Evaluating of traumatic brain injuries using artificial neural networks

The purpose of this study is to develop a diagnostic system to detect the severity of traumatic brain injuries using artificial neural networks. Three layered back propagation neural network with an input layer of 10 nodes whose output providing the inputs to a hidden layer was used. Thirty-two patients with traumatic brain injuries in different age and gender were taken in the study. Electroencephalography, Trauma and Glasgow coma scores were used for evaluating the data. The results obtained from the system were compared with the findings of neurologists. We found a significant relationship between the findings of neurologists and systems output for normal, mild, moderate and severe electroencephalography tracing data. Getting this system in routine use will lead to make a rapid decision for the degree of trauma with electroencephalography and revised trauma score.     

Automatic segmentation of corpus collasum using Gaussian mixture modeling and Fuzzy C means methods

This paper presents a comparative study of the success and performance of the Gaussian mixture modeling and Fuzzy C means methods to determine the volume and cross-sectionals areas of the corpus callosum (CC) using simulated and real MR brain images. The Gaussian mixture model (GMM) utilizes weighted sum of Gaussian distributions by applying statistical decision procedures to define image classes. In the Fuzzy C means (FCM), the image classes are represented by certain membership function according to fuzziness information expressing the distance from the cluster centers. In this study, automatic segmentation for midsagittal section of the CC was achieved from simulated and real brain images. The volume of CC was obtained using sagittal sections areas. To compare the success of the methods, segmentation accuracy, Jaccard similarity and time consuming for segmentation were calculated. The results show that the GMM method resulted by a small margin in more accurate segmentation (midsagittal section segmentation accuracy 98.3% and 97.01% for GMM and FCM); however the FCM method resulted in faster segmentation than GMM. With this study, an accurate and automatic segmentation system that allows opportunity for quantitative comparison to doctors in the planning of treatment and the diagnosis of diseases affecting the size of the CC was developed. This study can be adapted to perform segmentation on other regions of the brain, thus, it can be operated as practical use in the clinic.     

The selection of technology forecasting method using a multi-criteria interval-valued intuitionistic fuzzy group decision making approach

Technological forecasting is a tool for organizations to develop their technology strategies. The quality of forecasting is extremely important for the accuracy of the results and in turn company future. Therefore a proper selection methodology of forecasting technique that considers the characteristics of technology and resources needed such as cost, time is essential. On the other hand, although many forecasting techniques are available, there is a high uncertainty in choosing the most appropriate technique among a set of available techniques. In this paper interval valued intuitionistic fuzzy technique for order preference by similarity to ideal solution (TOPSIS) method is proposed for the solution of technological forecasting technique selection problem. The proposed method includes seven selection criteria and twelve forecasting technique alternatives. The methodology is applied for 3D TV technology. The results revealed that Fisher Pry method is found as the most appropriate method for forecasting since it has the highest closeness coefficient.     

Development of a decision support system for robot selection

With the availability of more different robot types and models along with their separate specifications, selecting the most appropriate robot is becoming more difficult and complicated for companies. Furthermore, a common set of robot selection criteria is not available for the decision makers. In this study, a two-phase robot selection decision support system, namely ROBSEL, is developed to help the decision makers in their robot selection decisions. In development of ROBSEL, an independent set of criteria is obtained first and arranged in the Fuzzy Analytical Hierarchy Process (FAHP) decision hierarchy. In the first elimination phase of the decision support system, the user obtains the feasible set of robots by providing limited values for the 15 requirements. ROBSEL, then, uses FAHP decision hierarchy to rank the feasible robots in the second phase. ROBSEL is illustrated and tested and several critical issues in its practical usage are explored in the paper. The applications of ROBSEL show that ROBSEL is a useful, practical and easy to use robot selection tool and improves robot selection decisions in the companies.     

The effects of temperature,radiation, and illumination on current–voltage characteristics of Au/PVA(Co,Zn-doped)/n-Si Schottky diodes

Polyvinyl alcohol (PVA)/(Co-Ni) nanofiber film was fabricated on silicon wafer using electrospinning technique. The topography of the produced PVA/(Co-Ni) nanofiber film was examined by scanning electron microscopy (SEM). The Au/Poly (vinyl alcohol) (Co, Ni-doped)/n-Si Schottky diode (SD) was thermally formed in evaporating system after the spinning process. At first, the current–voltage (I–V) characteristics of Au/PVA (Co, Zn-doped)/n-Si SD was measured at the room temperature (300 K). For the investigating the effect of temperature, illumination and radiation on Au/PVA (Co, Zn-doped)/n-Si SD comparatively, the measurement was performed under the illumination intensity of 200 W, at 380K, and finally the radiation dose of 22 kGy respectively. The diode characteristics such as the zero-bias barrier height (ϕ_Bo), ideality factor (n) and series resistance (R_s) were calculated at room temperature and under the condition of high temperature, illumination, and radiation. It was found that these characteristics were affected by the illumination and radiation as well as the temperature. The density of interface states (N_ss) distribution profiles as a function of (E_c - E_ss) extracted from the forward I–V measurements were also affected by illumination and radiation even if just a bit. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

