SGT-Net: A Transformer-Based Stratified Graph Convolutional Network for 3D Point Cloud Semantic Segmentation

In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently sparse.Therefore,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud space.Most current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation tasks.In this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range dependency.Specifically,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive field.In addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is effective.We demonstrate the validity and superiority of our method on the S3DIS and ShapeNet datasets.Through ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.

An improved pulse coupled neural networks model for semantic IoT

In recent years,the Internet of Things(IoT)has gradually developed applications such as collecting sensory data and building intelligent services,which has led to an explosion in mobile data traffic.Meanwhile,with the rapid development of artificial intelligence,semantic communication has attracted great attention as a new communication paradigm.However,for IoT devices,however,processing image information efficiently in real time is an essential task for the rapid transmission of semantic information.With the increase of model parameters in deep learning methods,the model inference time in sensor devices continues to increase.In contrast,the Pulse Coupled Neural Network(PCNN)has fewer parameters,making it more suitable for processing real-time scene tasks such as image segmentation,which lays the foundation for real-time,effective,and accurate image transmission.However,the parameters of PCNN are determined by trial and error,which limits its application.To overcome this limitation,an Improved Pulse Coupled Neural Networks(IPCNN)model is proposed in this work.The IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons,and all its parameters are set adaptively,which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of images.Experimental segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation Datasets.The IPCNN method achieves a better segmentation result without training,providing a new solution for the real-time transmission of image semantic information.

TSPN: Term-Based Semantic Peer-to-Peer Networks

In this paper, we propose Term-based Semantic Peerto-Peer Networks （TSPN） to achieve semantic search. For each peer, TSPN builds a full text index of its documents. Through the analysis of resources, TSPN obtains series of terms, and distributes these terms into the network. Thus, TSPN can use query terms to locate appropriate peers to perform semantic search. Moreover, unlike the traditional structured P2P networks, TSPN uses the terms, not the peers, as the logical nodes of DHT. This can withstand the impact of network chum. The experimental results show that TSPN has better performance compared with the existing P2P semantic searching algorithms.

Generative Multi-Modal Mutual Enhancement Video Semantic Communications

Recently,there have been significant advancements in the study of semantic communication in single-modal scenarios.However,the ability to process information in multi-modal environments remains limited.Inspired by the research and applications of natural language processing across different modalities,our goal is to accurately extract frame-level semantic information from videos and ultimately transmit high-quality videos.Specifically,we propose a deep learning-basedMulti-ModalMutual Enhancement Video Semantic Communication system,called M3E-VSC.Built upon a VectorQuantized Generative AdversarialNetwork(VQGAN),our systemaims to leverage mutual enhancement among different modalities by using text as the main carrier of transmission.With it,the semantic information can be extracted fromkey-frame images and audio of the video and performdifferential value to ensure that the extracted text conveys accurate semantic information with fewer bits,thus improving the capacity of the system.Furthermore,a multi-frame semantic detection module is designed to facilitate semantic transitions during video generation.Simulation results demonstrate that our proposed model maintains high robustness in complex noise environments,particularly in low signal-to-noise ratio conditions,significantly improving the accuracy and speed of semantic transmission in video communication by approximately 50 percent.

FusionNN:A Semantic Feature Fusion Model Based on Multimodal for Web Anomaly Detection

With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althoughthis approach can achieve higher detection performance,it requires huge human labor and resources to maintainthe feature library.In contrast,semantic feature engineering can dynamically discover new semantic featuresand optimize feature selection by automatically analyzing the semantic information contained in the data itself,thus reducing dependence on prior knowledge.However,current semantic features still have the problem ofsemantic expression singularity,as they are extracted from a single semantic mode such as word segmentation,character segmentation,or arbitrary semantic feature extraction.This paper extracts features of web requestsfrom dual semantic granularity,and proposes a semantic feature fusion method to solve the above problems.Themethod first preprocesses web requests,and extracts word-level and character-level semantic features of URLs viaconvolutional neural network(CNN),respectively.By constructing three loss functions to reduce losses betweenfeatures,labels and categories.Experiments on the HTTP CSIC 2010,Malicious URLs and HttpParams datasetsverify the proposedmethod.Results show that compared withmachine learning,deep learningmethods and BERTmodel,the proposed method has better detection performance.And it achieved the best detection rate of 99.16%in the dataset HttpParams.

Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation

Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars.It remains a challenge because of large intra-class variations between the support and query images.Existing approaches utilize 4D convolutions to mine semantic correspondence between the support and query images.However,they still suffer from heavy computation,sparse correspondence,and large memory.We propose axial assembled correspondence network(AACNet)to alleviate these issues.The key point of AACNet is the proposed axial assembled 4D kernel,which constructs the basic block for semantic correspondence encoder(SCE).Furthermore,we propose the deblurring equations to provide more robust correspondence for the aforementioned SCE and design a novel fusion module to mix correspondences in a learnable manner.Experiments on PASCAL-5~i reveal that our AACNet achieves a mean intersection-over-union score of 65.9%for 1-shot segmentation and 70.6%for 5-shot segmentation,surpassing the state-of-the-art method by 5.8%and 5.0%respectively.

Semantic Path Attention Network Based on Heterogeneous Graphs for Natural Language to SQL Task

The natural language to SQL(NL2SQL)task is an emerging research area that aims to transform a natural language with a given database into an SQL query.The earlier approaches were to process the input into a heterogeneous graph.However,previous models failed to distinguish the types of multi-hop connections of the heterogeneous graph,which tended to ignore crucial semantic path information.To this end,a two-layer attention network is presented to focus on essential neighbor nodes and mine enlightening semantic paths for feature encoding.The weighted edge is introduced for schema linking to connect the nodes with semantic similarity.In the decoding phase,a rule-based pruning strategy is offered to refine the generated SQL queries.From the experimental results,the approach is shown to learn a good encoding representation and decode the representation to generate results with practical meaning.

DuFNet:Dual Flow Network of Real-Time Semantic Segmentation for Unmanned Driving Application of Internet of Things

The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.

Semantic-aware graph convolution network on multi-hop paths for link prediction

Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack transparency of model prediction principles. In this paper,a new graph convolutional network path semantic-aware graph convolution network(PSGCN) is proposed to achieve modeling the semantic information of multi-hop paths. PSGCN first uses a random walk strategy to obtain all-hop paths in KGs,then captures the semantics of the paths by Word2Sec and long shortterm memory(LSTM) models,and finally converts them into a potential representation for the graph convolution network(GCN) messaging process. PSGCN combines path-based inference methods and graph neural networks to achieve better interpretability and scalability. In addition,to ensure the robustness of the model,the value of the path thresholdKis experimented on the FB15K-237 and WN18RR datasets,and the final results prove the effectiveness of the model.

Searching scheme in P2P system based on semantic overlay network

In consideration of the limitation of super-peer overlay network, the semantic information was introduced into the super-peers＇ organization. A novel P2P （peer-to-peer） searching model, SSP2P, was put forward. The peers in the model were organized in a natural area autonomy system （AAS） based on the smallworld theory. A super-peer was selected in each AAS based on power law; and all the super-peers formed different super-peer semantic networks. Thus, a hierarchical super-peer overlay network was formed. The results show that the model reduces the communication cost and enhances the search efficiency while ensuring the system expansibility. It proves that the introduction of semantic information in the construction of a super-peer overlay is favorable to P2P system capability.

Semantic web-based networked manufacturing knowledge retrieval system

To deal with a lack of semantic interoperability of traditional knowledge retrieval approaches, a semantic-based networked manufacturing （NM） knowledge retrieval architecture is proposed, which offers a series of tools for supporting the sharing of knowledge and promoting NM collaboration. A 5-tuple based semantic information retrieval model is proposed, which includes the interoperation on the semantic layer, and a test process is given for this model. The recall ratio and the precision ratio of manufacturing knowledge retrieval are proved to be greatly improved by evaluation. Thus, a practical and reliable approach based on the semantic web is provided for solving the correlated concrete problems in regional networked manufacturing.

