Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Uzun, Sevda(66)
- Merdan, Mehmet(56)
- Duran, Celal(50)
- Ozdes, Duygu(47)
- Kaygusuz, Abdullah(42)
- Demir, Selim(37)
- Turan, Ibrahim(37)
- Ashyralyyev, Charyyar(34)
- Dokuz, Abdurrahman(33)
- Araz, Onur(31)
- Öztürk, Serkan(31)
- Sipahi, Ferkan(30)
- Kandemir, Raif(28)
- Arslan, Mehmet(27)
- Karsli, Orhan(27)
- Kulakaç, Nurşen(26)
- Baltacı, Cemalettin(25)
- Gücer, Mehmet Ali(25)
- Kurt, Kemal(25)
- Maden, Nafiz(25)
- Ozturk, Samet(25)
- Topal, Fevzi(25)
- Baltaci, Cemalettin(24)
- Yücel, Cem(24)
- Aliyazicioglu, Yuksel(23)
- Bayrakdaroglu, Serdar(23)
- Kankal, Murat(23)
- Peker, Iskender(23)
- Yolcu, Halil(23)
- Reis, Hatice Catal(21)
- Topal, Meryem(21)
- Vural, Alaaddin(21)
- Aydin, Aydanur(20)
- Aydin, Faruk(20)
- Bayraktar, Alemdar(20)
- Kurnaz, Muammer(20)
- Çelik, Necati(20)
- Ürkek, Bayram(20)
- Cakir, Tufan(18)
- Günen, Mehmet Akif(18)
Yayınlar
- MakaleAçık Erişim2024Scopus SJRQ2Elevation-dependent growth trends of Picea orientalis (L.) Peterm forests in the Fırtına Creek Basin (Rize/Turkey)
Işık, Fatih; Bahadır, Muhammet; Zeybek, Halil İbrahim; Hatipoğlu, İlter Kutlu
Changes in climatic conditions have ecological and economic consequences or impact for trees and forest stands. In this respect, it is crucial to understand the radial growth trends of trees, their ecological response across elevation gradients, and the possible impacts of climate change on the species. In this study, Picea orientalis (L.) Peterm, located in the Fırtına Creek Basin in the northern part of the Eastern Black Sea Mountains in northeastern Turkey, was investigated along different elevation gradients in the context of climate-growth response. In the study, six site chronologies along an elevation gradient from 900 m to 2050 m were developed. Dendroclimatological methods were applied to assess the elevation-dependent radial growth characteristics of trees. In total, 200 increment cores were collected from 98 living trees. The relationships between climate and tree ring growth along the elevation gradient showed a positive relationship between growth and temperature at upper elevations (1700–1900 m) and a positive relationship between growth and precipitation at middle elevations (1400–1600 m). In particular, January–April mean temperatures and May rainfall were positively correlated with tree-ring growth. At lower elevations (900–1100 m), the correlation coefficients between climate and growth are insignificant because, at these altitudes, the species have optimum ecological conditions. It was also found that mean temperatures between 0 °C and 2 °C in January–April and total precipitation between 60 and 100 mm in January–February positively affect tree growth. However, if these thresholds are exceeded, it is possible that growth may be adversely affected. This research underscores the complex interplay between climate variables and tree growth along elevation gradients, highlighting the need for adaptive management strategies in the face of changing climatic conditions.
AtıfScopus4OpenAlex2
İncele - MakaleYalnız künye2024Scopus SJRQ2The Effect of Video-Based Simulation Training on Nursing Students' Motivation and Academic Achievement A Mixed Study
Koçan, Sema; Kulakaç, Nurşen; Aktug, Cemile; Demirel, Sevgül
This study was conducted to determine the effect of video-based simulation education on nursing students' motivation and academic achievement. The research was designed in a mixed model. A quasi-experimental method with a pretest-posttest control group was used for the quantitative part, and the descriptive phenomenology approach was used as the qualitative research method. The sample of the study consisted of second-year nursing students in two state universities in eastern Turkey. The data were collected with the Student Information Form, the Academic Achievement Test, and the Motivation Resources and Problems Scale using Google Forms Web application. Qualitative data were collected through online semistructured interview forms and focus group interviews. According to the results, the posttest academic achievement and Motivation Resources and Problems Scale mean scores of the students in the intervention group were significantly higher than those of the control group (P < .05). In the analysis of the qualitative, three main themes emerged: We felt fortunate that it increased information retention,” “We felt like we were in real practice environment,” and “It made us feel that we were nurses.” The results showed the use of video-based simulation can be suggested as a strategy to promote classroom teaching and engage students.
