Research on Chest X-Ray Image Diagnosis of Covid-19 Based on Improved ResNet

With the outbreak of covid-19 in 2020, timely and effective diagnosis and treatment of each covid-19 patient is particularly important. This paper combines the advantages of deep learning in image recognition, takes RESNET as the basic network framework, and carries out the experiment of improving the residual structure on this basis. It is tested on the open source new coronal chest radiograph data set, and the accuracy rate is 82.3%. Through a series of experiments, the training model has the advantages of good generalization, high accuracy and fast convergence. This paper proves the feasibility of the improved residual neural network in the diagnosis of covid-19. © 2023 SPIE.

Integrating deep learning algorithms for the lung segmentation and body-part-specific anatomical classification with Medical Imaging and Data Resource Center (MIDRC)

Medical Imaging and Data Resource Center (MIDRC) has been built to support AI-based research in response to the COVID-19 pandemic. One of the main goals of MIDRC is to make data collected in the repository ready for AI analysis. Due to data heterogeneity, there is a need to standardize data and make data-mining easier. Our study aims to stratify imaging data according to underlying anatomy using open-source image processing tools. The experiments were performed using Google Colaboratory on computed tomography (CT) imaging data available from the MIDRC. We adopted the existing open-source tools to process CT series (N=389) to define the image sub-volumes according to body part classification, and additionally identified series slices containing specific anatomic landmarks. Cases with automatically identified chest regions (N=369) were then processed to automatically segment the lungs. In order to assess the accuracy of segmentation, we performed outlier analysis using 3D shape radiomics features extracted from the left and right lungs. Standardized DICOM objects were created to store the resulting segmentations, regions, landmarks and radiomics features. We demonstrated that the MIDRC chest CT collections can be enriched using open-source analysis tools and that data available in MIDRC can be further used to evaluate the robustness of publicly available tools. © 2023 SPIE.

SignalR based Real-Time applications in education

Before Covid, we introduced our own classroom response system to improve the effectiveness of our teaching. To this end, we adopted an open-source technique, SignalR, which provides a framework for building real-time web applications. Overnight, due to the emergency situation starting in 2019, education was moved to the virtual space. Both students and professors had to learn how to teach or learn using only online facilities, without a testing period. During the emergency, a synchronous online teaching mode was required by our university, so the choice was made to use Microsoft Teams, implemented with SignalR for real-time functionality. After the emergency, we were all happy to have our 'old life' back and return to our personal teaching style, but is it possible, is it possible to continue teaching in the same way as before Covid-19 - is it possible to step into the same river twice? Students have become accustomed to convenient, modern, digital options during the online education period and now that we are back in school, they insist that we continue to use the new tools. In this essay, we want to describe the changes in students' attitudes that we can usefully build on in the future and that will influence the further development of our project. © 2023 IEEE.

Digital Public Health Solutions in Response to the COVID-19 Pandemic: Comparative Analysis of Contact Tracing Solutions Deployed in Japan and Germany.

BACKGROUND: In response to the COVID-19 pandemic, numerous countries, including the likes of Japan and Germany, initiated, developed, and deployed digital contact tracing solutions in an effort to detect and interrupt COVID-19 transmission chains. These initiatives indicated the willingness of both the Japanese and German governments to support eHealth solution development for public health; however, end user acceptance, trust, and willingness to make use of the solutions delivered through these initiatives are critical to their success. Through a case-based analysis of contact tracing solutions deployed in Japan and Germany during the COVID-19 pandemic we may gain valuable perspectives on the transnational role of digital technologies in crises, while also projecting possible directions for future pandemic technologies. OBJECTIVE: In this study, we investigate (1) which types of digital contact tracing solutions were developed and deployed by the Japanese and German governments in response to the COVID-19 pandemic and (2) how many of these solutions are open-source software (OSS) solutions. Our objective is to establish not only the type of applications that may be needed in response to a pandemic from the perspective of 2 geographically diverse, world-leading economies but also how prevalent OSS pandemic technology development has been in this context. METHODS: We analyze the official government websites of Japan and Germany to identify digital solutions that are developed and deployed for contact tracing purposes (for any length of time) during the timeframe January-December 2021, specifically in response to the COVID-19 pandemic. We subsequently perform a case-oriented comparative analysis, also identifying which solutions are published as open-source. RESULTS: In Japan, a proximity tracing tool (COVID-19 Contact-Confirming Application [COCOA]) and an outbreak management tool (Health Center Real-time Information-sharing System on COVID-19 [HER-SYS]) with an integrated symptom tracking tool (My HER-SYS) were developed. In Germany, a proximity tracing tool (Corona-Warn-App) and an outbreak management tool (Surveillance Outbreak Response Management and Analysis System [SORMAS]) were developed. From these identified solutions, COCOA, Corona-Warn-App, and SORMAS were published as open-source, indicating support by both the Japanese and German governments for OSS pandemic technology development in the context of public health. CONCLUSIONS: Japan and Germany showed support for developing and deploying not only digital contact tracing solutions but also OSS digital contact tracing solutions in response to the COVID-19 pandemic. Despite the open nature of such OSS solutions' source code, software solutions (both OSS and non-OSS) are only as transparent as the live or production environment where their processed data is hosted or stored. Software development and live software hosting are thus 2 sides of the same coin. It is nonetheless arguable that OSS pandemic technology solutions for public health are a step in the right direction for enhanced transparency in the interest of the greater public good.

