System design and optimization problems require large-scale chemical kinetic models. Pure kinetic models of naphtha pyrolysis need to solve a complete set of stiff ODEs and is therefore too computational expensive. On...System design and optimization problems require large-scale chemical kinetic models. Pure kinetic models of naphtha pyrolysis need to solve a complete set of stiff ODEs and is therefore too computational expensive. On the other hand, artificial neural networks that completely neglect the topology of the reaction networks often have poor generalization. In this paper, a framework is proposed for learning local representations from largescale chemical reaction networks. At first, the features of naphtha pyrolysis reactions are extracted by applying complex network characterization methods. The selected features are then used as inputs in convolutional architectures. Different CNN models are established and compared to optimize the neural network structure.After the pre-training and fine-tuning step, the ultimate CNN model reduces the computational cost of the previous kinetic model by over 300 times and predicts the yields of main products with the average error of less than 3%. The obtained results demonstrate the high efficiency of the proposed framework.展开更多
The prediction of essential proteins, the minimal set required for a living cell to support cellular life, is an important task to understand the cellular processes of an organism. Fast progress in high-throughput tec...The prediction of essential proteins, the minimal set required for a living cell to support cellular life, is an important task to understand the cellular processes of an organism. Fast progress in high-throughput technologies and the production of large amounts of data enable the discovery of essential proteins at the system level by analyzing Protein-Protein Interaction （PPI） networks, and replacing biological or chemical experiments. Furthermore, additional gene-level annotation information, such as Gene Ontology （GO） terms, helps to detect essential proteins with higher accuracy. Various centrality algorithms have been used to determine essential proteins in a PPI network, and, recently motif centrality GO, which is based on network motifs and GO terms, works best in detecting essential proteins in a Baker＇s yeast Saccharomyces cerevisiae PPI network, compared to other centrality algorithms. However, each centrality algorithm contributes to the detection of essential proteins with different properties, which makes the integration of them a logical next step. In this paper, we construct a new feature space, named CENT-ING-GO consisting of various centrality measures and GO terms, and provide a computational approach to predict essential proteins with various machine learning techniques. The experimental results show that CENT-ING-GO feature space improves performance over the INT-GO feature space in previous work by Acencio and Lemke in 2009. We also demonstrate that pruning a PPI with informative GO terms can improve the prediction performance further.展开更多
随着第五代通信网络技术(5G)的发展,智慧城市中物联网(Internet of Things,IoT)的应用规模和多样性呈现出爆炸式增长.海量的智能传感设备组网给高动态的物联网通信服务质量带来了巨大的威胁.部分关键设备节点的失效以及网络攻击易引发...随着第五代通信网络技术(5G)的发展,智慧城市中物联网(Internet of Things,IoT)的应用规模和多样性呈现出爆炸式增长.海量的智能传感设备组网给高动态的物联网通信服务质量带来了巨大的威胁.部分关键设备节点的失效以及网络攻击易引发物联网的链锁崩塌效应,影响网络应用的服务质量.因此,如何优化大规模物联网拓扑的鲁棒能力成为当下的研究挑战.目前,针对物联网拓扑结构的优化问题,研究者们提出了启发式算法、智能学习机制和多目标优化策略等创新方法提高物联网拓扑结构的鲁棒能力.但是,这些方法需牺牲巨大的计算资源来获得不成比例的鲁棒性能增益,网络规模越大,该现象越明显.为了解决这个问题并平衡计算开销和提升鲁棒性能,本文提出了一种基于网络模体(Motif)的轻量级物联网拓扑优化策略LITOS.首先利用物联网拓扑结构的社区属性,设计一种基于网络模体的异步社区发现算法,将大规模复杂拓扑结构分解为轻量级局部网络拓扑.然后,基于CPU多核心的计算资源,设计深度强化学习机制,异步优化轻量级物联网局部拓扑结构,从而降低网络整体优化运行时间,提高拓扑结构鲁棒能力.在实验方面,与其他先进的优化算法相比,该策略在运行时间方面降低了1~2个数量级,在鲁棒性提升方面,与最优算法相差大约10%.展开更多
Urban tourism is considered a complex system,and multiscale exploration of the organizational patterns of attraction networks has become a topical issue in urban tourism,so exploring the multiscale characteristics and...Urban tourism is considered a complex system,and multiscale exploration of the organizational patterns of attraction networks has become a topical issue in urban tourism,so exploring the multiscale characteristics and connection mechanisms of attraction networks is important for understanding the linkages between attractions and even the future destination planning.This paper uses geotagging data to compare the links between attractions in Beijing,China during four different periods:the pre-Olympic period(2004–2007),the Olympic Games and subsequent‘heat period’(2008–2013),the post-Olympic period(2014–2019),and the COVID-19(Corona Virus Disease 2019)pandemic period(2020–2021).The aim is to better understand the evolution and patterns