Underground fires pose a significant threat to production safety in coal mines, and existing detection methods suffer from drawbacks such as poor adaptability to complex subterranean environments and excessive model parameters. To address the need for deploying object detection models on resource-constrained devices, this paper proposes a novel and efficient algorithm forUndergroundFireYOLOdetection, named UF-YOLO. The core innovation of this method is threefold: first, the StarNet module is introduced into the backbone to significantly reduce model parameters and computational complexity without sacrificing accuracy; second, the Cross-scale Context Fusion Module (CCFM) is integrated into the neck to enhance the model’s detection capability for fires of various scales, particularly small targets; and finally, Partial Convolution (PConv) is integrated to extract spatial features more efficiently, further reducing redundant computations and memory access. On our self-built Mine Fire Image Dataset (MFID), compared to the baseline model YOLOv11m, UF-YOLO reduces parameters by 77.1%, increases inference speed by 60.6%. Experimental results on the public COCO val 2017 dataset demonstrate that the proposed method outperforms state-of-the-art (SOTA) models such as YOLOv12. The results confirm that UF-YOLO can be efficiently deployed on the edge-side of coal mine IoVT monitoring systems to performe accurate and real-time fire detection. This work provides a new intelligent paradigm for the real-time monitoring of underground fires.

The security of voice control in the Voice Internet of Things (Voice IoT) heavily relies on the fast and accurate authentication of the command issuer. In this work, we focus on the critical application scenario of Voice IoT in underground coal mines, where voice commands typically last 4–10 seconds. Speech in this scenario typically consists of short, imperative utterances and faces challenges from environmental noise and device heterogeneity. The limitations of traditional speaker verification models in temporal modeling restrict their performance in such scenarios. To address this, this paper proposes a three-dimensional attention module (Branch-MFA) designed for Voice IoT. This module employs a dual-parallel branch architecture: the MFA branch is responsible for extracting attention in the frequency and channel dimensions, and its multi-scale nature enables it to effectively focus on speaker-discriminative frequency bands that remain stable under noise and different collection devices, thereby enhancing the model’s environmental robustness; the GLTA branch, through its innovative grouped variable-length attention mechanism, specifically models the temporal structure of these short voice commands, addressing the challenge of sparse temporal information in short utterances. By integrating the dual-branch outputs through a fusion module, we construct the Branch-MFA-TDNN model. Experiments on the Cn-Celeb dataset show that this model significantly outperforms baseline models in short-utterance verification tasks, particularly for the challenging 4–10 second duration relevant to mine communications, providing an identity authentication solution for Voice IoT that combines high security and real-time performance. We have also released the code1for future comparison.

The Internet of Nano Things (IoNT) refers to an interconnected network of nanoscale components engineered to perform tasks such as data processing, storage, and actuation. IoNT has broad applications, including environmental monitoring and pollution source localization. In order to achieve monitoring and localization for multiple releasing sources (RSs), the deployment of nanosensor networks is indispensable. However, constrained by spatial limitations and high costs, sensors can only be sparsely deployed, resulting in severe degradation in localization performance. In this paper, we consider a turbulent diffusion molecular communication scenario and the objective is to enable multi-source localization and obstacle perception with sparse nanosensors. For sparse signal recovery, we first propose a real-symmetric based on Truncated Nuclear Norm Regularization with Alternating Direction Method of Multipliers (RS-TNNR) matrix completion algorithm, which utilizes the spatial symmetry of molecular diffusion to achieve precise data recovery under high missing ratios. Furthermore, for multi-source localization and obstacle perception, we also propose an Adaptive Iterative Grid based on Sparse Bayesian Learning (AIG-SBL) algorithm, which enhances the localization accuracy with SBL, mitigates off-grid errors via the proposed adaptive iterative grid, and simultaneously estimates obstacle position and radii. Simulation results demonstrate the effectiveness of the proposed algorithms for RS-TNNR and AIG-SBL.

This paper addresses the challenges of automatic monitoring and restoration in ancient mural conservation, aiming to enhance the efficiency and quality of heritage preservation. Traditional manual inspection is time-consuming and often misses early damage, while existing digital restoration models struggle with consistent restoration, especially for large-scale damage. To address these issues, we propose an Internet of things (IoT)-based solution combining event-driven edge intelligence and artificial intelligence generated content (AIGC) techniques. A fine-tuned EdgeSAM model, using a Conv-adapter, enables efficient damage segmentation at the edge; an event-driven mechanism reduces resource consumption; and a LoRA-tuned PowerPaint model, aided by Blip2 and Qwen, provides effective restoration of large damaged areas. Cloud-side processing utilizes AIGC techniques to restore damaged mural areas, ensuring high-quality restoration while minimizing communication demands. Experimental results demonstrate that the proposed method achieves accurate damage monitoring on resource-constrained edge devices and generates diverse, contextually appropriate restoration results on cloud servers, providing a deployment-oriented feasibility validation under simulated temporal degradation and real hardware constraints.

Perceiving scene depth and 3D structure is fundamental for environmental comprehension and interaction in Internet of Video Things (IoVT) devices. Self-supervised monocular depth estimation, which leverages photometric consistency across sequential video frames without requiring ground-truth labels from active sensors, has emerged as a compelling paradigm. Nevertheless, this paradigm suffers from inherent limitations in low-texture or occluded regions, where photometric supervision becomes ambiguous or invalid, typically leading to structural degradation and indistinct object boundaries when inferring depth. To mitigate this limitation, we propose a dual-branch local distillation framework that harnesses priors from depth foundation models (DFMs) to alleviate depth ambiguity and improve fine-grained estimation accuracy. Specifically, guided by a frozen DFM, the framework synergistically employs local-context and cross-context supervision to optimize a student network, facilitating robust perception of depth discontinuities and precise boundary modeling. Furthermore, to enhance the spatial representation within a lightweight architecture, we design DE-LiteMono as the student model, which recovers geometric details through a detail enhancement block and fusion modules. Moreover, a spatial distance consistency loss is introduced to explicitly model the relative geometric topology in the image plane, providing robust structural guidance. Extensive experiments on standard benchmarks, including KITTI, Cityscapes, and Make3D, demonstrate that the proposed method outperforms state-of-the-art self-supervised methods, achieving sharper depth boundaries, reduced ambiguity, and superior quantitative performance.