MultiSero: An Open-Source Multiplex-ELISA Platform for Measuring Antibody Responses to Infection.

A multiplexed enzyme-linked immunosorbent assay (ELISA) that simultaneously measures antibody binding to multiple antigens can extend the impact of serosurveillance studies, particularly if the assay approaches the simplicity, robustness, and accuracy of a conventional single-antigen ELISA. Here, we report on the development of multiSero, an open-source multiplex ELISA platform for measuring antibody responses to viral infection. Our assay consists of three parts: (1) an ELISA against an array of proteins in a 96-well format; (2) automated imaging of each well of the ELISA array using an open-source plate reader; and (3) automated measurement of optical densities for each protein within the array using an open-source analysis pipeline. We validated the platform by comparing antibody binding to Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) antigens in 217 human sera samples, showing high sensitivity (0.978), specificity (0.977), positive predictive value (0.978), and negative predictive value (0.977) for classifying seropositivity, a high correlation of multiSero determined antibody titers with commercially available SARS-CoV-2 antibody tests, and antigen-specific changes in antibody titer dynamics upon vaccination. The open-source format and accessibility of our multiSero platform can contribute to the adoption of multiplexed ELISA arrays for serosurveillance studies, for SARS-CoV-2 and other pathogens of significance.

Mathematical Evaluation of Covid-19 Detection Technique Using Cxr Radiographs of Patients, Using Densenet-201

A current COVID-19 detection tool is CXR imaging, which has been developing since 2019 to provide early diagnosis;it can be performed in any health unit and is more affordable than Real Time Polymerase Chain Reaction (RT-PCR) tests. However, diagnosis with Chest X Ray (CXR) images had not achieved the predictive capacity required to replace the RT-PCR test;previous studies with a limited number of images have evaluated their models. This research seeks to contribute to the detection of COVID-19 from CXR images, with the evaluation of a convolutional neural network model from CXR images, through the use of open source code on a free dataset of approximately 30 thousand images. The algorithm and mathematical model used was DenseNet-201. The results of the experiment show a precision and accuracy of more than 95% and specificity, sensitivity, predictive ability and F1 measurement of more than 90%.Copyright © 2022, Anka Publishers. All rights reserved.

SARS-CoV-2 risk assessment for a 30-minute car journey

In this paper a numerical methodology for close proximity exposure (<2m) is applied to the analysis of aerosol airborne dispersion and SARS-CoV-2 potential infection risk during short journeys in passenger cars. It consists of a three-dimensional transient Eulerian-Lagrangian numerical model coupled with a recently proposed SARS-CoV-2 emission approach, using the open-source software OpenFOAM. The numerical tool, validated by Particle Image Velocimetry (PIV), is applied to the simulation of aerosol droplets emitted by a contagious subject in a car cabin during a 30-minute journey and to the integrated risk assessment for SARS-CoV-2 for the other passengers. The effects of different geometrical and thermo-fluid-dynamic influence parameters are investigated, showing that both the position of the infected subject and the ventilation system design affect the amount of virus inhaled and the highest-risk position inside the passenger compartment. Calculated infection risk, for susceptible passengers in the car, can reach values up to 59%. © 2022 17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022. All rights reserved.

