Search

COVID-19 is a novel virus which is originated from Wuhan, a city in China. By March 2021, World Health Organization has confirmed the virus has increased in the number of infections to over 117 million cases globally. In this scenario of increasing Corona infected patients, most hospitals are lagging in the availability of the Corona test kits. Owing to the lack of precise automated toolkits, auxiliary diagnostic tools are in high demand. Therefore, it becomes necessary to enforce AI-based automatic detection techniques. It can also address the issue of unavailability of physicians in remote areas. This study proposes the use of deep neural networks and transfer learning for the detection of COVID-19 infectees through radio-graphs of chest X-rays. We have used hand-crafted Convolutional Neural Network (CNN) besides using the existing famous pre-trained networks employing transfer learning. Remarkable accuracy achieved was 96.89% for our hand-crafted CNN, 92.67% for ResNet34, and 98.26% on DenseNet-121, respectively. However, our hand-crafted CNN required 8 million less parameters than ResNet34 and comparable to DenseNet-121.

Human beings tend to incrementally learn from the rapidly changing environment without comprising or forgetting the already learned representations. Although deep learning also has the potential to mimic such human behaviors to some extent, it suffers from catastrophic forgetting due to which its performance on already learned tasks drastically decreases while learning about newer knowledge. Many researchers have proposed promising solutions to eliminate such catastrophic forgetting during the knowledge distillation process. However, to our best knowledge, there is no literature available to date that exploits the complex relationships between these solutions and utilizes them for the effective learning that spans over multiple datasets and even multiple domains. In this paper, we propose a continual learning objective that encompasses mutual distillation loss to understand such complex relationships and allows deep learning models to effectively retain the prior knowledge while adapting to the new classes, new datasets, and even new applications. The proposed objective was rigorously tested on nine publicly available, multi-vendor, and multimodal datasets that span over three applications, and it achieved the top-1 accuracy of 0.9863% and an F1-score of 0.9930.

Background & Aims: The diarrheagenic pathogen, enteropathogenic Escherichia coli (EPEC), uses a type III secretion system to deliver effector molecules into intestinal epithelial cells (IECs). While exploring the basis for the lateral membrane separation of EPEC-infected IECs, we observed infection-induced loss of the desmosomal cadherin desmoglein-2 (DSG2). We sought to identify the molecule(s) involved in, and delineate the mechanisms and consequences of, EPEC-induced DSG2 loss. Methods: DSG2 abundance and localization was monitored via immunoblotting and immunofluorescence, respectively. Junctional perturbations were visualized by electron microscopy, and cell–cell adhesion was assessed using dispase assays. EspH alanine-scan mutants as well as pharmacologic agents were used to evaluate impacts on desmosomal alterations. EPEC-mediated DSG2 loss, and its impact on bacterial colonization in vivo, was assessed using a murine model. Results: The secreted virulence protein EspH mediates EPEC-induced DSG2 degradation, and contributes to desmosomal perturbation, loss of cell junction integrity, and barrier disruption in infected IECs. EspH sequesters Rho guanine nucleotide exchange factors and inhibits Rho guanosine triphosphatase signaling; EspH mutants impaired for Rho guanine nucleotide exchange factor interaction failed to inhibit RhoA or deplete DSG2. Cytotoxic necrotizing factor 1, which locks Rho guanosine triphosphatase in the active state, jasplakinolide, a molecule that promotes actin polymerization, and the lysosomal inhibitor bafilomycin A, respectively, rescued infected cells from EPEC-induced DSG2 loss. Wild-type EPEC, but not an espH-deficient strain, colonizes mouse intestines robustly, widens paracellular junctions, and induces DSG2 re-localization in vivo. Conclusions: Our studies define the mechanism and consequences of EPEC-induced desmosomal alterations in IECs. These perturbations contribute to the colonization and virulence of EPEC, and likely related pathogens. Keywords: EPEC, Desmoglein, DSG2, Host–Pathogen Interaction

Data mining and machine learning algorithms deal with large amount of data, which with the invention of cost-efficient devices has increased by massive amounts. Many algorithms of these domains are not part of real-time systems because of their computational complexity and large data on which they need to work. A lot of algorithms are being implemented on parallel processing systems like GPUs and FPGAs to achieve the desired speed. The purpose of this article is to provide parallel processing model of mean shift clustering algorithm, targeted to run on FPGA. The general model consists of multiple homogeneous processing entities (PEs) connected through a bus. These PEs work in collaborative working environment with each PE working independently and also communicating with its peers according to the requirements of algorithms. The proposed architecture is implemented on FPGA for one-dimensional data. The algorithm is tested on 99 images from segmentation evaluation database for different number of PEs and different number of fractional bits used to represent mean. The simplicity of algorithm resulted in utilizing only 10.31% of total device slice registers and 33% of total slice LUTs of Spartan 6 FPGA. The processing requirements for the proposed algorithm show that it can be used in real-time systems.

