Mixup-Inf-Net: A data augmentation algorithm for segmentation of new coronary pneumonia infections

In 2020, the global spread of Coronavirus Disease 2019 exposed entire world to a severe health crisis. This has limited fast and accurate screening of suspected cases due to equipment shortages and and harsh testing environments. The current diagnosis of suspected cases has benefited greatly from the use of radiographic brain imaging, also including X-ray and scintigraphy, as a crucial addition to screening tests for new coronary pneumonia disease. However, it is impractical to gather enormous volumes of data quickly, which makes it difficult for depth models to be trained. To solve these problems, we obtained a new dataset by data augmentation Mixup method for the used chest CT slices. It uses lung infection segmentation (Inf-Net [1]) in a deep network and adds a learning framework with semi-supervised to form a Mixup-Inf-Net semi-supervised learning framework model to identify COVID-19 infection area from chest CT slices. The system depends primarily on unlabeled data and merely a minimal amount of annotated data is required;therefore, the unlabeled data generated by Mixup provides good assistance. Our framework can be used to improve improve learning and performance. The SemiSeg dataset and the actual 3D CT images that we produced are used in a variety of tests, and the analysis shows that Mixup-Inf-Net semi-supervised outperforms most SOTA segmentation models learning framework model in this study, which also enhances segmentation performance. © 2023 SPIE.

A New Machine Learning Framework for Detecting COVID-19 From Clinical Data on Lung And Heart Function

Currently, the need for real-time COVID-19 detection methods with minimal tools and cost is an important challenge. The available methods are still difficult to apply, slow, costly, and their accuracy is low. In this work, a novel machine learning-based framework to predict COVID-19 is proposed, which is based on rapid inpatient clinical tests of lung and heart function. Compared with current cognition therapy techniques, the proposed framework can significantly improve the accuracy and time performance of COVID-19 diagnosis without any lab or equipment requirements. In this work, five parameters of clinical testing were adopted;Respiration rate, Heart rate, systolic blood pressure, diastolic blood pressure, and mean arterial blood pressure. After obtaining results for these tests, a pre-trained intelligent model based on Random Forest Tree (RFT) machine learning algorithm is used for detection. This model was trained by about 13,558 records of the COVID19 testing dataset collected from King Faisal Specialist Hospital and Research Centre (KFSH&RC) in Saudi Arabia. Experiments have shown that the proposed framework performs highly in detecting COVID infections by 96.9%. Its results can be output in minutes, which supports clinical staff in screening COVID-19 patients from their inpatient clinical data. © 2022 IEEE.

An interpretable machine learning framework to understand bikeshare demand before and during the COVID-19 pandemic in New York City

In recent years, bikesharing systems have become increasingly popular as affordable and sustainable micromobility solutions. Advanced mathematical models such as machine learning are required to generate good forecasts for bikeshare demand. To this end, this study proposes a machine learning modeling framework to estimate hourly demand in a large-scale bikesharing system. Two Extreme Gradient Boosting models were developed: one using data from before the COVID-19 pandemic (March 2019 to February 2020) and the other using data from during the pandemic (March 2020 to February 2021). Furthermore, a model interpretation framework based on SHapley Additive exPlanations was implemented. Based on the relative importance of the explanatory variables considered in this study, share of female users and hour of day were the two most important explanatory variables in both models. However, the month variable had higher importance in the pandemic model than in the pre-pandemic model. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

Quarantine in Motion: A Graph Learning Framework to Reduce Disease Transmission Without Lockdown

Exposure notification applications are developed to increase the scale and speed of disease contact tracing. Indeed, by taking advantage of Bluetooth technology, they track the infected population's mobility and then inform close contacts to get tested. In this paper, we ask whether these applications can extend from reactive to preemptive risk management tools? To this end, we propose a new framework that utilizes graph neural networks (GNN) and real-world Foursquare mobility data to predict high risk locations on an hourly basis. As a proof of concept, we then simulate a risk-informed Foursquare population of over 36,000 people in Austin TX after the peak of an outbreak. We find that even after 50% of the population has been infected with COVID-19, they can still maintain their mobility, while reducing the new infections by 13%. Consequently, these results are a first step towards achieving what we call Quarantine in Motion. © 2022 IEEE.

