ABSTRACT
MIDRC was created to facilitate machine learning research for tasks including early detection, diagnosis, prognosis, and assessment of treatment response related to the COVID-19 pandemic and beyond. The purpose of the Technology Development Project (TDP) 3c is to create resources to assist researchers in evaluating the performance of their machine learning algorithms. An interactive decision tree has been developed, organized by the type of task that the machine learning algorithm is being trained to perform. The user can select information such as: (a) the type of task, (b) the nature of the reference standard, and (c) the type of the algorithm output. Based on the user responses, they can obtain recommendations regarding appropriate performance evaluation approaches and metrics, including literature references, short video tutorials, and links to available software. Five tasks have been identified for the decision tree: (a) classification, (b) detection/localization, (c) segmentation, (d) time-to-event analysis, and (e) estimation. As an example, the classification branch of the decision tree includes binary and multi-class classification tasks and provides suggestions for methods and metrics as well as software recommendations, and literature references for situations where the algorithm produces either binary or non-binary (e.g., continuous) output and for reference standards with negligible or non-negligible variability and unreliability. The decision tree has been made publicly available on the MIDRC website to assist researchers in conducting task-specific performance evaluations, including classification, detection/localization, segmentation, estimation, and time-to-event tasks. © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.
ABSTRACT
Solutions to screen and diagnose positive patients for the SARS-CoV-2 promptly and efficiently are critical in the context of the COVID-19 pandemic's complex evolution. Recent researches have demonstrated the efficiency of deep learning and particularly convolutional neural networks (CNNs) in classifying and detecting lung disease-related lesions from radiographs. This paper presents a solution using ensemble learning techniques on advanced CNNs to classify as well as localize COVID-19-related abnormalities in radiographs. Two classifiers including EfficientNetV2 and NFNet are combined with three detectors, DETR, Yolov7 and EfficientDet. Along with gathering and training the model on a large number of datasets, image augmentation and cross validation are also addressed. Since then, this study has shown promising results and has received excellent marks in the Society for Imaging Informatics in Medicine's competition. The analysis in model selection for the trade-off between speed and accuracy is also given. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Since the beginning of world-wide COVID-19 pandemic, facial masks have been recommended to limit the spread of the disease. However, these masks hide certain facial attributes. Hence, it has become difficult for existing face recognition systems to perform identity verification on masked faces. In this context, it is necessary to develop masked Face Recognition (MFR) for contactless biometric recognition systems. Thus, in this paper, we propose Complementary Attention Learning and Multi-Focal Spatial Attention that precisely removes masked region by training complementary spatial attention to focus on two distinct regions: masked regions and backgrounds. In our method, standard spatial attention and networks focus on unmasked regions, and extract mask-invariant features while minimizing the loss of the conventional Face Recognition (FR) performance. For conventional FR, we evaluate the performance on the IJB-C, Age-DB, CALFW, and CPLFW datasets. We evaluate the MFR performance on the ICCV2021-MFR/Insightface track, and demonstrate the improved performance on the both MFR and FR datasets. Additionally, we empirically verify that spatial attention of proposed method is more precisely activated in unmasked regions. © 2023 IEEE.
