In this study, Cobalt (Co) doped Copper Oxide (CuO) films at different concentrations were deposited on glass substrates, using the Chemical Bath Deposition method. The films were characterized by Field Emission Scanning Electron Microscopy (FESEM), X-Ray Diffraction XRD), Ultra Violet-Visible Spectroscopy (UV-Vis.) and two-point contact method. The SEM showed that nanoplates formed increased in size and voids on the films surface decreased with increasing Co concentration. The XRD patterns revealed an increase in crystallite size with increasing (from 14.40 to 18.60 nm) Co concentration and no secondary phase was formed. The EDS spectra showed the presence of Co in the film composition with increasing concentration. The results of UV-Vis. spectroscopy showed that transmittance and band gap values could be changed with Co doping and thus the CuO band gap could be adjusted with the Co doping. The temperature-dependent current-voltage measurement results obtained with the two-point contact method showed that activation energy levels increased (from 0.134 to 0.232 eV) with increasing Co concentration. It was also observed that the conductivity increased with increasing temperature.
{"title":"Solution‐Based Fabrication of Copper Oxide Thin Film Influence of Transition Metal (Cobalt) Doping on Structural, Morphological, Electrical, and Optical Properties","authors":"Samed ÇETİNKAYA","doi":"10.31127/tuje.1290655","DOIUrl":"https://doi.org/10.31127/tuje.1290655","url":null,"abstract":"In this study, Cobalt (Co) doped Copper Oxide (CuO) films at different concentrations were deposited on glass substrates, using the Chemical Bath Deposition method. The films were characterized by Field Emission Scanning Electron Microscopy (FESEM), X-Ray Diffraction XRD), Ultra Violet-Visible Spectroscopy (UV-Vis.) and two-point contact method. The SEM showed that nanoplates formed increased in size and voids on the films surface decreased with increasing Co concentration. The XRD patterns revealed an increase in crystallite size with increasing (from 14.40 to 18.60 nm) Co concentration and no secondary phase was formed. The EDS spectra showed the presence of Co in the film composition with increasing concentration. The results of UV-Vis. spectroscopy showed that transmittance and band gap values could be changed with Co doping and thus the CuO band gap could be adjusted with the Co doping. The temperature-dependent current-voltage measurement results obtained with the two-point contact method showed that activation energy levels increased (from 0.134 to 0.232 eV) with increasing Co concentration. It was also observed that the conductivity increased with increasing temperature.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135601812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Optimal power flow (OPF) is one of the most challenging optimization problems of power engineering. Owing to the high computational complexity of the OPF problem, a powerful and robust optimization algorithm is required to solve it. This paper has been centered on the optimization of OPF problem using circulatory system-based optimization (CSBO) algorithm. The solution quality of CSBO is compared with the recently introduced state-of-the-art metaheuristic algorithms i.e., artificial rabbits optimization (ARO), african vultures optimization algorithm (AVOA), and chaos game optimization (CGO). The practicability of the algorithms was evaluated on the IEEE-57 and 118-bus power networks for the optimization of various objectives, i.e., fuel cost, power loss, voltage deviation, and enhancement of voltage stability. Based on OPF results of the IEEE 57-bus power system, it is seen that the best fuel cost and voltage deviation results are calculated to be 41666.2344 $/h and 0.5871 p.u with the CSBO method. Given the OPF results of the IEEE 118-bus power network, it is observed that the CSBO algorithm presented the best fuel cost and active power loss values of 134934.3140 $/h, and 16.4688 MW. Moreover, OPF solutions obtained from 30 algorithm runs were analyzed using the Wilcoxon statistical test method. Consequently, the present paper reports that the CSBO algorithm produces better-quality OPF solutions compared to its competitors and other literature studies.