A Novel Deep Learning Model For Hotel Demand and Revenue Prediction amid COVID-19

The COVID-19 pandemic has cast a substantial impact on the tourism and hospitality sector. Public policies such as travel restrictions and stay-at-home orders had significantly affected tourist activities and service businesses' operations and profitability. It is essential to develop interpretable forecasting models to support managerial and organizational decision-making. We developed DemandNet, a novel deep learning framework for predicting time series data under the influence of the COVID-19 pandemic. The DemandNet framework has the following unique characteristics. First, it selects the top static and dynamic features embedded in the time series data. Second, it includes a nonlinear model which can provide interpretable insight into the previously seen data. Third, a novel prediction model is developed to leverage the above characteristics to make robust long-term forecasts. We evaluated DemandNet using daily hotel demand and revenue data from eight cities in the US between 2013 and 2020. Our findings reveal that DemandNet outperforms the state-of-art models and can accurately predict the effect of the COVID-19 pandemic on hotel demand and revenue. © 2022 IEEE Computer Society. All rights reserved.

Generalizable Segmentation of COVID-19 Infection From Multi-Site Tomography Scans: A Federated Learning Framework

COVID-19-like pandemics are a major threat to the global health system that causes a lot of deaths across ages. Large-scale medical images (i.e., X-rays, computed tomography (CT)) dataset is favored to the accuracy of deep learning (DL) in the screening of COVID-19-like pneumonia. The cost, time, and efforts for acquiring and annotating, for instance, large CT datasets make it impossible to obtain large numbers of samples from a single institution. The research attentions have been moved toward sharing medical images from numerous medical institutions. However, owing to the necessity to preserve the privacy of the data of a patient, it is challenging to build a centralized dataset from many institutions, especially during the pandemic. More. The difference in the data acquisition process from one institution to another brings another challenge known as distribution heterogeneity. This paper presents a novel federated learning framework, called Federated Multi-Site COVID-19 (FEDMSCOV), for efficient, generalizable, and privacy-preserved segmentation of COVID-19 infection from multi-site data. In FEDMSCOV, a novel is local drift smoothing (LDS) module encodes the input from feature space to frequency space, aiming to suppress the modules that are not conducive to generalization. Given the smoothed local updated, FEDMSCOV presents a novel Mixture-of-Expert (MoE) scheme to resolve global shift in parameters. An adapted differential privacy method is applied to design and protect the privacy of local updates during the training. Experimental evaluation on a large-scale multi-institutional COVID-19 dataset demonstrated the efficiency of the proposed framework over competing learning approaches with statistical significance. IEEE

Identifying Targeted and Generalized Offensive Speech from Anti-asian Social Media Conversations

During the Covid-19 pandemic Asian-Americans have been targets of prejudice and negative stereotyping. There has also been volumes of counter speech condemning this jaundiced attitude. Ironically, however, the dialogue on both sides is filled with offensive and abusive language. While abusive language directed at Asians encourages violence and hate crimes against this ethnic group, the use of derogatory language to insult alternative points of view showcases utter lack of respect and exploits people's fears to stir up social tensions. It is thus important to identify and demote both types of offensive content from anti-Asian social media conversations. The goal of this paper is to present a machine learning framework that can achieve the dual objective of detecting targeted anti-Asian bigotry as well as generalized offensive content. Tweets were collected using the hashtag #chinavirus. Each tweet was annotated in two ways;either it condemned or condoned anti-Asian bias, and whether it was offensive or non-offensive. A rich set of features both from the text and accompanying numerical data were extracted. These features were used to train conventional machine learning and deep learning models. Our results show that the Random Forest classifier can detect both generalized and targeted offensive content with around 0.88 accuracy and F1-score. Our results are promising from two perspectives. First, our approach outperforms contemporary efforts on detecting online abuse against Asian-Americans. Second, our unified approach detects both offensive speech targeted specifically at Asian-Americans and also identifies its generalized form which has the potential to mobilize a large number of people in socially challenging situations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Detecting Drift in Healthcare AI Models Based on Data Availability

There is an increasing interest in the use of AI in healthcare due to its potential for diagnosis or disease prediction. However, healthcare data is not static and is likely to change over time leading a non-adaptive model to poor decision-making. The need of a drift detector in the overall learning framework is therefore essential to guarantee reliable products on the market. Most drift detection algorithms consider that ground truth labels are available immediately after prediction since these methods often work by monitoring the model performance. However, especially in real-world clinical contexts, this is not always the case as collecting labels is often more time consuming as requiring experts' input. This paper investigates methodologies to address drift detection depending on which information is available during the monitoring process. We explore the topic within a regulatory standpoint, showing challenges and approaches to monitoring algorithms in healthcare with subsequent batch updates of data. This paper explores three different aspects of drift detection: drift based on performance (when labels are available), drift based on model structure (indicating causes of drift) and drift based on change in underlying data characteristics (distribution and correlation) when labels are not available. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

