Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Uzun, Sevda(7)
- Araz, Onur(6)
- Ozdes, Duygu(6)
- Duran, Celal(5)
- Şahin, Rıdvan(5)
- Kankal, Murat(4)
- Reis, Hatice Catal(4)
- Saydam Eker, Çiğdem(4)
- Şan, Murat(4)
- Alemdag, Selcuk(3)
- Anaç, Halil(3)
- Cakir, Tufan(3)
- Günen, Mehmet Akif(3)
- Ozturk, Kasif Furkan(3)
- Turk, Veysel(3)
- Çelik, Orkun(3)
- Öztürk, Serkan(3)
- Adali, Zafer(2)
- Alemdağ, Selçuk(2)
- Alkan, Hamdi(2)
- Aydin, Aydanur(2)
- Baltacı, Cemalettin(2)
- Bayram, Adem(2)
- Büyüksaraç, Aydın(2)
- Catal Reis, Hatice(2)
- Cebi, S.(2)
- Cevik Onar, S.(2)
- Dağ, Serhat(2)
- Ekici, Lutfiye(2)
- Gül, Abdulkadir(2)
- Kahraman, C.(2)
- Kahraman, Muhammet Mustafa(2)
- Karatas, Seyda Merve(2)
- Kaya, Ayberk(2)
- Khoshelham, Kourosh(2)
- Köseoğlu, Ali(2)
- Melek, Mesut(2)
- Merdan, Mehmet(2)
- Nacar, Sinan(2)
- Ozeken, Sengul Tugba(2)
Yayınlar
- MakaleYalnız künye2022Scopus SJRQ2Detection of damaged buildings after an earthquake with convolutional neural networks in conjunction with image segmentation
Ünlü, Ramazan; Kiriş, Recep
Detecting damaged buildings after an earthquake as quickly as possible is important for emergency teams to reach these buildings and save the lives of many people. Today, damaged buildings after the earthquake are carried out by the survivors contacting the authorities or using some air vehicles such as helicopters. In this study, AI-based systems were tested to detect damaged or destroyed buildings by integrating into street camera systems after unexpected disasters. For this purpose, we have used VGG-16, VGG-19, and NASNet convolutional neural network models which are often used for image recognition problems in the literature to detect damaged buildings. In order to effectively implement these models, we have first segmented all the images with the K-means clustering algorithm. Thereafter, for the first phase of this study, segmented images labeled “damaged buildings” and “normal” were classified and the VGG-19 model was the most successful model with a 90% accuracy in the test set. Besides, as the second phase of the study, we have created a multiclass classification problem by labeling segmented images as “damaged buildings,” “less damaged buildings,” and “normal.” The same three architectures are used to achieve the most accurate classification results on the test set. VGG-19 and VGG-16, and NASNet have achieved considerable success in the test set with about 70%, 67%, and 62% accuracy, respectively.
AtıfScopus22WoS14OpenAlex25
İncele - MakaleYalnız künye2022Scopus SJRQ2Effect of earthquake frequency content on seismic-induced vibration control of structures equipped with tuned mass damper
Araz, Onur; Cakir, Tufan; Ozturk, Kasif Furkan
The main goal of this paper is to investigate the influence of the earthquake frequency content on the optimization of tuned mass damper (TMD) for multi-story buildings. Earthquake frequency content is divided into three groups (i.e., low, intermediate and high frequency content) according to the ratio of peak ground acceleration to the peak ground velocities. Time-domain analyses are performed to obtain the dynamic responses of 10-story and 40-story shear buildings equipped with a TMD under twelve different earthquake records. Advanced firefly algorithm is used to obtain the optimum parameters of the TMD such as the frequency ratio and the damping ratio. The optimization criterion is selected as the minimization of the maximum top story displacement of the building with TMD. The optimum parameters of TMD designed by this paper and its control performance are compared with those of other previous works available in the literature. Compared to the other methods, the optimum TMD designed by this study especially performs better in reducing the maximum top story displacements. Furthermore, it is discussed why TMD is ineffective in reducing the maximum floor accelerations of 40-story building, and then the effect of different mass ratios and objective functions in reducing the maximum responses of both buildings under critical earthquake excitation is investigated in detail. The results also show that the frequency content of earthquake ground motions has a significant effect on the optimum parameters of TMD and its control performance.
