Night-time population consistently explains the transmission dynamics of coronavirus disease 2019 in three megacities in Japan.

Background: Mobility data are crucial for understanding the dynamics of coronavirus disease 2019 (COVID-19), but the consistency of the usefulness of these data over time has been questioned. The present study aimed to reveal the relationship between the transmissibility of COVID-19 in Tokyo, Osaka, and Aichi prefectures and the daily night-time population in metropolitan areas belonging to each prefecture. Methods: In Japan, the de facto population estimated from GPS-based location data from mobile phone users is regularly monitored by Ministry of Health, Labor, and Welfare and other health departments. Combined with this data, we conducted a time series linear regression analysis to explore the relationship between daily reported case counts of COVID-19 in Tokyo, Osaka, and Aichi, and night-time de facto population in downtown areas estimated from mobile phone location data, from February 2020 to May 2022. As an approximation of the effective reproduction number, the weekly ratio of cases was used. Models using night-time population with lags ranging from 7 to 14 days were tested. In time-varying regression analysis, the night-time population level and the daily change in night-time population level were included as explanatory variables. In the fixed-effect regression analysis, the inclusion of either the night-time population level or daily change, or both, as explanatory variables was tested, and autocorrelation was adjusted by introducing first-order autoregressive error of residuals. In both regression analyses, the lag of night-time population used in best fit models was determined using the information criterion. Results: In the time-varying regression analysis, night-time population level tended to show positive to neutral effects on COVID-19 transmission, whereas the daily change of night-time population showed neutral to negative effects. The fixed-effect regression analysis revealed that for Tokyo and Osaka, regression models with 8-day-lagged night-time population level and daily change were the best fit, whereas in Aichi, the model using only the 9-day-lagged night-time population level was the best fit using the widely applicable information criterion. For all regions, the best-fit model suggested a positive relationship between night-time population and transmissibility, which was maintained over time. Conclusion: Our results revealed that, regardless of the period of interest, a positive relationship between night-time population levels and COVID-19 dynamics was observed. The introduction of vaccinations and major outbreaks of Omicron BA. Two subvariants in Japan did not dramatically change the relationship between night-time population and COVID-19 dynamics in three megacities in Japan. Monitoring the night-time population continues to be crucial for understanding and forecasting the short-term future of COVID-19 incidence.

MobCovid: Confirmed Cases Dynamics Driven Time Series Prediction of Crowd in Urban Hotspot.

Monitoring the crowd in urban hot spot has been an important research topic in the field of urban management and has high social impact. It can allow more flexible allocation of public resources such as public transportation schedule adjustment and arrangement of police force. After 2020, because of the epidemic of COVID-19 virus, the public mobility pattern is deeply affected by the situation of epidemic as the physical close contact is the dominant way of infection. In this study, we propose a confirmed case-driven time-series prediction of crowd in urban hot spot named MobCovid. The model is a deviation of Informer, a popular time-serial prediction model proposed in 2021. The model takes both the number of nighttime staying people in downtown and confirmed cases of COVID-19 as input and predicts both the targets. In the current period of COVID, many areas and countries have relaxed the lockdown measures on public mobility. The outdoor travel of public is based on individual decision. Report of large amount of confirmed cases would restrict the public visitation of crowded downtown. But, still, government would publish some policies to try to intervene in the public mobility and control the spread of virus. For example, in Japan, there are no compulsory measures to force people to stay at home, but measures to persuade people to stay away from downtown area. Therefore, we also merge the encoding of policies on measures of mobility restriction made by government in the model to improve the precision. We use historical data of nighttime staying people in crowded downtown and confirmed cases of Tokyo and Osaka area as study case. Multiple times of comparison with other baselines including the original Informer model prove the effectiveness of our proposed method. We believe our work can make contribution to the current knowledge on forecasting the number of crowd in urban downtown during the Covid epidemic.

EpiMob: Interactive Visual Analytics of Citywide Human Mobility Restrictions for Epidemic Control.