Industrial IoVT (Internet of Video Things) still faces the dual bottleneck of insufficient accuracy and poor real-time performance in circuit board tiny defect detection. To this end, we propose RGM-YOLO (RefConv–GhostNet–CBAM-enhanced YOLOv8 ), which introduces deformable convolution and channel attention via RefConv and GhostNet modules, and experimentally validates it on the BDL-PCB (Bare Die on Laminate–Printed Circuit Board) large-scale dataset. Experimental results show that RGM-YOLO achieves 94.2% in mAP50 and 67.3% in mAP90–95, representing improvements of 2.4% and 11.2% over the baseline model, YOLOv8. The number of parameters and GFLOPs is reduced by 4.2M and 2.5G, respectively, while the FPS increases from 78 to 102. This approach offers a high-precision, low-latency defect detection paradigm for edge IoVT devices targeting small defects and can be generalized to other industrial quality-inspection scenarios.

Recently, edge computing has emerged as a prevailing paradigm in applying deep learning-based object detection models, offering a promising solution for time-sensitive tasks. However, existing edge object detection faces several challenges: 1) These methods struggle to balance detection precision and model lightweightness. 2) Existing generalized edge-deployment designs offer limited adaptability for object detection. 3) Current works lack real-world evaluation and validation. To address these challenges, we propose theEdgeDetectionToolbox(ED-TOOLBOX), which leverages generalizable plug-and-play components to enable edge-site adaptation of object detection models. Specifically, we propose a lightweightReparameterized Dynamic Convolutional Network(Rep-DConvNet) that employs a weighted multi-shape convolutional branch structure to enhance detection performance. Furthermore, ED-TOOLBOX includes aSparse Cross-Attention(SC-A) network that adopts a localized-mapping-assisted self-attention mechanism to facilitate a well-craftedJoint Modulein adaptively transferring features for further performance improvement. Moreover, we propose anEfficient Headfor the classification and location modules to achieve more efficient prediction. Additionally, in practical industrial scenarios, we identify that helmet detection-one of the most representative edge object detection tasks-overlooks band fastening, which introduces potential safety hazards. To address this, we build aHelmet Band Detection Dataset(HBDD) and apply an edge object detection model optimized by the ED-TOOLBOX to tackle this real-world task. Extensive experiments validate the effectiveness of components in ED-TOOLBOX. In visual surveillance simulations, ED-TOOLBOX-assisted edge detection models outperform sixstate-of-the-artmethods, enabling real-time and accurate detection. These results demonstrate that our approach offers a superior solution for edge object detection.

Cross-modal federated learning is constrained by bandwidth and on-device compute. We present Mobiflip: a minimalist strategy that freezes a lightweight backbone and communicates only a channel-wise \(1\times 1\) scaling adapter appended to the image branch. Guided by the Information Bottleneck, we prove that under common distributional and linear-encoder surrogates, per-channel scaling attains the linear optimum; coupled with the directional geometry of (Mobile)CLIP, the adapter is, in first-order approximation, an optimal preconditioner of the cosine-similarity space—preserving discriminative directions while compressing redundancy and suppressing inter-client drift. We adopt MobileCLIP as a mobile-friendly backbone to jointly minimize compute and communication. On CIFAR-10/100 and medical imaging, a single aggregation already yields stable Bacc; each round transmits only about 0.7% of backbone parameters with \(>\!\!92\%\) reduction in communication. Compared with recent federated multimodal/large-model methods, Mobiflip maintains—or even improves—accuracy under ultra-low communication.

Traditional centralized model training assumes that data samples are readily available and can be processed without constraints. In contrast, decentralized machine learning (DML) addresses the limitation by collaborative model training and inference directly on distributed data sources. The transformation from data centralization to decentralization helps comply with data regulations and improves system scalability with reduced reliance on cloud servers. However, a tradeoff between model personalization and generalization exists: the fine-tuning of local training data distribution sacrifices model generalization on the testing data distribution that differs from the training data distribution. To improve the tradeoff, we propose a DML framework that can inherently make model personalization and generalization easier by selecting a model among multiple ones judiciously. We develop a scalable selector for model selection and use blockchain to achieve model consensus. The personalized model selector is then proposed for test-time adaptation. Using computer simulations, we show that our method not only outperforms competitive personalization benchmarks but also generalizes well for new data distributions with various shifts.

The integrity of electronic health record (EHR) is susceptible to compromise by hardware failures, software errors, or human errors. To date, numerous data integrity verification schemes have been proposed, but most face challenges related to third-party auditing and communication overhead. To address this, a novel EHR integrity verification scheme based on a multi-branch authentication tree is presented in this paper. By integrating an edge-based batch processing mechanism with data identity labeling technology, a low-overhead data verification framework is constructed, effectively reducing communication load. A minimal multi-branch tree structure is innovatively designed to enable parallel authentication and batch signing of data blocks. Concurrently, a random security code generation algorithm is introduced to ensure data security. Experimental and analytical results demonstrate that the proposed scheme maintains correctness, efficiency, and security, consistently achieving 100 % precision in detecting corrupted EHR data replicas. This scheme provides an efficient and reliable data integrity guarantee mechanism for EHR within edge computing environments and contributes significantly to building a trustworthy medical service system.

As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional (∊, ϑ)-differential privacy, while prevalent, exhibits limited adaptability for many applications. To mitigate these constraints, we present alpha differential privacy (ADP), an innovative privacy framework grounded in alpha divergence, which provides a more flexible assessment of privacy consumption. This study delineates the theoretical underpinnings of ADP and contrasts its performance with competing privacy frameworks across many scenarios. Empirical assessments demonstrate that ADP offers enhanced privacy guarantees in small to moderate iteration contexts, particularly where severe privacy requirements are necessary. The suggested method markedly improves privacy-preserving methods, providing a flexible solution for contemporary data analysis issues in a data-centric environment.

