Early Alerts Research Articles

First Demonstration of Early Warning Gravitational-wave Alerts

Abstract Gravitational-wave observations became commonplace in Advanced LIGO-Virgo’s recently concluded third observing run. 56 nonretracted candidates were identified and publicly announced in near real time. Gravitational waves from binary neutron star mergers, however, remain of special interest since they can be precursors to high-energy astrophysical phenomena like γ-ray bursts and kilonovae. While late-time electromagnetic emissions provide important information about the astrophysical processes within, the prompt emission along with gravitational waves uniquely reveals the extreme matter and gravity during—and in the seconds following—merger. Rapid communication of source location and properties from the gravitational-wave data is crucial to facilitate multimessenger follow-up of such sources. This is especially enabled if the partner facilities are forewarned via an early warning (pre-merger) alert. Here we describe the commissioning and performance of such a low-latency infrastructure within LIGO-Virgo. We present results from an end-to-end mock data challenge that detects binary neutron star mergers and alerts partner facilities before merger. We set expectations for these alerts in future observing runs.

An Automated Early Alert System for Natural Disaster Risk Reduction: A Review

According to the research published in the last decades, many peoples died due to natural disasters. So, some researchers tried to find a method and solution to reduce these disasters and risks. Lamentably, there is not any value system for a warning from certain dangerous disasters in the country. This suggestion is constructive to diagnose this kind of problem; every country follows different tactics. Based on the various sources of natural weather monitoring systems in the heterogeneous country regions, this review found no solution to warn the community in real-time. This examination is to find the weakness of the current situation as the growth of technology nowadays. Today mobile application's new technology helps an early alert system for natural disaster risk reduction (DRR) that authorities employed in several ways to reduce the natural disaster risks.

Habituation Alteration in Infants with Periventricular Echogenicity as an Indicator of Neurocognitive Impairment

ABSTRACT Habituation difficulties may suggest neurocognitive impairment. Periventricular echogenicity (PVE) potentially causes subtle damage that poses neuropsychological risk. Habituation was evaluated through heart rate and behavioral states in infants at 36–37 weeks of corrected age between control and PVE groups. PVE infants showed early alertness and abrupt changes in behavioral states. However, the comparison group could better regulate their states. Heart rate was significantly high and remained unchanged in the PVE group but decreased in the control group. Alterations during the habituation paradigm in PVE infants could be early indicators of neuropsychological risk impairment. Scope of early habituation assessment is discussed.

Epidemiological Analysis of the 2019 Dengue Epidemic in Bhutan.

Bhutan experienced its largest and first nation-wide dengue epidemic in 2019. The cases in 2019 were greater than the total number of cases in all the previous years. This study aimed to characterize the spatiotemporal patterns and effective reproduction number of this explosive epidemic. Weekly notified dengue cases were extracted from the National Early Warning, Alert, Response and Surveillance (NEWARS) database to describe the spatial and temporal patterns of the epidemic. The time-varying, temperature-adjusted cohort effective reproduction number was estimated over the course of the epidemic. The dengue epidemic occurred between 29 April and 8 December 2019 over 32 weeks, and included 5935 cases. During the epidemic, dengue expanded from six to 44 subdistricts. The effective reproduction number was <3 for most of the epidemic period, except for a ≈1 month period of explosive growth, coinciding with the monsoon season and school vacations, when the effective reproduction number peaked >30 and after which the effective reproduction number declined steadily. Interventions were only initiated 6 weeks after the end of the period of explosive growth. This finding highlights the need to reinforce the national preparedness plan for outbreak response, and to enable the early detection of cases and timely response.