ABSTRACT
At the outbreak of COVID-19, researchers worldwide are seeking approaches to containing this disease. It is necessary to monitor social distance in enclosed public areas, such as subways or shopping malls. Passive localization, such as surveillance cameras, is a natural candidate for this issue, which is meaningful for rapid response to finding the infected suspect. However, the latest surveillance camera system is rotatable, even movable. And it is impossible for professionals to regularly calibrate the extrinsic parameters in a large-scale application, like COVID-19 suspect monitoring. We propose an inertial-aided passive localization method using surveillance camera for social distance measurement without the necessity to obtain extrinsic parameters. Moreover, the hardware modification cost of the off-the-shelf commercial camera is low, which suits the immediate application. The method uses SGBM (Semi-Global Block Matching) for 3D reconstruction and combines YOLOv3 and Gaussian Mixture Model (GMM) clustering algorithm to extract pedestrian point clouds in real time. Combining the 2D DNN-based and model-based methods makes a better balance between the computational load and the detection accuracy than end-to-end 3D DNN-based method. The inertial sensor provides an extra observation for the coordinate transformation from the camera frame into the world ground frame. Results show we can get a decimeter-level social distancing accuracy under noisy background and foreground environments at a low cost, which is promising for urgent COVID-19 public area monitoring. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
Halliburton uses the term "local content" to describe programs to develop and use local resources in providing our services in that host country. Local content requirements vary by country, but commonly include providing employment opportunities to local citizens, procurement of goods and services from within the country, manufacturing and value addition through partnerships with and development of local entities, training programs to develop the technical skills of local individuals and businesses, and carry out research and development for finding indigenous alternates of imported materials. In almost all cases, local content requirements are mandated by the laws of the countries where we operate. Adhering to and improving local content is an important part of Halliburton's commitment to support the countries in which it operates and it also brings benefits for both Halliburton and local communities. In this paper, we share a case study of how Halliburton carried out the process of localizing chemical manufacturing in Saudi Arabia, the steps taken, and support extended in developing the local suppliers. Meeting local content requirements requires precise collaboration and communication between regional and country management teams, compliance with host country laws and regulations, adherence to Halliburton company policies, and meeting the quality standards the National Operating Company which is the end user in most cases. The methodology for achieving effective localization results started with setting the right strategy and putting challenging but achievable targets. This localization initiative exemplifies company efforts to create value in every aspect of the company's business through the In-Kingdom Total Value Add (iktva) program mandated by the national operating company in the country. Having a local source of manufacturing and supply chain mitigates any disruptions like the one we saw during COVID 19 whereby the movement across borders was partially closed and supply chain globally was disrupted. Any local souring effectively diminishes the impact of any such disruptions. This initiative considered more than 50 Halliburton commercial chemical products and resulted in more than 10 successful replacements. Halliburton was able to export three products to company's operations outside Saudi Arabia. Partnering with Saudi Aramco, chamber of commerce and local manufacturers and suppliers in this program will drive additional domestic value creation to support a rapidly changing economic environment and foster future prosperity. Copyright © 2022, International Petroleum Technology Conference.
ABSTRACT
The COVID-19 outbreak impacted the people's lives in the world. Lockdown is one way of controlling the spread of the virus. In Indonesia, the government would rather implement public activity restriction than lockdown. The detailed comprehension of the effect of lockdown or similar policies on air pollution is valuable for making future policies about the control of pandemics as well as its effect on air quality. To understand the effect of public activity restriction (PAR) and its correlation with air pollution, mobile monitoring (MM) of particulate matter (PM2.5) was performed in the urban area of Bandung, Indonesia, in July 2021. Based on MM using a bicycle, we found that a PAR had an impact on air pollution. Our result showed that there was a decrease between 20% and 30% in 3 of 6 sub-districts. The advantage of MM was highlighted by the prominent visualization of the concentration of PM2.5 MM data at the level of the road. Localization of polluted roads could be seen clearly through the MM method. The uncovering effect of PAR on air pollution using the MM method will provide important insights for government and policymakers to develop future policy that controls air pollution for better citizen health. © 2023, AAGR Aerosol and Air Quality Research. All rights reserved.
