Background Cross-modal retrieval has attracted widespread attention in many cross-media similarity search applications,particularly image-text retrieval in the fields of computer vision and natural language processing...Background Cross-modal retrieval has attracted widespread attention in many cross-media similarity search applications,particularly image-text retrieval in the fields of computer vision and natural language processing.Recently,visual and semantic embedding(VSE)learning has shown promising improvements in image text retrieval tasks.Most existing VSE models employ two unrelated encoders to extract features and then use complex methods to contextualize and aggregate these features into holistic embeddings.Despite recent advances,existing approaches still suffer from two limitations:(1)without considering intermediate interactions and adequate alignment between different modalities,these models cannot guarantee the discriminative ability of representations;and(2)existing feature aggregators are susceptible to certain noisy regions,which may lead to unreasonable pooling coefficients and affect the quality of the final aggregated features.Methods To address these challenges,we propose a novel cross-modal retrieval model containing a well-designed alignment module and a novel multimodal fusion encoder that aims to learn the adequate alignment and interaction of aggregated features to effectively bridge the modality gap.Results Experiments on the Microsoft COCO and Flickr30k datasets demonstrated the superiority of our model over state-of-the-art methods.展开更多
Protein tertiary structure is indispensible in revealing the biological functions of proteins. De novo perdition of protein tertiary structure is dependent on protein fold recognition. This study proposes a novel meth...Protein tertiary structure is indispensible in revealing the biological functions of proteins. De novo perdition of protein tertiary structure is dependent on protein fold recognition. This study proposes a novel method for prediction of protein fold types which takes primary sequence as input. The proposed method, PFP-RFSM, employs a random forest classifier and a comprehensive feature representation, including both sequence and predicted structure descriptors. Particularly, we propose a method for generation of features based on sequence motifs and those features are firstly employed in protein fold prediction. PFP-RFSM and ten representative protein fold predictors are validated in a benchmark dataset consisting of 27 fold types. Experiments demonstrate that PFP-RFSM outperforms all existing protein fold predictors and improves the success rates by 2%-14%. The results suggest sequence motifs are effective in classification and analysis of protein sequences.展开更多
The use of time-frequency entropy to quantitatively assess the stability of submerged arc welding process considering the distribution features of arc energy is reported in this paper. Time-frequency entropy is employ...The use of time-frequency entropy to quantitatively assess the stability of submerged arc welding process considering the distribution features of arc energy is reported in this paper. Time-frequency entropy is employed to calculate and analyze the stationary current signals, non-stationary current and voltage signals in the submerged arc welding process. It is obtained that time-frequency entropy of arc signal can be used as arc stability judgment criteria of submerged arc welding. Experimental results are provided to confirm the effectiveness of this approach.展开更多
Network virtualization is a promising approach for resource management that allows customized Virtual Networks (VNs) to be multiplexed on a shared physical infrastructure. A key function that network virtualization ...Network virtualization is a promising approach for resource management that allows customized Virtual Networks (VNs) to be multiplexed on a shared physical infrastructure. A key function that network virtualization can provide is Virtual Network Embedding (VNE), which maps virtual networks requested by users to a shared substrate network maintained by an Internet service provider. Existing research has worked on this, but has primarily focused on maximizing the revenue of the Internet service provider. In this paper, we consider energy-aware virtual network embedding, which aims at minimizing the energy consumption for embedding virtual networks in a substrate network. In our optimization model, we consider energy consumption of both links and nodes. We propose an efficient heuristic to assign virtual nodes to appropriate substrate nodes based on priority, where existing activated nodes have higher priority for hosting newly arrived virtual nodes. In addition, our proposed algorithm can take advantage of activated links for embedding virtual links so as to minimize total energy consumption. The simulation results show that, for all the cases considered, our algorithm can improve upon previous work by an average of 12.6% on acceptance rate, while the consumed energy can be reduced by 12.34% on average.展开更多
To solve the traffic load imbalance issue in cellular networks, which is often in the form of hot-spots caused by the different user mobility levels, one of the good solutions at present is to construct heterogeneous ...To solve the traffic load imbalance issue in cellular networks, which is often in the form of hot-spots caused by the different user mobility levels, one of the good solutions at present is to construct heterogeneous integrated wireless networks that combine cellular networks and wireless local area networks (WLANs) together. In general, the traffic volume is significantly heavier in the hot-spots of cellular networks and a higher data transferring rate can be provided by introducing a WLAN so as to raise the utilization of the channel and achieve a good balance between user satisfaction and the efficiency of the network. In this paper, we provide a comprehensive performance comparison of the systems both before and after the integration, based on an existing mathematical model, focusing on both the qualitative and the quantitative analysis of changes in the performance of the system to validate the efficiency and superiority of the cellular/WLAN integrated systems over cellular-only systems.展开更多
Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip (MPSoC). Tasks of the applications need to be mapped on the MPSoC resources efficiently i...Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip (MPSoC). Tasks of the applications need to be mapped on the MPSoC resources efficiently in order to satisity their performance constraints. Exploring all the possible mappings, i.e., tasks to resources combinations exhaustively may take days or weeks. Additionally, the exploration is performed at design-time, which cannot handle dynamism in applications and resources' status. A runtime mapping technique can cater for the dynamism but cannot guarantee for strict timing deadlines due to large computations involved at run-time. Thus, an approach performing feasible compute intensive exploration at design-time and using the explored results at run-time is required. This paper presents a solution in the same direction. Communicationaware design space exploration (CADSE) techniques have been proposed to explore different mapping options to be selected at run-time subject to desired performance and available MPSoC resources. Experiments show that the proposed techniques for exploration are faster over an exhaustive exploration and provides almost the same quality of results.展开更多
基金Supported by the National Natural Science Foundation of China (62172109,62072118)the National Science Foundation of Guangdong Province (2022A1515010322)+1 种基金the Guangdong Basic and Applied Basic Research Foundation (2021B1515120010)the Huangpu International Sci&Tech Cooperation foundation of Guangzhou (2021GH12)。
文摘Background Cross-modal retrieval has attracted widespread attention in many cross-media similarity search applications,particularly image-text retrieval in the fields of computer vision and natural language processing.Recently,visual and semantic embedding(VSE)learning has shown promising improvements in image text retrieval tasks.Most existing VSE models employ two unrelated encoders to extract features and then use complex methods to contextualize and aggregate these features into holistic embeddings.Despite recent advances,existing approaches still suffer from two limitations:(1)without considering intermediate interactions and adequate alignment between different modalities,these models cannot guarantee the discriminative ability of representations;and(2)existing feature aggregators are susceptible to certain noisy regions,which may lead to unreasonable pooling coefficients and affect the quality of the final aggregated features.Methods To address these challenges,we propose a novel cross-modal retrieval model containing a well-designed alignment module and a novel multimodal fusion encoder that aims to learn the adequate alignment and interaction of aggregated features to effectively bridge the modality gap.Results Experiments on the Microsoft COCO and Flickr30k datasets demonstrated the superiority of our model over state-of-the-art methods.
