Network Mobility Research Articles

Routes of importation and spatial dynamics of SARS-CoV-2 variants during localised interventions in Chile

Abstract Human mobility is strongly associated with the spread of SARS-CoV-2 via air travel on an international scale, and with population mixing and the number of people moving between locations on a local scale. However, these conclusions are drawn mostly from observations in the context of the global north where international and domestic connectivity is heavily influenced by the air travel network; scenarios where land-based mobility can also dominate viral spread remain understudied. Furthermore, research on the effects of non-pharmaceutical interventions (NPIs) has mostly focused on national- or regional-scale implementations, leaving gaps in our understanding of the potential benefits of implementing NPIs at higher granularity. Here, we use Chile as a model to explore the role of human mobility on disease spread within the global south; the country implemented a systematic genomic surveillance program and NPIs at a very high spatial granularity. We combine viral genomic data, anonymised human mobility data from mobile phones and official records of international travellers entering the country to characterise the routes of importation of different variants, the relative contributions of airport and land border importations and the real-time impact of the country’s mobility network on the diffusion of SARS-CoV-2. The introduction of variants which are dominant in neighbouring countries (and not detected through airport genomic surveillance) is predicted by land border crossings and not by air travellers, and the strength of connectivity between comunas (Chile’s lowest administrative divisions) predicts the time of arrival of imported lineages to new locations. A higher stringency of local NPIs was also associated with fewer domestic viral importations. Our analysis sheds light on the drivers of emerging respiratory infectious disease spread outside of air travel, and on the consequences of disrupting regular movement patterns at lower spatial scales.

Analyzing disruptions in post-pandemic population return patterns: A network perspective on Chinese cities

The COVID-19 pandemic has fundamentally reshaped global socio-economic structures, precipitating a profound transformation in people's lifestyles. An in-depth analysis of the disruptions in post-pandemic population returns patterns and the evolving driving factors can facilitate socio-economic recovery, development, and macro-control. This paper employs social network analysis to examine the spatial patterns and evolving urban locational attributes of the Population Mobility Network (PMN) during post-holiday returns in major Chinese cities amid the pandemic, assessing the impact of varying proximities on the PMN. The results indicate that: (1) During the pandemic, the geographic patterns of population mobility in China underwent significant fluctuations, with distinct regional and temporal variations, while intercity connections increasingly shifted toward shorter trips. (2) From 2019 to 2022, major Chinese cities experienced notable changes in status and connectivity, evolving into a multi-centric structure within the national population mobility network. (3) Community clusters predominantly adhere to provincial demarcations, maintaining stable structures within major urban agglomerations despite intense intra-regional competition, with clear distinctions in community stability between northern and southern regions. (4) Beyond traditional socio-economic factors, the level of digital finance has emerged as a new driver of population mobility, with the varied attributes of inter-city relationships also significantly influencing the PMN. Studying spatial patterns and urban location from the perspective of population mobility can inform post-pandemic optimization of national resource allocation and urban recovery strategies.

AI/ML-based services and applications for 6G-connected and autonomous vehicles

AI and ML emerge as pivotal in overcoming the limitations of traditional network optimization techniques and conventional control loop designs, particularly in addressing the challenges of high mobility and dynamic vehicular communications inherent in the domain of connected and autonomous vehicles (CAVs). The survey explores the contributions of novel AI/ML techniques in the field of CAVs, also in the context of innovative deployment of multilevel cloud systems and edge computing as strategic solutions to meet the requirements of high traffic density and mobility in CAV networks. These technologies are instrumental in curbing latency and alleviating network congestion by facilitating proximal computing resources to CAVs, thereby enhancing operational efficiency also when AI-based applications require computationally-heavy tasks. A significant focus of this survey is the anticipated impact of 6G technology, which promises to revolutionize the mobility industry. 6G is envisaged to foster intelligent, cooperative, and sustainable mobility environments, heralding a new era in vehicular communication and network management. This survey comprehensively reviews the latest advancements and potential applications of AI/ML for CAVs, including sensory perception enhancement, real-time traffic management, and personalised navigation.