On the Design of Communication-Efficient Federated Learning for Health Monitoring

With the booming deployment of Internet of Things, health monitoring applications have gradually prospered. Within the recent COVID-19 pandemic situation, interest in permanent remote health monitoring solutions has raised, targeting to reduce contact and preserve the limited medical resources. Among the technological methods to realize efficient remote health monitoring, federated learning (FL) has drawn particular attention due to its robustness in preserving data privacy. However, FL can yield to high communication costs, due to frequent transmissions between the FL server and clients. To tackle this problem, we propose in this paper a communication-efficient federated learning (CEFL) framework that involves clients clustering and transfer learning. First, we propose to group clients through the calculation of similarity factors, based on the neural networks characteristics. Then, a representative client in each cluster is selected to be the leader of the cluster. Differently from the conventional FL, our method performs FL training only among the cluster leaders. Subsequently, transfer learning is adopted by the leader to update its cluster members with the trained FL model. Finally, each member fine-tunes the received model with its own data. To further reduce the communication costs, we opt for a partial-layer FL aggregation approach. This method suggests partially updating the neural network model rather than fully. Through experiments, we show that CEFL can save up to to 98.45% in communication costs while conceding less than 3% in accuracy loss, when compared to the conventional FL. Finally, CEFL demonstrates a high accuracy for clients with small or unbalanced datasets. © 2022 IEEE.

SmartTensors: Unsupervised and Physics-informed Machine Learning Framework for the Geoscience Applications

SmartTensors (https://github.com/SmartTensors) is a novel framework for unsupervised and physics-informed machine learning for geoscience applications. The methods in SmartTensors AI platform are developed using advanced matrix/tensor factorization constrained by penalties enforcing robustness and interpretability (e.g., nonnegativity, sparsity, physics, and mathematical constraints;etc.). This framework has been applied to analyze diverse datasets related to a wide range of problems: from COVID-19 to wildfires and climate. Here, we will focus on the analysis of geothermal prospectivity of the Great Basin, U.S. The basin covers a vast area that is yet to be thoroughly explored to discover new geothermal resources. The available regional geochemical data are expected to provide critical information about the geothermal reservoir properties in the basin, including temperature, fluid/heat flow, boundary conditions, and spatial extent. The geochemical data may also include hidden (latent) information that is a proxy for geothermal prospectivity. We processed the sparse geochemical dataset of 18 geochemical attributes observed at 14,341 locations. The data are analyzed using our GeoThermalCloud toolbox for geothermal exploration (https://github.com/SmartTensors/GeoThermalCloud.jl) whichis also a part of the SmartTensors framework. An unsupervised machine learning using non-negative matrix factorization with customized k-means clustering (NMFk) as implemented in SmartTensors identified three hidden geothermal signatures representing low-, medium-, and high-temperature reservoirs, respectively (Fig). NMFk also evaluated the probability of occurrence of these types of resources through the studied region. NMFk also reconstructed attributes from sparse into continuous over the study domain. Future work will add in the ML analyses other regional- and site-scale datasets including geological, geophysical, and geothermal attributes. © 2022 Society of Exploration Geophysicists and the American Association of Petroleum Geologists.

Hybrid individualized assistance-oriented learning system framework for STEM-Education

The imparting of knowledge and skills in STEM education, especially under the influence of the Covid-19 pandemic, is increasingly taking place online and through digital formats. The partially asynchronous instruction eliminates, on the one hand, the social relation in the learning process and, on the other hand, the direct experience with physical objects. Here, the digital learning systems provide learning tools and controls to support the learning process on a general basis. Existing methods for simulating physical objects (digital twins) are also used to a minimal extent. The following approach presents a learning system framework that enables individualized learning, including all dimensions (social, physical). Implementing a concept that uses a personalized assistance system to orchestrate the individual learning steps enables efficient and effective learning. Applying the learning system framework exemplifies the STEM education at Reutlingen University in the logistics learning factory Werk150. © 2022 IEEE.