GETTING TO BETTER PANDEMIC AND EPIDEMIC PREPAREDNESS AND RESPONSE

The earlier we can detect and identify health threats, the faster we can respond and the more lives we can save...not to mention the impact on other aspects of societies and economies, as we clearly see through COVID-19 and other infectious disease events in our history. But responding faster requires us to do something with those things that we detect earlier first. It requires us to transform what we get through surveillance systems and the other vast amounts of information available to us in our increasingly digital world to intelligence that can then lead to appropriate actions. This should inform our collective priorities for surveillance;we need to ask ourselves how we can improve our intelligence so that the decisions that are made and the policies that are put in place are better informed, more timely and, ultimately, more effective in protecting lives and livelihoods. Seeking to address this very question, and in the midst of the COVID-19 pandemic, the World Health Organization's Hub for Pandemic and Epidemic Intelligence was created. This presentation will provide an overview of some of the intelligence work preceding its creation through the Epidemic Intelligence from Open Sources (EIOS) initiative and highlight some of its key activities and ambitions moving forward. [ FROM AUTHOR] Copyright of International Journal of Infectious Diseases is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Streaming Big Data with Open-source: A Comparative Study and Architectural Recommendations

This study focusses on providing state-of-the-art infrastructure for data pipelines in e-Commerce sector, especially for online stores. With people going digital and also latest impact of Covid-19, daily e-Commerce companies are dealing with large amount of data (terabytes to petabytes). With growing Internet of Things, systems of computing devices which are interrelated. The inter-relation may be between mechanical and digital machines, objects or people. The interrelated objects will be provided with unique identifiers and the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction. Growth of big data poses several challenges and opportunities in every field of its usage. Realtime analysis of data and its inference gives a competitive edge over its partners in every business field especially in e-commerce. Recent advances in technology and tools have exposed new opportunities to get actionable insights from historical data like market data, customer demographics, along with real-time data. Advancement in distributed streaming technology makes it important to investigate existing streaming data pipeline capabilities in eCommerce sector with a focus on online stores. This study analyzes the published research works on streaming data pipelines in e-commerce sector also to facilitate e-commerce's variety of data streaming applications requirement. A state-of-the-art lambda architecture for streaming is proposed completely based on open-source technologies. Challenge in proprietary owned streaming platforms are vendor lock-in, limited ability to customize, cost, limited innovation & support. Proposed reference architecture will address many streaming use cases compared to its competitors, it has support of large open-source community in providing the inter-operability between streaming & related technologies like connectors, apart from providing better performance apart from other open-source based product advantages. © 2023 IEEE.

The Impact of the Scientific Metaverse on the Biotech Industry: How Virtual Reality Helped Researchers Fight Back Against COVID-19

The coronavirus disease 2019 pandemic not only precipitated a digital revolution but also led to one of the largest scientific collaborative open-source initiatives. The EXaSCale smArt pLatform Against paThogEns for CoronaVirus (EXSCALATE4CoV) consortium, led by Dompé farmaceutici S.p.A., brought together 18 global organizations to counter international pandemics more rapidly and efficiently. The consortium also partnered with Nanome, an extended reality software company whose software facilitates the visualization, modification, and simulation of molecules via augmented reality, mixed reality, and virtual reality applications. To characterize the molecular structure of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and to identify promising drug targets, the EXSCALATE4CoV team utilized methods such as homology modeling, molecular dynamics simulations, high-throughput virtual screening, docking, and other computational procedures. Nanome provided analysis of those computational procedures and supplied virtual reality headsets to help scientists better understand and interact with the molecular dynamics and key chemical interactions of SARS-CoV-2. Nanome's collaborative ideation platform enables scientific breakthroughs across research institutions in the fight against the coronavirus pandemic and other diseases. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Smartwatch-based ecological momentary assessments for occupant wellness and privacy in buildings

This paper describes the adaptation of an open-source ecological momentary assessment smartwatch platform with three sets of micro-survey wellness-related questions focused on i) infectious disease (COVID-19) risk perception, ii) privacy and distraction in an office context, and iii) triggers of various movement-related behaviors in buildings. This platform was previously used to collect data for thermal comfort, and this work extends its use to other domains. Several research participants took part in a proof-of-concept experiment by wearing a smartwatch to collect their micro-survey question preferences and perception responses for two of the question sets. Participants were also asked to install an indoor localization app on their phone to detect where precisely in the building they completed the survey. The experiment identified occupant information such as the tendencies for the research participants to prefer privacy in certain spaces and the difference between infectious disease risk perception in naturally versus mechanically ventilated spaces. © 2022 17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022. All rights reserved.

No Transfer Without Validation: A Data Sharing Framework Use Case.

Availability and accessibility are important preconditions for using real-world patient data across organizations. To facilitate and enable the analysis of data collected at a large number of independent healthcare providers, syntactic- and semantic uniformity need to be achieved and verified. With this paper, we present a data transfer process implemented using the Data Sharing Framework to ensure only valid and pseudonymized data is transferred to a central research repository and feedback on success or failure is provided. Our implementation is used within the CODEX project of the German Network University Medicine to validate COVID-19 datasets at patient enrolling organizations and securely transfer them as FHIR resources to a central repository.