Initial validation and feasibility of a Standardized Navigation Of Winter Mobility & Accessibility Network (SNOWMAN) course for wheelchairs

Many Canadian manual wheelchair users face many challenges in winter months such as slippage on ice- or snow-covered ramps, snow windrows, and casters becoming stuck in deep or hard packed snow. These barriers impact wheelchair users’ ability to participate in the community. This study aimed to evaluate the validity and feasibility of a winter wheelchair obstacle course known as the Standardized Navigation Of Winter Mobility & Accessibility Network (SNOWMAN). The results demonstrated that the SNOWMAN course authentically represented real-world winter conditions, as confirmed by participant responses and qualitative feedback from four manual wheelchair users. The course was comprehensive, covering a range of winter obstacles typically encountered by wheelchair users. Construct validity was established by differentiating performance between manual wheelchairs and a motorized platform with snow tracks, showcasing varying completion times and device satisfaction levels. Feasibility was also assessed, with the administration protocol being mostly adhered to, safety measures implemented, and usability scores meeting acceptable thresholds. The SNOWMAN course showed promise for evaluating wheelchair adaptations and devices for winter conditions, as well as training users in winter mobility skills. Future research directions include comparing different wheeled mobility devices, exploring adaptations for usability in winter, and developing new technology tailored for challenging terrains and winter conditions. The SNOWMAN course could serve as a valuable tool for both research and clinical applications in enhancing winter mobility for wheelchair users.

Revolutionizing Urban Mobility: Smart Transportation & Vehicle-to-Infrastructure Communication – A Review

The burgeoning popularity of IoT technology has significantly altered transportation, with an extensive variety of repercussions. Intelligent Transportation Systems (ITS) are at the vanguard of this change, which has the potential to fundamentally change urban transportation for both individuals and businesses. ITS has expanded considerably in recent years, owing to global urbanization and industrialization advancements. It is regarded as a game-changing technology that improves road safety, improves traffic flow, and improves the entire driving experience. Despite many research efforts on ITS applications and simulation platforms, formal semantic descriptions for intelligent transportation systems have been noticeably lacking. Rising rates of accidents suggest the necessity for a robust Smart Transport System (STS) that prioritizes improving mobility, and reliability, as well as reducing carbon dioxide and methane emissions from automobiles beyond dispersing gains throughout everywhere. Multiple traffic signal management approaches have been designed to enhance real-time traffic movement at intersections, but none have achieved seamless, congestion-free traffic movements. The creation of an interconnected unified framework that integrates and links vehicles with VANET, IoT, and AI technologies will significantly affect the establishment of an innovative reliable mobility network. Internet of Vehicles (IoV) systems will connect several automobiles to share vital information through an IoT-enabled network. Vehicle-to-infrastructure (V2I) communication is essential in developing intelligent transportation and rail traffic management systems, significantly improving road traffic safety and efficiency. A V2I system integrates transmission and analysis capabilities into vehicles and corresponding infrastructure. Wireless sensors are strategically positioned along highways or driving zones in this system. The significance of safe and effective V2X communication between automobiles and facilities expands substantially as intelligent modes of transport progress.

Model of Sustainable Household Mobility in Multi-Modal Transportation Networks

Nowadays, urban and suburban areas face increasing environmental pressures, and encouraging sustainable transportation behaviors at the household level has become crucial. This paper presents a model of a decision support system (DSS) for promoting sustainable household mobility choices in multi-modal transport networks. The system was modeled using an enhanced Petri Net approach, allowing for the dynamic representation of complex transport networks and multi-modal journey options. The model incorporated various sustainability factors. These were combined into a single environmental impact score, which was considered alongside travel time and cost in the route optimization process. Simulation results demonstrated the DSS’s capability to guide users toward more sustainable mobility choices. The model also showed potential as a tool for policymakers to assess the impact of various sustainable transportation initiatives and infrastructure investments. This paper discussed the versatile applications of the system. It also addressed the limitations of Petri Net models in transportation systems and suggested future research directions.