AtıfScopus5WoS3OpenAlex4
İncele - MakaleAçık Erişim2024Scopus SJRQ2The novel numerical solutions for time-fractional Fornberg-Whitham equation by using fractional natural transform decomposition method
Alkan, Aslı; Anaç, Halil
The time-fractional partial differential equations were solved by the fractional natural transform decomposition method. Fractional derivatives are Caputo sense. The Fornberg-Whitham equation is a generalization of the Korteweg-de Vries (KdV) equation, which describes the propagation of long waves in shallow water. It includes higher-order dispersion terms, making it applicable to a wider range of dispersive media the fractional natural transform decomposition method (FNTDM) was also used to examine applications, and the solutions obtained by this method have been compared to those obtained by the variational iteration method, fractional variational iteration method, and homotopy perturbation method. In addition, the MAPLE package drew graphs of the solutions of nonlinear time-fractional partial differential equations, taking into account physics. The method described in this study exhibited a notable degree of computational precision and straightforwardness when used to the analysis and resolution of intricate phenomena pertaining to fractional nonlinear partial differential equations within the domains of science and technology.
AtıfScopus10WoS6OpenAlex13İncele - MakaleAçık Erişim2024Scopus SJRQ1Optimizing Memristor-Based Synaptic Devices for Enhanced Energy Efficiency and Accuracy in Neuromorphic Machine Learning
Gökgöz, Baki; Aydin, Tolga; Gül, Fatih
The traditional Von Neumann computing architecture, which necessitates data transfer between external memory and the processor, incurs significant energy and time costs when running deep learning (DL) and machine learning (ML) architectures. The primary issue with the energy and time efficiency of this architecture stems from the frequent and intensive data transfers between memory and the processor. Therefore, memristive synaptic devices are utilized to overcome this energy and time inefficiency while performing cognitive tasks. The fundamental working principle of memristive devices is to reduce the need for data transfer by combining memory and processing in the same location, thereby significantly decreasing both energy consumption and the time required for operations. However, to achieve the desired level of efficiency in terms of energy and time consumption from neuromorphic systems, the performance of these systems needs to be further improved with respect to accuracy and test error rates for classification applications. Achieving high accuracy performance in such deep learning or machine learning models necessitates optimization processes not only at the hardware level but also at the algorithmic level. In this context, this paper presents a comprehensive examination and comparison of the frequently used SGD and its momentum variants for deep learning and machine learning applications in memristor-based neuromorphic computing systems. The study thoroughly investigates the performance of critical metrics such as the learning properties, energy efficiency, and accuracy rates of the nano-scale titanium dioxide (TiO2) based synaptic device. The experimental results for the MNIST dataset showed AdaDelta 89.48%, AdaGrad 79.00%, Adam 79.13%, AdaMax 79.68%, Momentum 88.55%, Nadam 81.20%, RMSprop 84.91% and SGD 89.47% accuracy. The experimental results for the CIFAR dataset showed AdaDelta 90.51%, AdaGrad 82.08%, Adam 83.10%, AdaMax 81.76%, Momentum 91.25%, Nadam 82.45%, RMSprop 88.11% and SGD 90.21% accuracy. 2024 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.
