Search

Auto-associative networks are a type of Artificial Neural Network (ANN) architectures that has been used in a variety of engineering areas for the past two decades. In auto-associative networks, the knowledge to be extracted from a database is the identity function. In other words, this particular network is trained to reproduce its inputs and output(s). Due to the fact that the network is optimized on inputs, as well as outputs, obtaining highly accurate results can be challenging. In this study, auto-associative network was explored using seven civil engineering databases from various applications and with a range of data types. The architecture of the auto-associative networks was developed with only three layers - input, hidden, and output layers - in order to maintain the generalization capabilities. Only the output was considered when assessing the statistical accuracy measures. A traditional ANN model was developed for each database to provide an initial estimate of the output. Then these estimates and the inputs were used to develop the auto-associative network. The auto-associative network improved the statistical accuracy measures for some databases relative to the traditional ANN approach. Overall, the auto-associative network yielded promising results and can be applicable to civil engineering databases.

There is no agreement on the involvement of angiotensin II type 1 receptor (AT1R) gene A(1166)C variant and essential hypertension. The purpose of this study was to investigate the association between angiotensin II type 1 receptor (AT1R) gene A(1166)C variants with essential hypertension and some related parameters in a sample of Jordanian hypertensive patients. DNA samples from 108 hypertensive individuals and 102 age- and gender-matched non-hypertensive controls of the Jordanian population were analyzed by polymerase chain reaction followed by restriction fragment length polymorphism assay (PCR-RFLP) methods to determine the frequency of A(1166)C variants alleles. No statistically significant differences were found in the distribution of alleles and genotypes between hypertensive and non-hypertensive individuals, not even after gender segregation. The frequency of the variant allele (C(1166)) was significantly higher in the early-onset compared to the late-onset group of hypertensive males, in subjects with positive family history of hypertension, and in subjects with high waist circumference. In conclusion, the A(1166)C polymorphism is not associated with essential hypertension in Jordanian hypertensive individuals. However, it was associated with an early onset of hypertension in males, with positive family history of hypertension, and with high waist circumference irrespective of blood pressure status.

Background: There are incon- sistent reports concerning N-acetyltransfer- ase 2 (NAT2) genotypes in diabetes mellitus (DM). Objective: The objective of the study was to explore any association between NAT2 genotypes and Type 1 and Type 2 DM in Jordanians. Methods: 106 Type 1 and 110 Type 2 DM patients attending the "National Center for Diabetes, Endocrinology and Ge- netics", Amman, Jordan, were included in the study. DNA was extracted from venous blood using a commercial DNA extraction kit. NAT2 genotyping was performed using polymerase chain reaction-restriction frag- ment length polymorphism (PCR-RFLP). Results: The frequency of the genotype that encodes rapid acetylation (the wild-type genotype NAT2*4/4) was similar in the two types of diabetes mellitus. Those which en- code intermediate acetylation (NAT2*4/5, NAT2*4/6, and NAT2*4/7) were higher in Type 2 diabetes (0.482) compared to Type 1 diabetes (0.339), while the frequency of genotypes which encode slow acetyla- tion (NAT2*5/5, NAT2*5/6, NAT2*5/7, NAT2*6/6, NAT2*6/7, and NAT2*7/7) were higher in Type 1 diabetes (0.547) compared to Type 2 diabetes (0.418). Conclusion: There is excess of genotypes encoding intermedi- ate acetylation in Type 2 DM and an excess of slow acetylator genotypes in Type 1 DM. Furthermore, NAT2*4/6 genotype (which encodes intermediate acetylation) was more prevalent in Type 2 DM. Type 1 DM behaved similar to non-diabetic controls in regard to acetylation status.

This study is intended to facilitate damage detection in concrete bridge girders without the need for visual inspection while minimizing field measurements. Beams with different material and cracking parameters were modeled using ABAQUS finite-element analysis software to obtain stiffness values at specified nodes. The resulting database was then used to train an artificial neural network (ANN) model to inversely predict the most probable cracking pattern. The aim is to use the ANN approach to solve an inverse problem where a unique analytical solution is not attainable. Accordingly, simple span beams with three, five, seven, and nine stiffness nodes and a single crack were modeled in this work. To confirm that the ANN approach can characterize the logic within the databases, networks with geometric, material, and cracking parameters as inputs and stiffness values as outputs were created. These networks provided excellent prediction accuracy measures (R2 values>99%). For the inverse problem, the n...

Background and Aims Thiopurine S-methyltransferase (TPMT) is responsible for inactivation of thiopurine drugs which are commonly used in leukemia, organ transplantation and autoimmune diseases. The gene encoding TPMT is polymorphic, and both phenotyping and genotyping studies have shown ethnic variations in gene sequence and enzyme activity worldwide. The aim of this study is to identify the most common genetic polymorphisms of TPMT in healthy Jordanian volunteers and patients with rheumatoid arthritis (RA). Methods A polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP) assay was used to identify the frequency of TPMT ( *2, *3A, *3B, and *3C ) polymorphisms in 250 healthy Jordanian volunteers and 110 RA patients. Results Only four healthy subjects (1.6%) and one RA patient (0.9%) with variant alleles were identified in this study. Two healthy subjects had the TPMT*3A allele and the other two had the TPMT*3B allele, whereas the one RA patient had the TPMT*3A allele. No homozygous polymorphisms were detected and all genotypes detected were heterozygous ( *1/*3A ) ( *1/*3B ). None of the subjects had TPMT*2 or TPMT*3C variant alleles. Conclusions Mutant alleles identified in this study have a low frequency. TPMT ( *3A and *3B ) were the only detected heterozygous alleles. No homozygous variant allele was detected. Further studies are necessary to identify other variant alleles that might uniquely occur in Jordanians.