ABSTRACT
The recent SARS-COV-2 virus, also known as COVID-19, badly affected the world's healthcare system due to limited medical resources for a large number of infected human beings. Quarantine helps in breaking the spread of the virus for such communicable diseases. This work proposes a nonwearable/contactless system for human location and activity recognition using ubiquitous wireless signals. The proposed method utilizes the channel state information (CSI) of the wireless signals recorded through a low-cost device for estimating the location and activity of the person under quarantine. We propose to utilize a Siamese architecture with combined one-dimensional convolutional neural networks (1-D-CNNs) and bi-directional long short-term memory (Bi-LSTM) networks. The proposed method provides high accuracy for the joint task and is validated on two real-world testbeds, first, using the designed low-cost CSI recording hardware, and second, on a public dataset for joint activity and location estimation. The human activity recognition (HAR) results outperform state-of-the-art machine and deep learning methods, and localization results are comparable with the existing methods. © 2001-2012 IEEE.
ABSTRACT
COVID-19 has been rapidly spreading worldwide and infected more than 1 million people with over 690k deaths reported. It is urgent and crucial to identify COVID-19-infected patients by computed tomography (CT) accurately and rapidly. However, we found that two problems, weak supervision and lack of interpretability, hindered its development. To address these challenges, we propose an attention-based multi-flow network for COVID-19 classification and lesion localization from chest CT. In the proposed model, we built a Resnet-based multi-flow network to learn the local information and the longitudinal information from the full chest sequence slice. To assist doctors in decision-making, the attention mechanism integrated into the network, which can locate the key slices and key parts from a full chest CT sequence of patients. We have systematically evaluated our method on the CT images of 1031 cases, including 420 COVID-19 cases, 311CAP cases, and 300 non-pneumonia cases. Our method could obtain an average accuracy of 82.3%, with 85.7% sensitivity and 86.4 % specificity, which outperformed previous works. © 2022 IEEE.
ABSTRACT
Bluetooth Low Energy (BLE) has become very common for tracking applications in homes, stadiums, malls, and hospitals over the last decade. With the outbreak of COVID, the technology was widely used for local tracking of the virus spread [1]. However, despite broad interest in using BLE as a tracker, the primary method is based on Received Signal Strength Indication (RSSI) measurements. On the other hand, the previous studies have demonstrated that this method is prone to multi-path and is inaccurate. With the introduction of BLE Direction Finding a shift in localization method has occurred. With the introduction of BEL direction finding, indoor tracking has come closer to its ultimate goal of asset tracking and positioning in crowded indoor environments. In this paper we present a new fast switching antenna array specifically designed for BLE direction finding. Using our newly designed antenna array and switch, we reached to accuracy of approximately 5° degrees. © 2022 IEEE.
ABSTRACT
Contact tracing is a key approach to control the spread of Covid-19 and any other pandemia. Recent attempts have followed either traditional ways of tracing (e.g. patient interviews) or unreliable app-based localization solutions. The latter has raised both privacy concerns and low precision in the contact inference. In this work, we present the idea of contact tracing through the multipath profile similarity. At first, we collect Channel State Information (CSI) traces from mobile devices, and then we estimate the multipath profile. We then show that positions that are close obtain similar multipath profiles, and only this information is shared outside the local network. This result can be applied for deploying a privacy-preserving contact tracing system for healthcare authorities. © 2022 Owner/Author.
ABSTRACT
The COVID-19 pandemic demanded innovative approaches to handle the situation around the globe. The Coronavirus challenged the effectiveness and practice of conventional surface disinfection methods. Existing disinfection methods rely on the manual administration of disinfectants. They are time-consuming, costly, and subject to human error. The paper proposes the implementation of an Ultraviolet Disinfection module that can be attached to any autonomous mobile robot. The autonomous Ultraviolet-C (UV-C) disinfection robot helps the user disinfect the premise without human intervention. The proposed system ensures proper disinfection by discovering near-optimal paths through the environment in minimum time. © 2022 IEEE.
ABSTRACT
Due to impact for Coronavirus, Automotive industry faced challenges from global supply chain. Localization and De-globalization topic become more and more important. Automotive component purchasing strategy will be focused on localization. Target to keep whole supply chain safety and reduce additional risk and cost. © 2022 IEEE.
