Digital twin is emerging as a key technology to monitor the status of complex industry systems. Valuable insights, such as running statuses and anomalies, can be analyzed from the collected system status timely. Considering that the data updating from each system component (known as a physical object) to its digital twin is performed continuously, timely and accurate streaming analytics based on machine learning models is a key technology to analyze such data efficiently. In this paper, we focus on enabling low-delay yet highly-accurate streaming analytics for digital twin applications in mobile edge computing (MEC) networks. Specifically, we formulate a fundamental optimization problem of digital twin placements and model selections for streaming analytics, with the aim of minimizing both the analytic loss and the processing delay. To this end, we first consider the problem with a single query, for which, we propose an approximation algorithm with provable approximation ratio for a special case, and then devise an efficient algorithm for the original problem with a single query. We then study the online digital twin placement and model selection problem for streaming analytics with multiple queries under real scenarios, where resource demands of arrival queries and resource availability of MEC network are uncertain. We propose an online learning algorithm with a bounded regret to make admission policies. We finally evaluate the performance of the proposed algorithms by extensive simulations. Results show that the weighted sums of the total processing delay and the cumulative loss in the solution delivered by the proposed algorithms outperform their counterparts by 12.5% with a single query and 13.3% with multiple queries, respectively.

Big data analytics for Earth observation has been playing an increasingly important role in supporting environmental monitoring, disaster early warning, and sustainable development through timely analysis of massive multi-source data collected by satellites. With the growing need for such timely Big Data analysis, Space Edge Computing (SEC) networks have been proposed to provide in-orbit analytic services for users worldwide, by integrating computing capability through Low-Earth-Orbit (LEO) satellites. However, the monitoring frequency of LEO satellites over specific target areas remains limited due to orbital constraints, making it difficult to meet the high-frequency data acquisition demands of Big Data analytics. Satellite inclination maneuver is a promising method to cover a wide range of target areas and enhance monitoring frequency by adjusting orbital inclination of satellites. Although such maneuvering enables satellites to timely process datasets, reducing energy wastage caused by inter-satellite data transmission, it consumes propulsion fuel, which is limited and difficult to replenish in a timely manner. Therefore, balancing the energy consumed for data processing and the fuel consumed for maneuvering is essential for efficient and sustainable Big Data analytics in SEC networks. In this paper, we aim to optimize Big Data query evaluation problem with satellite maneuver in an SEC network, focusing on minimizing the weighted sum of energy consumed for processing and fuel consumed for maneuvering. Specifically, we consider that each Earth observation service needs to guarantee a certain level of monitoring frequency, which may not always be satisfied by the original orbital coverage of LEO satellites. In such cases, some satellites will be selected to perform inclination maneuvers for additional monitoring and processing to guarantee the quality of Earth observation services. To this end, we first propose an approximation algorithm with a provable approximation ratio for the offline query evaluation problem, which leverages a customized auxiliary graph to jointly minimize energy and fuel consumption. We then devise an online learning algorithm, referred to as the customized Lipschitz bandit learning algorithm, with a bounded regret for the online Big Data query evaluation problem in an SEC network. We finally evaluate the performance of the proposed algorithms in a real SEC network topology. Experiment results show that the performance of the proposed algorithms achieve 11% lower energy consumption and 10.6% lower fuel consumption than those of their comparison counterparts.

Data stream processing is a functionality of various AI applications to obtain continuous insights from data streams. Serverless edge computing (SEC) is a key solution for implementing data stream processing requests by deploying serverless functions into cloudlets. However, existing data stream processing methods focus more on processing delay, ignoring fault tolerance and complex dependencies among functions, resulting in critical events being missed in the event of any fault and processing inefficiency. Besides, due to the uncertainty of data streams, existing function deployment methods may not be suitable for their newly changed data rates, causing resource waste or shortages. To address these problems, we first propose an optimization framework to enable efficient and fault tolerant function deployment, such that the delay of data stream processing is minimized while meeting its fault tolerant requirements and resource capacity constraints of cloudlets in an SEC network. We then design an online learning algorithm that predicts data rate changes through a multi-timescale machine learning method and proactively adjusts instance locations and numbers to absorb data rate uncertainty. Experimental results in a real test-bed show that our proposed algorithms outperform their counterparts by 13.5% on the average delay and 26.3% on the average fault tolerance.

