Sürdürülebilir Kalkınma Amaçları

• 4
• 3
• 2
• 1
• 1
• 1
• 1
• 1

• MakaleAçık Erişim2026/r/munzur/6091
  Sentiment Analysis of Monkeypox Tweets Using a Hybrid CNN-BiGRU Based Deep Learning Model

  Can, Umit

  Recently, epidemics have disrupted people's lives. Following the COVID-19 pandemic, cases of monkeypox, a rare disease, began to appear worldwide. These incidents raised societal tension and anxiety. Understanding public attitudes, sentiments, and perceptions regarding the epidemic is essential for developing and implementing effective policies and countermeasures. Online social media platforms are essential venues for expressing feelings and views. In particular, Twitter provides valuable information for measuring societal sentiment. Machine learning and deep learning methods have recently been widely used in social network analysis. Deep learning models, which deliver strong performance, particularly on complex and nonlinear problems, are used in natural language processing and text mining. In this study, a Convolutional Neural Network Bidirectional Gated Recurrent Unit (CNN-BiGRU) hybrid deep learning model was developed by combining a CNN and a BiGRU and applied for the monkeypox sentiment analysis. The dataset was labeled as positive, negative, or neutral with Valence Aware Dictionary and sEntiment Reasoner (VADER). In addition, FastText and Term Frequency-Inverse Document Frequency (TF-IDF) word-embedding methods were used for feature extraction, and the performance of machine-learning and deep-learning methods was evaluated separately. As a result of the experimental studies, the FastText-CNN-BiGRU model obtained the highest results with 0.9382 accuracy, 0.9347 macro precision, 0.9367 macro recall, 0.9355 macro F-score, and 0.9875 macro ROC-AUC. The FastText-CNN model was the second most successful, achieving 0.9303 accuracy, 0.9268 macro precision, 0.9280 macro recall, 0.9271 macro F-score, and 0.9862 macro ROC-AUC. The FastText-BiGRU model was the third most successful, achieving 0.9262 accuracy, 0.9224 macro precision, 0.9255 macro recall, 9236 macro F-score, and 0.9838 macro ROC-AUC.

  İncele
• MakaleAçık Erişim2024/r/munzur/6314
  Application of Deep Learning for Voice Command Classification in Turkish Language

  Çelik, Yusuf

  In this study, a deep learning model was developed for the recognition and classification of voice commands using the Turkish Speech Command Dataset. The division of training, validation, and test sets was carried out on an individual basis. This approach aims to prevent the model from memorizing and to enhance its generalization capability. The model was trained using Mel-Frequency Cepstral Coefficients (MFCC) features extracted from voice files, and its classification performance was evaluated in detail. The findings indicate that the model successfully classifies voice commands with a high accuracy rate, achieving an overall accuracy of 92.3% on the test set, highlighting the potential of deep learning approaches in voice recognition technologies

  AtıfOpenAlex6

  İncele
• MakaleAçık Erişim2024/r/munzur/6004
  Experimental Investigation of Rejuvenated Asphalt Mixtures Using Bio-Oils from Different Biomass Sources

  Altundoğan, Hamdi Soner; Furtana, Beyza; Yılmaz, Mehmet

  Asphalt mixes containing Recycled Asphalt Pavement (RAP) materials are generally harder than traditional mixes. Different rejuvenators are used to soften recycled asphalt pavement by reducing this hardness. In this study, recycled asphalt pavement was added to bituminous hot mixtures at 3 different rates (25%, 50% and 75%). To rejuvenate bituminous hot mixtures containing RAP, three different rejuvenators (pine cone, olive pomace and wheat straw) were added to the mixtures. This study investigated the effect of asphalt mixtures containing RAP and rejuvenator on the mechanical properties. Marshall test and moisture damage test were performed to examine the mechanical properties of asphalt mixture samples. As the bio-oil content in asphalt mixtures increases, the stability values of the mixtures decrease. As the bio-oil ratio in asphalt mixtures increases, tensile strength (TS) values decrease in both unconditioned and conditioned mixtures. While the increase in bio-oil reduces the tensile strength ratio, the shrinkage ratio of mixtures prepared with RAP increases. The bio-oil derived from pomace has been identified as the most effective rejuvenator among those tested.

