Cracks are indicators that affect the stability and integrity of infrastructures. Fast, reliable, and cost-effective crack detection methods are required to overcome the shortcomings of traditional approaches. This paper works on a transfer learning approach based on the deep convolutional neural network model VGG19 to detect cracks. Further, the proposed method is based on an improved VGG-19 model. The experiment is carried out on the SDNET2018 annotated images dataset. The dataset comprises of total 15k images, training set consists of 5000 cracked and 5000 un-cracked images of walls, pavements, and bridges. The experimental results on the proposed model provide 91.8% accuracy in detecting cracks on the testing set. The paper concluded that fine-tuning of the VGG19 (Visual Geometry Group) model accomplish satisfactory results in detecting cracks on images of multiple infrastructures.

Introduction:Patients with Sickle Cell Disease (SCD) have numerous risk factors including but not limited to iron overload, avascular bone necrosis, infection especially acute chest syndrome and frequent pain crisis. Incidence of Clostridium Difficile infection (C. Diff) in sickle cell disease patients is lower than the general population but they are frequently hospitalized for vaso-occlusive crisis and are often given empirical antibiotic treatment which puts them at high risk for C. Diff (1). Here we are describing trends and predictors of C. Diff among SCD patients and how C.diff burgen has changed over the time in Sickle cell patients. Methods:We used National Inpatient Sample (NIS) for the years 2008-2017 by Healthcare Cost and Utilization Project. We extracted a study cohort of all-cause hospitalizations among SCD patients using International Classification of Diseases (9th/10th Editions) Clinical Modification diagnosis codes (ICD-9-CM/ICD-10-CM). Concurrent C. Diff and other comorbidities were identified by ICD-9/10-CM codes and Elixhauser comorbidity software. Our primary objective was to delineate temporal trends, and predictors of C. Diff infection in SCD patients. We utilized Cochran Armitage trend test and multivariable survey logistic regression models to analyze the trends, predictors and outcomes. Results:Out of a total 991,848 all-cause hospitalizations among SCD patients, 5,182 (1.81%) hospitalizations were complicated with C. Diff infection. Prevalence of C.Diff infection increased from 3/1000 hospitalizations in 2008 to 6/1000 hospitalizations in 2017 (pTrend<0.0001) with a 6% yearly increase (OR:1.06; 95%CI:1.04-1.09; p<0.001) (Figure.1). Patients who developed C.Diff infection had higher mean age (39 vs 33-years; p<0.001), and more likely to be females (62% vs 38%; p<0.001). Furthermore, in multivariable regression analysis, increasing age (OR:1.1; 95%CI:1.1-1.1; p<0.0001), females (OR:1.2; 95%CI:1.1-1.4; p<0.001), neurological disorders (OR:1.6; 95%CI:1.2-1.9; p<0.001), weight loss (OR:2.5; 95%CI:2.0-3.2; p<0.001), depression (OR:1.5; 95%CI:1.2-1.9; p<0.001), and renal failure (OR:1.3; 95%CI:1.2-1.6; p<0.001) were associated with higher odds of C. Diff infection. Also other concurrent conditions like liver disorders (OR:1.5; 95%CI:1.2-2.0; p<0.001), congestive heart failure (OR:1.3; 95%CI:1.1-1.6; p<0.001), and septicemia (OR:3.6; 95%CI:3.1-4.3; p<0.001) were also associated with increased odds of developing C.Diff infection. Among the patients who developed C.Diff infection, 15% were discharged to long term facilities and 4% died during the hospitalization. Moreover C.Diff infection was also associated with higher length of stay (11 vs 6-days; p<0.001). Discussion:In this nationally representative study, we observed that prevalence of C.Diff among SCD has been increasing over the last decade. We were also able to delineate several factors such as renal failure, liver disorder, CHF and septicemia which were significantly associated with development of C.Diff infection. Modifiable factors require better optimization which may eventually decrease the C.diff infection prevalence but this conclusion needs more in-depth studies to establish the causal relationship. References: (1) Ahmed J, Kumar A, Jafri F, Batool S, Knoll B, Lim SH. Low Incidence of Hospital-OnsetClostridium difficileInfection in Sickle Cell Disease.N Engl J Med. 2019;380(9):887-888. doi:10.1056/NEJMc1815711 Disclosures No relevant conflicts of interest to declare.

Bays International was incorporated in 1996. Over the years it faced numerous challenges including: high employee turnover (particulary saleforce), limited expansion capabilities, low penetration in semi-urban markets, high operating expenses like rentals, increasing duties (on luxury products), low cash-flows, low budgets for advertising and marketing as compared to competitors, less awareness amongst consumers, volatile consumer preferences (especially by millennial), weak brands’ loyalties, counterfeits/fake products, smuggling and infiltration from grey channels, high number of foreign and local chains entering the market, price war especially with local chains, and uncertain political situation. Four interviews were conducted from management and two interviews from ex employees. Moreover, a lot of open access documents of the company were reviewed. Pertinent literature reveiew also revealed interesting insights about emerging consumer trends and cosmetic industry along with interviews of some marketing directors of leading global brands. The Bays leadership believes that key parameters are improving over time. The case covers how the company maneuvered itself since its inception and launched numerous other brands targeted towards different segments of the society, in order to steer towards growth in changing internal and external environment. The case is based on a scenario when there is yet another increase of taxes by the government in 2019 and presents troublesome situations to branding cum marketing strategy for the company to consider.

No abstract