Real-Time Human Mobility Modeling with Multi-View Learning

Real-time human mobility modeling is essential to various urban applications. To model such human mobility, numerous data-driven techniques have been proposed. However, existing techniques are mostly driven by data from a single view, e.g., a transportation view or a cellphone view, which leads to over-fitting of these single-view models. To address this issue, we propose a human mobility modeling technique based on a generic multi-view learning framework called coMobile. In coMobile, we first improve the performance of single-view models based on tensor decomposition with correlated contexts, and then we integrate these improved single-view models together for multi-view learning to iteratively obtain mutually-reinforced knowledge for real-time human mobility at urban scale. We implement coMobile based on an extremely large dataset in the Chinese city Shenzhen, including data about taxi, bus and subway passengers along with cellphone users, capturing more than 27 thousand vehicles and 10 million urban residents. The evaluation results show that our approach outperforms a single-view model by 51% on average.

The frequency and intensity of natural disasters has significantly increased over the past decades and this trend is predicted to continue. Facing these possible and unexpected disasters, understanding and simulating of human emergency mobility following disasters will becomethe critical issue for planning effective humanitarian relief, disaster management, and long-term societal reconstruction. However, due to the uniquenessof various disasters and the unavailability of reliable and large scale human mobility data, such kind of research is very difficult to be performed. Hence, in this paper,we collect big and heterogeneous data (e.g. 1.6 million users' GPS records in three years, 17520 times of Japan earthquake data in four years, news reporting data, transportation network data and etc.) to capture and analyze human emergency mobility following different disasters. By mining these big data, we aim to understand what basic laws govern human mobility following disasters, and develop a general model of human emergency mobility for generating and simulating large amount of human emergency movements. The experimental results and validations demonstrate the efficiency of our simulation model, and suggest that human mobility following disasters may be significantly morepredictable and can be easier simulated than previously thought.

In recent decades, the frequency and intensity of natural disasters has increased significantly, and this trend is expected to continue. Therefore, understanding and predicting human behavior and mobility during a disaster will play a vital role in planning effective humanitarian relief, disaster management, and long-term societal reconstruction. However, such research is very difficult to perform owing to the uniqueness of various disasters and the unavailability of reliable and large-scale human mobility data. In this study, we collect big and heterogeneous data (e.g., GPS records of 1.6 million users 1 over 3 years, data on earthquakes that have occurred in Japan over 4 years, news report data, and transportation network data) to study human mobility following natural disasters. An empirical analysis is conducted to explore the basic laws governing human mobility following disasters, and an effective human mobility model is developed to predict and simulate population movements. The experimental results demonstrate the efficiency of our model, and they suggest that human mobility following disasters can be significantly more predictable and be more easily simulated than previously thought.

In this paper, we seek to improve understanding of the structure of human mobility, with a view to using this for designing algorithms for the dissemination of data among mobile users. We analyse community structures and node centrality from the human mobility traces and use these two metrics to design efficient forwarding algorithms in terms of delivery ratio and delivery cost for mobile networks. This is the first empirical study of community and centrality using real human mobility datasets.

Elbow fracture diagnosis often requires patients to take both frontal and lateral views of elbow X-ray radiographs. In this paper, we propose a multiview deep learning method for an elbow fracture subtype classification task. Our strategy leverages transfer learning by first training two single-view models, one for frontal view and the other for lateral view, and then transferring the weights to the corresponding layers in the proposed multiview network architecture. Meanwhile, quantitative medical knowledge was integrated into the training process through a curriculum learning framework, which enables the model to first learn from "easier" samples and then transition to "harder" samples to reach better performance. In addition, our multiview network can work both in a dual-view setting and with a single view as input. We evaluate our method through extensive experiments on a classification task of elbow fracture with a dataset of 1,964 images. Results show that our method outperforms two related methods on bone fracture study in multiple settings, and our technique is able to boost the performance of the compared methods. The code is available at https://github.com/ljaiverson/multiview-curriculum.

Digital technologies have recently become more advanced, allowing for the development of social networking sites and applications. Despite these advancements, phone calls and text messages still make up the largest proportion of mobile data usage. It is possible to study human communication behaviors and mobility patterns using the useful information that mobile phone data provide. Specifically, the digital traces left by the large number of mobile devices provide important information that facilitates a deeper understanding of human behavior and mobility configurations for researchers in various fields, such as criminology, urban sensing, transportation planning, and healthcare. Mobile phone data record significant spatiotemporal (i.e., geospatial and time-related data) and communication (i.e., call) information. These can be used to achieve different research objectives and form the basis of various practical applications, including human mobility models based on spatiotemporal interactions, real-time identification of criminal activities, inference of friendship interactions, and density distribution estimation. The present research primarily reviews studies that have employed mobile phone data to investigate, assess, and predict human communication and mobility patterns in the context of crime prevention. These investigations have sought, for example, to detect suspicious activities, identify criminal networks, and predict crime, as well as understand human communication and mobility patterns in urban sensing applications. To achieve this, a systematic literature review was conducted on crime research studies that were published between 2014 and 2022 and listed in eight electronic databases. In this review, we evaluated the most advanced methods and techniques used in recent criminology applications based on mobile phone data and the benefits of using this information to predict crime and detect suspected criminals. The results of this literature review contribute to improving the existing understanding of where and how populations live and socialize and how to classify individuals based on their mobility patterns. The results show extraordinary growth in studies that utilized mobile phone data to study human mobility and movement patterns compared to studies that used the data to infer communication behaviors. This observation can be attributed to privacy concerns related to acquiring call detail records (CDRs). Additionally, most of the studies used census and survey data for data validation. The results show that social network analysis tools and techniques have been widely employed to detect criminal networks and urban communities. In addition, correlation analysis has been used to investigate spatial–temporal patterns of crime, and ambient population measures have a significant impact on crime rates.

