Limited Testing Resources Research Articles

COVID-19 Identification System from X-Ray Images of Chest using Deep Neural Network with Transfer Learning

Recently, the impact of COVID-19 has significantly diminished; however, it has not been completely eradicated. There are still instances where individuals are experiencing suffering due to this life-threatening virus which has a significant impact on health care as well as lifestyles throughout the world. So, early discovery is important to controlling case extension and the death rate. The RT-PCR is known as the true leading diagnosis test; nevertheless, the expense and result times of these tests are long, thus additional quick and accessible diagnostic techniques are required. However, most countries are suffering due to limited testing resources and kits. The unavailability of testing resources, kits, and a rising amount of regular occurrences, caused us to develop a model on Deep Learning which may benefit radiologists as well as doctors for detecting COVID-19 instances using images of chest X-rays. For developing a representation of modality-specific features, a convolutions neural network and a variety of ImageNet pre-trained models are trained and evaluated at the patient level by using different available CXR datasets. We choose 5000 images in total from the dataset collected from Kaggle where we kept 4000 images in case of training and validation, and the remaining 1000 in case of testing. We use four Pre-train Deep CNN Models which are very popular for image calcification. VVG16, VGG19, InceptionV3, and Resnet50 CNN Models we choose to analyze the performance and find the best one among them. In our testing, we get 88.5% testing accuracy on ResNet and 95.10% on InceptionV3 models while VGG19 gives 90.22% accuracy and VGG16 gives the highest 96.10% accuracy. To increase performance accuracy, Transfer Learning knowledge is transmitted and fine-tuned. After applying Transfer Learning in the modified VGG16 we got an accuracy of 97% which is clearly an improvement over the previous VGG16 model. GUB JOURNAL OF SCIENCE AND ENGINEERING, Vol 10(1), 2023 P 53-67

Impact of trans-regional travel-related testing on epidemic spreading

The convenient transport network enables people to travel quickly and frequently across regions, but it also brings serious challenges to the emergency management of infectious diseases. This work extends the classical SEIR model by incorporating trans-regional population movements and contact infections during travel. It also includes cross-regional population testing and treatment measures to curb the spread of infectious diseases across regions. According to these characteristics, a Net-SEIHR model is established and its diffusion properties are deduced. Further, the cooperative allocation problem of limited detection resources and its control strategy are discussed. Numerical experiments show that the control measures can reduce the speed of trans-regional transmission of infectious diseases and the peak of treatment. In the case of limited testing resources, it is necessary to strengthen the detection of people in the inflow regions.

Real-time and visual detection of viable Salmonella in milk from remote pasture via IMS-LAMP-NALFS

Salmonella is a prevalent foodborne pathogen commonly found in dairy products. Controlling the presence of Salmonella during dairy product production is of utmost concern due to the potential for contamination at any stage of the production chain, particularly at the source. Moreover, the unique location of pastures and limited testing resources further highlight the necessity of establishing a rapid and precise detection method to ensure milk quality control and enhance overall farm safety. To address these issues, in this study, we constructed a method as well as a portable toolbox for rapid on-site detection of Salmonella. The method involves immunomagnetic separation (IMS) using streptavidin-coupled magnetic nanoparticles and biotinylated antibodies. The reaction conditions for magnetic capture and enrichment of Salmonella were optimized to efficiently remove matrix interference from milk and enhance detection sensitivity. Additionally, an improved propidium monoazide (PMAxx) treatment was employed to eliminate false positive results caused by dead bacteria. This treatment was combined with loop-mediated isothermal amplification (LAMP) and nucleic acid lateral flow strip (NALFS) (LAMP-NALFS) for on-site detection of viable bacteria in milk. The resulting IMS-LAMP-NALFA assay achieved rapid and sensitive detection of viable Salmonella, with a detection sensitivity of 1 × 102 CFU/mL in milk samples, completed within 90 min under optimal conditions. Based on this achievement, a portable toolbox was designed for easy transportation and on-site testing in pastures. It is equally applicable for rapid detection of viable Salmonella contamination in food products in resource-limited areas such as pastures, where the observed detection rate of Salmonella in unpasteurized raw milk was 7.93 % (28 out of 353 samples tested). Consequently, the IMS-LAMP-NALFA method and the associated portable toolbox represent highly effective means of enhancing the detection of viable Salmonella in dairy products.

