The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion model, requiring retraining for each attribute and hindering real-time applicability, or use classifier-based guidance post-training, which does not account for topology scale and practical constraints. In this paper, we show from a discrete perspective that gradients from a pre-trained graph?level classifier can be incorporated into the discrete reverse diffusion posterior to steer generation toward specified structural properties. Based on this insight, we propose Classifier-guided Conditional Topology Generation with Persistent Homology (CoPHo), which builds a persistent homology filtration over intermediate graphs and interprets features as guidance signals that steer generation toward the desired properties at each denoising step. Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics, and we further validate its transferability on the QM9 molecular dataset. The code is available at https://github.com/Lrbomchz/CoPHo.

Task scheduling is a critical component in edge computing. Many advanced scheduling strategies select the most suitable execution node based on user-reported resource requirements, thereby enhancing user experience. However, the reliance on user-reported resource demands presents a potential vulnerability, as malicious users could exploit this to disrupt edge servers. In this paper, we propose a hypothetical offloading attack scenario in which an attacker submits tasks with falsified resource demands, directing these tasks to specific nodes. A high volume of malicious tasks leads to congestion at the targeted node, causing delays and potential failures for latency-sensitive tasks. Due to the black-box nature of the offloading strategy and the unknown system environment, we model the task parameter manipulation as a multi-dimensional multi-armed bandit (MAB) process with non-stationary rewards. This approach aims to maximize the attack efficiency within limited attack costs. We introduce UCB algorithm for Multidimensional space with Cost constraints and Non-stationary rewards(UCB-MCN), an extended MAB algorithm designed to optimize the attacker's cumulative reward. In a simulated environment, UCB-MCN is tested against various offloading strategies and defense mechanisms. Evaluation results demonstrate the effectiveness of UCB-MCN and highlight new security concerns within edge computing.

With the increasing popularity of golf, more and more amateurs are focusing on this sport. Deep learning based golf swing event detection becomes a meaningful task, yet current research relies on RGB images as the unique input, leading to insufficient accuracy in limited-sample scenarios. In this paper, we propose an improved dual-stream network framework, Frame-Skeleton, for detecting golf swing events. The framework combines RGB images and skeleton sequences, utilizing ST-GCN (Spatial-Temporal Graph Convolutional Network) to process joint features, significantly enhancing recognition accuracy and robustness in scenarios with limited data. Additionally, we construct a golf swing dataset, Frameflow, which contains down-the-line golf swing videos of professional and non-professional golfers, providing a new data source for research. Experimental validation shows that Frame-Skeleton outperforms traditional single-stream methods on the benchmark Golfdb dataset and demonstrates stronger generalization capabilities on the smaller Frameflow dataset.

The widespread deployment of Internet of Things (IoT) devices, coupled with their often limited security capabilities, has significantly increased the network attack surface. Consequently, network asset managers need to continuously monitor and assess vulnerable IoT devices to mitigate potential threats. However, existing passive IoT device identification approaches, which rely on network traffic analysis, are hindered by substantial labeling requirements and computational overhead, severely limiting their practicality in real-world environments. To address these challenges, we propose FS-IoT, a fast few-shot IoT device identification framework. FS-IoT introduces the concept of packet bursts as the fundamental unit of recognition and systematically explores their extraction, representation, classification, and aggregation for IoT device identification. Experimental evaluations on two public datasets demonstrate that FS-IoT achieves superior accuracy (99.94% and 98.15%) while requiring only 2% of the labeled training data needed by state-of-the-art methods. Furthermore, FS-IoT improves recognition speed by an order of magnitude, making it highly suitable for practical, large-scale deployments.

