Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is cr...Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.展开更多
Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training per...Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training performance, the ability to effectively exploit the dataset, and the ability to adapt to complex environments when deploying the model. By utilizing the knowledge distillation techniques, the article strives to overcome the above challenges with the inheritance of the advantages of both the teacher model and the student model. More precisely, the ResNet152-PSP-Net model’s characteristics are utilized to train the ResNet18-PSP-Net model. Pyramid pooling blocks are utilized to decode multi-scale feature maps, creating a complete semantic map inference. The student model not only preserves the strong segmentation performance from the teacher model but also improves the inference speed of the prediction results. The proposed method exhibits a clear advantage over conventional convolutional neural network (CNN) models, as evident from the conducted experiments. Furthermore, the proposed model also shows remarkable improvement in processing speed when compared with light-weight models such as MobileNetV2 and EfficientNet based on latency and throughput parameters. The proposed KD-SegNet model obtains an accuracy of 96.3% and a mIoU (mean Intersection over Union) of 77%, outperforming the performance of existing models by more than 15% on the same training dataset. The suggested method has an average training time that is only 0.51 times less than same field models, while still achieving comparable segmentation performance. Hence, the semantic segmentation frames are collected, forming the motion trajectory for the system in the environment. Overall, this architecture shows great promise for the development of knowledge-based systems for MR’s navigation.展开更多
Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a chall...Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.展开更多
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 to...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.展开更多
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. Ex...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.展开更多
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 e...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.展开更多
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, mecha...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.展开更多
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 variation...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.展开更多
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 heterogene...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.展开更多
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 sy...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.展开更多
Because of everyone＇s involvement in social networks, social networks are full of massive multimedia data, and events are got released and disseminated through social networks in the form of multi-modal and multi-att...Because of everyone＇s involvement in social networks, social networks are full of massive multimedia data, and events are got released and disseminated through social networks in the form of multi-modal and multi-attribute heterogeneous data. There have been numerous researches on social network search. Considering the spatio-temporal feature of messages and social relationships among users, we summarized an overall social network search framework from the perspective of semantics based on existing researches. For social network search, the acquisition and representation of spatio-temporal data is the basis, the semantic analysis and modeling of social network cross-media big data is an important component, deep semantic learning of social networks is the key research field, and the indexing and ranking mechanism is the indispensable part. This paper reviews the current studies in these fields, and then main challenges of social network search are given. Finally, we give an outlook to the prospect and further work of social network search.展开更多
Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive...Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.展开更多
Abstract： It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic netw...Abstract： It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic network knowledge representation processing. A new extended Petri net is defined based on qualitative mapping, which strengths the expressive ability of the feature of thinking and the mode of action of brain. A model of semantic network knowledge representation based on new Petri net is given. Semantic network knowledge has a more efficient representation and reasoning mechanism. This model not only can reflect the characteristics of associative memory in semantic network knowledge representation, but also can use Petri net to express the criterion changes and its change law of recognition judgment, especially the cognitive operation of thinking based on extraction and integration of sensory characteristics to well express the thinking transition course from quantitative change to qualitative change of human cognition.展开更多
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...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.展开更多
The growing threat of malware,particularly in the Portable Executable(PE)format,demands more effective methods for detection and classification.Machine learning-based approaches exhibit their potential but often negle...The growing threat of malware,particularly in the Portable Executable(PE)format,demands more effective methods for detection and classification.Machine learning-based approaches exhibit their potential but often neglect semantic segmentation of malware files that can improve classification performance.This research applies deep learning to malware detection,using Convolutional Neural Network(CNN)architectures adapted to work with semantically extracted data to classify malware into malware families.Starting from the Malconv model,this study introduces modifications to adapt it to multi-classification tasks and improve its performance.It proposes a new innovative method that focuses on byte extraction from Portable Executable(PE)malware files based on their semantic location,resulting in higher accuracy in malware classification than traditional methods using full-byte sequences.This novel approach evaluates the importance of each semantic segment to improve classification accuracy.The results revealed that the header segment of PE files provides the most valuable information for malware identification,outperforming the other sections,and achieving an average classification accuracy of 99.54%.The above reaffirms the effectiveness of the semantic segmentation approach and highlights the critical role header data plays in improving malware detection and classification accuracy.展开更多