AtıfScopus11WoS8OpenAlex13İncele - MakaleYalnız künye2024Scopus SJRQ2Effects of combining phosphorus (P) and zinc (Zn) fertilization on P-Zn distribution and yield in safflower
Korkmaz, Kursat; Kılıç, Rahman; Akgün, Mehmet; Kara, Şevket Metin
The interaction of P and Zn is a crucial factor affecting plant growth and yield. The aim of this study was to investigate the combined effects of P and Zn on P-Zn distribution in safflower tissues and seed yield. A two-year study was conducted in farmer fields in northeastern Turkey during 2014 and 2015 years. P applications consisted of four levels (0, 3, 6 and 9 kg P2O5 da−1) that were allotted to the main plots. Sub-plots were composed of three Zn levels (0, 0.5 and 1 kg Zn da−1). The results showed that P and Zn applications had a significant effect on the P and Zn concentration of straw, head, seed, and yield. P concentration in straw, head, and seed increased significantly with increasing P and Zn levels. Zn concentration decreased with high P levels compared to the control, while it increased with increasing Zn levels regardless of P application. At low P levels, yield did not respond to Zn treatments; however, at high P doses, Zn application resulted in a dramatic increase in yield compared to the control. In order to increase seed yield, instead of P and Zn sole application, their combined application was very effective, and doses of 9 kg P2O5 da−1 and 0.5 kg Zn da−1 showed the optimum performance. In conclusion, this study revealed that in P- and Zn-deficient soil, P treatments increased seed yield remarkably, but the combined application of P and Zn resulted in even higher yield increases.
AtıfScopus3WoS3OpenAlex8İncele - MakaleAçık Erişim2024Scopus SJRQ1Enhancing brain tumor classification through ensemble attention mechanism
CELIK, Fatih; CELIK, Kemal; CELIK, Ayse
Brain tumors pose a serious threat to public health, impacting thousands of individuals directly or indirectly worldwide. Timely and accurate detection of these tumors is crucial for effective treatment and enhancing the quality of patients’ lives. The widely used brain imaging technique is magnetic resonance imaging, the precise identification of brain tumors in MRI images is challenging due to the diverse anatomical structures. This paper introduces an innovative approach known as the ensemble attention mechanism to address this challenge. Initially, the approach uses two networks to extract intermediate- and final-level feature maps from MobileNetV3 and EfficientNetB7. This assists in gathering the relevant feature maps from the different models at different levels. Then, the technique incorporates a co-attention mechanism into the intermediate and final feature map levels on both networks and ensembles them. This directs attention to certain regions to extract global-level features at different levels. Ensemble of attentive feature maps enabling the precise detection of various feature patterns within brain tumor images at both model, local, and global levels. This leads to an improvement in the classification process. The proposed system was evaluated on the Figshare dataset and achieved an accuracy of 98.94%, and 98.48% for the BraTS 2019 dataset which is superior to other methods. Thus, it is robust and suitable for brain tumor detection in healthcare systems.
AtıfScopus42WoS21OpenAlex42İncele - MakaleAçık Erişim2024Scopus SJRQ1Damage assessment of Siverek Castle during the Kahramanmaraş Earthquakes (Mw 7.7 and Mw 7.6) on 06 February 2023: Remediation and strengthening proposals
Nasery, Mohammad Manzoor; Çelik, Muhammet; Şadoğlu, Erol
On February 6, 2023, two significant earthquakes with magnitudes (Mw) of 7.7 and 7.6 struck Turkey, occurring nine hours apart. In addition to the tragic loss of over 50,000 lives in the earthquakes centered in Kahramanmaraş, hundreds of thousands of engineering structures, such as residences, schools, hospitals, historical landmarks, highways, and more, were severely damaged. This study assesses the damages and risk scenario following the Kahramanmaraş earthquakes concerning Siverek Castle. In addition, remediation and strengthening proposals, required to eliminate the damage and the possible risk, have been developed. The initial stage involved observational damage assessments on the castle and surrounding slopes as part of field studies, identifying five different types of damage and potential risks. Subsequently, a precise 3D digital model of the damaged castle and its slopes was generated using the digital photogrammetry method. Additionally, geological and geophysical studies were conducted in the field to determine the characteristics of the mound structure, historical castle walls, soil and rock on the slope. Non-destructive, geophysical methods consisting Vertical Electrical Sounding (VES), Seismic Refraction Method (SRM) and Multichannel Analysis of Surface Waves (MASW) measurements were specifically employed in the area with historical remnants. To verify the obtained data, five boreholes were drilled in the lower parts of the slope, and experimental studies were conducted to determine the soil and rock material properties of the slope. In the numerical studies, a total of 54 2D stability analyses were performed under static, long-term static, and dynamic conditions. Additionally, 1000 different probabilistic rockfall analyses were conducted, both in 2D and 3D, to calculate the run-out distance, bounce height, velocity, and kinetic energies of the blocks that fell or were about to fall during the earthquake. In the final stage of the study, remediation and strengthening recommendations were prepared for the strengthening of the fortification walls and slopes where failures occurred, and stability analyses were conducted. Consequently, a design proposal recommending five distinct approaches to remediate and strengthen the castle and slopes impacted by the Kahramanmaraş earthquakes was endorsed by the relevant authorities, and construction has commenced. When the remediation and strengthening works are completed, the security of the cultural heritage will be ensured, and it is planned to be opened to visitors.