IAPCP: An Effective Cross‐Project Defect Prediction Model via Intra‐Domain Alignment and Programming‐Based Distribution Adaptation

Cross‐project defect prediction (CPDP) aims to identify defect‐prone software instances in one project (target) using historical data collected from other software projects (source), which can help maintainers allocate limited testing resources reasonably. Unfortunately, the feature distribution discrepancy between the source and target projects makes it challenging to transfer the matching feature representation and severely hinders CPDP performance. Besides, existing CPDP models require an intensively expensive and time‐consuming process to tune a lot of parameters. To address the above limitations, we propose an effective CPDP model named IAPCP based on distribution adaptation in this study, which consists of two stages: correlation alignment and intra‐domain programming. Correlation alignment first calculates the covariance matrices of the source and target projects and then erases some features of the source project (i.e., whitening operation) and employs the features of the target project (i.e., target covariance) to fill the source project, thereby well aligning the source and target feature distributions and reducing the distribution discrepancy across projects. Intra‐domain programming can directly learn a nonparametric linear transfer defect predictor with strong discriminative capacity by solving a probabilistic annotation matrix (PAM) based on the adjusted features of the source project. The model does not require model selection and parameter tuning. Extensive experiments on a total of 82 cross‐project pairs from 16 software projects demonstrate that IAPCP can achieve competitive CPDP effectiveness and efficiency compared with multiple state‐of‐the‐art baseline models.

Data-driven adaptive testing resource allocation strategies for real-time monitoring of infectious diseases

Since 2002, with the SARS outbreak, infectious diseases, including the ongoing COVID-19 pandemic, have continued to be a major global public health threat. It is critical to develop effective data science methods to quickly detect disease outbreaks and contain their rapid globalized spread. However, in practice, limited testing availability, and thus insufficient testing data poses significant challenges in effective analysis and real-time monitoring of infectious diseases, especially during early stages of a novel disease outbreak. To tackle these challenges, this article proposes adaptive testing resource allocation strategies integrated with a physics-informed model to dynamically allocate limited testing resources across different communities. The physics-informed model accounts for transmission dynamics and health disparities, enabling effective health risk assessment despite limited data. By integrating nonstationary Multi-Armed Bandit techniques that strike superior balance between exploring the communities with high uncertain risks and exploiting those with high risk levels, the proposed methodology facilitates test allocation to collect high-quality testing data for early outbreak detection. Theoretical analysis is carried out to evaluate the performance of the proposed allocation strategies, ensuring either sublinear or linear dynamic pseudo-regret under regularity assumptions. A comprehensive simulation study is conducted under three transmission scenarios to thoroughly evaluate the proposed methodology.

Predicting Aging-Related Bugs Using Network Analysis on Aging-Related Dependency Networks

Software aging, a phenomenon that exhibits an increasing failure rate or progressive performance degradation in long-running software systems, has caused serious cost damage or even loss of human lives. To aid aging-related bug (ARB, whose activation can result in software aging) detection and removal before software release, ARB prediction was proposed. Based on the prediction results, software teams can allocate limited testing resources to ARB-prone modules. Previous research has proposed several methods for both within-project and cross-project ARB prediction. However, they are based on the same set of metrics focusing on the contents of a single module, and only six metrics are aging-related. In this paper, we develop aging-related network measures by constructing an aging-related dependency network to model the flow of aging-related information in the software. Our evaluation on three commonly used open-source projects reveals that aging-related network measures show an inconsistent association with ARB-proneness in three projects, and the performance of aging-related network measures varies under different ARB prediction settings.

Geographic Targeting of COVID-19 Testing to Maximize Detection in Los Angeles County.

