Since we all have our own set of limitations when it comes to perceiving the world and reasoning profoundly, we are constantly met with uncertainty as a result of a lack of information (lexical impression, incompleteness), as well as specific measurement inaccuracies. It has been found that uncertainty, which shows up as ambiguity, is the root cause of complexity, which is everywhere in the real world. Most of the uncertainty in civil engineering systems comes from the fact that the constraints (parameters) are hard to understand and are described in a vague way. The ambiguity comes from a number of sources, including physical arbitrariness, statistical uncertainty due to using limited information to estimate these characteristics, and model uncertainty due to using overly simplified methods and idealized depictions of actual performances. Thus, It is better to combine fuzzy set theory and fuzzy logic. Fuzzy logic is well-suited to modeling the indeterminacy and ambiguity that result from multiple factors and a lack of data. In order to improve upon a previous predictive model, this paper makes use of a smart model built on a fuzzy logic system (FLS). Precipitation, temperature, humidity, slope, and land use data were all taken into account as input variables in the fuzzy model. Toprak's original explanation of the simple membership function and fuzzy rules generation technique (SMRGT) was based on the fuzzy-Mamdani methodology, and used the flow coefficient as its output. The model's results were compared to available data. The following factors were considered in the comparison: 1) The maximum, minimum, mean, standard deviation, skewness, variation, and correlation coefficients are the seven statistical parameters. 2) Four types of error criteria: Mean Absolute Relative Error (MARE), Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). 3) Scatter diagram.
{"title":"Application of a New Fuzzy Logic Model Known as \"SMRGT\" for Estimating Flow Coefficient Rate","authors":"Ayşe Yeter GÜNAL, Ruya MEHDİ","doi":"10.31127/tuje.1225795","DOIUrl":"https://doi.org/10.31127/tuje.1225795","url":null,"abstract":"Since we all have our own set of limitations when it comes to perceiving the world and reasoning profoundly, we are constantly met with uncertainty as a result of a lack of information (lexical impression, incompleteness), as well as specific measurement inaccuracies. It has been found that uncertainty, which shows up as ambiguity, is the root cause of complexity, which is everywhere in the real world. Most of the uncertainty in civil engineering systems comes from the fact that the constraints (parameters) are hard to understand and are described in a vague way. The ambiguity comes from a number of sources, including physical arbitrariness, statistical uncertainty due to using limited information to estimate these characteristics, and model uncertainty due to using overly simplified methods and idealized depictions of actual performances. Thus, It is better to combine fuzzy set theory and fuzzy logic. Fuzzy logic is well-suited to modeling the indeterminacy and ambiguity that result from multiple factors and a lack of data. In order to improve upon a previous predictive model, this paper makes use of a smart model built on a fuzzy logic system (FLS). Precipitation, temperature, humidity, slope, and land use data were all taken into account as input variables in the fuzzy model. Toprak's original explanation of the simple membership function and fuzzy rules generation technique (SMRGT) was based on the fuzzy-Mamdani methodology, and used the flow coefficient as its output. The model's results were compared to available data. The following factors were considered in the comparison: 1) The maximum, minimum, mean, standard deviation, skewness, variation, and correlation coefficients are the seven statistical parameters. 2) Four types of error criteria: Mean Absolute Relative Error (MARE), Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). 3) Scatter diagram.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136156878","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}
Mert Takci, Inci Develioglu, H. F. Pulat, H. Demi̇rci̇
Back stability analysis, in-lab testing, and field tests may all be used to assess the behavior of stability of slopes. Each of these approaches has benefits and drawbacks compared to one another. Amongst these approaches, laboratory modeling stands out with its ability to prepare identical samples, keep external conditions under control, and measure deformations precisely. In this study, laboratory-based slope models at 1(Horizontal)/1(Vertical), 2/3, and 1/3 angles including the effects of precipitation and external loading were created. The results of these models were compared with those of the Plaxis 2D software. First, models were built using highly permeable cohesionless coarse-grained soils, and mixtures containing high plasticity clay (bentonite) at different rates were then prepared to investigate the effect of fine-grained soils on stability. Laboratory tests such as sieve analysis, specific gravity, consistency limits, Standard Proctor, and direct shear were used to assess the geotechnical index properties of soils. Incremental surcharge loads were placed on the slope models and surface deformations, and local and general collapses under the effect of precipitation were observed. Laboratory model results highlighted that the fines content had a non-negligible effect on stability. When the slope behaviors were examined, it was observed that the models with a 1/3 slope had more severe local fractures and collapses. The stability of the slope is negatively affected when bentonite content in soil mixtures rises. The results of Plaxis 2D analysis are compatible with those of laboratory model tests and the safety factors obtained from Plaxis 2D range from 0.98 to 11.4.