AtıfScopus21WoS19OpenAlex20İncele - MakaleAçık Erişim2024Scopus SJRQ2A new species of Buresilia (Opiliones, Phalangiidae) from Turkey
Kurt, Kemal; Kurt, Pinar
A new harvestman species, Buresilia gumushanensis sp. nov. (Opiliones: Phalangiidae), is described based on male specimens collected from Gümüşhane province, Turkey. Detailed descriptions, diagnostic features and pictures of the new species are provided, together with mitochondrial cytochrome c oxidase subunit I (COI) sequences. The phylogenetic tree constructed using the COI gene region revealed the phylogenetic position of the genus Buresilia within the family Phalangiidae. In addition, the new species is compared with known species of the genus Buresilia.
- MakaleAçık Erişim2024Scopus SJRQ2Enterococcus durans SL70, a Novel Exopolysaccharide Producer from Traditional Sourdough Fermentation of Einkorn (Triticum monococcum L. ssp. monococcum)
Genc, Berna; Karatas, Seyda Merve; Tunç, Merve Tuğçe
Research background. Given the potential of microbial exopolysaccharides from lactic acid bacteria in various industrial processes, alternative sources for the isolation of lactic acid bacteria are highly topical. In this study, we used a traditional sourdough from einkorn (Triticum monococcum L. ssp. monococcum) as a source of lactic acid bacteria for the isolation, identification and determination of exopolysaccharide producers. Experimental approach. The sourdough was prepared from einkorn according to the traditional method. Lactic acid bacteria were isolated and purified using the single colony technique on MRS and M17 media. The isolates were characterised using matrix-assisted laser desorption ionization-time of flight mass (MALDI-TOF) spectrometry. All isolates were analysed for extracellular polysaccharide production and one isolate was selected for purification and characterisation of its polysaccharide. Results and conclusions. The isolates were identified as Lactobacillus plantarum, L. paraplantarum, L. brevis, Pediococcus pentosaceus, Enterococcus faecium and E. durans. The production of exopolysaccharides by all lactic acid bacteria was evaluated and it was found that all strains (except one) were capable of producing exopolysaccharides. One polysaccharide (EPS-SL70) was purified from the isolates of E. durans SL70. This anionic heteropolysaccharide had, in addition to the carbohydrate backbone, a protein structure that did not contain nucleic acid. The carbohydrate backbone consisted of mannose, glucose, rhamnose, arabinose, xylose and galactose. Novelty and scientific contribution. The microbial flora of traditional einkorn sourdough has been identified in this study and represents the first report on the exopolysaccharide production by lactic acid bacteria in traditional einkorn sourdough. Additionally, Enterococcus durans from einkorn sourdough was identified as a new exopolysaccharide producer.