of attraction networks at different scales in Beijing and to provide insights for tourism planning in the destination.The results show that the macro,meso-,and microscales network characteristics of attraction networks have inherent logical relationships that can explain the commonalities and differences in the development process of tourism networks.The macroscale attraction network degree Matthew effect is significant in the four different periods and exhibits a morphological monocentric structure,suggesting that new entrants are more likely to be associated with attractions that already have high value.The mesoscale links attractions according to the common purpose of tourists,and the results of the community segmentation of the attraction networks in the four different periods suggest that the functional polycentric structure describes their clustering effect,and the weak links between clusters result from attractions bound by incomplete information and distance,and the functional polycentric structure with a generally more efficient network of clusters.The pattern structure at the microscale reveals the topological transformation relationship of the regional collaboration pattern,and the attraction network structure in the four different periods has a very similar imp展开更多
Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new solutions.It is a challenging task to accurately detect,extract,and represent...Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new solutions.It is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based networks.In previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node classification.However,the content of semantic information is quite complex.Although graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of loss.Therefore,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology network.The Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node classification.We verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.展开更多
基金Supported by the National Natural Science Foundation of China(U1462206)
文摘System design and optimization problems require large-scale chemical kinetic models. Pure kinetic models of naphtha pyrolysis need to solve a complete set of stiff ODEs and is therefore too computational expensive. On the other hand, artificial neural networks that completely neglect the topology of the reaction networks often have poor generalization. In this paper, a framework is proposed for learning local representations from largescale chemical reaction networks. At first, the features of naphtha pyrolysis reactions are extracted by applying complex network characterization methods. The selected features are then used as inputs in convolutional architectures. Different CNN models are established and compared to optimize the neural network structure.After the pre-training and fine-tuning step, the ultimate CNN model reduces the computational cost of the previous kinetic model by over 300 times and predicts the yields of main products with the average error of less than 3%. The obtained results demonstrate the high efficiency of the proposed framework.
文摘The prediction of essential proteins, the minimal set required for a living cell to support cellular life, is an important task to understand the cellular processes of an organism. Fast progress in high-throughput technologies and the production of large amounts of data enable the discovery of essential proteins at the system level by analyzing Protein-Protein Interaction （PPI） networks, and replacing biological or chemical experiments. Furthermore, additional gene-level annotation information, such as Gene Ontology （GO） terms, helps to detect essential proteins with higher accuracy. Various centrality algorithms have been used to determine essential proteins in a PPI network, and, recently motif centrality GO, which is based on network motifs and GO terms, works best in detecting essential proteins in a Baker＇s yeast Saccharomyces cerevisiae PPI network, compared to other centrality algorithms. However, each centrality algorithm contributes to the detection of essential proteins with different properties, which makes the integration of them a logical next step. In this paper, we construct a new feature space, named CENT-ING-GO consisting of various centrality measures and GO terms, and provide a computational approach to predict essential proteins with various machine learning techniques. The experimental results show that CENT-ING-GO feature space improves performance over the INT-GO feature space in previous work by Acencio and Lemke in 2009. We also demonstrate that pruning a PPI with informative GO terms can improve the prediction performance further.
