An L norm for efficient power quality monitoring

Real-time monitoring of power quality requires extensive data-handling and data-processing capabilities. These requirements limit the scope of monitoring, despite the fact that microprocessor-based monitoring systems have seen significant increase in their storage and computational power. Development of compact algorithms will benefit power quality in two ways; they will allow monitoring of more points simultaneously for large systems, and they will help create powerful embeddable monitoring architectures within small power devices, such as a breaker, motors, or power drives. This paper proposes use of the distance L¹ norm as an indicator of power quality. We show how this approach will improve the computational and storage requirements. This work presents analyses of the proposed norm, how it compares with traditional approaches, and examples of its applications.     

Gastric Tract Disease Recognition Using Optimized Deep Learning Features

Artificial intelligence aids for healthcare have received a great deal of attention. Approximately one million patients with gastrointestinal diseases have been diagnosed via wireless capsule endoscopy (WCE). Early diagnosis facilitates appropriate treatment and saves lives. Deep learning-based techniques have been used to identify gastrointestinal ulcers, bleeding sites, and polyps. However, small lesions may be misclassified. We developed a deep learning-based best-feature method to classify various stomach diseases evident in WCE images. Initially, we use hybrid contrast enhancement to distinguish diseased from normal regions. Then, a pretrained model is fine-tuned, and further training is done via transfer learning. Deep features are extracted from the last two layers and fused using a vector length-based approach. We improve the genetic algorithm using a fitness function and kurtosis to select optimal features that are graded by a classifier. We evaluate a database containing 24,000 WCE images of ulcers, bleeding sites, polyps, and healthy tissue. The cubic support vector machine classifier was optimal; the average accuracy was 99%.     

Controlled release of Montelukast Sodium from pH-sensitive injectable hydrogels

pH sensitive hydrogels showed excellent drug release properties, with promise for other biomedical applications. Also, the impact of molecular weight (MW) and degree of deacetylation (DDA) of chitosan on the fabricated chitosan/poly (vinyl alcohol) (3:1 mol ratio) hydrogel with selective silane crosslinker amount was evaluated for controlled drug delivery. The FTIR spectroscopy confirmed the incorporated components and the developed interactions among the polymer chains. The hydrogel characteristics were expressed by their responsive behaviour in different environments (water, ionic media and pH). The hydrogel sample (CH1000) having chitosan with higher MW and DDA exhibited more thermal stability and bacterial growth inhibition against E.coli. All hydrogels exhibited maximum swelling at basic and neutral pH and less swelling was observed in acidic media. For drug release analysis performed in simulated gastric fluid, hydrogel showed controlled drug release in 2 h but it was more than 10%, consequently cannot be used for oral purpose. In simulated intestinal fluid, hydrogels exhibited more than 80% release within 90 min. This characteristic phenomenon at neutral pH empowered hydrogel appropriate towards injectable and targeted controlled release of applicable drug. It was concluded that the prepared hydrogel can be administered directly into the venous circulation through syringe and can be used with better results for biomedical applications.     

Influence of openings on seismic performance of masonry building walls

In the present study, finite element analysis has been carried out for a single storey one-room masonry building with different aspect ratios and with different positions of openings in different walls subjected to the seismic force with varying direction. The response spectrum method has been employed for its seismic analysis. The variation of two most critical parameters namely, maximum principal tensile stress and maximum shear stress has been studied for monitoring the performance of masonry walls. It is observed from the present study that the critical direction of seismic force for the development of maximum stresses in the walls of a room with openings is along the short wall of the room and maximum principal tensile stress and maximum shear stress developed in the shear walls generally increase as the aspect ratio of the building increases and it is greatly influenced by the position of openings. It is also observed that the maximum principal tensile stress occurs in short wall and maximum shear stress occurs in long wall.     

Recognition and Detection of Diabetic Retinopathy Using Densenet-65 Based Faster-RCNN

Diabetes is a metabolic disorder that results in a retinal complication called diabetic retinopathy (DR) which is one of the four main reasons for sightlessness all over the globe. DR usually has no clear symptoms before the onset, thus making disease identification a challenging task. The healthcare industry may face unfavorable consequences if the gap in identifying DR is not filled with effective automation. Thus, our objective is to develop an automatic and cost-effective method for classifying DR samples. In this work, we present a custom Faster-RCNN technique for the recognition and classification of DR lesions from retinal images. After pre-processing, we generate the annotations of the dataset which is required for model training. Then, introduce DenseNet-65 at the feature extraction level of Faster-RCNN to compute the representative set of key points. Finally, the Faster-RCNN localizes and classifies the input sample into five classes. Rigorous experiments performed on a Kaggle dataset comprising of 88,704 images show that the introduced methodology outperforms with an accuracy of 97.2%. We have compared our technique with state-of-the-art approaches to show its robustness in term of DR localization and classification. Additionally, we performed cross-dataset validation on the Kaggle and APTOS datasets and achieved remarkable results on both training and testing phases.     

A decision tree framework for shot classification of field sports videos

The Journal of Supercomputing - Automated approaches to analyze sports video content have been heavily explored in the last few decades to develop more informative and effective solutions for...     

Embedding neural networks for semantic association in content based image retrieval

Content based image retrieval (CBIR) systems provide potential solution of retrieving semantically similar images from large image repositories against any query image. The research community are competing for more effective ways of content based image retrieval, so they can be used in serving time critical applications in scientific and industrial domains. In this paper a Neural Network based architecture for content based image retrieval is presented. To enhance the capabilities of proposed work, an efficient feature extraction method is presented which is based on the concept of in-depth texture analysis. For this wavelet packets and Eigen values of Gabor filters are used for image representation purposes. To ensure semantically correct image retrieval, a partial supervised learning scheme is introduced which is based on K-nearest neighbors of a query image, and ensures the retrieval of images in a robust way. To elaborate the effectiveness of the presented work, the proposed method is compared with several existing CBIR systems, and it is proved that the proposed method has performed better then all of the comparative systems.

     

An efficient U-Net framework for lung nodule detection using densely connected dilated convolutions

The Journal of Supercomputing - Remote health monitoring is an important aspect especially for remote locations where standard medical facilities are not available. Smart cities use a similar...     

Pandemic Analysis and Prediction of COVID-19 Using Gaussian Doubling Times

COVID-19 has become a pandemic, with cases all over the world, with widespread disruption in some countries, such as Italy, US, India, South Korea, and Japan. Early and reliable detection of COVID-19 is mandatory to control the spread of infection. Moreover, prediction of COVID-19 spread in near future is also crucial to better plan for the disease control. For this purpose, we proposed a robust framework for the analysis, prediction, and detection of COVID-19. We make reliable estimates on key pandemic parameters and make predictions on the point of inflection and possible washout time for various countries around the world. The estimates, analysis and predictions are based on the data gathered from Johns Hopkins Center during the time span of April 21 to June 27, 2020. We use the normal distribution for simple and quick predictions of the coronavirus pandemic model and estimate the parameters of Gaussian curves using the least square parameter curve fitting for several countries in different continents. The predictions rely on the possible outcomes of Gaussian time evolution with the central limit theorem of statistics the predictions to be well justified. The parameters of Gaussian distribution, i.e., maximum time and width, are determined through a statistical χ2-fit for the purpose of doubling times after April 21, 2020. For COVID-19 detection, we proposed a novel method based on the Histogram of Oriented Gradients (HOG) and CNN in multi-class classification scenario i.e., Normal, COVID-19, viral pneumonia etc. Experimental results show the effectiveness of our framework for reliable prediction and detection of COVID-19.