AtıfScopus21WoS17OpenAlex18İncele - MakaleAçık Erişim2022Scopus SJRQ2Optimization of three-element tuned mass damper based on minimization of the acceleration transfer function for seismically excited structures
Araz, Onur
The three-element tuned mass damper (T-TMD) is an effective passive control device for single-degree of freedom structures due to harmonic external force. Unlike previous studies, this study aims at proposing a methodology for optimization of T-TMD positioned at the top floor of multi-degree of freedom structures under seismic loads. The equations of motion for a multi-story building controlled by a T-TMD are derived, and the T-TMD is then optimized using an advanced firefly algorithm (AFA) in the frequency domain. The aim of the optimization is to minimize the amplitude of the acceleration transfer function of the top floor of the building. The proposed methodology is implemented in two different shear buildings, and the optimum parameters are then verified by using benchmark earthquakes with different frequency components. The comparisons with the available works illustrate the availability of the AFA. The effect of the mass ratio on the optimum parameters of the T-TMD is also discussed in detail. Numerical results show that the use of the optimum T-TMD is an effective strategy to minimize the maximum structural responses of the multi-story buildings under seismic excitations. In particular, the optimum T-TMD is very effective when the maximum story responses (i.e., displacement and acceleration) occur at the top floor of the building.
AtıfScopus28WoS27OpenAlex27İncele - MakaleAçık Erişim2022Scopus SJRQ2Innovative polygon trend analyses with star graph for rainfall and temperature data in agricultural regions of Turkey
Acar, Emine; Kankal, Murat; Akçay, Fatma; Şan, Murat
Agriculture is affected by climate change, such as extreme increases or decreases rainfall and temperature patterns. It is possible to research that effect by using trend analysis methodologies. This paper investigates trends of monthly total rainfall and mean temperature data of nine selected stations from agricultural regions of Turkey between 1969 and 2020. To the end, the classical Mann–Kendall, Innovative Trend Significance Test (ITST), and Innovative Polygon Trend Analysis (IPTA) with Star Graph methods providing the opportunity to examine seasonal behavior were used for trend analysis. The analysis reveals that about 96% of all monthly rainfall in the Mann-Kendall test has no trend. However, nearly all stations tend to decrease (increase) in November (September) in both innovative approaches. For temperature, it is seen that increasing trend or no trend dominated in general. There were increasing trends in the innovative approaches throughout the year except for April. Temperatures have increased significantly throughout the year in all regions over the last decades. With the help of IPTA, it was also concluded that the seasonal internal variability of rainfall over the entire time and in the last 30 years is quite complex and persists in all agricultural regions. The results show that irregular changes in rainfall and rising temperatures in all stations negatively affected crop yield and/or required more irrigation. In addition, according to the results obtained by comparing trend methods, innovative approaches are very insistent on determining of trend and provide additional information through a visual review of trend behaviors.