Many severe acute respiratory syndrome coronavirus 2 infections have not been detected, reported, or isolated. For community testing programs to locate the most cases under limited testing resources, we developed and evaluated quantitative approaches for geographic targeting of increased coronavirus disease 2019 testing efforts. For every week from December 5, 2021, to July 23, 2022, testing and vaccination data were obtained in ∼340 cities/communities in Los Angeles County, and models were developed to predict which cities/communities would have the highest test positivity 2 weeks ahead. A series of counterfactual scenarios were constructed to explore the additional number of cases that could be detected under targeted testing. The simplest model based on most recent test positivity performed nearly as well as the best model based on most recent test positivity and weekly tests per 100 persons in identifying communities that would maximize the average yield of cases per test in the following 2 weeks and almost as well as the perfect knowledge of the actual positivity 2 weeks ahead. In the counterfactual scenario, increasing testing by 1% 2 weeks ahead and allocating all tests to communities with the top 10% of predicted positivity would yield a 2% increase in detected cases. Simple models based on current test positivity can predict which communities may have the highest positivity 2 weeks ahead and hence could be allocated with more testing resources.

Pre-trained Model-based Software Defect Prediction for Edge-cloud Systems

Edge-cloud computing is a distributed computing infrastructure that brings computation and data storage with low latency closer to clients. As interest in edge-cloud systems grows, research on testing the systems has also been actively studied. However, as with traditional systems, the amount of resources for testing is always limited. Thus, we suggest a function-level just-in-time (JIT) software defect prediction (SDP) model based on a pre-trained model to address the limitation by prioritizing the limited testing resources for the defect-prone functions. The pre-trained model is a transformer-based deep learning model trained on a large corpus of code snippets, and the fine-tuned pre-trained model can provide the defect proneness for the changed functions at a commit level. We evaluate the performance of the three popular pre-trained models (i.e., CodeBERT, GraphCodeBERT, UniXCoder) on edge-cloud systems in within-project and cross-project environments. To the best of our knowledge, it is the first attempt to analyse the performance of the three pre-trained model-based SDP models for edge-cloud systems. As a result, we can confirm that UniXCoder showed the best performance among the three in the WPDP environment. However, we also confirm that additional research is necessary to apply the SDP models to the CPDP environment.

The relationship between controllability, optimal testing resource allocation, and incubation-latent period mismatch as revealed by COVID-19.

The severe shortfall in testing supplies during the initial COVID-19 outbreak and ensuing struggle to manage the pandemic have affirmed the critical importance of optimal supply-constrained resource allocation strategies for controlling novel disease epidemics. To address the challenge of constrained resource optimization for managing diseases with complications like pre- and asymptomatic transmission, we develop an integro partial differential equation compartmental disease model which incorporates realistic latent, incubation, and infectious period distributions along with limited testing supplies for identifying and quarantining infected individuals. Our model overcomes the limitations of typical ordinary differential equation compartmental models by decoupling symptom status from model compartments to allow a more realistic representation of symptom onset and presymptomatic transmission. To analyze the influence of these realistic features on disease controllability, we find optimal strategies for reducing total infection sizes that allocate limited testing resources between 'clinical' testing, which targets symptomatic individuals, and 'non-clinical' testing, which targets non-symptomatic individuals. We apply our model not only to the original, delta, and omicron COVID-19 variants, but also to generically parameterized disease systems with varying mismatches between latent and incubation period distributions, which permit varying degrees of presymptomatic transmission or symptom onset before infectiousness. We find that factors that decrease controllability generally call for reduced levels of non-clinical testing in optimal strategies, while the relationship between incubation-latent mismatch, controllability, and optimal strategies is complicated. In particular, though greater degrees of presymptomatic transmission reduce disease controllability, they may increase or decrease the role of non-clinical testing in optimal strategies depending on other disease factors like transmissibility and latent period length. Importantly, our model allows a spectrum of diseases to be compared within a consistent framework such that lessons learned from COVID-19 can be transferred to resource constrained scenarios in future emerging epidemics and analyzed for optimality.

