Learning linear non-Gaussian directed acyclic graph with diverging number of nodes

An acyclic model, often depicted as a directed acyclic graph (DAG), has been widely employed to represent directional causal relations among collected nodes. In this article, we propose an efficient method to learn linear non-Gaussian DAG in high dimensional cases, where the noises can be of any continuous non-Gaussian distribution. The proposed method leverages the concept of topological layer to facilitate the DAG learning, and its theoretical justification in terms of exact DAG recovery is also established under mild conditions. Particularly, we show that the topological layers can be exactly reconstructed in a bottom-up fashion, and the parent-child relations among nodes can also be consistently established. The established asymptotic DAG recovery is in sharp contrast to that of many existing learning methods assuming parental faithfulness or ordered noise variances. The advantage of the proposed method is also supported by the numerical comparison against some popular competitors in various simulated examples as well as a real application on the global spread of COVID-19. ©2022 Ruixuan Zhao, Xin He, and Junhui Wang.

EPIDEMICS FROM THE EYE OF THE PATHOGEN

While a common trend in disease modeling is to develop models of increasing complexity, it was recently pointed out that outbreaks appear remarkably simple when viewed in the incidence vs. cumulative cases (ICC) plane. This article details the theory behind this phenomenon by analyzing the stochastic Susceptible, Infected, Recovered (SIR) model in the cumulative cases domain. We prove that the Markov chain associated with this model reduces, in the ICC plane, to a pure birth chain for the cumulative number of cases, whose limit leads to an independent increments Gaussian process that fluctuates about a deterministic ICC curve. We calculate the associated variance and quantify the additional variability due to estimating incidence over a finite period of time. We also illustrate the universality brought forth by the ICC concept on real-world data for Influenza A and for the COVID-19 outbreak in Arizona. © 2022 SIAM.Published by SIAM.

Impact of Upsurge in Covid-19 Cases on Indian Stock Market: A Machine Learning Approach

In the present study, the influence of the surge in pandemic cases and fatalities due to pandemics on the stock performance of NIFTY 50 have been analyzed by employing a regression analysis algorithm using Python Software. The data have been collected for 27 months starting from 1st Jan 2020 to 31st March 2022 and for the application of machine learning tools the data connected to the stock market and COVID 19 have been integrated into the first phase and thereafter preprocessing has been carried out on the data to bring uniformity to data in the second phase. After preprocessing in the third phase data has been evaluated using five leading regression algorithms. The findings of the study reflected that COVID 19 figures and fatalities have severally impacted the stock market returns of the leading index i.e., NIFTY 50. Further, it was gathered from the study that REPTree regression would be a better fit to the model and Gaussian Process would be least fitted to the model as REPTree the lower values of MAE, RMSE, RAE, and R2 error in case of performance evaluation of upsurge in COVID 19 fatalities and surge in stock market returns. © 2022 IEEE.

Multi-Output Gaussian Process-Based Data Augmentation for Multi-Building and Multi-Floor Indoor Localization

Location fingerprinting based on Received Signal Strength Indicator (RSSI) has become a mainstream indoor localization technique due to its advantage of not requiring the installation of new infrastructure and the modification of existing devices, especially given the prevalence of Wi-Fi-enabled devices and the ubiquitous Wi-Fi access in modern buildings. The use of Artificial Intelligence (AI)/Machine Learning (ML) technologies like Deep Neural Networks (DNNs) makes location fingerprinting more accurate and reliable, especially for large-scale multi-building and multi-floor indoor localization. The application of DNNs for indoor localization, however, depends on a large amount of preprocessed and deliberately-labeled data for their training. Considering the difficulty of the data collection in an indoor environment, especially under the current epidemic situation of COVID-19, we investigate three different methods of RSSI data augmentation based on Multi-Output Gaussian Process (MOGP), i.e., by a single floor, by neighboring floors, and by a single building;unlike Single-Output Gaussian Process (SOGP), MOGP can take into account the correlation among RSSI observations from multiple Access Points (APs) deployed closely to each other (e.g., APs on the same floor of a building) by collectively handling them. The feasibility of the MOGP-based RSSI data augmentation is demonstrated through experiments using a recently-published work based on Recurrent Neural Network (RNN) indoor localization model and the UJIIndoorLoc, i.e., the most popular publicly-available multi-building and multi-floor indoor localization database;the RNN model trained with the UJIIndoorLoc database, augmented by using the whole RSSI data of a building in fitting an MOGP model (i.e., by a single building), outperforms the other two augmentation methods and reduces the mean three-dimensional positioning error from 8.62 m to 8.42 m in comparison to the RNN model trained with the original UJIIndoorLoc database. © 2022 IEEE.