AtıfScopus22WoS22OpenAlex26İncele - MakaleAçık Erişim2022Scopus SJRQ2Insights into brewed tea waste as a green and low-priced adsorbent for solid-phase extraction of Cd(II) ions: isotherm, kinetic, and artificial neural network approach
Ozdes, Duygu; Tilki, Nida; Seker, Serdal; Duran, Celal
In the present research, brewed tea waste (BTW) was utilized as a green, low-priced, and abundant adsorbent for separation/preconcentration of Cd(II) ions through solid-phase extraction method from water and foods for the first time. BTW was applied as a natural adsorbent, without using any chelating agent to bind Cd(II) ions or any chemical reagent for its modification. A three-layer artificial neural network model using backpropagation algorithm was utilized to explicate a prediction model for the extraction performance of Cd(II) ions by selecting the input parameters as solution pH, quantity of BTW, sample volume, eluent concentration and volume, and equilibrium time for desorption. The preconcentration factor, relative standard deviation, and detection limit were attained as 100, 3.03%, and 0.56 µg L−1, respectively. It was decided that the Langmuir isotherm model is acceptable to characterize the retention of Cd(II) ions on BTW. This result pointed out that the active binding sites on the BTW surface are homogeneously distributed. Adsorption capacity of BTW was achieved as 41.5 mg g−1 which is higher than several expensive and difficult-to-prepare adsorbents. Adsorption kinetics was elucidated by pseudo-second order kinetic model. After confirmed the accuracy of the method with spike/recovery studies, it was employed for Cd(II) determination in water (stream and sea water) and food (eggplant, lettuce, parsley, apple, and apricot) samples with high accuracy. The inferences of the study proved that the BTW offers a magnificent application prospect in the extraction of Cd(II) ions.
AtıfScopus9WoS9OpenAlex9İncele - MakaleYalnız künye2022Scopus SJRQ2The relationship between the risk of eating disorder and meal patterns in University students
Kabakuş Aykut, Memnune; Bilici, Saniye
Purpose: This study was carried out to evaluate the relation between meal patterns and the risk of eating disorders in university students. Methods: The study was conducted on a total of 331 volunteer students with a mean age of 22.08 ± 1.80 years, 56.5% female. Participants’ sociodemographic characteristics, health information and eating habits like meal skipping and dieting were questioned. Sick, Control, One stone, Fat, Food (SCOFF) Eating Disorders Scale and Eating Disorder Examination Questionnaire (EDE-Q) were used to determine eating behavior disorders, with face to face interviews by the researches. Results: A significant correlation was found between dieting and skipping meals and the risk of eating disorders in both genders (p < 0.05). In addition, when the reasons for skipping meals were questioned, a significant relationship was detected between skipping meals and eating behaviour disorders by 3.285 times (p = 0.000). Also, every unit of increase in body mass index (BMI) values of individuals who participated to the study led to an increase in eating disorders by a factor of 1.262 (p = 0.000). Conclusions: Our findings support concerns about the negative health effects of increasing overweight among university students in accordance with the data that the increase in BMI values led to an increase in eating disorders. Notably a significant correlation was found between dieting, skipping meals and the risk of eating disorders in both genders it is highlighting the need for monitoring and early diagnosis of eating disorders in youth with simple scales like SCOFF. Level of evidence: Level V, cross-sectional descriptive study.
AtıfScopus19WoS17OpenAlex26
İncele - MakaleAçık Erişim2022Scopus SJRQ2A new cryptic species of the Darevskia parvula group from NE Anatolia (Squamata, Lacertidae)
Arribas, Oscar; Candan, Kamil; Kurnaz, Muammer; Kumlutaş, Yusuf; Caynak, Elif Yıldırım; Ilgaz, Çetin
In this study, we re-examine the Darevskia parvula group comprehensively using morphology, osteology and mitochondrial phylogeny, and describe a new endemic species from Turkey: Darevskia tuniyevisp. nov. A total of 257 adult specimens were evaluated for external morphology (scalation and biometry) with univariate (descriptive statistics and ANOVA with post-hoc tests) and multivariate (Discriminant Analysis and ANOSIM) analyses. In parallel, osteological data and molecular analyses using three DNA markers (mitochondrial 16S rRNA and Cyt-b, nuclear Rag-1) were used to complete the description of the new taxon. The molecular phylogenetic analyses indicated that the D. parvula group is composed of three taxa as D. parvula, D. adjarica and D. tuniyevisp. nov., and showed that D. adjarica and D. tuniyevisp. nov. are reciprocal sister taxa. On the other hand, D. adjarica is morphologically very different from other two forms, while D. parvula is hardly distinguishable externally from D. tuniyevisp. nov. Therefore, we can consider that D. parvula and D. tuniyevisp. nov. are cryptic species. These two cryptic species retain their primitive morphology within the group, while D. adjarica has changed, perhaps due to different bioclimatic conditions in its Pleistocene refuge and current area.
