Learning Social Meta-knowledge for Nowcasting Human Mobility in Disaster

Human mobility nowcasting is a fundamental research problem for intelligent transportation planning, disaster responses and management, etc. In particular, human mobility under big disasters such as hurricanes and pandemics deviates from its daily routine to a large extent, which makes the task more challenging. Existing works mainly focus on traffic or crowd flow prediction in normal situations. To tackle this problem, in this study, disaster-related Twitter data is incorporated as a covariate to understand the public awareness and attention about the disaster events and thus perceive their impacts on the human mobility. Accordingly, we propose a Meta-knowledge-Memorizable Spatio-Temporal Network (MemeSTN), which leverages memory network and meta-learning to fuse social media and human mobility data. Extensive experiments over three real-world disasters including Japan 2019 typhoon season, Japan 2020 COVID-19 pandemic, and US 2019 hurricane season were conducted to illustrate the effectiveness of our proposed solution. Compared to the state-of-the-art spatio-temporal deep models and multivariate-time-series deep models, our model can achieve superior performance for nowcasting human mobility in disaster situations at both country level and state level. © 2023 ACM.

It's about Time: Analytical Time Periodization

This paper presents a novel approach to the problem of time periodization, which involves dividing the time span of a complex dynamic phenomenon into periods that enclose different relatively stable states or development trends. The challenge lies in finding such a division of the time that takes into account diverse behaviours of multiple components of the phenomenon while being simple and easy to interpret. Despite the importance of this problem, it has not received sufficient attention in the fields of visual analytics and data science. We use a real-world example from aviation and an additional usage scenario on analysing mobility trends during the COVID-19 pandemic to develop and test an analytical workflow that combines computational and interactive visual techniques. We highlight the differences between the two cases and show how they affect the use of different techniques. Through our investigation of possible variations in the time periodization problem, we discuss the potential of our approach to be used in various applications. Our contributions include defining and investigating an earlier neglected problem type, developing a practical and reproducible approach to solving problems of this type, and uncovering potential for formalization and development of computational methods.

Multi-step CNN forecasting for COVID-19 multivariate time-series

The new coronavirus (COVID-19) has spread to over 200 countries, with over 36 million confirmed cases as of October 10, 2020. As a result, numerous machine learning models capable of forecasting the epidemic worldwide have been produced. This paper reviews and summarizes the most relevant machine learning forecasting models for COVID-19. The dataset is derived from the world health organization (WHO) COVID-19 dashboard, and it contains official daily counts of COVID-19 cases, fatalities, and vaccination use reported by countries, territories, and regions. We propose various convolutional neural network (CNN) based models such as CNN, single exponential smoothing CNN (S-CNN), moving average CNN (MA-CNN), smoothed moving average CNN (SMA-CNN), and moving average smoothed CNN (MAS-CNN). Here, MAPE and MSE are used to assess the suggested models. MAPE is frequently used to compare accuracy across time series with different scales. MSE, the model must strive for a total forecast equal to the entire demand. That is, optimizing MSE seeks to create a forecast that is right on average and so unbiased. The final result shows that SMA-CNN outperformed its baselines in both MAPE and MSE. The main contribution of this novel forecasting approach is a more accurate result as a base of the strategy of preventing COVID-19 spreads. © 2023, Universitas Ahmad Dahlan. All rights reserved.

Exploring the short-term and long-term linkages between carbon price and influence factors considering COVID-19 impact.

Because of global lock-downs caused by the unexpected COVID-19, the interactions between emission trading and related markets have changed significantly compared to the pre-COVID-19 period. Considering the pandemic effect, this paper established an integrated system to identify the relationship trajectories between carbon trading market and impact factors. A noise-assisted multivariate empirical mode decomposition (N-A MEMD) method was utilized to simultaneously decompose the original multi-dimensional time series into intrinsic mode functions (IMFs), after which the Lempel-Ziv (LZ) complexity algorithm was applied to reconstruct the IMFs into high-frequency (HF), low-frequency (LF), and trend modules. Vector autoregression (VAR) and vector error correction (VEC) models were then used to systematically simulate the correlations. The time span was split into pre-COVID-19 and post-COVID-19 periods for comparison, and the mobility trends data during the outbreak period released by the Apple company was chosen to reflect the pandemic effects. The empirical analysis results revealed the energy prices, macroeconomic index, and exchange rate are the main external impact factors of carbon price in the short term. Summarizing from the cointegration models over the long term, the market stability reserve (MSR) mechanism was found to have ability on stabilizing the carbon price under the epidemic shock. Furthermore, the COVID-19 was found to complicate the relationships between carbon price and influence factors, which resulted in fluctuating markets.