Mapping Artificial Intelligence Applications Deployed Against COVID-19 Alongside Ethics and Human Rights Considerations

This article presents an extensive and global survey on the use of Artificial Intelligence (AI) to address the COVID-19 epidemic and a comprehensive discussion of the ethical and human rights implications of AI's deployment during the pandemic. AI applications contributed to the COVID-19 response including through early warnings and alerts; tracking and prediction; diagnosis and prognosis; drug treatments; and social and medical management. There are human rights issues and ethical risks to consider with these uses of AI technology, for example, equality, non-discrimination and accessibility – particularly as they impact on gender, ethnicity, locality, and wealth. To understand risks before relying on such methods, we must assess whether data can be collected any more effectively from people in remote or disadvantaged areas than with the traditional methods. Other questions would include whether information is gathered equally from women and men, and older people; do all ethnicities have equal access to phones and mobile data; and does the cost of internet access and data use discriminate against poorer people? While the 'coronacrisis' advanced AI-based responses to global health emergencies, this wide-reaching AI capacity, raises an array of ethical and human rights challenges. The need for governments to act quickly and globally in tackling the coronavirus resulted in unprecedented practices amid a lack of public trust. AI technologies assisted governments to curb the global epidemiological threat. Yet, the application of these tools threatened fundamental rights. AI based interventions such as contact tracing raised valid fears of “surveillance creep”. Global human rights are implicated in the measures targeting the spread of COVID-19-related misinformation. Concern over the impact of the internet as a carrier of fake news amplified during COVID-19. Conspiracy theories and alternative narratives mushroomed all over the world. While some fears of misinformation in the current context are valid, the pandemic resulted in an unprecedented global crackdown on freedom of expression. AI applications during the pandemic challenged widely-held commitments to privacy, autonomy, and civil liberties. The “coronacrisis” was viewed by some as a perfect storm to undermine rights to privacy, as effected by surveillance, and freedom of expression. Tech-based responses to COVID-19 included drone surveillance, facial recognition technologies, contact-tracing and quarantine-enforcement apps. With no expiration date or sunset clauses in sight for these technologies' deployment, there are concerns that these surveillance measures could deteriorate privacy further and long-term. While AI is a powerful tool, humans remain central in evaluating and interpreting its output and its ethical application. Human input, across disciplines, remains needed for the optimal application of AI against COVID-19 and other contexts. Overcoming the lack of data needed to optimize AI as a pandemic tool will require a careful balance between data privacy and public health. Increasing diagnostic data is valuable and essential to save lives, train AI, and harness AI for other public health applications. Due to the technical, ethical, and human rights risks, AI must develop alongside human rights and ethical considerations.

Development of an Early Alert System for an Additional Wave of COVID-19 Cases using a Recurrent Neural Network with Long Short-Term Memory

The impact of the still ongoing “Coronavirus Disease 2019” (COVID-19) pandemic has been and is still vast, affecting not only global human health and stretching healthcare facilities, but also profoundly disrupting societal and economic systems worldwide. The nature of the way the virus spreads causes cases to come in further recurring waves. This is due a complex array of biological, societal and environmental factors, including the novel nature of the emerging pathogen. Other parameters explaining the epidemic trend consisting of recurring waves are logistic-organizational challenges in the implementation of the vaccine roll-out, scarcity of doses and human resources, seasonality, meteorological drivers, and community heterogeneity, as well as cycles of strengthening and easing/lifting of the mitigation interventions. Therefore, it is crucial to be able to have an early alert system to identify when another wave of cases is about to occur. The availability of a variety of newly developed indicators allows for the exploration of multi-feature prediction models for case data. Ten indicators were selected as features for our prediction model. The model chosen is a Recurrent Neural Network with Long Short-Term Memory. This paper documents the development of an early alert/detection system that functions by predicting future daily confirmed cases based on a series of features that include mobility and stringency indices, and epidemiological parameters. The model is trained on the intermittent period in between the first and the second wave, in all of the South African provinces.

