6 results
Search Results
Now showing 1 - 6 of 6
Article Citation - WoS: 44Citation - Scopus: 49A Neural Network-Based Approach for Calculating Dissolved Oxygen Profiles in Reservoirs(Springer London Ltd, 2003) Soyupak, S; Karaer, F; Gürbüz, H; Kivrak, E; Sentürk, E; Yazici, AA Neural Network (NN) modelling approach has been shown to be successful in calculating pseudo steady state time and space dependent Dissolved Oxygen (DO) concentrations in three separate reservoirs with different characteristics using limited number of input variables. The Levenberg-Marquardt algorithm was adopted during training. Pre-processing before training and post processing after simulation steps were the treatments applied to raw data and predictions respectively. Generalisation was improved and over-fitting problems were eliminated: Early stopping method was applied for improving generalisation. The correlation coefficients between neural network estimates and field measurements were as high as 0.98 for two of the reservoirs with experiments that involve double layer neural network structure with 30 neurons within each hidden layer. A simple one layer neural network structure with 11 neurons has yielded comparable and satisfactorily high correlation coefficients for complete data set, and training, validation and test sets of the third reservoir.Article Citation - WoS: 11Citation - Scopus: 12Predictive Models for Mechanical Properties of Expanded Polystyrene (eps) Geofoam Using Regression Analysis and Artificial Neural Networks(Springer London Ltd, 2022) Akis, E.; Guven, G.; Lotfisadigh, B.Initial elastic modulus and compressive strength are the two most important engineering properties for modeling and design of EPS geofoams, which are extensively used in civil engineering applications such as light-fill material embankments, retaining structures, and slope stabilization. Estimating these properties based on geometric and physical parameters is of great importance. In this study, the compressive strength and modulus of elasticity values are obtained by performing 356 unconfined compression tests on EPS geofoam samples with different shapes (cubic or disc), dimensions, loading rates, and density values. Using these test results, the mechanical properties of the specimens are predicted by linear regression and artificial neural network (ANN) methods. Both methods predicted the initial modulus of elasticity (E-i), 1% strain (sigma(1)), 5% strain (sigma(5)), and 10% strain (sigma(10)) strength values on a satisfactory level with a coefficient of correlation (R-2) values of greater than 0.901. The only exception was in prediction of sigma(1) and E-i in disc-shaped samples by linear regression method where the R-2 value was around 0.558. The results obtained from linear regression and ANN approaches show that ANN slightly outperform linear regression prediction for E-i and sigma(1) properties. The outcomes of the two methods are also compared with results of relevant studies, and it is observed that the calculated values are consistent with the results from the literature.Article Citation - WoS: 11Citation - Scopus: 13Automated Selection of Optimal Material for Pressurized Multi-Layer Composite Tubes Based on an Evolutionary Approach(Springer London Ltd, 2018) Azad, Saeid Kazemzadeh; Akis, TolgaDecision making on the configuration of material layers as well as thickness of each layer in composite assemblies has long been recognized as an optimization problem. Today, on the one hand, abundance of industrial alloys with different material properties and costs facilitates fabrication of more economical or light weight assemblies. On the other hand, in the design stage, availability of different alternative materials apparently increases the complexity of the design optimization problem and arises the need for efficient optimization techniques. In the present study, the well-known big bang-big crunch optimization algorithm is reformulated for optimum design of internally pressurized tightly fitted multi-layer composite tubes with axially constrained ends. An automated material selection and thickness optimization approach is employed for both weight and cost minimization of one-, two-, and three-layer tubes, and the obtained results are compared. The numerical results indicate the efficiency of the proposed approach in practical optimum design of multi-layer composite tubes under internal pressure and quantify the optimality of different composite assemblies compared to one-layer tubes.Article Citation - WoS: 13Citation - Scopus: 15Daily Living Activities, Exercise Capacity, Cognition, and Balance in Copd Patients With and Without Frailty(Springer London Ltd, 2022) Kagiali, Sezen; Inal-Ince, Deniz; Cakmak, Aslihan; Calik-Kutukcu, Ebru; Saglam, Melda; Vardar-Yagli, Naciye; Coplu, LutfiBackground Information on the interaction between frailty and chronic obstructive pulmonary disease (COPD) is limited. Aims This study aimed to compare activities of daily living (ADL), exercise