08]; Gazi University Scientific Research Projects UnitGazi University Scientific Research Projects Unit funded the presented study with Grant No. 06/2018-08
INNOVATIVE SYNERGIES IN AIRCRAFT PROPULSION: THE CONCEPT OF HYBRID POWER SYSTEMS WITH CONTRA-ROTATING PROPELLERS
No full textAnsys; et al.; Honeywell; International Gas Turbine Institute (IGTI); Rolls-Royce; Siemens69th ASME Turbo Expo 2024: Turbomachinery Technical Conference and Exposition, GT 2024 -- 24 June 2024 through 28 June 2024 -- London -- 202367In an era characterized by escalating emphasis on fuel economy and the mitigation of greenhouse gas emissions within the aerospace industry, this paper presents an innovative paradigm including the hybrid electric engine with contra-rotating propellers. This article unveils a pioneering technological achievement, exemplified by our patented invention registered under the identifier IB/2021/060538, which received a gold medal at the ICAN 2022 International Invention competition in Toronto, Canada, represents a noteworthy advancement in the domain of hybrid engine technology. It is imperative to acknowledge that the concept is currently in the conceptual design phase, necessitating further refinement to attain its maximum potential. The engine, characterized as a contra-rotating propeller system, engenders an efficiency gain ranging from 6% to 16% relative to single-fuel engines, with one internal combustion engine providing half of the required power and the electric motor complementing the remaining share. This innovative system comprises two distinct configurations: a system with two electric motors and one fuel engine in which one of the electric engines is used as a backup engine. In case of user preference or fuel engine failure, the backup electric is engaged in place of the fuel engine. This paradigm-shifting innovation effectively changes the conventional internal combustion engine into a multi-engine anti-torque system, facilitating augmented thrust generation while simultaneously reducing fuel consumption by an impressive margin of 40% to 60% when compared with conventional engine models. Beyond its commendable fuel efficiency, the hybrid engine is characterized by a satisfactory level of reliability. This is related to the inclusion of a backup electric motor. In addition to the internal combustion engine, supporting the system with the ability to manage system failures and maintain power output even under emergency circumstances. Notably, the fundamental concept of the contra-rotating propeller system is not entirely novel, however, our innovative approach harmoniously synchronizes two electric motors, thereby containing the advantages inherent in the contra-rotating system with the reliability attributed to electric propulsion. Copyright © 2024 by ASME.Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK, (123M222); Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTA
Evaluation of Rockfill Stabilized-Geosynthetics Reinforced Road Base with Repeated Plate Loading Tests
No full textIn this study, the performance of unpaved road sections over soft clay soil geosynthetic-reinforced and stabilized with rock fill layer was evaluated using repeated plate loading tests. A total of 10 field tests were carried out using a circular model rigid plate with a diameter of 0.30 m. The parameters investigated included the location and type of geosynthetics and loading conditions (number of loading cycle and traffic loading condition). Based on the test results, the least deformation was observed in the rockfill section. The geocell placed at a depth of one-third thickness of the granular fill layer from the top showed improved performance and was more effective as compared with other geosynthetic reinforcements. However, for granular fill geosynthetic-reinforced or stabilized with rock fill layer, the results demonstrate an improvement in the rutting performance of the pavement and the definite trend of increasing reloading elastic modulus, depending on the traffic loading situation. It has been also observed that the use of geocell or geogrid reinforcement in granular fill layer or more rigid rockfill layer provides an important increase in the modulus improvement ratio (MIR) by at least 36%, 45% and 60% compared to the granular fill section, respectively.Republic of Turkey Osmaniye Special Provincial Administration Institution; Osmaniye Korkut Ata University Scientific Research Projects Unit [OKUEBAP-2014-PT3-033]The work presented in this paper was carried out with supporting from the republic of Turkey Osmaniye Special Provincial Administration Institution and Osmaniye Korkut Ata University Scientific Research Projects Unit, grant number OKUEBAP-2014-PT3-033