In Internet of things (IoT) systems enabled by 6G, unmanned aerial vehicles (UAVs), acting as communication nodes, have the advantages of flexible deployment and wide-area coverage. The channel prediction capability of UAVs for ground communication is of great significance for improving the reliability of IoT communication systems. We propose an innovative and interpretable paradigm for channel prediction based on “physical feature extraction + machine learning”. Specificallywe proposes a real-time UAV-to-ground channel prediction method that leverages propagation environment sensing data, aiming to enhance prediction accuracy and generalization by deeply integrating environmental and communication information. Firstly, we construct the first UAV sensing-communication integrated dataset featuring multi-band, multi-dimensional channel parameters, including UAV-to-ground RGB images, depth maps, and channel data. We then extract multimodal features with clear physical significance relevant to wireless propagation, such as relative position, relative altitude, relative volume, and transmitter-receiver distance. Finally, this paper designs a fusion architecture based on convolutional neural network (CNN) and multilayer perceptron (MLP). This architecture takes multimodal feature data as input, utilizes CNN to extract local features of multi-modal features, and models the fusion of multi-modal features through MLP. Experimental results demonstrate that our model consistently outperforms comparative model. Importantly, our feature analysis quantitatively reveals—for the first time—that building volume is the most influential factor in channel behavior, and that prediction accuracy degrades with increasing flight altitude. Furthermore, system-level simulations confirm that channel prediction leads to substantial improvements in network performance. This work presents a robust and interpretable framework for environment-aware channel characterization, laying a foundation for future 6G intelligent communication systems.

With the rapid advancement of technologies such as artificial intelligence and the Internet of Things, video surveillance—being a core component of video IoT systems—has been widely adopted for underground coal mine safety monitoring. However, the dim lighting and heavy coal dust in underground mines result in poor visibility and significant detail loss in monitoring images, posing a major challenge to coal mine safety management. To address these issues, we propose a low-light image enhancement method tailored for underground coal mine environments, based on Zero-DCE. In our method, traditional convolutions are replaced with Ghost modules to reduce computational cost while maintaining feature extraction capability. Additionally, we incorporate global context blocks and a Vision Transformer branch to integrate more global information into the model. Specifically, the global context blocks improve the model’s ability to correct uneven illumination and prevent overexposure. Meanwhile, the Vision Transformer branch captures long-range dependencies and fuses local and global features to enhance brightness while mitigating color distortion. Furthermore, we replace the original quadratic iterative function with a reciprocal illumination mapping function, enabling more stable and perceptually aligned brightness adjustments. Experimental results on the coal mine underground personnel dataset demonstrate that our method outperforms several state-of-the-art low-light enhancement techniques, achieving superior results in both qualitative and quantitative evaluations. These findings indicate that our approach significantly improves the visibility and overall quality of underground coal mine monitoring images.

With the rapid development of Visual Internet of Things (VIoT) and text detection technology, they have been widely combined and applied to many industrial production sites, such as label text detection, achieving impressive results. However, there are still many shortcomings in the text detection technology: 1) the existing VIoT system has very limited detection precision for text with large scale changes, especially for some small-scale text detection; 2) the existing text detection algorithms cannot meet the actual situation, as the labels often contain handwritten texts, and the text to be detected is arbitrary shape; and 3) in the actual detection, there are many creases or defects on the text label. To solve the above problems, this article designs a text detection method based on a multiscale selection fusion feature pyramid and multisemantic spatial network (MSNet) to assist the VIoT system in detecting label text. First, a multiscale selective fusion feature pyramid is designed, which not only uses the texture extraction module to effectively improve the text texture feature and multiscale feature extraction ability, but also uses the cross-scale selective fusion block to selectively fuse the features of different stages to reduce the influence of pollution on detection. In addition, a MSNet is designed to capture the multisemantic spatial information of each feature channel by using the multiscale deep shared 1-D convolution, which effectively integrates global context dependence and multisemantic spatial prior. Experimental results show that the comprehensive index F-measure on the public datasets ICDAR2015, total-text, and CTW1500 is increased by 5.7%, 3.3%, and 3.8%, respectively. Furthermore, the precision, recall, and F-measure on the dataset label-text are 94.6%, 90.7%, and 92.6%, respectively. The label text detection VIoT system we designed has been deployed in the field and achieved excellent performance. The code of our proposed method can be found in:https://github.com/rebornone1/MSNet

The explosive growth of remote-sensing images generated by emerging space–air–ground integrated IoT networks makes centralized detector training infeasible due to limited bandwidth and strict data privacy constraints. While lightweight single-stage object detectors offer efficiency, they suffer significant accuracy degradation for small, dense, and arbitrarily oriented targets. Furthermore, existing federated object detection frameworks typically neglect client heterogeneity. To overcome these limitations, we propose a two-stage personalized federated detection framework. In Stage 1, we independently train a conventional single-stage rotated object detector on each client and aggregate model updates using an adaptive similarity momentum aggregation (ASMA) strategy, effectively pooling knowledge across non-IID client datasets to improve global generalization. In Stage 2, each client is equipped with a private selective depthwise attention convolution (SDAConv) module, leveraging Stage-1 priors to reconstruct fine-grained, client-specific features without additional communication overhead, thus tailoring predictions to local data distributions. Experiments conducted on five non-IID splits derived from DOTA-1.0, along with DIOR and VisDrone datasets, demonstrate improvements of up to +3.5 mAP compared to federated learning baselines under the same communication budget, simultaneously maintaining global robustness and enhancing local detection accuracy.

Clear monitoring images are crucial for the safe operation of coal mine Internet of Video Things (IoVT) systems. However, low illumination and uneven brightness in underground environments significantly degrade image quality, posing challenges for enhancement methods that often rely on difficult-to-obtain paired reference images. Additionally, there is a tradeoff between enhancement performance and computational efficiency on edge devices within IoVT systems.To address these issues, we propose a multimodal image enhancement method tailored for coal mine IoVT, utilizing an ISP operations within a differentiable CNN framework fusion architecture optimized for uneven illumination. This two-stage strategy combines global enhancement with detail optimization, effectively improving image quality, especially in poorly lit areas. A contrastive language-image pretraining (CLIP)-based multimodal iterative optimization allows for unsupervised training of the enhancement algorithm. By integrating traditional image signal processing (ISP) with convolutional neural networks (CNN), our approach reduces computational complexity while maintaining high performance, making it suitable for real-time deployment on edge devices. Experimental results demonstrate that our method effectively mitigates uneven brightness and enhances key image quality metrics, with preservation of original visual information (PSNR) improvements of 2.9%–4.9%, structural similarity (SSIM) by 4.3%–11.4%, and visual information fidelity (VIF) by 4.9%–17.8% compared to seven state-of-the-art algorithms. Simulated coal mine monitoring scenarios validate our method’s ability to balance performance and computational demands, facilitating real-time enhancement and supporting safer mining operations.