{"title":"Laboratory Modeling and Analysis of Slopes of Different Geometry Under the Effect of Precipitation","authors":"Mert Takci, Inci Develioglu, H. F. Pulat, H. Demi̇rci̇","doi":"10.31127/tuje.1191246","DOIUrl":"https://doi.org/10.31127/tuje.1191246","url":null,"abstract":"Back stability analysis, in-lab testing, and field tests may all be used to assess the behavior of stability of slopes. Each of these approaches has benefits and drawbacks compared to one another. Amongst these approaches, laboratory modeling stands out with its ability to prepare identical samples, keep external conditions under control, and measure deformations precisely. In this study, laboratory-based slope models at 1(Horizontal)/1(Vertical), 2/3, and 1/3 angles including the effects of precipitation and external loading were created. The results of these models were compared with those of the Plaxis 2D software. First, models were built using highly permeable cohesionless coarse-grained soils, and mixtures containing high plasticity clay (bentonite) at different rates were then prepared to investigate the effect of fine-grained soils on stability. Laboratory tests such as sieve analysis, specific gravity, consistency limits, Standard Proctor, and direct shear were used to assess the geotechnical index properties of soils. Incremental surcharge loads were placed on the slope models and surface deformations, and local and general collapses under the effect of precipitation were observed. Laboratory model results highlighted that the fines content had a non-negligible effect on stability. When the slope behaviors were examined, it was observed that the models with a 1/3 slope had more severe local fractures and collapses. The stability of the slope is negatively affected when bentonite content in soil mixtures rises. The results of Plaxis 2D analysis are compatible with those of laboratory model tests and the safety factors obtained from Plaxis 2D range from 0.98 to 11.4.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75291915","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}
Abdul Ahad ABRO, Waqas Ahmed SIDDIQUE, Mir Sajjad Hussain TALPUR, Awais Khan JUMANİ, Erkan YAŞAR
The ensemble learning method is considered a meaningful yet challenging task. To enhance the performance of binary classification and predictive analysis, this paper proposes an effective ensemble learning approach by applying multiple models to produce efficient and effective outcomes. In these experimental studies, three base learners, J48, Multilayer Perceptron (MP), and Support Vector Machine (SVM) are being utilized. Moreover, two meta-learners, Bagging and Rotation Forest are being used in this analysis. Firstly, to produce effective results and capture productive data, the base learner, the J48 decision tree is aggregated with the rotation forest. Secondly, machine learning and ensemble learning classification algorithms along with the five UCI Datasets are being applied to progress the robustness of the system. Whereas, the recommended mechanism is evaluated by implementing five performance standards concerning the accuracy, AUC (Area Under Curve), precision, recall and F-measure values. In this regard, extensive strategies and various approaches were being studied and applied to obtain improved results from the current literature; however, they were insufficient to provide successful results. We present experimental results which demonstrate the efficiency of our approach to well-known competitive approaches. This method can be applied to image identification and machine learning problems, such as binary classification.