  • 
  AtıfOpenAlex1·TR Dizin1

  İncele
• MakaleAçık Erişim2023/r/munzur/6484
  An Optimization Approach for A Biogas Supply Chain using Goal Programming and Mixed Integer Linear Programming

  Derse, Onur; Göçmen, Elifcan

  Environmental concerns prompt the world for a transition to renewable energy sources from fossil energy. Reducing the dependency on non-renewable sources of energy is prerequisite for the sustainable world and less environmental pollution. Biogas energy, which is one of the most important renewable energy sources, is produced by burning organic wastes and can be used in many different fields. In this study, a two-stage approach is undertaken to optimize a biogas supply chain design by incorporating of 30 districts in Izmir. In the first stage, the selection of the most suitable biogas plants is considered by the goal programming approach, which is of great importance to decide the optimal location with high energy potential. The most suitable sites for the biogas plants are obtained as Konak and Narlıdere districts. In the second stage, the location problem of the biogas vehicle charging stations (BVS) for biogas vehicles is handled considering the results of the first stage using mixed integer linear programming (MILP) approach. Computational results demonstrate that it would be more appropriate to establish BVS in 12 districts of İzmir. The model and solution approach are pioneering for supply chain problems and an efficient tool for renewable energy plans.

  • 
  • 
  • 
  • 
  AtıfOpenAlex3

  İncele
• MakaleAçık Erişim2023/r/munzur/6483
  Lichens as Biomonitors of Air Pollutants Deposition: Strategically Important Element Pollution

  Topal, Murat; Topal, E.Işıl Arslan; Aslan, Ali; Öbek, Erdal

  Investigation of various species of lichen as biomonitors of air pollutants deposition and evaluation of element pollution were aimed. Maximum accumulation was 43.9±2.1 mg/kg in X. somloensis. Strontium in lichen species was quite high. Percentages of strontium for L.pulmonaria, C.furcata, U.longissima, X.somloensis, and F.caperata were between 58% and 78% indicating the efficient accumulation of strontium. Lichens were also accumulated strategically important elements. Maximum contamination factors in lichens were for strontium and tantalum. Maximum contamination factors of hafnium, niobium, lithium, gallium, and bismuth were for L. pulmonaria while maximum contamination factors of strontium, yttrium, scandium, and cerium were for X.somloensis. Maximum contamination factor of tantalum was for F.caperata. Enrichment factors for L.pulmonaria, C.furcata, and F.caperata were higher than 10, only for bismuth while lower than 10 for U.longissima. Enrichment factors for X.somloensis were higher than 10. Pollution load indexes for L.pulmonaria and U.longissima were higher than 1. Presence of strategically important elements in lichens showed that lichen species can be used as biomonitors of air pollutants.

  • 
  AtıfOpenAlex1

  İncele
• MakaleAçık Erişim2023/r/munzur/6414
  The Antioxidant Capacities and Antimicrobial Activities of Some Salvia L. Seeds

  Ökkeş; Yılmaz, Okkes; Yilmaz; Kurşat, Murat; Kirbag, Sevda; Civelek, Şemsettin; Emre, Irfan; Sönmez, Pınar Erecevıt; Emre, Mustafa Yunus

  The goal of present study is to find the penolic contents, antioxidant activities and antimicrobial capacities in the seeds of five Salvia L. taxa two of which are endemics (Salvia euphratica var. leiocalycina and Salvia euphratica var. euphratica). The flavonoid and phenolic acid are determined by using HPLC while the antioxidant activities are determined based on different methods. Also, the antimicrobial activities of some Salvia species are determined by using the well agar method. The current study found that the studied Salvia species have low flavonoid. It has been found that Salvia euphratica var. euphratica has high vanillic acid, ferulic acid and rosmarinic acid among the studied taxa. Similarly, it has been found that Salvia euphratica var. euphratica has high DPPH and ABTS radical scavening capacity in all concentrations. It has been also found that Salvia euphratica var. euphratica has highest total phenolic content (372,63±0,87 µgGAE/mg) whilst Salvia tricholoda has low total phenolic content (46,41±1,71 µgGAE/mg). In addition, this study demonstrated that Salvia tricholoda has lowest metal chelating activity (37,35±0,51%). Furthermore, present study found that the lipid peroxidation levels of the studied Salvia taxa are between 18,21±0,37 mg/kg and 21,03±0,22 mg/kg while it has been found that the antibacterial properties of the Salvia taxa under study are altering.

