Accurate and robust locomotion mode prediction is crucial for seamless interaction between humans and assistive devices. While multimodal sensing offers a promising avenue for enhanced accuracy, existing approaches often struggle to demonstrate clear advantages over unimodal methods, largely due to a lack of understanding regarding each modality's unique characteristics and task-specific strengths. To address this, we present a systematic comparative analysis of Inertial Measurement Unit (IMU) and surface Electromyography (sEMG) modalities for human locomotion mode prediction. Utilizing a public dataset (nine subjects, 17 gait activities), our experiments rigorously evaluated performance across cyclic and non-cyclic locomotion tasks, considering both steady-state and transition-state. We investigated the impact of deep learning architectures (CNN, LSTM, TCN) and sliding-window lengths (short vs. long) on prediction accuracy and stability. Statistical analyses reveal significant performance differences dependent on modality, window length, and gait type. Notably, our findings demonstrate that optimal classification accuracy is achieved by leveraging IMU data with short windows for non-cyclic locomotion modes prediction and sEMG data with long windows for cyclic locomotion modes prediction, with Temporal Convolutional Networks (TCNs) consistently yielding superior overall results. These findings offer concrete guidelines for effectively fusing multimodal data, leveraging modality-specific strengths to enable adaptive, interpretable, and high-performance locomotion mode prediction.

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.

Metaverse, as the cyberspace against the real world, offers various immersive services enabling users to entertain, learn and work. The digital twin (DT) technology acts as a fundamental enabler of Metaverse services by mapping user devices to DTs and timely analyzing the status of user devices. Mobile edge computing (MEC) significantly improves the QoS of DT-empowered Metaverse services because it can deploy DTs in cloudlets closer to user devices. However, each user device often has a complex structure with multiple interdependent subsystems that frequently communicate. Further, the resources in MEC network are highly distributed and limited. Thus, provisioning DT-empowered Metaverse services in MEC networks faces the challenge of efficiently mapping intertwining subsystems in user devices to DTs, maximizing admitted service requests and resource utilization. In this paper, we first formulate throughput maximization problems for DT-empowered Metaverse services in an MEC network, with the aim to maximize the total data rate of service requests of Metaverse services while meeting resource capacity constraints of the MEC network. We then propose an approximation algorithm with a provable approximation ratio for the problem with a given set of service requests if both monitoring and analytical DTs are consolidated into a single edge server. Otherwise, we devise an efficient heuristic for the problem with monitoring and analytical DTs possibly being placed into different edge servers. We also consider a dynamic throughput maximization problem of Metaverse service provisioning for a given monitoring period, in which service requests arrive into the system dynamically without the knowledge of future arrivals, service resource demands, and service delay requirements, for which we devise an online learning algorithm. We finally evaluate the performance of the proposed algorithms by extensive simulations. Simulation results show that the throughputs of the proposed algorithms outperform their comparison counterparts by at least 50 %.

The increasing number of Distributed Denial of Service (DDoS) attacks poses a major threat to the Internet, highlighting the importance of DDoS mitigation. Most existing approaches require complex training methods to learn data features, which increases the complexity and generality of the application. In this paper, we propose DrLLM, which aims to mine anomalous traffic information in zero-shot scenarios through Large Language Models (LLMs). To bridge the gap between DrLLM and existing approaches, we embed the global and local information of the traffic data into the reasoning paradigm and design three modules, namely Knowledge Embedding, Token Embedding, and Progressive Role Reasoning, for data representation and reasoning. In addition we explore the generalization of prompt engineering in the cybersecurity domain to improve the classification capability of DrLLM. Our ablation experiments demonstrate the applicability of DrLLM in zero-shot scenarios and further demonstrate the potential of LLMs in the network domains. The implementation of DrLLM is available at https://github.com/liuup/DrLLM.

The emergence of Internet of Vehicles (IoV) technology provides a wider range of application scenarios for edge computing based on Vehicle-to-everything (V2X). It is essential to ensure the high availability and reliability of services in IoV systems. Currently, cloud service providers have established a data center level of fault tolerance, such as redundancy and checkpoints, guaranteeing the reliability of cloud infrastructure and reducing phenomena such as service termination or downtime. However, current computing systems reactively handle failures. Especially in edge computing, this approach not only lacks flexibility but also consumes excessive system resources, which is not conducive to ensuring the reliability in resource-constrained systems and poses security risks to end users. To mitigate this problem, we propose a Proactive Fault-tolerance Driven Task Scheduling System. Different from the traditional reactive strategies, the proposed framework predicts the possible system crashes by monitoring the critical state indicators of the computing system. According to the prediction results, a class of tasks or services that are most likely to be terminated are rescheduled in advance. Extensive experiments are conducted, and evaluation results demonstrate that our proposed proactive fault tolerance framework can effectively improve the long-term performance of the IoV edge system.