Wearable device-based Human Activity Recognition (HAR) has attracted considerable interest with the rapid development of the Internet of things (IoT), and Federated Learning (FL) has been widely adopted in this domain for its ability to collaboratively train models across decentralized devices while preserving privacy. However, its performance is hindered by data heterogeneity arising from variations in the placement of the wearable devices, user behaviors, and physiological characteristics. In this work, we present LDA-FedHAR, a federated HAR framework designed for wearable devices by capturing more common knowledge from aligned client HAR data. It performs Local HAR Data Alignment (LDA) on each client, which is an entirely on-device alignment method that operates independently on local HAR data. By computing the transformation matrix solely from local HAR data and applying it to the data itself, LDA projects heterogeneous client data into a unified space, thereby reducing inter-client discrepancies at the source. To further enhance efficiency and robustness, we propose two IMU-specific variants, LDA(S-IMU) and LDA(C-IMU), which explore intra-and inter-IMU correlations based on practical placements of wearable devices. Experiments are conducted on 4 public HAR datasets: HHAR, Shoaib2014, OPPORTUNITY++, and PAMAP2. The results show that LDA effectively reduces inter-client discrepancies, and LDA-FedHAR along with its variants consistently outperforms state-of-the-art FL methods. Moreover, the improvements achieved by integrating LDA into other FL methods highlight its applicability.

Perceiving scene depth and 3-D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in leveraging large-scale unlabeled datasets to achieve competitive performance, thereby playing an increasingly important role in depth estimation. Despite recent methods providing additional supervisory signals through self-distillation strategies to improve depth estimation, an effective method for generating pseudo-depth labels suitable for addressing occlusion issues among elements far from the camera remains unexplored. To address this limitation, we propose a patch-based self-distillation learning framework to exploit the potential of self-supervised monocular depth estimation in recovering fine-grained scene depth. In the proposed framework, elements far from the camera within the input image are enlarged by enlarging and cropping operations in the patch-based self-distillation branch. Guided by photometric consistency, the model learns the detailed occlusion relationships among elements from the enlarged patches, producing patch depth maps with fine structures. In the main branch, which takes full-scale images as input, patch depth maps serve as pseudo-depth labels through self-distillation loss to provide additional supervisory signals for regions where photometric consistency fails to offer effective supervision. This forces the depth estimation network to recover fine structures of elements far from the camera in full-scale input images. Regarding the architecture of the depth estimation network, we introduce a bin-center prediction. In this prediction, a global aggregator based on self-attention provides additional scene structure queries for adaptive scene depth discretization. Finally, to encourage the model to explore more general cues for depth inference beyond road plane cues, we propose a PatchMix data augmentation method to enhance the model’s generalization ability to unseen scenes. Extensive experiments on the KITTI dataset show that the proposed method significantly improves performance over the baseline, particularly in fine-grained scene depth estimation. Moreover, the model also exhibits good generalization performance when transferred to the Make3D and Cityscapes datasets.

For visual disbalance defects (VDDs) in low-light images, such as brightness unevenness and color imbalance, existing enhancement methods struggle to extract defect features from local regions and apply adaptive enhancement based on varying degrees of these defects. To address these challenges, we propose an unsupervised multi-modal enhancement method based on a high-order adaptive curve, named CLIP-AE. Specifically, we introduce a multi-modal recurrent optimization approach utilizing contrastive language-image pre-training (CLIP). This method iteratively optimizes variable embedded prompts and an Adaptive Enhancement Module (AEM) to establish dependencies between the prompts and detailed style features in the images, guiding the AEM to perform adaptive image enhancement. Additionally, we implement a progressive feature alignment strategy to enhance the model's ability to perceive style features and improve optimization efficiency by using multiple enhanced images with identical content features and incremental style features. In the AEM, the optimized Hyperparameters Generative Network (HGN) generates the optimal hyperparameters, which drive a High-Dimensional Nested Gamma correction (HDN-Gamma) to perform pixel-wise adaptive enhancement for VDDs. HDN-Gamma further maps pixel values using specific enhancement curves to avoid artifacts. Extensive experiments demonstrate that our method effectively improves visual disbalance defects and reduces artifacts. Compared to seven state-of-the-art algorithms, our method shows significant improvements (PSNR: 16.46%, 16.89%, and 15.14%; SSIM: 9.26%, 8.02%, and 9.85%; MUSIQ: 6.37%, 6.54%, and 7.45%) on the LOL, SICE, and MIT-Adobe FiveK datasets. Our approach offers a novel solution for applying multimedia technology in low-light image enhancement tasks.

In the context of the digital age, utilizing cutting-edge technology for the digitization and creative expansion of ancient murals is crucial, aimed at preserving and passing on cultural heritage. Existing image outpainting techniques suffer from a lack of semantic guidance. This article introduces MuralAgent, a multimodal model based on Retrieval-Augmented Generation (RAG) technology. It precisely extracts key information from mural images and integrates it with a constructed ancient texts knowledge base to ensure the cultural and semantic consistency of the expanded images. Moreover, fine-tuning the Stable Diffusion model ensures the fidelity of the generated image styles. Specifically, this study involves constructing an ancient texts knowledge base for accurate matching, designing specific prompts for GPT-4V(ision) to extract key information, and innovatively expanding artworks through Stable Diffusion, providing a novel way for the public to reinterpret ancient murals.

Price Oracle Manipulation Attacks (POMAs) are increasingly occurring in blockchain systems, and result in significant financial loss. Prior work on detecting POMAs only considers single-transaction attacks, in which the entire attack is contained within a single transaction. We systematically study POMAs in blockchain systems (Ethereum). We find that POMAs that span multiple transactions have become much more frequent than single-transaction POMAs. Thus, there is a compelling need for a framework that can detect POMAs spanning multiple transactions. Moreover, there is a need to come up with generic rules for detecting POMAs rather than rely on past attack patterns like prior work has done.We first devise first-principle rules for detecting POMAs based on traditional stock market manipulation attacks. We then propose POMABuster, which leverages these rules to detect POMAs spanning both single and multiple transactions. POMABuster leverages common characteristics of POMA attackers’ behavior to optimize its detection. We evaluate POMABuster on 2.5 years’ worth of transactions from the blockchain, as well as a dataset compiled from the Code4rena audit reports. Our results demonstrate that POMABuster detects nearly 6.5X more POMAs than prior work. Further, POMABuster has a 1% worst-case false positive rate, and zero false negative rate, both of which significantly outperform prior work.