Image coloring is an inherently uncertain and multimodal problem.By inputting a grayscale image into a coloring network,visually plausible colored photos can be generated.Conventional methods primarily rely on semanti...Image coloring is an inherently uncertain and multimodal problem.By inputting a grayscale image into a coloring network,visually plausible colored photos can be generated.Conventional methods primarily rely on semantic information for image colorization.These methods still suffer from color contamination and semantic confusion.This is largely due to the limited capacity of convolutional neural networks to learn deep semantic information inherent in images effectively.In this paper,we propose a network structure that addresses these limitations by leveraging multi-level semantic information classification and fusion.Additionally,we introduce a global semantic fusion network to combat the issues of color contamination.The proposed coloring encoder accurately extracts object-level semantic information from images.To further enhance visual plausibility,we employ a self-supervised adversarial training method.We train the network structure on various datasets with varying amounts of data and evaluate its performance using the ImageNet validation set and COCO validation set.Experimental results demonstrate that our proposed algorithm can generate more realistic images compared to previous approaches,showcasing its high generalization ability.展开更多
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 se...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.展开更多
In recent years, a few researches focus on the similarity measure of semantic trajectories in road networks, since semantic trajectories in road networks have smaller volumes, higher qualities and can better reflect u...In recent years, a few researches focus on the similarity measure of semantic trajectories in road networks, since semantic trajectories in road networks have smaller volumes, higher qualities and can better reflect user behaviors. However, these works do not further discuss how to efficiently search similar trajectories. Thus, to implement an efficient similarity search, we design an index called SIET based on the structures of road networks. Then, we propose a novel algorithm called SSN-BF to search similar trajectories efficiently by using best-first strategy. At last, we take the experimental evaluations on real dataset and prove the efficiency of our algorithm.展开更多
基金supported by the HFIPS Director’s Foundation(YZJJ202207-TS),the National Natural Science Foundation of China(82371931)the Natural Science Foundation of Anhui Province(2008085MC69)+3 种基金the Natural Science Foundation of Hefei City(2021033)the General Scientific Research Project of Anhui Provincial Health Commission(AHWJ2021b150)the Collaborative Innovation Program of Hefei Science Center,CAS(2021HSC-CIP013)the Anhui Province Key Research and Development Project(202204295107020004).
文摘Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.
基金funded by Hanoi University of Science and Technology(HUST)under project number T2023-PC-008.
文摘Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training performance, the ability to effectively exploit the dataset, and the ability to adapt to complex environments when deploying the model. By utilizing the knowledge distillation techniques, the article strives to overcome the above challenges with the inheritance of the advantages of both the teacher model and the student model. More precisely, the ResNet152-PSP-Net model’s characteristics are utilized to train the ResNet18-PSP-Net model. Pyramid pooling blocks are utilized to decode multi-scale feature maps, creating a complete semantic map inference. The student model not only preserves the strong segmentation performance from the teacher model but also improves the inference speed of the prediction results. The proposed method exhibits a clear advantage over conventional convolutional neural network (CNN) models, as evident from the conducted experiments. Furthermore, the proposed model also shows remarkable improvement in processing speed when compared with light-weight models such as MobileNetV2 and EfficientNet based on latency and throughput parameters. The proposed KD-SegNet model obtains an accuracy of 96.3% and a mIoU (mean Intersection over Union) of 77%, outperforming the performance of existing models by more than 15% on the same training dataset. The suggested method has an average training time that is only 0.51 times less than same field models, while still achieving comparable segmentation performance. Hence, the semantic segmentation frames are collected, forming the motion trajectory for the system in the environment. Overall, this architecture shows great promise for the development of knowledge-based systems for MR’s navigation.
基金supported by the STI2030-Major-Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.
基金The National High Technology Research and Devel-opment Program of China (863Program) (No2003AA1Z2560,2002AA414060)the Key Science and Technology Program of Shaanxi Province (No2006K04-G10)
文摘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.
基金The National Natural Science Foundation of China(No.60275016).
文摘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.
基金supported in part by the National Science Foundation of China under Grant 62101253the Natural Science Foundation of Jiangsu Province under Grant BK20210283+2 种基金the Jiangsu Provincial Inno-vation and Entrepreneurship Doctor Program under Grant JSSCBS20210158the Open Research Foun-dation of National Mobile Communications Research Laboratory under Grant 2022D08the Research Foundation of Nanjing for Returned Chinese Scholars.
文摘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.
基金This Project is supported by National Natural Science Foundation of China(No.59875058).
文摘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.
基金supported in part by the Key Research and Development Program of Guangdong Province(2021B0101200001)the Guangdong Basic and Applied Basic Research Foundation(2020B1515120071)。
文摘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.
文摘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.