{"title":"Optimal Power Flow Analysis with Circulatory System-Based Optimization Algorithm","authors":"Hüseyin BAKIR","doi":"10.31127/tuje.1282429","DOIUrl":"https://doi.org/10.31127/tuje.1282429","url":null,"abstract":"Optimal power flow (OPF) is one of the most challenging optimization problems of power engineering. Owing to the high computational complexity of the OPF problem, a powerful and robust optimization algorithm is required to solve it. This paper has been centered on the optimization of OPF problem using circulatory system-based optimization (CSBO) algorithm. The solution quality of CSBO is compared with the recently introduced state-of-the-art metaheuristic algorithms i.e., artificial rabbits optimization (ARO), african vultures optimization algorithm (AVOA), and chaos game optimization (CGO). The practicability of the algorithms was evaluated on the IEEE-57 and 118-bus power networks for the optimization of various objectives, i.e., fuel cost, power loss, voltage deviation, and enhancement of voltage stability. Based on OPF results of the IEEE 57-bus power system, it is seen that the best fuel cost and voltage deviation results are calculated to be 41666.2344 $/h and 0.5871 p.u with the CSBO method. Given the OPF results of the IEEE 118-bus power network, it is observed that the CSBO algorithm presented the best fuel cost and active power loss values of 134934.3140 $/h, and 16.4688 MW. Moreover, OPF solutions obtained from 30 algorithm runs were analyzed using the Wilcoxon statistical test method. Consequently, the present paper reports that the CSBO algorithm produces better-quality OPF solutions compared to its competitors and other literature studies.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135831929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The primary function of the geofoams consists of providing; i) lightweight fill for construction on soft ground (i.e. embankment), ii) relatively stiff base for subgrade installation below a highway (i.e. roadway, runway foundation), bridge approach (i.e. abutment backfill), and iii) slope stabilization for retaining structures. In those applications, the geofoams are in direct contact with soils and this interaction results in development of an interface where likelihood of a failure to initiate is higher. For this reason, the frictional resistance and the type of shear response mobilizing at these soil – geofoam interfaces control the stability of composite system, and hence, govern the integrity of the infrastructure. Soil – geofoam interfaces have been studied through an extensive experimental program by performing multiple series of interface shear tests using two different granular soils (i.e. beach sand and construction material sand) and one cohesive soil (i.e. bentonite clay) as well as a soil mixture containing 75% sand and 25% clay by dry weight at distinct loading conditions (i.e. normal stresses: 25, 100, 250; low, moderate, high loading conditions, respectively). Using the shear stress versus horizontal displacement curves obtained, some important engineering design parameters including peak shear stress, residual shear stress, interface sensitivity (i.e. peak/residual ratio) and displacement required to reach peak stress have been determined and the variations in those interface mechanical properties as a function of loading condition and counterface soil type have been investigated. It was seen that the peak as well as residual shear stresses increased with an increase in normal stress. Further, granular soil (sand) interfaces demonstrated relatively larger frictional strengths (both peak and residual) as compared to that of not only cohesive soil (clay) interface but also soil mixture (sand and clay) interface. Additionally, the higher the angularity of granular soil particles became, the larger the interface shear strengths (peak and residual), when sheared against geofoams, developed in light of experimental results attained as a result of interface shear tests on different material combinations.
{"title":"Counterface Soil Type and Loading Condition Effects on Granular/Cohesive Soil – Geofoam Interface Shear Behavior","authors":"Tanay KARADEMİR","doi":"10.31127/tuje.1279304","DOIUrl":"https://doi.org/10.31127/tuje.1279304","url":null,"abstract":"The primary function of the geofoams consists of providing; i) lightweight fill for construction on soft ground (i.e. embankment), ii) relatively stiff base for subgrade installation below a highway (i.e. roadway, runway foundation), bridge approach (i.e. abutment backfill), and iii) slope stabilization for retaining structures. In those applications, the geofoams are in direct contact with soils and this interaction results in development of an interface where likelihood of a failure to initiate is higher. For this reason, the frictional resistance and the type of shear response mobilizing at these soil – geofoam interfaces control the stability of composite system, and hence, govern the integrity of the infrastructure. Soil – geofoam interfaces have been studied through an extensive experimental program by performing multiple series of interface shear tests using two different granular soils (i.e. beach sand and construction material sand) and one cohesive soil (i.e. bentonite clay) as well as a soil mixture containing 75% sand and 25% clay by dry weight at distinct loading conditions (i.e. normal stresses: 25, 100, 250; low, moderate, high loading conditions, respectively). Using the shear stress versus horizontal displacement curves obtained, some important engineering design parameters including peak shear stress, residual shear stress, interface sensitivity (i.e. peak/residual ratio) and displacement required to reach peak stress have been determined and the variations in those interface mechanical properties as a function of loading condition and counterface soil type have been investigated. It was seen that the peak as well as residual shear stresses increased with an increase in normal stress. Further, granular soil (sand) interfaces demonstrated relatively larger frictional strengths (both peak and residual) as compared to that of not only cohesive soil (clay) interface but also soil mixture (sand and clay) interface. Additionally, the higher the angularity of granular soil particles became, the larger the interface shear strengths (peak and residual), when sheared against geofoams, developed in light of experimental results attained as a result of interface shear tests on different material combinations.