ABSTRACT
In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection. Our fact-checking module, which is supported by novel natural language inference methods with a self-attention network, outperforms state-of-the-art approaches. It is also able to give automated veracity assessment and ranked supporting evidence with the stance towards the claim to be checked. In addition, PANACEA adapts the bi-directional graph convolutional networks model, which is able to detect rumours based on comment networks of related tweets, instead of relying on the knowledge base. This rumour detection module assists by warning the users in the early stages when a knowledge base may not be available. © 2023 Association for Computational Linguistics.
ABSTRACT
The coronavirus disease 2019 (COVID-19) epidemic has spread worldwide and the healthcare system is in crisis. Accurate, automated and rapid segmentation of COVID-19 lesion in computed tomography (CT) images can help doctors diagnose and provide prognostic information. However, the variety of lesions and small regions of early lesion complicate their segmentation. To solve these problems, we propose a new SAUNet++ model with squeeze excitation residual (SER) module and atrous spatial pyramid pooling (ASPP) module. The SER module can assign more weights to more important channels and mitigate the problem of gradient disappearance;the ASPP module can obtain context information by atrous convolution using various sampling rates. In addition, the generalized dice loss (GDL) can reduce the correlation between lesion size and dice loss, and is introduced to solve the problem of small regions segmentation of COVID-19 lesion. We collected multinational CT scan data from China, Italy and Russia and conducted extensive comparative and ablation studies. The experimental results demonstrated that our method outperforms state-of-the-art models and can effectively improve the accuracy of COVID-19 lesion segmentation on the dice similarity coefficient (our: 87.38% vs. U-Net++: 84.25%), sensitivity (our: 93.28% vs. U-Net++: 89.85%) and Hausdorff distance (our: 19.99 mm vs. U-Net++: 26.79 mm), respectively.
ABSTRACT
Mangrove tourism is one of the tourist destinations offered by tourism managers that is currently gaining popularity and popularity among tourists. Keeping tourists coming back can be a very effective strategy for developing tourist destinations. This study employs Experiential Marketing as a strategy to increase tourist interest. Because research in the field of experiential marketing in nature tourism destinations such as mangrove tourism is still limited, the topics of this study are experiential marketing and visitor visit intention. The purpose of this study was to determine the impact of strategic experiential modules (SEMs) on visitor revisits intention. The research method used is quantitative with the variable dimensions of SEMs and visitor revisits intention, a sample of 93 tourists with a purposive sampling technique, and multiple linear regression analysis techniques. The results showed that the sense, act, and relate variables had a positive and significant impact on the visitor revisits intention, while the feel variable had a positive but not significant impact, and the think variable had a negative but not significant impact on the visitor revisits intention.
ABSTRACT
With the COVID-19 outbreak in 2019, the world is facing a major crisis and people's health is at serious risk. Accurate segmentation of lesions in CT images can help doctors understand disease infections, prescribe the right medicine and control patients' conditions. Fast and accurate diagnosis not only can make the limited medical resources get reasonable allocation, but also can control the spread of disease, and computer-aided diagnosis can achieve this purpose, so this paper proposes a deep learning segmentation network LLDSNet based on a small amount of data, which is divided into two modules: contextual feature-aware module (CFAM) and shape edge detection module (SEDM). Due to the different morphology of lesions in different CT, lesions with dispersion, small lesion area and background area imbalance, lesion area and normal area boundary blurred, etc. The problem of lesion segmentation in COVID-19 poses a major challenge. The CFAM can effectively extract the overall and local features, and the SEDM can accurately find the edges of the lesion area to segment the lesions in this area. The hybrid loss function is used to avoid the class imbalance problem and improve the overall network performance. It is demonstrated that LLDSNet dice achieves 0.696 for a small number of data sets, and the best performance compared to five currently popular segmentation networks. © 2023 SPIE.
