Yazar "Sozen, Eser" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • [ X ]
    Öğe
    Data Mining and Pixel Distribution Approach for Wood Density Prediction
    (2019) Bardak, Timuçin; Bardak, Selehattin; Sozen, Eser
    The wood material has strategic importance in economic development. Innovations are the basic premise of commercial success in the wood industry, as in all industries. The density of wood provides valuable information about the physical and mechanical properties of the wood, and it is also directly related to the productivity in the forest industry. Many non-destructive test studies have been conducted to evaluate the physical properties of wood structures. This study was conducted to predict the density of wood in the species of oak (Quercus robur) and beech (Fagus orientalis L.) using the number of pixels in a grayscale image and data mining. To this purpose, pixel density of data was processed with the data collected from the images of wood specimens. This data was used as descriptor variables in artificial neural networks and random forest algorithm. The designed artificial neural network model and random forest algorithm allowed the prediction of density with an accuracy of 95.19% and 96.36%, respectively for the testing phase. As a result, this study showed that pixel density and data mining have the potential to be used as an instrument for predicting the density of wood.
  • [ X ]
    Öğe
    Determination of strain distributions of solid wood and plywood in bending test by digital image correlation
    (Kastamonu Univ, 2017) Bardak, Timucin; Bardak, Selahattin; Sozen, Eser
    Aim of study: In this study, it is aimed to compare displacement and strain fields of the plywood obtained from fagus coverings, oak (Quecus robur) and beech (Fagus orientalis L.) by digital image correlation method. Material and Methods: As wood material, beech (Fagus orientalis L.), oak (Quecus robur) and plywood obtained from fagus veneers were used. Then the densities and modulus of ruptures of the test specimens were calculated. Digital Image Correlation Analysis (DIC) was developed to resolve the displacement on the surface of a specimen. Deformation of the material can be achieved by tracking the displacement of markers on the sample surface. Main results: The results of the studies were found to be the highest static bending strenght in beech material and the lowest in plywood. The DIC technique is effective in detecting the displacement and strain, which helps to understand the bending behavior of solid wood and plywood Research highlights: The results from this research indicate that the DIC technique is capable of measuring full-field deformations in different wood complex structures. Due to limited DIC study in the field of wood engineering, there is a need for more extensive work in the future.
  • [ X ]
    Öğe
    FP-Growth Algoritması Kullanılarak Tüketiciler ve Mobilya Kullanım Süresi Arasındaki İlişkilerin Belirlenmesi
    (2022) Sozen, Eser; Bardak, Timuçin; Bardak, Selahattin
    Mobilyalar günlük hayat içinde çeşitli amaçlar için, farklı sürelerde tüm kültürlerde insanlar tarafından yaygın olarak kullanılmaktadır. Mobilya ve insan etkileşimi birçok açıdan incelenmesi gereken önemli bir konudur. Hem tüketicilerin sağlığının korunması hem de satın alma davranışlarını tam olarak anlamak için mobilyaların kullanım süresi bilgisine ihtiyaç bulunmaktadır. Bu çalışmada anket yöntemi ile tüketicilerin demografik bilgileri ve farklı mobilyalar için kullanım süreleri belirlenmiştir. Elde edilen verilerden Frequent Pattern (FP)-Growth algoritması ile farklı mobilyaların kullanım süresi ve tüketicilerin arasındaki ilişkiler belirlenmiştir. Çalışma sonucunda en güçlü birliktelik, yemek yeme mobilyalarında en kısa süre geçirenlerin kilosunun yüksek ve erkek olması arasında olduğu tespit edilmiştir. Çalışma mobilyalarında günlük 4 saat vakit geçirenlerin lisans mezunu erkek olması diğer bir birliktelik kuralıdır. Yine 18-25 yaş aralığındaki bireylerin yemek yeme mobilyalarında geçirdiği süreye ait birliktelik kuralına göre %69 doğruluk oranı ile 30 dakika olarak belirlenmiştir. Veri madenciliğine dayalı önerilen yöntem tüketiciler ve farklı mobilyalar için kullanım süresi arasındaki ilişkilerin etkili ve başarılı bir şekilde tespit edilebileceğini göstermektedir. Veri bilimi tüketici davranışlarını anlamak için karar vericilere yeni bakış açıları sunabilir. Bununla birlikte mobilya endüstrisinde kaliteyi artırmak için veri analizine dayalı yeni çalışmalara ihtiyaç duyulmaktadır.