414P Lessons learnt from clinico-genomic profiling of families with Li Fraumeni Syndrome: The largest case series from the Indian setting

Li Fraumeni Syndrome (LFS) is an inherited cancer predisposition syndrome due to TP53 gene mutation. There is sparse literature on LFS from India owing to limited testing resources and less awareness among medical practitioners.

Surveillance for endemic infectious disease outbreaks: Adaptive sampling using profile likelihood estimation.

Outbreaks of an endemic infectious disease can occur when the disease is introduced into a highly susceptible subpopulation or when the disease enters a network of connected individuals. For example, significant HIV outbreaks among people who inject drugs have occurred in at least half a dozen US states in recent years. This motivates the current study: how can limited testing resources be allocated across geographic regions to rapidly detect outbreaks of an endemic infectious disease? We develop an adaptive sampling algorithm that uses profile likelihood to estimate the distribution of the number of positive tests that would occur for each location in a future time period if that location were sampled. Sampling is performed in the location with the highest estimated probability of triggering an outbreak alarm in the next time period. The alarm function is determined by a semiparametric likelihood ratio test. We compare the profile likelihood sampling (PLS) method numerically to uniform random sampling (URS) and Thompson sampling (TS). TS was worse than URS when the outbreak occurred in a location with lower initial prevalence than other locations. PLS had lower time to outbreak detection than TS in some but not all scenarios, but was always better than URS even when the outbreak occurred in a location with a lower initial prevalence than other locations. PLS provides an effective and reliable method for rapidly detecting endemic disease outbreaks that is robust to this uncertainty.

Controlling Epidemics Through Optimal Allocation of Test Kits and Vaccine Doses Across Networks

Efficient testing and vaccination protocols are critical aspects of epidemic management. To study the optimal allocation of limited testing and vaccination resources in a heterogeneous contact network of interacting susceptible, recovered, and infected individuals, we present a degree-based testing and vaccination model for which we use control-theoretic methods to derive optimal testing and vaccination policies. Within our framework, we find that optimal intervention policies first target high-degree nodes before shifting to lower-degree nodes in a time-dependent manner. Using such optimal policies, it is possible to delay outbreaks and reduce incidence rates to a greater extent than uniform and reinforcement-learning-based interventions, particularly on certain scale-free networks.

SHSE: A subspace hybrid sampling ensemble method for software defect number prediction

Software defect number prediction (SDNP) helps allocate limited testing resources by ranking software modules according to the predicted defect numbers. However, the highly skewed distribution of defects greatly degrades the performance of SDNP models by preventing SDNP models from ranking software modules accurately. This paper introduces a novel subspace hybrid sampling ensemble (SHSE) method based on feature subspace construction, hybrid sampling, and ensemble learning for building high-performance SDNP models. Specifically, we first construct a series of feature subspace to ensure the diversity of base learners. In each of feature subspace, we then use the proposed hybrid sampling method to balance the training subset without losing too much information and introducing lots of noisy data caused by only using undersampling or oversampling techniques. Finally, we train each base learner and combine them by using the proposed weighted ensemble strategy. Experiments are performed on 27 public defect datasets. We compare SHSE with five state-of-the-art resampling-based models and four zero-inflated/hurdle models in terms of the ranking performance measure fault-percentile-average (FPA). To demonstrate the effectiveness of SHSE, two statistical testing methods including Wilcoxon Signed-rank test and Scott–Knott Effect Size Difference test are utilized. Cliff’s δ is also computed for quantifying the difference when there is significant difference between SHSE and each baseline. The experimental results show that SHSE significantly outperforms the baselines and improves the performance over each baseline with as least medium effect size on most datasets. On average, SHSE improves the performance over the resampling-based methods by 8.7% ∼ 14.4% and the zero-inflate/hurdle models by 10.3% ∼ 15.2%. It can be concluded that SHSE is a more promising alternative for software defect number prediction. • Proposing a novel subspace hybrid sampling ensemble method called SHSE. • Comparing with five sampling-based models and four zero-inflated/hurdle models. • Considering both within-project and cross-project defect number prediction scenarios. • Experimental results on 27 datasets with statistical testing show the superiority.