COVID-19 전후 우리나라 지역 간 이동 네트워크의 특성 분석

The purpose of this study is to analyze the characteristics of the interregional mobility network in South Korea before and after COVID-19. South Korea has been experiencing a decline in population not only in the overall population, but also by region, which has become a major social problem. Under these circumstances, interregional travel can contribute to revitalizing local economies, and local governments are exploring various policies to increase the number of visitors. This study uses social, economic, tourism infrastructure, and public relations variables as factors that can explain interregional travel networks in South Korea, and utilizes social network analysis methods. In addition, to consider the COVID-19 pandemic as a variable that has had a significant impact on interregional travel networks in recent years, the study compares the pre- and post-COVID-19 periods in 2019 and 2021. We find that the use of social media before and after the COVID-19 outbreak is very useful in explaining interregional travel networks in South Korea. In particular, we find that social media is more useful than traditional tourism infrastructure in explaining intraregional visitor flows. While it is important for local governments to expand traditional tourism infrastructure, they need to better utilize social media as a medium to communicate this effectively.

Cross-provincial inpatient mobility patterns and their determinants in China

BackgroundThe incongruity between the regional supply and demand of healthcare services is a persistent challenge both globally and in China. Patient mobility plays a pivotal role in addressing this issue. This study aims to delineate the cross-provincial inpatient mobility network (CIMN) in China and identify the underlying factors influencing this CIMN.MethodsWe established China’s CIMN by applying a spatial transfer matrix, utilizing the flow information from 5,994,624 cross-provincial inpatients in 2019, and identified the primary demand and supply provinces for healthcare services. Subsequently, we employed GeoDetector to analyze the impact of 10 influencing factors—including medical resources, medical quality, and medical expenses—on the spatial patterns of CIMN.FindingsBeijing, Shanghai, Zhejiang, and Jiangsu provinces are the preferred medical destinations for cross-provincial inpatients, while Anhui, Henan, Hebei, and Jiangsu provinces are the main sources for cross-provincial inpatients. Patient flow between provinces decreases with distance. The spatial distribution of medical resources, medical quality, and medical expenses account for 87%, 73%, and 56% of the formation of CIMN, respectively. Additionally, interactions between these factors enhance explanatory power, suggesting that considering their interactions can more effectively optimize medical resources and services.ConclusionsThe analysis of CIMN reveals the supply and demand patterns of healthcare services, providing insights into the inequality characteristics of healthcare access. Furthermore, understanding the driving factors and their interactions offers essential evidence for optimizing healthcare services.

Quantifying spatial interaction centrality in urban population mobility: A mobility feature- and network topology-based locational measure

Spatial interaction centrality reflects the relative importance of population mobility within a location in urban population mobility. Population mobility networks visually represent urban population mobility, with mobility features and network topology contributing to the quantification of spatial interaction centrality of locations (i.e., geographical nodes). However, existing centrality measures rarely consider mobility features and network topology simultaneously. Centrality quantification also ignores the differences in distance effects between long- and short-distance trips. These factors have led to the inaccurate quantification of centrality. We propose an algorithm called k-dis-weight-shell that quantifies the spatial interaction centrality of geographical nodes at different spatiotemporal scales. Considering the different effects of distance on long- and short-distance trips, we use a spatial continuous wavelet transformation to estimate the radiation radius of geographical nodes. Then, by combining network topology with mobility features (mobility distance and flow), the algorithm transforms them into a ranked order of spatial interaction centrality. Tested in Wuhan and Chengdu, our algorithm outperforms six existing benchmarks. For cases in urban planning and epidemic management, results show that k-dis-weight-shell effectively distinguishes similarities and differences between the distribution of population mobility's spatial interaction centrality and the urban center hierarchy at a coarse spatiotemporal scale. Additionally, it reveals a double wave phenomenon of spatiotemporal correlation between population mobility and COVID-19 transmission before and after lockdown at a fine spatiotemporal scale.

