Using the DTFM Method to Analyse the Degradation Process of Bilateral Trade Relations between China and Australia

Quantitative assessment and visual analysis of the multidimensional features of international bilateral product trade are crucial for global trade research. However, current methods face poor salience and expression issues when analysing the characteristics of China—Australia bilateral trade from 1998 to 2019. To address this, we propose a new perspective that involves period division, feature extraction, construction of product space, and spatiotemporal analysis by selecting the display competitive advantage index using the digital trade feature map (DTFM) method. Our results reveal that the distribution of product importance in China—Australia bilateral trade is heavy-tailed, and that the number of essential products has decreased by 68% over time. The proportion of products in which China dominates increased from 71% to 77%. Furthermore, Australia consistently maintains dominance in the most crucial development in trade, and the supremacy of the head product is becoming stronger. Based on these findings, the stability of bilateral trade between Australia and China is declining, and the pattern of polarisation in the importance of traded products is worsening. This paper proposes a novel method for studying Sino—Australian trade support. The analytical approach presented can be extended to analyse the features of bilateral trade between other countries.

Social Media Driven Big Data Analysis for Disaster Situation Awareness: A Tutorial

Situational awareness tries to grasp the important events and circumstances in the physical world through sensing, communication, and reasoning. Tracking the evolution of changing situations is an essential part of this awareness and is crucial for providing appropriate resources and help during disasters. Social media, particularly Twitter, is playing an increasing role in this process in recent years. However, extracting intelligence from the available data involves several challenges, including (a) filtering out large amounts of irrelevant data, (b) fusion of heterogeneous data generated by the social media and other sources, and (c) working with partially geo-tagged social media data in order to deduce the needs of the affected people. Spatio-temporal analysis of the data plays a key role in understanding the situation, but is available only sparsely because only a small fraction of people post relevant text and of those very few enable location tracking. In this paper, we provide a comprehensive survey on data analytics to assess situational awareness from social media big data.

Learning the Protein Language Model of SARS-CoV-2 Spike Proteins

Ahstract-SARS-CoV-2 virus has long been evolving posing an increased risk in terms of infectivity and transmissibility which causes greater impact in communities worldwide. With the surge of collected SARS-CoV-2 sequences, studies found out that most of the emerging variants are linked to increased mutations in the spike (S) protein as observed in Alpha, Beta, Gamma, and Delta variants. Multiple approaches on genomic surveillance have been performed to monitor the mutational status and spread of the virus however most are heavily dependent on labels attributed to these sequences. Hence, this study features a system that has the capability to learn the protein language model of SARS-CoV-2 spike proteins, based on a bidirectional long-short term memory (BiLSTM) recurrent neural network, using sequence data alone. Upon obtaining the sequence embedding from the model, observed clusters are generated using the Leiden clustering algorithm and is visualized to monitor similarities between variants in terms of grammatical probability and semantic change. Additionally, the system measures the validity of a user-generated next-generation sequence capturing potential sequence mutations indicative of viral escape, particularly mutations by substitutions. Further studies on methods uncovering semantic rules that govern spike proteins are recommended to learn more about other viral characteristics conclusive of the future of the COVID-19 pandemic. © 2023 IEEE.

An Improved Accuracy in Anticipating the User Nature using a novel logistic regression algorithm throughout the pandemic across online social media based on Indian metrics over Support Vector Clustering Algorithm

This study's primary goal is to apply machine learning classifier techniques to raise the intensity percentage of user nature detection in order to detect the impact of coronavirus on Twitter users by comparing Novel Logistic Regression and Support Vector Clustering algorithms. Materials and Methods: The accuracy percentage with a confidence interval of 95% and G-power (value =0.8) was determined many times using the LR method with test size =10 and the SVC algorithm with test size =10. The likelihood that an item belongs to one category or another is predicted using a LR model. Support Vector Clustering algorithm generates a line or hyperplane that divides the data into categories. Results and Discussion: LR model has greater efficiency (91%) when compared to Support Vector Clustering (59%). Two groups are numerically unimportant, according to the data obtained with a coefficient of determination of p=0.121 (p>0.05). Conclusion: LR performs substantially better than the Support Vector Clustering. © 2022 IEEE.

