Mobility Prediction Research Articles

Reliable routing in MANET with mobility prediction via long short-term memory

A MANET consists of a self-configured group of transportable mobile nodes that lacks a central infrastructure to manage network traffic. To facilitate communication, govern route discovery, and manage resources, all moving nodes in multi-hop wireless networks (MANETs) work together. These networks struggle with dependability, energy consumption, and collision avoidance. The goal of this research project is to establish a new, dependable MANET routing model, where the selection of predictor nodes comes first. For selecting predictor nodes based on factors like distance, security (risk), Receiver Signal Strength Indicator (RSSI), Packet Delivery Ratio (PDR), and energy, the adaptive weighted clustering algorithm (AWCA) is used in this case. Using the Interfused Slime and Battle Royale Optimization with Arithmetic Crossover (IS&BRO–AC) model, the node with the lower weight is selected as the Cluster Head (CH). Additionally, mobility prediction is carried out, in which the node mobility is forecast using Improved Long Short Term Memory (LSTM) while taking distance and Receiver Signal Strength Indicator (RSSI) into account. Based on the forecast, trustworthy data transfer is implemented, ensuring more accurate and dependable MANET routing. The examination of RSSI, PDR, and other metrics is completed at the end.

State Transition Graph-Based Spatial–Temporal Attention Network for Cell-Level Mobile Traffic Prediction

Mobile traffic prediction enables the efficient utilization of network resources and enhances user experience. In this paper, we propose a state transition graph-based spatial–temporal attention network (STG-STAN) for cell-level mobile traffic prediction, which is designed to exploit the underlying spatial–temporal dynamic information hidden in the historical mobile traffic data. Specifically, we first identify the semantic context information over different segments of the historical data by constructing the state transition graphs, which may reveal different patterns of random fluctuation. Then, based on the state transition graphs, a spatial attention extraction module using graph convolutional networks (GCNs) is designed to aggregate the spatial information of different nodes in the state transition graph. Moreover, a temporal extraction module is employed to capture the dynamic evolution and temporal correlation of the state transition graphs over time. Such a spatial–temporal attention network can be further integrated with a parallel long short-term memory (LSTM) module to improve the accuracy of mobile traffic prediction. Extensive experiments demonstrate that the STG-STAN can better exploit the spatial–temporal information hidden in the state transition graphs, achieving superior performance compared with several baselines.

Abstract 14207: Mobile ECG Atrial Fibrillation Prediction Enhancement Powered by Standard ECG Algorithm With Artificial Intelligence

Introduction: Artificial intelligence (AI) using electrocardiogram (ECG) enabled to predict atrial fibrillation (AF) in patients without documented AF. It needs 12-lead ECG with tremendous data learning. Mobile 1-lead ECG is more convenient to surveil cardiac rhythm with simple measurement. However, AI-enabled arrhythmia predictability by mobile ECG is limited due to single channel utilization and longer duration for arrhythmia diagnosis. Hypothesis: We aimed to enhance mobile ECG AF prediction AI algorithm integrated with 12-lead ECG deep learning model. Methods: Based on 552,372 12-lead ECG data of 318,321 patients, a statistical AF prediction model employing a deep-learning approach was constituted. The raw data of 6,792 1-lead mobile ECGs were acquired from 6,792 patients for about 1 minute at 250Hz. A statistical AF prediction model with mobile ECG employing a deep-learning approach was constituted. Resnet structure was utilized to distinguish subtle changes of the vicinity of P-wave. Both 12-lead ECG and mobile ECG were allocated to training, validation, testing datasets in a 6:2:2 ratio. Then, we conducted transfer learning using the standard 12-lead ECG’s deep learning model to improve performance of 1-lead mobile ECG deep learning model. Results: AF was annotated in 26,541 (4.8%) with 12-lead ECG whereas 1,443 (21.2%) with 1-lead mobile ECG. The area under the curve (AUC) value for predicting AF was 0.910 with 12-lead ECG, and 0.721 with mobile ECG . The predictive performance of mobile ECG was 79.7% in accuracy, 47.5% in sensitivity and 50.3% in F1-score. The AUC value of mobile ECG after applying transfer learning based on 12-lead ECG for AF prediction was increased to 0.905 with accuracy of 89.1%, sensitivity of 71.3% and F1-score of 57.7%. Conclusions: Integration with deep learning algorithm of standard 12-lead ECG significantly improved the model performance of mobile ECG AF prediction model compared to 1-lead mobile ECG only based model. Easy application of mobile ECG with enhanced AF predictability might serve a more convenient method as a pre-emptive assistive tool to provide probabilistic prediction for PAF screening rather than 12-lead ECG.