ABSTRACT
One of the most significant problems in industrial processes is the loss of energy according to the sort of heat. Thermoelectrics are a promising alternative to recovering this type of thermal energy, as they can convert heat into electricity, improving the industrial efficiency of the process. This article presents the characteristics of low-cost thermoelectric modules typically used for generation (SP1848-27145SA (TEG-GEN)) and refrigeration (TEC1-12706 (TEC-REF)), both utilized in this research for heat recovery. The modules were evaluated against various configurations, source distances, and distributed systems in order to determine optimal recovery conditions. The experiments were conducted both at the laboratory level and in a large-scale furnace of the traditional ceramics industry, and they revealed that even refrigeration modules are suitable for energy recovery, particularly in developing countries, whereas other generators are more expensive and difficult to obtain. These thermoelectric generators were tested for low-temperature heat recovery in regular furnaces, and the results are to be implemented elsewhere. Results show that even the thermoelectric refrigeration modules can be a solution for heat recovery in many heat sources, which would be particularly strategic for developing countries.
ABSTRACT
With the appearance of the COVID-19 pandemic, the practice of e-learning in the cloud makes it possible to: avoid the problem of overloading the institutions infrastructure resources, manage a large number of learners and improve collaboration and synchronous learning. In this paper, we propose a new e-leaning process management approach in cloud named CLP-in-Cloud (for Collaborative Learning Process in Cloud). CLP-in-Cloud is composed of two steps: i) design general, configurable and multi-tenant e-Learning Process as a Service (LPaaS) that meets different needs of institutions. ii) to fulfill the user needs, developpe a functional and non-functional awareness LPaaS discovery module. For functional needs, we adopt the algorithm A* and for non-functional needs we adopt a linear programming algorithm. Our developed system allows learners to discover and search their preferred configurable learning process in a multi-tenancy Cloud architecture. In order to help to discover interesting process, we come up with a recommendation module. Experimentations proved that our system is effective in reducing the execution time and in finding appropriate results for the user request.
ABSTRACT
Memes can be a useful way to spread information because they are funny, easy to share, and can spread quickly and reach further than other forms. With increased interest in COVID-19 vaccines, vaccination-related memes have grown in number and reach. Memes analysis can be difficult because they use sarcasm and often require contextual understanding. Previous research has shown promising results but could be improved by capturing global and local representations within memes to model contextual information. Further, the limited public availability of annotated vaccine critical memes datasets limit our ability to design computational methods to help design targeted interventions and boost vaccine uptake. To address these gaps, we present VaxMeme, which consists of 10,244 manually labelled memes. With VaxMeme, we propose a new multimodal framework designed to improve the memes' representation by learning the global and local representations of memes. The improved memes' representations are then fed to an attentive representation learning module to capture contextual information for classification using an optimised loss function. Experimental results show that our framework outperformed state-of-the-art methods with an F1-Score of 84.2%. We further analyse the transferability and generalisability of our framework and show that understanding both modalities is important to identify vaccine critical memes on Twitter. Finally, we discuss how understanding memes can be useful in designing shareable vaccination promotion, myth debunking memes and monitoring their uptake on social media platforms. © 2023 ACM.
