Application of expert systems in prediction of flexural strength of cement mortars

Eyyup Gulbandilar,Yilmaz Kocak 사단법인 한국계산역학회 2016 Computers and Concrete, An International Journal Vol.18 No.1

In this study, an Artificial Neural Network (ANN) and Adaptive Network-based Fuzzy Inference Systems (ANFIS) prediction models for flexural strength of the cement mortars have been developed. For purpose of constructing this models, 12 different mixes with 144 specimens of the 2, 7, 28 and 90 days flexural strength experimental results of cement mortars containing pure Portland cement (PC), blast furnace slag (BFS), waste tire rubber powder (WTRP) and BFS+WTRP used in training and testing for ANN and ANFIS were gathered from the standard cement tests. The data used in the ANN and ANFIS models are arranged in a format of four input parameters that cover the Portland cement, BFS, WTRP and age of samples and an output parameter which is flexural strength of cement mortars. The ANN and ANFIS models have produced notable excellent outputs with higher coefficients of determination of R2, RMS and MAPE. For the testing of dataset, the R2, RMS and MAPE values for the ANN model were 0.9892, 0.1715 and 0.0212, respectively. Furthermore, the R2, RMS and MAPE values for the ANFIS model were 0.9831, 0.1947 and 0.0270, respectively. As a result, in the models, the training and testing results indicated that experimental data can be estimated to a superior close extent by the ANN and ANFIS models.

Tracing sub-surface swept profiles of tapered toroidal end mills between level cuts

Eyyup Aras 한국CDE학회 2019 Journal of computational design and engineering Vol.6 No.4

Development of closed-form solutions and algorithms for constructing sub-surface swept profiles (SWP) of toroidal and conical bodies is presented in this paper. While the problem of identifying the entire SWP of such surfaces has been extensively investigated in extant studies, construction of subsurface SWPs has rarely been addressed despite the subject being of great significance to machining process employing nonstandard-shaped NC tools. Torus shapes considered in extant literature are restricted to the fourth quadrant of a tube cross section. In industrial applications, however, profile cutters contain different regions of a toroidal surface. To identify SWP elements in the proposed study, a single analytical expres-sion in one variable has been deduced using two moving frames. The basic idea behind such a formula-tion is to employ the one-to-many strategy, which greatly reduces the computational cost and effort. Algorithms to identify feasible domains of SWP parameters at each level cut, where toroidal and conical surfaces meet, have also been proposed in this study. This is important, since cutting a tool surfaces along the rotation axis divides SWP-parameter domains into non overlapping sets of intervals that must be addressed for each tool posture. In addition, this study demonstrates that for certain tool postures, while C1 continuity between sub-surfaces is satisfied, the SWP connectivity is lost at some points. To locate these so called singular-characteristic points, some precomputation steps have been performed. Lastly, several factors affecting the smoothness of SWPs have been identified and discussed.

Vector-valued envelope functions for constructing tool swept surfaces in continuous domains

Aras Eyyup 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.2

This paper proposes the vector-valued envelope functions to describe form cutters’ swept profiles at the choice of particular motion instances. The general idea behind such a formulation is to embed the tangency constraint into the tool surface expression and form a single continuous function to describe the segmental curves whose elements lie on the envelopes. This results in skipping unnecessary calculations when no envelope-surface point is associated with the specified input data, reducing the sizeable computational burden due to repetitive constraint implementations, and most importantly, depending on the tool kinematics’ complexity, avoiding the tangency-constraint violations between successive envelope-surface points where the exact fit cannot be obtained. In this study, firstly, the NC tool surface models present in extant literature have been restructured using the four-parameter set of spheres to attain the required one-to-one correspondence between the domain and range sets of these functions, followed by excluding the tangency-constraint evaluations by introducing the systematic parameter-reduction procedures that led to the development of constraint-embedded envelope functions. Next, we introduced the branch-existence test, which allowed us to check whether these functions are continuous over closed domain intervals. Finally, we covered algorithms for implementing the functions.

Predicting the compressive strength of cement mortars containing FA and SF by MLPNN

Yilmaz Kocak,Eyyup Gulbandilar,Muammer Akcay 사단법인 한국계산역학회 2015 Computers and Concrete, An International Journal Vol.15 No.5

In this study, a multi-layer perceptron neural network (MLPNN) prediction model for compressive strength of the cement mortars has been developed. For purpose of constructing this model, 8 different mixes with 240 specimens of the 2, 7, 28, 56 and 90 days compressive strength experimental results of cement mortars containing fly ash (FA), silica fume (SF) and FA+SF used in training and testing for MLPNN system was gathered from the standard cement tests. The data used in the MLPNN model are arranged in a format of four input parameters that cover the FA, SF, FA+SF and age of samples and an output parameter which is compressive strength of cement mortars. In the model, the training and testing results have shown that MLPNN system has strong potential as a feasible tool for predicting 2, 7, 28, 56 and 90 days compressive strength of cement mortars.