Masked image modeling (MIM), as a self-supervised learning paradigm in computer vision, has gained widespread attention among researchers. MIM operates by training the model to predict masked patches of the image. Given the sparse nature of image semantics, it is imperative to devise a masking strategy that steers the model towards reconstructing high-semantic regions. However, conventional mask strategies often miss these high-semantic regions or lack alignment with the masks and semantics. To solve this, we propose the Global Patch-wise Attention (GPA) framework, a transferable and efficient framework for MIM pre-training. We observe that the attention between patches can be the metric of identifying high-semantic regions, which can guide the model to learn more effective representations. Therefore, we firstly define the global patch-wise attention via vision transformer blocks. Then we design the soft-to-hard mask generation to guide the model gradually focusing on high semantic regions identified by GPA (GPA as a teacher). Finally, we design an extra task to predict GPA (GPA as a feature). Experiments conducted under various settings demonstrate that our proposed GPA framework enables MIM to learn better representations, which benefit the model across a wide range of downstream tasks. Furthermore, our GPA framework can be easily and effectively transferred to various MIM architectures.

In the age of 5G and the advent of 6G technology, meeting various applications' diverse and stringent QoS requirements has gained greater urgency. Most existing works only address this problem by optimizing network resource allocation or routing generation, ignoring their mutual influence. In this paper, we jointly optimize resource allocation and routing generation while comprehensively considering the mutual influence and demonstrating that joint optimization is a bilevel optimization problem. We propose BIJO, consisting of two-level agents, to explore using DRL to address the bilevel optimization problem. The upper agent allocates resources for different types of services and the lower agents choose the forwarding path for each type of service. The two-level agents are optimized interactively and iteratively. Extensive experiments on Mininet confirm that BIJO provides a win-win outcome, where various requirements are met as much as possible and network resources are utilized evenly.

Due to the fast developments of 5G and IoT technologies, Inter-Datacenter (Inter-DC) networks are facing unprecedented pressure to duplicate large volumes of geographically distributed user data in a real-time manner. Meanwhile, with the expansion of Inter-DC networks scale, link/node failures also become increasingly frequent, negatively affecting the data transmission efficiency. Therefore, link failure recovery methods become of utmost importance. Many works investigated fast failure recovery, yet none of them consider the deployment overhead of such recovery schemes. While in this paper, we found that the side-effect of deploying recovery strategies and the future availability of the recovered transmissions are also crucial for fast recovery. So we propose a fast and low-redundancy failure recovery framework, FLAIR, which consists of a fast recovery strategy FRAVaR and a redundancy removal algorithm ROSE. FRAVaR takes full consideration of deployment overhead by minimizing shuffle traffic. On its base, ROSE regularly eliminates the cumulative rerouting redundancy by removing unnecessary routing updates. The experiment results on 4 realistic network topologies show that FLAIR successfully reduces up to 48.2% deployment overhead compared with the state-of-the-art solutions, and thus reduces up to 70.2% recovery speed and improves up to 36% network utilization.

Video popularity prediction, also known as predicting the future popularity of a video, is a task that generally uses various modalities of the video, such as visual, audio, text, and metadata, to make predictions. However, the traditional approach puts all the modalities directly into a model for processing, which introduces noise and redundancy into the model. To address this issue, we propose Cost-effective Modality Selection(CeMS) for video popularity prediction, which can adaptively select cost-effective modalities as input based on the features of the metadata. Specifically, a policy network first obtains the prior information from metadata to analyze the differences in representation ability and computation cost between various modalities. Then, with the policy estimation, an optimal set of cost-effective modalities is determined, and the backbone network corresponding to the selected modalities is activated for feature extraction. Finally, the semantic information of all selected modalities is fed into the decoder to yield the predicted popularity. Experiments demonstrate that our proposed approach yields 63%-69% reduction in computation when compared to the traditional baseline that simply uses all the modalities. Additionally, we achieve consistent improvements in accuracy over the state-of-the-art methods.

Recent adaptive methods for efficient video recognition mostly follow the two-stage paradigm of "preview-then-recognition" and have achieved great success on multiple video benchmarks. However, this two-stage paradigm involves two visits of raw frames from coarse-grained to fine-grained during inference (cannot be parallelized), and the captured spatiotemporal features cannot be reused in the second stage (due to varying granularity), being not friendly to efficiency and computation optimization.To this end, inspired by human cognition, we propose a novel recognition paradigm of "View while Moving" for efficient long-untrimmed video recognition.In contrast to the two-stage paradigm, our paradigm only needs to access the raw frame once.The two phases of coarse-grained sampling and fine-grained recognition are combined into unified spatiotemporal modeling, showing great performance.Moreover, we investigate the properties of semantic units in video and propose a hierarchical mechanism to efficiently capture and reason about the unit-level and video-level temporal semantics in long-untrimmed videos respectively.Extensive experiments on both long-untrimmed and short-trimmed videos demonstrate that our approach outperforms state-of-the-art methods in terms of accuracy as well as efficiency, yielding new efficiency and accuracy trade-offs for video spatiotemporal modeling.

