Transfer learned deep feature based crack detection using support vector machine: a comparative study.

Technology offers a lot of potential that is being used to improve the integrity and efficiency of infrastructures. Crack is one of the major concerns that can affect the integrity or usability of any structure. Oftentimes, the use of manual inspection methods leads to delays which can worsen the situation. Automated crack detection has become very necessary for efficient management and inspection of critical infrastructures. Previous research in crack detection employed classification and localization-based models using Deep Convolutional Neural Networks (DCNNs). This study suggests and compares the effectiveness of transfer learned DCNNs for crack detection as a classification model and as a feature extractor to overcome this restriction. The main objective of this paper is to present various methods of crack detection on surfaces and compare their performance over 3 different datasets. Experiments conducted in this work are threefold: initially, the effectiveness of 12 transfer learned DCNN models for crack detection is analyzed on three publicly available datasets: SDNET, CCIC and BSD. With an accuracy of 53.40%, ResNet101 outperformed other models on the SDNET dataset. EfficientNetB0 was the most accurate (98.8%) model on the BSD dataset, and ResNet50 performed better with an accuracy of 99.8% on the CCIC dataset. Secondly, two image enhancement methods are employed to enhance the images and are transferred learned on the 12 DCNNs in pursuance of improving the performance of the SDNET dataset. The results from the experiments show that the enhanced images improved the accuracy of transfer-learned crack detection models significantly. Furthermore, deep features extracted from the last fully connected layer of the DCNNs are used to train the Support Vector Machine (SVM). The integration of deep features with SVM enhanced the detection accuracy across all the DCNN-dataset combinations, according to analysis in terms of accuracy, precision, recall, and F1-score.

Role of glutathione S-transferase Mu-1 (GSTM1) polymorphism in oligospermic infertile males.

The aim of this study was to examine whether an association exists between glutathione S-transferase Mu-1 (GSTM1) gene polymorphism and idiopathic male infertility. Forty-two men with infertility and 43 fertile men were recruited for this study. GSTM1 gene was analysed using PCR technique. The frequency of GSTM1 null (-) genotype was observed to be 45.2% in infertile men as against 20.09% in fertile men. Subjects with the GSTM1 null genotype had lower sperm concentrations and motility when compared with the subjects with GSTM1-positive genotype in both the groups. This study shows that the frequency of GSTM1 null (-) genotype is significantly high in infertile males when compared with the frequency in fertile males (OR = 0.32, P = 0.017, 95% CI = 0.124-0.831).

Modeling and optimization of a pharmaceutical formulation system using radial basis function network.

A Pharmaceutical formulation is composed of several formulation factors and process variables. Quantitative model based pharmaceutical formulation involves establishing mathematical relations between the formulation variables and the resulting responses, and optimizing the formulation conditions. In a formulation system involving several objectives, the desirable formulation conditions for one property may not always be desirable for other characteristics, thus leading to the problem of conflicting objectives. Therefore, efficient modeling and optimization techniques are needed to devise an optimal formulation system. In this work, a novel method based on radial basis function network (RBFN) is proposed for modeling and optimization of pharmaceutical formulations involving several objectives. This method has the advantage that it automatically configures the RBFN using a hierarchically self organizing learning algorithm while establishing the network parameters. This method is evaluated by using a trapidil formulation system as a test bed and compared with that of a response surface method (RSM) based on multiple regression. The simulation results demonstrate the better performance of the proposed RBFN method for modeling and optimization of pharmaceutical formulations over the regression based RSM technique.

Cytogenetic evaluation of traffic policemen occupationally exposed to vehicular exhaust.

BACKGROUND & OBJECTIVE: Automobile exhaust consists of many toxic components and is considered to be a major health concern in urban areas. Traffic policemen are occupationally exposed to vehicular exhaust during the traffic control. Hence, the present study was aimed to evaluate genotoxic effects of vehicular exhaust in traffic policemen in Hyderabad, south India. METHODS: Analysis of chromosomal aberrations was carried out in 136 traffic policemen, including 78 non smokers and 58 smokers who were exposed to vehicular exhaust for a period of 1-28 yr. For comparison, 115 healthy males including 69 non smokers and 46 smokers of the same age group and socio-economic status (who were not exposed to any chemical or radiation at their workplace) were studied. RESULTS: A significant increase (P<0.05) was observed in the mean frequency of chromosomal aberrations in non smoker and smoker traffic policemen (6.48 and 8.96 respectively) when compared to their respective control groups (3.35 and 4.30). According to the age a significant increase in the frequency of chromosomal aberrations was observed both in control and exposed groups (P<0.05). As the duration of exposure increased in traffic policemen, there was a corresponding increase in the frequency of chromosomal aberrations. INTERPRETATION & CONCLUSION: Cytogenetic damage was more pronounced in smokers when compared to non smokers. Age and duration of exposure also appear to play a vital role in causing cytogenetic damage. Thus the present study suggests that the induction of cytogenetic damage might be due to the cumulative effect of smoking, age and duration of exposure to vehicular exhaust.

Isolation and analysis of partial cDNA sequence coding for superoxide dismutase in Wuchereria bancrofti.

Molecular characterization of Wuchereria bancrofti is essential to develop suitable anti-filarial drugs and vaccines. We describe here isolation, sequence analysis and cloning of a partial cDNA of an enzyme superoxide dismutase from this parasite. The immunoscreening of a lambda zap W. bancrofti microfilarial (Mf) cDNA library with microfilaremic sera had resulted in the isolation of several seroreactive clones including, WbSOD. This clone contained a 309 bp insert and showed significant nucleotide and deduced amino acid sequence homologies to the superoxide dismutases of other nematode parasites. The antioxidant property of this enzyme may have important contribution in the defense mechanism of the parasite against host immune response.