Abstract Existing image enhancement algorithms often fail to effectively address issues of visual disbalance, such as brightness unevenness and color distortion, in low‐light images. To overcome these challenges, we propose a TransISP‐based image enhancement method specifically designed for low‐light images. To mitigate color distortion, we design dual encoders based on decoupled representation learning, which enable complete decoupling of the reflection and illumination components, thereby preventing mutual interference during the image enhancement process. To address brightness unevenness, we introduce CNNformer, a hybrid model combining CNN and Transformer. This model efficiently captures local details and long‐distance dependencies between pixels, contributing to the enhancement of brightness features across various local regions. Additionally, we integrate traditional image signal processing algorithms to achieve efficient color correction and denoising of the reflection component. Furthermore, we employ a generative adversarial network (GAN) as the overarching framework to facilitate unsupervised learning. The experimental results show that, compared with six SOTA image enhancement algorithms, our method obtains significant improvement in evaluation indexes (e.g., on LOL, PSNR: 15.59%, SSIM: 9.77%, VIF: 9.65%), and it can improve visual disbalance defects in low‐light images captured from real‐world coal mine underground scenarios.

With the rapid development of Internet of Things (IoT) and UAV technology, for the whole IoT system of vehicle detection, the middle and high level of information transmission and server processing has made a breakthrough, so at the bottom of the real-time detection of the vehicle by the UAV is the key to the whole system. However, UAV vehicle detection faces the challenges of too many small targets in the image leading to low detection accuracy, limited hardware platform resources requiring control of model size, and real-time detection requiring high inference speed. Aiming at the above problems, we propose a lightweight model PrFu-YOLO based on YOLOv8 improvement, which achieves a good balance between the accuracy, inference speed, and model size. And it realizes real-time vehicle detection embedded in an UAV platform. To solve the problem of low vehicle detection accuracy, we design a new structure PrFuFPN based on adding a small target detection layer to achieve more advanced feature fusion. To address the limited resources of the platform and the problem of real-time vehicle detection, we add GhostConv to the structure and constantly try to adjust the parameters of the network. Finally, extensive experiments were conducted on the VisDrone2019 and CARPK data sets to fully evaluate the model. Compared to YOLOv8s on the VisDrone2019 test set, mAP50 was improved by 10.05%, mA95 by 14.54%, the number of parameters was reduced by 8.13%, and the model size was reduced by 12.5%, while the FPS of 67.13 fully met the needs of real-time detection.

Video surveillance as an important function of internet of video things (IoVT) system has been widely used in coal mine monitoring for coal mine safety with excellent results, however, there are still many shortcomings: 1) Existing coal mine IoVT systems have limited detection accuracy for small-sized objects; 2) Coal mine video surveillance systems generally adopt centralized cloud computing, transmission of massive data causes high latency, which seriously affects the response speed of object detection function; 3) The concept drift caused by the data stream seriously affect the detection effect of the offline algorithm. To address the above issues, we propose a small object detection method based federated intelligence to assist coal mine IoVT for object detection. First, we design a lightweight neural network Rep-ShuffleNet to improve YOLOv8, the state-of-the-art YOLO algorithm, to maintain high detection accuracy while dramatically increasing the inference speed, and with the advantage of lightweight, it can be deployed to embedded devices for low-latency edge computing; Moreover, we design a federated learning-based MLC-FL algorithm for local algorithms’ automatic and efficient optimization by asynchronous communication and data interaction reduction strategy. The experimental results show that with the assistance of federated intelligence model optimization strategies, the lightweight YOLOv8 has excellent detection performance (mAP: 94.6%, APsmall: 86.7%, FPS: 21.6), thus to assist coal mine IoVT to realize accurate and real-time underground small object detection.

The growing utilization of unmanned aerial vehicles (UAVs) across diverse industries has led to increased interest in UAV-assisted data acquisition for the Internet of Things (IoT). The security of image data collected by UAVs during transmission within the IoT has become a critical concern. This article focuses on the security challenges associated with UAV-assisted image data collection in the IoT and presents a dedicated framework designed to enhance the security of this process. Given the high-resolution nature of UAV-captured images, traditional encryption methods face difficulties in directly and effectively encrypting such data. To address this issue, this article introduces an efficient chaotic image encryption algorithm integrated into the proposed protection framework. The algorithm features a novel 1-D chaotic system for generating effective chaotic sequences. For the scrambling phase, a chaotic four-spiral transformation method is employed, and the diffusion process utilizes the Fibonacci matrix. This strategic approach aims to minimize pixel correlation within the image, thereby bolstering the overall security of the encryption process. Experimental validation conducted on authentic UAV image data sets demonstrates the superior, practical, secure, and efficient characteristics of the proposed algorithm.

In the Internet of Things (IoT) employing centralized machine learning, security is a major concern due to the heterogeneity of end devices. Malicious devices could launch poisoning attacks to degrade machine learning models. Distributed machine learning (DML) with blockchain provides a potential solution. Once local weights are recorded on the blockchain, model aggregation with defensive schemes can be executed on smartphones to prevent attacks. However, blockchain with the proof-of-work (PoW) consensus mechanism wastes computing resources and adds latency to DML. Computing resources can be utilized more efficiently with proof-of-useful-work (uPoW), which secures transactions by solving relevant real-world problems. We propose a novel uPoW method to minimize per-round latency of DML. The uPoW mining process schedules DML instances among multi-access edge computing (MEC) servers by solving a multi-way number partitioning problem. Moreover, poisoning attacks on heterogeneous training data pose significant challenges to blockchain-based DML. To address this problem, we propose a novel aggregation protocol, named$\mathit{Corrected Krum}$, to counter such attacks and improve the convergence speed of DML. By leveraging the mean-field approximation method, training errors are corrected to reduce the negative impact of poisoning attacks. Simulation results show that our proposed blockchain approach can significantly speed up DML compared with benchmarks.