Prioritizing COVID-19 Vaccine Delivery for the Indian Population

As India has successfully developed a vaccine to fight against the COVID-19 pandemic, the government has started its immunization program to vaccinate the population. Initially, with the limited availability in vaccines, a prioritized roadmap was required to suggest public health strategies and target priority groups on the basis of population demographics, health survey information, city/ region density, cold storage facilities, vaccine availability, and epidemiologic settings. In this paper, a machine learning-based predictive model is presented to help the government make informed decisions/insights around epidemiological and vaccine supply circumstances by predicting India's more critical segments that need to be catered to with vaccine deliveries as quickly as possible. Public data were scraped to create the dataset;exploratory data analysis was performed on the dataset to extract important features on which clustering and ranking algorithms were performed to figure out the importance and urgency of vaccine deliveries in each region. Copyright © 2022 IGI Global.

INCREMENTAL TEXT CLUSTERING ALGORITHM FOR CLOUD-BASED DATA MANAGEMENT IN SCIENTIFIC RESEARCH PAPERS

This study aims to build clusters of similar research papers. Text clustering for research articles is challenging because re-clustering is necessary to handle newly added papers. An incremental clustering algorithm is presented to find similar research papers for COVID-19 related literature. The proposed approach uses an incremental word embedding generation technique to extract feature vectors of the papers. The initial clustering is done by using the K-means algorithm by two NLP feature extraction models;TF-IDF and Word2vec. The clustering results show that the Word2vec outperforms the TF-IDF model. With increasing COVID-19 literature continuously, the ultimate focus is to add the newly published papers to the existing clusters without re-clustering. Title, , and full body of papers are considered for testing the proposed incremental algorithm. Clustering quality is evaluated by the Microsoft language similarity package, which shows clustering of the full-text body outperforms the and title of papers. © 2022 Society for Modeling & Simulation International (SCS)

HSD103 Evolution 2019-2020 of Immune Checkpoint Inhibitors (ICI) Administration in Hospitalization at Home (HAH) for Cancer Patients in France: Descriptive Analysis From the French Public Health Insurance Database (PMSI)

Objectives: Hospitalization At Home (HAH), facility delivering hospital care at home, constitutes an alternative to hospitalization for ICI infusion. This work aims to describe the evolution of ICI administration in HAH between 2019-2020 in the COVID epidemic context, to characterize patients and their care pathways. Method(s): Through national hospital database (PMSI), all patients with at least one ICI infusion per year, 2019 and 2020 (including Covid-19 lock-down), were identified with a 6-year retrospective chain of all ICI infusion stays. Patients' journey was analyzed (days number before and during HAH period, alternation HAH/ day care unit (DCU) infusion), based on descriptive analysis and treatment sequences clustering algorithms (TAK). Result(s): HAH patients significantly increased from 60 in 2019 to 339 in 2020 but remained limited (0,67% of 2020 ICI patients). Infusions have significantly increased during Covid-19 lock-down periods and remain at a higher level during the rest of 2020. Mean age and gender characteristics tend to be similar (62 and 66 years old, 37% and 33% women). Lung cancer (77% and 64%) and melanoma (23% and 27%) remained the most frequent tumors treated, but head and neck cancers (8%) and renal carcinoma (3%) were newly observed in 2020. Most administered ICIs in 2020 remained nivolumab (49%) and pembrolizumab (41%). In 2020, number of days before HAH was still close to a year (340days) and higher than the days number spent in HAH (n=110). In 2019 and 2020, treatment sequence analysis shows lung cancer patients mainly managed in HAH after first HAH infusion as well as for melanoma in 2019. In 2020, it shows different patterns for melanoma with HAH/DCU alternation dominance after first HAH infusion. Conclusion(s): Despite easier HAH access since Covid-19, HAH remains limited. French Society for Cancer Immunotherapy 2020 recommendations should contribute to HAH development. Copyright © 2022

The Infant Transcriptome in Meningococcal Septic Shock: A Force in Precision Cellular Dysfunction Suggesting a Cytokine Storm?

BACKGROUND AND AIM: The ideal biomarker(s) to track evolution and the underlying basis of sepsis remain elusive. We hypothesized that assessing differential mRNA gene expression may aid in tracking sepsis pathogenesis in infants with meningococcal septic shock (MSS). METHOD(S): Temporal paediatric gene expression datasets from Meningococcal Group B sepsis studies in the United Kingdom (MSS1, 29 samples) and Holland (MSS2, 41 samples) underwent Principal Component Analysis (PCA) and Gene Set Enrichment Analysis (GSEA). RESULT(S): Gene-expression clustering algorithm for both datasets demonstrated a baseline state on admission, an intermediate state, and a final state. Additionally, PCA plots suggested a gene-expression trajectory. The MSS1 study showed that 410 genes differentiated survivors from a nonsurvivor, including the ICAM-3 gene. Moreover GSEA t-Test identified apoptosis to be significantly differently (p = 0.02 and q = 0.15) associated with the fatal case compared to the four survivors in MSS1. Also in MSS1, we identified a genesignature for cytokine production which included 5 genes (CLC, HFE, HLA-F, NLRP3, TNFRSF1B) from the cytokine GSEA gene panel. The genes NLRP3 and TNFRSF1B have been noted in the cytokine storm of Coronavirus infection. Also Transcript Time Course Analysis (TTCA) confirmed differential gene function associated with Coronavirus. CONCLUSION(S): Transcriptomic analysis in two independent datasets in infants with MSS identified a trajectorial pattern. Further, the transcriptome expression differed between survivors and non-survivors, suggesting differences in cytokine signalling. Including the existence of genes associated with the cytokine storm of SARS-CoV2. The exploitability of transcriptome analysis to guide therapy and prognosis requires further investigation. (Figure Presented).