AtıfScopus14WoS11OpenAlex11İncele - MakaleYalnız künye2022Scopus SJRQ2InSiNet: a deep convolutional approach to skin cancer detection and segmentation
Reis, Hatice Catal; Turk, Veysel; Khoshelham, Kourosh; Kaya, Serhat
Cancer is among the common causes of death around the world. Skin cancer is one of the most lethal types of cancer. Early diagnosis and treatment are vital in skin cancer. In addition to traditional methods, method such as deep learning is frequently used to diagnose and classify the disease. Expert experience plays a major role in diagnosing skin cancer. Therefore, for more reliable results in the diagnosis of skin lesions, deep learning algorithms can help in the correct diagnosis. In this study, we propose InSiNet, a deep learning-based convolutional neural network to detect benign and malignant lesions. The performance of the method is tested on International Skin Imaging Collaboration HAM10000 images (ISIC 2018), ISIC 2019, and ISIC 2020, under the same conditions. The computation time and accuracy comparison analysis was performed between the proposed algorithm and other machine learning techniques (GoogleNet, DenseNet-201, ResNet152V2, EfficientNetB0, RBF-support vector machine, logistic regression, and random forest). The results show that the developed InSiNet architecture outperforms the other methods achieving an accuracy of 94.59%, 91.89%, and 90.54% in ISIC 2018, 2019, and 2020 datasets, respectively. Since the deep learning algorithms eliminate the human factor during diagnosis, they can give reliable results in addition to traditional methods. Graphical abstract: [Figure not available: see fulltext.]
AtıfScopus170WoS313OpenAlex160İncele - MakaleAçık Erişim2022Scopus SJRQ3Phytoremediation ability of Helichrysum arenarium plant for Au and Ag: case study at Demirören village (Gümüşhane, Turkey)
Vural, Alaaddin; Safari, Semaneh
It was investigated ability of Helichrysum arenarium plant, in phytoextraction, phytostabilization, and phytoremediation in this study. Soil and plant samples were collected from the Demirören alteration site which has the potential of gold mineralization and analyzed for gold and silver. When the results of the analysis were evaluated, it was determined that the gold and silver contents in the soil did not show compatibility with the gold and silver contents of the plants grown at the same point. It was concluded that the high gold and silver concentrations in the plants are related to the hydrothermal alteration and weathering at the point where the plants grow. For investigation of phytoremediation ability of the plant, translocation factor (TF), bio-concentration factor (BCF), and bioaccumulation factor (BAF) were calculated. The values of TF, BAF, and BCF for Ag are equal 0.33, 0.043, and 0.13 and for Au are equal 2.04, 0.59, and 0.29, respectively. So, obtained data show that Helichrysum arenarium is not appropriate for phytoextraction and phytostabilization of gold and silver in this case, but H. arenarium can be used in phyto-mining and for biogeochemical exploration of gold. Considering that the gold and silver concentrations in the developed soil in the study area are low concentrations, it is predicted that a similar study will yield satisfactory-interesting results when it is made in plants grown on the gold mineralization/enrichment areas.
AtıfScopus9WoS9OpenAlex11İncele - MakaleYalnız künye2022Scopus SJRQ2Effect of different objective functions on control performance of tuned mass damper for a high-rise building considering soil–structure interaction
Araz, Onur; Ozturk, Kasif Furkan; Cakir, Tufan
This paper deals with the optimization of the tuned mass damper (TMD) with different objective functions for high-rise building under earthquake motions considering soil–structure interaction (SSI). A study is conducted to search for the TMD that outperforms five objective functions (i.e., OF-1–OF-5) containing combinations of the structural responses and foundation responses. The main goal of the present study is to evaluate and compare the control performance of these five objective functions. The optimum parameters of TMD are obtained by particle swarm algorithm (PSA) to minimize the acceleration transfer function. To determine the dynamic response of a 40-story building under the influence of SSI, six different foundation soil conditions and eight different earthquake records are considered. The results show that the SSI effects on the dynamic response of the high-rise building resting on relatively soft soil types such as SD and SE are of critical importance. It is shown that the effectiveness of the optimum TMD designed by OF-1 is better than the others in suppressing the peak response values for all soil types. After OF-1, the best performances are obtained for OF-3 and OF-5 which yield approximately the same effectiveness. It is also found that different earthquake records, soil types and objective functions are very effective on the effectiveness of TMD.