Mechanical and microstructural properties of low-carbon steel-plate-reinforced gray cast iron

In the present experimental study, strengthening of gray cast iron by reinforcing with steel plates was investigated in the as-cast and normalized conditions. Normalizing heat treatments were applied to the specimens at temperatures of 800 °C and 850 °C. Three-point bend specimens were manufactured from gray cast iron and also from gray cast iron with reinforced steel plates. Flexural strengths of the steel-plate-reinforced cast iron were calculated for four distinct volume fractions (V_r = 0.04, 0.08, 0.12, and 0.16). The current study shows that the steel-plate-reinforced gray cast iron has higher flexural strength and flexural modulus than the cast iron without reinforcement. The flexural strength considerably increases with slight increase in normalization temperature. Optical and scanning electron microscopy analyses were used to examine flake morphology and microstructures of gray cast iron and steel-plate-reinforced gray cast iron. It is noted that carbon diffuses from the gray cast iron to the steel plates. A transition region containing partially dissolved graphite and having high hardness was observed due to the carbon diffusion.     

Fixed-Bed Pyrolysis of Hazelnut (Corylus Avellana L.) Bagasse: Influence of Pyrolysis Parameters on Product Yields

Fixed-bed slow pyrolysis experiments have been conducted on a sample of hazelnut bagasse to determine particularly the effects of pyrolysis temperature, heating rate, particle size and sweep gas flow rate on the pyrolysis product yields. The temperature of pyrolysis, heating rate, particle size and sweep gas flow rate were varied in the ranges 350–550° C, 10 and 50° C/min, 0.224–1.800 mm and 50–200 cm³/min, respectively. Under the various pyrolysis conditions applied in the experimental studies, the obtained char, liquid, and gas yield values ranged between 26 and 35 wt%, 23 and 34.40 wt%, and 25 and 32 wt%, respectively. The maximum biooil yield of 34.40% was obtained at the final pyrolysis temperature of 500°C, with a heating rate of 10° C/min, particle size range of 0.425–0.600 mm and a sweep gas flow rate of 150 cm³/min.     

Seismic microzonation of the historic peninsula of İstanbul

In this study, the geological and geotechnical conditions of old Istanbul (Fatih and Eminönü provinces) were investigated in detail and a seismic microzonation study was undertaken for this historical peninsula, which is the site of many ancient structures. Dynamic site response, liquefaction potential and slope stability analyses were carried out, based on field and laboratory tests and earthquake time histories computed with respect to probabilities of exceedance of 10 and 40% in 50 years. The output data obtained from the analyses were evaluated by GIS techniques, and ground shaking, liquefaction susceptibility and landslide hazard maps were prepared.     

A novel method for color determination of edible oils in L*a*b* format

A simple method that uses visible spectrophotometer data and an artificial neural network (ANN) was developed to determine edible oil color based on the L*a*b* format. The 100 oil samples consisted of nine pure oils, a sesame oil blend and three heated oils. Binary, ternary and quaternary mixtures of these 13 oils in different ratios were prepared, and absorbance values of the samples were measured in the visible region (380–700 nm). The absorbance values at wavelengths of 416, 456, 483, 537, 611 and 672 nm were used to train, validate and test the network. Strong correlations between the instrumental L*a*b*ΔE and the estimated L*a*b*ΔE were found for the test samples, with correlation coefficients (R²) of 0.989, 0.984, 0.996 and 0.992 for L*, a*, b*, and ΔE, respectively. The effects of number and combination of the wavelengths used for training of the ANN on the estimation capability of the network for the test samples were also investigated. Although a good agreement, average R² of 0.991– 0 993 for L*a*b*, was obtained for combinations composed of three to six wavelengths with 483 and 537 nm in common, the best R² value was obtained when all six wavelengths were used to train the ANN. The developed method is objective, cost effective and simple, and allows the color measurement with a basic visible spectrophotometer and disposable cuvettes.     

The influence of different circular hole perforations on interlaminar shear strength of a novel fiber metal laminates

This study characterizes surface treated classic type fiber metal laminates (FMLs) interlaminar shear strength (ILSS) based on a glass mat reinforced polyphenylene sulphide composite and an aluminum alloy. The effect of concentration of γ‐glycidoxypropyltrimethoxysilane surface treatment on ILSS of adhesive bonding between aluminum sheet and composite laminates has been investigated. After determining the silane concentration, novel FML material is manufactured using a compression moulding process which involves aluminum sheets with different circular hole perforations (Array type A and B) with two circular hole diameters (ϕ3 and ϕ5 mm) and two total hole area/closed area: 0.05 and 0.06) to develop mechanical interlocking between aluminum layers and composite laminates. Tensile tests are performed to investigate the effect of different circular hole perforations on ILSS properties of FMLs. Test results show that ILSS is improved with increasing the circular hole diameter and decreased with the number of holes as correlated with undrilled FMLs. Failure modes, damage initiation, and progression of FMLs with different open hole perforations are determined with optical microscope. POLYM. COMPOS., 37:963–973, 2016. © 2014 Society of Plastics Engineers