How optimal allocation of limited testing capacity changes epidemic dynamics

Insufficient testing capacity has been a critical bottleneck in the worldwide fight against COVID-19. Optimizing the deployment of limited testing resources has therefore emerged as a keystone problem in pandemic response planning. Here, we use a modified SEIR model to optimize testing strategies under a constraint of limited testing capacity. We define pre-symptomatic, asymptomatic, and symptomatic infected classes, and assume that positively tested individuals are immediately moved into quarantine. We further define two types of testing. Clinical testing focuses only on the symptomatic class. Non-clinical testing detects pre- and asymptomatic individuals from the general population, and a concentration parameter governs the degree to which such testing can be focused on high infection risk individuals. We then solve for the optimal mix of clinical and non-clinical testing as a function of both testing capacity and the concentration parameter. We find that purely clinical testing is optimal at very low testing capacities, supporting early guidance to ration tests for the sickest patients. Additionally, we find that a mix of clinical and non-clinical testing becomes optimal as testing capacity increases. At high but empirically observed testing capacities, a mix of clinical testing and non-clinical testing, even if extremely unfocused, becomes optimal. We further highlight the advantages of early implementation of testing programs, and of combining optimized testing with contact reduction interventions such as lockdowns, social distancing, and masking.

Enhanced growth model of software reliability with generalized inflection S-shaped testing-effort function

The software project manager must plan and conduct testing activities economically and efficiently. Due to the constraints, such as limited testing resources, delivery time, and cost, it isn’t easy to conclude. The software reliability growth models (SRGMs) based on testing-effort, help the project manager in the decision process. Therefore, we reckon the testing effort function (TEF) during model formulation. This paper introduces a new model for estimating the growth of software reliability. This model incorporates generalized inflection S-shaped (GISS) distribution for TEF. Here, the TEF is involved as a time-dependent failure rate function. Besides, the developed model is in perfect debugging environment. Here, we estimate the values of the unknown parameters by the least square estimation (LSE). All the performance measures are calculated using real software failure data-set and comparisons made between the proposed model and the existing models. It is noted that the performance of the proposed model prediction for the total number of faults is more trustworthy.

A rapid, easy, and scalable whole blood monocyte CD169 assay for outpatient screening during SARS-CoV-2 outbreak, and potentially other emerging disease outbreaks.

Objective:The COVID-19 corona virus disease outbreak is globally challenging health systems and societies. Its diagnosis relies on molecular methods, with drawbacks revealed by mass screening. Upregulation of neutrophil CD64 or monocyte CD169 has been abundantly reported as markers of bacterial or acute viral infection, respectively. We evaluated the sensitivity of an easy, one-step whole blood flow cytometry assay to measure these markers within 10 min, as a potential screening test for COVID-19 patients.Methods:Patients (n = 177) with confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection were tested on 10 µL blood and results were compared with reverse transcriptase-quantitative polymerase chain reaction (RT-qPCR).Results:We observed 98% and 100% sensitivity in early-stage (n = 52) and asymptomatic patients (n = 9), respectively. Late-stage patients, who presented for a second control RT-qPCR, were negative for both assays in most cases. Conversely, neutrophil CD64 expression was unchanged in 75% of cases, without significant differences between groups.Conclusion:Monocyte CD169 evaluation was highly sensitive for detecting SARS-CoV-2 infection in first-presentation patients; and it returns to basal level upon infection clearance. The potential ease of fingerprick collection, minimal time-to-result, and low cost rank this biomarker measurement as a potential viral disease screening tool, including COVID-19. When the virus prevalence in the tested population is usually low (1%−10%), such an approach could increase the testing capacity 10 to 100-fold, with the same limited molecular testing resources, which could focus on confirmation purposes only.