In Computer vision object detection and classification are active fields of research. Applications of object detection and classification include a diverse range of fields such as surveillance, autonomous cars and robotic vision. Many intelligent systems are built by researchers to achieve the accuracy of human perception but could not quite achieve it yet. Convolutional Neural Networks (CNN) and Deep Learning architectures are used to achieve human like perception for object detection and scene identification. We are proposing a novel method by combining previously used techniques. We are proposing a model which takes multi-spectral images, fuses them together, drops the useless images and then provides semantic segmentation for each object (person) present in the image. In our proposed methodology we are using CNN for fusion of Visible and thermal images and Deep Learning architectures for classification and localization. Fusion of visible and thermal images is carried out to combine informative features of both images into one image. For fusion we are using Encoder-decoder architecture. Fused image is then fed into Resnet-152 architecture for classification of images. Images obtained from Resnet-152 are then fed into Mask-RCNN for localization of persons. Mask-RCNN uses Resnet-101 architecture for localization of objects. From the results it can be clearly seen that Fused model for object localization outperforms the Visible model and gives promising results for person detection for surveillance purposes. Our proposed model gives the Miss Rate of 5.25% which is much better than the previous state of the art method applied on KAIST dataset.

The light curve analysis of the heavenly bodies is an indispensable tool for understanding the physical phenomena that govern them. Large telescopes like the LSST will produce an excess of data produced that will necessitate the need for automated methods to sift through it quickly and efficiently as doing so manually can be truly laborious. Furthermore, such a method should be able classify the observed astronomical objects accurately. Keeping this in view, we have proposed an automated classification method using the simulated, photometric light curves in to 14 different classes. We have built our classification model by extracting several features and employing Random Forest classifier. Our proposed methodology performs reasonably well for most of the classes while others still offer a little room for improvement. As our proposed methodology relies on features extracted from photometric light curves, therefore it can be adapted and extended for use in other fields that rely on similar light curves.

In the last couple of decades, Convolution Neural Network (CNN) emerged as the most active field of research. There are a number of applications of CNN, and its architectures are used for the improvement of accuracy and efficiency in various fields. In this paper, we aim to use CNN in order to generate fusion of visible and thermal camera images to detect persons present in those images for a reliable surveillance application. There are various kinds of image fusion methods to achieve multi-sensor, multi-modal, multi-focus and multi-view image fusion. Our proposed methodology includes Encoder-Decoder architecture for fusion of visible and thermal images and ResNet-152 architecture for classification of images to detect if there is a person present in the image or not. Korea Advanced Institute of Science and Technology (KAIST) multispectral dataset consisting of 95,000 visible and thermal images is used for training of CNNs. During experimentation, it is observed that fused architecture outperforms individual visible and thermal based architectures, where fused architecture gives 99.2% accuracy while visible gives 97% and thermal gives 97.6% accuracy.

Morbidity and mortality attributed to

Technological advancements in todays information age has helped the researchers to capture digital footprints of humans with regards to their daily activities. These logs of information posses valuable information for the data analytics who process it to find hidden pattern and unique behavior. Among the many algorithms k-means clustering is one of the very popular and widely used algorithm in the field of data mining and machine learning. k-means provides natural segments of dataset provided for clustering. It uses proximity to assign data points to a specific cluster, here the criteria of allocation is the minimum distance from the cluster center. Unfortunately, the rate of data growth has not been met by the speed of the algorithms. A number of hardware based solutions have been proposed to increase the processing power of different algorithms. In this paper, we present a novel algorithm for k-mean clustering which exploits the data redundancy occurring in the dataset. The proposed algorithm performs computations for the available unique items in the dataset and uses its frequency to finalize the results. Furthermore, FPGA based hardware architecture for the proposed algorithm is also presented in the paper. The performance of the proposed algorithm and its hardware implementation is evaluated using execution time, speedup and throughput. The proposed architecture provides speedup of 23 times and 2600 times against sequential hardware architecture and software implementation with a very small area requirement.