Identifying, exploring, and interpreting time series shapes in multivariate time intervals

We introduce a concept of episode referring to a time interval in the development of a dynamic phenomenon that is characterized by multiple time-variant attributes. A data structure representing a single episode is a multivariate time series. To analyse collections of episodes, we propose an approach that is based on recognition of particular patterns in the temporal variation of the variables within episodes. Each episode is thus represented by a combination of patterns. Using this representation, we apply visual analytics techniques to fulfil a set of analysis tasks, such as investigation of the temporal distribution of the patterns, frequencies of transitions between the patterns in episode sequences, and co-occurrences of patterns of different variables within same episodes. We demonstrate our approach on two examples using real-world data, namely, dynamics of human mobility indicators during the COVID-19 pandemic and characteristics of football team movements during episodes of ball turnover. © 2023 The Author(s)

Superhighways and roads of multivariate time series shock transmission: Application to cryptocurrency, carbon emission and energy prices

Inferring the heterogeneous connection pattern of a networked system of multivariate time series observations is a key issue. In finance, the topological structure of financial connectedness in a network of assets can be a central tool for risk measurement. Against this, we propose a topological framework for variance decomposition analysis of multivariate time series in time and frequency domains. We build on the network representation of time–frequency generalized forecast error variance decomposition (GFEVD), and design a method to partition its maximal spanning tree into two components: (a) superhighways, i.e. the infinite incipient percolation cluster, for which nodes with high centrality dominate;(b) roads, for which low centrality nodes dominate. We apply our method to study the topology of shock transmission networks across cryptocurrency, carbon emission and energy prices. Results show that the topologies of short and long run shock transmission networks are starkly different, and that superhighways and roads considerably vary over time. We further document increased spillovers across the markets in the aftermath of the COVID-19 outbreak, as well as the absence of strong direct linkages between cryptocurrency and carbon markets. © 2023 Elsevier B.V.

VECTOR AUTOREGRESSIVE INTEGRATING MOVING AVERAGE (VARIMA) MODEL OF COVID-19 PANDEMIC AND OIL PRICE

Purpose: A coronavirus associated with severe respiratory syndrome has created Coronavirus Disease 2019 (COVID-19), a highly contagious illness that affects the entire world population. On the other hand, COVID-19 is having a direct impact on human life because of its proliferation. So, the study's goal is to forecast and analyze the impact of the COVID-19 pandemic and the oil price utilizing multiple time series analysis methods (VARIMA model). Theoretical framework: Recent literature has reported that the multivariate time series is robust model for forecasting and analyzing dynamic relationship between series, while the univariate ARIMA model has been generalized to include vector variables, that is an extension of its capabilities. The VAR (p) model analyzes the interdependence between two or more series but does not take into account the impact of shocks at various time variable delays. Design/methodology/approach: This study uses VARMA (p, q) model which links a set of variables to their prior iterations as well as those of other variables and shocks to those same variables. Sample data concerning the COVID-19 pandemic and oil price was globally provided. It contains daily observations of them variables for the years 2020-2022. Findings: The best model is VARIMA (2,1,2), and the results shown that the oil price is not only influenced by itself but also influenced by the Covid-19 pandemic. Moreover, the standard error grows over time of the forecast. Research, Practical & Social implications: The best model is sound for short-term forecasting but unstable for long-term forecasting. Future researchers can integrate factors across areas. Include tourism demand and industry variables in modeling. Originality/value: Collecting COVID-19 pandemic data and oil price series in a modern model that is a multivariate time series model with a high predicted level of model accuracy between these variables in order to predict and analyze the effects between them series and estimate the interaction between these two series with the most recent data is the value of this study, and then offers merchants the chance to comprehend the forecasting of oil price throughout the covid-19 effects as well as the associated risks. © 2022 AOS-Estratagia and Inovacao. All rights reserved.