Force estimation is the core indicator for evaluating the performance of tactile sensors, and it is also the key technical path to achieving precise force feedback mechanisms. This study proposes a design method for a visual tactile sensor (VBTS) that integrates a magnetic perception mechanism, and develops a new tactile sensor called MagicGel. The sensor uses strong magnetic particles as markers and captures magnetic field changes in real time through Hall sensors. On this basis, MagicGel achieves the coordinated optimization of multimodal perception capabilities: it not only has fast response characteristics, but also can perceive non-contact status information of home electronic products. Specifically, MagicGel simultaneously analyzes the visual characteristics of magnetic particles and the multimodal data of changes in magnetic field intensity, ultimately improving force estimation capabilities.

Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from teacher networks without access to the real dataset. However, generator-based DFKD methods often suffer from insufficient diversity or low-confidence in synthetic images, negatively impacting student network performance. This paper introduces DFMC, a generative feature-driven framework to mitigate the inherent limitations of DFKD. We propose exploiting semantic description between generative feature domains to guide augmentation strategies, avoiding random abstract inputs caused by inconsistent semantic quality. Then, by applying noise to the generative features, we produce contrastive learning pairs indirectly, limiting the sampling range of the feature domain to encourage the student network to learn domain-invariant features. Finally, we guide the student network to deeply mimic the teacher’s layer-wise implicit classification behavior for the augmented synthetic images. Extensive experiments across various datasets and downstream tasks demonstrate the effectiveness of DFMC, achieving significant improvements while preventing student networks from overfitting to semantic ambiguous images.

Peatlands, which constitute only 3% of Earth’s land surface, store an estimated 612 Pg of carbon. Due to escalating warming and anthropogenic impacts, numerous peatlands undergo degradation, releasing stored carbon into the atmosphere and exacerbating global warming. The accurate delineation of the extents and boundaries of peatlands is imperative to mitigate peatland degradation, but it also remains a considerable challenge. This study developed a peatland machine-learning classification model using an object-based random forest (RF) algorithm, comprehensive spatiotemporal features, and multisource remote sensing data, including Sentinel-1, Sentinel-2 imagery, and digital elevation model (DEM). A high-resolution peatland map (10 m) was generated for the Changbai Mountains (CBM) in northeastern China. The results show that spectral indices from May play a particularly significant role in enhancing the accuracy of the classification. The study achieved an overall accuracy (OA) exceeding 94%, with the classification accuracy for the peatland category surpassing 91%. The analysis revealed that peatlands cover approximately 1197.09 km2 in the area, with over 80% situated below 1000 m a.s.l., around 70% on slopes less than 4°, and more than 80% within 5 km of a water body. This study proposes the novel methods for selecting feature variables in classification, aiming to enhance the accuracy of peatland mapping, thus providing critical insights and a benchmark for future refined mapping efforts. The results from this mapping endeavor hold substantial implications for the conservation and management of peatlands.

Existing methods for diagnosing middle ear diseases using temporal bone computed tomography (CT) imaging primarily focus on adult datasets and require labor-intensive manual input from radiologists to label and select regions of interest (ROIs). These methods rely on prior knowledge and introduce inter- and intra-observer variability. Additionally, the selected ROIs typically consist of a few 2D slices, underutilizing the 3D capabilities of CT imaging. Moreover, these methods are not reproducible on pediatric datasets, where rapidly developing heads exhibit greater morphological variability. To address these challenges, we developed a fully automated framework for precise diagnosis of pediatric chronic suppurative otitis media (CSOM) and cholesteatoma (MEC) using temporal bone CT imaging. Our method automatically detects the most informative 3D ROIs by calculating entropy changes in the 3D anatomical structures of the middle ear, eliminating the need for annotations or prior knowledge. We also introduce a multi-scale classification network that incorporates a global-local feature interaction strategy and uses a wide and deep multi-layer transformer for feature extraction, effectively learning feature dependencies. Experimental results on a dataset of CT images from 603 pediatric patients show that our method achieves a classification accuracy of 93.17% and an AUC-ROC of 96.84%, outperforming state-of-the-art methods. This innovative approach reduces radiologists’ workload, aids automated surgical navigation, and has the potential to transform diagnostic workflows in otolaryngology.