Management of the radiotherapy quality control using automated Big Data processing

Introduction. In Moscow, the state-of-the-art information technologies for cancer care data processing are widely used in routine practice. Data Science approaches are increasingly applied in the field of radiation oncology. Novel arrays of radiotherapy performance indices can be introduced into real-time cancer care quality and safety monitoring. The purpose of the study. The short review of the critical structural elements of automated Big Data processing and its perspectives in the light of the internal quality and safety control organization in radiation oncology departments. Material and methods. The PubMed (Medline) and E-Library databases were used to search the articles published mainly in the last 2-3 years. In total, about 20 reports were selected. Results. This paper highlights the applicability of the next-generation Data Science approaches to quality and safety assurance in radiation oncological units. The structural pillars for automated Big Data processing are considered. Big Data processing technologies can facilitate improvements in quality management at any radiotherapy stage. Simultaneously, the high requirements for quality and integrity across indices in the databases are crucial. Detailed dose data may also be linked to outcomes and survival indices integrated into larger registries. Discussion. Radiotherapy quality control could be automated to some extent through further introduction of information technologies making comparisons of the real-time quality measures with digital targets in terms of minimum norms / standards. The implementation of automated systems generating early electronic notifications and rapid alerts in case of serious quality violation could drastically improve the internal medical processes in local clinics. Conclusion. The role of Big Data tools in internal quality and safety control will dramatically increase over time.

Dementia Caregivers' Experiences and Reactions to Remote Activity Monitoring System Alerts.

Technology-based tools, including remote activity monitoring (RAM) systems, have been proposed as valuable aids for family caregivers of people with dementia. Previous analyses have shown limited effects of these systems and highlighted a number of barriers, including false alarms. We used data from an ongoing embedded mixed method randomized controlled intervention to describe patterns of alerts and their association with receipt of the RAM system and caregiver outcomes. Quantitative analyses showed a modest positive association between the number of alerts during the first month and system review score. In addition, qualitative results illustrated the importance of alert context, including utility, accuracy, and type of alert delivery. These findings highlight the relevance of early alerts to engagement with and perceived benefit from the RAM system. [Journal of Gerontological Nursing, 47(1), 13-20.].

A Prospective Study on Epidemiology, Clinical Profile and Outcome of Hospitalized Cases of Swine Flu (H1N1) During 2018-2019 Outbreak in North West Zone of Rajasthan

Background: Since World Health Organization declared H1N1 (Swine flu) a pandemic disease on April 29, 2009, it is continuing to be a major public health problem and it has significant regional and seasonal variation. Therefore, this study was planned to evaluate epidemiology, clinical profile, course of illness and their outcome. Material and Method: Present prospective crosssectional study was conducted on RT-PCR confirmed cases of swine flu admitted in dedicated swine flu ward in the Department of Medicine, S.P. Medical College &amp; Associated Group of P.B.M. Hospitals, Bikaner. All patients were subjected to detailed clinical examination and relevant investigation as per proforma. Clinical and epidemiological data were collected. All patients subjected for routine lab examination including complete blood count, renal function test, liver function test, fasting blood sugar, ABG, X-ray chest PA view and other specific investigation as per requirement. Result: Most females belonged to age group 18-35 years and most of the malesbelonged to age group &gt;55 years. Most of cases belonged to category C (62%) and urban residential area (55.7%). Most common symptom was cough (98.7%) followed by fever (91.1%), sore throat (86.1%), sputum (83.5%), nasal discharge (73.4%), breathlessness (72.2%), headache (58.2%), chest pain (27.8%) and palpitation (16.5%). Our study shows multiple organ involvement during the course of swine flu as indicated by increasing blood urea (36.7%), serum direct bilirubin (19%), serum creatinine (18.9%), SGOT (68.3%), SGPT (37.8%) and decreasing serum albumin (63.3%). Overall mortality rate in our study was 8.8%.It was high in females (9.1%) as compare to males(8.6%).All deceased belonged to category C and cough was the most common presenting symptom followed by sore throat, nasal discharge, sputum and fever. Conclusion: Our study shows there are certain factors which can affect outcome in the cases of swine flu. Female gender, elderly age, co morbidity and the duration of illness(6-10 days) are the important factors associated with poor outcome. Early recognition and alertness is important to reduce morbidity and mortality. Patients should also be screened for multiple organ involvement at the time of hospitalization by laboratory test like CBC, RFT, LFT for early diagnosis of multiple organ involvement so as to treat appropriately to prevent multiple organ failure and mortality.

