With the rapid advancement of big data processing and artificial intelligence (AI), data center networks (DCNs) must deliver more efficient resource management and data transmission mechanisms. Unfortunately, due to the significant differences in bandwidth requirements, transmission patterns, and temporal characteristics across various traffic types in DCNs (such as short flows, long flows, and bursty flows), traditional buffer allocation strategies fail to adapt flexibly to these disparities. In this paper, we propose Enhanced Buffer Management (EBM), a novel buffer-sharing scheme designed for scenarios that require higher performance from DCNs. Unlike prior approaches, EBM employs a multi-level flow identification and adaptive threshold adjustment mechanism to enhance the flexibility and efficiency of buffer management under varying traffic conditions. Specifically, EBM first performs coarse-grained and fine-grained classification of traffic based on packet size, inter-arrival interval, and other flow characteristics. It then applies an improved threshold computation function to allocate buffer space differentially across traffic classes while maintaining allocation smoothness. Our evaluation results demonstrate that EBM significantly improves performance under realistic workloads. For instance, it reduces the 99th percentile Flow Completion Time (FCT) slowdown by 32.7% for short flows in the web-search workload and by 45.1% for incast flows in the hadoop workload, all without sacrificing overall throughput.

Leveraging ubiquitous WiFi infrastructures, intrusion detection methods based on Received Signal Strength (RSS) offer compelling advantages, including cost-effectiveness and privacy protection. However, existing RSS-based intrusion detection solutions fall short of accurately estimating and extending the WiFi sensing bound. In this paper, we propose a novel model of motion-disturbed RSS and design an effective R-ratio indicator to extend the intrusion detection bound. Specifically, we first establish a general model of motion-disturbed RSS and derive the blocked area and reflection area in this RSS model. Then, we define the WiFi intrusion detection bound and propose a performance indicator called R-ratio to extend the bound with RSS. Furthermore, based on the statistical properties of noise, we design an efficient filter to further weaken the noise. We also propose two new methods to further extend intrusion detection bound. Extensive experimental results demonstrate that the proposed power sum ratio based intrusion detection method can approximately double the WiFi intrusion detection bound compared to other methods with raw RSS data, and our developed motion-disturbed RSS model can provide valuable insights and guidance to the intrusion detection system.

Although radio frequency (RF)-based activity recognition has made significant progress in recent years, the sensing performance will be significantly degraded under class imbalance conditions, especially when minority and majority classes share semantically similar local motion patterns. Traditional data augmentation approaches in the original sample space may cause semantic deviation and meanwhile bring high computational cost. Instead, in this work we turn to address the issue at feature level, in which we focus on how to distinguish highly similar actions and mitigate imbalance-induced decision boundary bias. To tackle these challenges, we present attention-guided context enhancement network (AceNet), which designs a discriminative feature extractor and develops a feature-augmentation based classifier refinement strategy. Specifically, an attention-guided mechanism is presented to dynamically select the most distinctive temporal segments, and a hierarchical Transformer structure is then proposed to characterize both inner-segment micro-dynamics and inter-segment contextual relationships. Moreover, AceNet synthesizes features via Synthetic Minority Over-sampling Technique (SMOTE) to balance feature distribution for each category and then refine the classifier parameters to mitigate class imbalance bias. Comprehensive experiments on two public datasets with different RF modalities demonstrate that AceNet significantly outperforms existing approaches under various levels of data scarcity at a low cost.

Accurate early detection of obstructive sleep apnea (OSA) is critical for enabling timely auto-adjusting positive airway pressure (APAP) interventions. However, existing methods largely rely on binary classification (normal vs. apnea), failing to capture the transitional state preceding OSA onset and inducing therapy delays-hampered by open issues of ambiguous biomarkers and signal temporal misalignment. To address this, this study redefines sleep physiology into three distinct states: normal breathing, pre-apnea transitional (30 s pre-onset), and apnea. This study further proposes DREAM-OSA, a dual-modal transformer framework that specifically targets the transitional states, providing APAP with a sufficient advance response window (up to 10 s) to enable true early prediction of OSA events. It synergizes the complementary electroencephalogram (EEG) and respiratory signals through: 1) Modality-Specific Tokenization: EEG (decomposed into$\delta, \theta, \alpha, \beta, \gamma$bands) and respiratory signals are segmented into 1 s patches, encoded via dedicated 1DCNNs while preserving temporal-spectral structural information through learnable embeddings; and 2) Hierarchical Attention: Intra-modal self-attention captures temporal-spectral dynamics within each modality, while inter-modal cross-attention models bidirectional EEG-respiratory interactions. Evaluated on the MASS-SS1 dataset vs. the state-of-the-art methods towards real-time OSA early warning, DREAM-OSA achieves: overall accuracy up to 95.0%, and per-class F1-scores reaching 91.9% (normal), 94.9% (transitional), and 97.0% (apnea), demonstrating significantly more reliable detection of the transitional states, whereas its counterparts face performance bottleneck.