AtıfScopus22WoS22OpenAlex25İncele - MakaleYalnız künye2021Scopus SJRQ2Enological properties of red wine produced from native Kösetevek grapes (Vitis vinifera L.) cultivated in Eastern Anatolia
Arpa Zemzemoglu, Tuba Eda; Darıcı, Merve; Cabaroglu, Turgut
The aim of this study was to determine the potential of red wine production from the Kösetevek grape variety (Vitis Vinifera L.) cultivated in Elazig province of Turkey and to define the characteristics of Kösetevek wines. To determine the grapes for wine production quality, the general composition, phenolic compounds, aroma compounds and sensory analysis of the wines were carried out. Aroma compounds were performed by solid-phase extraction (SPE) and then analyzed by gas chromatography (GC) along with gas chromatography/mass spectrometry (GC/MS). Results showed that the red wines obtained from Kösetevek grapes consisted of 50 aroma compounds for 2014 vintages and 49 aroma compounds for 2015 vintages. Esters were the main components contributing to the Kösetevek wine aroma along with ethyl hydrogen succinate and ethyl–4–hydroxy butanoate. The amount of total phenolic compounds, total anthocyanin, and the tannin in Kösetevek wines were found to be between 3705.45 and 3015.63 mg/L, 554.25–502.35 mg/L, and 4.5–3.95 g/L at 2014–2015 vintages, respectively. As to sensory evaluation, Kösetevek wines were characterized as a deep purple color, middle to high body, and rich in red fruit (cherries, plums), and dried fruit odors. This study has provided enological properties and aroma characterization of Kösetevek wines. The results of the study showed that Kösetevek wines could be considered as an alternative to other wines obtained from native grape varieties of the region.
AtıfScopus4WoS4OpenAlex4İncele - MakaleYalnız künye2021Scopus SJRQ1Effects of puzzolanic materials in surface paste disposal by pilot-scale tests: observation of physical changes
Bascetin, A.; Adiguzel, D.; Eker, H.; Odabas, E.; Tuylu, S.
There are only a few pilot schemes, especially among scientific studies carried out to solve numerous environmental and ecological problems created by water during tailing storage on the surface. It is extremely important to establish precautions that can be taken, especially in the tailing storage process by examining the physical, chemical, mineralogical, and geotechnical changes that develop due to the effect of moisture in the tailing and surface water. In this study, 2 different pilot-scale designs of storage with no additions (reference) and with binder additions (cement and fly ash) to some layers were observed in field conditions for about 1 year to determine the effects of seasonal changes on paste material. The results of the measurements revealed that the water content of the reference design was ~ 10% higher than that of the design with cement addition at the substrates that provide stability and sudden temperature changes at the top layer of the reference design was found to be ~ 35 °C. Maximum sudden temperature changes in layers with cement addition and layers with cement and fly ash addition were observed to be ~ 15 °C. As a result, the use of cement has made the material more resistant to external factors. However, the study also revealed that fly ash could be used instead of cement with a substitute rate of 50% to reduce the cost for long-term storage in terms of industrial applications.
