Although deep neural networks have significantly improved object detection accuracy, manually designing efficient architectures is costly, and NAS networks incur high computational overhead, limiting their applicability in resource-constrained or real-time scenarios. This study aims to develop an efficient neural architecture search method capable of rapidly generating low-latency, high-performance detection networks on edge devices. We propose Knowledge-Guided Neural Architecture Search (KGNAS). First, explicit knowledge from a hardware universal deployment framework is used to enrich the search space; second, implicit knowledge characterizes the impact of memory interactions in hierarchical operator blocks on latency; finally, a zero-cost proxy metric evaluates the feature extraction capability of the backbone without training. Experiments show that KGNAS can design efficient networks for various edge devices within one hour, reducing inference latency by 88% compared to DetNAS with only a 3% accuracy loss.

The periodicity of time series has significantly advanced long-term forecasting and has attracted extensive research efforts. However, existing methods still suffer from neglecting critical low-energy periodic components and high sensitivity to outliers. To address these issues, we propose the PeriOdic Spectra Transition via MAmba Network (POSTMAN). This architecture introduces the periodic spectrum deviation forecasting (PSDF) technique, which extracts the shared spectrum to represent the common periodic features and generates deviation spectra to represent the specific periodic features. The shared periodic spectrum retains the critical low-amplitude components, while the deviation spectra preserve the slight differences between periods. To effectively leverage the differences, we develop a spectral convolution-enhanced Frequency Mamba Block (FMB), which learns the transition patterns of periodic deviation spectra and inhibits the impact of outliers during the transition procedure. Experiments on seven mainstream time series datasets demonstrate that POSTMAN outperforms existing state-of-the-art models in accuracy and robustness.

Network slicing has become a primary function of 5G/6G network resource management. However, the existing slicing schemes have not sufficiently discussed the reconfiguration optimization schemes brought by user behavior changes and mobile network environment fluctuations, leading to excessive service interruption rates and slice reconfiguration costs in dynamic environments. To address this problem, this paper proposes an End-to-end Steady-state Adaptive slicing method for Dynamic network state and load (ESAD). To realize the steady-state slicing decisions, ESAD takes the steady-state degree of network slicing and reconfiguration cost as the objective and constructs the slicing reconfiguration probability evaluation function based on the service load dynamics function and the time-varying function of the network channel conditions. To improve the predictability and steady-state degree of the slicing decision, ESAD introduces an ensemble deep learning method to predict the load service fluctuation based on the user behavior model and employs reinforcement learning to compute the channel dynamics boundary, which guides the slicing decision to balance the network dynamics factors. Experiments on quality of service assurance for 5G cloud game rendering class prove that ESAD can reduce reconfiguration probability and long-term reconfiguration cost by 49.45%–58.50% while improving system QoS assurance and capacity.

Automatic multi-modal depression recognition using artificial intelligence technology is crucial to advance early diagnosis and treatment. Existing methods suffer from a weak performance in detecting depression due to incomplete unimodal semantic information and insufficient fusion effects. To address these challenges, we propose a novel Semantic-Enhanced Dual Cross-modal Fusion Network (SE-DCFN) for multi-modal depression recognition, specifically designed for text-audio data. Firstly, we utilize a prompt learning-based text encoder and a language-audio pertaining-based audio encoder to capture specific information to enhance the semantic representation. Then, we introduce a dual cross-modal fusion module based on self-attention and cross-attention mechanisms to effectively explore linguistic and acoustic representation, facilitating inter-modal and intra-modal interaction and fusion. Additionally, a triplet contrastive loss is formulated to optimize the training process of the SE-DCFN. Experimental results on the EATD-Corpus dataset and AVEC-2017 dataset demonstrate the effectiveness and superiority of our proposed SE-DCFN on multi-modal depression recognition, outperforming existing methods.