Impact of initial outbreak locations on transmission risk of infectious diseases in an intra-urban area

Infectious diseases usually originate from a specific location within a city. Due to the heterogenous distribution of population and public facilities, and the structural heterogeneity of human mobility network embedded in space, infectious diseases break out at different locations would cause different transmission risk and control difficulty. This study aims to investigate the impact of initial outbreak locations on the risk of spatiotemporal transmission and reveal the driving force behind high-risk outbreak locations. First, we built a SLIR (susceptible-latent-infectious-removed)-based age-stratified meta-population model, integrating mobile phone location data, to simulate the spreading process of an infectious disease across fine-grained intra-urban regions (i.e., 649 communities of Shenzhen City, China). Based on the simulation model, we evaluated the transmission risk caused by different initial outbreak locations by proposing three indexes including the number of infected cases (CaseNum), the number of affected regions (RegionNum), and the spatial diffusion range (SpatialRange). Finally, we investigated the contribution of different influential factors to the transmission risk via machine learning models. Results indicate that different initial outbreak locations would cause similar CaseNum but different RegionNum and SpatialRange. To avoid the epidemic spread quickly to more regions, it is necessary to prevent epidemic breaking out in locations with high population-mobility flow density. While to avoid epidemic spread to larger spatial range, remote regions with long daily trip distance of residents need attention. Those findings can help understand the transmission risk and driving force of initial outbreak locations within cities and make precise prevention and control strategies in advance.

Self‐healing reversible network from furfuryl‐functionalized copoly(triazine‐r‐polypropylene glycol‐r‐polydimethylsiloxane)

AbstractNew shape‐memory networks composed of both reversible Diels–Alder covalent crosslinks and the hydrogen and π–π stacking bonds of triazine functional groups, with self‐healing properties as a result of the reversibility of these dynamic bonds were achieved from a furfuryl‐functionalized copoly(triazine‐r‐polypropylene glycol‐r‐polydimethylsiloxane), crosslinked with a maleimide end‐capped polycaprolactone and a long polycaprolactone‐based chain extender. The presence of multiple dynamic bonds, including the Diels–Alder and triazine‐derived π–π stacking and H‐bond interactions as well as the enhanced network mobility arising from polypropylene glycol, polydimethylsiloxane and polycaprolactone segments upon triggering the shape memory effect resulted in a material with high toughness (~200 MPa J−1) and efficient healing ability (with a recoveries of tensile strength and toughness after being cut and healed of 87% and 94%, respectively).Highlights Furfuryl dichlorotriazine was coupled with PPG and PDMS forming a copolymer. The copolymer was crosslinked with PCL‐dimaleimide and PCL‐difuran extender. Multiple dynamic bonds (Diels–Alder, π–π stacking and H‐bond) were present. The network showed high toughness and good healing performance.

Mobility and Temperature Sensitive Energy Efficient Routing (MTS-EER) protocol in a wireless body area network

Sensor technology advancements have provided the platform to implement wireless body area networks, thanks to the nanosized sensor units capable of sensing, aggregating, and forwarding physiological information. The collected information is routed to the desired destination unit for data analysis and decision-making in remote healthcare. However, improving energy utilization remains a brain-teasing problem for the research community, especially considering imbalanced energy consumption and postural movements. Mobility contributes to disconnectivity issues, high energy drainage, and retransmission delays. In addition, the sensor node’s thermal level also poses a challenge in maintaining safer and reliable data transmission. To overcome these issues, a novel Mobility and Temperature Sensitive Energy-Efficient Routing ¬(MTS-EER) algorithm has been proposed that includes a two-step process. In step 1, an Intelligent Path Estimation Function (IPEF) is designed considering the sensor’s mobility, temperature, and energy level. IPEF depends on crucial parameters i.e.: - residual energy, signal-to-noise ratio (SNR), distance, total energy, and most importantly temperature of the sensor unit. The sensor node with the least IPEF is selected as the Cluster Head (CH). In step 2, an optimized and sustainable energy conservation model (OSECM) is implemented based on the Adaptive Transmission Power (ATP) and the Power Management Module (PMM). The ATP conserves the energy via intelligently varying the transmission power and PMM manages the sleep pattern of sensor nodes to yield a high network lifetime and efficient energy utilization. The algorithm includes a clustering approach with dual sink nodes to conserve energy and improve reliability. Finally, the results are compared with the recent state-of-the-art research work. The proposed algorithm provides better results considering residual energy, throughput, network lifetime, and end-to-end delay.