Biomedical Image Classification Using Convolutional Neural Networks

Recent research trends in the field image processing have focussed on challenges and few techniques for processing and classification tasks related to it. Image classification aims at classifying images based on several predefined categories. Several research works have been carried out to overcome shortcomings in image classification, nevertheless the output was restricted to the elementary low-level picture. Several deep neural network techniques are employed for image classification such as Convolutional Neural Network, Machine Learning Algorithms like Random Forest, SVM, etc. In this paper, we aim at designing a COVID-19 detection using the CNN model with support of Open-Source software such as Keras, Python, Google Colab, Google Drive, Kaggle, and Visual Studio for aggregate, design, create, train, visualize, and analyze bulk load of data on the cloud after programing a Deep neural network without a need for high-end processing hardware. We have made use of weights to test and analyse the accuracy, visualize and predict the condition of a lung using chest X-Rays at certain accuracy. This will help in identifying the problems of the patients at a faster rate, thus giving an appropriate treatment at an early stage itself to saving one life. © 2023 IEEE.

Geographical Dependence of Open Hardware Optimization: Case Study of Solar Photovoltaic Racking

Open-source technological development is well-known for rapid innovation and providing opportunities to reduce costs and thus increase accessibility for a wide range of products. This is done through distributed manufacturing, in which products are produced close to end users. There is anecdotal evidence that these opportunities are heavily geographically dependent, with some locations unable to acquire components to build open hardware at accessible prices because of trade restrictions, tariffs, taxes, or market availability. Supply chain disruptions during the COVID-19 pandemic exacerbated this and forced designers to pivot towards a la carte-style design frameworks for critical system components. To further develop this phenomenon, a case study of free and open-source solar photovoltaic (PV) racking systems is provided. Two similar open-source designs made from different materials are compared in terms of capital costs for their detailed bill of materials throughout ten locations in North, Central and South America. The differences in economic optimization showed that the costs of wood-based racks were superior in North America and in some South American countries, while metal was less costly in Central and South America. The results make it clear that open hardware designs would be best to allow for local optimization based on material availability in all designs. © 2023 by the authors.

Classification of Lung CT Scan Images using Machine Learning

Timely discovery of COVID-19 may safeguard numerous diseased people. Several such lung diseases can turn to be life threatening. Early detection of these diseases can help in treating them at an early stage before it becomes threatening. In this paper, the proposed 3D CNN model helps in classifying the CT scans as normal and abnormal, which can then be used to treat the patients after recognizing the diseases. Chest X-ray is fewer commanding in the initial phases of the sickness, while a CT scan of the chest is advantageous even formerly symptoms seem, and CT scan accurately identify the anomalous features which are recognized in images. Besides this, using the two forms of images will raise the database. This will enhance the classification accuracy. In this paper the model used is a 3D CNN model;using this model the predictions are done. The dataset used is acquired from NKP Salve Medical Institute, Nagpur. This acquired dataset is used for prediction while an open source database is used for training the CNN model. After training the model the prediction were successfully completed, with these proposed 3D CNN model total accuracy of 87.86% is achieved. This accuracy can further be increased by using larger dataset. © 2022 IEEE.

An Effective Threat Detection Framework for Advanced Persistent Cyberattacks

Recently, with the normalization of non-face-to-face online environments in response to the COVID-19 pandemic, the possibility of cyberattacks through endpoints has increased. Numerous endpoint devices are managed meticulously to prevent cyberattacks and ensure timely responses to potential security threats. In particular, because telecommuting, telemedicine, and tele-education are implemented in uncontrolled environments, attackers typically target vulnerable endpoints to acquire administrator rights or steal authentication information, and reports of endpoint attacks have been increasing considerably. Advanced persistent threats (APTs) using various novel variant malicious codes are a form of a sophisticated attack. However, conventional commercial antivirus and anti-malware systems that use signature-based attack detection methods cannot satisfactorily respond to such attacks. In this paper, we propose a method that expands the detection coverage in APT attack environments. In this model, an open-source threat detector and log collector are used synergistically to improve threat detection performance. Extending the scope of attack log collection through interworking between highly accessible open-source tools can efficiently increase the detection coverage of tactics and techniques used to deal with APT attacks, as defined by MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK). We implemented an attack environment using an APT attack scenario emulator called Carbanak and analyzed the detection coverage of Google Rapid Response (GRR), an open-source threat detection tool, and Graylog, an open-source log collector. The proposed method expanded the detection coverage against MITRE ATT&CK by approximately 11% compared with that conventional methods. © 2023 Tech Science Press. All rights reserved.