MG-ASTN: Multigraph Framework With Attentive Spatial–Temporal Networks for Crowd Mobility Prediction

Predicting urban crowd patterns/flows is a challenging task due to complex spatial-temporal (ST) dependencies. In this paper, we aim to examine and report the capability and effectiveness of the current most widely used Graph Convolutional Networks (GCNs) on mobile data analysis in ST networks for crowd flow forecasting. Specifically, we propose a novel dual-stream framework leveraging Multi-Graph with Attentive Spatial-Temporal Networks (MG-ASTN) to simultaneously predict crowd in-out flow and OD flow based on the trajectory data collected by on-board devices (e.g., GPS). MG-ASTN utilizes Multi-Graph Convolutional Networks encoding non-Euclidean correlations to explore pair-wise relationships among regions. In addition, we further apply a cross-channel attention mechanism with 3D Temporal Convolutional Network to address the heterogeneity of ST features and capture more meaningful data representations for multi-task learning. In the evaluation, we conduct experiments based on 2 real-world datasets and verify most well-known state-of-the-art methods for crowd flow prediction. The results demonstrate that MG-ASTN could outperform other solutions -in-out flow prediction with lowest RMSE and MAE, and OD flow prediction beyond others in most cases, thus it has great potential in modeling the complex correlations among regions in ST networks and enabling accurate prediction in urban computing.

Evaluation of non-destructive tools for preliminary environmental risk assessment during mining exploration

Environmental assessment is generally performed when a mining project is at an advanced development stage, such as the prefeasibility study. It involves several laboratory tests such as detailed characterisation and geochemical mobility prediction tests, which require many samples considered representative of the deposit. Having early characterisation information could be useful to select the most relevant samples for the overall environmental assessment. The present study proposes a selection of non destructive and portable tools for improving the early environmental assessment of a mineral deposit. Three tools (x-ray fluorescence (XRF), mineral spectrometer, carbonate staining) were identified to form a preliminary environmental assessment methodology that can be performed directly on the exploration site. This methodology was applied to two different mining projects: i) a well developed mine, LaRonde zone 5, with available geochemical data in a volcanic-associated massive sulfide (VMS) context, and ii) an exploration project, O’Brien, with ongoing geochemical acquisition in an Au-quartz vein context. Both mine sites are in the south of the Blake River Group within the Abitibi greenstone belt, Quebec, Canada. The first site was used to validate the developed methodology, whereas the second acted as a test site to apply the methodology as a preliminary environmental assessment. The results on the first site confirmed that the selected tools provide geochemical and mineralogical data sets comparable to those of traditional testing methods. The developed methodology then enabled the classification of preliminary geo-environmental domains for the second site. Standard static and kinetic tests were performed on the second site samples to confront the preliminary assessment protocol. The proposed preliminary protocol made it possible to discriminate low-risk samples versus those with a potentially higher risk for the selection of subsequent environmental assessments.

Coarse-Grained Model for Prediction of Hole Mobility in Polyethylene.

Electrical conductivity measurements of polyethylene indicate that the semicrystalline structure and morphology influence the conductivity. To include this effect in atomistic charge transport simulations, models that explicitly or implicitly take morphology into account are required. In the literature, charge transport simulations of amorphous polyethylene have been successfully performed using short oligomers to represent the polymer. However, a more realistic representation of the polymer structure is desired, requiring the development of fast and efficient charge transport algorithms that can handle large molecular systems through coarse-graining. Here, such a model for charge transport simulations in polyethylene is presented. Quantum chemistry calculations were used to define six segmentation rules on how to divide a polymer chain into shorter segments representing localized molecular orbitals. Applying the rules to amorphous systems yields distributions of segments with mode and median segment lengths relatively close to the persistence length of polyethylene. In an initial test, the segments of an amorphous polyethylene were used as hopping sites in kinetic Monte Carlo (KMC) simulations, which yielded simulated hole mobilities that were within the experimental range. The activation energy of the simulated system was lower compared to the experimental values reported in the literature. A conclusion may be that the experimental result can only be explained by a model containing chemical defects that generate deep traps.

