6746 research outputs found
Sort by
Comprehensive Comparison of Deep Learning Architectures for Stroke Classification From CT Images
No full textIsik UniversityStroke, a leading cause of death and permanent disability worldwide, is classified into ischemic and hemorrhagic types. Accurate and timely classification from CT images is critical for effective treatment in emergency care. This study compares modern deep learning models ResNet, ViT, EfficientNet, Inception, ResNeXt, MobileNet, ConvNeXt, ConvNeXtV2, and DaViT - for classifying stroke (ischemic, hemorrhagic) and non-stroke cases from CT images. Models were evaluated using the 2021 Teknofest stroke dataset based on accuracy, precision, specificity, and computational efficiency. Results show that while advanced models like ViT and ConvNeXtV2 offer high performance, lightweight architectures such as MobileNet (F1-score: 97.59%) are clinically viable and ideal for resource-limited environments. © 2025 Elsevier B.V., All rights reserved
Towards Geodetic-Level Accuracy in Low-Cost GNSS: Tectonic Velocity Determination Capabilities of the U-Blox ZED-F9P Over a Year Multi-GNSS PPP-AR Time Series
No full textThe growing availability of low-cost dual-frequency GNSS receivers is enhancing their suitability for various kinds of geodetic applications. Geodetic monitoring of the continuous crustal deformation using GNSS time series analysis is one of the commonly used geodetic applications. To maintain the most accurate estimated parameters such as secular velocity, seasonal signal parameters and offsets, geodetic-grade GNSS receivers are commonly used in the GNSS time series analysis. However, due to the increasing availability of low-cost dual-frequency GNSS receivers and advancements in software and hardware, these receivers have now reached a level that supports the GNSS time series analysis. In this study, over a year of multi-GNSS PPP-AR time series of the u-blox ZED-F9P low-cost GNSS receiver are investigated by evaluating the accuracy of the estimated parameters, comparing them with data from a geodetic-grade GNSS receiver monumented on a building roof. The results show that the minimum detrended standard deviation obtained from White Noise (WN) estimation is achieved using GPS + GLONASS + Galileo PPP for both receivers. The computed annual velocity and amplitude differences obtained from the GNSS time series between the u-blox ZED-F9P and the geodetic-grade GNSS receivers using GPS + GLONASS + Galileo PPP-AR are found as 0.6 mm / 0.4 mm / 0.8 mm and 1.5 mm / 0.4 mm / 0.2 mm for north, east, and up components, respectively. © 2025 Elsevier B.V., All rights reserved
A Comprehensive Review on YOLO Versions for Object Detection
No full textThe need for methods used for object detection has gained increasing momentum in recent years. Starting with traditional image processing techniques, this process has been facilitated by the addition of deep learning. Object detection is currently used in areas such as autonomous vehicles, disease diagnosis, robotic vision and industry. The types of systems that are predicted to be needed more and more in the age of developing technology are also increasing. In particular, YOLO (You Only Look Once), which is mostly preferred in real-time object detection, is preferred because it achieves high accuracy in a short time. This paper analyses the main versions of the YOLO algorithm since its first release. The paper systematically analyses the architectural differences between the versions of the YOLO algorithm, the strengths and weaknesses of the models and their contribution to performance. At the same time, in most of the previous studies on YOLO, a comprehensive comparison of the YOLOv9-v11 models is not presented and new architectural features are not evaluated. This review provides an in-depth analysis of the main versions from YOLOv1 to YOLOv11, including recent innovations such as NMS-free, Oriented Bounding Boxes (OBB), GELAN and PGI. This work is intended to be a useful guide for researchers and developers interested in the field. © 2025 Elsevier B.V., All rights reserved