Integrated Sensing and Communication (ISAC) is regarded as a promising approach to improve the original performance for unmanned aerial vehicle (UAV) networks. Nevertheless, it is still limited by the UAV's energy constraints and dynamic links with user equipment (UE). To address these issues, we attempt to deploy the Reconfigurable Intelligent Surface (RIS) for signal reflection, improving sensing and communication performance. Additionally, employing downlink-uplink decoupling (DUDe) can enable each UE to associate with diverse UAVs for downlink (DL) and uplink (UL), further enhancing transmission quality. Therefore, we study the RIS deployment, decoupled UE- UAV association and trajectory design for a RIS-aided UAV network. A joint optimization problem is formulated for maximizing the sum rate in UL and DL. Specifically, we transform the joint problem as a Markov Decision Process, and employ a distributed multi-agent deep reinforcement learning (MADRL) approach to select policies. Moreover, we develop a robust Proximal Policy Optimization (PPO) algorithm to train the AC networks, wherein the Random Environment Distribution is utilized for adapting to varying scenarios and we design an intrinsic reward to expand UAV s' exploration range. Simulation results validate the feasibility and superiority of the RED-PPO approach through comparative analysis.

The risk of adverse effects in Electroconvulsive Therapy (ECT), such as cognitive impairment, can be high if an excessive stimulus is applied to induce the necessary generalized seizure (GS); Conversely, inadequate stimulus results in failure. Recent efforts to automate this task can facilitate statistical analyses on individual parameters or qualitative predictions. However, this automation still significantly lags behind the requirements in clinical practices. This study addresses this issue by predicting the probability of GS induction under the joint restriction of a patient's EEG (electroencephalogram) and the stimulus parameters, sustained by a two-stage learning model (namely ECTnet): 1) Temporal-Spatial Feature Learning. Channel-wise convolution via multiple convolution kernels first learns the deep features of the EEG, followed by a "ConvLSTM" constructing the temporal-spatial features aided with the enforced convolution operations at the LSTM gates; 2) GS Prediction. The probability of seizure induction is predicted based on the EEG features fused with stimulus parameters, through which the optimal parameter setting(s) may be obtained by minimizing the stimulus charge while ensuring the probability above a threshold. Experiments have been conducted on EEG data from 96 subjects with mental disorders to examine the performance and design of ECTnet. These experiments indicate that ECTnet can effectively automate the selection of optimal stimulus parameters: 1) an AUC of 0.746, F1-score of 0.90, a precision of 89% and a recall of 93% in the prediction of seizure induction have been achieved, outperforming the state-of-the-art counterpart, and 2) inclusion of parameter features increases the F1-score by 0.054.

In mobile edge computing (MEC), edge servers and mobile terminals use federated learning distributed architecture to build a deep model, so that terminals can cooperate in training without sharing data. Distributed training requires network virtualization to provide high bandwidth and low latency characteristics to support large-scale parallel computing. Traditional virtual network embedding (VNE) relies on a static network topology, which lacks flexibility and incurs high resource costs during model training. To improve the efficiency of embedding distributed training tasks, we propose a novel Node Selection and Dynamic Topology resource allocation scheme for VNE of distributed training, NSDT-VNE, based on reconfigurable network topology. This algorithm divides the underlying network into static and dynamic topologies, enhancing low latency for small flows while providing high bandwidth for large flows as needed. Additionally, we introduce a two-phase coordinated alternating optimization algorithm that optimizes embedding decisions at both computational and topological levels, ensuring optimal node selection. Overall, NSDT-VNE follows demand-aware network design principles, allowing continuous optimization of the underlying topology. Compared to state-of-the-art heuristic and reinforcement learning-based virtual network algorithms, NSDT-VNE achieves superior performance, with request acceptance rates improving by 6.67% to 25.68% and embedding revenue increasing by approximately 7% to 32%.

Despite the widespread application of radio frequency (RF) signal-based human action recognition, traditional solutions can only recognize seen categories and the perception scope is restrained by the limited activity classes. When a novel category emerges, the model needs to be optimized again on additionally collected samples at the cost of computation and labor burden. To address this challenge, we develop the mmZeAR system, which learns semantic knowledge from available vision data as class attributes and then transforms the classification into a matching problem. Specifically, we build the attribute space by fusing the coarse-grained video classification features and fine-grained angle change features of 3D joint skeletons. Then we design an efficient feature extraction backbone named TriSqN, which integrates triple radar heatmaps into the final representations by sufficiently exploring the heterogeneous and complementary characteristics. Finally, a projection network is developed between semantic attributes and radar features to construct indirect relationships between samples and labels. By implementing mmZeAR on millimeter wave (mmWave) radar signal datasets, our extensive experiments have demonstrated its remarkable recognition accuracy in novel category recognition with zero effort and achieved state-of-the-art performance.