Effectiveness of Intravitreal Ranibizumab for Diabetic Macular Edema with Serous Retinal Detachment

Mahmut Kaya,Eyyup Karahan,Taylan Ozturk,Nilufer Kocak,Suleyman Kaynak 대한안과학회 2018 Korean Journal of Ophthalmology Vol.32 No.4

Purpose: To evaluate the effectiveness of intravitreal injection of ranibizumab (IVR) in treating diabetic macular edema (DME) with serous retinal detachment (SRD) based on spectral domain optical coherence tomography (SD-OCT) patterns. Methods: One hundred thirty-four eyes of 134 patients with DME who underwent SD-OCT evaluation were included in this study. We retrospectively analyzed the medical records of patients who received IVR for the treatment of DME. Their eyes were classified into three groups according to the following SD-OCT features: SRD, diffuse retinal thickness and cystoid macular edema. The three groups were compared regarding changes in best-corrected visual acuity and central foveal thickness (CFT) after IVR. Results: The mean age was 61.4 ± 9.2 years (range, 44 to 81 years). The average length of the follow-up period was 9.4 ± 3.4 months (range, 6 to 24 months). The mean CFT value was significantly reduced in all groups (p < 0.001) after treatment. Increases in best-corrected visual acuity were statistically significant for the diffuse retinal thickness and cystoid macular edema groups (p < 0.001 and p < 0.001, respectively). However, there was no significant improvement after IVR injection in the SRD group (p = 0.252). In the SRD group, patients with ellipsoid zone disruption and external limiting membrane disruption demonstrated poorer visual gains at the last follow-up visit (p < 0.005 and p = 0.002, respectively). Conclusions: A significant reduction in CFT with required IVR injections in DME with SRD was achieved but was accompanied by a worse functional outcome in the SRD group. The presence of subretinal fluid on SD-OCT in study eyes may be a poor prognostic factor for visual acuity.

Investigation of the Effect on the Physical and Mechanical Properties of the Dosage of Additive in Self-consolidating Concrete

Yuksel Esen,Eyyup Orhan 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.7

The objective of this study was to investigate the effect of superplasticizer and mineral admixture contents on the properties of Self-Consolidating Concrete (SCC). Silica fume was used as a mineral admixture and polycarboxylate based third generation superplasticizer was used as a chemical admixture. In order to determine the optimum admixture dosages; trial mixes were prepared with varying admixture dosages. Nine concrete mixtures with different admixture dosages were prepared from trial mixes. Hardened concrete properties and self-compactability criteria of these series were determined and test results were compared between these SCC mixtures. It was observed that 10S1.3A (10% Silica Fume, 1.3% Superplasticizer) and 10S1.5A (10% Silica Fume, 1.5% Superplasticizer) mixtures show the best performance with regard to fresh and hardened concrete properties.

Estimation of compressive strength of BFS and WTRP blended cement mortars with machine learning models

Giyasettin Ozcan,Yilmaz Kocak,Eyyup Gulbandilar 사단법인 한국계산역학회 2017 Computers and Concrete, An International Journal Vol.19 No.3

The aim of this study is to build Machine Learning models to evaluate the effect of blast furnace slag (BFS) and waste tire rubber powder (WTRP) on the compressive strength of cement mortars. In order to develop these models, 12 different mixes with 288 specimens of the 2, 7, 28, and 90 days compressive strength experimental results of cement mortars containing BFS, WTRP and BFS+WTRP were used in training and testing by Random Forest, Ada Boost, SVM and Bayes classifier machine learning models, which implement standard cement tests. The machine learning models were trained with 288 data that acquired from experimental results. The models had four input parameters that cover the amount of Portland cement, BFS, WTRP and sample ages. Furthermore, it had one output parameter which is compressive strength of cement mortars. Experimental observations from compressive strength tests were compared with predictions of machine learning methods. In order to do predictive experimentation, we exploit R programming language and corresponding packages. During experimentation on the dataset, Random Forest, Ada Boost and SVM models have produced notable good outputs with higher coefficients of determination of R2, RMS and MAPE. Among the machine learning algorithms, Ada Boost presented the best R2, RMS and MAPE values, which are 0.9831, 5.2425 and 0.1105, respectively. As a result, in the model, the testing results indicated that experimental data can be estimated to a notable close extent by the model.