Cooperating Graph Neural Networks With Deep Reinforcement Learning for Vaccine Prioritization.

This study explores the vaccine prioritization strategy to reduce the overall burden of the pandemic when the supply is limited. Existing vaccine distribution methods focus on macro-level or simplified micro-level assuming homogeneous behavior within populations without considering mobility patterns. Directly applying these models for micro-level vaccine allocation leads to sub-optimal solutions. To address the issue, we first proposed a Trans-vaccine-SEIR model to incorporate mobility heterogeneity in disease propagation. Then we develop a novel deep reinforcement learning to seek the optimal vaccine allocation strategy for the disease evolution system. The graph neural network is used to effectively capture the structural properties of the mobility network and extract disease features. In our evaluation, the proposed framework reduces 7%-10% of infections and deaths compared to the baseline strategies. Extensive evaluation shows that the proposed framework is robust to seek the optimal vaccine allocation with diverse mobility patterns. In particular, we find transit usage restriction is significantly more effective than restricting cross-zone mobility for the top 10% age-based and income-based zones under optimal vaccine allocation strategy. These results provide valuable insights for areas with limited vaccines and low logistic efficacy.

Spatial scales of COVID-19 transmission in Mexico.

During outbreaks of emerging infectious diseases, internationally connected cities often experience large and early outbreaks, while rural regions follow after some delay. This hierarchical structure of disease spread is influenced primarily by the multiscale structure of human mobility. However, during the COVID-19 epidemic, public health responses typically did not take into consideration the explicit spatial structure of human mobility when designing nonpharmaceutical interventions (NPIs). NPIs were applied primarily at national or regional scales. Here, we use weekly anonymized and aggregated human mobility data and spatially highly resolved data on COVID-19 cases at the municipality level in Mexico to investigate how behavioral changes in response to the pandemic have altered the spatial scales of transmission and interventions during its first wave (March-June 2020). We find that the epidemic dynamics in Mexico were initially driven by exports of COVID-19 cases from Mexico State and Mexico City, where early outbreaks occurred. The mobility network shifted after the implementation of interventions in late March 2020, and the mobility network communities became more disjointed while epidemics in these communities became increasingly synchronized. Our results provide dynamic insights into how to use network science and epidemiological modeling to inform the spatial scale at which interventions are most impactful in mitigating the spread of COVID-19 and infectious diseases in general.

A Survey of Controller Placement Problem in SDN-IoT Network

AbstractThe Internet of Things (IoT) refers to the billions of intelligent physical devices connected to the Internet for collecting and sharing data. However, implementing IoT in large-scale industrial applications presents numerous challenges, including network management and scalability. These challenges encompass: complex network management tasks that are increasingly difficult to maintain, increased network resource usage, mobility, and high energy consumption. Software-defined networking (SDN) addresses these limitations by enforcing centralized control of all devices and leveraging a global network view. SDN is a networking paradigm that separates the control plane from the data plane, allowing managers to centralize the control of the network infrastructure. For large networks, such as IoT networks, multiple controllers are needed to manage the network efficiently. The Controller Placement Problem (CPP) involves the challenge of deploying the optimal number of controllers in a network while satisfying specific performance requirements such as latency, load balancing, and computation time. This paper provides an overview of recent research efforts addressing CPP issues in the SDN-IoT domain.