Structures of semantic networks: how do we learn semantic knowledge

Global semantic structures of two large semantic networks, HowNet and WordNet, are analyzed. It is found that they are both complex networks with features of small-world and scale-free, but with special properties. Exponents of power law degree distribution of these two networks are between 1.0 and 2. 0, different from most scale-free networks which have exponents near 3.0. Coefficients of degree correlation are lower than 0, similar to biological networks. The BA （Barabasi-Albert） model and other similar models cannot explain their dynamics. Relations between clustering coefficient and node degree obey scaling law, which suggests that there exist self-similar hierarchical structures in networks. The results suggest that structures of semantic networks are influenced by the ways we learn semantic knowledge such as aggregation and metaphor.

Multi-task Learning of Semantic Segmentation and Height Estimation for Multi-modal Remote Sensing Images

Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively utilize multi-modal remote sensing data to break through the performance bottleneck of single-modal interpretation.In addition,semantic segmentation and height estimation in remote sensing data are two tasks with strong correlation,but existing methods usually study individual tasks separately,which leads to high computational resource overhead.To this end,we propose a Multi-Task learning framework for Multi-Modal remote sensing images(MM_MT).Specifically,we design a Cross-Modal Feature Fusion(CMFF)method,which aggregates complementary information of different modalities to improve the accuracy of semantic segmentation and height estimation.Besides,a dual-stream multi-task learning method is introduced for Joint Semantic Segmentation and Height Estimation(JSSHE),extracting common features in a shared network to save time and resources,and then learning task-specific features in two task branches.Experimental results on the public multi-modal remote sensing image dataset Potsdam show that compared to training two tasks independently,multi-task learning saves 20%of training time and achieves competitive performance with mIoU of 83.02%for semantic segmentation and accuracy of 95.26%for height estimation.

Modeling and Defending Passive Worms over Unstructured Peer-to-Peer Networks

Passive worms can passively propagate through embedding themselves into some sharing files, which can result in significant damage to unstructured P2P networks. To study the passive worm behaviors, this paper firstly analyzes and obtains the average delay for all peers in the whole transmitting process due to the limitation of network throughput, and then proposes a mathematical model for the propagation of passive worms over the unstructured P2P networks. The model mainly takes the effect of the network throughput into account, and applies a new healthy files dissemination-based defense strategy according to the file popularity which follows the Zipf distribution. The simulation results show that the propagation of passive worms is mainly governed by the number of hops, initially infected files and uninfected files. The larger the number of hops, the more rapidly the passive worms propagate. If the number of the initially infected files is increased by the attackers, the propagation speed of passive worms increases obviously. A larger size of the uninfected file results in a better attack performance. However, the number of files generated by passive worms is not an important factor governing the propagation of passive worms. The effectiveness of healthy files dissemination strategy is verified. This model can provide a guideline in the control of unstructured P2P networks as well as passive worm defense.

SEMANTIC NETWORK PRESENTATION OF MECHANICAL MOTION SCHEME AND ITS MECHANISM TYPES SELECTION METHOD

The presentation method of the mechanical motion scheme must support thewhole process of conceptual design. To meet the requirement, a semantic network method is selectedto represent process level, action level, mechanism level and relationships among them. Computeraided motion cycle chart exploration can be realized by the representation and revision of timecoordination of mechanism actions and their effect on the design scheme. The uncertain reasoningtechnology based on semantic network is applied in the mechanism types selection of the needledriving mechanism of industrial sewing mechanism, and the application indicated it is correct,useful and advance.

Edge Semantic Cognitive Intelligence for 6G Networks:Novel Theoretical Models,Enabling Framework,and Typical Applications

Edge intelligence is anticipated to underlay the pathway to connected intelligence for 6G networks,but the organic confluence of edge computing and artificial intelligence still needs to be carefully treated.To this end,this article discusses the concepts of edge intelligence from the semantic cognitive perspective.Two instructive theoretical models for edge semantic cognitive intelligence(ESCI)are first established.Afterwards,the ESCI framework orchestrating deep learning with semantic communication is discussed.Two representative applications are present to shed light on the prospect of ESCI in 6G networks.Some open problems are finally listed to elicit the future research directions of ESCI.