An Improving Accuracy in Predicting the spread of Covid over Online Social Networks based on Geographical Location using Novel Autoregressive Algorithm comparing Support Vector Clustering Algorithm

Aim: The purpose of this research work is to heighten the efficiency percent of geographical location identification to relieve the effect of covid using device studying classifiers by evaluating novel Logistic Regression algorithm and Random Forest algorithm.Materials and Methods: Logistic Regression algorithm with sample size = 10, G-power (value=0.8)and Random Forest algorithm with sample size = 10 were predicted many times to evaluate the efficiency percentage. Logistic Regression is evaluated by using its weights and configurations.Results and Discussion: Logistic Regression algorithm has better accuracy (92%) when compared to Random Forest Algorithm accuracy(21%). The results achieved with significance value p=0.680 (p>0.05) shows that two groups are statistically insignificant.Conclusion: Logistic Regression algorithm performed significantly better than the Random Forest algorithm.

Incremental Text Clustering Algorithm For Cloud-Based Data Management In Scientific Research Papers

This study aims to build clusters of similar research papers. Text clustering for research articles is challenging because re-clustering is necessary to handle newly added papers. An incremental clustering algorithm is presented to find similar research papers for COVID-19 related literature. The proposed approach uses an incremental word embedding generation technique to extract feature vectors of the papers. The initial clustering is done by using the K-means algorithm by two NLP feature extraction models;TF-IDF and Word2vec. The clustering results show that the Word2vec outperforms the TF-IDF model. With increasing COVID-19 literature continuously, the ultimate focus is to add the newly published papers to the existing clusters without re-clustering. Title, , and full body of papers are considered for testing the proposed incremental algorithm. Clustering quality is evaluated by the Microsoft language similarity package, which shows clustering of the full-text body outperforms the and title of papers. © 2022 SCS.

Comprehensive Analysis of the COVID-19: Based on the Social-Related Indexes From NUMBEO.

Background: The COVID-19 has been spreading globally since 2019 and causes serious damage to the whole society. A macro perspective study to explore the changes of some social-related indexes of different countries is meaningful. Methods: We collected nine social-related indexes and the score of COVID-safety-assessment. Data analysis is carried out using three time series models. In particular, a prediction-correction procedure was employed to explore the impact of the pandemic on the indexes of developed and developing countries. Results: It shows that COVID-19 epidemic has an impact on the life of residents in various aspects, specifically in quality of life, purchasing power, and safety. Cluster analysis and bivariate statistical analysis further indicate that indexes affected by the pandemic in developed and developing countries are different. Conclusion: This pandemic has altered the lives of residents in many ways. Our further research shows that the impacts of social-related indexes in developed and developing countries are different, which is bounded up with their epidemic severity and control measures. On the other hand, the climate is crucial for the control of COVID-19. Consequently, exploring the changes of social-related indexes is significative, and it is conducive to provide targeted governance strategies for various countries. Our article will contribute to countries with different levels of development pay more attention to social changes and take timely and effective measures to adjust social changes while trying to control this pandemic.

Oxygen saturation measurements using novel diffused reflectance with hyperspectral imaging: Towards facile COVID-19 diagnosis.