  • 
  • 
  AtıfOpenAlex1·TR Dizin1

  İncele
• MakaleAçık Erişim2023/r/munzur/5745
  Deep Learning-Based Automatic Helmet Detection System in Construction Site Cameras

  Korkmaz, Adem; Ağdaş, Mehmet Tevfik

  Ensuring worker safety in high-risk environments such as construction sites is of paramount importance. Personal protective equipment, particularly helmets, plays a critical role in preventing severe head injuries. This study aims to develop an automated helmet detection system using the state-of-the-art YOLOv8 deep learning model to enhance safety monitoring in real-time. The dataset used for the study consists of 16,867 images, with various data augmentation and preprocessing techniques applied to improve the model's robustness. The YOLOv8 model achieved a 96.9% mAP50 score, outperforming other deep learning models in similar studies. The results demonstrate the effectiveness of the YOLOv8 model for accurate and efficient helmet detection in construction sites, paving the way for improved safety monitoring and enforcement in the construction industry.

  • 
  • 
  AtıfOpenAlex15·TR Dizin3

  İncele
• MakaleAçık Erişim2022/r/munzur/6541
  The Mechanical and Thermal Behavior of Electrostatic Powder Coating Waste Reinforced Epoxy Composites

  Kismet, Yilmaz; Doğan, Akar

  The present study investigates the mechanical and thermal behavior of polyurethane electrostatic powder coating waste reinforced epoxy composites. Different percentages of electrostatic powder coating waste (3, 6, and 9 wt. %) reinforced epoxy composites were manufactured. The mixture of polyurethane powder coating waste and epoxy was mixed with a magnetic stirrer to ensure that the polyurethane powder coating waste was dispersed well in the epoxy, and then the mixture was placed under vacuum and air bubbles were removed. Tensile and three-point tests were performed to determine the changes in the mechanical properties of the materials, and thermogravimetric analysis was conducted to determine the thermal properties. In addition, images were taken with scanning electron microscopy for morphological features. The study revealed that the three-point flexural strength was increased by up to 8% and 15%, respectively, in the samples with 3 wt% and 6 wt% powder coating waste additives. The material's tensile strength decreased by up to 27% with powder coating waste reinforcement. However, the opposite trend was observed in the modulus of elasticity. Additionally, no significant difference was observed in the thermal properties of the materials. Also, from scanning electron microscopy analysis, it was observed that the inclusion of powder coating waste changed the damage mechanism of the material.

  • 
  • 
  İncele
• MakaleAçık Erişim2022/r/munzur/6485
  Failure-based maintenance planning using bayesian networks: a case study hydraulic turbine

  Yucesan, Melih; Kahraman, Gökhan

  The assessment of existing infrastructures in the energy sector is of great economic importance for the world. The extension of the power generation life of hydroelectric power plants depends on logical decisions regarding the maintenance and renewal of the equipment. For this purpose, a Bayesian network (BN) has been applied to evaluate the failures in the hydraulic turbine to calculate the failure of the turbine. Forty-six nodes have been identified that will affect the operation of the system. Preventive measures have been established for failures with the highest posterior probability. By creating four different cases, failure probabilities and the change of the main fault have been calculated. How much savings could be made in each case is determined with the maintenance. This proposed framework will be guided in determining the maintenance strategies for hydroelectric power plant operators.

  • 
  • 
  AtıfOpenAlex1

  İncele
• MakaleYalnız künye2020/r/munzur/6801
  Cevap Yüzey Yöntemi Kullanılarak Poli(VPi–ko-MA) / Grafen Kompozitlerinin İletkenliğinin Optimizasyonu

  Torgut, Gulben

  Bu çalışmada, öncelikle poli(Vinil pivalat–ko-Maleik anhidrit) [poli(VPi-ko-MA)] kopolimeri serbest radikalikpolimerizasyon yöntemiyle 65 oC’de 24 saat süreyle sentezlenmiştir. FT-IR ile karakterize edilen kopolimerinkütlece farklı miktarlarda Grafen (GF) içeren kompozitleri çözelti döküm tekniği ile hazırlanmıştır. KompozitlerFT-IR ve SEM teknikleri ile karakterize edilmiştir. Uygulanan voltaj, frekans ve GF içeriği arasında kantitatif birilişki elde etmek için cevap yüzey yöntemi (CYY) kullanılmıştır. Ölçülen cevap, kompozitlerin elektriksel (AC)iletkenliğidir. Modeldeki parametrelerin (frekans, voltaj ve GF miktarı) önemi, varyans analizi ile belirlenmiştir(ANOVA). Model, maksimum elektriksel iletkenliği, 1619 Hz frekansta, voltaj 15.56 V'da ve GF miktarı ağırlıkça% 9.99 için 6.93×10-8 S cm-1 olarak öngörmüştür.

  AtıfTR Dizin1

  İncele