In this paper, an optimal multi user detector in DS/CDMA communication systems based on the mean field annealing (MFA) neural network is proposed. It is shown that the NP complete problem of minimizing the objective...In this paper, an optimal multi user detector in DS/CDMA communication systems based on the mean field annealing (MFA) neural network is proposed. It is shown that the NP complete problem of minimizing the objective function of the optimal multi user detector can be translated into minimizing an MFA network energy function. Numerical results show that the proposed detector offers significant performance gain relative to the conventional detector and decorrelating detector while it can be implemented easily in analog hardware.展开更多
A new recommendation method was presented based on memetic algorithm-based clustering. The proposed method was tested on four highly sparse real-world datasets. Its recommendation performance is evaluated and compared...A new recommendation method was presented based on memetic algorithm-based clustering. The proposed method was tested on four highly sparse real-world datasets. Its recommendation performance is evaluated and compared with that of the frequency-based, user-based, item-based, k-means clustering-based, and genetic algorithm-based methods in terms of precision, recall, and F1 score. The results show that the proposed method yields better performance under the new user cold-start problem when each of new active users selects only one or two items into the basket. The average F1 scores on all four datasets are improved by 225.0%, 61.6%, 54.6%, 49.3%, 28.8%, and 6.3% over the frequency-based, user-based, item-based, k-means clustering-based, and two genetic algorithm-based methods, respectively.展开更多
Advanced traveler information systems （ATIS） can not only improve drivers＇ accessibility to the more accurate route travel time information, but also can improve drivers＇ adaptability to the stochastic network cap...Advanced traveler information systems （ATIS） can not only improve drivers＇ accessibility to the more accurate route travel time information, but also can improve drivers＇ adaptability to the stochastic network capacity degradations. In this paper, a mixed stochastic user equilibrium model was proposed to describe the interactive route choice behaviors between ATIS equipped and unequipped drivers on a degradable transport network. In the proposed model the information accessibility of equipped drivers was reflected by lower degree of uncertainty in their stochastic equilibrium flow distributions, and their behavioral adaptability was captured by multiple equilibrium behaviors over the stochastic network state set. The mixed equilibrium model was formulated as a fixed point problem defined in the mixed route flows, and its solution was achieved by executing an iterative algorithm. Numerical experiments were provided to verify the properties of the mixed network equilibrium model and the efficiency of the iterative algorithm.展开更多
Research in spreadsheet management proved that the overuse of slow thinking, rather than fast thinking, is the primary source of erroneous end-user computing. However, we found that the reality is not that simple. To ...Research in spreadsheet management proved that the overuse of slow thinking, rather than fast thinking, is the primary source of erroneous end-user computing. However, we found that the reality is not that simple. To view end-user computing in its full complexity, we launched a project to investigate end-user education, training, support, activities, and computer problem solving. In this project we also set up the base and mathability-extended typology of computer problem solving approaches, where quantitative values are assigned to the different problem solving methods and activities. In this paper we present the results of our analyses of teaching materials collected in different languages from all over the world and our findings considering the different problem solving approaches, set in the frame of different thinking modes, the characteristics of expert teachers, and the meaning system model of teaching approaches. Based on our research, we argue that the proportions of fast and slow thinking and most importantly their manifestation are responsible for erroneous end-user activities. Applying the five-point mathability scale of computer problem solving, we recognized slow thinking activities on both tails and one fast thinking approach between them. The low mathability slow thinking activities, where surface navigation and language details are focused on, are widely accepted in end-user computing. The high mathability slow thinking problem solving activities, where the utilization of concept based approaches and schema construction take place, is hardly detectable in end-user activities. Instead of building up knowledge which requires slow thinking and then using the tools with fast thinking, end-users use up their slow thinking in aimless wandering in huge programs, making wrong decisions based on their untrained, clueless intuition, and distributing erroneous end-user documents. We also found that the dominance of low mathability slow thinking activities has its roots in the education system and through this we point out that we are in great need of expert teachers and institutions and their widely accepted approaches and methods.展开更多