Along with the development of 5G and IoT technologies in recent years, Inter Data Center (Inter-DC) network is facing an explosive growth of geographically distributed user data, which needs to be duplicated among DCs in a real-time manner. Transmission-based applications require high availability that is going beyond 99.99%. However, with the expansion of Inter-DC network scale, link failures are also growing, which seriously affects data transmission efficiency, so fast link failure recovery is then urgently needed. Many previous works have been done to achieve fast failure recovery, but most of them ignore two key points, 1) the cost of deploying recovery strategies, and 2) the side-effect of re-transmission to network availability. These two factors make the existing failure recovery process too slow to be practical in real-time online industrial environments. To achieve realistic fast recovery from Inter-DC network failures, we propose a failure recovery framework FRAVaR, which achieves high network availability with very little deployment overhead. Particularly, FRAVaR reduces the deployment overhead by a novel incremental routing strategy to isolate link failures. In other words, it only needs to shuffle a tiny amount of traffic within a small failure isolation domain. On this base, FRAVaR further adopts a risk assessment theory named Value-at-Risk (VaR) to control flow re-transmission. We implement a prototype of FRAVaR and conduct a series of experiments on 4 real InterDC network topologies (ATT North America, IBM, GlobalCenter, AGIS). Experiment results show that FRAVaR outperforms state-of-the-art solutions on the recovery speed by 70.2%.1

Contouring prostate tumor in magnetic resonance images is a prerequisite for diagnosis. Automatically segmenting blurred lesion regions is challenging and requires fully leveraging multi-parameter MR images. This paper proposes MFSL-Net, an end-to-end network that cascades two novel sub-networks: 1) a modality fusion network that selectively fuses information of two MRI modalities by expanding a dual-stream CNN with spatial and channel attention modules; 2) a shape learning network that integrates shape learning and context learning to recognize the shape and edge information while preserving high-resolution semantic information. We justify MFSL-Net’s design by ablation experiments and compare its performance with the state-of-the-art approaches. Experimental results show a 3.6% improvement in Dice Similarity Coefficient, which confirms the effectiveness of MFSL-Net.

With the tremendous growth of video contents and mobility demands, there is a need to develop more personalized video services. Split-screen services, such as picture in picture become more and more popular. Furthermore, the user's viewing environment affects the user's quality of experience (QoE). Therefore, video transmission of split-screen services face several major challenges, such as to quantify the impact of environmental factors on user's QoE; how to assess the user's QoE of the split-screen services; how to choose the bit-rate of each video stream to maximize user's QoE of the split-screen services. To address these challenges, in the paper, an environment-aware adaptive transmission (EAAT) scheme for split-screen video streaming is first presented. Then, we introduce a mathematical model for characterizing user's QoE to be affected by environmental factors in the proposed EAAT. In the model, the QoE of user's relationship with the viewing environment is proposed. Based on the model, a problem of maximizing user's QoE is formulated, and we develop a heuristic algorithm to solve the optimization problem. In addition, we conduct various trace-bandwidth experiments to rigorously evaluate the proposed EAAT scheme in different network environments, and show that EAAT can enrich the video quality while saving network resources.

Due to the low cost, high bandwidth and compatibility of Ethernet, Ethernet-based fronthaul has been utilized to carry sampled radio frequency (RF) signals from radio equipment (RE) to the radio equipment controller (REC). Meeting the stringent performance requirements regarding jitter for the Common Public Radio Interface (CPRI) over Ethernet is challenging. In this paper, a time division multiplexing (TDM) slot-based scheduling (TSS) algorithm is proposed to minimize the jitter; this algorithm consists of two main modules: slot greedy allocation and low-delay collaboration. Specifically, low-complexity slot greedy allocation aims to solve the NP-hard problem caused by the optimal slot allocation, and the low-delay collaboration among different switches is employed to avoid the large delays caused by a strict slot assignment. In the Ethernet-based fronthaul network, the simulation results demonstrate that, compared with the conventional benchmark algorithm, the TSS algorithm ensures lower jitter, and this significant decrease is achieved without incurring a large delay.