Bootstrapping Network Autoregressive Models for Testing Linearity

We develop methodology for network data with special attention to epidemic network spatio-temporal structures. We provide estimation methodology for linear network autoregressive models for both continuous and count multivariate time series. A study of non-linear models for inference under the assumption of known network structure is provided. We propose a family of test statistics for testing linearity of the imposed model. In particular, we compare empirically two bootstrap versions of a supremum-type quasi-score test. Synthetic data are employed to demonstrate the validity of the methodological results. Finally, an epidemic application of the proposed methodology to daily COVID-19 cases detected on province-level geographical network in Italy complements the work. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Evolution of global music trends: An exploratory and predictive approach based on Spotify data

Music listening choices are considered to be a factor capable of measuring people's emotions. Thanks to the explosion of streaming music applications in recent years, it is possible to describe listening trends of the global population based on emotional features. In this paper we have analysed the most popular songs from 52 countries on Spotify through their features of danceability, positivity and intensity. This analysis allows exploring how these song features reflect mood trends along with other contextual factors that may affect the population's listening behaviour, such as the weather or the influence of the COVID-19 pandemic. Finally, we have proposed a multivariate time series model to predict the preferred type of music in those countries based on their previous music listening patterns and the contextual factors. The results show some relevant behavioural changes in these patterns due to the effect of the pandemic. Furthermore, the resulting prediction model enables forecasting the type of music listened to in three different groups of countries in the next 4 months with an error around 1%. These results may help to better understand streaming music consumption in businesses related to the music and marketing industry. © 2022 Elsevier B.V.

BiT-MAC: Mortality prediction by bidirectional time and multi-feature attention coupled network on multivariate irregular time series.

Mortality prediction is crucial to evaluate the severity of illness and assist in improving the prognosis of patients. In clinical settings, one way is to analyze the multivariate time series (MTSs) of patients based on their medical data, such as heart rates and invasive mean arterial blood pressure. However, this suffers from sparse, irregularly sampled, and incomplete data issues. These issues can compromise the performance of follow-up MTS-based analytic applications. Plenty of existing methods try to deal with such irregular MTSs with missing values by capturing the temporal dependencies within a time series, yet in-depth research on modeling inter-MTS couplings remains rare and lacks model interpretability. To this end, we propose a bidirectional time and multi-feature attention coupled network (BiT-MAC) to capture the temporal dependencies (i.e., intra-time series coupling) and the hidden relationships among variables (i.e., inter-time series coupling) with a bidirectional recurrent neural network and multi-head attention, respectively. The resulting intra- and inter-time series coupling representations are then fused to estimate the missing values for a more robust MTS-based prediction. We evaluate BiT-MAC by applying it to the missing-data corrupted mortality prediction on two real-world clinical datasets, i.e., PhysioNet'2012 and COVID-19. Extensive experiments demonstrate the superiority of BiT-MAC over cutting-edge models, verifying the great value of the deep and hidden relations captured by MTSs. The interpretability of features is further demonstrated through a case study.

Improving performance of deep learning predictive models for COVID-19 by incorporating environmental parameters.

The Coronavirus disease 2019 (COVID-19) pandemic has severely crippled the economy on a global scale. Effective and accurate forecasting models are essential for proper management and preparedness of the healthcare system and resources, eventually aiding in preventing the rapid spread of the disease. With the intention to provide better forecasting tools for the management of the pandemic, the current research work analyzes the effect of the inclusion of environmental parameters in the forecasting of daily COVID-19 cases. Three univariate variants of the long short-term memory (LSTM) model (basic/vanilla, stacked, and bi-directional) were employed for the prediction of daily cases in 9 cities across 3 countries with varying climatic zones (tropical, sub-tropical, and frigid), namely India (New Delhi and Nagpur), USA (Yuma and Los Angeles) and Sweden (Stockholm, Skane, Uppsala and Vastra Gotaland). The results were compared to a basic multivariate LSTM model with environmental parameters (temperature (T) and relative humidity (RH)) as additional inputs. Periods with no or minimal lockdown were chosen specifically in these cities to observe the uninhibited spread of COVID-19 and explore its dependence on daily environmental parameters. The multivariate LSTM model showed the best overall performance; the mean absolute percentage error (MAPE) showed an average of 64% improvement from other univariate models upon the inclusion of the above environmental parameters. Correlation with temperature was generally positive for the cold regions and negative for the warm regions. RH showed mixed correlations, most likely driven by its temperature dependence and effect of allied local factors. The results suggest that the inclusion of environmental parameters could significantly improve the performance of LSTMs for predicting daily cases of COVID-19, although other positive and negative confounding factors can affect the forecasting power.