Prediction of Uniaxial Compressive Strength of Rocks by Non-Destructive Testing Via Different Machine Learning Algorithms
No full textUniaxial Compressive Strength (UCS) is a fundamental parameter in engineering projects, often serving as a primary input for various analyses. The direct determination of UCS requires laboratory sample preparation in accordance with established standards. However, in cases where sample extraction is unfeasible due to the rock type or field conditions, UCS must be estimated through indirect methods. Over the years, numerous rock properties such as porosity, density, P-wave velocity, and Schmidt hammer rebound value have been employed as predictor variables for UCS estimation. In this study, UCS was predicted using Schmidt hammer rebound (SHR) and Leeb hardness (HL), which are practical, cost-effective, and non-destructive testing methods. Various machine learning algorithms including Linear Regression, Ridge Regression, Lasso Regression, ElasticNet Regression, Random Forest, Gradient Boosting, and Support Vector Regression were applied for prediction. The correlation coefficient (R2) obtained from these models ranged between 0.75 and 1.00. Among the tested models, the Random Forest (RF) algorithm demonstrated the highest prediction accuracy, with validation metrics of RMSE = 1.93, MSE = 0.87, and R-2
Eco-Friendly Leaching of Metallic Silver With Boric Acid: Kinetics Study
No full textThis article discusses the kinetics of using a hydrogen peroxide solution to dissolve pure metallic silver in boric acid. The impact of temperature, rotation speed, hydrogen peroxide (H2O2) concentration, and boric acid concentration were investigated. The results indicate that silver dissolution rate and rotation speed have a positive relationship. Additionally, boric acid concentrations ranging from 0.10 to 0.40 M significantly enhance the dissolution process. The hydrogen peroxide concentration has no discernible influence on the rate of dissolution. While temperatures between 20 and 40 degrees C are beneficial, temperatures above 40 degrees C had the opposite effect and caused a layer of boron oxide (B2O3) to form. The activation energy was determined to be 30.49 kJ/mol
Kenevir Lifli Kompozit Malzemelerde Farklı Bağlayıcıların Isı, Nem, Yangın ve Ses Performansına Etkisi
No full textKenevirin sağladığı düşük yoğunluk, yüksek ısı yalıtım kapasitesi ve kenevirin hızlı büyümesi, biyolojik çeşitlilik, karbon tutma kapasitesi gibi çevre dostu özellikler, bu levhaların enerji verimliliğini artırırken, yapıların dayanıklılığını da desteklemektedir. Bu tez çalışması, bu levhaların potansiyel kullanım alanlarını, malzeme karışımındaki farklı oranların etkisini ve levhaların performansını incelemektedir. Yapılan bu çalışma, yapı sektöründe yenilikçi ve sürdürülebilir çözümler arayışına önemli bir katkı sağlanması hedeflenmektedir. Kenevir kıtığının yapı malzemesi olarak kullanımı, hem çevresel etkileri azaltma hem de enerji verimliliğini artırma potansiyeli taşımaktadır. Konya Teknik Üniversitesi Teknik Bilimler Meslek Yüksekokulu İnşaat Laboratuvarı'nda ham MDF malzemeden deney düzeneği oluşturulmuştur. Oluşturulan deney düzeneğinde 1. grup olarak %35, %25 ve %15 oranında ağırlıkça kenevir kıtığı, kil ve kireç karışımdan eni ve boyu 50 cm ölçülerinde 5 cm kalınlığında levhalar üretilmiştir. 2. Grup olarak %35, %25 ve % 15 oranında ağırlıkça kenevir kıtığı, kil, kireç ve çimento karışımından eni ve boyu 50 cm ölçülerinde 5 cm kalınlığında levhalar üretilmiştir. Üretilen bu levhalarla içten kaplanarak her bir malzeme için mevcut ortam sıcaklığı, 15, 20, 25, 30, 35 ve 40 °C sıcaklıklarda ve sabit sıcaklık için de 100, 125, 250, 500, 1000 ve 2000 Hz'de olmak üzere deneyler yapılmıştır. Isı ve ses deney sonuçları, ayrıca 6 farklı malzeme için tek noktadan yanma deneyi ve nem sonuçları kıyaslanmıştır. Yapılan deneyler sabit sıcaklıkta ses geçirimliliği ve ısı geçirimliliği en düşük %35 oranında kenevir kıtığı, kil ve kireç karışımlı levha olmuştur. Tek nokta yanma deneyinde ise yanma dayanımı en yüksek %15 oranında kenevir kıtığı, kil, kireç ve çimento olduğu sonucuna