跨域推荐技术通过深入挖掘及利用其他域的有用信息,有效提升目标域的推荐表现,为解决用户冷启动问题提供了一种有效途径。然而,当前跨域推荐方法存在局限,未能细粒度地扩展隐式关系,并且忽视了嵌入向量中可能包含的冗余信息,从而制约了...跨域推荐技术通过深入挖掘及利用其他域的有用信息,有效提升目标域的推荐表现,为解决用户冷启动问题提供了一种有效途径。然而,当前跨域推荐方法存在局限,未能细粒度地扩展隐式关系,并且忽视了嵌入向量中可能包含的冗余信息,从而制约了跨域推荐系统的性能。鉴于此,提出一种基于域内和域间元路径聚合的跨域推荐方法,IMCDR(intra-domain and inter-domain meta-paths aggregation based cross-domain recommendation)。IMCDR首先通过细粒度地计算实体多字段的语义嵌入,有效扩展用户-用户和物品-物品关系;然后,IMCDR基于域内元路径和域间元路径为每个节点分别生成私有特征和共享特征,并将它们有效融合,以获得更高质量的嵌入向量。在三个跨域推荐任务上的综合实验结果表明,IMCDR在有效性和性能上具有明显优势。展开更多
In the rolling production of steel,predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categorie...In the rolling production of steel,predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories.This scenario poses a significant hurdle for machine learning models,leading to what is commonly known as the“cold-start problem”.To address this issue,we propose a knowledge graph attention neural network for steel manufacturing(SteelKGAT).By leveraging expert knowledge and a multi-head attention mechanism,SteelKGAT aims to enhance prediction accuracy.Our experimental results demonstrate that the SteelKGAT model outperforms existing methods when generalizing to previously unseen products.Only the SteelKGAT model accurately captures the feature trend,thereby offering correct guidance in product tuning,which is of practical significance for new product development(NPD).Additionally,we employ the Integrated Gradients(IG)method to shed light on the model's predictions,revealing the relative importance of each feature within the knowledge graph.Notably,this work represents the first application of knowledge graph attention neural networks to address the cold-start problem in steel rolling production.By combining domain expertise and interpretable predictions,our knowledge-informed SteelKGAT model provides accurate insights into the mechanical properties of products even in cold-start scenarios.展开更多
对于大规模多用户多输入多输出正交频分复用(Multiple-Input Multiple-Output-Orthogonal Frequency Division Multiplexing,MIMO-OFDM)下行链路系统,可以利用基站大量天线提供的丰富自由度来降低峰均功率比(Peak-to-Average Power Rati...对于大规模多用户多输入多输出正交频分复用(Multiple-Input Multiple-Output-Orthogonal Frequency Division Multiplexing,MIMO-OFDM)下行链路系统,可以利用基站大量天线提供的丰富自由度来降低峰均功率比(Peak-to-Average Power Ratio,PAPR)。提出了将OFDM调制、预编码及PAPR约束整合为一个非凸优化问题,即在多用户间的干扰(Multiple User interference,MUI)和PAPR为约束条件下最小化系统发射功率,并采用投影梯度下降法(Projected Gradient Method,PGM)直接解决PAPR感知预编码问题。仿真实验验证了所提出的PGM方法在降低PAPR和最小化符号错误率方面的出色性能。与现有方法相比,所提出的PGM方法具有更快的收敛速度和更低的复杂度。展开更多
文摘In this paper, an optimal multi user detector in DS/CDMA communication systems based on the mean field annealing (MFA) neural network is proposed. It is shown that the NP complete problem of minimizing the objective function of the optimal multi user detector can be translated into minimizing an MFA network energy function. Numerical results show that the proposed detector offers significant performance gain relative to the conventional detector and decorrelating detector while it can be implemented easily in analog hardware.
基金supporting by grant fund under the Strategic Scholarships for Frontier Research Network for the PhD Program Thai Doctoral degree
文摘A new recommendation method was presented based on memetic algorithm-based clustering. The proposed method was tested on four highly sparse real-world datasets. Its recommendation performance is evaluated and compared with that of the frequency-based, user-based, item-based, k-means clustering-based, and genetic algorithm-based methods in terms of precision, recall, and F1 score. The results show that the proposed method yields better performance under the new user cold-start problem when each of new active users selects only one or two items into the basket. The average F1 scores on all four datasets are improved by 225.0%, 61.6%, 54.6%, 49.3%, 28.8%, and 6.3% over the frequency-based, user-based, item-based, k-means clustering-based, and two genetic algorithm-based methods, respectively.
基金Projects(51378119,51578150)supported by the National Natural Science Foundation of China
文摘Advanced traveler information systems （ATIS） can not only improve drivers＇ accessibility to the more accurate route travel time information, but also can improve drivers＇ adaptability to the stochastic network capacity degradations. In this paper, a mixed stochastic user equilibrium model was proposed to describe the interactive route choice behaviors between ATIS equipped and unequipped drivers on a degradable transport network. In the proposed model the information accessibility of equipped drivers was reflected by lower degree of uncertainty in their stochastic equilibrium flow distributions, and their behavioral adaptability was captured by multiple equilibrium behaviors over the stochastic network state set. The mixed equilibrium model was formulated as a fixed point problem defined in the mixed route flows, and its solution was achieved by executing an iterative algorithm. Numerical experiments were provided to verify the properties of the mixed network equilibrium model and the efficiency of the iterative algorithm.
