Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models. We identify a suitable Convolutional Neural Network (CNN) model through initial comparative study of several popular CNN models. We then optimize the selected VGG19 model for the image modalities to show how the models can be used for the highly scarce and challenging COVID-19 datasets. We highlight the challenges (including dataset size and quality) in utilizing current publicly available COVID-19 datasets for developing useful deep learning models and how it adversely impacts the trainability of complex models. We also propose an image pre-processing stage to create a trustworthy image dataset for developing and testing the deep learning models. The new approach is aimed to reduce unwanted noise from the images so that deep learning models can focus on detecting diseases with specific features from them. Our results indicate that Ultrasound images provide superior detection accuracy compared to X-Ray and CT scans. The experimental results highlight that with limited data, most of the deeper networks struggle to train well and provides less consistency over the three imaging modes we are using. The selected VGG19 model, which is then extensively tuned with appropriate parameters, performs in considerable levels of COVID-19 detection against pneumonia or normal for all three lung image modes with the precision of up to 86% for X-Ray, 100% for Ultrasound and 84% for CT scans.
This paper proposes a big-data analytics-based approach that considers social media (Twitter) data for the identification of supply chain management issues in food industries. In particular, the proposed approach includes (i) the capturing of relevant tweets based on keywords, (ii) the pre-processing of the raw tweets, and (iii) text analysis using a support vector machine (SVM) and hierarchical clustering with multiscale bootstrap resampling. The result of this approach included a cluster of words which could inform supply-chain (SC) decision makers about customer feedback and issues in the flow/quality of food products. A case study in the beef supply chain was analysed using the proposed approach, where three weeks of data from Twitter were used. The results indicated that the proposed text analytics approach can be helpful to effectively identify and summarise crucial customer feedback for the supply chain management. This study proposes a holistic approach, in which social media data are utilised in the domain of the food supply chain. The findings of the analysis have been linked to all the segments of the supply chain.
To provide the overview of this SI, initially a broad search was conducted to document the number of papers published in the area of 'Big data analytics' the search period used was from 2012 to 14 March 2018. An overview of the number of articles is presented in Fig. 1. After looking into the journal's specific search, Fig. 2 clearly demonstrates that the Annals of Operations Research was the leading journal in terms of the numbers of papers from Scopus.
Recently, big data (BD) has attracted researchers and practitioners due to its potential usefulness in decision-making processes. Big data analytics (BDA) is becoming increasingly popular among manufacturing companies as it helps gain insights and make decisions based on BD. However, there many barriers to the adoption of BDA in manufacturing supply chains. It is therefore necessary for manufacturing companies to identify and examine the nature of each barrier. Previous studies have mostly built conceptual frameworks for BDA in a given situation and have ignored examining the nature of the barriers to BDA. Due to the significance of both BD and BDA, this research aims to identify and examine the critical barriers to the adoption of BDA in manufacturing supply chains in the context of Bangladesh. This research explores the existing body of knowledge by examining these barriers using a Delphi-based analytic hierarchy process (AHP). Data were obtained from five Bangladeshi manufacturing companies. The findings of this research are as follows: i) data-related barriers are most important, ii) technology-related barriers are second, and iii) the five most important components of these barriers are a) lack of infrastructure, b) complexity of data integration, c) data privacy, d) lack of availability of BDA tools and e) high cost of investment. The findings can assist industrial managers to understand the actual nature of the barriers and potential benefits of using BDA and to make policy regarding BDA adoption in manufacturing supply chains. A sensitivity analysis was carried out to justify the robustness of the barrier rankings.
One of the most challenging research subjects in remote sensing is feature extraction, such as road features, from remote sensing images. Such an extraction influences multiple scenes, including map updating, traffic management, emergency tasks, road monitoring, and others. Therefore, a systematic review of deep learning techniques applied to common remote sensing benchmarks for road extraction is conducted in this study. The research is conducted based on four main types of deep learning methods, namely, the GANs model, deconvolutional networks, FCNs, and patch-based CNNs models. We also compare these various deep learning models applied to remote sensing datasets to show which method performs well in extracting road parts from high-resolution remote sensing images. Moreover, we describe future research directions and research gaps. Results indicate that the largest reported performance record is related to the deconvolutional nets applied to remote sensing images, and the F1 score metric of the generative adversarial network model, DenseNet method, and FCN-32 applied to UAV and Google Earth images are high: 96.08%, 95.72%, and 94.59%, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.