AI-Powered Semantic Segmentation and Fluid Volume Calculation of Lung CT Images in COVID-19 Patients

COVID-19 pandemic is a deadly disease spreading very fast. People with the confronted immune system are susceptible to many health conditions. A highly significant condition is pneumonia, which is found to be the cause of death in the majority of patients. The main purpose of this study is to find the volume of GGO and consolidation of a COVID-19 patient, so that the physicians can prioritize the patients. Here, we used transfer learning techniques for segmentation of lung CTs with the latest libraries and techniques which reduces training time and increases the accuracy of the AI Model. This system is trained with DeepLabV3 + network architecture and model ResNet50 with ImageNet weights. We used different augmentation techniques like Gaussian noise, horizontal shift, color variation, etc., to get to the result. Intersection over Union (IoU) is used as the performance metrics. The IoU of lung masks is predicted as 99.78% and that of infected masks is as 89.01%. Our work effectively measures the volume of infected region by calculating the volume of infected and lung mask region of the patients. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Identifying the Effective Restriction and Vaccination Policies During the COVID-19 Crisis in Sydney: A Machine Learning Approach

This study identified effective COVID-19 restriction policies and the best times to deploy them to minimise locally acquired COVID-19 cases in Sydney. We normalised stringency levels of individual COVID-19 policies, usage levels of urban mobility, and vaccination rates to establish unbiased multivariate time-series features. We introduced the time-lag from 1 day to 15 d before when the governments have officially announced the number of locally acquired COVID-19 cases to the multivariate features. This time-lag dimension allows us to decide critical timings for announcing various COVID-19 related policies and vaccinations to control rapidly increasing infections. We used principal component analysis (PCA) to reduce the dimensions of the multivariate features. A Gaussian process regression (GPR) estimated the daily number of locally acquired COVID-19 cases based on the reduced dimensional features. The model outperformed diverse parametric and non-parametric models in estimating the daily number of infections. We successfully identified effective restriction policies and the best times to implement them to minimise the rate of confirmed COVID-19 cases by analysing PCA coefficients and kernel functions in GPR. © 2022, Springer Nature Switzerland AG.

Analysis of Prediction Data for the Third Wave of COVID-19 in Bogor Regency

The COVID-19 pandemic is far from over. The government has carried out several policies to suppress the development of COVID-19 is no exception in Bogor Regency. However, the public still has to be vigilant especially now we will face a year-end holiday that can certainly be a trigger for the third wave of COVID-19. Therefore, researchers aim to make predictions of the increase in positive cases, especially in the Bogor Regency area to help the government in making policies related to COVID-19. The algorithms used are Gaussian Process, Linear Regression, and Random Forest. Each Algorithm is used to predict the total number of COVID-19 cases for the next 21 days. Researchers approached the Time Series Forecasting model using datasets taken from the COVID-19 Information Center Coordinationn Center website. The results obtained in this study, the method that has the highest probability of accurate and appropriate data contained in the Gaussian Process method. Prediction data on the Linear Regression method has accurate results with actual data that occur with Root Mean Square Error 1202.6262. © 2021 IEEE.

Machine Learning Based Prediction Models for the Percentage Deaths Due to COVID-19

Worldwide COVID-19 pandemic is currently affecting all countries and led to loss of human life. A lot of scientific research are conducted in different areas to improve the future response. The purpose of the project is to use Machine learning (ML) techniques in predicting COVID-19 deaths which will enhance the hospitals response. This paper contributes by developing models that can predict COVID-19 deaths based on three factors: total number of elderly patients (greater than 65 years), diabetic patients, and smoking patients. Gaussian Process Regression (GPR), Support Vector Regression (SVR), Artificial Neural Network-Multi Layer Perceptron (ANN-MLP), and Artificial Neural Network-nonlinear autoregressive network with exogenous inputs (ANN-NARX) approaches are used to build the predictive models. All models are trained and tested using trusted data reported by the World Health Organization (WHO) in various countries. The developed models revealed very good results with excellent prediction rate and performance, especially GPR, which has the best performance. Also, it showed that region-based predictive models are more suitable than a single general model. The GPR predictive model showed the best performance compared to other models. © 2021 IEEE.

Early Detection of COVID-19 Hotspots Using Spatio-Temporal Data

Recently, the Centers for Disease Control and Prevention (CDC) has worked with other federal agencies to identify counties with increasing coronavirus disease 2019 (COVID-19) incidence (hotspots) and offers support to local health departments to limit the spread of the disease. Understanding the spatio-temporal dynamics of hotspot events is of great importance to support policy decisions and prevent large-scale outbreaks. This paper presents a spatio-temporal Bayesian framework for early detection of COVID-19 hotspots (at the county level) in the United States. We assume both the observed number of cases and hotspots depend on a class of latent random variables, which encode the underlying spatio-temporal dynamics of the transmission of COVID-19. Such latent variables follow a zero-mean Gaussian process, whose covariance is specified by a non-stationary kernel function. The most salient feature of our kernel function is that deep neural networks are introduced to enhance the model's representative power while still enjoying the interpretability of the kernel. We derive a sparse model and fit the model using a variational learning strategy to circumvent the computational intractability for large data sets. Our model demonstrates better interpretability and superior hotspot-detection performance compared to other baseline methods. IEEE

A Machine Learning Approach to Daily Capacity Planning in E-Commerce Logistics

Due to the accelerated activity in e-commerce especially since the COVID-19 outbreak, the congestion in the transportation systems is continually increasing, which affects on-time delivery of regular parcels and groceries. An important constraint is the fact that a given number of delivery drivers have a limited amount of time and daily capacity, leading to the need for effective capacity planning. In this paper, we employ a Gaussian Process Regression (GPR) approach to predict the daily delivery capacity of a fleet starting their routes from a cross-dock depot and for a specific time slot. Each prediction specifies how many deliveries in total the drivers in a given cross-dock can make for a certain time-slot of the day. Our results show that the GPR model outperforms other state-of-the-art regression methods. We also improve our model by updating it daily using shipments delivered within the day, in response to unexpected events during the day, as well as accounting for special occasions like Black Friday or Christmas. © 2022, Springer Nature Switzerland AG.