  • [ X ]
    Öğe
    Predicting Effects of Selected Impregnation Processes on the Observed Bending Strength of Wood, with Use of Data Mining Models
    (North Carolina State Univ Dept Wood & Paper Sci, 2021) Bardak, Selahattin; Bardak, Timucin; Peker, Huseyin; Sozen, Eser; Cabuk, Yildiz
    Wood materials have been used in many products such as furniture, stairs, windows, and doors for centuries. There are differences in methods used to adapt wood to ambient conditions. Impregnation is a widely used method of wood preservation. In terms of efficiency, it is critical to optimize the parameters for impregnation. Data mining techniques reduce most of the cost and operational challenges with accurate prediction in the wood industry. In this study, three data-mining algorithms were applied to predict bending strength in impregnated wood materials (Pinus sylvestris L. and Millettia laurentii). Models were created from real experimental data to examine the relationship between bending strength, diffusion time, vacuum duration, and wood type, based on decision trees (DT), random forest (RF), and Gaussian process (GP) algorithms. The highest bending strength was achieved with wenge (Millettia laurentii) wood in 10 bar vacuum and the diffusion condition during 25 min. The results showed that all algorithms are suitable for predicting bending strength. The goodness of fit for the testing phase was determined as 0.994, 0.986, and 0.989 in the DT, RF, and GP algorithms, respectively. Moreover, the importance of attributes was determined in the algorithms.
  • [ X ]
    Öğe
    The effects of the moisture content of laminated veneer lumber on bending strength and deformation determination via two-dimensional digital image correlation
    (Sage Publications Ltd, 2021) Sozen, Eser; Kayahan, Kadir; Bardak, Timucin; Bardak, Selahattin
    This study determined the bending strength values of laminated veneer lumber (LVL) made with beech (Fagus orientalis L.) veneer obtained by the peeling process and having four different moisture content values (0%/oven dry, 12%, 18%, and 25%). Bending tests were carried out in two different ways, i.e., for the flatwise and edgewise aspects of the LVL. Strain maps were created using two-dimensional digital image correlation (2 D DIC) and the samples having different moisture contents were compared. At the same time, the amount of displacement of the samples during the bending test was determined via conventional and DIC methods. Results of the study determined that the moisture content was effective in bending strength and tension zones. It was observed that increasing moisture content created homogeneous distribution of deformation. It was also observed that the data obtained by the 2 D DIC method were compatible with those obtained by the conventional method.
  • [ X ]
    Öğe
    The Impact of Nanoparticles and Moisture Content on Bonding Strength of Urea Formaldehyde Resin Adhesive
    (Zagreb Univ, Fac Forestry, 2018) Bardak, Timucin; Sozen, Eser; Kayahan, Kadir; Bardak, Selahattin
    Wood and wood products have been used in different environmental conditions. Moisture content (MC) and relative humidity (RH) are key parameters for these conditions and bonding strength. Nanotechnology has paved the way to more durable adhesives. An experimental study was conducted to examine the effects of various nanoparticles and moisture content on bonding strength of urea formaldehyde (UF) resin adhesive. In this study, nanosilicon dioxide (SiO2) and titanium dioxide (TiO2) were blended with UF. Nanoparticle reinforced adhesives were processed at different nano fillers concentrations (0.5 % and 1 %) and each adhesive was tested at the moisture content of 0 %, 12 %, 18 % and 25 %. According to the results of bonding strength tests, contained nano-SiO2 adhesives showed better bonding strengths as compared to the control (pure UF) and contained nano-TiO2 adhesives. The highest bonding strength has been determined at 12% wood moisture in all specimens. Increasing the moisture content has decreased bonding strength of all samples including control samples. This study showed that nano (SiO2 and TiO2) particles have improved the bonding strength of pure UF. Besides, the addition of nano-SiO2 and nano-TiO2 changed the physicochemical properties of UF adhesive by XRD test. The novelty of this study was to demonstrate that nanoparticles (SiO2 and TiO2) could be beneficial for the bonding strength of UF adhesive in harsh environmental conditions.