Vadose Zone Monitoring as a Key to Groundwater Protection

Currently, monitoring programs designed for groundwater protection are mainly based on information from observation wells. This, however, creates a paradox, since identification of pollution in well water is clear evidence that the groundwater is already polluted. The poor state of contaminated aquifers all over the world, and the inability, in practice, to fully remediate contaminated aquifers suggest that groundwater monitoring alone has failed to provide the vital information required to prevent groundwater pollution. That said, groundwater pollution initiates on the land surface, and the contaminants have to traverse the unsaturated zone, long before reaching the water table. Therefore, monitoring programs that can provide real-time information on the hydraulic and chemical state of the unsaturated zone are essential for achieving early warnings of pollution potential and providing imperative protection from pollution hazards. Currently, most of the commercially available monitoring technologies are rather limited in their capability to provide early alerts of pollution processes taking place deep in the unsaturated zone, above the water table. Accordingly, monitoring technologies for the unsaturated zone have to be engineered as “off-the-shelf” commercial products, made available for application by practitioners in all fields of hydrology. From scientific and technological points of view, such ambitions are not out of reach. Yet they require an urgent call for a revolutionary shift in monitoring focus, from the groundwater itself to the unsaturated zone above it.

Toward an Early Warning System for Health Issues Related to Particulate Matter Exposure in Brazil: The Feasibility of Using Global PM2.5 Concentration Forecast Products

PM2.5 severely affects human health. Remotely sensed (RS) data can be used to estimate PM2.5 concentrations and population exposure, and therefore to explain acute respiratory disorders. However, available global PM2.5 concentration forecast products derived from models assimilating RS data have not yet been exploited to generate early alerts for respiratory problems in Brazil. We investigated the feasibility of building such an early warning system. For this, PM2.5 concentrations on a 4-day horizon forecast were provided by the Copernicus Atmosphere Monitoring Service (CAMS) and compared with the number of severe acute respiratory disease (SARD) cases. Confounding effects of the meteorological conditions were considered by selecting the best linear regression models in terms of Akaike Information Criterion (AIC), with meteorological features and their two-way interactions as explanatory variables and PM2.5 concentrations and SARD cases, taken separately, as response variables. Pearson and Spearman correlation coefficients were then computed between the residuals of the models for PM2.5 concentration and SARD cases. The results show a clear tendency to positive correlations between PM2.5 and SARD in all regions of Brazil but the South one, with Spearman’s correlation coefficient reaching 0.52 (p &lt; 0.01). Positive significant correlations were also found in the South region by previously correcting the effects of viral infections on the SARD case dynamics. The possibility of using CAMS global PM2.5 concentration forecast products to build an early warning system for pollution-related effects on human health in Brazil was therefore established. Further investigations should be performed to determine alert threshold(s) and possibly build combined risk indicators involving other risk factors for human respiratory diseases. This is of particular interest in Brazil, where the COVID-19 pandemic and biomass burning are occurring concomitantly, to help minimize the effects of PM emissions and implement mitigation actions within populations.

Studying DOZE-OFF in student using ELECTROENCEPHALOGRAPHY system

Sleep deprivation of high school and university students is currently an actual concerning issue. Sleep deprivation is one of the leading causes of dozing-off during daytime. Usually, the state of drowsiness is very little concerned, but studies on drowsiness show the importance of investigating the frequency of occurrence as well as the need to clarify the cause and propose limited measures appeared dozing-off. Dozing-off is not only an undesirable state and disrupts daily activities, but also provides information on personal health status. In that case, early alertness for dozing-off event is very helpful in preventing unwanted consequences. The study has designed a process to record dozing-off event, then constructed and implemented the hypnogram processing program that evaluated quantitative changes in polysomnography signals at sleep onset, the transition time from wake stage to sleep stage. By analyzing the energy spectrum of the signal and using wavelet transform in combine with the support vector machine algorithm, the research allows a comprehensive evaluation of the state of dozing-off. Determining the exact time of onset of sleep is very important in the study of drowsiness. Extracting the time of this event appears to help develop an application for early warning dozing-off. Besides, it allows making an initial assessment of the condition of the subject when the time of drowsiness begins suddenly. Six recordings from volunteered students were processed from a 45-minute vigilance test. All of the volunteers had no neuropathy and were well explained to the procedures used in this study. The results show that depending on kinds of different applications, signals such as EEG, EOG, or EMG are used individually or in combination to fetch suitable results. The result presented a successful method to distinguish dozing-off event with other stages.