文摘Research in spreadsheet management proved that the overuse of slow thinking, rather than fast thinking, is the primary source of erroneous end-user computing. However, we found that the reality is not that simple. To view end-user computing in its full complexity, we launched a project to investigate end-user education, training, support, activities, and computer problem solving. In this project we also set up the base and mathability-extended typology of computer problem solving approaches, where quantitative values are assigned to the different problem solving methods and activities. In this paper we present the results of our analyses of teaching materials collected in different languages from all over the world and our findings considering the different problem solving approaches, set in the frame of different thinking modes, the characteristics of expert teachers, and the meaning system model of teaching approaches. Based on our research, we argue that the proportions of fast and slow thinking and most importantly their manifestation are responsible for erroneous end-user activities. Applying the five-point mathability scale of computer problem solving, we recognized slow thinking activities on both tails and one fast thinking approach between them. The low mathability slow thinking activities, where surface navigation and language details are focused on, are widely accepted in end-user computing. The high mathability slow thinking problem solving activities, where the utilization of concept based approaches and schema construction take place, is hardly detectable in end-user activities. Instead of building up knowledge which requires slow thinking and then using the tools with fast thinking, end-users use up their slow thinking in aimless wandering in huge programs, making wrong decisions based on their untrained, clueless intuition, and distributing erroneous end-user documents. We also found that the dominance of low mathability slow thinking activities has its roots in the education system and through this we point out that we are in great need of expert teachers and institutions and their widely accepted approaches and methods.
文摘跨域推荐技术通过深入挖掘及利用其他域的有用信息,有效提升目标域的推荐表现,为解决用户冷启动问题提供了一种有效途径。然而,当前跨域推荐方法存在局限,未能细粒度地扩展隐式关系,并且忽视了嵌入向量中可能包含的冗余信息,从而制约了跨域推荐系统的性能。鉴于此,提出一种基于域内和域间元路径聚合的跨域推荐方法,IMCDR(intra-domain and inter-domain meta-paths aggregation based cross-domain recommendation)。IMCDR首先通过细粒度地计算实体多字段的语义嵌入,有效扩展用户-用户和物品-物品关系;然后,IMCDR基于域内元路径和域间元路径为每个节点分别生成私有特征和共享特征,并将它们有效融合,以获得更高质量的嵌入向量。在三个跨域推荐任务上的综合实验结果表明,IMCDR在有效性和性能上具有明显优势。
基金supported by the National Key R&D Program(No.2021YFB3702404)National Natural Science Foundation of China(Nos.52311530082 and U22A20106)support provided by“Xingliao Talent Plan”project(Grant No.XLYC2203027)is gratefully acknowledged.
文摘In the rolling production of steel,predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories.This scenario poses a significant hurdle for machine learning models,leading to what is commonly known as the“cold-start problem”.To address this issue,we propose a knowledge graph attention neural network for steel manufacturing(SteelKGAT).By leveraging expert knowledge and a multi-head attention mechanism,SteelKGAT aims to enhance prediction accuracy.Our experimental results demonstrate that the SteelKGAT model outperforms existing methods when generalizing to previously unseen products.Only the SteelKGAT model accurately captures the feature trend,thereby offering correct guidance in product tuning,which is of practical significance for new product development(NPD).Additionally,we employ the Integrated Gradients(IG)method to shed light on the model's predictions,revealing the relative importance of each feature within the knowledge graph.Notably,this work represents the first application of knowledge graph attention neural networks to address the cold-start problem in steel rolling production.By combining domain expertise and interpretable predictions,our knowledge-informed SteelKGAT model provides accurate insights into the mechanical properties of products even in cold-start scenarios.
文摘对于大规模多用户多输入多输出正交频分复用(Multiple-Input Multiple-Output-Orthogonal Frequency Division Multiplexing,MIMO-OFDM)下行链路系统,可以利用基站大量天线提供的丰富自由度来降低峰均功率比(Peak-to-Average Power Ratio,PAPR)。提出了将OFDM调制、预编码及PAPR约束整合为一个非凸优化问题,即在多用户间的干扰(Multiple User interference,MUI)和PAPR为约束条件下最小化系统发射功率,并采用投影梯度下降法(Projected Gradient Method,PGM)直接解决PAPR感知预编码问题。仿真实验验证了所提出的PGM方法在降低PAPR和最小化符号错误率方面的出色性能。与现有方法相比,所提出的PGM方法具有更快的收敛速度和更低的复杂度。