Reconfigurable intelligent surface (RIS) is regarded as a promising technology to assist indoor millimeter wave (mm-Wave) communication due to its ability to manipulate electromagnetic waves directionally. Due to the complexity of indoor environment, different RIS deployment strategies significantly affect the system performance. However, the existing work investigating RIS indoor deployment ignored the influence of human mobility to indoor signal coverage, therefore a practical indoor deployment strategy remains unknown. In this letter, based on the consideration of human blockage to mm-Wave signal and probability distribution of human location, we propose an indoor RIS deployment strategy with human mobility model to minimize the outage probability, which is more applicable to the realistic indoor environment. An algorithm is presented to minimize the outage probability at a subspace scale of the room geometry and calculate the corresponding RIS location for single RIS deployment and multiple RISs cooperative deployment. Numerical results are provided to display how our deployment strategy works, which indicate that deploying RIS correctly can decrease the indoor communication outage probability significantly.

Deep multi-view representation learning focuses on training a unified low-dimensional representation for data with multiple sources or modalities. With the rapidly growing attention of graph neural networks, more and more researchers have introduced various graph models into multi-view learning. Although considerable achievements have been made, most existing methods usually propagate information in a single view and fuse multiple information only from the perspective of attributes or relationships. To solve the aforementioned problems, we propose an efficient model termed Dual Fusion-Propagation Graph Neural Network (DFP-GNN) and apply it to deep multi-view clustering tasks. The proposed method is designed with three submodules and has the following merits: a) The proposed view-specific and cross-view propagation modules can capture the consistency and complementarity information among multiple views; b) The designed fusion module performs multi-view information fusion with the attributes of nodes and the relationships among them simultaneously. Experiments on popular databases show that DFP-GNN achieves significant results compared with several state-of-the-art algorithms.

Urban greenspaces are crucial for public health, climate resilience and community well‐being, yet there are inequalities in accessibility in cities across the world. The ‘x‐minute city’ framework has been proposed as a potential solution, proposing that essential services and amenities—including greenspace—should be accessible within a short commute from every residence. However, current approaches to measuring and implementing this framework often rely on single dimensional metrics that fail to capture the full complexity of how people actually access and use urban greenspaces. This review synthesizes methods from three distinct fields to develop a more comprehensive understanding of greenspace accessibility: geographic information science (GIScience), which provides spatial analytical tools; behavioural ecology (BE), which offers frameworks for understanding movement decisions; and human mobility analysis, which reveals movement patterns through the urban environment. While GIScience approaches allow for the identification of spatial inequalities in greenspace distribution, they often overlook the behavioural and social factors that influence actual usage, highlighted in BE approaches. Similarly, human mobility models can track movement patterns but may miss environmental and cultural factors. To bridge the gap between these methods, we introduce the Multi‐context Inclusive City (MIC) framework, which integrates spatial, behavioural and mobility perspectives to analyse greenspace accessibility. This framework moves beyond proximity measures to incorporate diverse experiences, movement pathways and the environmental and social factors that influence greenspace usage. The MIC framework offers practical guidance for selecting appropriate models and methods based on specific research questions or planning objectives. By providing a more nuanced understanding of how people interact with urban greenspaces, this framework can help planners and policymakers develop more effective strategies for creating equitable, accessible and sustainable cities. Read the free Plain Language Summary for this article on the Journal blog.

This study focuses on the detection of COVID-19 using chest X-ray images. With the rapid global spread of the highly contagious disease, early and accurate detection is crucial to prevent further transmission. We propose a multi-view approach that leverages different deep-learning methods to detect COVID-19 based on chest X-ray images. The framework presented in this study aims to capture both complementary and correlative information from multiple views. By using pre-trained deep convolutional neural network (CNN) models such as ResNet50 and VGG16 to extract deep features from the X-ray images. Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) algorithms are then employed to classify the X-ray images based on the learned feature representations. The single-view models using VGG16 and ResNet50 with SVM achieved accuracy scores of 97% and 98% respectively. Similarly, using KNN, the single-view models achieved accuracy scores of 89% and 95%. Recognizing the potential of multi-view learning to improve generalization performance. We utilized early fusion to integrate the outputs of the pre-trained models and fed them into SVM and KNN classifiers. The multi-view model achieved accuracy scores of 98% and 92% respectively. The experimental results demonstrate that the multi-view deep learning methods outperformed the single-view deep models in detecting COVID-19 from chest X-ray images. The findings of this study have practical implications as they can assist experts in early diagnosis of COVID-19 cases, highlighting the effectiveness of the proposed methods.