ulaşılmıştır. Nem oranı deneyinde ise nem oranının en yüksek olan levha %35 oranlı kenevir kıtığı, kil ve kireç karışımıdır.Hemp's low density and high thermal insulation capacity, along with its environmentally friendly properties such as rapid growth, biodiversity support, and carbon sequestration, contribute to improved energy efficiency and structural durability in building boards. This thesis explores the potential applications of these boards, the effects of varying material ratios, and their overall performance. The study aims to contribute significantly to the development of innovative and sustainable solutions in the construction industry. Using hemp shiv as a construction material has the potential to reduce environmental impacts while enhancing energy efficiency. An experimental setup was established using raw MDF at the Construction Laboratory of Konya Technical University, Technical Sciences Vocational School. In this setup, Group 1 boards were produced using 35%, 25%, and 15% hemp shiv, clay, and lime. Group 2 boards were made with the same hemp shiv ratios, but with the addition of cement to the mixture. All boards were produced with a width and height of 50 cm and a thickness of 5 cm. The boards were used for internal wall cladding. Experiments were conducted at ambient temperatures of 15, 20, 25, 30, 35, and 40°C. Additionally, tests were performed at fixed temperatures for frequencies of 100, 125, 250, 500, 1000, and 2000 Hz. Thermal and acoustic performance, single-point combustion resistance, and moisture content were evaluated across six different material types. Results showed that the board with 35% hemp shiv, clay, and lime had the lowest heat and sound transmission. The highest fire resistance was observed in the board containing 15% hemp shiv, clay, lime, and cement. The highest moisture content was found in the board with 35% hemp shiv, clay, and lime
Seismic Response Analysis of Different Soil Types With Equivalent Linear Analysis Method
No full textIn this study; With DEEPSOIL v7 software, seismic behavior analyzes of a region were made with 1D, "Equivalent Linear Analysis Method". The method that offers the closest solution to the reality in the solution of engineering problems is the nonlinear solution method. However, it is very difficult to obtain and analyze the necessary parameters. For this reason, this method was chosen, which is not difficult to solve and gives the closest results to the nonlinear solution. Analyzes were made in the direction of whether the soil profile will absorb the earthquake in the event of a possible earthquake or, on the contrary, will increase the earthquake effect and transmit it to the building foundation. As a result of the analysis, the peak acceleration values were calculated and defined with acceleration-time-depth graphs. In this study, in which the seismic responses of different types of soil structures were investigated, it was observed that the soil structure was non-linear, the shear wave velocity value was an important parameter in determining the dynamic behavior of the soil, and the damping ratio of the soil increased with the increase in the shear wave velocity value
Angular Analysis of the B0 → K*(892)0μ+μ- Decay in Proton-Proton Collisions at √s=13 TeV
No full textHall, Geoffrey/0000-0002-6299-8385; Tapper, Alexander/0000-0003-4543-864XA full set of optimized observables is measured in an angular analysis of the decay B-0 -> K*(892)(0)mu(+)mu(-) using a sample of proton-proton collisions at root s = 13 TeV, collected with the CMS detector at the LHC, corresponding to an integrated luminosity of 140 fb(-1). The analysis is performed in six bins of the squared invariant mass of the dimuon system, q(2), over the range 1.1 q(2) 16 GeV2. The results are among the most precise experimental measurements of the angular observables for this decay and are compared to a variety of predictions based on the standard model. Some of these predictions exhibit tension with the measurements.We congratulate our colleagues in the CERN accelerator departments for the excellent performance of the LHC