Zonguldak Bülent Ecevit University Institutional Repository
Not a member yet
9495 research outputs found
Sort by
Usage of Weka Software Based On Machine Learning Algorithms for Prediction of Liver Fibrosis/Cirrhosis
No full textThe liver, a life-sustaining organ, plays a substantial role in many body functions. Liver diseases have become an important world health problem in terms of prevalence, incidences, and mortalities. Liver fibrosis/cirrhosis is great of importance, because if not treated in time liver cancer could be occurred and spread to other parts of the body. For this reason, early diagnosis of liver fibrosis/cirrhosis gives significance. Accordingly, this study investigated the performances of different machine learning algorithms for prediction of liver fibrosis/cirrhosis based on demographic and blood values. In this context, random forest, k nearest neighbour, C4.5 decision tree, K-star, random tree and reduced error pruning tree algorithms were used. Two distinct approaches were employed to evaluate the performances of machine learning algorithms. In the first approach, the entire features of dataset were utilized, while in the second approach, only the features selected through principal component analysis were used. Each approach was rigorously assessed using both 10-fold cross-validation and data splitting (70% train and 30% test) techniques. By conducting separate evaluations for each approach, a comprehensive understanding of the effectiveness of utilizing all features versus extracted features based principal component analysis was attained, providing valuable insights into the impact of feature dimensionality reduction on model performance. In this study, all analyses were implemented on WEKA data mining tool. In the first approach, the classification accuracies of random forest algorithm were 89.72% and 90.75% with the application of data splitting (70%-30%) and cross-validation techniques, respectively. In the second approach, where feature reduction is performed using principal component analysis technique, the accuracy values obtained from data splitting and cross-validation techniques of random forest algorithm were 88.61% and 88.83%, respectively. The obtained results revealed out that random forest algorithm outperformed for both approaches. Besides, the application of principal component analysis technique negatively affected the classification performance of used machine learning algorithms. It is thought that the proposed model will guide specialist physicians in making appropriate treatment decisions for patients with liver fibrosis/cirrhosis, potentially leading to death in its advanced stages.</jats:p
Evaluation of the current transport mechanism depending on the temperature of Schottky structures with Ti:DLC interlayer
No full textThis study emphasizes the possible current transport mechanisms (CTMs) of the Schottky structure with Ti:DLC interlayer for a wide temperature interval (80–470 K). In the related temperature interval, the ideality factor (n) and barrier height (ΦBo) values changed from 6.95 to 2.28 and 0.19 to 0.87 eV, respectively. These temperature dependent n and ΦBo values show that the CTM deviates significantly from the standard TE theory and that the barrier at the metal/semiconductor interface is not homogeneous. Additionally, the observed deviation from linearity of the Richardson plot (RP) at low temperatures and obtained very low Richardson constant (A*) at higher temperatures when compared to its theoretical value are other evidence of deviation from TE theory. The observed two separate linear in the ΦBo-e/2kT plot reveal the Double-Gaussian distribution (DGD) corresponding low and moderate temperature intervals. The modified RP based on the GD of the BH gives a closer to the theoretical value of A*. Along with CTM analyses, the structure's series resistance (RS) was estimated via both Ohm's law and Cheung functions. Finally, the Card-Rhoderick method was applied to achieve the variations of the interface trap density (Dit) depending on energy for each temperature by considering voltage-dependent n and ΦB
Estimating the crashworthiness performances of crushboxes using artificial neural network
No full textAbstractStudies on the development of energy absorbing systems that minimize vehicle chassis damage in traffic accidents are increasing day by day. Many designs have been made in the studies on crushboxes used to absorb the energy released in the event of an accident. These design works are quite costly and take a long time. In this study, to design crushboxes faster and more economically was estimated using artificial neural network. The input layer of the artificial neural network model consists of three different materials, thicknesses (between 0.8 and 2.2 mm) and three different initial speeds. In the artificial neural network model, 42 different models were created by changing the different training functions (training, trainlm and trainrp), transfer functions (tansig and logsig) and the number of neurons in the hidden layer (between 9 and 33). R2 and root mean square error (RMSE) methods were used to evaluate the efficiency of artificial neural network models. The training function was found to be highly accurate (R2: 0.99999 and root mean square error: 0.314727E‐05) when the training function was “trainlm” and the number of neurons in the hidden layer was 33. The training and testing results of the artificial neural network model show that artificial neural networks can be used to estimate the specific energy absorption/energy/peak crush force value of crushboxes.</jats:p
