Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than eve...Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than ever before, and the process is quite time-consuming. Therefore, finding and recommending proper reviewers for the emerging Pull-Requests becomes a vital task. However, most of the current studies mainly focus on recommending reviewers by checking whether they will participate or not without differentiating the participation types. In this paper, we develop a two-layer reviewer recommendation model to recommend reviewers for Pull-Requests （PRs） in GitHub projects from the technical and managerial perspectives. For the first layer, we recommend suitable developers to review the target PRs based on a hybrid recommendation method. For the second layer, after getting the recommendation results from the first layer, we specify whether the target developer will technically or managerially participate in the reviewing process. We conducted experiments on two popular projects in GitHub, and tested the approach using PRs created between February 2016 and February 2017. The results show that the first layer of our recommendation model performs better than the previous work, and the second layer can effectively differentiate the types of participation.展开更多
In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental ...In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental combat form of the future, i.e.,“web-based kill,” and the operation loop theory. Firstly, we pioneer the operation loop recommendation problem with operation ring quality as the objective and closed-loop time as the constraint, and construct the corresponding planning model.Secondly, considering the case where there are multiple decision objectives for the combat ring recommendation problem,we propose for the first time a multi-objective optimization algorithm, the multi-objective ant colony evolutionary algorithm based on decomposition(MOACEA/D), which integrates the multi-objective evolutionary algorithm based on decomposition(MOEA/D) with the ant colony algorithm. The MOACEA/D can converge the optimal solutions of multiple single objectives nondominated solution set for the multi-objective problem. Finally,compared with other classical multi-objective optimization algorithms, the MOACEA/D is superior to other algorithms superior in terms of the hyper volume(HV), which verifies the effectiveness of the method and greatly improves the quality and efficiency of commanders’ decision-making.展开更多
With the arrival of the big data era,the phenomenon of information overload is becoming increasingly severe.In response to the common issue of sparse user rating matrices in recommendation systems,a collaborative filt...With the arrival of the big data era,the phenomenon of information overload is becoming increasingly severe.In response to the common issue of sparse user rating matrices in recommendation systems,a collaborative filtering recommendation algorithm was proposed based on improved user profiles in this study.Firstly,a profile labeling system was constructed based on user characteristics.This study proposed that user profile labels should be created using basic user information and basic item information,in order to construct multidimensional user profiles.TF-IDF algorithm was used to determine the weights of user-item feature labels.Secondly,user similarity was calculated by weighting both profile-based collaborative filtering and user-based collaborative filtering algorithms,and the final user similarity was obtained by harmonizing these weights.Finally,personalized recommendations were generated using Top-N method.Validation with the MovieLens-1M dataset revealed that this algorithm enhances both recommendation Precision and Recall compared to single-method approaches(recommendation algorithm based on user portrait and user-based collaborative filtering algorithm).展开更多
The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service amon...The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service among a large amount of service candidates. A novel user preferences-aware recommendation approach for trustworthy services is presented. For describing the requirements of new users in different application scenarios, user preferences are identified by usage preference, trust preference and cost preference. According to the similarity analysis of usage preference between consumers and new users, the candidates are selected, and these data about service trust provided by them are calculated as the fuzzy comprehensive evaluations. In accordance with the trust and cost preferences of new users, the dynamic fuzzy clusters are generated based on the fuzzy similarity computation. Then, the most suitable services can be selected to recommend to new users. The experiments show that this approach is effective and feasible, and can improve the quality of services recommendation meeting the requirements of new users in different scenario.展开更多