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135140231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yoga is an exercise developed in ancient India. People perform yoga in order to have mental, physical, and spiritual benefits. While yoga helps build strength in the mind and body, incorrect postures might result in serious injuries. Therefore, yoga exercisers need either an expert or a platform to receive feedback on their performance. Since access to experts is not an option for everyone, a system to provide feedback on the yoga poses is required. To this end, commercial products such as smart yoga mats and smart pants are produced; Kinect cameras, sensors, and wearable devices are used. However, these solutions are either uncomfortable to wear or not affordable for everyone. Nonetheless, a system that employs computer vision techniques is a requirement. In this paper, we propose a deep-learning model for yoga pose classification, which is the first step of a quality assessment system. We introduce a wavelet-based model that first takes wavelet transform of input images. The acquired subbands, i.e., approximation, horizontal, vertical, and diagonal coefficients of the wavelet transform are then fed into separate convolutional neural networks (CNN). The obtained probability results for each group are fused in order to have the final yoga class prediction. A publicly available dataset with 5 yoga poses is used. Since the number of images in the dataset is not enough for a deep learning model, we also perform data augmentation to increase the number of images. We compare our results to a CNN model and the three models that employ the subbands separately. Results obtained using the proposed model outperforms the accuracy output achieved with the compared models.
{"title":"Comparison of CNN-Based Methods for Yoga Pose Classification","authors":"Vildan ATALAY AYDIN","doi":"10.31127/tuje.1275826","DOIUrl":"https://doi.org/10.31127/tuje.1275826","url":null,"abstract":"Yoga is an exercise developed in ancient India. People perform yoga in order to have mental, physical, and spiritual benefits. While yoga helps build strength in the mind and body, incorrect postures might result in serious injuries. Therefore, yoga exercisers need either an expert or a platform to receive feedback on their performance. Since access to experts is not an option for everyone, a system to provide feedback on the yoga poses is required. To this end, commercial products such as smart yoga mats and smart pants are produced; Kinect cameras, sensors, and wearable devices are used. However, these solutions are either uncomfortable to wear or not affordable for everyone. Nonetheless, a system that employs computer vision techniques is a requirement. In this paper, we propose a deep-learning model for yoga pose classification, which is the first step of a quality assessment system. We introduce a wavelet-based model that first takes wavelet transform of input images. The acquired subbands, i.e., approximation, horizontal, vertical, and diagonal coefficients of the wavelet transform are then fed into separate convolutional neural networks (CNN). The obtained probability results for each group are fused in order to have the final yoga class prediction. A publicly available dataset with 5 yoga poses is used. Since the number of images in the dataset is not enough for a deep learning model, we also perform data augmentation to increase the number of images. We compare our results to a CNN model and the three models that employ the subbands separately. Results obtained using the proposed model outperforms the accuracy output achieved with the compared models.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135526172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The aim of this study is to estimate the elevation points used in the creation of the digital elevation model, which is the most important data of the projects and required in the engineering project, using horizontal and vertical location informations and three different heuristic regression techniques. As the study area, an area with mid-level elevations, located in the Marmara region, and covering a part of the intersection of Edirne, Kırklareli and Tekirdağ provinces was chosen. In the study, the estimations were investigated for three different sized areas, and these areas are square areas with the dimensions of 1x1 km, 10x10 km and 100x100 km, respectively. A total of 3500 elevation points were used in the study, and this number is constant in all areas, and 60% of these points were used in the testing phase and 40% in the training phase. The models used in the study are M5 model tree (M5-tree), multivariate adaptive regression curves (MARS) and Least Square Support Vector Regression (LSSVR). The results of the models were evaluated according to three different comparison criteria. These, coefficient of determination (R2), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were used. When the modeling results are examined; M5-Tree regression method gave the best results (1), LSSVR method was better than MARS methods (2), The most successful input data was found in datasets using X and Y coordinates information, and the worst results were found in datasets using X coordinates (3). As the study area increased, the model performance did not improve (4). The least error was obtained in the modeling of 1x1 km area, and the highest R² was obtained from the modeling of 10x10 km area (5). It was concluded that the M5-tree method is a very successful method in height modeling.