Improved Multiresolution Neural Network for Mobility-Aware Security and Content Caching for Internet of Vehicles

With the emerging communication and computation technologies, the Internet of Vehicles (IoV) has become a new paradigm that enables vehicles to communicate with Road Side Units (RSUs) as well as with other vehicles to collect or exchange information. However, the inherent characteristics of IoV, such as the high mobility of the vehicle and the limited storage capacity of the edge nodes, cause numerous difficulties in developing a caching scheme. Therefore, in this paper, a novel improved Multinomial Recurrent Neural Network (MRNN) classifier and 2CK-ECC algorithm are proposed to predict the vehicular mobility, security, and content caching for the IoV. Initially, the vehicles are checked for registration. Afterwards, vehicle login and vehicle authentication take place. Then, mobility prediction is carried out for the authenticated vehicles using the MRNN Classifier. After that, vehicle clustering is done via the novel Variance Balanced Iterative Reducing and Clustering Using Hierarchies (VBIRCH) technique. Next, the Relay Vehicles (RVs) are selected using the novel Harris Self Avoiding Hawks Optimization (HSAHO). Further, the data contents are divided into chunks and saved in the cache memory. From the cache memory, data is transferred to the RSU. Finally, a novel Caesar Combined Key-based Elliptic Curve Cryptography (2CK-ECC) algorithm is investigated for secure data transmission. The experimental outcomes demonstrate that the proposed technique outperforms the existing base line approaches.

Next Generation Mobile Networks' Enablers: Machine Learning-Assisted Mobility, Traffic, and Radio Channel Prediction

Machine learning (ML) is an important component for enabling automation in radio access networks (RANs). The work on applying ML for RAN has been under development for several years and is now also drawing attention in 3GPP standardization fora. A key component of multiple features, highlighted in the recent 3GPP specification work, is the use of mobility, traffic and radio channel prediction. These types of predictions form intelligence enablers to leverage the potentials of ML for RAN enhancements, in both current and future wireless networks. Our contributions are twofold, first we provide an overview with representative evaluation results of current applications that utilize these intelligence enablers. Next, we discuss how those enablers likely will be a cornerstone for emerging 6G use cases such as wireless energy harvesting. As the journey to 6G remains an open research area, we highlight how the development of these enablers can unlock new features in future mobile networks.

Mobility-aware Vehicular Cloud formation mechanism for Vehicular Edge Computing environments

Rapid advancements in vehicular technology and increased vehicle modernization have led to the emergence of intelligent and interconnected entities. As a result, the Vehicular Edge Computing (VEC) paradigm has gained prominence. This paradigm enables the provision of cloud computing services close to vehicular users by utilizing the idle computational resources of vehicles to execute tasks that require computing power beyond what is available locally. Aggregating these computational resources in the vehicular context is known as Vehicular Cloud (VCloud) formation. However, leveraging and aggregating these resources poses several challenges due to the dynamic nature of the vehicular environment. One of the main challenges is the efficient selection of vehicles to assume management roles in the distribution of computational power within the group, often referred to as leading vehicles. This research presents a mobility-aware mechanism called PREDATOR to enhance the VCloud formation process. In this mechanism, the Roadside Unit (RSU) provides vehicular mobility predictions, enabling the selection of the most stable vehicles within the RSU coverage area to assume leadership roles in the VCloud. In this context, vehicle stability is associated with a vehicle’s time within the RSU coverage area, known as dwell time. PREDATOR employs a microscopic perspective to select vehicles with the longest dwell time in the VCloud, allowing for efficient management of computational resource utilization. Simulation results have demonstrated that PREDATOR not only increases the VCloud lifetime but also minimizes leader changes, reduces network message exchange, mitigates packet collisions, and facilitates the effective utilization of aggregated vehicular resources compared to state-of-the-art approaches.