AtıfScopus22WoS17OpenAlex38İncele - MakaleAçık Erişim2021Scopus SJRQ2A Data-Driven Approach to Control Fugitive Dust in Mine Operations
Kahraman, Muhammet Mustafa; Erkayaoglu, Mustafa
Particulate matter (PM) is one of the main actors related to air pollution caused by surface mining. Fugitive dust, considered as particulate matter that cannot be collected by conventional measures, is classified by the particle size. The Environmental Protection Agency (EPA) categorizes PM as coarse and fine particles based on the particle size being less than 10 μm (PM10) and less than 2.5 μm (PM2.5). Basic operations of surface mining such as drilling and blasting, loading, haulage, and processing are processes that can potentially generate fugitive dust. Regulations and legislations enforce the mining industry to use environmental monitoring systems, fugitive dust level measured by PM10 level as part of this. Air quality monitors are positioned at different locations around surface coal mines and track air quality levels during production. This study introduces a data-driven methodology to handle air quality issues related to fugitive dust at surface coal mines. Data is sourced from different mine equipment in real-time and they are integrated with air quality monitoring systems to provide information to support decisions for fugitive dust. The method is implemented and demonstrated in a case study at a large surface coal mine.
AtıfScopus22WoS18OpenAlex13İncele - MakaleAçık Erişim2021Scopus SJRQ1Diagnosis of COVID-19 and non-COVID-19 patients by classifying only a single cough sound
Melek, Mesut
In the last month of 2019, a new virus emerged in China, spreading rapidly and affecting the whole world. This virus, which is called corona, is the most contagious type of virus that humanity has ever encountered. The virus has caused a huge crisis worldwide as it leads to severe infections and eventually death in humans. On March 11, 2020, it was announced by the World Health Organization that a COVID-19 outbreak has occurred. Computer-aided digital technologies, which eliminate many problems and provide convenience in people's lives, did not leave humanity alone in this regard and rushed to provide a solution for this unfortunate event. One of the important aspects in which computer-aided digital technologies can be effective is the diagnosis of the disease. Reverse transcription-polymerase chain reaction (RT-PCR), which is a standard and precise technique for diagnosing the disease, is an expensive and time-consuming method. Moreover, its availability is not the same all over the world. For this reason, it can be very attractive and important to distinguish the COVID-19 disease from a cold or flu through a cough sound analysis via smartphones which have entered into the lives of many people in recent years. In this study, we proposed a machine learning-based system to distinguish patients with COVID-19 from non-COVID-19 patients by analyzing only a single cough sound. Two different data sets were used, one accessible for the public and the other available on request. After combining the data sets, the features were obtained from the cough sounds using the mel-frequency cepstral coefficients (MFCCs) method, and then, they were classified with seven different machine learning classifiers. To determine the optimum values of hyperparameters for MFCCs and classifiers, the leave-one-out cross-validation (LOO-CV) strategy was implemented. Based on the results, the k-nearest neighbors classifier based on the Euclidean distance (kNN Euclidean) with the accuracy rate, sensitivity of COVID-19, sensitivity of non-COVID-19, F-measure, and area under the ROC curve (AUC) of 0.9833, 1.0000, 0.9720, 0.9799, and 0.9860, respectively, is more successful than other classifiers. Finally, the best and most effective features were determined for each classifier using the sequential forward selection (SFS) method. According to the results, the proposed system is excellent compared with similar studies in the literature and can be easily used in smartphones and facilitate the diagnosis of COVID-19 patients. In addition, since the used data set includes reflex and unconscious coughs, the results showed that conscious or unconscious coughing has no effect on the diagnosis of COVID-19 patients based on the cough sound.