Time-sensitive Networking (TSN) has been extensively utilized to enable the transport of time-sensitive fronthaul flows in Ethernet-bridged networks. However, recently emerged ultra-low delay and jitter requirements of the TSN pose great challenges to Common Public Radio Interface (CPRI) over Ethernet. Considering this, we propose a Deterministic Transmittable Time-Based Asynchronous Scheduler (DTT-BAS) in this paper. The DTT- BAS uses the deterministic transmittable timestamp as the core scheduling mechanism, which numerically compares the timestamps to optimize the flow scheduling in the network. For the fronthaul scenario, simulation results validate that the DTT-BAS achieves a high probability of zero jitter and reduces the influence of clock skews with a delay performance close to IEEE 802.1CM frame preemption algorithm.

It's a great challenge to offer a fine-grained and accurate air quality monitoring service in urban areas limited to the cost of the professional facilities. With the development of the wireless sensor networks (WSNs), it brings new opportunity to achieve this goal at low cost. However, WSNs are quite different on temporal and spatial distribution, some WSNs even have irregular real-time features, which makes it a hard problem to use the data collected from different WSNs to achieve the same goal. In this paper, we propose a framework for air quality estimation based on multi-source heterogeneous data collected from WSNs. We collect five kinds of data from different sources in real world, including the data with irregular real-time features. We divide the data sets into three sub classifiers to make the analysis and get the final results with an extreme learning machine (ELM) based multilayer perceptron model. The results show that our method outperforms other methods, and the precision of classification can be 90.8%.

With the tremendous growth of video contents and mobility demands, there is a need to develop more personalized video services. Split-screen service, e.g., picture in picture, becomes more and more popular. However, the video transmission of split-screen service still faces several major challenges, one of which is how to assess the users' quality of experience (QoE) of the split-screen service. There may be multiple videos for different resolutions displayed on one screen. A consistent way is needed to assess the users' QoE of the split-screen service. The second challenge is how to choose bitrate of each video stream to maximize users' QoE of the split-screen service. Multiple video streams are transmitted to user over resource-constrained wireless networks. Therefore, it is a difficult issue to select an appropriate bitrate for every video streaming. To address these challenges, in this paper, we first present a dynamic adaptive video transmission scheme (DAVTS) based on MPEG Media Transport (MMT) protocol. Then we introduce a novel mathematical model for characterizing users' QoE to be affected by some factors in the proposed DAVTS. In the model, the objective method of QoE assessment of split-screen service is proposed. Based on the model a problem of maximum income in QoE of users is considered. We use a transmission bitrate selection (TBS) algorithm to solve the optimization problem. Simulation results demonstrate that DAVTS can enrich the video quality while reduce video jitters.

This paper studies how to extract and group essential nodes to guarantee loop freedom during the update of the network, while minimizing update time. We propose a model to establish the relationships of loops which may arise during the updating procedure. Given the model, we design a heuristic algorithm, with the recursive optimizing for the relationships, to extract essential nodes for the loop-free update, and shorten the updating time. The performance of our proposal has been examined and we verified that our algorithm would obviously reduce the update time.

Recent studies have shown that the flow table size of hardware SDN switch cannot match the number of concurrent flows. Combined SDN Forwarding Element (CFE), which comprises software switch and hardware switch, becomes an alternative approach for tackling this problem. Because software switch has lower lookup speed than hardware switch, different proportions of traffic allocated to software switches in CFE have different effects on the delay bounds of all flows entering CFE. As delay-guarantee is a nontrivial task for network providers, especially with the increasing number of delay-sensitive applications, a model to analyze the delay bound given a flow allocation in CFE is important. With the one-to-one correspondence between flow allocation and rules placement solution, the analytical model can be used to evaluate and compare rules placement solutions and provide a basis for designing better rules placement solution in CFE. In this paper, we propose an analytical model for CFE based on network calculus, and then validate this model through simulations in NS-3.