The outbreak of coronavirus disease (COVID-19) has swept across more than 180 countries and territories since late January 2020. As a worldwide emergency response, governments have implemented various measures and policies, such as self-quarantine, travel restrictions, work from home, and regional lockdown, to control the spread of the epidemic. These countermeasures seek to restrict human mobility because COVID-19 is a highly contagious disease that is spread by human-to-human transmission. Medical experts and policymakers have expressed the urgency to effectively evaluate the outcome of human restriction policies with the aid of big data and information technology. Thus, based on big human mobility data and city POI data, an interactive visual analytics system called Epidemic Mobility (EpiMob) was designed in this study. The system interactively simulates the changes in human mobility and infection status in response to the implementation of a certain restriction policy or a combination of policies (e.g., regional lockdown, telecommuting, screening). Users can conveniently designate the spatial and temporal ranges for different mobility restriction policies. Then, the results reflecting the infection situation under different policies are dynamically displayed and can be flexibly compared and analyzed in depth. Multiple case studies consisting of interviews with domain experts were conducted in the largest metropolitan area of Japan (i.e., Greater Tokyo Area) to demonstrate that the system can provide insight into the effects of different human mobility restriction policies for epidemic control, through measurements and comparisons.

Epidemic versus economic performances of the COVID-19 lockdown: A big data driven analysis.

Lockdown measures have been a "panacea" for pandemic control but also a violent "poison" for economies. Lockdown policies strongly restrict human mobility but mobility reduce does harm to economics. Governments meet a thorny problem in balancing the pros and cons of lockdown policies, but lack comprehensive and quantified guides. Based on millions of financial transaction records, and billions of mobility data, we tracked spatio-temporal business networks and human daily mobility, then proposed a high-resolution two-sided framework to assess the epidemiological performance and economic damage of different lockdown policies. We found that the pandemic duration under the strictest lockdown is less about two months than that under the lightest lockdown, which makes the strictest lockdown characterize both epidemiologically and economically efficient. Moreover, based on the two-sided model, we explored the spatial lockdown strategy. We argue that cutting off intercity commuting is significant in both epidemiological and economical aspects, and finally helped governments figure out the Pareto optimal solution set of lockdown strategy.

FedVoting: A Cross-Silo Boosting Tree Construction Method for Privacy-Preserving Long-Term Human Mobility Prediction.

The prediction of human mobility can facilitate resolving many kinds of urban problems, such as reducing traffic congestion, and promote commercial activities, such as targeted advertising. However, the requisite personal GPS data face privacy issues. Related organizations can only collect limited data and they experience difficulties in sharing them. These data are in "isolated islands" and cannot collectively contribute to improving the performance of applications. Thus, the method of federated learning (FL) can be adopted, in which multiple entities collaborate to train a collective model with their raw data stored locally and, therefore, not exchanged or transferred. However, to predict long-term human mobility, the performance and practicality would be impaired if only some models were simply combined with FL, due to the irregularity and complexity of long-term mobility data. Therefore, we explored the optimized construction method based on the high-efficient gradient-boosting decision tree (GBDT) model with FL and propose the novel federated voting (FedVoting) mechanism, which aggregates the ensemble of differential privacy (DP)-protected GBDTs by the multiple training, cross-validation and voting processes to generate the optimal model and can achieve both good performance and privacy protection. The experiments show the great accuracy in long-term predictions of special event attendance and point-of-interest visits. Compared with training the model independently for each silo (organization) and state-of-art baselines, the FedVoting method achieves a significant accuracy improvement, almost comparable to the centralized training, at a negligible expense of privacy exposure.

Applying State-of-the-Art Deep-Learning Methods to Classify Urban Cities of the Developing World.

This paper shows the efficacy of a novel urban categorization framework based on deep learning, and a novel categorization method customized for cities in the global south. The proposed categorization method assesses urban space broadly on two dimensions-the states of urbanization and the architectural form of the units observed. This paper shows how the sixteen sub-categories can be used by state-of-the-art deep learning modules (fully convolutional network FCN-8, U-Net, and DeepLabv3+) to categorize formal and informal urban areas in seven urban cities in the developing world-Dhaka, Nairobi, Jakarta, Guangzhou, Mumbai, Cairo, and Lima. Firstly, an expert visually annotated and categorized 50 × 50 km Google Earth images of the cities. Each urban space was divided into four socioeconomic categories: (1) highly informal area; (2) moderately informal area; (3) moderately formal area, and (4) highly formal area. Then, three models mentioned above were used to categorize urban spaces. Image encompassing 70% of the urban space was used to train the models, and the remaining 30% was used for testing and validation of each city. The DeepLabv3+ model can segment the test part with an average accuracy of 90.0% for Dhaka, 91.5% for Nairobi, 94.75% for Jakarta, 82.0% for Guangzhou city, 94.25% for Mumbai, 91.75% for Cairo, and 96.75% for Lima. These results are the best for the DeepLabv3+ model among all. Thus, DeepLabv3+ shows an overall high accuracy level for most of the measuring parameters for all cities, making it highly scalable, readily usable to understand the cities' current conditions, forecast land use growth, and other computational modeling tasks. Therefore, the proposed categorization method is also suited for real-time socioeconomic comparative analysis among cities, making it an essential tool for the policymakers to plan future sustainable urban spaces.

