Xiaoli Liu

Mobile Augmented Reality (MAR) applications pose unique challenges due to computation intensity, constrained device resources, and high interactive rendering requirements. The emergence of 5G 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.

6G networks are envisioned to enable the Internet of Things (IoTs) and foster ubiquitous sensing. Urban opportunistic crowdsensing, which leverages participants carrying mobile sensing units (MSUs) in their daily activities to collect data, enables low-cost and large-scale urban sensing for applications such as air quality monitoring, pothole detection, and noise classification. However, urban opportunistic crowdsensing poses challenges to conventional cloud-based centralized learning due to the unpredictable nature of crowdsensed data collection and privacy concerns from uploading personal information to the centralized cloud. Federated learning (FL), where MSUs act as data sources and computing nodes, offers a promising alternative to mitigating these issues. Despite FL’s potential, urban crowdsensing contexts’ spatial-temporal diversity, mobility, constrained resources, and emerging privacy concerns present new challenges. In this paper, we explore the opportunities and challenges of FL in urban opportunistic sensing in 6G networks and suggest potential optimization strategies. Furthermore, we conduct field experiments in Helsinki, Finland, and design an FL-based air quality calibration method for opportunistic crowdsensing to demonstrate the feasibility of our vision.

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.

Industry 4.0, leveraging the Internet of Things (IoT) and Artificial Intelligence (AI), is a key enabler for many automated processes in modernized industrial applications. This paper addresses significant challenges pertaining to sensing and data analytics by connecting a large number of industrial IoT (IIoT) devices and deploying federated learning on 5G edge networks. We envision a federated learning-based 5G edge architecture for IIoT and develop an AI algorithm, i.e., an LSTM autoencoder algorithm for anomaly detection, on the 5G edge.We conduct comprehensive scalability analytics of communication and computation resources on our 5G edge IoT testbed. Our experimentation verifies that 1) federated AI algorithms can be deployed on 5G edge servers for latency-sensitive analytics, and 2) 5G edge supports scalable deployment of IIoT devices with low latency.

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-i.i.d. (non-independently and identically distributed) 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 models 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 models performance by up to 3.2% compared to reference works.

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.

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.

Mobile augmented reality (MAR) systems typically offload computation-intensive tasks to edge servers. This paper contributes a comparative analysis of Genetic Algorithm (GA) and Ant Colony Optimization (ACO) in task offloading optimization for MAR on the edge, in terms of latency and power consumption across eight distinct setups with varying server configurations and tasks. Our experimental findings indicate that the ACO algorithm consistently manifests lower latency than the GA algorithm in setups where the servers are in proximity to the edge devices. However, the GA outperforms the ACO algorithm in setups where the servers are situated at a greater distance. The ACO algorithm primarily offloads tasks to a single server, resulting in consistent latency performance, while the GA demonstrates a more diverse task offloading strategy by distributing tasks across multiple servers and the local device. The latency fluctuations in the ACO are primarily attributed to changes in the offloading patterns, especially when tasks are offloaded to different servers than those predominantly used. On the other hand, the GA algorithm, with its more varied offloading approach, exhibits less significant latency variations. Regarding to power consumption, the GA algorithm generally consumes higher power than the ACO algorithm in most setups due to its more diverse task distribution strategy.