本研究的目的是利用水平和垂直位置信息以及三种不同的启发式回归技术，估计用于创建数字高程模型的高程点，这是项目中最重要的数据，也是工程项目所需的数据。作为研究区域，选择了位于马尔马拉地区的一个中等海拔区域，覆盖了Edirne, Kırklareli和tekirdalu省交界处的一部分。在研究中，研究了三个不同大小的区域，这些区域分别为1x1 km, 10x10 km和100x100 km的方形区域。研究中总共使用了3500个高程点，这个数字在所有区域都是恒定的，其中60%的高程点用于测试阶段，40%用于训练阶段。研究中使用的模型有M5模型树(M5-tree)、多变量自适应回归曲线(MARS)和最小二乘支持向量回归(LSSVR)。根据三种不同的比较标准对模型的结果进行评价。这些，决定系数(R2)，平均绝对误差(MAE)和均方根误差(RMSE)。当对建模结果进行检验时;M5-Tree回归方法的结果最好(1)，LSSVR方法优于MARS方法(2)，X和Y坐标信息的数据集输入数据最成功，X坐标信息的数据集结果最差(3)。随着研究面积的增加，模型性能没有提高(4)。在1x1 km区域建模时误差最小。在10x10 km区域的模拟中，R²最高(5)。结果表明，M5-tree方法是一种非常成功的高度模拟方法。
{"title":"Prediction of elevation points using three different heuristic regression techniques","authors":"Vahdettin Demir, Ramazan Doğu","doi":"10.31127/tuje.1257847","DOIUrl":"https://doi.org/10.31127/tuje.1257847","url":null,"abstract":"The aim of this study is to estimate the elevation points used in the creation of the digital elevation model, which is the most important data of the projects and required in the engineering project, using horizontal and vertical location informations and three different heuristic regression techniques. As the study area, an area with mid-level elevations, located in the Marmara region, and covering a part of the intersection of Edirne, Kırklareli and Tekirdağ provinces was chosen. In the study, the estimations were investigated for three different sized areas, and these areas are square areas with the dimensions of 1x1 km, 10x10 km and 100x100 km, respectively. A total of 3500 elevation points were used in the study, and this number is constant in all areas, and 60% of these points were used in the testing phase and 40% in the training phase. The models used in the study are M5 model tree (M5-tree), multivariate adaptive regression curves (MARS) and Least Square Support Vector Regression (LSSVR). The results of the models were evaluated according to three different comparison criteria. These, coefficient of determination (R2), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were used. When the modeling results are examined; M5-Tree regression method gave the best results (1), LSSVR method was better than MARS methods (2), The most successful input data was found in datasets using X and Y coordinates information, and the worst results were found in datasets using X coordinates (3). As the study area increased, the model performance did not improve (4). The least error was obtained in the modeling of 1x1 km area, and the highest R² was obtained from the modeling of 10x10 km area (5). It was concluded that the M5-tree method is a very successful method in height modeling.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80426107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In Diesel Engines, the heat energy obtained from the glow plug increases the engine's ability to start up in cold climatic conditions and significantly reduces emissions of harmful gases leaving the exhaust. In cold climatic conditions, before the start off of diesel vehicles it is necessary to wait for about 10 s the cylinder block heating. This period negatively affects driving comfort. In this study, the mathematical results of the processes to optimize the time required for the glow plug to reach the required temperature have been experimentally proven. A test apparatus was developed to confirm experimentally the theoretical results. Thanks to these improvements concerning the manufacture of the glow plug, the time period to reach 850 ° C has been reduced by approximately 5 s. The proposed design is in accordance with the glow plug present in the market. Currently the whole glow plug must be changed at the end of lifetime, with our improvement only the inner tube resistance can be easily changed involving a cost reduction by about 60%.