Yo-Yo Machines

Yo-Yo Machines are playful communication devices designed to help people feel socially connected while physically separated. We designed them to reach as many people as possible, both to make a positive impact during the COVID-19 pandemic and to assess a self-build approach to circulating research products and the appeal of peripheral and expressive communication devices. A portfolio of four distinct designs, based on over 30 years of research, were made available for people to make by following simple online instructions (yoyomachines.io). Each involves connecting a pair of identical devices over the internet to allow simple communication at a distance. This paper describes our motivation for the project, previous work in the area, the design of the devices, supporting website and publicity, and how users have made and used Yo-Yo Machines. Finally, we reflect on what we learned about peripheral and expressive communication devices and implications for the self-build approach.

Overcoming Chip Shortages: Low-Cost Open-Source Parametric 3-D Printable Solderless SOIC to DIP Breakout Adapters

The COVID-19 pandemic exposed the vulnerability of global supply chains of many products. One area that requires improved supply chain resilience and that is of particular importance to electronic designers is the shortage of basic dual in-line package (DIP) electronic components commonly used for prototyping. This anecdotal observation was investigated as a case study of using additive manufacturing to enforce contact between premade, off-the-shelf conductors to allow for electrical continuity between two arbitrary points by examining data relating to the stock quantity of electronic components, extracted from Digi-Key Electronics. This study applies this concept using an open hardware approach for the design, testing, and use of a simple, parametric, 3-D printable invention that allows for small outline integrated circuit (SOIC) components to be used in DIP package circuits (i.e., breadboards, protoboards, etc.). The additive manufacture breakout board (AMBB) design was developed using two different open-source modelers, OpenSCAD and FreeCAD, to provide reliable and consistent electrical contact between the component and the rest of the circuit and was demonstrated with reusable 8-SOIC to DIP breakout adapters. The three-part design was optimized for manufacturing with RepRap-class fused filament 3-D printers, making the AMBB a prime candidate for use in distributed manufacturing models. The AMBB offers increased flexibility during circuit prototyping by allowing arbitrary connections between the component and prototyping interface as well as superior organization through the ability to color-code different component types. The cost of the AMBB is CAD $0.066/unit, which is a 94% saving compared to conventional PCB-based breakout boards. Use of the AMBB device can provide electronics designers with an increased selection of components for through-hole use by more than a factor of seven. Future development of AMBB devices to allow for low-cost conversion between arbitrary package types provides a path towards more accessible and inclusive electronics design as well as faster prototyping and technical innovation.

Adding to Agile Software Development

How integrating DFSS into agile software development can help address the human aspects of these processes A German university of applied sciences with about 5,500 students needed new software due to COVID-19-related laws and decrees that required universities to perform contact tracking in case of potential COVID-19 exposure. Agile is a software development philosophy based on using self-organized teams.2 The goal of agile is to develop a basic working version of the software quickly, and continuously improve the software and add more features in accordance with customer or stakeholder wishes.3 Unlike many other software development methods, agile does not have predefined stages or documents4 and is ideally suited to coping with evolving and changing stakeholder requirements.5 One advantage of agile is discovering software design flaws quicker than classic stage-based software development models.6 Finding design flaws quickly is advantageous because fixing the software design late in the project is costly and time consuming. The problem statement was a verbal "digitize contact tracking," and there were frequent attempts to expand the project to include additional objectives such as ensuring people maintained social distancing, registering students for study spaces and improving carbon dioxide monitoring. Leveraging DFSS While agile is well suited to software development, it is less suited to dealing with many of the organizational problems that were encountered. [...]future projects would benefit from integrating a DFSS framework into such projects.

Explainable COVID-19 Three Classes Severity Classification Using Chest X-Ray Images

COVID-19 has been raging for almost three years ever since its first outbreak. It is without a doubt that it is a common human goal to end the pandemic and how it was before it started. Many efforts have been made to work toward this goal. In computer vision, works have been done to aid medical professionals into faster and more effective procedures when dealing with the disease. For example, disease diagnosis and severity prediction using chest imaging. At the same time, vision transformer is introduced and quickly stormed its way into one of the best deep learning models ever developed due to its ability to achieve good performance while being resources friendly. In this study, we investigated the performance of ViT on COVID19 severity classification using an open-source CXR images dataset. We applied different augmentation and transformation techniques to the dataset to see ViT's ability to learn the features of the different severity levels of the disease. It is concluded that training ViT using the horizontally flipped images added to the original dataset gives the best overall accuracy of 0.862. To achieve explainability, we have also applied Grad-CAM to the best performing model to make sure it is looking at relevant region of the CXR image upon predicting the class label. © 2022 IEEE.