AtıfScopus3WoS2OpenAlex4İncele - MakaleYayıncıda açık erişim2024Scopus SJRQ1Public's social media use during the Kahramanmaraş earthquakes on 6 February 2023
Mızrak, Sefa
Social media facilitates crisis management and emergency response efforts by disseminating disaster information during disasters. Understanding the positive and negative contributions of social media to disaster management after devastating disasters will make social media more effective and efficient for crisis management in the future. The objective of this study was to investigate the public's social media use in the 15-day period after the earthquakes that occurred on February 6, 2023, in Türkiye. The study was designed both quantitatively and qualitatively. The data were collected from 1698 people residing in Türkiye via a survey method and analyzed via descriptive, ordinal logistic regression, and thematic analysis. The thoughts of 245 participants regarding social media use were analyzed qualitatively. The results showed that social media was employed as a powerful resource for sharing information after the earthquakes. The participants used Instagram the most and followed the social media accounts of the institutions the most. Posting the physical and psychological damage of earthquakes and humanitarian aid negatively affected the participants and caused them to think that social media was useless. Due to the information shared by social media phenomena and nongovernmental organizations, the participants stated that social media was useful after the earthquakes. For people to share posts that will contribute to search and rescue, aid and damage assessment on reliable and high-follower social media accounts, disaster managers, scientists and policy makers should understand communities' usage intentions, satisfaction and criticism regarding social media accounts and platforms during previous disasters.
AtıfScopus15WoS13OpenAlex20İncele - MakaleAçık Erişim2024Scopus SJRQ1Prediction of effect of fabrication parameters on the properties of B4C ceramic particle reinforced AA2024 matrix nanocomposites using neural networks
Varol, Temel; Çanakçı, Aykut; Özşahin, Şükrü; Beder, Murat; Akçay, Serhatcan Berk
In the present study, a prediction model was created to predict the impact of B4C content, milling time and matrix size on the hardness and density of AA2024-B4C nanocomposites produced by means of flake powder metallurgy. The process involved synthesizing AA2024-B4C nanocomposite powders by mechanical milling followed by preparing nanocomposites by hot pressing. The matrix size of the AA2024 alloy powders, the milling time, and the B4C content were selected as the input parameters. On the other hand, the density and the hardness of the AA2024-B4C nanocomposites were designed as the output parameters. The results showed that the sintered density is significantly improved by decreasing matrix size. It was found that density of AA2024–3 wt%B4C nanocomposites is lower than AA2024–1 wt%B4C nanocomposites. However, the hardness of AA2024–3 wt%B4C nanocomposites is better than AA2024–1 wt%B4C nanocomposites. The AA2024-B4C nanocomposite prediction model could predict hardness and density with a mean absolute percentage error (MAPE) of 0.32% and 1.38%. The results show that the ANN model is a useful tool for the matrix size effect prediction, milling time and B4C content on the density and hardness of AA2024-B4C nanocomposites prepared by flake powder metallurgy.
AtıfScopus6WoS5OpenAlex6İncele - MakaleAçık Erişim2024Scopus SJRQ1In-plane crushing behavior and energy absorption of CFRP honeycombs with different core topologies
Pehlivan, Levent; Baykasoğlu, Cengiz
The in-plane crushing behavior and energy absorption performance of carbon fiber reinforced polymer (CFRP) honeycombs with different core topologies were experimentally investigated under uniaxial loading conditions. Three types of CFRP honeycomb core topologies (i.e. circular, square and hexagonal) with different cell wall thicknesses and heights were considered in the designs. The honeycomb samples were fabricated by the molding and bonding process, which is widely used in the easy, fast and economical manufacturing of thin-walled honeycomb structures. A total of twenty-seven sample groups were experimentally tested for each loading condition, in which honeycomb samples with different core topologies were designed to have almost the same weights for a meaningful comparison. The experimental results revealed that all honeycomb designs have higher in-plane compression strength in the expansion direction, and hexagonal honeycombs showed the highest strength and energy absorption performance in both directions due to their stable load-carrying capacity and outstanding force efficiency. In particular, the experimental findings showed that the crushing strength and the specific energy absorption of CFRP honeycomb structures can be improved up to 6.1 and 4.2 times, respectively, by properly adjusting the cell wall thickness and height parameters. The results also revealed that the proposed lightweight CFRP honeycombs with the structural densities of 155–283 kg/m3 showed better in-plane crushing performance than many competing cellular topologies.
