Automatic hepatitis diagnosis system based on Linear Discriminant Analysis and Adaptive Network based on Fuzzy Inference System

In this paper, an automatic diagnosis system based on Linear Discriminant Analysis (LDA) and Adaptive Network based on Fuzzy Inference System (ANFIS) for hepatitis diseases is introduced. This automatic diagnosis system deals with the combination of feature extraction and classification. This automatic hepatitis diagnosis system has two stages, which feature extraction – reduction and classification stages. In the feature extraction – reduction stage, the hepatitis features were obtained from UCI Repository of Machine Learning Databases. Then, the number of these features was reduced to 8 from 19 by using Linear Discriminant Analysis (LDA). In the classification stage, these reduced features are given to inputs ANFIS classifier. The correct diagnosis performance of the LDA-ANFIS automatic diagnosis system for hepatitis disease is estimated by using classification accuracy, sensitivity and specificity analysis, respectively. The classification accuracy of this LDA-ANFIS automatic diagnosis system for the diagnosis of hepatitis disease was obtained in about 94.16%.     

Symbolic Regression Based Extreme Learning Machine Models for System Identification

Neural Processing Letters - Reproducible machine learning models with less number of parameters and fast optimization are preferred in embedded system design for the applications of artificial...     

Hydrogen permeability and structure of vanadium alloy membranes

Experimental data on hydrogen permeability through membrane alloys V₈₅Ni₁₅, V₉₀Ti₁₀, and V₉₀Co₁₀ (at %) are presented. Hydrogen permeability tests have been carried out in the temperature range of 623–873 K at pressures of ~4.5, 14, and 30 kPa. Results of X-ray diffraction analysis of samples are presented. Microstructure of the membrane alloys has been investigated before and after hydrogen permeability tests.     

Drying Behavior of Meat Samples at Various Fiber Directions and Air Conditions

The aim of this study was to investigate the effects of meat fiber directions and air conditions on moisture and temperature developments, shrinkage, and effective diffusivity constants compared to homogenous minced meat samples. The lean meat with three fiber directions and minced meat samples were dried at temperatures of 48 and 70°C and air flow rates of 0.5, 1.0, and 1.7 m/s. The minced meat samples showed 1.0 ± 0.19 to 4.4 ± 0.03°C higher temperature values and 2.3 ± 0.004 to 6.2 ± 0.003% lower moisture losses than the lean meat samples in all fiber directions. The lowest temperatures were observed in lean meat with h ₁ (normal flow, normal drying) fiber direction. The highest moisture loss and diffusion coefficient were observed in lean meat with h ₂ (parallel flow, normal drying) and v (normal flow, parallel drying) fiber directions, which also possessed the shortest drying times (10.4 and 13.4 h, respectively). The estimated diffusion coefficient values ranged between 1.11 × 10^?9 and 5.54 × 10^?9. The results indicated that lean and minced meat samples differed in their drying behaviors in a tray dryer under the tested conditions with >90% reproducibility (or ≤10% coefficient of variation).     

Characterization of bio-oil obtained from fruit pulp pyrolysis

Apricot pulps was pyrolyzed in a fixed-bed reactor under different pyrolysis conditions to determine the role of final temperature, sweeping gas flow rate and steam velocity on the product yields and liquid product composition with a heating rate of 5 °C/min. Final temperature range studied was between 300 and 700 °C and the highest liquid product yield was obtained at 550 °C. Liquid product yield increased significantly under nitrogen and steam atmospheres. For the optimum conditions, pyrolysis of peach pulp was furthermore studied. Liquid products obtained under the most suitable conditions were characterized by FTIR and ¹H-NMR. In addition, gas chromatography/mass spectrophotometer was achieved on all pyrolysis oils. Characterization showed that bio-oil could be a potential source for synthetic fuels and chemical feedstock.     

Upgrading of fast pyrolysis bio-oil over Fe modified ZSM-5 catalyst to enhance the formation of phenolic compounds

The present study is aimed to investigate the upgrading of beech sawdust pyrolysis bio-oil through catalytic cracking of its vapors over Fe-modified ZSM-5 zeolite in a fixed bed tubular reactor. The zeolite supported iron catalyst was successfully prepared with varying metal loading ratios (1, 5, 10 wt%) via dry impregnation method and further characterized by BET, XRD, and SEM-EDX techniques. TG/FT-IR/MS analysis was used for the detection of biomass thermal degradation. Product yields of non-catalytic and catalytic pyrolysis experiments were determined and the obtained results show that bio-oil yields decreased in the presence of catalysts. Besides, the bio-oil composition is characterized by GC/MS. It was indicated that the entity of the ZSM-5 and Fe/ZSM-5 catalyst reveal a significant enhancement quality of the pyrolysis products in comparison with non-catalytic experiment. The catalyst increased oxygen removal from the organic phase of bio-oil and further developed the production of desirable products such as phenolics and aromatic compounds.