No abstract

Swine coronaviruses (SCoVs) are one of the most devastating pathogens affecting the livelihoods of farmers and swine industry across the world. These include transmissible gastroenteritis virus (TGEV), porcine epidemic diarrhea virus (PEDV), porcine respiratory coronavirus (PRCV), porcine hemagglutinating encephalomyelitis virus (PHEV), swine acute diarrhea syndrome coronavirus (SADS-CoV), and porcine delta coronavirus (PDCoV). Coronaviruses infect a wide variety of animal species and humans because these are having single stranded-RNA that accounts for high mutation rates and thus could break the species barrier. The gastrointestinal, cardiovascular, and nervous systems are the primary organ systems affected by SCoVs. Infection is very common in piglets compared to adult swine causing high mortality in the former. Bat is implicated to be the origin of all CoVs affecting animals and humans. Since pig is the only domestic animal in which CoVs cause a wide range of diseases; new coronaviruses with high zoonotic potential could likely emerge in the future as observed in the past. The recently emerged severe acute respiratory syndrome coronavirus virus-2 (SARS-CoV-2), causing COVID-19 pandemic in humans, has been implicated to have animal origin, also reported from few animal species, though its zoonotic concerns are still under investigation. This review discusses SCoVs and their epidemiology, virology, evolution, pathology, wildlife reservoirs, interspecies transmission, spill-over events and highlighting their emerging threats to swine population. The role of pigs amid ongoing SARS-CoV-2 pandemic will also be discussed. A thorough investigation should be conducted to rule out zoonotic potential of SCoVs and to design appropriate strategies for their prevention and control.

We propose a framework for compressing state-of-the-art Single Shot MultiBox Detector (SSD). The framework addresses compression in the following stages: Sparsity Induction, Filter Selection, and Filter Pruning. In the Sparsity Induction stage, the object detector model is sparsified via an improved global threshold. In Filter Selection & Pruning stage, we select and remove filters using sparsity statistics of filter weights in two consecutive convolutional layers. This results in the model with the size smaller than most existing compact architectures. We evaluate the performance of our framework with multiple datasets and compare over multiple methods. Experimental results show that our method achieves state-of-the-art compression of 6.7X and 4.9X on PASCAL VOC dataset on models SSD300 and SSD512 respectively. We further show that the method produces maximum compression of 26X with SSD512 on German Traffic Sign Detection Benchmark (GTSDB). Additionally, we also empirically show our method's adaptability for classification based architecture VGG16 on datasets CIFAR and German Traffic Sign Recognition Benchmark (GTSRB) achieving a compression rate of 125X and 200X with the reduction in flops by 90.50% and 96.6% respectively with no loss of accuracy. In addition to this, our method does not require any special libraries or hardware support for the resulting compressed models.

No abstract

No abstract

No abstract

No abstract

The recent research is developing in a vast speed to develop the cloud orchestration system. In cloud system the remotely managed servers are storing, finding, removing, replacing and retrieving the various services in an adaptive optimized manner. The lot of services are provided by the vast number of providers in the market with the help of approximation theory by the rough set system (RST). RST finds in helping in getting the efficient cloud resources as a service to the users. The proposed OCRS (Optimized Cost Resource System) approach is being simulated and compared with the existing cloud simulator. The simulator gives the approximate results in many parameters of cloud services. In all aspects our algorithm is performing better.