Traditional indoor location data sharing methods using centralized servers face issues like safe and reliable transmission, personal privacy leaks, location information tampering, and computing and storage loads, hampering the growth of personalized indoor services. In this paper, a novel mobile blockchain-enabled federated learning (MBFL) data sharing framework for indoor positioning is presented. Then, we derive training latency and reward of the individual user, and formulate latency-limited resource allocation as a non-cooperative game. We propose an efficient alternating iterative algorithm to achieve the Nash equilibrium of this game. Numerical results demon-strate that the proposed alternating iterative algorithm achieves rapid convergence. Furthermore, when confronted with model poisoning attacks, the MBFL method exhibits superior security performance compared to the traditional FL method.

Traditional indoor location information management methods based on centralized servers have problems such as safe and reliable transmission, personal privacy leaks, location information tampering, and computing and storage loads. These problems have seriously affected the development of personalized services based on indoor location information. In this paper, a novel mobile blockchain-enabled federated learning (MBFL) information management framework for indoor positioning is presented, comprising the mobile blockchain model, the federated learning (FL) model, and the InterPlanetary file storage model. Then, we design the MBFL algorithm, establishing a robust foundation for collaborative model training, efficient block mining, and secure data storage. Moreover, we derive training and mining latency as well as the individual user rewards, and formulate latency-limited resource allocation strategies as a non-cooperative game. We propose an efficient alternating iterative algorithm to achieve the Nash equilibrium of this game. Numerical results demonstrate that the proposed alternating iterative algorithm achieves rapid convergence and strikes an effective balance between economic and time efficiency. Furthermore, when confronted with model poisoning attacks, the MBFL algorithm exhibits superior security performance compared to the traditional FL algorithm. Future work will focus on adapting the MBFL framework for various indoor environments and enhancing consumption and computational efficiency with hybrid consensus mechanisms.

Multivariate time series data (Mv-TSD) portray the evolving processes of the system(s) under examination in a “multi-view” manner. Factorization methods are salient for Mv-TSD analysis with the potentials of structural feature construction correlating various data attributes. However, research challenges remain in the derivation of factors due to highly scattered data distribution of Mv-TSD and intensive interferences/outliers embedded in the source data. The proposed Enhanced Bayesian Factorization approach (Enhanced-BF) addresses the challenges in three phases: (1) variant scale partitioning applies to Mv-TSD according to degree of amplitude and obtains the blocks of variant scales; (2) hierarchical Bayesian model for tensor factorization automatically derives the factors of each block with interferences suppressed; (3) Bayesian unification model merges those block factors to construct the final structural features.Enhanced-BFhas been evaluated using a case study of brain data engineering with multivariate electroencephalogram (EEG). Experimental results indicate that the proposed method manifests robustness to the interferences and outperforms the counterparts in terms of operation efficiency and error when factorizing EEG tensor. Besides,Enhanced-BFexcels in factorization-based analysis of ongoing autism spectrum disorder (ASD) EEG: 3 times speed-up in factorization and$87.35\%$accuracy in ASD discrimination. The latent factors (“biomarkers”) can distinctly interpret the typical EEG characteristics of ASD subjects.

To support more Internet-of-Things devices, we present a novel blockchain-enabled heterogeneous cellular network (HetNet). In this network, devices store block data to the cloud service provider, offload the proof-of-work mining tasks to base stations (BSs), and associate with the macrocell BS or small-cell BSs. Then, we analyze the user association problem, computation offloading problem, and block storage problem in the blockchain-enabled HetNet. We also design corresponding algorithms to solve these problems. Furthermore, to tackle the challenge of data congestion of BSs, based on the obtained computation offloading and block storage strategies, we propose a modified user association algorithm. The analysis shows that the proposed blockchain-enabled HetNet can effectively attain computing offloading, block storage, and user association strategies, and more devices can access the blockchain network. Analytical results show that the proposed modified user association algorithm can greatly avoid data congestion of BSs. Numerical results demonstrate the effectiveness of our proposed algorithms for computation offloading and block storage, and the proposed modified user association algorithm has a significantly great advantage compared with the traditional nearest BS association algorithm in terms of avoiding data congestion.