Multivariate Time Series Forecasting using ARIMAX, SARIMAX, and RNN-based Deep Learning Models on Electricity Consumption

Growing energy consumption has been a contemporary problem, especially in the climate crisis and the COVID-19 pandemic. Many statistical reports have stated that there is an increase in energy consumption from residential households to the industrial sector. Electricity consumption forecasting is extremely important as it supports power system decision-making and management. In this paper, traditional ARIMAX and SARIMAX forecasting models and RNN-based deep learning models were used to model the electricity consumption historical data of a two-storied house located in Houston, Texas, USA. The features used in the modeling process include the daily-average electricity consumption historical data of the two-storied house, day category (weekday, weekend, vacation day, and COVID-lockdown), and weather-related variables. Each model's respective error performance on the testing dataset is compared. The result showed that RNN-based deep learning models outperformed the traditional ARIMAX and SARIMAX models in forecasting the daily-average electricity consumption of the two-storied house and that the performance of the RNN-based deep learning models doesn't differ significantly from each other. © 2022 IEEE.

Mortality Prediction with Bidirectional Coupled and Gumbel Subset Network on Irregularly Multivariate Time Series

Mortality prediction is a crucial challenge because of multivariate time series (MTS) complexity, which are sparse, irregularly, asynchronous and hold missing values for various reasons in a single acquisition. Various methods are proposed to deal with missing values for the final mortality prediction. However, existing models only capture the temporal dependencies within a time series and are inefficient to capture the dependencies between time series to rebuild missing values for mortality prediction. To address these challenges, in this paper, we present an end-to-end imputation and mortality prediction model, named bidirectional coupled and Gumbel subset network (BiCGSN), for mortality prediction with such irregularly multivariate time series. Our proposed model (BiCGSN) uses a recurrent network to learn the temporal dependencies (intra-time series couplings) and uses a Gumbel selector on multi-head attention to obtain the relationship between the variables (inter-time series couplings) in the forward and backward directions. Then the learned bidirectional inter-and intra-time series couplings are fused to impute missing values for further mortality prediction. We evaluate our model on PhysioNet2012 and COVID-19 datasets to imputation and predict mortality. Experiments show that BiCGSN obtains the AUC 0.869 and 0.911 on two real-world datasets respectively and outperforms all the baselines. © 2022 IEEE.

Identifying, exploring, and interpreting time series shapes in multivariate time intervals

We introduce a concept of episode referring to a time interval in the development of a dynamic phenomenon that is characterized by multiple time-variant attributes. A data structure representing a single episode is a multivariate time series. To analyse collections of episodes, we propose an approach that is based on recognition of particular patterns in the temporal variation of the variables within episodes. Each episode is thus represented by a combination of patterns. Using this representation, we apply visual analytics techniques to fulfil a set of analysis tasks, such as investigation of the temporal distribution of the patterns, frequencies of transitions between the patterns in episode sequences, and co-occurrences of patterns of different variables within same episodes. We demonstrate our approach on two examples using real-world data, namely, dynamics of human mobility indicators during the COVID-19 pandemic and characteristics of football team movements during episodes of ball turnover.

Evolution of global music trends: An exploratory and predictive approach based on spotify data

Music listening choices are considered to be a factor capable of measuring people’s emotions. Thanks to the explosion of streaming music applications in recent years, it is possible to describe listening trends of the global population based on emotional features. In this paper we have analysed the most popular songs from 52 countries on Spotify through their features of danceability, positivity and intensity. This analysis allows exploring how these song features reflect mood trends along with other contextual factors that may affect the population’s listening behaviour, such as the weather or the influence of the COVID-19 pandemic. Finally, we have proposed a multivariate time series model to predict the preferred type of music in those countries based on their previous music listening patterns and the contextual factors. The results show some relevant behavioural changes in these patterns due to the effect of the pandemic. Furthermore, the resulting prediction model enables forecasting the type of music listened to in three different groups of countries in the next 4 months with an error around 1%. These results may help to better understand streaming music consumption in businesses related to the music and marketing industry.