Cloud gaming is a novel service provisioning technology that offloads parts of game software from terminals to powerful cloud infrastructures. However, the commercial charging model for cloud gaming is still in its infancy. In this paper, we reveal the deficiencies of existing cloud gaming pricing models and propose CryptoArcade, a token-based cloud gaming system that adopts cryptocurrency as a payment method. Using cryptocurrency, CryptoArcade provides a transparent and resource-aware pricing method, enabling a time irrelevant silent payment on the floating price to protect players' interests, which avoids the Quality of Experience (QoE) degradation caused by traditional dynamic models. While CryptoArcade can solve the problem of pricing strategies, players still face decision headaches caused by having commission overhead and pre-deposit amounts on blockchains. To better understand players' trading behaviors in this decision-making, we consider a marketplace where players trade tokens through smart contracts before gaming sessions. Considering the uncertainty of future token consumption, we use Prospect Theory (PT) in modeling and obtain the optimal solution in closed form. When comparing with the benchmark expect utility theory (EUT), we show that with the same external factors, EUT players are more likely to buy tokens than PT ones.

In Internet of Things (IoT) employing centralized machine learning, security is a major concern due to the heterogeneity of end devices. Decentralized machine learning (DML) with blockchain is a potential solution. However, blockchain with proof-of-work (PoW) consensus mechanism wastes computing resources and adds latency to DML. Computing resources can be utilized more efficiently with proof-of-useful-work (uPoW), which secures transactions by solving real-world problems. We propose a novel uPoW method that exploits PoW mining to accelerate DML through a task scheduling framework for multi-access edge computing (MEC) systems. To provide a good quality-of-service for the system, we minimize the latency by solving a multi-way number partitioning problem in the extended form. A novel uPoW-based mechanism is proposed to schedule DML tasks among MEC servers effectively. Simulation results show that our proposed blockchain strategies accelerate DML significantly compared with benchmarks.

Traditional centralized token exchange (CEX) has been suffering from hacking due to the centralized management of users’ tokens. In contrast, decentralized token exchange (DEX) maintains users’ assets by smart contracts in a decentralized manner, but introduces additional overhead in terms of gas fee and transaction confirmation latency. Hybrid decentralized token exchange (HEX) has been proposed to combine the benefits of CEX and DEX. However, existing HEX is criticized for two issues. First, trading transactions are time-consuming and expensive for frequent token traders. Second, excessive simultaneous transactions might cause the pending transaction congestion in the Ethereum network. In this paper, we propose a payment channel based HEX, which extends existing solutions by adding a new payment channel layer to benefit frequent traders and alleviate the pending transaction congestion. Besides, we propose the very first gas-price vs. transaction-confirmation-latency function to guide Ethereum transaction issuers to choose an optimal gas price that minimizes the overall cost. Extensive simulations are conducted to compare the cost in the proposed HEX with that in the conventional HEX. The results demonstrate the effectiveness of our proposed mechanism in terms of reducing gas fees and transaction confirmation latency for frequent traders as well as the pending transaction congestion in Ethereum.

With the popularization of mobile smart devices (e.g., smartphones, tablets), the number of mobile game players increases significantly. This makes mobile gaming industry rise and take up a large piece of global game market. Different from the traditional players playing games on their personal computers with wired local area network or Wi-Fi access, mobile game players nowadays play online games on their smart devices that communicate to cloud servers via wireless cellular networks. Therefore, the monetary cost for game content downloading and updating via cellular networks may increase the burden of gamers. Meanwhile, an unpredictable latency may be introduced by communication links of wireless cellular networks. This may negatively affect player's gaming experience. In fact, we can predict the next movement of the player in the game and preload the maps that have high probability to go. Meanwhile, if any of these maps have been downloaded and cached by other players nearby, with the Device-to-Device (D2D) communication networks, people may preload these maps freely. In this paper, we focus on the problem that how to select maps to preload from either game server or neighborhood with the consideration of limited storage space on smart devices. We first formulate an optimization problem. Since the formulated problem is NP-hard, we decouple the problem into two subproblems and solve them iteratively to get a suboptimal solution. Simulation results show that our proposed scheme can significantly increase the utility received by mobile players.

Device-to-device (D2D) relay network is regarded as a promising technology to meet the drastically increasing demands on local-based communication services. The relay devices on users with social behaviors will inevitably cause the negative effects on the stability of D2D communications. To improve the stability of the communication over mobile relays, we exploit users' social information in terms of contact duration to characterize the social stabilities of potential relays. Furthermore, with optimal stopping theory, we propose a joint social-physical relay re-selection scheme. This scheme takes into account the mobility of the currently selected relay as well as the social stability and physical conditions of potential relays. This can avoid the interruption of relayed communication and achieve the long-term increase of the relayed data traffic. Our scheme is shown to exhibit the stage-dependent policy structure that is adaptive for different mobility and social stability. This structure indicates that the relay re-selection scheme can achieve the tradeoff between the cost of relay probing and the amount of relayed data traffic. We conduct extensive simulations to demonstrate the superiority of our proposed scheme compared with other baseline schemes. The impact of social stability and mobility on the performance are revealed by our simulation results.

With the flourishing of smart mobile devices (e.g., smartphones, tablets), development of mobile cloud computing has received more and more attentions from both industry and academia. Compared with the traditional way of executing large- scale computational tasks on powerful desktop computers and the cloud, mobile cloud computing is featured by the ubiquitous availability, flexibility, and low-cost. However, this feature also brings challenges when we build the satisfactory mobile computing system. First, the computational power on a mobile device is not comparable with that on a personal computer such that many computation-intensive tasks cannot be independently handled by mobile devices. Second, offloading computational tasks to the cloud introduces additional monetary costs (e.g. wireless communication cost, computational service cost), which may be pricy for users. In this paper, we propose a novel connectivity- aware task scheduling paradigm to enable mobile device users to accomplish computation-intensive tasks cooperatively in the device-to-device (D2D) network by incorporating the "fog" - aggregate of computational powers in the ad-hoc. A supernode at the base station is responsible for scheduling cooperation tasks based on user mobility. To further enhance the quality of experience (QoE) for the users, we propose a lightweight heuristic algorithm to perform task scheduling to ensure low cooperative task execution time. Simulation results show that our cooperative paradigm efficiently reduces the average task execution time for mobile device users in the D2D network.