Oxygen saturation level plays a vital role in screening, diagnosis, and therapeutic assessment of disease's assortment. There is an urgent need to design and implement early detection devices and applications for the COVID-19 pandemic; this study reports on the development of customized, highly sensitive, non-invasive, non-contact diffused reflectance system coupled with hyperspectral imaging for mapping subcutaneous blood circulation depending on its oxygen saturation level. The forearm of 15 healthy adult male volunteers with age range of (20-38 years) were illuminated via a polychromatic light source of a spectrum range 400-980 nm. Each patient had been scanned five times to calculate the mean spectroscopic reflectance images using hyperspectral camera. The customized signal processing algorithm includes normalization and moving average filter for noise removal. Afterward, employing K-means clustering for image segmentation to assess the accuracy of blood oxygen saturation (SpO2) levels. The reliability of the developed diffused reflectance system was verified with the ground truth technique, a standard pulse oximeter. Non-invasive, non-contact diffused reflectance spectrum demonstrated maximum signal variation at 610 nm according to SpO2 level. Statistical analysis (mean, standard deviation) of diffused reflectance hyperspectral images at 610 nm offered precise calibrated measurements to the standard pulse oximeter. Diffused reflectance associated with hyperspectral imaging is a prospective technique to assist with phlebotomy and vascular approach. Additionally, it could permit future surgical or pharmacological intercessions that titrate or limit ischemic injury continuously. Furthermore, this technique could offer a fast reliable indication of SpO2 levels for COVID-19 diagnosis.

A Review on Categorizing the COVID19 Dataset using K-Means Clustering Algorithm

COVID19 is a magical wand that has entirely changed the human beings to embrace a new normal life. Increase in the number of COVID19 cases has laid a huge burden on the healthcare system in identifying, analysing, and treating. Infection of this disease is developed in various stages from mild to severe, where, treatment also varies based on these stages. People are panic that even with simple cough, fever and viral infection, assume to be COVID19 and rush to hospitals for treatment. This situation leads to a crucial condition for hospitals in treating patients with severe infection and emergency cases. To avoid such situation, patients must be categorized into three different groups based on their severity, before coming to hospital. As the number of waves and COVID19 cases are increasing, manual categorization of patients based on their severity becomes less possible. One of the fastest and optimal solution is to use machine learning approach. A clustering technique could be used categorize the dataset. © 2021 IEEE.

Clustering based Contact Tracing Analysis and Prediction of SARS-CoV-2 Infections

INTRODUCTION: Contact tracing is a method to track the victims, which have been infected from the host with any particular disease. Therefore, clustering based machine learning techniques can be employed for contact tracing. Contact tracing can be automated by using technology and thus helps us in producing much more accurate and efficient results. OBJECTIVES: This work aims at finding usefulness of clustering techniques for contact tracing. Two different clustering techniques namely density-based clustering and partitioning-based clustering have been used to analyse corresponding results for COVID-19 infected cases. The dataset is generated from a mock data generator with certain assumptions. RESULTS: The paper compares DBSCAN and K-means for contact tracing for COVID-19 Pandemic. The comparative analysis of two algorithms is presented. CONCLUSION: The effectiveness of certain clustering algorithms in COVID-19 contact tracing is analysed. DBSCAN performs well for clustering tasks. This work only focuses on possible techniques useful for contact tracing and does not claim any medical accuracy © 2021. Meenu Gupta et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited

The impact of the COVID-19 pandemic on O-D flow and airport networks in the origin country and in Northeast Asia.

The ongoing COVID-19 pandemic has posed a global threat to human health. In order to prevent the spread of this virus, many countries have imposed travel restrictions. This difficult situation has dramatically affected the airline industry by reducing the passenger volume, number of flights, airline flow patterns, and even has changed the entire airport network, especially in Northeast Asia (because it includes the original disease seed). However, although most scholars have used conventional statistical analysis to describe the changes in passenger volume before and during the COVID-19 outbreak, very few of them have applied statistical assessment or time series analysis, and have not even examined how the impact may be different from place to place. Therefore, the purpose of this study was to identify the impact of COVID-19 on the airline industry and affected areas (including the origin-destination flow and the airport network). First, a Clustering Large Applications (CLARA) algorithm was used to group numerous origin-destination (O-D) flow patterns based on their characteristics and to determine if these characteristics have changed the severity of the impact of each cluster during the COVID-19 outbreak. Second, two statistical tests (the paired t-test and the Wilcoxon signed-rank test) were utilized to determine if the entire airport network and the top 30 hub airports changed during COVID-19. Four centrality measurement indices (degree, closeness, eigenvector, and betweenness centrality) of the airports were used to assess the entire network and ranking of individual hub airports. The study data, provided by The Official Aviation Guide (OAG) from December 2019 to April 2020, indicated that during the COVID-19 outbreak, there was a decrease in passenger volume (60%-98.4%) as well as the number of flights (1.5%-82.6%). However, there were no such significant changes regarding the popularity ranking of most airports during the outbreak. Before this occurred (December 2019), most hub airports were in China (April 2020), and this trend remain similar during the COVID-19 outbreak. However, the values of the centrality measurement decreased significantly for most hub airports due to travel restrictions issued by the government.