{"title":"Determination of optimum design parameters of glow plug and experimental verification","authors":"Muciz Özcan, M. F. Ünlerşen, M. Şen","doi":"10.31127/tuje.1062681","DOIUrl":"https://doi.org/10.31127/tuje.1062681","url":null,"abstract":"In Diesel Engines, the heat energy obtained from the glow plug increases the engine's ability to start up in cold climatic conditions and significantly reduces emissions of harmful gases leaving the exhaust. In cold climatic conditions, before the start off of diesel vehicles it is necessary to wait for about 10 s the cylinder block heating. This period negatively affects driving comfort. In this study, the mathematical results of the processes to optimize the time required for the glow plug to reach the required temperature have been experimentally proven. A test apparatus was developed to confirm experimentally the theoretical results. Thanks to these improvements concerning the manufacture of the glow plug, the time period to reach 850 ° C has been reduced by approximately 5 s. The proposed design is in accordance with the glow plug present in the market. Currently the whole glow plug must be changed at the end of lifetime, with our improvement only the inner tube resistance can be easily changed involving a cost reduction by about 60%.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79134491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is a well-known fact that the absence of infill walls at the ground story, which is termed as “open ground story” may lead to a soft-story deficiency, especially in the case of non-ductile buildings. The previous severe earthquakes have shown that catastrophic destruction may occur in such a condition. Therefore, the seismic assessment of open ground story reinforced frames, where the effects of infill walls are incorporated, is of vital importance. However, the effects of infill walls are generally disregarded or considered indirectly in the seismic assessment procedures of the codes. This may mislead the actual condition of the open ground story buildings at different performance levels. This study aims to assess a non-ductile reinforced concrete frame with an open ground story regarding the collapse prevention performance level. The pushover and incremental dynamic analyses results are evaluated following the code limitations for collapse prevention. The results demonstrate the measure of misleading caused by the ignorance of infills at the upper stories while applying these code limitations.
{"title":"Collapse capacity assessment of non-ductile open ground story reinforced concrete frame","authors":"Emre AKIN, Emad KANAS","doi":"10.31127/tuje.1071965","DOIUrl":"https://doi.org/10.31127/tuje.1071965","url":null,"abstract":"It is a well-known fact that the absence of infill walls at the ground story, which is termed as “open ground story” may lead to a soft-story deficiency, especially in the case of non-ductile buildings. The previous severe earthquakes have shown that catastrophic destruction may occur in such a condition. Therefore, the seismic assessment of open ground story reinforced frames, where the effects of infill walls are incorporated, is of vital importance. However, the effects of infill walls are generally disregarded or considered indirectly in the seismic assessment procedures of the codes. This may mislead the actual condition of the open ground story buildings at different performance levels. This study aims to assess a non-ductile reinforced concrete frame with an open ground story regarding the collapse prevention performance level. The pushover and incremental dynamic analyses results are evaluated following the code limitations for collapse prevention. The results demonstrate the measure of misleading caused by the ignorance of infills at the upper stories while applying these code limitations.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136340142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine Learning (ML) has been used in the prediction of geolocation with improved accuracies in this work. The pre-processed data was subjected to prediction analytics using 22 machine learning algorithms over regression mode. It was observed that Extra Trees Regressor performed well with better accuracies in predicting latitude, longitude, and Haversine distance, respectively. Regression models like CatBoost, Extreme Gradient boosting, Light Gradient boosting machine, and Gradient boosting regressor were also tested. The R2 values were computed for each case, and we obtained 0.96 (Longitude), 0.98 (Latitude), and 0.96 (Haversine), respectively. The evaluation of models was done using metrics like MAE, MASE, RMSE, R2, RMSLE, and MAPE and R2 is considered most important than others. The effect of data point was calculated using Cooks’ distance, and the variable fluoride has a significant impact on the prediction accuracy of Longitude followed by RSC, Cl, SO4, SAR, NO3, NA, Ca, EC and pH variables. In the prediction of latitude, the SAR variable played a significant role, followed by Na and TH. According to the t-SNE manifold, three longitude values were quite different from the others. This work is supported by some of the manifests like Cooks’ distance outlier detection, feature importance plot, t-SNE manifold, prediction error plot, residuals plot, RFECV plot, and validation curve. This work is done to report that the challenge of predicting both latitude and longitude on a common ground is solved partially, if not completely, and machine learning tools can be used for this purpose. Haversine distance can be obtained from latitude and longitude and can be used in the prediction of geolocation.