AtıfScopus27WoS26OpenAlex28İncele - MakaleAçık Erişim2024Scopus SJRQ1The impact of implementing backbone architectures on fracture segmentation in X-ray images
Turk, Salih; Bingol, Ozkan; Coskuncay, Ahmet; Aydin, Tolga
X-ray imaging is widely utilized for the detection of bone fractures due to its affordability, rapid processing capabilities, broad accessibility, and ease of use. Despite these advantages, the intricate analysis of X-ray images necessitates advanced computational techniques to fully exploit their rich informational content. Notably, accurate segmentation of these images plays a critical role in aiding medical professionals with precise diagnoses and effective treatment planning. This study examines the impact of integrating different backbone architectures for the task of fracture segmentation in X-ray images. Specifically, the research focuses on enhancing the widely-used DeepLabV3 model by incorporating pre-trained networks such as ResNet50, ResNet101, and MobileNetV3 into the encoder component to improve feature extraction and segmentation accuracy. The FracAtlas dataset, which presents unique challenges due to its small size and the diversity of fractures from various anatomical regions, was employed for model evaluation. Data augmentation techniques were implemented to expand the dataset, and an additional subset focusing on cropped images of fracture areas was developed. The models were trained over 50 epochs, and their performance was assessed using metrics such as Intersection over Union (IoU), loss values, and Dice scores. The results indicate that the DeepLabV3 model with ResNet-based backbones achieved IoU values exceeding 0.93 on the original dataset and demonstrated outstanding performance on the augmented and cropped datasets, with AUC values reaching up to 0.99. The study also highlights the computational complexity of the models, with ResNet101 exhibiting the highest time complexity, while MobileNetV3 was the most efficient in terms of processing time and memory consumption.
AtıfScopus8WoS6OpenAlex6İncele - MakaleAçık Erişim2024Scopus SJRQ2Optimizing Advanced High-Strength Steel Joints via Regional Rapid Cooling in Resistance Spot Welding
Hıdıroglu, Mehtap; Aydın, Kemal; Kahraman, Nizamettin
During resistance spot welding (RSW), the thermal cycles that occur cause microstructural differentiations in the heat-affected zones of martensitic steels, leading to internal stresses. In this context, a new and innovative methodology has been developed to minimize the adverse effects of heterogeneous hardness changes in the welding area on joint durability. This methodology utilizes a unique prototype setup based on the regional rapid cooling (RRC) process, which is integrated into the welding machine and operates in synchronization with the machine during the process. Through this setup, the aim is to effectively control the microstructure and hardness values in the welding area. This innovative approach presents potential improvements in the field of welding technology by aiming to optimize material performance during the welding process. According to microstructure results, the RRC process has narrowed the heat-affected zone to 1.27 mm, increased the hardness values by 9.2%, showed a 3% increase in tensile-shear strength, a 9% increase in cross-tension strength, and based on fatigue strength results, no fractures occurred in all specimens subjected to a force of 0.3 kN.
AtıfScopus4WoS3OpenAlex4İncele - MakaleAçık Erişim2024Scopus SJRQ2Innovations in dairy technology: probiotics in Turkish white cheese production
Mazlum, Halit; Atasever, Mustafa
Cheese offers significant advantages as a probiotic carrier food compared to fermented milk and yoğurt due to its fat content, solid matrix, higher pH, low oxygen levels, and longer shelf life. This study examined Turkish white cheeses ripened with both classical starter culture (Lactococcus lactis subsp. lactis and Lactococcus lactis subsp. cremoris) and various probiotic cultures (Lactobacillus acidophilus, Lactobacillus casei, Lactobacillus paracasei, and Bifidobacterium bifidum). The quality and functional properties of these cheeses were investigated to evaluate the effect of adding probiotics to traditional starter culture and their potential for use as carrier food for probiotics. During the 90-days ripening period, the numbers of L. acidophilus, L. casei, L. paracasei, and B. bifidum were determined to be in the range of 8.09 ± 0.34–8.65 ± 0.30, 7.19 ± 0.28–8.12 ± 0.90, 7.01 ± 1.45–8.73 ± 0.98, and 7.16 ± 1.10–8.21 ± 1.19 log cfu/g, respectively. The study found that probiotic levels in the cheese remained above the effective threshold (≥ 107 cfu/g) throughout the ripening process. This was accompanied by an increase in water-soluble nitrogen, an indicator of proteolysis, leading to higher ripening index values in all cheese samples. In terms of sensory evaluation, cheeses with L. acidophilus and L. paracasei were particularly well-received, scoring higher (7.90 ± 0.30–8.47 ± 0.12, 7.80 ± 0.34–8.75 ± 0.12, respectively) in taste and aroma than the others. Overall, probiotics positively influenced the quality and functional properties of the white cheese. Notably, the L. casei ATCC 393 strain, used for the first time in Turkish white cheese production, proved highly compatible with existing production technologies. It was concluded from the study that Turkish white cheese is a suitable food for transporting probiotics to the intestinal environment.