Forecasting Crude Oil Prices with Major S&P 500 Stock Prices: Deep Learning, Gaussian Process, and Vine Copula

This paper introduces methodologies in forecasting oil prices (Brent and WTI) with multivariate time series of major S&P 500 stock prices using Gaussian process modeling, deep learning, and vine copula regression. We also apply Bayesian variable selection and nonlinear principal component analysis (NLPCA) for data dimension reduction. With a reduced number of important covariates, we also forecast oil prices (Brent and WTI) with multivariate time series of major S&P 500 stock prices using Gaussian process modeling, deep learning, and vine copula regression. To apply real data to the proposed methods, we select monthly log returns of 2 oil prices and 74 large-cap, major S&P 500 stock prices across the period of February 2001–October 2019. We conclude that vine copula regression with NLPCA is superior overall to other proposed methods in terms of the measures of prediction errors.

Spatial Weighted Robust Clustering of Multivariate Time Series Based on Quantile Dependence With an Application to Mobility During COVID-19 Pandemic

In this article, a fuzzy clustering model for multivariate time series based on the quantile cross-spectral density and principal component analysis is extended by including: 1) a weighting system which assigns a weight to each principal component in accordance with its importance concerning the underlying clustering structure and 2) a penalization term allowing to take into account the spatial information. The iterative solutions of the new model, which employs the exponential distance in order to gain robustness against outlying series, are derived. A simulation study shows that the weighting system substantially enhances the effectiveness of the former approach. The behavior of the extended model in terms of the spatial penalization term is also analyzed. An application involving multivariate time series of mobility indicators concerning COVID-19 pandemic highlights the usefulness of the proposed technique.

Multivariate time series analysis on variables that influence pandemic expansion

The ongoing COVID-19 pandemic has wreaked havoc on social and economic systems worldwide. The variance in the rapidly increasing number of illnesses and deaths in each country is primarily due to national policies and actions. As a result, governments and institutions need to get insights into the critical factors influencing COVID-19 future case counts to properly manage the adverse effects of pandemics and promptly prepare appropriate measures. Thus, in this paper, we conduct extensive experiments on the real-world covid-19 datasets to examine the important factors influencing in the pandemic growth. In particular, we perform an exploratory data analysis to get the statistic and characteristics of multivariate time-series data on pandemic dynamic. Also, we utilize a statistical measure such as Pearson correlation to compute the relations of the past on the future daily new cases. The experimental results demonstrate that some restrictions have a positive effect on daily new confirmed cases at the early stage of the local pandemic transmission. Also, the results show that the early trend of COVID-19 can be explained well by human mobility in various categories. Thus, our proposed framework can be served as a guideline for future pandemic prevention and control decision-making. © 2022 IEEE.

Classifying Anomalous Members in a Collection of Multivariate Time Series Data Using Large Deviations Principle: An Application to COVID-19 Data

Anomaly detection for time series data is often aimed at identifying extreme behaviors within an individual time series. However, identifying extreme trends relative to a collection of other time series is of significant interest, like in the fields of public health policy, social justice and pandemic propagation. We propose an algorithm that can scale to large collections of time series data using the concepts from the theory of large deviations. Exploiting the ability of the algorithm to scale to high-dimensional data, we propose an online anomaly detection method to identify anomalies in a collection of multivariate time series. We demonstrate the applicability of the proposed Large Deviations Anomaly Detection (LAD) algorithm in identifying counties in the United States with anomalous trends in terms of COVID-19 related cases and deaths. Several of the identified anomalous counties correlate with counties with documented poor response to the COVID pandemic. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Comparative Study between Univariate and Multivariate Time Series Models for COVID-19 Forecasting

COVID-19, a disease produced by the SARS-CoV-2 virus, has had and continues to have a major influence on humankind. This pandemic has wreaked havoc on the global economy, pushing governments to take drastic steps to control its spread. Forecasting the growth of COVID-19 can assist healthcare providers, policymakers, manufacturers, and merchants predict the pandemic's recurrence and the general public to have faith in the decisions made by them. Various existing findings showed that time-series techniques could learn and scale to properly anticipate how many people would be harmed by Covid-19 in the future. In this research, we did a comparative analysis of univariate time series models and multivariate time series models for confirming a better model at the end. As a result, we aim to bring out a time series model that is more suitable for forecasting the progression of pandemics worldwide, thus being a more reliable model. The research results showed that multivariate time series forecasting produced much better results for long-range than univariate time series models, which showed better results when expecting shorter periods. © 2021 IEEE.