在这项工作中，机器学习(ML)已被用于预测地理位置，并提高了准确性。预处理后的数据在回归模式上使用22种机器学习算法进行预测分析。观察到Extra Trees Regressor分别在预测纬度、经度和哈弗辛距离方面表现良好，精度较高。对CatBoost、Extreme Gradient boosting、Light Gradient boosting machine、Gradient boosting regressor等回归模型进行了测试。计算每个病例的R2值，我们分别得到0.96(经度)、0.98(纬度)和0.96(哈弗辛)。模型的评估使用指标如MAE、MASE、RMSE、R2、RMSLE和MAPE，其中R2被认为是最重要的。利用库氏距离计算数据点的影响，氟变量对经度的预测精度影响显著，其次是RSC、Cl、SO4、SAR、NO3、NA、Ca、EC和pH变量。在纬度预测中，SAR变量的作用最显著，其次是Na和TH。根据t-SNE流形，三个经度值与其他经度值相差很大。本文的工作得到了库克斯距离异常点检测、特征重要性图、t-SNE流形、预测误差图、残差图、RFECV图和验证曲线等表的支持。这项工作的完成是为了报告在一个共同的基础上预测纬度和经度的挑战是部分解决的，如果不是完全解决的话，机器学习工具可以用于此目的。哈弗斯距离可由经纬度得到，可用于地理位置的预测。
{"title":"Machine learning empowered prediction of geolocation using groundwater quality variables over YSR district of India","authors":"Jagadish Kumar MOGARAJU","doi":"10.31127/tuje.1223779","DOIUrl":"https://doi.org/10.31127/tuje.1223779","url":null,"abstract":"Machine Learning (ML) has been used in the prediction of geolocation with improved accuracies in this work. The pre-processed data was subjected to prediction analytics using 22 machine learning algorithms over regression mode. It was observed that Extra Trees Regressor performed well with better accuracies in predicting latitude, longitude, and Haversine distance, respectively. Regression models like CatBoost, Extreme Gradient boosting, Light Gradient boosting machine, and Gradient boosting regressor were also tested. The R2 values were computed for each case, and we obtained 0.96 (Longitude), 0.98 (Latitude), and 0.96 (Haversine), respectively. The evaluation of models was done using metrics like MAE, MASE, RMSE, R2, RMSLE, and MAPE and R2 is considered most important than others. The effect of data point was calculated using Cooks’ distance, and the variable fluoride has a significant impact on the prediction accuracy of Longitude followed by RSC, Cl, SO4, SAR, NO3, NA, Ca, EC and pH variables. In the prediction of latitude, the SAR variable played a significant role, followed by Na and TH. According to the t-SNE manifold, three longitude values were quite different from the others. This work is supported by some of the manifests like Cooks’ distance outlier detection, feature importance plot, t-SNE manifold, prediction error plot, residuals plot, RFECV plot, and validation curve. This work is done to report that the challenge of predicting both latitude and longitude on a common ground is solved partially, if not completely, and machine learning tools can be used for this purpose. Haversine distance can be obtained from latitude and longitude and can be used in the prediction of geolocation.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134952793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Commodity products such as gold, silver, and metal have been seen as safe havens in past economic crises. This situation increases the interest in commodity products. Due to the COVID-19 pandemic, quarantine decisions and precautions have caused an economic slowdown in stock markets and consumer activities. This inactivity in the economy has led to the COVID-19 recession that started in February 2020. Because of the increase in the number of COVID-19 cases, the difficulty of physical buying-selling transactions has shown that commodity products can be a safe investment tool. Based on the fact that machine learning approaches gained importance in commodity price prediction, the main goal of this study is to understand whether machine learning methods are meaningful for commodity price prediction even in extraordinary situations. To measure commodities’ price volatility, a data set obtained from Borsa İstanbul is separated into pre-COVID-19 and COVID-19 periods. Daily prices for gold and silver commodities, from July 2018, which is before the ongoing COVID-19 recession, to October 2021 are used. The performances of the machine learning models were compared with MAE, MAPE, and RMSE metrics.