ABSTRACT
This paper discusses the design and implementation of an Internet of Things (IoT)-based telemedicine health monitoring system (THMS) with an early warning scoring (EWS) function that reads, assesses, and logs physiological parameters of a patient such as body temperature, oxygen saturation level, systemic arterial pressure, breathing patterns, pulse (heart) rate, supplemental oxygen dependency, consciousness, and pain level using Particle Photon microcontrollers interfaced with biosensors and switches. The Mandami fuzzy inference-based medical decision support system (FI-MDSS) was also developed using MATLAB to assist medical professionals in evaluating a patient's health risk and deciding on the appropriate clinical intervention. The patient's physiological measurements, EWS, and health risk category are stored on the Particle cloud and Thing Speak cloud platforms and can be accessed remotely and in real-time via the Internet. Furthermore, a RESTful application programming interface (API) was developed using GO language and PostgreSQL database to enhance data presentation and accessibility. Based on the paired samples t-tests obtained from 6 sessions with 10 trials for each vital sign per session, there were no significant differences between the clinical data obtained from the designed prototype and the commercially sold medical equipment. The mean differences between the compared samples for each physiological data were not more than 0.40, the standard deviations were less than 2.3, and the p-values were greater than 0.05. With a 96.67% accuracy, the FI-MDSS predicted health risk levels that were comparable to conventional EWS techniques such as the Modified National Early Warning Score (m-NEWS) and NEWS2, which are used in the clinical decision-making process for managing patients with COVID-19 and other infectious illnesses. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
The structural analysis module is a challenge for both teachers and students. The module content is usually presented to students in the form of a set of equations when solved, the structure of internal forces is obtained. Usually, the assignments adopted in such modules are paper‐based exams. Such a strategy may assess the capacity of the students to employ different sets of equations to solve a problem. However, this is not enough for a vivid educational atmosphere. Transforming these equations into a digital simulation is the best solution for the education process. Digitalization is more appealing to nowadays students and it gives the teacher a wide spectrum of discussions without the hindrance of calculations time. It is also a mitigation for the online teaching process during the Covid‐19 pandemic. This paper presents a digital simulation of different structures using a simple tool that enables students to visualize the simultaneous interaction between geometry, loading, boundary conditions, and internal forces. Furthermore, transforming this tool into an offline mobile app helps both the teacher and the student to gamify the investigation of any structure.
ABSTRACT
The aim of camouflaged object detection (COD) is to find objects that are hidden in their surrounding environment. Due to the factors like low illumination, occlusion, small size and high similarity to the background, COD is recognized to be a very challenging task. In this paper, we propose a general COD framework, termed as MSCAF-Net, focusing on learning multi-scale context-aware features. To achieve this target, we first adopt the improved Pyramid Vision Transformer (PVTv2) model as the backbone to extract global contextual information at multiple scales. An enhanced receptive field (ERF) module is then designed to refine the features at each scale. Further, a cross-scale feature fusion (CSFF) module is introduced to achieve sufficient interaction of multi-scale information, aiming to enrich the scale diversity of extracted features. In addition, inspired the mechanism of the human visual system, a dense interactive decoder (DID) module is devised to output a rough localization map, which is used to modulate the fused features obtained in the CSFF module for more accurate detection. The effectiveness of our MSCAF-Net is validated on four benchmark datasets. The results show that the proposed method significantly outperforms state-of-the-art (SOTA) COD models by a large margin. Besides, we also investigate the potential of our MSCAF-Net on some other vision tasks that are highly related to COD, such as polyp segmentation, COVID-19 lung infection segmentation, transparent object detection and defect detection. Experimental results demonstrate the high versatility of the proposed MSCAF-Net. The source code and results of our method are available at https://github.com/yuliu316316/MSCAF-COD. IEEE
ABSTRACT
A new wave of the Covid-19 pandemic struck Hong Kong in February 2022. It led to construction of a temporary 1000-bed hospital and 10 000-bed isolation and treatment facility on an island site in just 51 days using factory-made modules. To achieve such rapid construction, module assembly was carried out at a separate site between the factories and site. Several new modular construction technologies were also developed, including adjustable base supports, large-span roof modules, universal safety barriers and an intelligent cloud platform for construction management. But to enable sustainable construction of such emergency buildings in future, further studies on demolition, recycling and relocation of modular buildings need to be carried out in the post-pandemic era.