ABSTRACT
Responding to crises leads to a shift in priorities and actions, with this affecting the achievement of longer-term strategic ambitions. This paper contributes to understandings of governing crises by exploring the tension between short-term crisis response and the achievement of longer-term policy goals, through the discussion of the Covid-19 pandemic and localised decarbonisation ambitions in Greater Manchester. Prior to the Covid-19 pandemic, Greater Manchester outlined ambitions to achieve carbon neutrality by 2038 through the use of a place-based approach. Greater Manchester has been subject to a range of lockdown restrictions throughout the pandemic, with all aspects of society being impacted including decarbonisation ambitions. Thus providing a useful case study for understanding the impact that Covid-19 has had on the development and implementation of Greater Manchester's decarbonisation ambitions. Within this focus is placed on the opportunities and constraints experienced. A total of 22 semi-structured interviews were conducted with stakeholders associated with Greater Manchester's decarbonisation ambitions between October 2020 and April 2021. Stakeholders interviewed included regional and local government, academics, community organisations, non-profit organisations and activist groups. Novel insights obtained through the stakeholder interviews highlight how Covid-19 has simultaneously constrained and provided opportunities for decarbonisation in Greater Manchester. Based upon the experiences of the stakeholders interviewed, 4 crises which have affected the achievement of longer-term decarbonisation ambitions have been identified - a communication crisis, an engagement crisis, a participation crisis and crises of temporality. The crises identified and discussed either emerged or intensified as a result of the Covid-19 pandemic. Although these crises are discussed in relation to the impact of Covid-19 on decarbonisation, the learnings identified can be applied to other crises and long-term strategic ambitions.
ABSTRACT
COVID-19 digital contact tracing applications for smartphones have become popular worldwide to reduce the effects of the pandemic. We considered that contact information between smartphones used in these applications can be used for the indoor localization of pedestrians. In this paper, we propose two indoor pedestrian localization methods based on contact information obtained from Bluetooth low energy (BLE) beacons installed in pedestrian's smartphones. Proposed method 1 is multilateration, and proposed method 2 solves a nonlinear optimization problem to further improve the accuracy of method 1. These two proposed methods comprise three steps: (1) the smartphones and anchor nodes recognize the proximity relationship with neighbor nodes using BLE signals transmitted from other smartphones and anchor nodes. The recognized proximity relationship is sent to a server. (2) The server estimates the distance between each node (smartphone or anchor node) from the proximity relationship. (3) The positions of smartphones are estimated based on the distance between nodes estimated by the server. We verified the localization accuracy of the proposed methods through simulation experiments. In an indoor area of 15 m × 30 m, the average localization error of the proposed method 2 was 0.74 m when the pedestrian density was 0.5 /m2. © 2022 IEEE.
ABSTRACT
The recent SARS-COV-2 virus, also known as COVID-19, badly affected the world’s healthcare system due to limited medical resources for a large number of infected human beings. Quarantine helps in breaking the spread of the virus for such communicable diseases. This work proposes a non-wearable/contactless system for human location and activity recognition using ubiquitous wireless signals. The proposed method utilizes the Channel State Information (CSI) of the wireless signals recorded through a low-cost device for estimating the location and activity of the person under quarantine. We propose to utilize a Siamese architecture with combined one-dimensional Convolutional Neural Networks (1D-CNN) and Bi-directional long-short term memory (Bi-LSTM) networks. The proposed method provides high accuracy for the joint task and is validated on two real-world testbeds. First, using the designed low-cost CSI recording hardware, and second, on a public dataset for joint activity and location estimation. The HAR results outperform state-of-the-art machine and deep learning methods, and localization results are comparable with the existing methods. IEEE
ABSTRACT
The COVID-19 crisis has prompted humanitarian actors to rethink their practices in order to achieve a broader localisation of humanitarian aid. This new approach aims to recentre actors from the global South within humanitarian practices. In this article, the authors draw on an intersectional feminist theoretical framework and on the analysis of documents focusing on the localisation of humanitarian aid to study how gender and various power differentials factor into the localisation of humanitarian aid. The results indicate that power differentials are often not taken into account in documentation on localisation. It is therefore essential to bring more inclusivity to this field.