{"title":"Comparison of commodity prices by using machine learning models in the COVID-19 era","authors":"Sena Alparslan, T. Uçar","doi":"10.31127/tuje.1196296","DOIUrl":"https://doi.org/10.31127/tuje.1196296","url":null,"abstract":"Commodity products such as gold, silver, and metal have been seen as safe havens in past economic crises. This situation increases the interest in commodity products. Due to the COVID-19 pandemic, quarantine decisions and precautions have caused an economic slowdown in stock markets and consumer activities. This inactivity in the economy has led to the COVID-19 recession that started in February 2020. Because of the increase in the number of COVID-19 cases, the difficulty of physical buying-selling transactions has shown that commodity products can be a safe investment tool. Based on the fact that machine learning approaches gained importance in commodity price prediction, the main goal of this study is to understand whether machine learning methods are meaningful for commodity price prediction even in extraordinary situations. To measure commodities’ price volatility, a data set obtained from Borsa İstanbul is separated into pre-COVID-19 and COVID-19 periods. Daily prices for gold and silver commodities, from July 2018, which is before the ongoing COVID-19 recession, to October 2021 are used. The performances of the machine learning models were compared with MAE, MAPE, and RMSE metrics.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90297690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Yalnızardıç RCC dam constructed in 2015 is located in the Mediterranean region of Turkey, and it is intended for electric power production. The dam is approximately 303 m long and 92 m height. In this paper, the geotechnical properties of Yalnızardıç Dam's foundation and the grouting methods used to improve this foundation were examined to determine its performance for grouting. Engineering geological mapping, drilling, laboratory tests, and water pressure tests were undertaken to specify the foundation properties. In a consequence of tests, high-permeable and permeable zones were identified in the dam axis area. Grout curtain, including two rows of grouting holes, were built in the left abutment, thalweg and right abutment in accordance with the Lugeon tests and RQD results. Also, blanket (consolidation) grouts were built all foundation areas. Check boreholes along the foundation were opened after grouting treatment and Lugeon tests were performed. The results from the check boreholes indicated that average Lugeon (LU) values reduced, and the values were within the recommended limit. The process shows considerable accuracy in evaluating grouting efficiency.
{"title":"Assessment of Engineering Geology and Grouting Applications in Yalnızardıç Dam Site (Antalya, Turkey)","authors":"Ömür ÇİMEN, Halil İbrahim GÜNAYDIN","doi":"10.31127/tuje.1221774","DOIUrl":"https://doi.org/10.31127/tuje.1221774","url":null,"abstract":"The Yalnızardıç RCC dam constructed in 2015 is located in the Mediterranean region of Turkey, and it is intended for electric power production. The dam is approximately 303 m long and 92 m height. In this paper, the geotechnical properties of Yalnızardıç Dam's foundation and the grouting methods used to improve this foundation were examined to determine its performance for grouting. Engineering geological mapping, drilling, laboratory tests, and water pressure tests were undertaken to specify the foundation properties. In a consequence of tests, high-permeable and permeable zones were identified in the dam axis area. Grout curtain, including two rows of grouting holes, were built in the left abutment, thalweg and right abutment in accordance with the Lugeon tests and RQD results. Also, blanket (consolidation) grouts were built all foundation areas. Check boreholes along the foundation were opened after grouting treatment and Lugeon tests were performed. The results from the check boreholes indicated that average Lugeon (LU) values reduced, and the values were within the recommended limit. The process shows considerable accuracy in evaluating grouting efficiency.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135553347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：