Context-aware heatstroke relief station placement and route optimization for large outdoor events.

BACKGROUND: Heatstroke is becoming an increasingly serious threat to outdoor activities, especially, at the time of large events organized during summer, including the Olympic Games or various types of happenings in amusement parks like Disneyland or other popular venues. The risk of heatstroke is naturally affected by a high temperature, but it is also dependent on various other contextual factors such as the presence of shaded areas along traveling routes or the distribution of relief stations. The purpose of the study is to develop a method to reduce the heatstroke risk of pedestrians for large outdoor events by optimizing relief station placement, volume scheduling and route. RESULTS: Our experiments conducted on the planned site of the Tokyo Olympics and simulated during the two weeks of the Olympics schedule indicate that planning routes and setting relief stations with our proposed optimization model could effectively reduce heatstroke risk. Besides, the results show that supply volume scheduling optimization can further reduce the risk of heatstroke. The route with the shortest length may not be the route with the least risk, relief station and physical environment need to be considered and the proposed method can balance these factors. CONCLUSIONS: This study proposed a novel emergency service problem that can be applied in large outdoor event scenarios with multiple walking flows. To solve the problem, an effective method is developed and evaluates the heatstroke risk in outdoor space by utilizing context-aware indicators which are determined by large and heterogeneous data including facilities, road networks and street view images. We propose a Mixed Integer Nonlinear Programming model for optimizing routes of pedestrians, determining the location of relief stations and the supply volume in each relief station. The proposed method can help organizers better prepare for the event and pedestrians participate in the event more safely.

On-site Dining in Tokyo During the COVID-19 Pandemic: Time Series Analysis Using Mobile Phone Location Data.

BACKGROUND: During the second wave of COVID-19 in August 2020, the Tokyo Metropolitan Government implemented public health and social measures to reduce on-site dining. Assessing the associations between human behavior, infection, and social measures is essential to understand achievable reductions in cases and identify the factors driving changes in social dynamics. OBJECTIVE: The aim of this study was to investigate the association between nighttime population volumes, the COVID-19 epidemic, and the implementation of public health and social measures in Tokyo. METHODS: We used mobile phone location data to estimate populations between 10 PM and midnight in seven Tokyo metropolitan areas. Mobile phone trajectories were used to distinguish and extract on-site dining from stay-at-work and stay-at-home behaviors. Numbers of new cases and symptom onsets were obtained. Weekly mobility and infection data from March 1 to November 14, 2020, were analyzed using a vector autoregression model. RESULTS: An increase in the number of symptom onsets was observed 1 week after the nighttime population volume increased (coefficient=0.60, 95% CI 0.28 to 0.92). The effective reproduction number significantly increased 3 weeks after the nighttime population volume increased (coefficient=1.30, 95% CI 0.72 to 1.89). The nighttime population volume increased significantly following reports of decreasing numbers of confirmed cases (coefficient=-0.44, 95% CI -0.73 to -0.15). Implementation of social measures to restaurants and bars was not significantly associated with nighttime population volume (coefficient=0.004, 95% CI -0.07 to 0.08). CONCLUSIONS: The nighttime population started to increase after decreasing incidence of COVID-19 was announced. Considering time lags between infection and behavior changes, social measures should be planned in advance of the surge of an epidemic, sufficiently informed by mobility data.

1.6 Million transactions replicate distributed PV market slowdown by COVID-19 lockdown.

Solar PV has seen a spectacular market development in recent years and has become a cost competitive source of electricity in many parts of the world. Yet, prospective observations show that the coronavirus pandemic could impact renewable energy projects, especially in the distributed market. Tracking and attributing the economic footprint of COVID-19 lockdowns in the photovoltaic sector poses a significant research challenge. Based on millions of financial transaction records and 44 thousand photovoltaic installation records, we tracked the spatio-temporal sale network of the distributed photovoltaic market and explored the extent of market slowdown. We found that a two-month lockdown duration can be assessed as a high-risk threshold value. When the lockdown duration exceeds the threshold value, the monthly value-added loss reaches 67.7%, and emission reduction capacity is cut by 64.2% over the whole year. We show that risks of a slowdown in PV deployment due to COVID-19 lockdowns can be mitigated by comprehensive incentive strategies for the distributed PV market amid market uncertainties.