In recent years, the operation and maintenance of Intelligent Computing Center(ICC) have been moving toward the direction of cloud-native, intelligent, and green. Applications deployed in ICC are increasingly adopting containerization technology and microservice architecture. Although the adoption of microservice architecture is expected to simplify the development, deployment, and maintenance of software, the resource competition of microservices can lead to the degradation of application performance and thus affect the quality of user experience. In addition, dependencies between microservices can introduce the cascading effect. These issues make it challenging for operators to achieve efficient resource management while maintaining the quality of user experience.In this paper, we analyze the impact of dependencies between microservices on application performance. We model the service dependency graph as a weighted graph and propose a hybrid resource allocation method based on Deep Q-network. With the goal of maximizing the application performance while minimizing resources usage, our method evaluates the importance of microservices based on the service dependency graph to set the reward function. Using a reinforcement learning algorithm, our method adjusts the compute and network resources allocated to an application based on dynamically changing available resources. Experimental results show that our method can converge quickly and improve the application performance by approximately 68% while reducing the use of compute and network resources.

Text-based video retrieval is a well-studied task aimed at retrieving relevant videos from a large collection in response to a given text query. Most existing TVR works assume that videos are already trimmed and fully relevant to the query thus ignoring that most videos in real-world scenarios are untrimmed and contain massive irrelevant video content. Moreover, as users' queries are only relevant to video events rather than complete videos, it is also more practical to provide specific video events rather than an untrimmed video list. In this paper, we introduce a challenging but more realistic task called Multi-Granularity Video Content Retrieval (MGVCR), which involves retrieving both video files and specific video content with their temporal locations. This task presents significant challenges since it requires identifying and ranking the partial relevance between long videos and text queries under the lack of temporal alignment supervision between the query and relevant moments. To this end, we propose a novel unified framework, termed, Joint Searching and Grounding (JSG). It consists of two branches: (1) a glance branch that coarsely aligns the query and moment proposals using inter-video contrastive learning, and (2) a gaze branch that finely aligns two modalities using both inter- and intra-video contrastive learning. Based on the glance-to-gaze design, our JSG method learns two separate joint embedding spaces for moments and text queries using a hybrid synergistic contrastive learning strategy. Extensive experiments on three public benchmarks, i.e., Charades-STA, DiDeMo, and ActivityNet-Captions demonstrate the superior performance of our JSG method on both video-level retrieval and event-level retrieval subtasks. Our open-source implementation code is available at https://github.com/CFM-MSG/Code_JSG.

Text-based person retrieval aims at searching for a pedestrian image from multiple candidates with textual descriptions. It is challenging due to uncertain cross-modal alignments caused by the large intra-class variations. To address the challenge, most existing approaches rely on various attention mechanisms and auxiliary information, yet still struggle with the uncertain cross-modal alignments arising from significant intra-class variation, leading to coarse retrieval results. To this end, we propose a novel framework termed Deep Cross-modal Evidential Learning (DCEL), which deploys evidential deep learning to consider the cross-modal alignment uncertainty. Our DCEL model comprises three components: (1) Bidirectional Evidential Learning, which models alignment uncertainty to measure and mitigate the influence of large intra-class variation; (2) Multi-level Semantic Alignment, which leverages a proposed Semantic Filtration module and image-text similarity distribution to facilitate cross-modal alignments; (3) Cross-modal Relation Learning, which reasons about latent correspondences between multi-level tokens of image and text. Finally, we integrate the advantages of the three proposed components to enhance the model to achieve reliable cross-modal alignments. Our DCEL method consistently outperforms more than ten state-of-the-art methods in supervised, weakly supervised, and domain generalization settings on three benchmarks: CUHK-PEDES, ICFG-PEDES, and RSTPReid.

Network applications involve massive heterogeneous data fusion and analysis. Artificial intelligence can significantly improve the convenience and user experience, but it requires a lot of storage, bandwidth, and computing resources. Multiaccess edge computing (MEC) extends intelligence services to IoT devices through offloading approaches and joint processing, which solves the resource bottleneck. However, designing advanced collaboration technology to offload tasks to MEC servers is still challenging. Heuristic algorithms and deep reinforcement learning (DRL)-based approaches have been proposed to offload tasks and minimize application latency. However, heuristic algorithms heavily depend on accurate mathematical models for the MEC system, and DRL does not make fair use of the relationship between devices in the MEC graph. To solve this, we propose a task offloading mechanism based on graph neural network (GNN), which can directly learn on graph data with messages passing and aggregation. We propose a graph reinforcement learning-based offloading (GRLO) framework, which models MEC as an acyclic graph and the offloading policy by graph state migration. GRLO combines GNN with the actor-critic network and trains offloading decision makers without labels. To efficiently train the GRLO, we propose a method that quickly explores action space and approaches the optimal solution. The numerical results show that the GRLO has lower latency compared to baselines while having generalization ability to new environments and topologies. Moreover, we verified the effectiveness of GRLO on a prototype.

