fi=vertaisarvioitu|en=peerReviewed|

Mobile Augmented Reality (MAR) applications pose unique challenges due to computation intensity, constrained device resources, and high interactive rendering requirements. The emergence of 5 G and edge computing offers opportunities to offload computation to the edge and cloud, indirectly enhancing the computing capability and usage duration of MAR devices. However, existing general task offloading and multipath transmission techniques do not address the challenges in offloading path selection with multiple edges, dynamic resource competition awareness, and spatial computation with strong task dependencies. This paper contributes FPSelector, a flexible path selector for MAR offloading. We present a two-tier MAR-specific offloading scheme with multiple edge nodes. In offloading decisions, we design a reinforcement learning model to generate the selection policy for each packet of an AR data stream. This model incorporates an action masking mechanism, a comprehensive reward function, and state features complemented by a resource prediction module, making FPSelector aware of dynamic heterogeneous environments. Moreover, we propose an online learning strategy to facilitate real-time selection. To validate its efficacy, we compare FPSelector's performance against leading schedulers under various scenarios, demonstrating a notable reduction of 9.9% and 9.6% in overall completion time for 4 K and 8 K video-based MAR applications compared to its closest competitor.

We develop a portable and affordable solution for estimating personal exposure to black carbon (BC) using low-cost sensors and machine learning. Our approach uses other pollutants and environmental variables as proxies for estimating the concentrations of BC and combines this with machine learning based sensor calibration to improve the quality of the inputs that are used as proxies in the modeling. We extensively validate the feasibility of our approach and demonstrate its benefits with benchmarks conducted on real world data from two different urban locations with different population densities and characteristics. Our results demonstrate that our approach can accurately estimate BC (R2 higher than 0.9) without relying on a dedicated sensor. The results also highlight how calibration is essential for ensuring accurate modeling on low-cost sensor measurements. Our results offer a novel affordable and portable solution that can be used to estimate personal exposure to BC and, more generally, demonstrate how low-cost sensors and proxy modeling can increase the spatiotemporal scale at which information about BC level is available.

With the advancement of assisted and autonomous driving technologies, vehicles are being outfitted with an ever-increasing number of sensors. Among these, visible light sensors, or dash-cameras, produce visual data rich in information. Analyzing this visual data through crowdsensing allows for low-cost and timely perception of urban road conditions, such as identifying dangerous driving behaviors and locating parking spaces. However, uploading such massive visual data to the cloud for centralized processing can lead to significant bandwidth challenges and also raise privacy concerns among vehicle owners. Federated learning (FL), in which vehicles serve as both data generators and computing nodes, presents a promising solution to address these challenges. Nevertheless, urban roads are complex and vehicles in different locations encounter completely different scenes, resulting in non-independently and identically distributed (non-i.i.d.) characteristics. Additionally, the diversity in dash-camera and onboard computation resources may lead to differences in the performance of locally trained models. Indiscriminate aggregating of local models from all vehicles can potentially degrade the global model’s performance. To overcome these challenges, we introduce FedVisual, a model aggregation approach for FL in vehicular visual crowdsensing. FedVisual leverages deep Q-network (DQN) to select appropriate local models, considering the heterogeneities in visual data contents and vehicles’ specifications. By leveraging the historical training experience, an effective model selection strategy can be obtained without complex mathematical modeling. Through the extensive simulations of our self-collected driving videos, FedVisual reduces model aggregation latency by up to 3.8% while improving the model’s performance by up to 3.2% compared to reference works.

The coronavirus disease 2019 (COVID-19) pandemic has changed the world deeply. Urban trajectory big data collected by wireless sensing devices provide great assistance for COVID-19 prevention. However, except for contact tracing, trajectory data are rarely employed in other preventative scenarios against the pandemic. In this article, we try to extend the application of trajectories auto-collected by wireless sensing devices and simulate the epidemic spread in a trajectory data-driven manner. After that, the effects of three nonpharmacological measures are quantified. In contrast to existing studies, additional requirements such as the complex topological networks are needless in our simulation, where the interactions between agents are derived by the intersections of their trajectories. Concretely, the dynamic of virus propagation among individuals is first modeled, and then an agent-based microsimulation environment is built as an artificial system to conduct the epidemic spread simulation. Finally, the trajectories are loaded into the agents as the reliance for their interactions, and the macroscopic changes under different interventions are revealed in a bottom–up way. As a case study, we conduct the simulation based on the trajectories in a real region, in which we find the following. 1) Among the three examined nonpharmacological interventions, community containment is more effective than keeping social distance, which can lower the deaths to nearly 1/9 compared to no action, while travel restrictions play limited roles. 2) There is a strong positive correlation between population densities and mortality. 3) The timing of community containment triggered by confirmed diagnoses is proportional to the number of deaths, thus early containment will significantly decrease mortality.