and thank the technical and administrative staffs at CERN and at other CMS institutes for their contributions to the success of the CMS effort. In addition, we gratefully acknowledge the computing centers and personnel of the Worldwide LHC Computing Grid and other centers for delivering so effectively the computing infrastructure essential to our analyses. Finally, we acknowledge the enduring support for the construction and operation of the LHC, the CMS detector, and the supporting computing infrastructure provided by the following funding agencies: SC (Armenia), BMBWF and FWF (Austria); FNRS and FWO (Belgium); CNPq, CAPES, FAPERJ, FAPERGS, and FAPESP (Brazil); MES and BNSF (Bulgaria); CERN; CAS, MOST, and NSFC (China); Minciencias (Colombia); MSES and CSF (Croatia); RIF (Cyprus); SENESCYT (Ecuador); ERC PRG, RVTT3 and MoER TK202 (Estonia); Academy of Finland, MEC, and HIP (Finland); CEA and CNRS/IN2P3 (France); SRNSF (Georgia); BMBF, DFG, and HGF (Germany); GSRI (Greece); NKFIH (Hungary); DAE and DST (India); IPM (Iran); SFI (Ireland); INFN (Italy); MSIP and NRF (Republic of Korea); MES (Latvia); LMTLT (Lithuania); MOE and UM (Malaysia); BUAP, CINVESTAV, Conahcyt, LNS, SEP, and UASLP-FAI (Mexico); MOS (Montenegro); MBIE (New Zealand); PAEC (Pakistan); MES and NSC (Poland); FCT (Portugal); MESTD (Serbia); MCIN/AEI and PCTI (Spain); MoSTR (Sri Lanka); Swiss Funding Agencies (Switzerland); MST (Taipei); MHESI and NSTDA (Thailand); TUBITAK and TENMAK (Turkey); NASU (Ukraine); STFC (United Kingdom); DOE and NSF (USA). Individuals have received support from the Marie-Curie programme and the European Research Council and Horizon 2020 Grant, contract Nos. 675440, 724704, 752730, 758316, 765710, 824093, 101115353, 101002207, and COST Action CA16108 (European Union); the Leventis Foundation; the Alfred P. Sloan Foundation; the Alexander von Humboldt Foundation; the Science Committee, project no. 22rl-037 (Armenia); the Belgian Federal Science Policy Office; the Fonds pour la Formation a la Recherche dans l'Industrie et dans l'Agriculture (FRIA-Belgium); the F.R.S.-FNRS and FWO (Belgium) under the "Excellence of Science -EOS'' -be.h project n. 30820817; the Beijing Municipal Science ; Technology Commission, No. Z191100007219010 and Fundamental Research Funds for the Central Universities (China); the Ministry of Education, Youth and Sports (MEYS) of the Czech Republic; the Shota Rustaveli National Science Foundation, grant FR-22-985 (Georgia); the Deutsche Forschungsgemeinschaft (DFG), among others, under Germany's Excellence Strategy -EXC 2121 "Quantum Universe'' -390833306, and under project number 400140256 -GRK2497; the Hellenic Foundation for Research and Innovation (HFRI), Project Number 2288 (Greece); the Hungarian Academy of Sciences, the New National Excellence Program -UNKP, the NKFIH research grants K 131991, K 133046, K 138136, K 143460, K 143477, K 146913, K 146914, K 147048, 2020-2.2.1-ED-2021-00181, TKP2021-NKTA-64, and 2021-4.1.2-NEMZ_KI (Hungary); the Council of Science and Industrial Research, India; ICSC -National Research Centre for High Performance Computing, Big Data and Quantum Computing and FAIR -Future Artificial Intelligence Research, funded by the NextGenerationEU program (Italy); the Latvian Council of Science; the Ministry of Education and Science, project no. 2022/WK/14, and the National Science Center, contracts Opus 2021/41/B/ST2/01369 and 2021/43/B/ST2/01552 (Poland); the Fundacao para a Ciencia e a Tecnologia, grant CEECIND/01334/2018 (Portugal); the National Priorities Research Program by Qatar National Research Fund; MCIN/AEI/10.13039/501100011033, ERDF "a way of making Europe'', and the Programa Estatal de Fomento de la Investigacion Cientifica y Tecnica de Excelencia Maria de Maeztu, grant MDM-2017-0765 and Programa Severo Ochoa del Principado de Asturias (Spain); the Chulalongkorn Academic into Its 2nd Century Project Advancement Project, and the National Science, Research and Innovation Fund via the Program Management Unit for Human Resources ; Institutional Development, Research and Innovation, grant B39G670016 (Thailand); the Kavli