capacity, balance, and cognition in COPD patients with and without frailty. Methods Twenty frail and 28 non-frail COPD patients aged 55 years and over were included. Frailty was determined according to Fried et al. Dyspnea was evaluated using the modified Medical Research Council (mMRC) dyspnea scale. Respiratory and peripheral muscle strength were measured. Functional capacity was assessed using a 6-min walk test (6MWT); ADL performance was evaluated using the Glittre ADL test. The balance was evaluated using the functional reach test (FRT). Cognitive function was assessed using the Montreal Cognitive Evaluation (MoCA) Test. Quality of life was measured using the COPD Assessment Test (CAT). Results The mMRC and CAT scores were higher in the frail patients as compared with the non-frail patients (p < 0.05). The maximal inspiratory pressure, handgrip strength, 6MWT distance, and FRT score were lower in the frail patients as compared with the non-frail patients (p < 0.05). The duration for the Glittre ADL test was longer in the frail patients than the non-frail patients (p < 0.05). There was no significant difference between MoCA scores between groups (p > 0.05). Conclusions Frail COPD patients have increased dyspnea perception, impaired muscle strength, and functional capacity, ADL performance, balance, and quality of life. Whether pulmonary rehabilitation programs for patients with frail COPD need to be adapted with new rehabilitation strategies, including components of frailty, needs further investigation.Article Citation - WoS: 2Citation - Scopus: 1Evaluation of Laser Ablation for Recurrent Pilonidal Sinus Disease: Treatment Success, Recurrence Rates, and Patient Outcomes(Springer London Ltd, 2025) Emral, Ahmet Cihangir; Yazici, Sinan EfePurposePilonidal sinus disease (PD) is a chronic, recurrent inflammatory condition primarily affecting the sacrococcygeal region, often resulting in discomfort, abscess formation, and recurrent disease. Various surgical interventions, including laser ablation, have been employed to treat recurrent PD. This study evaluates the efficacy of laser ablation in patients with recurrent PD, focusing on treatment success, recurrence rates, complications, and recovery outcomes.MethodsA retrospective analysis of 37 patients with recurrent pilonidal sinus disease treated with laser ablation between January 2022 and January 2025 was conducted. Preoperative data, postoperative complications, healing time, Visual Analog Scale values, and return to normal activities were collected.ResultsThe results showed that 70.3% of patients achieved complete healing without recurrence, while 21.6% experienced recurrence within a mean follow-up of 9.6 months. Five patients (13.5%) developed superficial infections, which were managed with local dressing. The median time for wound healing was 35 days, and patients returned to normal activities in an median of 1 day. Persistent disease was observed in 8 patients (21.6%), of whom 5 patients (62.5%) achieved full epithelialization after retreatment with laser ablation.ConclusionThe ease of application, avoidance of hospitalization, minimal postoperative care, and rapid return to daily activities make laser treatment a safe and effective therapeutic option for patients with recurrent pilonidal disease, supported by favorable outcomes and low morbidity.Article Citation - WoS: 13Citation - Scopus: 23Evaluation of Efficientnet Models for Covid-19 Detection Using Lung Parenchyma(Springer London Ltd, 2023) Kurt, Zuhal; Isik, Sahin; Kaya, Zeynep; Anagun, Yildiray; Koca, Nizameddin; Cicek, SuemeyyeWhen the COVID-19 pandemic broke out in the beginning of 2020, it became crucial to enhance early diagnosis with efficient means to reduce dangers and future spread of the viruses as soon as possible. Finding effective treatments and lowering mortality rates is now more important than ever. Scanning with a computer tomography (CT) scanner is a helpful method for detecting COVID-19 in this regard. The present paper, as such, is an attempt to contribute to this process by generating an open-source, CT-based image dataset. This dataset contains the CT scans of lung parenchyma regions of 180 COVID-19-positive and 86 COVID-19-negative patients taken at the Bursa Yuksek Ihtisas Training and Research Hospital. The experimental studies show that the modified EfficientNet-ap-nish method uses this dataset effectively for diagnostic purposes. Firstly, a smart segmentation mechanism based on the k-means algorithm is applied to this dataset as a preprocessing stage. Then, performance pretrained models are analyzed using different CNN architectures and with our Nish activation function. The statistical rates are obtained by the various EfficientNet models and the highest detection score is obtained with the EfficientNet-B4-ap-nish version, which provides a 97.93% accuracy rate and a 97.33% F1-score. The implications of the proposed method are immense both for present-day applications and future developments.