A Machine Learning framework for Covid Detection Using Cough Sounds

The present COVID-19 diagnosis necessitates direct patient interaction, involves variable duration to get outcomes, and is costly. In certain poor nations, this is even unreachable to the populace at large, leading to a shortage of medical care. Therefore, a moderate, rapid, but also readily available method for the diagnosis of COVID-19 is essential. Several initiatives have been made to use smartphone-collected sounds and coughs to build machine learning algorithms that can categories and discriminate COVID-19 sounds with healthy tissue. The majority of prior studies used sounds like breathing or coughing to train their analyzers as well as get impressive outcomes. In order to carry out this significant investigation, we used this Coswara dataset, which contains recordings of nine distinct sound varieties of the COVID-19 state of cough, breathing, and speech. COVID-19 could be diagnosed more accurately using trained models on a variety of audio instead of a specific model trained on cough alone. This work examines the potential prospect of using machine learning techniques to enhance the identification of COVID-19 in such an initial and non-invasive manner through the monitoring of audio sounds. The XGBoost outperforms existing benchmark classification algorithms and achieves 92% accuracy with all sounds. Vowel/e/sound random forest with 98.36% was determined to be among the most effective, and the vowel/e/can also evaluated for the purpose of detecting compared to the other vowels;the impact of COVID-19 on sound quality is more precise. © 2022 IEEE.

PhysioVec: A Multi-stage Deep-Learning Framework for Searching Online Health Information with Breath Sound

The COVID-19 outbreak presents a major challenge in diagnosing and monitoring respiratory diseases. IoT has the potential to address the challenges by remotely providing patients with rich information about respiratory health. However, current IoT-based health monitoring systems do not provide users with sufficient information to access the rich information in Health Social Network (HSN). We developed PhysioVec, a framework for searching HSN using breath sounds. PhysioVec consists of three components: Local Recurrent Transformer (LRT), a Multivariate radial-basis Logistic Interpreter (MLI), and an existing sentence embedding module. LRT combines local attention and recurrent Transformer to reduce overfitting and improve performance in the segmentation of breathing sounds. Physiological information detected from breathing sounds is used to search for relevant health information. PhysioVec achieved 100%., 59.8%., 92.2%., and 100% precision in the top one search results for breath sound with the common cold, influenza, pneumonia, and bronchitis, respectively. Our proposed framework allows users to search HSN for useful information just by recording their breathing sounds on mobile phones. © 2022 IEEE.

A Survey Investigating the Key Factors and Theoretical E-Learning Frameworks During Crisis Periods

In the previous ten years, there has been an astounding expansion in the study and application of e-learning frameworks. The recent literature and e-learning ideas were investigated in this study, with e-learning research's different parameters being précised. E-learning processes' associated services, technology, as well as stakeholders, are the three principal aspects of e-learning systems. A typology of services comprising e-learning models is presented in a framework, with stakeholders, technology, and learning approaches being included. Accordingly, the aforementioned aspects are considered through a detailed literature review, with e-learning frameworks' relationship with the different classified stakeholder groups also clarified. Finally, ways to resolve the foremost challenges identified through the literature review are posed, with our e-learning system also presented. Furthermore, the proposed answer may direct and facilitate the appropriate appraisal of learners, educators, and educational facilities by decision-makers, drawing on data provided through live interaction.

StyleTrendGAN: A Deep Learning Generative Framework for Fashion Bag Generation

Dealing with fashion multimedia big data with Artificial Intelligence (AI) algorithms has become an appealing challenge for computer scientists, since it can serve as inspiration for fashion designers and can also allow to predict the next trendy items in the fashion industry. Moreover, with the global spread of COVID-19 pandemic, social media contents have achieved an increasingly crucial factor in driving retail purchase decisions, thus it has become mandatory for fashion brand analysing social media pictures. In this light, this paper aims at presenting StyleTrendGAN, a novel custom deep learning framework that has the ability to generate fashion items. StyleTrendGAN combines a Dense Extreme Inception Network (DexiNed) for sketches extraction and Pix2Pix for the transformation of the input sketches into the new handbag models. StyleTrendGAN increases the efficiency and accuracy of the creation of new fashion models compared to previous ones and to the classic human approach;it aims to stimulate the creativity of designers and the visualization of the results of a production process without actually putting it into practice. The approach was applied and tested on a newly collected dataset, “MADAME” (iMage fAshion Dataset sociAl MEdia) of images collected from Instagram. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the proposed approach. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Deep Learning Framework for the Classification of Lung Diseases Using Chest X-Ray Images