{"title":"A combined approach of base and meta learners for hybrid system","authors":"Abdul Ahad ABRO, Waqas Ahmed SIDDIQUE, Mir Sajjad Hussain TALPUR, Awais Khan JUMANİ, Erkan YAŞAR","doi":"10.31127/tuje.1007508","DOIUrl":"https://doi.org/10.31127/tuje.1007508","url":null,"abstract":"The ensemble learning method is considered a meaningful yet challenging task. To enhance the performance of binary classification and predictive analysis, this paper proposes an effective ensemble learning approach by applying multiple models to produce efficient and effective outcomes. In these experimental studies, three base learners, J48, Multilayer Perceptron (MP), and Support Vector Machine (SVM) are being utilized. Moreover, two meta-learners, Bagging and Rotation Forest are being used in this analysis. Firstly, to produce effective results and capture productive data, the base learner, the J48 decision tree is aggregated with the rotation forest. Secondly, machine learning and ensemble learning classification algorithms along with the five UCI Datasets are being applied to progress the robustness of the system. Whereas, the recommended mechanism is evaluated by implementing five performance standards concerning the accuracy, AUC (Area Under Curve), precision, recall and F-measure values. In this regard, extensive strategies and various approaches were being studied and applied to obtain improved results from the current literature; however, they were insufficient to provide successful results. We present experimental results which demonstrate the efficiency of our approach to well-known competitive approaches. This method can be applied to image identification and machine learning problems, such as binary classification.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135744256","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}
Cancer is one of the leading health problems occurring in various organs and tissues of the body and its incidence is increasing in the world. Lung cancer is one of the deadliest types of cancer. Due to its worldwide prevalence, increasing number of cases and deadly consequences, early detection of lung cancer, as with all other cancers, greatly increases the chances of survival. As with all other diseases, the diagnosis of cancer becomes possible after the appearance of various symptoms through the examinations of specialists. The recognizable symptoms of lung cancer include shortness of breath, coughing, wheezing, jaundice in the fingers, chest pain and difficulty swallowing. The diagnosis is made by an expert on site based on these symptoms and additional tests. The aim of this study is to detect the disease at an earlier stage based on the symptoms present, to assess more cases with less time and cost, and to achieve results in new situations that are as successful or even faster than those of human experts by deriving them from existing data using various algorithms. The goal is to develop an automated model that can detect early-stage lung cancer based on machine learning methods. The developed model includes 9 different machine learning algorithms (NB, LR, DT, RF, GB, SVM). The success of the classification algorithms used was evaluated using the metrics of accuracy, sensitivity and precision calculated with the parameters of the confusion matrix. The results obtained show that the proposed model can detect cancer diagnosis with a maximum accuracy of 91%. The application of this model will help medical practitioners to develop an automated and reliable system that can detect lung cancer. The proposed interdisciplinary method can also be applied to other types of cancer.
{"title":"Machine Learning-Based Lung Cancer Diagnosis","authors":"Mahmut Dirik","doi":"10.31127/tuje.1180931","DOIUrl":"https://doi.org/10.31127/tuje.1180931","url":null,"abstract":"Cancer is one of the leading health problems occurring in various organs and tissues of the body and its incidence is increasing in the world. Lung cancer is one of the deadliest types of cancer. Due to its worldwide prevalence, increasing number of cases and deadly consequences, early detection of lung cancer, as with all other cancers, greatly increases the chances of survival. As with all other diseases, the diagnosis of cancer becomes possible after the appearance of various symptoms through the examinations of specialists. The recognizable symptoms of lung cancer include shortness of breath, coughing, wheezing, jaundice in the fingers, chest pain and difficulty swallowing. The diagnosis is made by an expert on site based on these symptoms and additional tests. The aim of this study is to detect the disease at an earlier stage based on the symptoms present, to assess more cases with less time and cost, and to achieve results in new situations that are as successful or even faster than those of human experts by deriving them from existing data using various algorithms. The goal is to develop an automated model that can detect early-stage lung cancer based on machine learning methods. The developed model includes 9 different machine learning algorithms (NB, LR, DT, RF, GB, SVM). The success of the classification algorithms used was evaluated using the metrics of accuracy, sensitivity and precision calculated with the parameters of the confusion matrix. The results obtained show that the proposed model can detect cancer diagnosis with a maximum accuracy of 91%. The application of this model will help medical practitioners to develop an automated and reliable system that can detect lung cancer. The proposed interdisciplinary method can also be applied to other types of cancer.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87020881","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}
Lightweight and durable materials such as aluminum alloys are widely used in sectors such as defense industry, aerospace industry, automotive industry, and high-speed train manufacturing. Some of these materials cannot be welded by conventional methods due to their high thermal conductivity and low melting point. In welding processes, the material properties are expected to be as close as possible to base material. Friction stir welding (FSW) is a joining method that provides welding below the melting point of materials that cannot be welded by conventional methods or where the welding process causes the mechanical structure of the material to deteriorate. In this study, FSW application, advantages and disadvantages and usage areas of friction stir welding were examined.