Improvement in performance of SnSe-based photodetectors via post deposition sulfur diffusion
No full textThe work represents an enhancement in the photodetector properties of thermally evaporated SnSe thin films through both annealing and sulfurization processes. X-ray diffraction analysis showed the formation of SnSe 1-x S x alloy with a graded composition that was more S -rich near the surface when the sulfurization process was applied at 350 degrees C. Scanning electron microscopy results indicated that increasing the annealing temperature from 300 degrees C to 350 degrees C changed the microstructure greatly. When the sulfurization temperature was increased from 300 degrees C to 350 degrees C, the direct band gap of SnSe thin films decreased from 1.38 eV to 1.30 eV while the indirect band gap reduced from 0.91 eV to 0.71 eV. Raman spectra also confirmed the development of phase of SnSe 1-x S x for the sulfurized sample at 350 degrees C. Photocurrent-time curves of devices fabricated on all films demonstrated that sulfurization at high temperature increased the photocurrent values. It was further determined that devices made on sulfurized layers had smaller rise/fall times of 2.57/2.33 s compared to those fabricated on non-sulfurized films. The best responsivity and detectivity values were achieved as 2.07 x 10 -1 A/W and 1.19 x 10 7 Jones, respectively, for photodetectors fabricated on layers sulfurized at 350 degrees C
Assessment of the Effects of Induction Heating Induced-Healing on the Fracture Properties of Very Thin Asphalt Concrete
No full text10th International Conference on Maintenance and Rehabilitation of Pavements (MAIREPAV) -- JUL 24-26, 2024 -- Univ Minho, Guimaraes, PORTUGALSelf-healing by induction heating stands as a promising and sustainable technology for asphalt pavement maintenance applications. This study involves performing a series of test cycles, encompassing first SCB fracture testing on a waste steel fiber (WSF)-reinforced for an asphalt concrete for thin surface layers (BBTM) and asphalt concrete for binder layer (ACL), induction heating for healing, and subsequent second SCB fracture testing. The research aims to analyze how crack healing ability changes with a semi-circular bending (SCB) test before and after healing, considering the combination of BBTM and ACL with different WSF content. Based on the SCB test fractural parameters, the healing indexes (HI) are obtained through peak load (Fmax) and critical stress intensity factor (K-IC). Additionally, the fracture parameter results obtained based on the amount of WSF in the BBTMs and ACLs are consistent with the results of the indirect tension to cylindrical specimen (IT-CY) test. Consequently, it was emphasized that asphalt mixtures containing WSF have the potential to heal cracks through induction heating, and the healing ability can be improved depending on theWSF content of the wearing and binder layer. In addition, it was shown that ACL and BBTM samples with higher stiffness values are much more difficult to heal in terms of Fmax and K-IC.[SGS23/042/OHK1/1T/11]This paper was supported by the project No. SGS23/042/OHK1/1T/11
Yapay Zekâ Tabanlı Hava Kalitesi İyileştirme Stratejilerinin Değerlendirilmesi
No full textGünümüzde hava kirliliği, kentsel ve sanayi bölgelerinde yaşayan milyonlarca insan için ciddi sağlık riskleri oluşturmaktadır. Bu makalede, yapay zekâ (AI) teknolojileri ve makine öğrenimi algoritmalarının hava kalitesini izleme ve iyileştirme stratejilerinin geliştirilmesinde nasıl kullanılabileceği ele alınmıştır. Bu araştırma, özellikle kentsel alanlarda hava kalitesi üzerinde etkili olan ana kirleticilerin dinamiklerini modellemek için makine öğrenmesi yaklaşımlarını kullanmaktadır. Bu çalışmada, çeşitli yapay zekâ modelleri (RF, SVM, ANN, CNN, RNN, GAN) kullanılarak hava kalitesi verilerinin analiz, tahmin ve simüle edilmesi süreçleri detaylı bir şekilde incelenmiştir. Ayrıca, bu modellerin hava kalitesi yönetimi için stratejik karar verme süreçlerinde nasıl entegre edilebileceği üzerinde durulmuştur. Yapay zekâ tabanlı modeller, gerçek zamanlı veri akışını analiz ederek, hava kalitesi üzerinde olumlu etkiler yaratabilecek müdahaleler önermektedir