The ever-increasing traffic created by mobile Internet users has challenged ISPs to implement fair pricing scheme. Time-based pricing schemes could be used to address this problem giving users the opportunity to choose when they desire to spend their own resources to access the Internet. However, distinct base stations that make up a cellular data network often do not experience the same workload over time. Thus, a time-based pricing approach could create an undesirable situation to users who happen to be in a region covered by a base station that is currently overloaded. This paper presents a workload-aware dynamic time-based pricing scheme which uses historical workload of each base station to differentiate prices in order to foster the geographically distribution of the Internet accesses over the ISP's network. We evaluate the proposed pricing scheme via simulation using some human mobility models, and compare it with two other state-of-the-art pricing schemes. Our experimental results show that the proposed approach is able to better redistribute the network workload among a larger number of base stations in different human mobility models, when compared to the alternatives. This allows ISP's to accommodate a larger number of users since our approach help ISP to avoid the overload of base station resources.

A significant challenge to make learning techniques more suitable for general purpose use is to move beyond i) complete supervision, ii) low dimensional data, iii) a single label and single view per instance. Solving these challenges allows working with complex learning problems that are typically high dimensional with multiple (but possibly incomplete) labelings and views. While other work has addressed each of these problems separately, in this paper we show how to address them together, namely <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">semi-supervised dimension reduction for multi-label and multi-view learning</i> (SSDR-MML), which performs optimization for dimension reduction and label inference in semi-supervised setting. The proposed framework is designed to handle both multi-label and multi-view learningsettings, and can be easily extended to many useful applications. Our formulation has a number of advantages. We explicitly model the information combining mechanism as a data structure (a weight/nearest-neighbor matrix) which allows investigating fundamentalquestions in multi-label and multi-view learning. We address one such question by presenting a general measure to quantify thesuccess of simultaneous learning of multiple labels or views. We empirically demonstrate the usefulness of our SSDR-MML approach, and show that it can outperform many state-of-the-art baseline methods.

Human migration is a type of human mobility, where a trip involves a person moving with the intention of changing their home location. Predicting human migration as accurately as possible is important in city planning applications, international trade, spread of infectious diseases, conservation planning, and public policy development. Traditional human mobility models, such as gravity models or the more recent radiation model, predict human mobility flows based on population and distance features only. These models have been validated on commuting flows, a different type of human mobility, and are mainly used in modeling scenarios where large amounts of prior ground truth mobility data are not available. One downside of these models is that they have a fixed form and are therefore not able to capture more complicated migration dynamics. We propose machine learning models that are able to incorporate any number of exogenous features, to predict origin/destination human migration flows. Our machine learning models outperform traditional human mobility models on a variety of evaluation metrics, both in the task of predicting migrations between US counties as well as international migrations. In general, predictive machine learning models of human migration will provide a flexible base with which to model human migration under different what-if conditions, such as potential sea level rise or population growth scenarios.

Wireless Body Area Networks (WBAN) open an interdisciplinary area within Wireless Sensor Networks (WSN) research, with a tremendous impact in healthcare area where sensors are used to monitor, collect and transmit biological parameters of the human body. We propose the first network-MAC cross-layer broadcast protocol in WBAN. Our protocol, evaluated in the OMNET++ simulator enriched with a realistic human body mobility and channel model issued from a recent research on biomedical and health informatics, outperforms existing flat broadcast strategies in terms of network coverage, sensors energy consumption and correct reception of FIFO-ordered packets. We investigate the resilience of both existing flat broadcast strategies and our new cross-layer protocol face to various transmission rates and human body mobility. Existing flat broadcast strategies, without exception, start to have a drastic drop of performance for transmission rates above 11 Kb/s while our cross-layer protocol maintains its good performance for transmission rates up to 190 Kb/s.

Even though human movement and mobility patterns have a high degree of freedom and variation, they also exhibit structural patterns due to geographic and social constraints. Using cell phone location data, as well as data from two online location-based social networks, we aim to understand what basic laws govern human motion and dynamics. We find that humans experience a combination of periodic movement that is geographically limited and seemingly random jumps correlated with their social networks. Short-ranged travel is periodic both spatially and temporally and not effected by the social network structure, while long-distance travel is more influenced by social network ties. We show that social relationships can explain about 10% to 30% of all human movement, while periodic behavior explains 50% to 70%. Based on our findings, we develop a model of human mobility that combines periodic short range movements with travel due to the social network structure. We show that our model reliably predicts the locations and dynamics of future human movement and gives an order of magnitude better performance than present models of human mobility.