PP255 Epigenetic Profile Predicts Response To Immunotherapy In Patients With Non-Small-Cell Lung Cancer: An Early Assessment

IntroductionEpigenetics is an innovative discipline that aims to provide biomarkers to aid in early diagnosis, patient risk classification, or outcome prediction. The identification of therapeutic targets is of particular interest in cancer therapy for selecting groups of patients who may benefit most from an intervention. Understanding the relationships between the immune system and tumor cells has led to new immunotherapy-based therapies that provide a promising alternative to conventional cancer therapies. The aim of this study was to conduct an early assessment of a novel epigenetic signature (EPIMMUNE) that could predict response to programmed cell death protein 1 (PD-1) inhibitor immunotherapy in patients with non-small cell lung cancer (NSCLC).MethodsWe identified the novel epigenetic signature EPIMMUNE through the Early Awareness and Alert System, “SINTESIS-new technologies” of the Agencia de Evaluación de Tecnologías Sanitarias in Spain (AETS-ISCIII). A literature search of PubMed, Embase, the Web of Science, the Trip database, the International Clinical Trials Registry Platform, ClinicalTrials.gov, The Cochrane Library, and the Centre for Reviews and Dissemination databases was conducted. Clinical studies on EPIMMUNE published in English or Spanish up to August 2019 were reviewed.ResultsOnly one retrospective study was found. Identification of EPIMMUNE was accomplished through interrogation of the DNA methylation status of CpG sites in 142 samples from adult patients with NSCLC who were treated with PD-1 inhibitors. EPIMMUNE was defined by 301 CpG sites whose methylation status was significantly associated with clinical response (progression-free and overall survival). No studies assessing the long-term clinical utility, impact on therapeutic decision making, or economic implications of EPIMMUNE were found.ConclusionsThe EPIMMUNE signature could provide an accurate and valid biomarker for identifying patients with NSCLC who may benefit from treatment with PD-1 inhibitors. However, the technology is under development, and there is only a single study on detecting the EPIMMUNE epigenetic profile and identifying the DNA methylation profiles associated with increased survival after PD-1 inhibitor therapy. More diagnostic accuracy studies and prospective, long-term trials are needed to evaluate the clinical impact this technology may have on therapeutic decision making. Given the limited evidence available, further research is needed before the technology can be disseminated.

PP262 PapSEEK: Liquid Biopsy For Endometrial And Ovarian Cancer Screening

IntroductionEndometrial and ovarian cancer are the first and second leading causes of death from gynecological cancer in Spain. Survival is generally determined by stage at diagnosis, but there is no test currently used for early detection of both tumor types. PapSEEK is a test developed to diagnose endometrial and ovarian cancer by detecting aneuploidies and somatic mutations commonly associated with both tumor types through DNA next-generation sequencing (NGS) of liquid from Papanicolaou test (Pap smear) samples. The objective of this work was to assess the effectiveness and safety of PapSEEK.MethodsPapSEEK was identified by the Early Awareness and Alert System, “SINTESIS-new technologies”, of the Agencia de Evaluación de Tecnologías Sanitarias in Spain (AETS-ISCIII). An early assessment of the technology was conducted through a literature search of the following databases: PubMed, Embase, the Web of Science, the Trip database, the International Clinical Trials Registry Platform, ClinicalTrials.gov, and The Cochrane Library. Clinical studies on the effectiveness and safety of PapSEEK published up to February 2019 were reviewed.ResultsThe evidence comprised proof of concept and diagnostic accuracy studies, which showed good preliminary results regarding the accuracy of the test for diagnosing endometrial cancer (sensitivity ranged from 0.81 to 0.93), but not for ovarian cancer (sensitivity ranged from 0.33 to 0.45). The specificity for both tumor types ranged from 0.99 to 1.00. Since PapSEEK uses a sampling method that is routinely used in clinical practice (the Pap smear), no evidence was found in the literature on the safety of the test.ConclusionsPapSEEK is a novel technology developed to diagnose endometrial and ovarian cancer by means of DNA-NGS of Pap smear samples. The identified studies showed good preliminary results regarding the ability of the test to diagnose endometrial cancer, but not ovarian cancer. PapSEEK may be useful as a screening tool for endometrial cancer. However, further research on PapSEEK is needed to prospectively evaluate its diagnostic accuracy, compare it with current tests used in the early diagnosis of both cancer types, evaluate its effect on patient survival and disease progression, and measure its economic impact.