Community-Based Testing Sites for SARS-CoV-2 - United States, March 2020-November 2021.

Immediately following the March 13, 2020 declaration of COVID-19 as a national emergency (1), the U.S. government began implementing national testing programs for epidemiologic surveillance, monitoring of frontline workers and populations at higher risk for acquiring COVID-19, and identifying and allocating limited testing resources. Effective testing supports identification of COVID-19 cases; facilitates isolation, quarantine, and timely treatment measures that limit the spread of SARS-CoV-2 (the virus that causes COVID-19); and guides public health officials about the incidence of COVID-19 in a community. A White House Joint Task Force, co-led by the Department of Health and Human Services (HHS) and the Federal Emergency Management Agency (FEMA), created the Community-Based Testing Sites (CBTS) program working with state and local partners (2). This report describes the timeline, services delivered, and scope of the CBTS program. During March 19, 2020-April 11, 2021, the CBTS program conducted 11,661,923 SARS-CoV-2 tests at 8,319 locations across the United States and its territories, including 402,223 (3.5%) administered through Drive-Through Testing, 10,129,142 (86.9%) through Pharmacies+ Testing, and 1,130,558 (9.7%) through Surge Testing programs. Tests administered through the CBTS program yielded 1,176,959 (10.1%) positive results for SARS-CoV-2. Among tested persons with available race data,* positive test results were highest among American Indian or Alaska Native (14.1%) and Black persons (10.4%) and lowest among White persons (9.9%), Asian persons (7.3%), and Native Hawaiian or Other Pacific Islanders (6.4%). Among persons with reported ethnicity, 25.3% were Hispanic, 15.9% of whom received a positive test result. Overall, 82.0% of test results were returned within 2 days, but the percentage of test results returned within 2 days was as low as 40.7% in July 2020 and 59.3% in December 2020 during peak testing periods. Strong partnerships enabled a rapid coordinated response to establish the federally supported CBTS program to improve access to no-charge diagnostic testing, including for frontline workers, symptomatic persons and close contacts, and persons living in high-prevalence areas. In April 2021, the CBTS Pharmacies+ Testing and Surge Testing programs were expanded into the Increasing Community Access to Testing (ICATT) program. As of November 12, 2021, the CBTS and ICATT programs conducted approximately 26.6 million tests with approximately 10,000 active testing sites. Although the CBTS program represented a relatively small portion of overall U.S. SARS-CoV-2 testing, with its successful partnerships and adaptability, the CBTS program serves as a model to guide current community-based screening, surveillance, and disease control programs, and responses to future public health emergencies.

Detection of SARS-CoV-2 RNA in Upper Respiratory Swap Samples by Pooling Method

Background:Widespread and effective use of molecular diagnostic tests is indispensable for protecting public health and containing the severe respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic. More than 1 year into the pandemic, as resources have reached a point of depletion, grouping samples in pools of certain sizes appears to be a reasonable method to reduce both the costs and the processing time without necessitating additional training, equipment, or materials.Aims:To assess whether the pooling strategy that was used in past outbreaks and is used in blood tests prior to transfusion for screening large populations can also be used in SARS CoV-2 tests.Study Design:Diagnostic accuracy study.Methods:This prospective study was conducted with 2815 samples, sent to the coronavirus disease 2019 (COVID-19) Laboratory of our hospital between February 12 and 21, 2021, to be tested for the presence of SARS-CoV-2. The samples were examined individually and in pools of five 100 μl taken from each sequential sample, using 3 different SARS-CoV-2 reverse transcription-polymerase chain reaction (RT-PCR) kits, the Allplex™ 2019-nCoV Assay kit (Seegene, Republic of Korea), the GeneMAP™ 2019-nCoV detection V.3 kit (GenMark, Türkiye), and the Bio-Speedy™ SARS-CoV-2 Double Gene™ RT-qPCR kit (Bioeksen, Türkiye) on the BioRAD CFX96™ Touch (Bio-Rad Laboratories Inc., Hercules, CA, USA) platform available in our laboratory.Results:Following the extraction of serial dilutions prepared from the SARS-CoV-2 RNA positive (cycle of threshold: 20) sample, the standard curves of RT-PCR were analyzed. By evaluating the efficiency (E) values, all 3 kits showed high sensitivity and similar results; while the highest level was detected with the Allplex™ 2019-nCoV Assay kit in the nucleocapsid (N) gene (E: 124%), the lowest was detected with the Double Gene™ RT-qPCR kit in the N and ORF 1ab genes (E: 90%). Of the samples included in the study, only 1 positive sample with low viral load was found to be negative when studied by pooling. The total number of kits to be used in pooled tests and then to individually retest the 5 samples in positive pools was calculated as 827 and the savings rate as 69.91% (1968/2815).Conclusion:The pooling strategy is an effective approach to extend the impact of limited testing resources and reagents available in certain periods of the COVID-19 pandemic. Testing by pooling samples requires improvement of RNA extraction methods and careful monitoring of RT-PCR test sensitivity to avoid missing low-positive entities. Therefore, based on the prevalence of COVID-19 in their regions, laboratories should conduct their own validation of pooling studies for RNA extraction and amplification methods they use.