Technological developments that specifically address automation,compliance with environmental regulations,and hazard avoidance have accelerated more quickly than other drilling and completion technologies in the Unite...Technological developments that specifically address automation,compliance with environmental regulations,and hazard avoidance have accelerated more quickly than other drilling and completion technologies in the United States.This brief article provides a review of areas experiencing some of the most dramatic advances,while describing the need and addressing the solutions as they are now,and how they can be developed in the future.One aspect that all the new technologies have in common is an enhanced use of data analytics and in many cases,cloud-based solutions.A challenge that all have is a need to be able to quickly accommodate rapidly evolving requirements for emissions detection,hazard monitoring,and a reduced carbon footprint.Many solutions to the challenges require the ability to repurpose existing databases and use them for new purposes.展开更多
Deep learning based recommendation methods, such as the recurrent neural network based recommendation method(RNNRec) and the gated recurrent unit(GRU) based recommendation method(GRURec), are proposed to solve the pro...Deep learning based recommendation methods, such as the recurrent neural network based recommendation method(RNNRec) and the gated recurrent unit(GRU) based recommendation method(GRURec), are proposed to solve the problem of time heterogeneous feedback recommendation. These methods out-perform several state-of-the-art methods. However, in RNNRec and GRURec, action vectors and item vectors are shared among users. The different meanings of the same action for different users are not considered. Similarly, different user preference for the same item is also ignored. To address this problem, the models of RNNRec and GRURec are modified in this paper. In the proposed methods, action vectors and item vectors are transformed into the user space for each user firstly, and then the transformed vectors are fed into the original neural networks of RNNRec and GRURec. The transformed action vectors and item vectors represent the user specified meaning of actions and the preference for items, which makes the proposed method obtain more accurate recommendation results. The experimental results on two real-life datasets indicate that the proposed method outperforms RNNRec and GRURec as well as other state-of-the-art approaches in most cases.展开更多
大规模在线教育的普及使得学习者面临课程选择困难,个性化学习路径推荐面临依赖单一模态数据导致语义表征局限,以及静态知识图谱难以生成动态可解释推荐逻辑的挑战。为解决上述问题,提出一种基于动态注意力强化学习的可解释学习路径推荐...大规模在线教育的普及使得学习者面临课程选择困难,个性化学习路径推荐面临依赖单一模态数据导致语义表征局限,以及静态知识图谱难以生成动态可解释推荐逻辑的挑战。为解决上述问题,提出一种基于动态注意力强化学习的可解释学习路径推荐(explainable learning path recommendation based on dynamic attention reinforcement learning,ELPRDARL)框架。首先,构建了异构协同知识图谱,集成课程文本、视觉内容及知识依赖关系,增强跨模态语义对齐能力;其次,设计了邻接节点动态注意力聚合机制,通过偏置修正策略调整实体关系权重,并利用双向交互聚合器融合多阶邻域特征,提升知识推理的细粒度表达能力;最后,提出知识图谱感知的强化学习策略,基于路径连通性奖励函数显式建模用户行为与知识拓扑的关联,生成包含全局奖励与局部注意力权重的可解释路径。基于MOOC数据集上的实验表明,本方法在NDCG、Recall、HR和Precision指标上分别达到22.85%、33.81%、52.01%和6.34%,较次优模型提升2.88%、3.55%、2.42%和3.26%。用户调研显示,80.36%的学习者认为路径解释显著提升了推荐透明度。本研究验证了动态注意力机制与强化学习的协同优化能有效平衡推荐精度与可解释性。展开更多
针对传统基于二部图的物质扩散算法难以适应用户偏好异质性和物品属性多样性的问题,提出了一种自适应属性协同的物质扩散算法(adaptive attribute-collaborative material diffusion,AACD)。首先引入属性竞争力系数,对用户偏好进行差异...针对传统基于二部图的物质扩散算法难以适应用户偏好异质性和物品属性多样性的问题,提出了一种自适应属性协同的物质扩散算法(adaptive attribute-collaborative material diffusion,AACD)。首先引入属性竞争力系数,对用户偏好进行差异化捕捉;其次构建用户-属性耦合结构,自适应调控扩散路径与强度,从而挖掘高阶协同信号并提升资源传递的灵活性;最后通过稳态解分析保证算法的收敛性。通过在Ciao等三个公开数据集上的实验显示,在MovieLens-1M数据集上,recall@N、precision@N和NDCG@N较最优基准模型分别提升了6.57%、7.03%和11.37%,其结果验证了AACD在缓解资源分配偏差问题和流行度偏移问题的有效性。展开更多
基金Project(2016-YFB1000805)supported by the National Grand R&D Plan,ChinaProjects(61502512,61432020,61472430,61532004)supported by the National Natural Science Foundation of China
文摘Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than ever before, and the process is quite time-consuming. Therefore, finding and recommending proper reviewers for the emerging Pull-Requests becomes a vital task. However, most of the current studies mainly focus on recommending reviewers by checking whether they will participate or not without differentiating the participation types. In this paper, we develop a two-layer reviewer recommendation model to recommend reviewers for Pull-Requests （PRs） in GitHub projects from the technical and managerial perspectives. For the first layer, we recommend suitable developers to review the target PRs based on a hybrid recommendation method. For the second layer, after getting the recommendation results from the first layer, we specify whether the target developer will technically or managerially participate in the reviewing process. We conducted experiments on two popular projects in GitHub, and tested the approach using PRs created between February 2016 and February 2017. The results show that the first layer of our recommendation model performs better than the previous work, and the second layer can effectively differentiate the types of participation.