Automated screening and classification of various lesions in medical images can assist clinicians in the treatment and management of many systemic and localized diseases. Manual inspection of medical images is often expensive and time-consuming. Automatic image-analysis employing computers can alleviate the difficulties of manual methods for screening a large amount of generated images. Inspired by the great success of deep learning, we propose a diagnostic system that can classify various lung diseases from chest X-ray images. In this work, chest X-ray images are applied to a deep-learning algorithm for classifying images into pneumothorax, viral pneumonia, COVID-19 pneumonia and healthy cases. The proposed system is trained with a set of 4731 chest X-ray images, and obtained an overall classification accuracy of 99% in images taken from two publicly available data sets. The promising results demonstrate the proposed system’s effectiveness as a diagnostic tool to assist health care professionals for categorizing images in any of the four classes. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Multi-modal Auditory-Visual-Tactile e-Learning Framework

With a high number of countries closing learning institutions due to the restrictions in response to the COVID-19 pandemic, over 80% of the world’s students was not attending school. As a response to this challenge, many educational institutions are increasing their efforts to utilise various educational technologies and provide remote learning opportunities. One of the biggest drawbacks of the majority of these existing solutions is limited support for hands-on laboratory work and practical experiences. This is especially relevant to science, technology, engineering, and mathematics (STEM) departments, which must continuously develop their laboratories and pedagogical tools to provide their students with effective study plans. To facilitate a safe, digital access to laboratories, a novel haptic-enabled framework for hands-on e-Learning is introduced in this work. The framework enables a fully-immersive tactile, auditory, and visual experience. This is achieved by combining virtual reality (VR) tools, with a novel wearable haptic device, which is designed by augmenting a low-cost commercial off-the-shelf (COTS) controller with vibrotactile actuators. For this purpose, the Unity game engine and the Valve Knuckles EV3 controllers are adopted. To demonstrate the potential of the proposed framework, a human subject study is presented. Results suggest that the proposed haptic-enabled framework improves the student engagement and illusion of presence. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

An Efficient Deep Learning Framework for Face Mask Detection in Complex Scenes

COVID-19 has caused a global health crisis that has infected millions of people across the globe. Currently, the fourth wave of COVID-19 is about to be declared as Omicron. The new variant of COVID-19 has caused an unprecedented increase in cases. According to World Health Organization, safety measures must be adopted in public places to prevent the spread of the virus. One effective safety measure is to wear face masks in crowded places. To create a safe environment, government agencies adopt strict rules to ensure adherence to safety measures. However, it is difficult to manually analyze the crowded scenes and identify people violating the safety measures. This paper proposed an automated approach based on a deep learning framework that automatically analyses the complex scenes and identifies people with face masks or without facemasks. The proposed framework consists of two sequential parts. In the first part, we generate scale aware proposal to cover scale variations, and in the second part, the framework classifies each proposal. We evaluate the performance of the proposed framework on a challenging benchmark data set. We demonstrate that the proposed framework achieves high performance and outperforms other reference methods by a considerable margin from experimental results. © 2022, IFIP International Federation for Information Processing.

The Distance Learning Framework for Design-Related Didactic Based on Cognitive Immersive Experience

This research is considered as the transformation of cognitive immersion based on the theory by Liu et al. (2021), to describe the possibilities of immersive learning by distance teaching tools. It provides insights among the importance of distance learning for design education, especially under specific situations such as COVID-19 pandemic. The tools to support distance learning are categorized and discussed, degrees of immersion are compared among formal learning, informal learning and social learning courseware. The methods rely on an extensive secondary research and literature review, aims to transform the theoretical framework of cognitive immersive learning by online-based tools, also provide new thoughts for innovatively teaching design in the future. As the output, we establish a theoretical model based on online tools, also a design framework to help with course design or idea visualization for instructors. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

COVID-19 diagnosis with convolution neural networks using CT images

As COVID-19 has spread worldwide, detecting the patients of COVID-19 and taking effective actions has gained more and more importance. Applying a deep learning framework to detect medical pictures has already been used for years. This paper mainly trained a large number of CT images of patients and normal people on three networks: AlexNet, VGG, and ResNet. Based on PyTorch, we build the network successfully and soon examine the performance of the three networks on the test and validation dataset. Our experiments demonstrate that the ResNet performs the best when detecting the COVID-19 CT images. It reaches the accuracy of 99.5%, which proves that it has a strong fitting ability in our dataset, which is not so large. However, when applying the pre-Trained model from the bigger dataset in a smaller dataset, the accuracy of AlexNet and VGGNet will increase accordingly while the accuracy of ResNet decreases. Though we have made many assumptions about the phenomenon, more experiments are needed after the experiment. © COPYRIGHT SPIE.