The combination of Device-to-Device (D2D) Communication in 5G Cellular Networks and vehicular networks will not only increase the performance of vehicular networks, but also increase the revenues for network operators and services providers. This paper proposes a 5G D2D routing method oriented to vehicular networks, which can increase the connectivity and scalability of vehicular networks while alleviating the traffic load of 5G base stations. Vehicular nodes are clustered according to their communication range, the speed and direction of the movements. Data are transferred among vehicles in the same and neighbor clusters in the D2D mode, only certain data packets are needed to be transferred through the 5G base stations. In this way, the traffic load of 5G based stations can be reduced greatly, whereas the data transmission delay of the vehicular networks can also be guaranteed. Simulation results show that our cluster-based routing mechanism is stable and inexpensive, and is suitable for the vehicular networks.

PM2.5 (particulate matter in the atmosphere with a diameter no more than 2.5 microns) in the air can cause great damage to human beings. It's a great challenge to offer a fine-grained and accurate PM2.5 monitoring service in urban areas as the required facilities are very expensive and huge. Since the PM2.5 has a significant scattering effect on visible light, the large-scale user-contributed image data collected by the mobile crowd sensing bring a new opportunity for understanding the urban PM2.5. After the analysis of image data, we find that several image features are very discriminative in PM2.5 inference. In this paper, we propose a fine-grained PM2.5 estimation method based on the random forest model without any PM2.5 measurement devices. We evaluate our approach with experiments based on five data sources: the meteorological data, the traffic data, the records from the monitoring sites, the POIs and the photos collected. The experimental results show that we have a high evaluation accuracy on PM2.5 estimation (precision: 0.875, recall: 0.872), which outperforms existing methods (Logistic, Naive Bayes, Random Tree, and BP ANN).

By separating the control and forwarding planes, Software-Defined networking (SDN) enables the forwarding paths to be flexibly controlled by the logically centralized controllers using the global network view. To introduce SDN into existing networks, it is necessary to upgrade traditional devices to SDN- enabled ones. However, due to the business, economic and management limitations, it is difficult to realize full SDN deployment. As a result, how to migrate existing devices to SDN-compliant ones becomes the obvious dilemma for every network operator. In this paper, we address this question from the network performance perspective, and study how to leverage the capability of SDN to maximize traffic flow that can be achieved in hybrid SDNs. We formulate the maximum flow problem in networks with partial SDN deployment, and develop a fast Fully Polynomial Time Approximation Scheme (FPTAS) for solving it. Simulation results using real topologies show that hybrid SDNs outperform traditional networks, and we can obtain a near optimal network performance when 50% of SDN nodes are deployed.

Interactive multiview video streaming (IMVS) allows viewers to periodically switch viewpoint. Its user experience can be further enhanced by creating virtual views from neighboring coded views using view synthesis techniques. Dynamic adaptive streaming over HTTP (DASH) is a new standard that can adjust the quality of video streaming according to the network condition. In this paper, we propose an improved DASH-based IMVS scheme over wireless networks. The main contributions are twofold. First, our scheme allows virtual views to be generated at either the cloud-based server or the client, and can adaptively select the optimal approach based on the network condition and the cost of the cloud. Second, scalable video coding is used in our system. Simulations with the NS3 tool demonstrate the advantage of our proposed scheme over the existing approach with client-based view synthesis and single-layer video coding.

Recently, Dynamic Adaptive Streaming over HTTP (DASH) has attracted significant attention. In this paper, we consider DASH-based transmission of scalable videos in wireless broadband access networks (e.g., long-term evolution and WiMAX), and propose three methods to enhance the quality of experience of wireless DASH users. First, we design an improved mapping scheme from scalable video coding layers to DASH layers that can provide the desired bitrates, enhance the video end-to-end throughput, and reduce the HTTP communication overhead. Second, we develop a DASH-friendly scheduling and resource allocation algorithm by integrating the DASH-based media delivery and the radio-level adaptation via a cross-layer approach. It utilizes the characteristics of video content and scalable video coding, and greatly reduces the possibility of video playback interruption by considering the client buffer status. The optimization problem is formulated as a mixed binary integer programming problem, and is solved by a subgradient method. Finally, a DASH proxy-based bitrate stabilization algorithm is proposed to improve the video playback smoothness that can achieve the desired tradeoff between playback quality and stability. Simulations with the Qualnet tool demonstrate that our schemes achieve better performances than other methods in the literature.