Randomization based evaluation of distinct topological and cancer expression characteristics of mutually acting gene pairs
No full textAbstract Small scale molecular network patterns and motifs are crucial for systems level understanding of cellular information transduction. Using randomizations, we statistically explored, previously overlooked basic patterns of mutually acting pairs, i.e. mutually positive (PP) or negative (NN) and positive–negative (PN) pairs, in two comprehensive and distinct large-scale molecular networks from literature; the human protein signaling network (PSN) and the human gene regulatory network (GRN). Only the positive and negative signs of all interacting pairs were randomized, while the gene pairs and the number of positive and negative signs in the original network were kept constant. While the numbers of NN and PN pairs were significantly higher, the number of PP pairs was significantly lower than randomly expected values. Genes participating in mutual pairs were more connected than other genes. NN genes were more connected than PP and PN in GRN for all types of degree values, including in, out, positive or negative connections, but less connected for in-degree and more connected for out-degree values in PSN. They also had significantly high number of intersections with each other and PN pairs than randomly expected values, indicating potential cooperative mechanisms. The three mutual interaction designs we examined had distinct RNA and protein expression correlation characteristics. NN protein pairs were uniquely over-represented across normal tissue samples, whose negative correlations were lost across cancer tissue samples. PP and PN pairs showed non-random positive RNA or protein expression correlation across normal or cancer tissue samples. Moreover, we developed an online tool, i.e. MGPNet, for further user specific analysis of mutual gene pairs. We identified SNCA with significantly enriched negatively correlated NN pairs. Unique non-random characteristics of mutual gene pairs identified in two different comprehensive molecular networks could provide valuable information for a better comparative understanding of molecular design principles between normal and cancer states. Insight Box/Paragraph Statement: This study provides a systems-level perspective on cellular information transduction by analyzing mutually acting pairs of genes. By examining mutually positive (PP), mutually negative (NN), and positive–negative (PN) pairs in the human protein signaling network (PSN) and the human gene regulatory network (GRN), we uncover significant variations in their connectivity and expression correlation. Our findings highlight the unique features of NN pairs across normal and cancer tissues and offer insights into molecular design principles. The development of the MGPNet tool further enhances user-specific analyses, enabling a deeper understanding of gene pair mechanisms and their potential cooperative roles in cellular processes.</jats:p
Identifying risk factors for blood culture negative infective endocarditis: An international ID-IRI study
No full textBlood culture-negative endocarditis (BCNE) is a diagnostic challenge, therefore our objective was to pinpoint high-risk cohorts for BCNE.The study included adult patients with definite endocarditis. Data were collected via the Infectious Diseases International Research Initiative (ID-IRI). The study analysing one of the largest case series ever reported was conducted across 41 centers in 13 countries. We analysed the database to determine the predictors of BCNE using univariate and logistic regression analyses.Blood cultures were negative in 101 (11.65 %) of 867 patients. We disclosed that as patients age, the likelihood of a negative blood culture significantly decreases (OR 0.975, 95 % CI 0.963-0.987, p < 0.001). Additionally, factors such as rheumatic heart disease (OR 2.036, 95 % CI 0.970-4.276, p = 0.049), aortic stenosis (OR 3.066, 95 % CI 1.564-6.010, p = 0.001), mitral regurgitation (OR 1.693, 95 % CI 1.012-2.833, p = 0.045), and prosthetic valves (OR 2.539, 95 % CI 1.599-4.031, p < 0.001) are associated with higher likelihoods of negative blood cultures. Our model can predict whether a patient falls into the culture-negative or culture-positive groups with a threshold of 0.104 (AUC±SE = 0.707 ± 0.027). The final model demonstrates a sensitivity of 70.3 % and a specificity of 57.0 %.Caution should be exercised when diagnosing endocarditis in patients with concurrent cardiac disorders, particularly in younger cases
Effects of frequently consumed beverages by children on the surface roughness of compomers.