Human mobility patterns in Brazil to inform sampling sites for early pathogen detection and routes of spread: a network modelling and validation study

Detecting and foreseeing pathogen dispersion is crucial in preventing widespread disease transmission. Human mobility is a fundamental issue in human transmission of infectious agents. Through a mobility data-driven approach, we aimed to identify municipalities in Brazil that could comprise an advanced sentinel network, allowing for early detection of circulating pathogens and their associated transmission routes. In this modelling and validation study, we compiled a comprehensive dataset on intercity mobility spanning air, road, and waterway transport from the Brazilian Institute of Geography and Statistics (2016 data), National Transport Confederation (2022), and National Civil Aviation Agency (2017-23). We constructed a graph-based representation of Brazil's mobility network. The Ford-Fulkerson algorithm was used to rank the 5570 Brazilian cities according to their suitability as sentinel locations, allowing us to predict the most suitable locations for early detection and to track the most likely trajectory of a newly emerged pathogen. We also obtained SARS-CoV-2 genetic data from Brazilian municipalities during the early stage (Feb 25-April 30, 2020) of the virus's introduction and the gamma (P.1) variant emergence in Manaus (Jan 6-March 1, 2021), for the purposes of model validation. We found that flights alone transported 79·9 million (95% CI 58·3-101·4 million) passengers annually within Brazil during 2017-22, with seasonal peaks occurring in late spring and summer, and road and river networks had a maximum capacity of 78·3 million passengers weekly in 2016. By analysing the 7 746 479 most probable paths originating from source nodes, we found that 3857 cities fully cover the mobility pattern of all 5570 cities in Brazil, 557 (10·0%) of which cover 6 313 380 (81·5%) of the mobility patterns in our study. By strategically incorporating mobility patterns into Brazil's existing influenza-like illness surveillance network (ie, by switching the location of 111 of 199 sentinel sites to different municipalities), our model predicted that mobility coverage would have a 33·6% improvement from 4 059 155 (52·4%) mobility patterns to 5 422 535 (70·0%) without expanding the number of sentinel sites. Our findings are validated with genomic data collected during the SARS-CoV-2 pandemic period. Our model accurately mapped 22 (51%) of 43 clade 1-affected cities and 28 (60%) of 47 clade 2-affected cities spread from São Paulo city, and 20 (49%) of 41 clade 1-affected cities and 28 (58%) of 48 clade 2-affected cities spread from Rio de Janeiro city, Feb 25-April 30, 2020. Additionally, 224 (73%) of the 307 suggested early-detection locations for pathogens emerging in Manaus corresponded with the first cities affected by the transmission of the gamma variant, Jan 6-16, 2021. By providing essential clues for effective pathogen surveillance, our results have the potential to inform public health policy and improve future pandemic response efforts. Our results unlock the potential of designing country-wide clinical sample collection networks with mobility data-informed approaches, an innovative practice that can improve current surveillance systems. Rockefeller Foundation.

Human Mobility Patterns during the 2024 Total Solar Eclipse in Canada

This study explores human mobility patterns during the 2024 total solar eclipse in Canada, leveraging de-identified network mobility data from TELUS Communications. We compare travel patterns during the total solar eclipse with a baseline period by averaging the visitor counts from April 15th to 19th, then calculate the change in visitor counts during the total solar eclipse relative to this baseline period (hereafter adjusted visitor counts). Using these adjusted visitor counts, we estimate that 589,290 Canadians traveled to areas within the path of totality to observe the eclipse. The findings highlight significant inter-provincial travel, with major influxes of visitors to Ontario, particularly near Lake Erie. We found significant evidence of a distance decay effect in the adjusted traveller counts to the path of totality. This study demonstrates the utility of de-identified network mobility data in understanding the dynamics of human mobility during once-in-a-lifetime events.

Multi-objective task offloading for highly dynamic heterogeneous Vehicular Edge Computing: An efficient reinforcement learning approach