Software Defined Networking (SDN) is an emerging networking paradigm that assumes a logically centralized control plane separated from the data plane. Despite all its advantages, separating the control and data planes introduces new challenges regarding resilient communications between the two. That is, disconnections between switches and their controllers could result in substantial packet loss and performance degradation. To achieve resilient control traffic forwarding, this paper investigates the protection of control traffic in SDNs with multiple controllers. We propose a control traffic protection scheme that combines both local rerouting and constrained reverse forwarding protections. This scheme enables switches to locally react to failures and redirect the control traffic to controllers by using standby backup forwarding options. Our goal is then to find a set of primary routes for control traffic, called protection control network, where as much control traffic as possible can benefit from the proposed protection scheme. We formulate the protection control network problem and develop an algorithm to solve it. Simulation results on real topologies show that our approach significantly improves the resilience of control traffic.

Recently dynamic adaptive streaming over HTTP (DASH) has gained significant attentions. In this paper, we study DASH-based transmission of scalable videos in wireless broadband access networks (e.g. LTE, WiMAX), and propose a DASH-friendly scheduling and resource allocation scheme (DFSRA) to enhance the Quality-of-Experience (QoE) of wireless DASH users. By integrating DASH-based media delivery and radio-level adaptation in a cross-layer manner, the scheme can determine the optimal wireless resource allocation. A gradient-based algorithm is proposed to solve the optimization problem, which has the following advantages over traditional algorithms: (1) The characteristics of video content and scalable video coding are utilized. (2) The client buffer status is considered to reduce video playback interruption and buffer overflow. Simulations with the Qualnet tool demonstrate that our scheme achieves better performance than existing methods in the literature.

In some practical scenarios such as tour guiding and children babysitting, one mobile device held by tour guides or parents need to know the distance and direction of another nearby mobile device held by tourist or children. However, to date, most existing pedestrian localization methods rely on a fixed external infrastructure, such as a global positioning system(GPS) or pre-deployed wifi access points to provide Localization service for mobile devices. Such methods are constrained either by limited GPS coverage or by complicated set-up procedures. We observe that, when two devices are moving, the change of their positions leads to the change of distance between them. Given the same movements, different relative locations between devices lead to different distance changes. Besides, the distance between and relative movement of devices can be measured by two phone-embedded sensors respectively. This motivates us to exploit the relative localization method by merely two mobile devices. In this work, we present Phone-Radar, which is an infrastructure-free device-to-device localization system. According to the propagation model of wireless signals, the change of distance between devices are modeled by the change of wireless signal strength between them. The movements of devices are recorded by the inertial sensors using step-counting method. We further study the relationship among the initial relative locations between the two devices, their relative movements and the change of received signal strength measurements. Moreover, we implement the proposed method and measure its performance under real world conditions. The testbed experiments show the efficiency of our proposed method.

Currently the increasing prevalence of multi-homing and traffic engineering leads to an explosive growth of the global routing table. It is well known that hierarchical addressing could improve the routing scalability. Hence, some proposals exploring the routing architecture for future Internet reuse the hierarchical addressing for the locator assignment. However, this may result in some ASes assigned too many prefixes which would consequently make hosts, routers, Internet Service Providers and Domain Name System faced with big challenges. By modeling the Internet AS-level topology using a hierarchical graph, we define the processes of prefix assignment and routing advertisement in different hierarchical addressing deployment ways. Then, we quantify the impact of these deployments on the prefix assignment and the routing scalability based on the real routing data. we find that when the deploying position gets lower, the prefix amount of arbitrary AS is getting smaller, while the size of the global Forwarding Information Base is monotonically increasing. Comparing with the actual Internet's data, suitable deployment ways for hierarchical addressing are obtained. With these deployment ways, the excessive prefix problem is solved and the size of the global Forwarding Information Base could be reduced into 56% or even 32% of the one in current Internet.