{"title":"FRICTION STIR WELDING: PROCESS AND APPLICATIONS","authors":"Emre Kaygusuz","doi":"10.31127/tuje.1107210","DOIUrl":"https://doi.org/10.31127/tuje.1107210","url":null,"abstract":"Lightweight and durable materials such as aluminum alloys are widely used in sectors such as defense industry, aerospace industry, automotive industry, and high-speed train manufacturing. Some of these materials cannot be welded by conventional methods due to their high thermal conductivity and low melting point. In welding processes, the material properties are expected to be as close as possible to base material. Friction stir welding (FSW) is a joining method that provides welding below the melting point of materials that cannot be welded by conventional methods or where the welding process causes the mechanical structure of the material to deteriorate. In this study, FSW application, advantages and disadvantages and usage areas of friction stir welding were examined.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83381985","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}
Uzay Gezer, B. Demir, Yusuf Kepir, Alper Günöz, Memduh Kara
Composite materials are advanced engineering materials with superior properties to traditional materials. One of the most important disadvantages is the high cost of composite materials. Therefore, producing composite materials from the first to the last stage is a very important process. Homogenization is the most important parameter in production since composites contain more than one material type in their structure. In addition, composite structures are sensitive materials against low-velocity impacts. In this study, the effect of reinforcement material combination and stacking sequence on mechanical properties used in the production of composite materials was investigated by low-velocity impact simulations using LS-DYNA software. The mass of the 12 mm diameter spherical impactor used in the analyzes was determined as 10 kg and low-velocity impact tests were applied at 20 J, 30 J and 40 J energy levels. The composite samples were modeled with 180x100mm dimensions and the contact between the impactor and the sample was made from the center of the composite structure. Numerical analyzes were performed using the Tsai-Wu damage criterion in the LS-DYNA software, and material properties were defined using the "Mat_Enhanced_Composite_Damage (MAT 055)" material card.
{"title":"A numerical study on the low-velocity impact response of hybrid composite materials","authors":"Uzay Gezer, B. Demir, Yusuf Kepir, Alper Günöz, Memduh Kara","doi":"10.31127/tuje.1191785","DOIUrl":"https://doi.org/10.31127/tuje.1191785","url":null,"abstract":"Composite materials are advanced engineering materials with superior properties to traditional materials. One of the most important disadvantages is the high cost of composite materials. Therefore, producing composite materials from the first to the last stage is a very important process. Homogenization is the most important parameter in production since composites contain more than one material type in their structure. In addition, composite structures are sensitive materials against low-velocity impacts. In this study, the effect of reinforcement material combination and stacking sequence on mechanical properties used in the production of composite materials was investigated by low-velocity impact simulations using LS-DYNA software. The mass of the 12 mm diameter spherical impactor used in the analyzes was determined as 10 kg and low-velocity impact tests were applied at 20 J, 30 J and 40 J energy levels. The composite samples were modeled with 180x100mm dimensions and the contact between the impactor and the sample was made from the center of the composite structure. Numerical analyzes were performed using the Tsai-Wu damage criterion in the LS-DYNA software, and material properties were defined using the \"Mat_Enhanced_Composite_Damage (MAT 055)\" material card.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81678766","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}
One of the significant problems of our time and future is environmental pollution. There are many factors that cause environmental pollution. The main reasons are waste material. With rapid industrialization and increasing population, production, consumption and service activities have increased. Waste management is a management process that includes minimization, separate collection at source, intermediate storage, pre-treatment, the establishment of waste transfer centers, recovery and disposal when necessary, which are qualified as outputs as a result of activities such as production, application and consumption. The purpose of waste management is to ensure the management of wastes generated by human action without harming the environment and human health. In this context, re-evaluation of agricultural and aquaculture products that turn into waste after being used as a product is important both in terms of economic and environmental pollution. Herein, the use of cumin black pulp, which is waste at the end of black seed oil production, as a bio-based filler material in EPDM was examined. Accordingly, the effects of cumin black pulp added to the EPDM matrix at different content on the rheological, mechanical and crosslinking degree of EPDM were determined. With the use of 10 phr cumin black pulp, the mechanical and rheological properties of EPDM and the degree of crosslinking increased. In addition, it was revealed that the vulcanization parameters were also enhanced. Consequently, it has been concluded as a result of the analysis that the waste cumin black pulp can be used as a filling material in the EPDM matrix. Thus, it has been seen that a product in the state of waste can be recovered and become an economic value.