Artificial intelligence has been adopted to facilitate monitoring, operation, and decision in the logistics field. Logistics robots with environment perception capability have been used to improve warehousing efficiency in logistics systems. However, autonomous mobile robots face computationally intensive and real-time demanding tasks such as navigation, localization, and obstacle avoidance. In this article, we present EventTube, an edge computing based event-aware system that can efficiently discover events from the video data captured by RGB-Monoculars and collaborate with individual devices to make timely decisions. EventTube deploys a semantic context extraction pipeline on edge servers to aggregate video streams from mobile robots and feed a few keyframes, including the start and end of the specific events to the successive perception pods, accelerating logistics robots’ response speed. The event-related model parameters are trained and updated online on a server. The video data collected at the warehouse site for our mobile robots show that EventTube significantly improves parcel delivery efficiency without affecting regular deliveries.

Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE).However, the existing prompt-tuning methods have not achieved satisfactory performance due to the lack of consideration of entity information.In this paper, we propose a bidirectional iterative prompt-tuning method for EAE, where the EAE task is treated as a clozestyle task to take full advantage of entity information and pre-trained language models (PLMs).Furthermore, our method explores event argument interactions by introducing the argument roles of contextual entities into prompt construction.Since template and verbalizer are two crucial components in a clozestyle prompt, we propose to utilize the role label semantic knowledge to construct a semantic verbalizer and design three kinds of templates for the EAE task.Experiments on the ACE 2005 English dataset with standard and low-resource settings show that the proposed method significantly outperforms the peer stateof-the-art methods.Our code is available at https://github.com/HustMinsLab/BIP.

Space-Air-Ground Integrated Network (SAGIN) as an efficient newly integration network could provide more comprehensive network services to meet the multifarious quality of service requirements in different Intelligent Transportation Systems (ITS). By taking advantage of SAGIN, Space-Air-Ground Integrated Vehicular Crowdsensing (SAGI-VCS) would have great potential and the services regarding ITS could be facilitated. However, centralized SAGI-VCS is usually vulnerable to malicious attacks and the trust issues are one of the main reasons that hinder its further development. Blockchain as a distributed hyperledger shows a vital potential to solve the trust problem of multiple participants who do not trust each other and tackle the security issues in SAGI-VCS. Additionally, selfishness is another factor that prevents vehicles from participating in SAGI-VCS. The vast majority of existing incentives for vehicular crowdsensing only focus on the terrestrial networks which cannot be directly used in SAGI-VCS. Meanwhile, the redundant winner phenomenon and the multi-attributes of participants are less considered by them. Toward this end, we first illustrate a blockchain-enabled service architecture for SAGI-VCS and then construct a unified representation model. Afterwards, a tensor computing based truthful incentive mechanism TensorBC for blockchain-enabled SAGI-VCS is proposed to motivate vehicles to participate in completing tasks, ensure the security of the whole process and maximize the social welfare. TensorBC not only can eliminate the redundant winner phenomenon, but also can guarantee the economic properties such as truthfulness, individual rationality and profitability. Finally, both the rigorous theoretical analysis and extensive experimental results show that TensorBC could achieve a better performance.