ABSTRACT
While localization and decolonization are two of the current paradigms in the humanitarian field, we question the relevance of the universal SPHERE standards. The purpose of this article is to offer a reflection on the applications of these standards, on how they were received by humanitarian actors and on the tensions that emerge from both their application and their reception. We were able to identify three levels of percolation and resistance to SPHERE standards. Our results point to some inherent contradictions between standards and localization in the paradigm of decolonization of contents and underlying intents, recently intensified by the Covid-19 crisis. © 2022 Canadian Association for the Study of International Development (CASID).
ABSTRACT
Chest X-ray (CXR) images have a high potential in the monitoring and examination of various lung diseases, including COVID-19. However, the screening of a large number of patients with diagnostic hypothesis for COVID-19 poses a major challenge for physicians. In this paper, we propose a deep learning-based approach that can simultaneously suggest a diagnose and localize lung opacity areas in CXR images. We used a public dataset containing 5, 639 posteroanterior CXR images. Due to unbalanced classes (69.2% of the images are COVID-19 positive), data augmentation was applied only to images belonging to the normal category. We split the dataset into train and test sets with proportional rate at 90:10. To the classification task, we applied 5-fold cross-validation to the training set. The EfficientNetB4 architecture was used to perform this classification. We used a YOLOv5 pre-trained in COCO dataset to the detection task. Evaluations were based on accuracy and area under the ROC curve (AUROC) metrics to the classification task and mean average precision (mAP) to the detection task. The classification task achieved an average accuracy of 0.83 ± 0.01 (95% CI [0.81, 0.84]) and AUC of 0.88 ± 0.02 (95% CI [0.85, 0.89]) in 5-fold over the test dataset. The best result was reached in fold 3 (0.84 and 0.89 of accuracy and AUC, respectively). Positive results were evaluated by the opacity detector, which achieved a mAP of 59.51%. Thus, the good performance and rapid diagnostic prediction make the system a promising means to assist radiologists in decision making tasks. © 2022 SPIE.
ABSTRACT
Indoor localization has been, for the past decade, a subject under intense development. There is, however, no currently available solution that covers all possible scenarios. Received Signal Strength Indicator (RSSI) based methods, although the most widely researched, still suffer from problems due to environment noise. In this paper, we present a system using Bluetooth Low Energy (BLE) beacons attached to the desks to localize students in exam rooms and, at the same time, automatically register them for the given exam. By using Kalman Filters (KFs) and discretizing the location task, the presented solution is capable of achieving 100% accuracy within a distance of 45cm from the center of the desk. As the pandemic gets more controlled, with our lives slowly transitioning back to normal, there are still sanitary measures being applied. An example being the necessity to show a certification of vaccination or previous disease. Those certifications need to be manually checked for everyone entering the university's building, which requires time and staff. With that in mind, the automatic check for Covid certificates feature is also built into our system.
ABSTRACT
Deep learning has shown successful performance not only in supervised disease detection but also lesion localization under the weakly supervised learning framework with medical image processing. However, few consider the semantic relationship among the diseases and lesions which plays a critical role in actual clinical diagnosis. In this work, we propose a novel framework: Feature map Graph Representational Probabilistic Class Activation Map (FGR-PCAM) to learn the graph structure of lesion-specific features and consider these relationships while also leveraging the localization ability of PCAM. Considering the relations of localized lesion-specific features has been shown to enhance both thoracic diseases classification and localization tasks on CheXpert and ChestXray14 datasets. Accurate classification and localization of Chest X-ray images would also help us fight against the COVID-19 and unveil COVID-19 fingerprints. © 2022 SPIE