Federated learning (FL) empowers a cohort of participating devices to contribute collaboratively to a global neural network model, ensuring that their training data remains private and stored locally. Despite its advantages in computational efficiency and privacy preservation, FL grapples with the challenge of non-IID (not independent and identically distributed) data from diverse clients, leading to discrepancies between local and global models and potential performance degradation. In this article, we propose FedGK, an innovative communication-efficient Group-Guided FL framework designed for heterogeneous data distributions. FedGK employs a localized-guided framework that enables the client to effectively assimilate key knowledge from teachers and peers while minimizing extraneous peer information in FL scenarios. We conduct an in-depth analysis of the dynamic similarities among clients over successive communication rounds and develop a novel clustering approach that accurately groups clients with diverse heterogeneities. We implement FedGK on public datasets with an innovative data transformation pattern called “cluster-shift non-IID”, which mirrors the more prevalent data distributions in real-world settings and could be grouped into clusters with similar data distributions. Extensive experimental results on public datasets demonstrate that the proposed approach FedGK improves accuracy by up to 32.89% and saves up to 53.33% communication cost over state-of-the-art baselines.

With the widespread application of mobile phones, it has become possible to study human mobility and travel behaviors based on cellular network data. Contrary to call detail records, the data is triggered by mobile cellular signaling and can provide fine-grained information about users’ daily routines. However, it does not explicitly provide semantic details about traveling traces, e.g., trip purposes. In this paper, we propose a methodological framework to handle large-scale cellular network data and discover the underlying trip purposes in an unsupervised way. We first devise heuristic rules to identify home/work purposes. Then, a flexible latent Dirichlet allocation (LDA) model is presented to discover the activities for remaining trips, in which each trip is depicted by four attributes, i.e. arrival time, age group, stay duration, and the point of interest tag for the destination. Experimental results show that the proposed method can identify diverse trip purposes by explaining their structures over trip attributes and outperform baselines in terms of log-likelihood and perplexity. We also analyze the difference between the automatically discovered trip purposes and those estimated from household census, and the analyzed results demonstrate the feasibility of our proposed method.

Augmented Reality (AR) provides immersive user experiences by overlaying digital information on physical environments. Context-awareness is crucial for delivering relevant augmentations that best suit users' requirements and their en-vironments. In this article, we combine context-aware reasoning with emerging AR applications to provide the most relevant infor-mation according to user and environment contexts. To support the best possible quality of experience, 5G edge computing enables the distribution of computation-intensive AR tasks to edge servers through 5G networks. We develop ConAR, a context-aware head-mounted display AR system that is deployed on the edge and cloud leveraging both environmental sensors and user profile context for navigation. ConAR is composed of a HoloLens application and a paired mobile client, which contains a context model for air quality forecasting, and rendering recommendations on holograms through a HoloLens 2 device. We evaluate our system performance by deploying our proposed air quality prediction algorithm on the edge and cloud while communicating to them using 5G and LTE connections. We measure network quality metrics and find the deployment on the edge with 5G connections significantly outperforms alternative solutions. Our results demonstrate that the 5G edge computing is suitable for supporting latency-sensitive analysis tasks for context-aware AR.

The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence, environmental monitoring stations are typically sparsely deployed, resulting in limited spatial resolution for measurements. Recently, low-cost air quality sensors have emerged as an alternative that can improve the granularity of monitoring. The use of low-cost air quality sensors, however, presents several challenges: They suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors, such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Periodic re-calibration can improve the accuracy of low-cost sensors, particularly with machine-learning-based calibration, which has shown great promise due to its capability to calibrate sensors in-field. In this article, we survey the rapidly growing research landscape of low-cost sensor technologies for air quality monitoring and their calibration using machine learning techniques. We also identify open research challenges and present directions for future research.

Heart rate is a good measure for physical exercise as it accurately reflects exercise intensity and is easy to measure. If the heart rate response to a complete exercise session is predicted beforehand, information related to the exercise can be inferred, such as exercise intensity and calorie consumption. While most current heart rate prediction models are developed and tested for the scenarios of indoor running exercise or low running speed exercise, we adopt a nonlinear Ordinary Differential Equation (ODE) model for complete outdoor running exercise sessions to predict the heart rate response and identify the parameters of the model with machine learning algorithms. The proposed model enables us to predict a complete outdoor running exercise session instead of predicting the heart rate for a short duration. Model validation is carried out both on the training and testing sets. Our results show that the proposed model captures very stable prediction performance.

Semantics associates meaning with Internet of Things (IoT) data and facilitates the development of intelligent IoT applications and services. However, the big volume of the data generated by IoT devices and resource limitations of these devices have given rise to challenges for applying semantic technologies. In this article, we present Cloud and edge based IoT architectures for semantic reasoning. We report three experiments that demonstrate how edge computing can facilitate IoT systems in terms of data transfer and semantic reasoning. We also analyze how distributing reasoning tasks between the Cloud and edge devices affects system performance.