With the high popularizing rate of smart devices, mobile gaming is an emerging arena in game industry with the purpose of providing ubiquitous game services to mobile players. Different from the traditional player who play games on their personal computers with wired local area network or WiFi access, more and more mobile players nowadays prefer to play online games on their smart devices that communicate to cloud servers via wireless cellular networks. Therefore, in the mobile cloud gaming context, the monetary cost of downloading or updating map files in games via cellular networks is a new issue that may effect players' experience. On the other hand, an unpredictable latency may be introduced by the wireless links in the cellular network. In fact, a mobile player can preload the maps that he has high probability to go. Moreover, mobile players nearby can also form a device-to-device (D2D) communication network to share their cached maps. In this paper, we consider the problem that with the limited storage space available on each player's device, how to select the maps on either neighboring devices or cloud server to preload so that the utility of the player can be maximized. We first formula an optimization problem and then present our solution. Simulation results show that our proposed map sharing and preloading scheme can significantly increase the utility received by mobile players.

Recently, many applications (e.g., wearable cognitive assistance) with the devices of Internet of Things (IoT) (e.g., Apple Watch and Google Glass) have been fast developed. However, the current Internet may not be suitable for the future IoT applications due to the limited capabilities of the data caching and content processing services with the existing Internet architecture. In this paper, we extend the named data networking and develop the object-oriented network (OON) as a novel Internet architecture to implement both the native data caching and content processing in the network layer. The datagrams with processable payloads as well as the cached contents are both referred to as the operable objects in OON for abstraction. With the proposed OON architecture, operable objects can be processed and transmitted by forwarding them to the subroutines of content processing programs and the interfaces of content deliveries, respectively, according to the proposed naming rules. For performance evaluation, we implement the dynamic adaptive multimedia streaming application atop the proposed OON architecture in ns-3. Our simulation results show that the proposed OON architecture can effectively increase the potential quality of experience for mobile users.

Mobile devices in close proximity can be connected in a device-to-device (D2D) manner to transfer digital objects (e.g., videos) to each other. By using D2D data offloading, mobile users can reduce the cost for data service from wireless cellular networks. However, due to users' mobility, the opportunity for a user to obtain his interested objects via D2D communication is transient. In this paper, we first propose an expected available duration (EAD) metric to evaluate the opportunity that an object can be downloaded by a user via D2D data offloading. The EAD metric takes into account the pairwise connectivity of users, social influence between users, diffusion of digital objects, and the time that users would like to wait for D2D data offloading. We then propose a distributed algorithm for a mobile device to determine the EAD of each object. Given a set of available objects in the neighborhood, a mobile device will first download the object that has the smallest EAD. We validate our model via trace-driven simulations. Results show that our proposed algorithm can effectively find the object that should be first downloaded. Comparing with existing schemes, our work can help users download more data via D2D data offloading.

In this paper, we study the robust beamforming design in cloud radio access networks, where remote radio heads (RRHs) are connected to a cloud server that performs signal processing and resource allocation in a centralized manner. Different from traditional approaches adopting a concave increasing function to model the utility of a user, we model the utility by a sigmoidal function of the signal-to-interference-plus-noise ratio (SINR) to capture the diminishing utility returns for very small and very large SINRs in real-time applications (e.g., video streaming). Our objective is to maximize the aggregate utility of the users while considering the imperfection of channel state information (CSI), limited backhaul capacity, and minimum quality of service requirements. Because of the sigmoidal utility function and some of the constraints, the formulated problem is non-convex. To efficiently solve the problem, we introduce a maximum interference constraint, transform the CSI uncertainty constraints into linear matrix inequalities, employ convex relaxation to handle the backhaul capacity constraints, and exploit the sum-of-ratios form of the objective function. This leads to an efficient resource allocation algorithm, which outperforms several baseline schemes, and closely approaches a performance upper bound for large CSI uncertainty or large number of RRHs.

Network slicing enables mobile virtual network operators (MVNOs) to lease network resources from a mobile network operator (MNO). The cloud radio access network (CRAN) architecture reduces the capital and operational expenditures for the MNO and also facilitates MVNOs running virtual machines on the cloud server. In this paper, we propose a beamforming scheme that coordinates multiple remote radio heads (RRHs) in C-RAN to improve the quality of experience (QoE) of users by maximizing their aggregate weighted quality of service (QoS). We model the QoS of each mobile user by a sigmoidal function and formulate the beamforming design as a non-convex optimization problem. By introducing an interference threshold, we first develop an iterative algorithm to determine a suboptimal solution of the original problem. Based on simulation results, we then show that a suitable interference threshold can be obtained in an off-line manner such that the suboptimal solution is a close-to-optimal solution of the original non-convex problem. Simulation results also show that the proposed scheme can significantly improve the aggregate weighted QoS of the mobile users compared to the traditional design where the weighted system sum rate is maximized.

We study the optimal resource allocation in the wireless powered underground sensor network (WPUSN) for throughput maximization. The WPUSN is a new networking paradigm where underground sensors can be replenished by a radio frequency energy harvesting technique and transmit geological data to the nearby aboveground access point in real time. In this paradigm, the underground portion of the wireless communication link suffers from severe path loss. Moreover, different underground sensors may have diverse data traffic demands. In this paper, we formulate an optimization problem to maximize the throughput in WPUSNs with the quality of service (QoS) consideration in terms of communication reliability and diverse data traffic demands. Specifically, we map the QoS requirements to signal-to-noise ratio thresholds and transform our problem into a convex optimization problem with linear constraints. We then present a closed-form solution for the transformed problem through a problem decomposition of the Karush-Kuhn-Tucker conditions. Our closed-form solution uncovers the insights that how the wireless channel states, reliability requirements, and data traffic demands affect the optimal resource allocation in the WPUSN. Finally, we demonstrate the effectiveness of the proposed scheme by running simulations.