Geo-aware graph-augmented self-attention network for individual mobility prediction

Even though some studies have found encouraging results, the sparsity of data and the complexity of mobility patterns remain significant challenges in predicting individual mobility. In order to effectively address the two challenges, we propose a novel framework called Geo-aware Graph-Augmented Self-Attention Network (GaGASAN). In GaGASAN, we construct a heterogeneous location graph consisting of a geospatial subgraph and a location transition subgraph to simultaneously model the impacts of geospatial distance and location transitions on all users. With the heterogeneous location graph, the impacts of geospatial distances and global location transitions of all users can be effectively merged, thereby mitigating the sparsity of individual mobility data. For the complex and variable mobility patterns of individuals, we employ a multi-scale time encoding technique and a self-attention mechanism to model different temporal patterns and capture long- and short-range contexts of sequence transitions. Extensive experiments shows that GaGASAN significantly outperforms eight baseline methods on all metrics. Our implementation code is available at https://github.com/mrc-wyh/GaGASAN.

Molecular Dynamics-Based Modeling of Ion-Neutral Collisions in an Open Ion Trajectory Simulation Framework.

Ion mobility spectrometry (IMS) and ion mobility mass spectrometry (IMS-MS) methods have become increasingly popular and are important analytical techniques to determine information about the structural parameters of gas-phase analytes. The accurate description of the interaction between molecular ions and neutral background gas particles is an essential part of high-quality simulations of such modern mass- and ion-mobility-spectrometric systems. Established ion-neutral collision models (Hard-sphere collision modeling and statistical diffusion simulations) in common ion-trajectory simulation systems like SIMION use strongly simplified assumptions and are thus limited in their predictive ability. In contrast, collision cross-section (CCS) modeling programs (e.g., MOBCAL, IMoS, and Colloidoscope) allow high-quality ion mobility predictions for low-field equilibrium conditions using explicit scattering processes with a molecular dynamics-based trajectory method but cannot be used for nonequilibrium collision modeling in an ion trajectory simulation. This work presents an extension to the open-source Ion Dynamics Simulation Framework (IDSimF), which allows the simulation of ion dynamics under arbitrary and even nonequilibrium conditions. It was extended by an advanced collision model employing the molecular dynamics trajectory method for a detailed microscopic description of ion-neutral collisions within ion-trajectory simulations. We used drift tube ion mobility spectrometry (DT-IMS) to validate the predictive abilities of the model and to estimate the runtime requirements for productive simulations. Simulated high-field ion mobilities for small ion systems in a drift tube IMS are compared to experimental values from the literature and an implementation of a hard-sphere model in IDSimF for helium and argon as background gas particles. Significant improvements in ion mobility predictions using the molecular dynamics trajectory approach are obtained with deviations of only a few percent from experimental values. Therefore, the established and publicly available MD collision model will serve as foundation for nonequilibrium ion dynamics simulations and the development of improved ion dynamics modeling methods.

Context-aware multi-head self-attentional neural network model for next location prediction

Accurate activity location prediction is a crucial component of many mobility applications and is particularly required to develop personalized, sustainable transportation systems. Despite the widespread adoption of deep learning models, next location prediction models lack a comprehensive discussion and integration of mobility-related spatio-temporal contexts. Here, we utilize a multi-head self-attentional (MHSA) neural network that learns location transition patterns from historical location visits, their visit time and activity duration, as well as their surrounding land use functions, to infer an individual’s next location. Specifically, we adopt point-of-interest data and latent Dirichlet allocation for representing locations’ land use contexts at multiple spatial scales, generate embedding vectors of the spatio-temporal features, and learn to predict the next location with an MHSA network. Through experiments on two large-scale GNSS tracking datasets, we demonstrate that the proposed model outperforms other state-of-the-art prediction models, and reveal the contribution of various spatio-temporal contexts to the model’s performance. Moreover, we find that the model trained on population data achieves higher prediction performance with fewer parameters than individual-level models due to learning from collective movement patterns. We also reveal mobility conducted in the recent past and one week before has the largest influence on the current prediction, showing that learning from a subset of the historical mobility is sufficient to obtain an accurate location prediction result. We believe that the proposed model is vital for context-aware mobility prediction. The gained insights will help to understand location prediction models and promote their implementation for mobility applications.