AtıfScopus38WoS26OpenAlex45İncele - MakaleYalnız künye2021Scopus SJRQ2Preparation of melon peel biochar/CoFe2O4 as a new adsorbent for the separation and preconcentration of Cu(II), Cd(II), and Pb(II) ions by solid-phase extraction in water and vegetable samples
Ozdes, Duygu; Duran, Celal
The present research describes the successful preparation of melon peel biochar modified with CoFe2O4 (MPBC/CoFe2O4) followed by its usage as a new sorbent to separate, preconcentrate, and determine the toxic heavy metal ions by magnetic solid-phase extraction. The metal ion desorption was performed by 0.1 M HCl solution with a volume of 5.0 mL. Flame atomic absorption spectrometry (FAAS) was utilized for detection of the analyte levels. SEM–EDX, TEM, XRD, and FTIR techniques were carried out to illuminate the structure of MPBC/CoFe2O4. The fundamental variables affecting the adsorption and elution efficiencies of the analyte ions including solution pH, MPBC/CoFe2O4 amount, type and concentration of eluent, adsorption and desorption equilibrium time, and sample volume were optimized. The detection limits were calculated as 0.41, 1.82, and 3.16 µg L−1 for Cu2+, Cd2+, and Pb2+ ions, respectively, with the relative standard deviation of lower than 4.2%. There were no substantial interference effects on the analyte ion recovery due to the presence of foreign ions at high levels. Five minutes of contact time was adequate to attain the adsorption equilibrium. The adsorption capacity of MPBC/CoFe2O4 was obtained as 106.4, 65.4, and 188.7 mg g−1 for Cu2+, Cd2+, and Pb2+ ions, respectively, by utilizing Langmuir isotherm model. The pseudo-second order model is favorable to identify the adsorption kinetics. The method was validated by spike/recovery test, and then, it was successfully implemented to determine the aforementioned analyte levels in sea and stream water, pepper, black cabbage, eggplant, and tomato samples.
AtıfScopus40WoS38OpenAlex39İncele - Kitap BölümüYalnız künye2021Scopus SJRQ4Safer-Driving: Application of Deep Transfer Learning to Build Intelligent Transportation Systems
Ünlü, Ramazan
Deep learning methods are widely used in the field of transportation as well as in many areas. These days, deep learning methods produce very successful results thanks to big data, where data collection and storage are much easier than in past years. However, it can be quite difficult to collect data or find the right data in some cases. On the other hand, even if the desired data is collected enough, training deep neural networks to learn from these data may not be comfortable in terms of hardware needed for ordinary users. In these cases, transfer learning can be an exit point, which is very popular in deep understanding, especially when the amount of data is limited. In this study, we have aimed to give comprehensive guidance on using a transfer learning strategy to create a detection model to establish a safer transportation system. More specifically, we have developed a classification model to alleviate accidents due to deer on the road. We have implemented VGG-16 convolutional neural network architecture as a part of the structured transfer learning framework. Computational results show that high accuracy performance can be achieved by implementing VGG-16 with the respectively small size of a dataset.
AtıfScopus1OpenAlex2İncele - Kitap BölümüAçık Erişim2021Scopus SJRQ4Energy Policy Recommendations for ASEAN Countries: Empirical Evidence from the Bootstrap Panel Granger Causality Analysis
Adali, Zafer; Korkmaz, Özge; Çelik, Orkun
In social sciences, especially in the economic literature, energy has been one of the most important topics. Energy seems to be dominant on the political and economic agendas because of nearly all economic activities linked to energy. Hence, all economies have endeavored to detect and implement policies to increase their efficiency and mitigate energy’s detrimental effects on the earth. This study’s principal mission is to check the connection between economic growth, non-renewable and renewable energy consumption in ASEAN-5 countries over 1990–2014 to recommend energy-saving policies. Within this view, bootstrap panel Granger causality test is applied. The model results indicate that economic growth causes renewable energy consumption in the Philippines and economic growth induces non-renewable energy consumption in Indonesia and Malaysia. A unidirectional causality relationship operating from renewable energy consumption to economic growth is approved for Brunei Darussalam. Finally, a unidirectional causality relationship working from renewable energy consumption to Brunei Darussalam’s economic growth is confirmed.