Efficient and targeted COVID-19 border testing via reinforcement learning

Throughout the coronavirus disease 2019 (COVID-19) pandemic, countries haverelied on a variety of ad hoc border control protocols to allow for non-essential travel while safeguarding public health, from quarantining all travellers to restricting entry from select nations on the basis of population-level epidemiological metrics such as cases, deaths or testing positivity rates1,2. Here we report the design and performance of a reinforcement learning system, nicknamed Eva. In the summer of 2020, Eva was deployed across all Greek borders to limit the influx of asymptomatic travellers infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and to inform border policies through real-time estimates of COVID-19 prevalence. In contrast to country-wide protocols, Eva allocated Greece's limited testing resources on the basis of incoming travellers' demographic information and testing results from previous travellers. By comparing Eva's performance against modelled counterfactual scenarios, we show that Eva identified 1.85 times as many asymptomatic, infected travellers as random surveillance testing, with up to 2-4 times as many during peak travel, and 1.25-1.45 times as many asymptomatic, infected travellers as testing policies that utilize only epidemiological metrics. We demonstrate that this latter benefit arises, at least partially, because population-level epidemiological metrics had limited predictive value for the actual prevalence of SARS-CoV-2 among asymptomatic travellers and exhibited strong country-specific idiosyncrasies in the summer of 2020. Our results raise serious concerns on the effectiveness of country-agnostic internationally proposed border control policies3 that are based on population-level epidemiological metrics. Instead, our work represents a successful example of the potential of reinforcement learning and real-time data for safeguarding public health.

A Novel Effort Measure Method for Effort-Aware Just-in-Time Software Defect Prediction

Just-in-time software defect prediction (JIT-SDP) is a fine-grained software defect prediction technology, which aims to identify the defective code changes in software systems. Effort-aware software defect prediction is a software defect prediction technology that takes into consideration the cost of code inspection, which can find more defective code changes in limited test resources. The traditional effort-aware defect prediction model mainly measures the effort based on the number of lines of code (LOC) and rarely considers additional factors. This paper proposes a novel effort measure method called Multi-Metric Joint Calculation (MMJC). When measuring the effort, MMJC takes into account not only LOC, but also the distribution of modified code across different files (Entropy), the number of developers that changed the files (NDEV) and the developer experience (EXP). In the simulation experiment, MMJC is combined with Linear Regression, Decision Tree, Random Forest, LightGBM, Support Vector Machine and Neural Network, respectively, to build the software defect prediction model. Several comparative experiments are conducted between the models based on MMJC and baseline models. The results show that indicators ACC and [Formula: see text] of the models based on MMJC are improved by 35.3% and 15.9% on average in the three verification scenarios, respectively, compared with the baseline models.