Offloading Mobile Data from Cellular Networks Through Peer-to-Peer WiFi Communication:A Subscribe-and-Send Architecture

Currently cellular networks do not have sufficient capacity to accommodate the exponential growth of mobile data requirements.Data can be delivered between mobile terminals through peer-to-peer WiFi communications(e.g.WiFi direct),but contacts between mobile terminals are frequently disrupted because of the user mobility.In this paper,we propose a Subscribe-and-Send architecture and an opportunistic forwarding protocol for it called HPRO.Under Subscribe-and-Send,a user subscribes contents on the Content Service Provider(CSP) but does not download the subscribed contents.Some users who have these contents deliver them to the subscribers through WiFi opportunistic peer-to-peer communications.Numerical simulations provide a robust evaluation of the forwarding performance and the traffic offloading performance of Subscribe-and-Send and HPRO.

A Hierarchical Trust Model for Peer-to-Peer Networks

Trust has become an increasingly important issue given society’s growing reliance on electronic transactions.Peer-to-peer(P2P)networks are among the main electronic transaction environments affected by trust issues due to the freedom and anonymity of peers(users)and the inherent openness of these networks.A malicious peer can easily join a P2P network and abuse its peers and resources,resulting in a large-scale failure that might shut down the entire network.Therefore,a plethora of researchers have proposed trust management systems to mitigate the impact of the problem.However,due to the problem’s scale and complexity,more research is necessary.The algorithm proposed here,HierarchTrust,attempts to create a more reliable environment in which the selection of a peer provider of a file or other resource is based on several trust values represented in hierarchical form.The values at the top of the hierarchical form are more trusted than those at the lower end of the hierarchy.Trust,in HierarchTrust,is generally calculated based on the standard deviation.Evaluation via simulation showed that HierarchTrust produced a better success rate than the well-established EigenTrust algorithm.

Analytical Comparison of Resource Search Algorithms in Non-DHT Mobile Peer-to-Peer Networks

One of the key challenges in ad-hoc networks is the resource discovery problem.How efciently&quickly the queried resource/object can be resolved in such a highly dynamic self-evolving network is the underlying question?Broadcasting is a basic technique in the Mobile Ad-hoc Networks(MANETs),and it refers to sending a packet from one node to every other node within the transmission range.Flooding is a type of broadcast where the received packet is retransmitted once by every node.The naive ooding technique oods the network with query messages,while the random walk scheme operates by contacting subsets of each node’s neighbors at every step,thereby restricting the search space.Many earlier works have mainly focused on the simulation-based analysis of ooding technique,and its variants,in a wired network scenario.Although,there have been some empirical studies in peer-to-peer(P2P)networks,the analytical results are still lacking,especially in the context of mobile P2P networks.In this article,we mathematically model different widely used existing search techniques,and compare with the proposed improved random walk method,a simple lightweight approach suitable for the non-DHT architecture.We provide analytical expressions to measure the performance of the different ooding-based search techniques,and our proposed technique.We analytically derive 3 relevant key performance measures,i.e.,the avg.number of steps needed to nd a resource,the probability of locating a resource,and the avg.number of messages generated during the entire search process.

Peer-to-Peer Networks 2

The development of network resources changes the network computing models. P2P networks, a new type of network adopting peer-to-peer strategy for computing, have attracted worldwide attention. The P2P architecture is a type of distributed network in which all participants share their hardware resources and the shared resources can be directly accessed by peer nodes without going through any dedicated servers. The participants in a P2P network are both resource providers and resource consumers. This article on P2P networks is divided into two issues. In the previous issue, P2P architecture, network models and core search algorithms were introduced. The second part in this issue is analyzing the current P2P research and application situations, as well as the impacts of P2P on telecom operators and equipment vendors.