ABSTRACT
Chemistry simulations using interactive graphic user interfaces (GUIs) represent uniquely effective and safe tools to support multidimensional learning. Computer literacy and coding skills have become increasingly important in the chemical sciences. In response to both of these facts, a series of Jupyter notebooks hosted on Google Colaboratory were developed for undergraduate students enrolled in physical chemistry. These modules were developed for use during the COVID-19 pandemic when Millsaps College courses were virtual and only virtual or online laboratories could be used. These interactive exercises employ the Python programming language to explore a variety of chemical problems related to kinetics, the Maxwell–Boltzmann distribution, numerical versus analytical solutions, and real-world application of concepts. All of the modules are available for download from GitHub (https://github.com/Abravene/Python-Notebooks-for-Physical-Chemistry). Accessibility was prioritized, and students were assumed to have no prior programming experience;the notebooks are cost-free and browser-based. Students were guided to use widgets to build interactive GUIs that provide dynamic representations, immediate access to multiple investigations, and interaction with key variables. To evaluate the perceived effectiveness of this introduction to Python programming, participants were surveyed at the beginning and end of the course to gauge their interest in pursuing programming and data analysis skills and how they viewed the importance of programming and data analysis for their future careers. Student reactions were generally positive and showed increased interest in programming and its importance in their futures, so these notebooks will be incorporated into the in-person laboratory in the future.
ABSTRACT
Together with the general health care, the training classes in Physical Culture and Sports for non-majors should focus on personal self-fulfillment thorough various forms of physical culture and sports. This has always been in the universities' academic plans, and the current State Educational Standard (3++), which provides with 400 academic hours for Physical Culture and Sports, is not an exception. These days, the outdoor classes for students are more relevant than ever against the background of the ongoing COVID-19 and restrictive social and sanitary measures (social distance). This work presents a module-base program and methodological support of teaching within the framework of Physical Culture and Sports discipline, including ski training, orienteering and general physical training. Each training module, which includes 8–13 comprehensive classes, is designed to implement an independent part of educational material following specific natural and climatic conditions. Its usefulness is tested through a pedagogical experiment on the students of Polytechnic School, Siberian Federal University. © Siberian Federal University. All rights reserved.
ABSTRACT
In this paper, stress data collection and analysis using 'Mind Scale™' is proposed. A fingertip pulse wave sensor module is utilized along a smartphone application. Biological signals such as pulse, voice and facial expression are analyzed with questionnaire and managed in the cloud. With the post-covid world, this system helps us to detect our mental health condition for new lifestyle. © 2023 IEEE.
ABSTRACT
Epidemic forecasting is the key to effective control of epidemic transmission and helps the world mitigate the crisis that threatens public health. To better understand the transmission and evolution of epidemics, we propose EpiGNN, a graph neural network-based model for epidemic forecasting. Specifically, we design a transmission risk encoding module to characterize local and global spatial effects of regions in epidemic processes and incorporate them into the model. Meanwhile, we develop a Region-Aware Graph Learner (RAGL) that takes transmission risk, geographical dependencies, and temporal information into account to better explore spatial-temporal dependencies and makes regions aware of related regions' epidemic situations. The RAGL can also combine with external resources, such as human mobility, to further improve prediction performance. Comprehensive experiments on five real-world epidemic-related datasets (including influenza and COVID-19) demonstrate the effectiveness of our proposed method and show that EpiGNN outperforms state-of-the-art baselines by 9.48% in RMSE. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Amid and post-COVID-19 pandemic, the matter of being in touch with patients to monitor their health matrices became somewhat challenging, especially in the rural areas of countries like Bangladesh and for elderlies. To address this issue, a patient health monitoring system is developed using a Programmable Intelligent Computer (PIC) microcontroller and Global System for Mobile Communications (GSM) protocol with the help of a pulse sensor, IR sensor, photodiodes, temperature sensor, etc., to measure 3 (three) crucial health matrices such as heartbeat/pulse, oxygen saturation level, and body temperature from a fingertip of the patient in 20 s remotely. Whenever the system measures the health matrices, it sends a short message service (SMS) report to a personal caretaker over GSM automatically. If the system finds any anomaly based on predefined threshold levels for each health parameter, it sends a SMS alert report to the designated doctor automatically as well. A prototype of the developed system is made, verified, and tested to be working perfectly as designed and programmed. In the experiment with the developed system, heart rate ranged from 61 to 105 bmp, body temperature ranged from 95.3 to 99.1 ℉, and oxygen saturation was minimum at 97%. According to the set threshold levels, which led to an automatic SMS alert to the caretaker's mobile phone. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