AtıfScopus5WoS5OpenAlex6İncele - MakaleAçık Erişim2024Scopus SJRQ1Different gait combinations based on multi-modal deep CNN architectures
Yaprak, Büşranur; Gedikli, Eyüp
Gait recognition is the process of identifying a person from a distance based on their walking patterns. However, the recognition rate drops significantly under cross-view angle and appearance-based variations. In this study, the effectiveness of the most well-known gait representations in solving this problem is investigated based on deep learning. For this purpose, a comprehensive performance evaluation is performed by combining different modalities, including silhouettes, optical flows, and concatenated image of the Gait Energy Image (GEI) head and leg region, with GEI itself. This evaluation is carried out across different multimodal deep convolutional neural network (CNN) architectures, namely fine-tuned EfficientNet-B0, MobileNet-V1, and ConvNeXt-base models. These models are trained separately on GEIs, silhouettes, optical flows, and concatenated image of GEI head and leg regions, and then extracted GEI features are fused in pairs with other extracted modality features to find the most effective gait combination. Experimental results on the two different datasets CASIA-B and Outdoor-Gait show that the concatenated image of GEI head and leg regions significantly increased the recognition rate of the networks compared to other modalities. Moreover, this modality demonstrates greater robustness under varied carrying (BG) and clothing (CL) conditions compared to optical flows (OF) and silhouettes (SF). Codes available at https://github.com/busrakckugurlu/Different-gait-combinations-based-on-multi-modal-deep-CNN-architectures.git
AtıfScopus4WoS3OpenAlex4İncele - Derleme MakaleYayıncıda açık erişim2024Scopus SJRQ2An overview memristor based hardware accelerators for deep neural network
Gökgöz, Baki; Gül, Fatih; Aydın, Tolga
The prevalence of artificial intelligence applications using artificial neural network architectures for functions such as natural language processing, text prediction, object detection, speech, and image recognition has significantly increased in today's world. The computational functions performed by artificial neural networks in classical applications require intensive and large-scale data movement between memory and processing units. Various software and hardware efforts are being made to perform these operations more efficiently. Despite these efforts, latency in data traffic and the substantial amount of energy consumed in data processing emerge as bottleneck disadvantages of the Von Neumann architecture. To overcome this bottleneck problem, it is necessary to develop hardware units specific to artificial intelligence applications. For this purpose, neuro-inspired computing chips are believed to provide an effective approach by designing and integrating a set of features inspired by neurobiological systems at the hardware level to address the problems arising in artificial intelligence applications. The most notable among these approaches is memristor-based neuromorphic computing systems. Memristors are seen as promising devices for hardware-level improvement in terms of speed and energy because they possess non-volatile memory and exhibit analog behavior. They enable effective storage and processing of synaptic weights, offering solutions for hardware-level development. Taking into account these advantages of memristors, this study examines the research conducted on artificial neural networks and hardware that can directly perform deep learning functions and mimic the biological brain, which is different from classical systems in today's context.