{"title":"THE EFFECT OF CUMIN BLACK (NIGELLA SATIVA) AS BIO-BASED FILLER ON RHEOLOGICAL AND MECHANICAL PROPERTIES OF EPDM COMPOSITES","authors":"A. Güngör","doi":"10.31127/tuje.1180753","DOIUrl":"https://doi.org/10.31127/tuje.1180753","url":null,"abstract":"One of the significant problems of our time and future is environmental pollution. There are many factors that cause environmental pollution. The main reasons are waste material. With rapid industrialization and increasing population, production, consumption and service activities have increased. Waste management is a management process that includes minimization, separate collection at source, intermediate storage, pre-treatment, the establishment of waste transfer centers, recovery and disposal when necessary, which are qualified as outputs as a result of activities such as production, application and consumption. The purpose of waste management is to ensure the management of wastes generated by human action without harming the environment and human health. In this context, re-evaluation of agricultural and aquaculture products that turn into waste after being used as a product is important both in terms of economic and environmental pollution. Herein, the use of cumin black pulp, which is waste at the end of black seed oil production, as a bio-based filler material in EPDM was examined. Accordingly, the effects of cumin black pulp added to the EPDM matrix at different content on the rheological, mechanical and crosslinking degree of EPDM were determined. With the use of 10 phr cumin black pulp, the mechanical and rheological properties of EPDM and the degree of crosslinking increased. In addition, it was revealed that the vulcanization parameters were also enhanced. Consequently, it has been concluded as a result of the analysis that the waste cumin black pulp can be used as a filling material in the EPDM matrix. Thus, it has been seen that a product in the state of waste can be recovered and become an economic value.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85650064","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}
Fracture toughness is an important phenomenon to reveal the actual strength of fractured rock materials. It is, therefore, crucial to use the fracture toughness models principally for simulating the performance of fractured rock medium. In this study, the mode-I fracture toughness (KIC) was investigated using several soft computing techniques. For this purpose, an extensive literature survey was carried out to obtain a comprehensive database that includes simple and widely used mechanical rock parameters such as uniaxial compressive strength (UCS) and Brazilian tensile strength (BTS). Several soft computing techniques such as artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), gene expression programming (GEP), and multivariate adaptive regression spline (MARS) were attempted to reveal the availability of these methods to estimate the KIC. Among these techniques, it was determined that ANN presents the best prediction capability. The correlation of determination value (R2) for the proposed ANN model is 0.90, showing its relative success. In this manner, the present study can be declared a case study, indicating the applicability of several soft computing techniques for the evaluation of KIC. However, the number of samples and independent variables should be increased to improve the established predictive models in future studies.