Foundation; the Nvidia Corporation; the Super-Micro Corporation; the Welch Foundation, contract C-1845; and the Weston Havens Foundation (USA).FWF; FNRS; FWO (Belgium); CNPq; CAPES; FAPERJ; FAPERGS; FAPESP (Brazil); BNSF (Bulgaria); MOST; NSFC (China); CSF (Croatia); RIF (Cyprus); SENESCYT (Ecuador); ERC PRG [MoER TK202]; Academy of Finland; MEC; CEA; CNRS/IN2P3 (France); SRNSF; BMBF; DFG; HGF (Germany); NKFIH (Hungary); DAE; DST; SFI (Ireland); INFN (Italy); NRF (Republic of Korea); MES (Latvia); MOE; UM (Malaysia); UASLP-FAI (Mexico); PAEC (Pakistan); FCT (Portugal); MESTD (Serbia); PCTI (Spain); Swiss Funding Agencies (Switzerland); NSTDA; TUBITAK; NASU (Ukraine); NSF (USA); Marie-Curie programme; European Research Council; Horizon 2020 Grant [675440, 724704, 752730, 758316, 765710, 824093, 101115353, 101002207]; COST Action [CA16108]; Leventis Foundation; Alfred P. Sloan Foundation; Alexander von Humboldt Foundation; Science Committee [22rl-037]; Belgian Federal Science Policy Office; Fonds pour la Formation a la Recherche dans l'Industrie et dans l'Agriculture (FRIA-Belgium); FWO (Belgium) under the "Excellence of Science -EOS [30820817]; Beijing Municipal Science ; Technology Commission [Z191100007219010]; Fundamental Research Funds for the Central Universities (China); Ministry of Education, Youth and Sports (MEYS) of the Czech Republic; Shota Rustaveli National Science Foundation [FR-22-985]; Deutsche Forschungsgemeinschaft (DFG) [EXC 2121, 400140256 -GRK2497]; Hellenic Foundation for Research and Innovation (HFRI) [2288]; Hungarian Academy of Sciences [K 131991, K 133046, K 138136, K 143460, K 143477, K 146913, K 146914, K 147048, 2020-2.2.1-ED-2021-00181, TKP2021-NKTA-64, 2021-4.1.2-NEMZ_KI]; Council of Science and Industrial Research, India - NextGenerationEU program (Italy); Latvian Council of Science; Ministry of Education and Science [2022/WK/14]; National Science Center [Opus 2021/41/B/ST2/01369, 2021/43/B/ST2/01552]; Fundacao para a Ciencia e a Tecnologia [CEECIND/01334/2018]; National Priorities Research Program by Qatar National Research Fund [MCIN/AEI/10.13039/501100011033]; ERDF "a way of making Europe'' [MDM-2017-0765]; Programa Severo Ochoa del Principado de Asturias (Spain); National Science, Research and Innovation Fund via the Program Management Unit for Human Resources ; Institutional Development, Research and Innovation [B39G670016]; Kavli Foundation; Nvidia Corporation; Welch Foundation [C-1845]; Weston Havens Foundation (USA
The Effect of Particulate Matter (PM2.5 and PM10) on Human Health and Cultural Heritage in the Historical City Centre of Konya
No full textThe population, that has increased dramatically with industrial activities in the last century, causes air pollution in cities. Particulate matter, among the pollutants that affect air pollution, threatens public health and historical buildings by trapping hazardous elements and carrying them with the wind. Therefore, identifying areas where particulate matter is concentrated can be an important tool for the protection of human health and cultural heritage. To this end, the relationship between black crust formation on historical buildings and the presence of particulate matter (PM2.5 and PM10), as well as its potential link to respiratory diseases in humans, was investigated in the historical city center of Konya, where air pollution levels have been considerably high over the past few decades. The study was conducted through both in-situ measurements (PM2.5 and PM10) and laboratory analyses, including SEM-EDX, XRF, and physical properties assessments. According to the findings of the study, it was determined that both the number of respiratory patients and the formation of black crust on monuments increased in regions where particulate matter was concentrated
Modeling and Adaptive Control of a Military Vehicle Dynamics With Weapon Carrier