文摘Protein tertiary structure is indispensible in revealing the biological functions of proteins. De novo perdition of protein tertiary structure is dependent on protein fold recognition. This study proposes a novel method for prediction of protein fold types which takes primary sequence as input. The proposed method, PFP-RFSM, employs a random forest classifier and a comprehensive feature representation, including both sequence and predicted structure descriptors. Particularly, we propose a method for generation of features based on sequence motifs and those features are firstly employed in protein fold prediction. PFP-RFSM and ten representative protein fold predictors are validated in a benchmark dataset consisting of 27 fold types. Experiments demonstrate that PFP-RFSM outperforms all existing protein fold predictors and improves the success rates by 2%-14%. The results suggest sequence motifs are effective in classification and analysis of protein sequences.
文摘The use of time-frequency entropy to quantitatively assess the stability of submerged arc welding process considering the distribution features of arc energy is reported in this paper. Time-frequency entropy is employed to calculate and analyze the stationary current signals, non-stationary current and voltage signals in the submerged arc welding process. It is obtained that time-frequency entropy of arc signal can be used as arc stability judgment criteria of submerged arc welding. Experimental results are provided to confirm the effectiveness of this approach.
基金supported by the Specialized Research Fund for the Doctoral Program of Higher Education of China(No.20131201110002)the Key Laboratory of Computer Architecture Opening Topic Fund Subsidization(No.CARCH201303)
文摘Network virtualization is a promising approach for resource management that allows customized Virtual Networks (VNs) to be multiplexed on a shared physical infrastructure. A key function that network virtualization can provide is Virtual Network Embedding (VNE), which maps virtual networks requested by users to a shared substrate network maintained by an Internet service provider. Existing research has worked on this, but has primarily focused on maximizing the revenue of the Internet service provider. In this paper, we consider energy-aware virtual network embedding, which aims at minimizing the energy consumption for embedding virtual networks in a substrate network. In our optimization model, we consider energy consumption of both links and nodes. We propose an efficient heuristic to assign virtual nodes to appropriate substrate nodes based on priority, where existing activated nodes have higher priority for hosting newly arrived virtual nodes. In addition, our proposed algorithm can take advantage of activated links for embedding virtual links so as to minimize total energy consumption. The simulation results show that, for all the cases considered, our algorithm can improve upon previous work by an average of 12.6% on acceptance rate, while the consumed energy can be reduced by 12.34% on average.
文摘To solve the traffic load imbalance issue in cellular networks, which is often in the form of hot-spots caused by the different user mobility levels, one of the good solutions at present is to construct heterogeneous integrated wireless networks that combine cellular networks and wireless local area networks (WLANs) together. In general, the traffic volume is significantly heavier in the hot-spots of cellular networks and a higher data transferring rate can be provided by introducing a WLAN so as to raise the utilization of the channel and achieve a good balance between user satisfaction and the efficiency of the network. In this paper, we provide a comprehensive performance comparison of the systems both before and after the integration, based on an existing mathematical model, focusing on both the qualitative and the quantitative analysis of changes in the performance of the system to validate the efficiency and superiority of the cellular/WLAN integrated systems over cellular-only systems.
基金The authors would like to thank the reviewers for their feedback and suggestions. We also wish to mention that this work is partly supported by Singapore Ministry of Education Academic Research Fund Tier 1 (R-263-000-655-133) and National Natural Science Foundation of China (NSFC) (Grant No. 61173032).
文摘Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip (MPSoC). Tasks of the applications need to be mapped on the MPSoC resources efficiently in order to satisity their performance constraints. Exploring all the possible mappings, i.e., tasks to resources combinations exhaustively may take days or weeks. Additionally, the exploration is performed at design-time, which cannot handle dynamism in applications and resources' status. A runtime mapping technique can cater for the dynamism but cannot guarantee for strict timing deadlines due to large computations involved at run-time. Thus, an approach performing feasible compute intensive exploration at design-time and using the explored results at run-time is required. This paper presents a solution in the same direction. Communicationaware design space exploration (CADSE) techniques have been proposed to explore different mapping options to be selected at run-time subject to desired performance and available MPSoC resources. Experiments show that the proposed techniques for exploration are faster over an exhaustive exploration and provides almost the same quality of results.