Pull-through failures of crest-fixed steel claddings initiated by transverse splitting

Crest-fixed steel claddings made of thin, high strength steel often suffer from local pull-through failures at their screw connections during high wind events such as storms and hurricanes. Currently there aren't any adequate design provisions for these cladding systems except for the expensive testing provisions. Since the local pull-through failures in the less ductile steel claddings are initiated by transverse splitting at the fastener hole, analytical studies have not been able to determine the pull-through failure loads. Analytical studies could be used if a reliable splitting criterion is available. Therefore a series of two-span cladding tests was conducted on a range of crest-fixed steel cladding systems under simulated wind uplift loads. The strains in the sheeting around the critical fastener holes were measured until the pull-through failure. This paper presents the details of the experimental investigation and the results including a strain criterion for the local pull-through failure.

Application of higher-order spectra for automated grading of diabetic maculopathy

Diabetic macular edema (DME) is one of the most common causes of visual loss among diabetes mellitus patients. Early detection and successive treatment may improve the visual acuity. DME is mainly graded into non-clinically significant macular edema (NCSME) and clinically significant macular edema according to the location of hard exudates in the macula region. DME can be identified by manual examination of fundus images. It is laborious and resource intensive. Hence, in this work, automated grading of DME is proposed using higher-order spectra (HOS) of Radon transform projections of the fundus images. We have used third-order cumulants and bispectrum magnitude, in this work, as features, and compared their performance. They can capture subtle changes in the fundus image. Spectral regression discriminant analysis (SRDA) reduces feature dimension, and minimum redundancy maximum relevance method is used to rank the significant SRDA components. Ranked features are fed to various supervised classifiers, viz. Naive Bayes, AdaBoost and support vector machine, to discriminate No DME, NCSME and clinically significant macular edema classes. The performance of our system is evaluated using the publicly available MESSIDOR dataset (300 images) and also verified with a local dataset (300 images). Our results show that HOS cumulants and bispectrum magnitude obtained an average accuracy of 95.56 and 94.39 % for MESSIDOR dataset and 95.93 and 93.33 % for local dataset, respectively.