A USER-FRIENDLY REMOTE-SENSING WEB-PLATFORM FOR BIODIVERSITY CONSERVATION AND MANAGEMENT IN PROTECTED AREAS

Abstract. The Chilean SNASPE is a complex network of 104 protected areas covering 18.5 million hectares of continental and insular Chile in South America. The geographical complexity and high biodiversity of the SNASPE make difficult to develop a unified monitoring system for conservation and management. In this contribution, we introduce a novel and remote-sensing web-platform for monitoring SNASPE units based completely in open acces data and software. The platform was designed in close cooperation with the Chilean forest service CONAF in order to make it applicable to the whole SNASPE. Following the framework of the Group on Earth Observation - Biodiversity Observation Network (GEO-BON), we used the Essential Biodiversity Variable (EBV) Phenology and MODIS Enhanced Vegetation Index (EVI) data to detect in near-real-time anomalies from the normal annual phenological cycle of vegetation. The platform is based on a flexible non-parametric probabilistic algorithm (the “npphen” R package) capable to reconstruct any type of leaf phenology and to quantify its inter-annual variation by means of confidence intervals around the most probable annual curve. Phenological anomalies are then calculated as a deviation from the expected annual cycle and judged based on their location within the confidence intervals. Anomalies located above 95% confidence interval trigger a “red alert” which is displayed on the web application as soon as the MODIS data become available. This user-friendly platform was implemented in the La Campana National Park giving early alerts of a severe drought in 2019, warning Conaf to implement actions to protect the park from potential wild fires.

Using Copernicus Sentinel-2 and Sentinel-3 data to monitor harmful algal blooms in Southern Chile during the COVID-19 lockdown

During the southern summer of 2020, large phytoplankton blooms were detected using satellite technology in Chile (western Patagonia), where intensive salmonid aquaculture is carried out. Some harvesting sites recorded massive fish mortalities, which were associated with the presence of the dinoflagellate species Cochlodinium sp. The bloom included other phytoplankton species, as Lepidodinium chlorophorum, which persistently changed the colour of the ocean to green. These blooms coincided with the government-managed emergency lockdown due to the COVID-19 pandemic. Local in situ sampling was slowed down. However, imagery from the Copernicus programme allowed operational monitoring. This study shows the benefits of both Sentinel-3 and Sentinel-2 satellites in terms of their spectral, spatial and temporal capabilities for improved algal bloom monitoring. These novel tools, which can foster optimal decision-making, are available for delivering early alerts in situations of natural catastrophes and blockages, such as those occurred during the global COVID-19 lockdown.