A novel group management scheme of clustered federated learning for mobile traffic prediction in mobile edge computing systems

A novel group management scheme of clustered federated learning for mobile traffic prediction in mobile edge computing systems

A Proactive Stable Scheme for Vehicular Collaborative Edge Computing

Due to the restricted computing resources and high upgrading costs, onboard processors alone cannot meet the quality of service (QoS) requirements of the emerging and constantly upgrading vehicular applications. Computation offloading is a feasible solution to the excessive computation-intensive tasks. Meanwhile, vehicular collaborative edge computing (VCEC) is a paradigm to make the best use of surrounding vehicles' idle computing resources when the task density on a specific road segment suddenly increases. However, the high mobility of vehicles and the ad hoc nature of vehicular networks make maintaining stable task offloading performance quite challenging. Especially when the idle computing resources surrounding vehicles are insufficient, there has not been researching to achieve stable offloading performance. Based on this, we consider a proactive strategy that can decrease the events that affect performance stability. First, we propose a mobility prediction model for future network status prediction. Then we design an adaptive task offloading scheme based on proactive adjusting (PATO) to maintain stable task offloading performance. The scheme includes a state processing model and a deep reinforcement learning (DRL)-based task offloading algorithm. Finally, we conduct extensive simulations in various scenarios with insufficient resources to validate the task offloading performance of PATO. Compared with the existing DRL-based algorithm, the simulation results show that PATO can improve the mean offloading utility by 95.4% and the completion ratio by 15.8%.

A Framework to Address Mobility Management Challenges in Emerging Networks

The key enablers for emerging cellular networks such as densification, concurrent operation at multiple bands and harnessing mmWave spectrum give birth to a peculiar set of new network management challenges. One such key challenge is the user mobility management. In this article, we identify the key issues that render current mobility management paradigm inadequate for delivering the expected Quality of Experience (QoE) and resource efficiency in emerging and future cellular networks. Together, these challenges call for paradigm shift in the way mobility is managed in cellular networks. We present an Advanced Mobility Management and Utilization Framework (A-MMUF) that can enable this paradigm shift by transforming mobility management from being a reactive to a proactive process. The core idea of A-MMUF is to build upon Mobility Prediction Models (MPMs) to predict various attributes of user mobility and traffic patterns such as next candidate cell for handover (HO), time of HO, future cell loads. These predictions are then leveraged to not only improve HO process for better QoE and less signaling overhead, but also to enable proactive automation to further maximize network performance in terms of energy and spectrum efficiency. However, understandably, the gains offered by the A-MMUF hinge on the accuracy of the MPMs, which may vary, not only with the choice of underlying machine learning technique, but also with the volume, variety, and fidelity of the training data. We analyze the potential gains of A-MMUF through three case studies: namely proactive HO, proactive Mobility Load Balancing (P-MLB), and proactive Energy Savings (P-ES). In addition to demonstrating significant gains in all three case studies, the results provide useful insights into the agility vs accuracy tradeoff that can be leveraged for choosing optimal machine learning models for practical deployment of A-MMUF.

An Information Theory Based Method for Quantifying the Predictability of Human Mobility

Research on human mobility drives the development of economy and society. How to predict when and where one will go accurately is one of the core research questions. Existing work is mainly concerned with performance of mobility prediction models. Since accuracy of predict models does not indicate whether or not one’s mobility is inherently easy to predict, there has not been a definite conclusion about that to what extent can our predictions of human mobility be accurate. To help solve this problem, we describe the formalized definition of predictability of human mobility, propose a model based on additive Markov chain to measure the probability of exploration, and further develop an information theory based method for quantifying the predictability considering exploration of human mobility. Then, we extend our method by using mutual information in order to measure the predictability considering external influencing factors, which has not been studied before. Experiments on simulation data and three real-world datasets show that our method yields a tighter upper bound on predictability of human mobility than previous work, and that predictability increased slightly when considering external factors such as weather and temperature.