In this paper, we investigate a novel blockchain-enabled heterogeneous cellular network (HetNet). In this network, mobile users associate with the serving base stations (BSs) and offload their computation-intensive proof-of-work mining tasks to the mobile edge computing server of the macro-cell BS. We initialize the user association strategy by using the traditional nearest BS association algorithm in the blockchain-enabled HetNet. Then, we formulate the computation offloading problem and design an alternating iterative algorithm to attain the computing demand strategies for all users. Based on obtained computing demand strategies, we propose a modified user association algorithm in order to improve the data congestion of BSs. Analytical results show that the blockchain-enabled HetNet can serve more users, and the proposed algorithms can effectively obtain strategies of user association and computation offloading. Numerical results demonstrate that the proposed alternating iterative algorithm for computation offloading has fast convergence and good stability, and the proposed modified user association algorithm can avoid data congestion better than the traditional nearest BS association algorithm.

To enable more Internet-of-Things (IoT) devices for participating in the Proof-of-Work (PoW) mining process of public blockchains, we propose a cooperative mobile-edge computing (MEC)-aided blockchain network. In the network, devices can offload computation-intensive PoW mining tasks to base stations and store their block data to the cloud service provider. Then, we study the joint computation offloading, block storage, and resource service pricing problem as a three-stage Stackelberg game. We analyze the subgame optimization problem in each stage and propose an iterative algorithm based on backward induction to achieve the Nash equilibrium of the Stackelberg game. Furthermore, we derive the upper bound of the ergodic throughput of the cooperative scheme and the maximum number of devices connected to the network. The analysis shows that the proposed cooperative MEC-aided blockchain network can significantly improve the system throughput, and more devices can access the blockchain network. Analytical results show that the proposed backward induction-based iterative algorithm can efficiently attain the Nash equilibrium of the game. Numerical results show that our proposed backward induction-based iterative algorithm has fast convergence and good stability, and the proposed cooperative scheme can serve more devices in comparison with other noncooperative schemes.

The proof-of-work (PoW) mining process requires a large amount of intensive computing, which leads to some plights such as heavy equipment and fixed access nodes in traditional blockchain networks. A novel mobile blockchain network with the help of a mobile edge computing (MEC) server is presented, where all mobile users participate in the PoW mining process. The traditional Bitcoin network adjusts the target difficulty value to ensure a stable block time. However, for MEC-assisted mobile blockchain networks, the adjusted difficulty value needs to be broadcast to all mobile users, which results in expensive communication costs. To maintain a stable block time of mobile blockchain networks, we formulate the delay-limited computation offloading strategy of the PoW-based mining task as a non-cooperative game that maximizes an individual revenue in the MEC-assisted mobile blockchain network. Specifically, the non-cooperative game problem can be divided into multiple sub-game optimization problems to obtain final solutions for all users. We analyze the sub-game optimization problem and prove the existence of Nash equilibrium (NE) of the non-cooperative game. Moreover, we design an alternating iterative algorithm based on the continuous relaxation and greedy rounding (CRGR) to achieve the NE of this game. Given the sub-optimal delay-limited computation offloading results, we also derive the optimal transmit power for an individual user within the maximum mining delay range. From the analytical results, we can see that the proposed CRGR-based alternating iterative algorithm can efficiently attain the sub-optimal delay-limited computation offloading strategies of all mobile users in the polynomial time. The individual transmit power increases accordingly with the delay-limited computation offloading strategies of all users. Numerical results demonstrate that the proposed CRGR-based alternating iterative algorithm has fast convergence and good stability.

Deploying a mobile edge computing (MEC) server in the mobile blockchain-enabled Internet of things (IoT) system is a promising approach to improve the system performance, however, it imposes a significant challenge on the trust of the MEC server. To address this problem, we first propose an untrusted MEC proof of work (PoW) scheme in mobile blockchain networks where plenty of nonce hash computing demands can be offloaded to the MEC server. Then, we design a nonce ordering algorithm for this scheme to provide fairer computing resource allocation for all mobile IoT devices/users. Specifically, we formulate the user’s nonce selection strategy as a non-cooperative game, where utilities of the individual user are maximized in the untrusted MEC-aided mobile blockchain networks. We also prove the existence of Nash equilibrium and analyze that the cooperation behavior is unsuitable for blockchain-enabled IoT devices by using the repeated game. Finally, we design the blockchain’s difficulty adjustment mechanism to ensure stable block times during a long period of time. Compared with the weighted round-robin algorithm, our proposed nonce ordering algorithm can provide fairer computation resources and optimal nonce selection strategies for all mobile users. Network stability is gained through the proposed blockchain’s difficulty adjustment mechanism. The analysis and optimization results provide valuable design insights for practical mobile blockchain IoT systems.