Сильные землетрясения земного шара и России в I полугодии 2020 г. по данным ФИЦ ЕГС РАН

The data on the seismicity of the Earth in the first half of 2020 at the level of strong earthquakes with mb6 are presented according to the Earthquake Early Alert Service (EEAS) of the Geo-physical Survey RAS. The review also includes information on weaker but destructive earth-quakes in the world and tangible earthquakes in Russia. In total, 64 earthquakes with mb6 were registered in the first half of the year, including four events in Russia. For 18 strong earthquakes, the EEAS published Informational messages within one or two days after their occurrence, for 16 of them the information on focal mechanisms was given. A comparative analysis of the seismic energy released in the territory of the Globe showed that in the first half of 2020 its amount corresponds to the average values for the last three years. The strongest earthquakes with MS=7.7 occurred on January 28 in the Caribbean Sea and on June 23 in Mexico, accompanied by fore- and aftershocks. The largest human casualties and material damage during the study period were caused by the catastrophic earthquake with MS=6.6 that occurred on January 24 in Turkey. As a result of the earthquake, 41 people died, 1607 were injured. On the territory of Russia, the strongest earthquake with MS=7.5 occurred on March 25 east of the Kuril Islands and was felt in Severo-Kurilsk with an intensity Ii=5–6. A total of 47 tangible earthquakes with mb=3.6–7.2 were recorded in Russia.

Towards resilient and smart cities: A real-time urban analytical and geo-visual system for social media streaming data

Cities worldwide are vulnerable to unpredictable extreme events such as disasters and public health crises. Urban big data and data-driven technologies have played an increasingly important role in building smart and resilient cities that can respond rapidly to these perturbations. However, many existing approaches had limited capabilities for processing big data, which has led to time-consuming and costly decision-making. Thus, we develop a real-time data-driven analytical and geo-visual system to enable smart and rapid responses to urban extreme events. The system is built on ArcGIS’s GeoEvent Server and Apache Spark and processes streaming data from social media with high speed, massive volume, and multiple modalities. The system employs online topic modeling and domain-adaptive sentiment analysis to track small-scale, undefined events, visualizes their spatial and semantic dynamics, and provides early alerts for crises and emergencies via an interactive online GIS platform. The proposed system has been applied during a large-scale hurricane and demonstrated effectiveness and agility in tracking and reporting emerging small-scale crises. The developed system can be applied in various urban scenarios to enable timely situation awareness and rapid response. This research contributes to the smart city safety and building rapidity of resilient cities.

Lessons learned from an under-reported mumps epidemic among Rohingya refugees in Cox's Bazar District, Bangladesh

BackgroundIn 2018, a large mumps epidemic coincided with an outbreak of diphtheria in refugee camps established in Bangladesh for the Rohingya people. These refugees did not receive a mumps-containing vaccine.MethodsCases of mumps were reported to the WHO's Early Warning, Alert and Response System (EWARS) during the Rohingya refugee crisis. The authors present amalgamated epidemiological data of a major, previously under-reported, mumps epidemic.ResultsIn total, 19 215 mumps cases across a total of 218 facilities were reported to EWARS during 2018. The attack rate was 2.1% of the whole population. Of these cases, 7687 (40%) were in children aged <5 y. Mumps was more commonly seen among males than females.ConclusionDetailed reporting of outbreaks of all vaccine-preventable diseases is essential to ensure appropriate vaccination decisions can be made in future humanitarian crises.

Predicting academic performance of students in Chinese-foreign cooperation in running schools with graph convolutional network

To improve students' performance effectively, many Chinese universities are establishing systems to predict student's academic performance and sending student's academic early alerts. With student's population of over 600,000, Chinese-foreign cooperation in running schools (CFCRS) has become one of the booming higher education forms in China. Compared with students in the non-cooperatively running programs, CFCRS students' academic performances are weaker on average. To predict the academic-at-risk students and provide efficient supports to the students, a precise and prompt academic prediction is in great need. Therefore, this research aims at representing a more efficient and accurate model to predict academic performance of CFCRS students which will be based on graph convolutional network. In this research, student's similarity is measured on academic performance by Pearson correlation coefficient. An undirected graph in which similar students are connected is conducted. Feature matrix is composed of students' previous grades. In addition, graph convolutional network is trained based on the undirected graph and feature matrix. In the experiment, it shows that this model predicts certain student's performance on certain course from the final exam results in previous semesters, which might improve learning efficiency and teaching quality. With an average accuracy of 81.5%, graph convolutional network outperforms support vector machine and random forest models.