Ex-ante online risk assessment for building emergency evacuation through multimedia data.

Ex-ante online risk assessment for building emergency evacuation is essential to protect human life and property. Current risk assessment methods are limited by the tradeoff between accuracy and efficiency. In this paper, we propose an online method that overcomes this tradeoff based on multimedia data (e.g. videos data from surveillance cameras) and deep learning. The method consists of two parts. The first estimates the evacuee position as input for training the assessment model to then perform risk assessment in real scenarios. The second considers a social force model based on the evacuation simulation for the output of training model. We verify the proposed method in simulation and real scenarios. Model sensitivity analyses and large-scale tests demonstrate the usability and superiority of the proposed method. By the method, the computation time of risk assessment could be decreased from 10 minutes (by traditional simulation method) to 2.18 s.

Pedestrian Trajectory Prediction in Extremely Crowded Scenarios.

Pedestrian trajectory prediction under crowded circumstances is a challenging problem owing to human interaction and the complexity of the trajectory pattern. Various methods have been proposed for solving this problem, ranging from traditional Bayesian analysis to Social Force model and deep learning methods. However, most existing models heavily depend on specific scenarios because the trajectory model is constructed in absolute coordinates even though the motion trajectory as well as human interaction are in relative motion. In this study, a novel trajectory prediction model is proposed to capture the relative motion of pedestrians in extremely crowded scenarios. Trajectory sequences and human interaction are first represented with relative motion and then integrated to our model to predict pedestrians' trajectories. The proposed model is based on Long Short Term Memory (LSTM) structure and consists of an encoder and a decoder which are trained by truncated back propagation. In addition, an anisotropic neighborhood setting is proposed instead of traditional neighborhood analysis. The proposed approach is validated using trajectory data acquired at an extremely crowded train station in Tokyo, Japan. The trajectory prediction experiments demonstrated that the proposed method outperforms existing methods and is stable for predictions of varying length even when the model is trained with a controlled short trajectory sequence.

Measuring spatio-temporal accessibility to emergency medical services through big GPS data.

Medical accessibility is an important indicator for evaluating the effectiveness of public health services. However, the previous medical accessibility studies mainly focus on spatial accessibility without considering temporal variation in population distribution which is significant for evaluating access to emergency medical service (EMS). This paper proposes a model of spatio-temporal accessibility to EMS called ST-E2SFCA based on adapting the enhanced two-step floating catchment area (E2SFCA) method. We apply our method to the greater Tokyo area for a large volume of GPS dataset with millions of users and compare the accessibility difference over space and time. To evaluate our model, we also analyze the distinction of our model over different weight sets and compare the performance of ST-E2SFCA with the traditional E2SFCA. The result shows that our method can illustrate the temporal difference and is suitable for measuring the spatio-temporal accessibility to EMS, thus can guide the hospital location selection and urban planning.

Village Building Identification Based on Ensemble Convolutional Neural Networks.

In this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86.

Object Discovery: Soft Attributed Graph Mining.

We categorize this research in terms of its contribution to both graph theory and computer vision. From the theoretical perspective, this study can be considered as the first attempt to formulate the idea of mining maximal frequent subgraphs in the challenging domain of messy visual data, and as a conceptual extension to the unsupervised learning of graph matching. We define a soft attributed pattern (SAP) to represent the common subgraph pattern among a set of attributed relational graphs (ARGs), considering both their structure and attributes. Regarding the differences between ARGs with fuzzy attributes and conventional labeled graphs, we propose a new mining strategy that directly extracts the SAP with the maximal graph size without applying node enumeration. Given an initial graph template and a number of ARGs, we develop an unsupervised method to modify the graph template into the maximal-size SAP. From a practical perspective, this research develops a general platform for learning the category model (i.e., the SAP) from cluttered visual data (i.e., the ARGs) without labeling "what is where," thereby opening the possibility for a series of applications in the era of big visual data. Experiments demonstrate the superior performance of the proposed method on RGB/RGB-D images and videos.

Weather effects on the patterns of people's everyday activities: a study using GPS traces of mobile phone users.