We present FGO-SLAM++, a real-time geometry-aware Gaussian SLAM system capable of processing video streams from arbitrary modalities. The system performs multi-view consistent map reconstruction by maintaining a continuous opacity field. Existing Gaussian SLAM systems face challenges in achieving efficient tracking and mapping while supporting multiple input modalities, which often necessitates a trade-off between rendering quality and geometric accuracy. This study demonstrates that it is possible to satisfy all these requirements simultaneously using video streams of arbitrary modalities. The core of the proposed method involves explicit geometric feature extraction to capture the underlying scene structure and estimate camera poses, followed by a Gaussian-based ray tracing strategy to construct and optimize an opacity field. Upon the detection of loop closures, the system performs global adjustment to enhance map consistency. Furthermore, the surface is directly extracted using the marching tetrahedra method and refined through a geometric constraint field. Extensive experiments demonstrate that the proposed method achieves superior performance in tracking accuracy, rendering quality, geometric reconstruction, and real-time efficiency.

We present EarEOG, a real-time wheelchair control system using around-ear electrooculogram (EOG) signals. Electrodes are placed in standard over-the-ear headphones to improve user comfort. By detecting around-the-ear signals from eye gestures and jaw clenching, EarEOG offers a non-invasive and intuitive approach to low-latency wheelchair control. We describe the methods for signal acquisition, as well as the algorithms used for signal processing and classification. The feasibility, robustness, and low latency of EarEOG were confirmed through two experiments. The algorithm demonstrated a classification accuracy of 94.1% for all motion signals, which further improved to 97.3% when personalized models were applied. To ensure stability, we examined electrode impedance and algorithm accuracy across multiple trials where participants operated simulated wheelchairs while wearing EarEOG. The results indicated that when the electrode impedance was below 1 MΩ, all participants successfully controlled the simulated wheelchair. Furthermore, EarEOG demonstrated low latency, with recognition delays of less than 125 ms.

Jaspreet Ranjit, Brihi Joshi, Rebecca Dorn, Laura Petry, Olga Koumoundouros, Jayne Bottarini, Peichen Liu, Eric Rice, Swabha Swayamdipta. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

In recent years, Graphical Processing Unit (GPU) is not only becoming a piece of hardware that accelerates graphics but also playing a key role in accelerating the fields of machine learning and artificial intelligence. The GPU’s heightened importance has led to increasing concern about the confidentiality of a GPU’s computing data as well as its internal communications. Although the GPU Trusted Execution Environment (TEE) has been implemented as a solution toward this issue, side-channel attacks in GPUs still remain as an open problem. In this work, we introduce Delay-masquerading Technique Upheld StrongBox (DTUBox) to strengthen the resilience of existing GPU TEE over StrongBox against side-channel attacks by injecting obfuscated noise with our developed algorithm, making the correlations difficult to reference between a task and workload. In our evaluation, we demonstrate that with only around 5% performance overhead, our approach could effectively lower the correlation rate to 38% between the original behavior sequences and the obfuscated sequences.

Abstract Nowadays, as the smart campus concept becomes a reality, virtual reality (VR) applications are being applied to connect students with the virtual teaching world via VR devices (VDs), enhancing learning efficiency. Nevertheless, VR applications are latency‐sensitive while VDs are subjected to shortcomings to handle many VR applications simultaneously. Fortunately, mobile edge computing (MEC) has been recognized as a promising solution that can bring abundant resources to VDs to relieve hardware limits. However, the computing resources of edge nodes in MEC are limited, and thus how to allocate resources effectively is critical. Meanwhile, some sensitive information of students collected by VD needs to be protected. In view of this, we investigate computation offloading for educational VR applications in MEC‐enabled smart campus. The aims of this issue are to optimize the motion‐to‐photon latency, energy consumption, and resource utilization while satisfying the privacy and security constraints. To this end, we propose a new multi‐objective optimization method using MoCell. Eventually, the experimental evaluations are designed to illustrate the effectiveness and superiority our proposed method.

Mobile edge computing (MEC), which is regarded as a promising paradigm, is proposed to provide smart cities that are supported by the Internet of Things (IoT) with low processing latency at the edge of the network, by offloading latency-critical tasks from MDs to edge service providers (ESPs). In this paper, we study the interaction between ESPs and MDs by formulating a Stackelberg game model, to optimize the strategies of computation offloading and resource allocation of the MDs, and the prices and investment spending on the privacy level of ESPs. Additionally, the social effect of MDs on privacy concerns is incorporated to study the impacts on the payoffs of players. We utilize distributed Alternating Direction Method of Multipliers (ADMM) algorithm to address the Stackelberg equilibrium problem in a distributed manner. Finally, numerical results illustrate that our proposed scheme can jointly achieve the maximum profits of ESPs and utilities of MDs.