No full textIn this study; mathematical modelling of a military vehicle dynamics with a weapon carrier and comprehensive simulation studies were carried out with five different controller designs, including sliding mode control and fuzzy logic based adaptive control, in addition to traditional controllers for the control of the weapon system, with different reference inputs and under the influence of different standard real road data. By modelling the full vehicle dynamics with high accuracy, an adaptive sliding mode controller system that can update the control parameters according to a fuzzy rule base against dynamic disturbances originating from the road for the control of the weapon system was designed. Firstly, the design parameters and dynamic coefficients of the system were determined according to military standards and similar studies in the literature, the equations of motion of the multi-degree-of-freedom system were obtained, the mathematical model was obtained, and the multi-mass dynamic model was compared and verified. Considering the international military vehicle test standards, five different feedback controllers (PID, cascade PID, Sliding Mode, Integral Sliding Mode, Fast Terminal Sliding Mode) were designed and simulated for the angular position control of the weapon system in the vehicle's constant speed movement under the effect of five different real road data. Afterwards, to improve the controller performance, a more robust controller was developed in which the system can give an adaptive response to disturbances and uncertainties originating from road irregularities, and the fast terminal sliding mode controller gains are updated simultaneously and based on fuzzy logic depending on the angular position error and change. From the simulation results, it was understood that sliding mode control approaches generally show a higher control performance on the system performance compared to the traditional PID controller, and the adaptive fast terminal sliding mode controller can be effective on the system's response to disturbances especially in difficult road conditions with high variability. The obtained results were presented graphically, compared and investigated.Bu çalışmada; silah taşıyıcılı askeri bir araç dinamiğinin matematiksel modellemesi ve silah sisteminin denetimine yönelik geleneksel kontrolcülerin yanı sıra kayan kipli kontrol ve bulanık mantık tabanlı uyarlamalı (adaptif) kontrol olmak üzere toplamda beş farklı kontrolcü tasarımı, farklı referans girişlerle ve farklı standart gerçek yol verileri etkisinde kapsamlı benzetim çalışmaları gerçekleştirilmiştir. Tam araç dinamiği yüksek doğrulukta modellenerek, silah sisteminin denetimine yönelik yoldan kaynaklı dinamik bozuculara karşı kontrol parametrelerini bulanık bir kural tabanına göre güncelleyebilen adaptif bir kayan kipli kontrolcü sistemi tasarlanmıştır. Öncelikle, sisteme ait tasarım parametreleri ve dinamik katsayılar askeri standartlara ve literatürdeki benzer çalışmalara göre belirlenerek, çok serbestlik dereceli sistemin hareket denklemleri elde edilmiş, matematiksel modeli oluşturulmuş, çok kütleli dinamik modeli kıyaslanarak doğrulanmıştır. Uluslararası askeri araç test standartları dikkate alınarak, aracın beş farklı gerçek yol verisi etkisindeki sabit hızda hareketinde, silah sisteminin açısal konum denetimine yönelik beş farklı yapıdaki geri beslemeli kontrolcü (PID, kaskad PID, Kayan Kipli, İntegral Kayan Kipli, Hızlı Terminal Kayan Kipli) tasarımı ve benzetim çalışmaları gerçekleştirilmiştir. Sonrasında, kontrolcü performansını geliştirmek amacıyla, sistemin yoldaki düzensizliklerden kaynaklı bozuculara ve belirsizliklere uyarlamalı bir tepki verebildiği, açısal konum hatasına ve değişimine bağlı olarak hızlı terminal kayan kipli kontrolcü kazançlarının bulanık mantık tabanlı ve eş zamanlı güncellendiği, daha gürbüz bir kontrolcü geliştirilmiştir. Benzetim sonuçlarından, genel olarak kayan kipli kontrol yaklaşımlarının sistem performansı üzerinde geleneksel PID kontrolcüye kıyaslasa daha yüksek bir kontrol performans gösterdiği, uyarlamalı hızlı terminal kayan kipli kontrolcünün ise özellikle yüksek değişkenliğe sahip zorlu yol şartlarındaki bozuculara karşı sistemin cevabı üzerinde etkili olabildiği anlaşılmıştır. Elde edilen sonuçlar grafiksel olarak sunulmuş, karşılaştırılarak değerlendirilmiştir