The metaverse has evolved from a theoretical concept into a digital infrastructure with multiple simultaneous users, real-time interaction, and high-quality immersive experiences. Traditional architecture inherited from multiplayer gaming cannot adequately meet these requirements due to rendering pressure, battery life, device weight, and service cost. While Cloud and Edge XR architectures address some constraints by offloading computation, they introduce latency issues that com promise immersion. Edge-end collaborative rendering XR offers a promising direction but struggles with task decomposition, edge resource utilization, and practical infrastructure. This paper presents Crossport, a cloud-edge-end architecture that enables microservice-based collaborative rendering for metaverseser vices. Crossport introduces a scene-based microservice decomposition methodology, a composition toolchain supporting multiple consumers, and containerization middleware for integration with existing infrastructure. Experimental evaluation shows Crossport reduces edge resource consumption by up to 29.5% in single-user scenarios and 55.3% in multi-user contexts while maintaining high-quality immersive experiences.

Process mining (PM)-based goal recognition (GR) techniques, which infer goals or targets based on sequences of observed actions, have shown efficacy in real-world engineering applications. This study explores the applicability of PM-based GR in identifying target poses for users employing powered transhumeral prosthetics. These prosthetics are designed to restore missing anatomical segments below the shoulder, including the hand. In this article, we aim to apply the GR techniques to identify the intended movements of users, enabling the motors on the powered transhumeral prosthesis to execute the desired motions precisely. In this way, a powered transhumeral prosthesis can assist individuals with disabilities in completing movement tasks. PM-based GR techniques were initially designed to infer goals from sequences of observed actions, where discrete event names represent actions. However, the electromyography electrodes and kinematic sensors on powered transhumeral prosthetic devices register sequences of continuous, real-valued data measurements. Therefore, we rely on methods to transform sensor data into discrete events and integrate these methods with the PM-based GR system to develop target pose recognition approaches. Two data transformation approaches are introduced. The first approach relies on the clustering of data measurements collected before the target pose is reached (the clustering approach). The second approach uses the time series of measurements collected while the dynamic user movement to perform linear discriminant analysis (LDA) classification and identify discrete events (the dynamic LDA approach). These methods are evaluated through offline and human-in-the-loop (online) experiments and compared with established techniques, such as static LDA, an LDA classification based on data collected at static target poses, and GR approaches based on neural networks. Real-time human-in-the-loop experiments further validate the effectiveness of the proposed methods, demonstrating that PM-based GR using the dynamic LDA classifier achieves superior F 1 score and balanced accuracy compared to state-of-the-art techniques.

The rapid adoption of microservice architectures has spurred research into addressing various challenges in microservice system evolution, such as service deployment and task offloading. While numerous solutions have been proposed by researchers, validating these approaches requires extensive experimentation, including both algorithmic testing and simulations across different Microservice-Based Applications (MBAs). However, current research lacks sufficient physical experimentation, which is essential for evaluating how these solutions perform when deployed on actual computing infrastructure with running microservice instances. This gap exists mainly because conducting physical experiments is complex and costly, primarily due to two barriers: the lack of standardized problem modeling approaches and the absence of suitable experimental platforms. To address these challenges, the Universal Evolution Model (UEM) was proposed that unifies different microservice research problems within a common evolution framework. This model frames research problems as approaches to evolve microservice systems under specific constraints to achieve desired objectives. Based on UEM and the widely-adopted Monitor-Analyze-Plan-Execute over a shared Knowledge (MAPE-K) model, a general Microservice System Evolution Architecture was designed that standardizes experimental processes across diverse research scenarios. Building on these foundations, MicroForge was presented, an open-source experimental platform equipped with tools for accelerating experiments. The platform incorporates RescueService, a carefully curated MBA. Through comprehensive evaluation across various MBAs, the functional effectiveness of MicroForge was validated. Additionally, a practical user guide was provided to facilitate the platform's adoption and utilization.

Goal Recognition (GR) is a research problem that studies ways to infer the goal of an intelligent agent based on its observed behavior and knowledge of the environment in which the agent operates. A common assumption of GR is that the environment is static. However, in many real-world scenarios, for example, recognizing customers’ preferences, it is necessary to recognize the goals of multiple agents or multiple goals of a single agent over an extended period. Therefore, it is reasonable to expect the environment to change throughout a series of goal recognition tasks. This paper presents three process mining-based solutions to the problem of adaptive GR in a changing environment implemented as different control strategies of a system for solving standard GR problems. As a standard GR system that gets controlled, we use the system grounded in process mining techniques, as it can adjust its internal GR mechanisms based on data collected while observing the operating agents. We evaluated our control strategies over synthetic and real-world datasets. The synthetic datasets were generated using the extended version of the Goal Recognition Amidst Changing Environments (GRACE) tool. The datasets account for different types of changes and drifts in the environment. The evaluation results demonstrate a trade-off between the GR performance over time and the effort invested in adaptations of the GR mechanisms of the system, showing that few well-planned adaptations can lead to a consistently high GR performance.

A transhumeral prosthesis restores missing anatomical segments below the shoulder, including the hand. Active prostheses utilize real-valued, continuous sensor data to recognize patient target poses, or goals, and proactively move the artificial limb. Previous studies have examined how well the data collected in stationary poses, without considering the time steps, can help discriminate the goals. In this case study paper, we focus on using time series data from surface electromyography electrodes and kinematic sensors to sequentially recognize patients' goals. Our approach involves transforming the data into discrete events and training an existing process mining-based goal recognition system. Results from data collected in a virtual reality setting with ten subjects demonstrate the effectiveness of our proposed goal recognition approach, which achieves significantly better precision and recall than the state-of-the-art machine learning techniques and is less confident when wrong, which is beneficial when approximating smoother movements of prostheses.

The problem of goal recognition requests to automatically infer an accurate probability distribution over possible goals an autonomous agent is attempting to achieve in the environment. The state-of-the-art approaches for goal recognition operate under full knowledge of the environment and possible operations the agent can take. This knowledge, however, is often not available in real-world applications. Given historical observations of the agents' behaviors in the environment, we learn skill models that capture how the agents achieved the goals in the past. Next, given fresh observations of an agent, we infer their goals by diagnosing deviations between the observations and all the available skill models. We present a framework that serves as an outline for implementing such data-driven goal recognition systems and its instance system implemented using process mining techniques. The evaluations we conducted using our publicly available implementation confirm that the approach is well-defined, i.e., all system parameters impact its performance, has high accuracy over a wide range of synthetic and real-world domains, which is comparable with the more knowledge-demanding state-of-the-art approaches, and operates fast.