Compressive strength estimation of concrete containing zeolite and diatomite: An expert system implementation

Giyasettin Ozcan,Yilmaz Kocak,Eyyup Gulbandilar 사단법인 한국계산역학회 2018 Computers and Concrete, An International Journal Vol.21 No.1

In this study, we analyze the behavior of concrete which contains zeolite and diatomite. In order to achieve the goal, we utilize expert system methods. The utilized methods are artificial neural network and adaptive network-based fuzzy inference systems. In this respect, we exploit seven different mixes of concrete. The concrete mixes contain zeolite, diatomite, mixture of zeolite and diatomite. All seven concrete mixes are exposed to 28, 56 and 90 days\' compressive strength experiments with 63 specimens. The results of the compressive strength experiments are used as input data during the training and testing of expert system methods. In terms of artificial neural network and adaptive network-based fuzzy models, data format comprises seven input parameters, which are; the age of samples (days), amount of Portland cement, zeolite, diatomite, aggregate, water and hyper plasticizer. On the other hand, the output parameter is defined as the compressive strength of concrete. In the models, training and testing results have concluded that both expert system model yield thrilling medium to predict the compressive strength of concrete containing zeolite and diatomite.

The Metabolic Syndrome is Associated with More Aggressive Prostate Cancer

Ozbek, Emin,Otunctemur, Alper,Dursun, Murat,Sahin, Suleyman,Besiroglu, Huseyin,Koklu, Ismail,Erkoc, Mustafa,Danis, Eyyup,Bozkurt, Muammer Asian Pacific Journal of Cancer Prevention 2014 Asian Pacific journal of cancer prevention Vol.15 No.9

Purpose: The aim of this study was to analyze any association between the metabolic syndrome (MetS) and risk of prostate cancer (PCa) and cancer grade among men undergoing radical prostatectomy for PCa. Materials and Methods: 50 patients with MetS and 50 patients without MetS who undervent radical prostatectomy (RP) were included in the study. Age at biopsy, height, weight, digital rectal examination (DRE), pre-biopsy PSA levels, prostate volume, histopathologic diagnosis after surgery and gleason scores were collected data from all patients. Histologic material obtained at biopsy was given a Gleason score; tumours with a Gleason score ${\geq}7$ were considered high grade and <7 were considered low grade. Results: The mean age at the time of biopsy was $63.7{\pm}5.94$ in patients with MetS and $61.6{\pm}6.14$ in patients without MetS. Men with MetS had significantly lower PSA levels (p=0.01) ($7.21{\pm}2.74$ and $8.81{\pm}2.72$, respectively). Also, the men with MetS had higher RP tumor grade (p=0.04). Conclusions: Men with MetS undergoing RP have lower PSA levels and have significantly higher grade PCa. We must be careful for screening PCa in patients with MetS. Although the patients had lower PSA levels, they may have high grade disease.

Renal Cell Carcinoma is More Aggressive in Turkish Patients with the Metabolic Syndrome

Ozbek, Emin,Otunctemur, Alper,Sahin, Suleyman,Dursun, Murat,Besiroglu, Huseyin,Koklu, Ismail,Polat, Emre Can,Erkoc, Mustafa,Danis, Eyyup,Bozkurt, Muammer Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.12

Background: Metabolic syndrome (MetS) is a multifactorial disease characterized by impaired glucose tolerance/diabetes, obesity, high triglyceride levels, low HDL levels, and hypertension. In this study we evaluate the relationship between tumor size and grade, and presence of the metabolic syndrome in patients with renal cell carcinoma. Materials and Methods: Between 2007-2013, radical nephrectomy was performed for 310 patients with renal tumors in our clinic and those with pathology reported renal cell carcinoma were enrolled and divided into two groups, with and without metabolic syndrome diagnosed on the basis of the National Cholesterol Education Program (NCEP) Adult Treatment Panel III (ATP III) criteria. The relationship between tumor size and grade of the two groups (Fuhrman nuclear degree) was evaluated statistically. Results: The metabolic syndrome was found in 70 patients, with a mean age of 65.5 (40-87), as compared to 58.8 (31-84) years in the non-metabolic syndrome group. Tumor size over 7 cm was found in 54% and 33%, respectively, and tumor grade over Fuhrman 3 in 56% and 32% of patients. Patients with metabolic syndrome had significantly higher tumor size and grade (p<0.05). In the presence of hypertension, diabetes and high triglyceride levels, significant assocations were again observed (p<0.05). Tumor size and degree also increased with increasing body mass index but this was not statistically significant (p>0.05). Conclusions: Renal cancer is more aggressive in patients with metabolic syndrome. Lifestyle and risk factors were revealed to be significant influences in renal cancer patients.