Deep learning techniques have shown significant success in cyber-physical-social systems (CPSS). As an instance of deep learning models, generative adversarial nets (GAN) model enables powerful and flexible image augmentation, image generation, and classification, thus can be applied to real-world CPSS settings. GAN model training needs a large collection of cyber-physical-social data originating from various CPSS devices. Numerous prevailing GAN models depend on a tacit assumption that several cyber-physical-social data providers present a reliable source to collect training data, which is seldom the case in real CPSS. The existing GAN models also fail to consider multi-dimensional latent structure. In our work, we put forward a novel blockchain-enabled tensor-based conditional deep convolutional GAN (TCDC-GAN) model for cyber-physical-social systems. The blockchain is employed to develop a decentralized and reliable cyber-physical-social data-sharing platform between numerous cyber-physical-social data providers, such that the training data and the model are documented on a ledger that is distributed. Furthermore, a tensor-based generator and a tensor-based discriminator are well designed by employing the tensor model. The results of extensive simulation experiments show the efficacy of the proposed TCDC-GAN model. Compared with the state-of-the-art models, our model gains superior estimation performance.

With the rapid development of Internet applications, diversified Quality of Service (QoS) has been required in packet routing to meet the demand of various types of applications. This paper presents an Intelligent QoS-aware Routing (IQoR) framework with the assistance of Deep Reinforcement Learning (DRL), which supports multi-class QoS provisioning for packet forwarding. The simulation results show that IQoR outperforms the widely-used benchmark routing algorithms by significantly reducing the average delay and jitter of packets.

The significant growth of the Internet of Things (IoT) takes a key and active role in healthcare, smart homes, smart manufacturing, and wearable gadgets. Due to complexness and difficulty in processing multimedia data, the IoT based scheme, namely Internet of Multimedia Things (IoMT) exists that is specialized for services and applications based on multimedia data. However, IoMT generated data are facing major processing and privacy issues. Therefore, tensor-based deep computation models proved a better platform to process IoMT generated data. A differentially private deep computation method working in the tensor space can attest to its efficacy for IoMT. Nevertheless, the deep computation model comprises a multitude of parameters; thus, it requires large units of memory and expensive computing units with higher performance levels, which hinders its performance for IoMT. Motivated by this, therefore, the paper proposes a deep private tensor train autoencoder (dPTTAE) technique to deal with IoMT generated data. Notably, the compression of weight tensors to manageable tensor train format is achieved through Tensor Train (TT) network. Moreover, TT format parameters are trained through higher-order back-propagation and gradient descent. We applied dPTTAE on three representative datasets. Comprehensive experimental evaluations and theoretical analysis show that dPTTAE enhances training time efficiency, and greatly improve memory utilization efficiency, attesting its potential for IoMT.

Coverage is one of the fundamental issues in wireless sensor networks, yet most of the current studies on coverage are based on the simplest disk coverage model. Based on the theory of field reconstruction, we proposed a novel coverage model called confident information coverage in our previous study. In this paper, based on the confident information coverage model, we study the critical sensor density to achieve complete coverage in randomly deployed sensor networks. We first use the average vacancy to measure the degree of coverage, and compute the average vacancy through the computation of the probability that an arbitrary point is not covered by randomly deployed sensors within its correlation range. We then propose a numerical computation method called discrete approximation algorithm to compute this probability, and prove that this probability is actually the limit of the output of the proposed algorithm. Furthermore, we derive the upper and lower bound for the average vacancy as a function of sensor density, which provides a useful insight for the critical sensor density to achieve complete coverage. The simulation results validate our theoretical analysis.

Nowadays, the fast development of wireless mesh networks have led to a significant growth of energy consumption. Green mesh networks consisting of rechargeable routers supplied by renewable energy sources such as solar power have become a cost-effective alternative solution. In this paper, we study the rechargeable router placement problem and formulate it as an optimization problem to minimize the number of deployed routers while ensuring system Quality of Service (QoS) constraints, including users' traffic demand, routers' energy consumption, network failure rate and traffic fairness among users. To assign users to appropriate routers, we first propose two cell association algorithms, namely, Nearest Cell Association Algorithm (NCA) and Proportional Fairness cell Association Algorithm (PFCA). The former only considers the system level efficiency, which may cause unfairness among different users. The later tries to achieve a balance between the network performance and the user fairness. We then design two heuristic placement algorithms embedded with the proposed cell association methods to find approximate solutions for the rechargeable router placement problem. Simulation results show that compared with the optimal placement achieved by exhaustive search, ours can achieve good performance while with greatly reduced computation complexity. Furthermore, the proposed PFCA algorithm can guarantee user fairness with a increase of placement cost.