Online teaching has globally become a part of the learning process and has been more well-established in developed countries. In developing countries, online teaching or e-Learning is not practiced or recognized officially by educational organizations and policymakers. On the other hand, it is well-known that computers and technology are the future; in such a case, the advancement of distance-learning or online learning is immensely remarkable. It has reduced teachers' and students' introversion concerning e-learning and technology and has provided a platform for learning new technologies and developing new skills. The recent COVID-19 lockdown impelled governments to start implementing E-learning in schools, which resulted in several challenges. This study attempts to analyze and interpret the challenges and potentials of implementing online learning by surveying through an online questionnaire using 'Google Forms' (N = 968) with responses from high school and primary school English teachers during the first week of March through the last week of April. The findings revealed that most teachers had negative perceptions of implementing e-learning for several reasons, including lack of essential facilities such as electricity, electronic devices, and the absence of required skills. The actual contributions of students and educators are also among the major obstacles. This research suggests introducing Information Communication Technology modules across media platforms and applications in the education departments, opening intensive courses for teachers, and developing educational facilities in the education departments and schools to overcome these limitations and challenges.
ABSTRACT
As a result of the lack of access to hospitals for medical students during the COVID-19 pandemics, a web-based platform is being developed in partnership between the Carol Davila University of Medicine and Pharmacy in Bucharest and the University Politehnica of Bucharest. The platform allows medical students to simulate their interactions with patients that would typically occur on a daily basis in hospitals and to receive feedback around their performances from their professors on real time or afterwards. The platform has been evaluated during different stages of implementation by different groups of students. During these evaluations, the students needed some help/support that was provided through email or Skype. Therefore, a support module that would facilitate the help/support process during the future evaluations was developed and integrated in the platform. © 2022 IEEE.
ABSTRACT
The process of making changes to software after it has been delivered to the client is known as maintainability. Maintainability deals with new or changed client requirements. Service-oriented architecture (SOA) is a method for developing applications that helps services work on different environments. SOA works on patterns of distributed systems that help different applications communicate with each other using different protocols. To assess the maintainability of service-oriented architecture, different factors are required. Some of these factors are analyzability, changeability, stability, and testability. Modification is the process of upgrading the software functionality. After modification of service-oriented architecture, the module will go to the testing phase. The evaluation and verification of whether a software product or application performs as intended is known as testing. The testing phase is a combination of various stages, such as individual module testing and testing after collaborations between them. This testing stage is time-consuming in the maintenance process. The term "outlier" refers to a module in software systems that deviates significantly from the rest of the module. It represents the collection of data, variables, and methods. For instance, the program might have been coded mistakenly or an investigation might not have been run accurately. To detect the outlier module, test cases are needed. A methodology is proposed to reduce the predefined test cases. K-means clustering is the best approach to calculate the number of test cases, but the outlier is not automatically determined. In this paper, a hybrid clustering approach is applied to detect the outlier. This clustering method is used in software testing to count the number of comments in various software and in medical science to diagnose the disease of Covid patients. The experimental outcomes show that our strategy achieves better results.
ABSTRACT
The discourse around online summative assessment has become one of the major issues in open distance learning (ODL) worldwide. There is a lack of major research in online summative assessment in environmental education (EE) module for the bachelor of education (B.Ed.) students in ODL. The purpose of this study was to explore online summative assessment of EE module for the B.Ed. students at the University of South Africa (UNISA) during COVID-19. This study employed a qualitative approach, purposive sampling, and an interpretive paradigm. Data were ethically collected using participant observation and documentation. It was thematically analysed. Online summative assessment policies were in place before the outbreak of COVID-19, but policies were not implemented. The university quickly transitioned from face-to-face to online summative assessment due to the COVID-19 pandemic, and lecturers were trained. Challenges included non-training of students for online summative assessment, corrupt answer books, lack of prompt response from ICT specialist, and connectivity problems.