Internet-of-Things (IoT) applications from many industries, such as transportation (maritime, road, rail, air) and fleet management, offshore monitoring, and farming are located in remote areas without cellular connectivity. Such IoT applications continuously generate stream data with hidden values that need to unveiled in real time. Streaming analytics is emerging as a popular type of Big Data analytics to process large volume of stream data for IoT applications in remote regions. Built upon terrestrial-satellite integrated networks, Satellite Edge Computing (SEC) equipped with computing resource in satellites has been envisioning as a key enabling technology to timely analyze stream data of IoT applications in remote regions on the Earth. Considering the dynamically-moving property of satellites in an SEC network, it is vital to optimize the responsiveness of each Big Data analytical query, such that none of such queries takes much longer time to wait for available satellites with sufficient computing resource. Furthermore, the uncertain data volumes of Big Data queries in SEC networks make the resources in satellites fragmented, particularly when the collaboration among satellites is intermittent. Therefore, directly application of existing methods may not guarantee the timelineness of streaming analytics in an SEC network. To address the afore-mentioned unique challenges of streaming analytics in SEC networks, it is urgent to design new algorithms and methods for timely Big Data processing. Specifically, we use theflow timeto capture the responsiveness of streaming analytics in satellite edge computing, which is the time between the generation of the first unit of a dataset and the finish time of the data processing. We consider the flow time minimization problem for query evaluation of Big Data analytics in an SEC network with the aim of minimizing the average flow time of Big Data analytical queries, under an assumption of uncertain volumes of datasets. To this end, we first propose an approximation algorithm with a provable approximation ratio for the offline version of the flow time minimization problem. We then devise an online learning algorithm, referred to the customized Lipschitz bandit learning algorithm, with a bounded regret for the online version of the problem. We finally evaluate the performance of the proposed algorithms in a real SEC network topology. Experiment results show that the performance of the proposed algorithm outperforms its counterparts by at least 13% in terms of flow time.

Abstract Carbon footprint monitoring provides significant basis for computing facilities to improve the computing efficiency and reduce the energy cost, which can enable low/zero carbon computing and facilitate the construction of sustainable cites. Massive sensing devices access to 5G base station to transmit collected carbon emission data, which requires intelligent access management. Fast uplink grant possesses the advantages of reducing signalling overhead and access conflicts while facing the problems of incomplete information and difficulty in guaranteeing priority constraint. This paper examines, the maximum access queuing delay minimization problem is formulated under the long‐term service priority constraint and the short‐term access management constraint. First, Lyapunov optimization is leveraged to decouple the long‐term service priority constraint and short‐term access management optimization, and decompose the long‐term stochastic optimization problem into a series of short‐term deterministic problems. Then, a priority‐aware deep Q‐network (DQN)‐based fast uplink grant access management (PDAC) algorithm is proposed to achieve intelligent access management with differentiated service priority requirements. PDAC utilizes DQN to handle non‐convex high‐dimensional optimization problem with service priority constraint to achieve intelligent access management and priority awareness. Simulation results demonstrate that PDAC outperforms the existing algorithms in access queuing delay, buffer queue backlog, and priority deficit fluctuation.

The real-time electrical equipment management, such as renewable energy, controllable loads, and storage units, plays a key role in low-carbon operation of smart industrial park. Digital twin (DT), which explores cloud-edge-device collaboration and artificial intelligence to establish accurate digital representation of physical equipment, is a cutting-edge technology to realize intelligent optimization of electrical equipment management. However, the practical implementation still faces reliability and communication efficiency problems, such as adverse impact of electromagnetic interference on DT reliability, high communication cost of DT model training, and uncoordinated resource allocation among cloud, edge, and device layers. We propose a Cloud-edge-device Collaborative reliable and Communication-efficient DT for lOW-carbon electrical equipment management named$\text{C}^{3}$-FLOW. It minimizes the long-term global loss function and time-average communication cost by jointly optimizing device scheduling, channel allocation, and computational resource allocation. Simulation results verify that$\text{C}^{3}$-FLOW performs superior in loss function, communication efficiency, and carbon emission reduction.