In the area of performance analysis of wireless networks, one critical issue is the hidden terminal problem, which is considered as one of the severest reasons for the degradation of network performance. In this paper, we incorporate reactive jamming scheme with distributed coordination function (DCF) in IEEE 802.11 based wireless local area networks (WLANs) to improve network throughput in the presence of hidden terminals. In the proposed protocol, we schedule access point (AP) to broadcast jamming signal reactively to hinder the simultaneous transmission of hidden terminals. Both analytical and numerical results show that our reactive jamming based protocol can constantly improve WLAN throughput for a wide range of conditions, compared with the traditional RTS/CTS.

Many applications in wireless sensor networks have strict coverage accuracy requirements and need to operate as long as possible. In this paper, based on the new confident information coverage model proposed in our previous study (Wang et al., 2012), we design a novel sensor scheduling algorithm to prolong the network lifetime. This algorithm organizes the sensors into a maximal number of set covers, each capable of providing required coverage. The task of reconstructing the physical phenomena will be accomplished only by the sensors from one working set cover, while all the other sensors are in sleep mode. And we rotate the working set cover to prolong the network lifetime. Our simulation results show that the proposed algorithm outperforms two typical peer algorithms in terms of longer network lifetime.

Indoor localization is important to many location based applications and services. Many indoor localization methods have been proposed and they can be roughly categorized into two groups: One is based on the distance estimation between a target point and the Access Points (APs); and the other is based on the Received Signal Strength (RSS) fingerprint map. However, the two approaches all assume that the locations of Access Points (APs) are known beforehand. In this paper, we consider a scenario that the locations of APs are not known, and we use measured RSS (Received Signal Strength) at some location-known reference points and their geographical information to estimate virtual APs' parameters. Then those parameters are used to locate new user by optimization method. Experiments show that the position accuracy of the proposed method approaches that of RADAR with less effort.

A substantial proportion of current Internet videos are poor in quality. To improve the visual experience, many visual quality optimization algorithms, such as denoising, sharpening are usually used. However, the unsuitable denoising will blur the image, the oversharpening will result in overshoot artifacts. To resolve this problem, many methods have been proposed to adaptively adjust the parameters based on the content of the videos. However, these methods are characterized with high computation complexity and are not easy for realtime video applications. In this paper, an effective visual optimization method, both denoising and sharpening, for low quality Internet videos is presented. A technique is used to get the approximate visual shape map from the video sequences. The shape information is exploited to adjust the denoising strength and sharpening masks. Thus a content adaptive visual optimization algorithm is achieved. The experimental results show that the proposed algorithm has good performance and can be used for Internet video applications.

Ad hoc networks, which do not rely on fixed infrastructure such as base stations, can be deployed rapidly and inexpensively in situations with geographical or time constraints. However, the nature of ad hoc networks makes them vulnerable to attacks, especially in routing protocols. In order to establish a secure route composed only by trusted nodes and prevent routes from being tampered by internal malicious nodes, we present a novel secure routing protocol based on token escrow set (SRPTES). SRPTES employs token with limited lifetime to control the trust relationships between neighboring nodes, and provides secure routing and packet forwarding services through valid token. As the core of SRPTES, it creates completely distributed and localized token escrow set (TES) which can maintain robust trust relationships among nodes and greatly reduce the overhead of key management. The simulation results show that SRPTES provides an effective security enhancement and improves the efficiency of routing establishment in insecure environment.

With the broad implementation of Internet, VoIP poses an important role on the Internet and provides a new way to people to contact each other. As VoIP's cheapness and simpleness, many institutes forecast that VoIP emerges as next spam entryway like e-mail service. In this paper, we propose a novel schema, called P2P-AVS (anti-voice-spam), against spam call on the VoIP networks. It bases on an open distributed architecture to store and share end users' personal evaluation about spammer. P2P-AVS system acts as a middleware of VoIP proxy server, and constructs a DHT network over them to make it more robust. Furthermore, we design a proper reputation model to measure user's histoy and combine others' evaluation so that we can detect spam calls. At last, we verify the reputation model through building simulation testbed. Results show that reputation model of P2P-AVS could detect spam calls accurately.