AtıfScopus2İncele - MakaleYalnız künye2021Scopus SJRQ2N epeta meyeri essential oil ameliorates fungal infection and the antioxidant response in grapevines (Vitis vinifera) infections by gray mold (Botrytis cinerea)
Karakuş, Sinem; Atici, Ökkeş; Köse, Cafer; Aydin, İhsan
The essential oil (EO) obtained from Nepeta meyeri Benth. used to struggle allelopathically with gray mold (Botrytis cinerea Pers.), which causes significant damage to vineyards (Vitis vinifera L. cv. Karaerik). The EO from N. meyeri was determined to contain 4aα, 7α, 7aα-nepetalactone (71.68%) at the highest rate when analyzed with GC/MS. Then, the doses (0.6, 0.8, and 1.0 µL/leaf) of 1 ppm EO solution were applied to the leaves together with the fungus inoculation (EO + F), as well as 1 day (EO + F1D) and 2 days (EO + F2D) before inoculation. The fungus application alone was evaluated as a control. Seven days after the inoculations, fungus development, lipid peroxidation level (as malondialdehyde), the contents of reactive oxygen species (ROS), photosynthetic pigments and soluble proteins, and the activities of antioxidant enzymes (superoxide dismutase, catalase, peroxidase, and glutathione reductase) were determined in the leaves. Findings revealed that EO + F1D among the applications and 1.0 µL/leaf among the EO doses significantly prevented fungus development on the leaf, compared to the control. Moreover, the same applications decreased ROS levels, such as H2O2 and O2·− and lipid peroxidation, while they increased antioxidant enzyme activities, as well as chlorophyll and soluble protein contents. Therefore, it can be suggested that the EO from N. meyeri has a potentially powerful usage as biofungicide in the allelopathic struggle against the infection of B. cinerea in vineyards.
AtıfScopus5WoS4OpenAlex6İncele - MakaleAçık Erişim2021Scopus SJRQ2Geochemistry and Pb isotopic proof for sources of heavy metal(loid)s in Late Cretaceous sandstones from Eastern Pontides (NE Turkey)
Saydam Eker, Çiğdem
Upper Cretaceous sedimentary rocks are widely exposed around Trabzon, Giresun and Gümüşhane in the eastern Pontides. The sedimentary rocks are mainly composed of sandstones and marls, and the thicknesses of these rocks range from 170 to 400 m. This paper focused on Late Cretaceous sandstones of Trabzon, Giresun and Gümüşhane regions to identify the concentrations, sources, deposition environment and conditions of certain heavy metal(loid)s (Zn, Pb, Cu, Ni, As, Co, Mo and V). Enrichment factor (EF), geo-accumulation index (Igeo), Pollution index (Pi), Pollution load index (Pln), Pb isotope and multivariate statistical analysis were performed to elucidate the pollution levels and sources. In general, the evaluation indices exhibited that the sandstones were moderately polluted by As in the Trabzon area, and strongly polluted by Ni and As, moderately polluted by Co and V in the Giresun and Gümüşhane areas. The results of multivariate statistical analyses indicated that As and partly Pb might be originated from anthropogenic sources, whereas other metals were derived from geogenic origin. Lead isotopic analysis demonstrated two characterized signatures of the pollution sources in the sandstones, one related to geogenic origin and the other to coal, gasoline and pesticides. The sandstones were deposited in transition—marine environment under oxic—weak oxic conditions and paleoclimatic conditions ranged from arid to moist during Late Cretaceous period.
AtıfScopus7WoS6OpenAlex10İncele - MakaleYalnız künye2021Scopus SJRQ2ReCRNet: a deep residual network for crack detection in historical buildings
Reis, Hatice Catal; Khoshelham, Kourosh
In historical buildings, surface cracks are important indicators of potential structural damage. Natural disasters and indirect human factors, which are frequently encountered in recent periods, negatively affect historical buildings and structures. Fast and cost-effective crack detection methods play a key role in structural health monitoring of historical buildings. This paper presents methodologies for identifying concrete cracks using deep learning. We propose ReCRNet, a deep learning architecture designed for classifying images of cracks. The performance of the proposed method is evaluated and compared with state-of-the-art methods such as AlexNet, VGG 19, linear support vector machine (SVM), and decision tree (DT). The results show that ReCRNet achieves better performance in terms of accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC), in comparison with the other crack classifiers. Accordingly, the proposed approach is recommended for automatic monitoring of historical buildings and building condition assessments.
AtıfScopus17OpenAlex15İncele