文摘随着第五代通信网络技术(5G)的发展,智慧城市中物联网(Internet of Things,IoT)的应用规模和多样性呈现出爆炸式增长.海量的智能传感设备组网给高动态的物联网通信服务质量带来了巨大的威胁.部分关键设备节点的失效以及网络攻击易引发物联网的链锁崩塌效应,影响网络应用的服务质量.因此,如何优化大规模物联网拓扑的鲁棒能力成为当下的研究挑战.目前,针对物联网拓扑结构的优化问题,研究者们提出了启发式算法、智能学习机制和多目标优化策略等创新方法提高物联网拓扑结构的鲁棒能力.但是,这些方法需牺牲巨大的计算资源来获得不成比例的鲁棒性能增益,网络规模越大,该现象越明显.为了解决这个问题并平衡计算开销和提升鲁棒性能,本文提出了一种基于网络模体(Motif)的轻量级物联网拓扑优化策略LITOS.首先利用物联网拓扑结构的社区属性,设计一种基于网络模体的异步社区发现算法,将大规模复杂拓扑结构分解为轻量级局部网络拓扑.然后,基于CPU多核心的计算资源,设计深度强化学习机制,异步优化轻量级物联网局部拓扑结构,从而降低网络整体优化运行时间,提高拓扑结构鲁棒能力.在实验方面,与其他先进的优化算法相比,该策略在运行时间方面降低了1~2个数量级,在鲁棒性提升方面,与最优算法相差大约10%.
基金Under the auspices of the National Natural Science Foundation of China(No.41971202)the National Natural Science Foundation of China(No.42201181)the Fundamental research funding targets for central universities(No.2412022QD002)。
文摘Urban tourism is considered a complex system,and multiscale exploration of the organizational patterns of attraction networks has become a topical issue in urban tourism,so exploring the multiscale characteristics and connection mechanisms of attraction networks is important for understanding the linkages between attractions and even the future destination planning.This paper uses geotagging data to compare the links between attractions in Beijing,China during four different periods:the pre-Olympic period(2004–2007),the Olympic Games and subsequent‘heat period’(2008–2013),the post-Olympic period(2014–2019),and the COVID-19(Corona Virus Disease 2019)pandemic period(2020–2021).The aim is to better understand the evolution and patterns of attraction networks at different scales in Beijing and to provide insights for tourism planning in the destination.The results show that the macro,meso-,and microscales network characteristics of attraction networks have inherent logical relationships that can explain the commonalities and differences in the development process of tourism networks.The macroscale attraction network degree Matthew effect is significant in the four different periods and exhibits a morphological monocentric structure,suggesting that new entrants are more likely to be associated with attractions that already have high value.The mesoscale links attractions according to the common purpose of tourists,and the results of the community segmentation of the attraction networks in the four different periods suggest that the functional polycentric structure describes their clustering effect,and the weak links between clusters result from attractions bound by incomplete information and distance,and the functional polycentric structure with a generally more efficient network of clusters.The pattern structure at the microscale reveals the topological transformation relationship of the regional collaboration pattern,and the attraction network structure in the four different periods has a very similar imp
基金supported by National Natural Science Foundation of China(62101088,61801076,61971336)Natural Science Foundation of Liaoning Province(2022-MS-157,2023-MS-108)+1 种基金Key Laboratory of Big Data Intelligent Computing Funds for Chongqing University of Posts and Telecommunications(BDIC-2023-A-003)Fundamental Research Funds for the Central Universities(3132022230).
文摘Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new solutions.It is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based networks.In previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node classification.However,the content of semantic information is quite complex.Although graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of loss.Therefore,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology network.The Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node classification.We verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.