基金supported in part by the National Key RD Program of China (2021YFF0602104-2,2020YFB1804604)in part by the 2020 Industrial Internet Innovation and Development Project from Ministry of Industry and Information Technology of Chinain part by the Fundamental Research Fund for the Central Universities (30918012204,30920041112).
文摘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.
文摘Because of everyone＇s involvement in social networks, social networks are full of massive multimedia data, and events are got released and disseminated through social networks in the form of multi-modal and multi-attribute heterogeneous data. There have been numerous researches on social network search. Considering the spatio-temporal feature of messages and social relationships among users, we summarized an overall social network search framework from the perspective of semantics based on existing researches. For social network search, the acquisition and representation of spatio-temporal data is the basis, the semantic analysis and modeling of social network cross-media big data is an important component, deep semantic learning of social networks is the key research field, and the indexing and ranking mechanism is the indispensable part. This paper reviews the current studies in these fields, and then main challenges of social network search are given. Finally, we give an outlook to the prospect and further work of social network search.
文摘Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.
文摘Abstract： It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic network knowledge representation processing. A new extended Petri net is defined based on qualitative mapping, which strengths the expressive ability of the feature of thinking and the mode of action of brain. A model of semantic network knowledge representation based on new Petri net is given. Semantic network knowledge has a more efficient representation and reasoning mechanism. This model not only can reflect the characteristics of associative memory in semantic network knowledge representation, but also can use Petri net to express the criterion changes and its change law of recognition judgment, especially the cognitive operation of thinking based on extraction and integration of sensory characteristics to well express the thinking transition course from quantitative change to qualitative change of human cognition.
基金Supported by the National Natural Science Foundation of China(No.61876144).
文摘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.
文摘The growing threat of malware,particularly in the Portable Executable(PE)format,demands more effective methods for detection and classification.Machine learning-based approaches exhibit their potential but often neglect semantic segmentation of malware files that can improve classification performance.This research applies deep learning to malware detection,using Convolutional Neural Network(CNN)architectures adapted to work with semantically extracted data to classify malware into malware families.Starting from the Malconv model,this study introduces modifications to adapt it to multi-classification tasks and improve its performance.It proposes a new innovative method that focuses on byte extraction from Portable Executable(PE)malware files based on their semantic location,resulting in higher accuracy in malware classification than traditional methods using full-byte sequences.This novel approach evaluates the importance of each semantic segment to improve classification accuracy.The results revealed that the header segment of PE files provides the most valuable information for malware identification,outperforming the other sections,and achieving an average classification accuracy of 99.54%.The above reaffirms the effectiveness of the semantic segmentation approach and highlights the critical role header data plays in improving malware detection and classification accuracy.
基金supported by the Key Technologies R&D Program of Tianjin(Nos.24YFZCSN00030 and 24YFYSHZ00090)。
文摘Image coloring is an inherently uncertain and multimodal problem.By inputting a grayscale image into a coloring network,visually plausible colored photos can be generated.Conventional methods primarily rely on semantic information for image colorization.These methods still suffer from color contamination and semantic confusion.This is largely due to the limited capacity of convolutional neural networks to learn deep semantic information inherent in images effectively.In this paper,we propose a network structure that addresses these limitations by leveraging multi-level semantic information classification and fusion.Additionally,we introduce a global semantic fusion network to combat the issues of color contamination.The proposed coloring encoder accurately extracts object-level semantic information from images.To further enhance visual plausibility,we employ a self-supervised adversarial training method.We train the network structure on various datasets with varying amounts of data and evaluate its performance using the ImageNet validation set and COCO validation set.Experimental results demonstrate that our proposed algorithm can generate more realistic images compared to previous approaches,showcasing its high generalization ability.
基金Supported by the National Natural Science Foundation of China( 60873225, 60773191, 70771043)National High Technology Research and Development Program of China ( 2007AA01Z403)Wuhan Youth Science and Technology Chenguang Program (200950431171)
文摘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.
基金Supported by the National Key Research and Development Program of the Ministry of Science and Technology of China(2016YFB1000700)
文摘In recent years, a few researches focus on the similarity measure of semantic trajectories in road networks, since semantic trajectories in road networks have smaller volumes, higher qualities and can better reflect user behaviors. However, these works do not further discuss how to efficiently search similar trajectories. Thus, to implement an efficient similarity search, we design an index called SIET based on the structures of road networks. Then, we propose a novel algorithm called SSN-BF to search similar trajectories efficiently by using best-first strategy. At last, we take the experimental evaluations on real dataset and prove the efficiency of our algorithm.