Clustering framework to cope with COVID-19 for cities in Turkey

Introduction: This article is the product of the research "Clustering Framework to Cope with COVID-19 for Cities in Turkey", developed at Bayburt University in 2021. Problem: Turkey's risk map, presented in January 2021, to take local decisions in tackling the COVID-19 pandemic, was based on confirmed cases only. Health, socio-economic and environmental indicators are also important for management decisions of COVID-19. The risk map to be designed by adding these indicators will support more effective decisions. Objective: The research aims to propose a clustering scheme to design a risk map of cities for Turkey. Methodology: The unsupervised clustering algorithm suggested dividing the cities of Turkey into clusters, considering health, socio-economic, environmental indicators, and the spread pattern of COVID-19. Results: We found that cities are clustered into five groups while megacity Istanbul alone formed a cluster, three of Turkey's largest cities formed another cluster. Other clusters consist of 19, 26, and 32 cities, respectively. The most important determinants which have predictive power are identified. Conclusion: The suggested clustering method can be a decision support system for policymakers to determine the differences and similarities of cities in quarantine decisions and normalization phases for the following periods of the pandemic. Originality: To the best of our knowledge, this study differs from previous studies because countries were grouped in previous studies by only considering the confirmed cases. In this study, cities were clustered in terms of the health, socio-economic, and environmental indicators to make decisions locally. Limitations: The distribution of confirmed cases by age could be added, especially to make decisions about education, but this data is not officially announced.

POSA235 Immune Checkpoint Inhibitors (ICI) Infusion at Home for Cancer Patients: An Analysis of the French National Hospital Database (PMSI)

Objectives: Hospitalization at home (HAH) is a French specific organization delivering hospital care at home. As part of a national ambulatory care policy, HAH for cancer intravenous treatments is becoming a priority. This work aims to describe the specificities of ICI infusion at home. Methods: Through national hospital database (PMSI), all patients with at least one ICI infusion in 2019 were identified. Patients’ characteristics and ICI infusion specificities in hospitals and in HAH were described. Patients’ journeys (time to infusion in HAH, time spent in HAH protocols, alternation of infusion in HAH and in hospitals after HAH infusion initiation) were retrospectively analyzed (maximum of 5-year prior period) using swimmer plots and clustering algorithms. Results: In 2019, 36,526 patients received ICI at least once in hospitals including 60 who had infusions at home. Patients treated at home were 62.2 years old (65.5 yo in hospitals) and 61.7% male (67.4% in hospitals). HAH’s patients suffered from lung cancer (77%;61% in hospitals) and melanoma (23%;14% in hospitals). HAH patients were mainly treated with nivolumab (58%, 54% in hospitals). Seven out of 22 French regions experienced home ICI infusion (min:1;max:21 patients). Average time from first infusion in hospitals to HAH initiation was close to one year (341 days, [95%CI 268-413]) and average time spent between first and last infusion in HAH was 115 days [95%CI 80-150]). Two types of HAH management protocol were observed: ‘All infusions in HAH’ and ‘Alternation of infusions in HAH and hospitals. Conclusions: This first study on ICI infusion at home through HAH highlights its limited use in France and the heterogeneity of the patients’ journey. In the context of the COVID-19 epidemic, a greater number of patients infused with ICI at home is expected. An update of this study in 2020 would be of interest.

A clustering-based approach for quality level verification of sanitation procedures in workplaces

With the COVID-19 pandemic outbreak, sanitizing procedures have become fundamental in work environments, where surfaces and objects are frequently touched by multiple people, enhancing the risk of exposure to the disease. To assure safe working conditions, it is of primary importance to assess the adherence of the sanitation activity to the recommended protocols with a certain level of accuracy. In this work, we propose a methodology able to estimate the accuracy level of sanitation procedures by applying clustering techniques on multiple features extracted from wrist-mounted accelerometric sensors measurements.

Distributed clustering algorithm for adaptive pandemic control

The COVID-19 pandemic has had severe consequences on the global economy, mainly due to indiscriminate geographical lockdowns. Moreover, the digital tracking tools developed to survey the spread of the virus have generated serious privacy concerns. In this paper, we present an algorithm that adaptively groups individuals according to their social contacts and their risk level of severe illness from COVID-19, instead of geographical criteria. The algorithm is fully distributed and therefore, individuals do not know any information about the group they belong to. Thus, we present a distributed clustering algorithm for adaptive pandemic control. Author