AtıfScopus16WoS13OpenAlex16İncele - MakaleAçık Erişim2024Scopus SJRQ1Enhancing the performance of parabolic trough solar collectors: Cost-effective innovative designs for sustainable energy harvesting
Karaağaç, Mehmet Onur; Akıncı, Burak; Ergün, Alper
This study aims to improve the performance and stability of parabolic trough solar collectors (PTSC), especially those with heat storage capacity. Three different receiver tube designs have been meticulously developed to achieve this goal. As a result of the research, the Black surface (BS) -PTSC and PTSC- Paraffin wax (PW) systems achieved 26.5% and 56.8% more thermal energy flow, respectively, compared to the conventional PTSC. In addition, while the average thermal efficiencies of the PTSC, BS-PTSC, and PTSC-PW systems were found to be 11.2%, 14.1%, and 16.9%, respectively, the average exergy efficiencies of the PTSC, BS-PTSC, and PTSC-PW were 1.4%, 1.9%, and 2.3%. Painting the black copper pipe and filling the receiver tube with paraffin wax PCM increased thermal and exergy efficiency. Besides, comparing the temperature differences based on the PTSC system, it was found that BS-PTSC and PTSC-PW systems have 12.3% and 16.4% higher tank temperatures, respectively. The findings of this research have demonstrated the potential of parabolic trough solar collectors equipped with heat storage. It has also increased the sustainability index in terms of sustainability and reduced CO2 emissions into the atmosphere. Furthermore, it has been shown that these simple and inexpensive designs, without significant modifications to the system, can achieve high thermal performance without unnecessary expensive components.
AtıfScopus23WoS20OpenAlex24İncele - MakaleAçık Erişim2024Scopus SJRQ2Corrosion and adhesion properties of MAO-coated LA91 magnesium alloy
Sukuroglu, Suleyman; Sukuroglu, Ebru Emine; Totik, Yasar; Gulten, Gokhan; Efeoglu, Ihsan; Avci, Selcuk
Magnesium–lithium alloy is used in different areas of industry and is known as a super light metallic engineering material. However, the use of these alloys is limited due to their surface properties under extreme loads and aggressive environments. Surface treatments can be applied to these alloys to increase their usage areas and improve their weak surface properties. In this study, the micro-arc oxidation method was applied to improve the surface properties of LA91 alloy. The corrosion and adhesion behaviour of the coated samples were investigated. The lowest corrosion current density in the coatings was obtained under Experiment 3. Experiment 3 has the highest Lc2 value due to the coating thickness and the denser and smaller diameter pores of the functional intermediate layer.
AtıfScopus15WoS14OpenAlex16İncele - MakaleAçık Erişim2024Scopus SJRQ1Accuracy assessment of UAV-based documentation of archaeological site: Kültepe-Kaneš
Günen, Mehmet Akif; Kulakoğlu, Fikri; Besdok, Erkan
High quality 2D/3D metric documentation of archaeological sites is used in many different applications such as archaeological-heritage management, digital archaeological excavation planning, orthophotographic documentation, and ancient Digital Surfaces Models (DSM) research. Structure-from-Motion based photogrammetry (SfM) is an indirect geodesic measurement technique based on multiple view image processing using high-level automation techniques. Using SfM to generate the high accuracy 2D/3D data needed for digital documentation of archaeological cultural heritage is relatively practical, economical, and fast. Factors such as the number of ground control points and their distribution to the study area, the robustness of the camera system model parameters, and the analytical model of the photogrammetric triangulation method used affect the accuracy of the data produced using SfM-photogrammetry. Kültepe-Kaneš, the center of the ancient Kingdom of Kaneš, which is located in central-Anatolia, was an Assyrian Trade Colony active between ca. 2000 BC and 1700 BC. The site, which was the center of the Old Assyrian trade colonies in Anatolia and one of the most important sites in ancient history, has been under excavation for the last 75 years. In this paper, high accuracy digital documentation of the Kültepe-Kaneš archaeological excavation area was made using different SfM methods. Statistical analysis revealed no significant difference in accuracy between Real-Time Kinematic (RTK) and Post-Process Kinematic (PPK) methods for the study area. This suggests that either PPK, RTK, or aerial triangulation with Ground Control Points (GCPs) can be employed to generate orthophotos and DSMs for archaeological sites with relatively flat surface areas, as long as a sufficient number of uniformly distributed GCPs are used.
AtıfScopus10WoS8OpenAlex5İncele