{"title":"A comparative study to estimate the mode I fracture toughness of rocks using several soft computing techniques","authors":"E. Köken, Tümay Kadakci̇ Koca","doi":"10.31127/tuje.1120669","DOIUrl":"https://doi.org/10.31127/tuje.1120669","url":null,"abstract":"Fracture toughness is an important phenomenon to reveal the actual strength of fractured rock materials. It is, therefore, crucial to use the fracture toughness models principally for simulating the performance of fractured rock medium. In this study, the mode-I fracture toughness (KIC) was investigated using several soft computing techniques. For this purpose, an extensive literature survey was carried out to obtain a comprehensive database that includes simple and widely used mechanical rock parameters such as uniaxial compressive strength (UCS) and Brazilian tensile strength (BTS). Several soft computing techniques such as artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), gene expression programming (GEP), and multivariate adaptive regression spline (MARS) were attempted to reveal the availability of these methods to estimate the KIC. Among these techniques, it was determined that ANN presents the best prediction capability. The correlation of determination value (R2) for the proposed ANN model is 0.90, showing its relative success. In this manner, the present study can be declared a case study, indicating the applicability of several soft computing techniques for the evaluation of KIC. However, the number of samples and independent variables should be increased to improve the established predictive models in future studies.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82831201","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}
Groundwater is an essential water source, becoming more vital due to shortages in available surface water resources. Hence, monitoring groundwater levels can show the amount of water available to extract and use for various purposes. However, the groundwater system is naturally complex, and we need models to simulate it. Therefore, we employed a deep learning model called CNN-biLSTM neural networks for modeling grounding, and the data was obtained from USGS. The data included daily groundwater levels from 2002 to 2021, and the data was divided into 95% for training and 5% for teasing. Besides, three deep CNN-biLSTM models were employed using three different algorithms (SGDM, ADAM, and RMSprop. Also, Bayesian optimization was used to optimize parameters such as the number of biLSTM layers and the number of biLSTM units. The model's performance was based on Spearman's Rank-Order Correlation (r), and the model with SGDM showed the best results compared to other models in this study. Finally, the CNN model with LSTM can simulate time series data effectively.
{"title":"MODELING OF DAILY GROUNDWATER LEVEL USING DEEP LEARNING NEURAL NETWORKS","authors":"M. M. Othman","doi":"10.31127/tuje.1169908","DOIUrl":"https://doi.org/10.31127/tuje.1169908","url":null,"abstract":"Groundwater is an essential water source, becoming more vital due to shortages in available surface water resources. Hence, monitoring groundwater levels can show the amount of water available to extract and use for various purposes. However, the groundwater system is naturally complex, and we need models to simulate it. Therefore, we employed a deep learning model called CNN-biLSTM neural networks for modeling grounding, and the data was obtained from USGS. The data included daily groundwater levels from 2002 to 2021, and the data was divided into 95% for training and 5% for teasing. Besides, three deep CNN-biLSTM models were employed using three different algorithms (SGDM, ADAM, and RMSprop. Also, Bayesian optimization was used to optimize parameters such as the number of biLSTM layers and the number of biLSTM units. The model's performance was based on Spearman's Rank-Order Correlation (r), and the model with SGDM showed the best results compared to other models in this study. Finally, the CNN model with LSTM can simulate time series data effectively.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84358708","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 effects of global climate change on hydrological and meteorological variables are increasing day by day. Therefore, hydro-meteorological parameters should be examined carefully. In this study, the effects of global climate change on the Hirfanli Dam Basin temperature series were investigated using the Mann-Kendall Test and Sequential Mann–Kendall Test. The annual mean temperature series of six stations recorded between 1965 and 2017 were analyzed and evaluated. It has been determined that the annual mean temperature has increased throughout the basin and significant increases started since the 1990s. Researches analysing the effects of global climate change on hydro-meteorological parameters related to the Hirfanli Dam Basin should be increased.
{"title":"Temperature series analysis of the Hirfanli Dam Basin with the Mann-Kendall and Sequential Mann-Kendall tests","authors":"Utku Zeybekoğlu","doi":"10.31127/tuje.1145716","DOIUrl":"https://doi.org/10.31127/tuje.1145716","url":null,"abstract":"The effects of global climate change on hydrological and meteorological variables are increasing day by day. Therefore, hydro-meteorological parameters should be examined carefully. In this study, the effects of global climate change on the Hirfanli Dam Basin temperature series were investigated using the Mann-Kendall Test and Sequential Mann–Kendall Test. The annual mean temperature series of six stations recorded between 1965 and 2017 were analyzed and evaluated. It has been determined that the annual mean temperature has increased throughout the basin and significant increases started since the 1990s. Researches analysing the effects of global climate change on hydro-meteorological parameters related to the Hirfanli Dam Basin should be increased.","PeriodicalId":23377,"journal":{"name":"Turkish Journal of Engineering and Environmental Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88853150","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：