This study explores the effects that the weather has on people's everyday activity patterns. Temperature, rainfall, and wind speed were used as weather parameters. People's daily activity patterns were inferred, such as place visited, the time this took place, the duration of the visit, based on the GPS location traces of their mobile phones overlaid upon Yellow Pages information. Our analysis of 31,855 mobile phone users allowed us to infer that people were more likely to stay longer at eateries or food outlets, and (to a lesser degree) at retail or shopping areas when the weather is very cold or when conditions are calm (non-windy). When compared to people's regular activity patterns, certain weather conditions affected people's movements and activities noticeably at different times of the day. On cold days, people's activities were found to be more diverse especially after 10AM, showing greatest variations between 2PM and 6PM. A similar trend is observed between 10AM and midnight on rainy days, with people's activities found to be most diverse on days with heaviest rainfalls or on days when the wind speed was stronger than 4 km/h, especially between 10AM-1AM. Finally, we observed that different geographical areas of a large metropolis were impacted differently by the weather. Using data of urban infrastructure to characterize areas, we found strong correlations between weather conditions upon people's accessibility to trains. This study sheds new light on the influence of weather conditions on human behavior, in particular the choice of daily activities and how mobile phone data can be used to investigate the influence of environmental factors on urban dynamics.

GPS-supported visual SLAM with a rigorous sensor model for a panoramic camera in outdoor environments.

Accurate localization of moving sensors is essential for many fields, such as robot navigation and urban mapping. In this paper, we present a framework for GPS-supported visual Simultaneous Localization and Mapping with Bundle Adjustment (BA-SLAM) using a rigorous sensor model in a panoramic camera. The rigorous model does not cause system errors, thus representing an improvement over the widely used ideal sensor model. The proposed SLAM does not require additional restrictions, such as loop closing, or additional sensors, such as expensive inertial measurement units. In this paper, the problems of the ideal sensor model for a panoramic camera are analysed, and a rigorous sensor model is established. GPS data are then introduced for global optimization and georeferencing. Using the rigorous sensor model with the geometric observation equations of BA, a GPS-supported BA-SLAM approach that combines ray observations and GPS observations is then established. Finally, our method is applied to a set of vehicle-borne panoramic images captured from a campus environment, and several ground control points (GCP) are used to check the localization accuracy. The results demonstrated that our method can reach an accuracy of several centimetres.

Walking analysis using an acceleration sensor.

It is important to evaluate walking stability to improve people's health. There are many cases of unstable walking even if people think they are in good health. A small, light acceleration sensor was attached to subjects' center of gravity to measure the acceleration displacement while the subjects were walking. By using the seasonal adjustment model it was possible to predict the periodic fluctuations observed, decomposing the original data into factors representing stability and instability. We suggest the walking stability of each subject using the ratio of the variance of instability to the variance of stability. This study provides useful information for understanding walking systems in preventive medicine and rehabilitative medicine.

Analysis of 1/f fluctuations of heart rate response while walking or listening to sounds.

This study analyzes the heart rate and voice response of young students while walking or listening to sounds based on 1/f (f=frequency) fluctuation using FFT spectral analysis. There was more positive 1/f fluctuation in heart rate response in normal walking or while listening to comfortable sounds than under stressful conditions, whereas the response was negatively influenced by walking with a heavy bag or while listening to noisy sounds. This study provides a useful method for preventive medicine, physical fitness, and a means for young subjects to maintain a state of well-being.

Three-dimensional image mosaicking using multiple projection planes for 3-D visualization of roadside standing buildings.

A novel image-mosaicking technique suitable for 3-D visualization of roadside buildings on websites or mobile systems is proposed. Our method was tested on a roadside building scene taken using a side-looking video camera employing a continuous set of vertical-textured planar faces. A vertical plane approximation of the scene geometry for each frame was calculated using sparsely distributed feature points that were assigned 3-D data through bundle adjustments. These vertical planes were concatenated to create an approximate model on which the images could be backprojected as textures and blended together. Additionally, our proposed method includes an expanded crossed-slits projection around far-range areas to reduce the "ghost effect," a phenomenon in which a particular object appears repeatedly in a created image mosaic. The final step was to produce seamless image mosaics using Dijkstra's algorithm to find the optimum seam line to blend overlapping images. We used our algorithm to create efficient image mosaics in 3-D space from a sequence of real images.

Spectral analysis in walking balance by elderly subjects.

Elderly people lose their rhythm of walking balance, because their body alignment and standing balance become less stable through aging. The fluctuations of both hips movement while walking were measured using a portable measurement system with two accelerometers. Before they have had physical exercise and when walking without shoe insoles, the fluctuations of the hip movement, having back and knee pain, was not rhythmic, and also not proportional to 1/f (f=frequency) fluctuation, their walking was unstable. After physical exercise and walking with insoles, their walking became rhythmic and was approximately close to proportional to 1/f fluctuation, and their walking improved. This study provides useful information for the improvement of walking.