No full textTo evaluate and compare changes on the surface roughness of conventional and colored compomers used in pediatric dentistry caused by beverages frequently consumed by children.176 conventional and colored compomer discs were prepared. The discs were divided into four equal subgroups and incubated in different beverages: distilled water, milk, fruit juice, and cola. The surface roughness of the samples was measured and recorded on Days 1, 7, 14, 21, and 28. The data obtained were statistically analyzed.In distilled water and milk, the surface roughness of the conventional compomer was higher than the colored compomer after Day 7 (P< 0.05). In fruit juice and cola, the surface roughness of conventional and colored compomers was similar at all timepoints (P< 0.05). There was a significant difference between discs incubated in distilled water and milk, on Days 21 and 28 (P< 0.05). The colored compomer showed the highest roughness in cola on Day 1, whereas the conventional compomer showed the highest roughness in milk on Day 21.Cola caused the highest surface roughness on the surface of colored compomers, whereas milk caused the highest surface roughness on conventional compomers
New solid state contact potentiometric sensor based on a thiosemicarbazone derivative molecule for determination of copper(II) ions in environmental samples
No full textThiosemicarbazone derivative molecules have proven to be good sensor materials in studies using various analytical methods. In this study, new ion-selective sensors were prepared using 2-furaldehyde thiosemicarbazone and their potentiometric properties were then tested. The prepared sensors exhibited a very good selectivity towards copper(II) ions over various ions. Surface images and mappings of the prepared sensors were examined by scanning electron microscopy. Copper(II)-selective sensors had a Nernstian response of 28.5 +/- 1.5 mV/decade, and a low detection limit of 6.89 x 10-6 mol L-1 over a wide concentration range of 1.0 x 10-5-1.0 x 10-1 mol L-1 (R2 = 0.9992). The newly prepared copper(II)-selective sensors were shown to be produced reproducibly, stable and economically. The sensors, which can operate in a wide pH range of 5.0-9.0 without being affected by pH changes, had a fast response time of 5 s. The newly developed copper(II)-selective sensors were used as indicator electrodes for the potentiometric titration of copper(II) ions with ethylenediaminetetraacetic acid and were successfully applied for the determination of copper(II) ion content in various environmental samples with very good performance. The data obtained with the developed sensor were compared with atomic absorption spectroscopy and it was determined that the results of both methods were compatible with each other.</p
The Effects of Coagulation on Adsorption of Micropollutants in Waste Water Treatment Plants
No full textAbstractIn this study, the potential positive or negative effects of the coagulation process during the adsorption of micropollutants were investigated in treated waste water. Single‐walled carbon nanotubes (SWCNTs) were employed as adsorbents in batch adsorption processes. Alum was used as a coagulant in batch coagulation experiments carried out in the laboratory to coagulate water samples obtained from effluents at the advanced biological wastewater treatment plant in the center of Zonguldak (ZWWTP), Turkey. The ultrafiltration process (UF) was used to demonstrate the importance of the dissolved organic matter content (DOM) for the removal of micropollutants by coagulation and adsorption. Consequently, coagulation was found to be effective in the removal of hydrophobic organics, that is, DOM fractions with molecular weights of 5 kDa and 1–3 kDa, while adsorption with SWCNT was effective in the removal of hydrophilic organics (<1 kDa). SWCNT adsorption was effective for the removal of carbamazepine, diclofenac, and triclosan in combined treatment steps. Furthermore, the removal of carbamazepine, diclofenac, and triclosan was above 90% with SWCNT adsorption before coagulation. It was concluded that the significant correlation between micropollutant removal and the reduction in UV254 is attributed to the general non‐selectivity of adsorption on the SWCNTs surface. Micropollutants and UV254 absorbing compounds adsorb simultaneously. It can be reasonably deduced that a high/low adsorptive removal of a specific micropollutant is typically accompanied by a high/low removal of UV254‐absorbing substances. Even though the majority of micropollutants also absorb UV254, their concentrations in municipal wastewater are insignificant in comparison to the overall UV254 measurements. Hence, correcting the actual UV254 measurements of the combined treatment for removal by coagulation produces adsorptive UV254 removal. In other words, if the removal of UV254 by coagulation is already known, the actual UV254 measurements obtained in a combined treatment step can be adjusted to produce UV254 removal by SWCNT adsorption. Therefore, UV254 can be used as a control parameter for carbamazepine, diclofenac, and triclosan removal and SWCNT dosing control utilizing differential UV254 measurements can be implemented.</jats:p
An Analytical Study on Dual Generalized Guglielmo Numbers
No full textIn this study, we investigate the generalized dual hyperbolic Guglielmo numbers and then various special cases are explored (including dual triangular numbers, dual triangular-Lucas numbers, dual oblong numbers, and dual pentagonal numbers). Binet's formulas, generating functions, and summation formulas for these numbers are presented. Additionally, Catalan's and Cassini's identities are provided, along with matrices associated with these sequences. Moreover, we give some identities and matrices related with these sequences.</jats:p