Vehicular Edge Computing (VEC) provides a flexible distributed computing paradigm for offloading computations to the vehicular network, which can effectively solve the problem of limited vehicle computing resources and meet the on-vehicle computing requests of users. However, the conflict of interest between vehicle users and service providers leads to the need to consider a variety of conflict optimization goals for computing offloading, and the dynamic nature of vehicle networks, such as vehicle mobility and time-varying network conditions, make the offloading effectiveness of vehicle computing requests and the adaptability to complex VEC scenarios challenging. To address these challenges, this paper proposes a multi-objective optimization model suitable for computational offloading of dynamic heterogeneous VEC networks. By formulating the dynamic multi-objective computational offloading problem as a multi-objective Markov Decision Process (MOMDP), this paper designs a novel multi-objective reinforcement learning algorithm EMOTO, which aims to minimize the average task execution delay and average vehicle energy consumption, and maximize the revenue of service providers. In this paper, a preference priority sampling module is proposed, and a model-augmented environment estimator is introduced to learn the environmental model for multi-objective optimization, so as to solve the problem that the agent is difficult to learn steadily caused by the highly dynamic change of VEC environment, thus to effectively realize the joint optimization of multiple objectives and improve the decision-making accuracy and efficiency of the algorithm. Experiments show that EMOTO has superior performance on multiple optimization objectives compared with advanced multi-objective reinforcement learning algorithms. In addition, the algorithm shows robustness when applied to different environmental settings and better adapting to highly dynamic environments, and balancing the conflict of interest between vehicle users and service providers.

Mobile traffic prediction with attention-based hybrid deep learning

Mobile data consumption is ever-increasing due to the continuous emergence of bandwidth-hungry mobile applications as well as the drastic increase in number of mobile terminals resulted from the pervasive adoption of Internet of Things. In the 5G+ era, network operators have to deal with new technical challenges on network management, resource optimization and mobility scheduling, which require the ability to perform efficient mobile traffic prediction. Traditional prediction methods using convex optimization, Markov model and linear equations cannot describe the various nonlinearity changes of network traffic. In this paper, we propose a novel traffic prediction algorithm for mobile networks by introducing a hybrid deep learning method equipped with the attention mechanism, which analyzes the traffic in cellular zones to determine the spatiotemporal characteristics in the residential community. The hybrid deep learning model includes autoregressive integrated moving average mode (ARIMA) preprocessing with decomposition ability for time series, external spatial feature variables, sequence-to-sequence (seq2seq; attention-based CNN-LSTM) pretraining and extreme gradient boosting (XGBoost) optimization processing for integrating nonlinear relationships. The CNN method shows good nonlinear generalization ability to mine deep features of community traffic and capture the nonlinear trend. Our proposed approach first decomposes the community traffic data into linear and residual parts through ARIMA and then seizes the deep features of community traffic through the constructed pretraining seq2seq framework. Finally, the pretraining outcomes are further adjusted by the XGBoost method. Simulation results show that the proposed solution improves the accuracy of prediction apparently.

Diels-Alder Network Blends as Self-Healing Encapsulants for Liquid Metal-Based Stretchable Electronics.

Two dynamic covalent networks based on the Diels-Alder reaction were blended to exploit the properties of the dissimilar polymer backbones. Furan-functionalized polyether amines based on poly(propylene oxide) (PPO) FD4000 and polydimethylsiloxane (PDMS) FS5000 were mixed in a common solvent and reversibly cross-linked with the same bismaleimide DPBM. The morphology of the phase-separated blends is primarily controlled by the concentration of backbones. Increasing the PDMS content of the blends results in a dilute droplet morphology at 25 wt %, with a growing size and concentration of droplets and the formation of two separate PPO- and PDMS-rich layers at 50 wt %. Further increasing the PDMS content to 75 wt % leads to larger droplets and a thicker layer of the secondary phase. The hydrophobic PDMS phase creates a barrier against water, while the more hydrophilic PPO phase enhances the resistance against oxygen diffusion. Lowering the maleimide-to-furan stoichiometric ratio resulted in a decrease in cross-link density and thus more flexible and stretchable encapsulants. Changes in the stoichiometric ratio also affected the phase morphology due to resulting changes in phase separation and network formation kinetics. Lowering the stoichiometric ratio also resulted in enhanced self-healing properties of 96% at room temperature as a consequence of the increased chain mobility in the blended networks. The self-healing blends were used to encapsulate liquid metal circuits to create stretchable strain sensors with a linear electro-mechanical response without much drift or hysteresis, which could be efficiently recovered by 90% after the damage-healing cycles.