Downloading remote files (e.g., pictures, videos) from online social networks via smart user equipments (UEs) (e.g., smartphones, tablets) is becoming popular. Friends who are nearby may want to download the same files shared by their mutual acquaintance. People can obtain these files in a device-to-device (D2D) manner via opportunistic connections to reduce their payment for data service. This is referred to as D2D data offloading. However, D2D communications on unlicensed spectrum using Bluetooth or WiFi-Direct may not maintain high data rate when many D2D pairs nearby need to communicate simultaneously. Since D2D connections are transient, it is important to improve spatial reuse of communication resources and increase the data rate of opportunistic D2D communications. In this paper, we propose a scheme to reuse the downlink licensed spectrum of cellular networks for D2D data offloading. Our proposed scheme includes determining the availability of digital files on neighbouring devices, estimating the channel gains, and performing channel allocation and power control for D2D pairs. Simulation results show that our proposed scheme does not affect the existing cellular UEs and it can also offload more data traffic when compared with WiFi-Direct on an unlicensed spectrum.

The current wireless cellular networks can be used to provide machine-to-machine (M2M) communication services. However, the Long Term Evolution (LTE) networks, which are designed for human users, may not be able to handle a large number of bursty random access requests from machine-type communication (MTC) devices. In this paper, we propose a scheme that uses both access class barring (ACB) and timing advance information to prevent random access overload in M2M systems. We formulate an optimization problem to determine the optimal ACB parameter, which maximizes the expected number of MTC devices successfully served in each random access slot. Hence, the number of random access slots required to serve all MTC devices can be minimized. To reduce the computational complexity and improve the practicability of the proposed scheme, we propose a closed-form approximate solution to the optimization problem and present an algorithm to estimate the number of active MTC devices requiring access in each random access slot. The correctness of the analytical model and the accuracy of the estimation algorithm are validated via simulations. Results show that both numerical and approximate solutions provide the same performance. Our proposed scheme can reduce nearly half of the random access slots required to serve all MTC devices compared to the existing schemes, which use timing advance information only, ACB only, or cooperative ACB.

Millimeter wave (mm-wave) communication has been considered as a promising technology for providing short range, high speed data service in wireless networks. In this paper, we apply the mm-wave technology for multimedia content distribution among different wireless devices in smart home networks. We study the resource allocation problem and propose a new multi-channel medium access control (MAC) protocol considering mm-wave channelization and various types of multimedia services. We define a set of utility functions for battery-constrained devices considering different types of services in smart home networks. We formulate a joint power and channel allocation problem to maximize the aggregate network utility, which is a non-convex mixed integer programming problem. We transform the problem into a series of convex mixed integer programming problems and develop an efficient algorithm to find the solution. Simulation results show that the proposed MAC protocol has superior performance compared to the existing single-carrier MAC protocol in IEEE 802.15.3c standard.

The existing wireless cellular networks can provide machine-to-machine (M2M) service to machine-type communication (MTC) devices deployed in large coverage areas. However, the current Long Term Evolution (LTE) cellular networks designed for human users may not be able to handle a large number of bursty random access requests from MTC devices. In this paper, we propose to jointly use access class barring (ACB) and timing advance (TA) command to reduce the random access overload. In our proposed scheme, the expected number of MTC devices served in one random access slot is determined by the coverage of the base station, total number of devices to be served, the number of preambles, and ACB parameter. By choosing the optimal ACB parameter, we can maximize the number of MTC devices being served in each random access slot. The total number of random access slots required by an LTE base station to serve all MTC devices can be minimized. Simulation results show that in typical LTE cellular networks, our proposed scheme can reduce at least a half of the total slots required by the base station to serve all MTC devices.

Opportunistic data forwarding draws more and more attention in the research community of wireless network after the initial work ExOR was published. However, as far as we know, all existing opportunistic data forwarding only use the nodes which are included in the forwarder list in the entire forwarding progress. In fact, even if a node is not a listed forwarder in the forwarder list, but it is on the direction from source node to destination node, and when it successfully overhears some packets by opportunity, the node actually can be utilized in the opportunistic data forwarding progress. In this paper, we propose the local cooperative relay for opportunistic data forwarding in mobile ad-hoc networks. In general, three contributions we have in this paper, 1) we open more node to participate in the opportunistic data forwarding even though the nodes are not included in the forwarder list, 2) we propose the procedure to select the best local relay node, namely the helper-node, from many candidates but require no inner communication between them, 3) the helper-node is selected just when it is needed, and the such real time selection can tolerate and bridge vulnerable links in mobile networks.

The link quality variation of wireless channels has been a challenging issue in data communications until recent explicit exploration in utilizing this characteristic. The same broadcast transmission may be perceived significantly differently, and usually independently, by receivers at different geographic locations. Furthermore, even the same stationary receiver may experience drastic link quality fluctuation over time. The combination of link-quality variation with the broadcasting nature of wireless channels has revealed a direction in the research of wireless networking, namely, cooperative communication. Research on cooperative communication started to attract interests in the community at the physical layer but more recently its importance and usability have also been realized at upper layers of the network protocol stack. In this article, we tackle the problem of opportunistic data transfer in mobile ad hoc networks. Our solution is called Cooperative Opportunistic Routing in Mobile Ad hoc Networks (CORMAN). It is a pure network layer scheme that can be built atop off-the-shelf wireless networking equipment. Nodes in the network use a lightweight proactive source routing protocol to determine a list of intermediate nodes that the data packets should follow en route to the destination. Here, when a data packet is broadcast by an upstream node and has happened to be received by a downstream node further along the route, it continues its way from there and thus will arrive at the destination node sooner. This is achieved through cooperative data communication at the link and network layers. This work is a powerful extension to the pioneering work of ExOR. We test CORMAN and compare it to AODV, and observe significant performance improvement in varying mobile settings.

Innovative routing in mobile ad hoc networks is crucial for unleashing the full potential of such networks. In this paper, we propose a new Proactive Source Routing (PSR) protocol that has a very small communication overhead but provides nodes with more network structure information than distance-vector based protocols. The value of the source routing protocol includes: 1) better control of path selection by the source nodes for congestion avoidance, load and energy consumption balancing, and bypassing untrusted areas, 2) alleviation of IP forwarding at intermediate nodes, and 3) support for opportunistic data forwarding. PSR complements DSR as a proactive counterpart to provide responsive data transportation services in heavily loaded networks. Our simulation results show that PSR achieves performance similar to OLSR and DSDV, but with only a small fraction of the communication overhead.