OPBRP - obstacle prediction based routing protocol in VANETs

Vehicular Ad-hoc Networks (VANETs) are recently getting high attention from different researchers due to increasing traffic problems, especially in densely populated countries. Increasing rates of accidents call for an Intelligent Transportation System (ITS) with efficient performance to reduce and mitigate this trend. The required enhancement of the ITS can be more focused on traffic performance, integrity, and reduction of the vehicles’ CO 2 emissions. Existing routing protocols for VANETs consider different situations and methods to establish reliable communication between the vehicles and infrastructures. However other situations have not been addressed carefully like the link stability between vehicles during packet exchange. This paper develops an Obstacle Prediction Based Routing Protocol (OPBRP) for vehicle detection, packets transmission to Roadside Units (RSU) and choosing a better route in terms of reliability via using vehicle's Kinematics and Mobility prediction in VANET. Two fundamental contributions are included in this paper: (1) Upgrading prediction routing protocol to transfer packets using a reliable path, and (2) Adding new logic in choosing the intermediate nodes to the destination to achieve a higher Packet delivery ratio (PDR). The OPBRP uses the predictive greedy as forwarding algorithm and the predictive perimeter forwarding as recovery algorithm after introducing enhancements to both algorithms to meet the requirements of VANETs environment. To materialize the value achieved from the mentioned contributions we tested the newly developed OPBRP against the existing routing protocols using Vehicle in Network Simulation (Veins) which shows that our proposed protocol outperformed current existing routing protocols in terms of PDR by achieving 18.46% improvement, end-to-end delay (E2E-Delay) by achieving 10.51% improvement, and total power consumption used in transmission by achieving 23.80% improvement.

Mobility Prediction Based Tracking of Moving Objects in Wireless Sensor Networks

Mobility Prediction Based Tracking of Moving Objects in Wireless Sensor Networks

Revealing an Inherently Limiting Factor in Human Mobility Prediction

Predicting how humans move within space and time is a central topic in many scientific domains such as epidemic propagation, urban planning, and ride-sharing. However, current studies neglect individuals' preferences to explore and discover new areas. Yet, neglecting novelty-seeking activities at first glance appears to be inconsequential on the ability to understand and predict individuals' trajectories. We claim and show the opposite in this work: exploration-like visits strongly impact mobility understanding and anticipation. We start by proposing a new approach to identifying exploration visits. Based on that, we construct individuals' mobility profiles using their exploration inclinations – <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Scouters</i> (i.e., extreme explorers), <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Routiners</i> (i.e., extreme returners), and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Regulars</i> (i.e., with no extreme behavior). Finally, we evaluate the impacts of novelty-seeking, quality of the data, and the prediction task formulation on the theoretical and practical predictability extents. The results show the validity of our profiling and highlight the obstructive impacts of novelty-seeking activities on the predictability of human trajectories. In particular, in the next-place prediction task, from 40% to 90% of predicted locations are wrong, notably with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Scouters</i> .

A New Individual Mobility Prediction Model Applicable to Both Ordinary Conditions and Large Crowding Events

Accurate prediction of individual mobility is crucial for developing intelligent transportation systems. However, while previous models usually focused on predicting individual mobility under ordinary conditions, the models that are applicable to large crowding events are still lacking. Here, we employ the smart card data of 6.5 million subway passengers of the Shenzhen Metro to develop a Markov chain-based individual mobility prediction model (i.e., SCMM) applicable to both ordinary and anomalous passenger flow situations. The proposed SCMM model improves the Markov chain model by incorporating the station-level anomalous passenger flow index and the collective mobility patterns of similar passengers. Compared with the benchmark models, the SCMM model achieves the highest prediction accuracy in both ordinary conditions and large crowding events. Our results highlight the importance of combining an individual’s own historical mobility data with collective mobility data and suggest the appropriate weights of individual and collective information considered in individual mobility modeling.