基金supported by the National Natural Science Foundation of China (72071206,71690233)the Science and Technology Innovation Program of Hunan Province (2020RC4046)。
文摘In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental combat form of the future, i.e.,“web-based kill,” and the operation loop theory. Firstly, we pioneer the operation loop recommendation problem with operation ring quality as the objective and closed-loop time as the constraint, and construct the corresponding planning model.Secondly, considering the case where there are multiple decision objectives for the combat ring recommendation problem,we propose for the first time a multi-objective optimization algorithm, the multi-objective ant colony evolutionary algorithm based on decomposition(MOACEA/D), which integrates the multi-objective evolutionary algorithm based on decomposition(MOEA/D) with the ant colony algorithm. The MOACEA/D can converge the optimal solutions of multiple single objectives nondominated solution set for the multi-objective problem. Finally,compared with other classical multi-objective optimization algorithms, the MOACEA/D is superior to other algorithms superior in terms of the hyper volume(HV), which verifies the effectiveness of the method and greatly improves the quality and efficiency of commanders’ decision-making.
文摘With the arrival of the big data era,the phenomenon of information overload is becoming increasingly severe.In response to the common issue of sparse user rating matrices in recommendation systems,a collaborative filtering recommendation algorithm was proposed based on improved user profiles in this study.Firstly,a profile labeling system was constructed based on user characteristics.This study proposed that user profile labels should be created using basic user information and basic item information,in order to construct multidimensional user profiles.TF-IDF algorithm was used to determine the weights of user-item feature labels.Secondly,user similarity was calculated by weighting both profile-based collaborative filtering and user-based collaborative filtering algorithms,and the final user similarity was obtained by harmonizing these weights.Finally,personalized recommendations were generated using Top-N method.Validation with the MovieLens-1M dataset revealed that this algorithm enhances both recommendation Precision and Recall compared to single-method approaches(recommendation algorithm based on user portrait and user-based collaborative filtering algorithm).
基金Project(61272148) supported by the National Natural Science Foundation of ChinaProject(2014FJ3122) supported by the Science and Technology Project of Hunan Province,China
文摘The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service among a large amount of service candidates. A novel user preferences-aware recommendation approach for trustworthy services is presented. For describing the requirements of new users in different application scenarios, user preferences are identified by usage preference, trust preference and cost preference. According to the similarity analysis of usage preference between consumers and new users, the candidates are selected, and these data about service trust provided by them are calculated as the fuzzy comprehensive evaluations. In accordance with the trust and cost preferences of new users, the dynamic fuzzy clusters are generated based on the fuzzy similarity computation. Then, the most suitable services can be selected to recommend to new users. The experiments show that this approach is effective and feasible, and can improve the quality of services recommendation meeting the requirements of new users in different scenario.
文摘Technological developments that specifically address automation,compliance with environmental regulations,and hazard avoidance have accelerated more quickly than other drilling and completion technologies in the United States.This brief article provides a review of areas experiencing some of the most dramatic advances,while describing the need and addressing the solutions as they are now,and how they can be developed in the future.One aspect that all the new technologies have in common is an enhanced use of data analytics and in many cases,cloud-based solutions.A challenge that all have is a need to be able to quickly accommodate rapidly evolving requirements for emissions detection,hazard monitoring,and a reduced carbon footprint.Many solutions to the challenges require the ability to repurpose existing databases and use them for new purposes.
基金supported by the National Natural Science Foundation of China(61403350)。
文摘Deep learning based recommendation methods, such as the recurrent neural network based recommendation method(RNNRec) and the gated recurrent unit(GRU) based recommendation method(GRURec), are proposed to solve the problem of time heterogeneous feedback recommendation. These methods out-perform several state-of-the-art methods. However, in RNNRec and GRURec, action vectors and item vectors are shared among users. The different meanings of the same action for different users are not considered. Similarly, different user preference for the same item is also ignored. To address this problem, the models of RNNRec and GRURec are modified in this paper. In the proposed methods, action vectors and item vectors are transformed into the user space for each user firstly, and then the transformed vectors are fed into the original neural networks of RNNRec and GRURec. The transformed action vectors and item vectors represent the user specified meaning of actions and the preference for items, which makes the proposed method obtain more accurate recommendation results. The experimental results on two real-life datasets indicate that the proposed method outperforms RNNRec and GRURec as well as other state-of-the-art approaches in most cases.
文摘大规模在线教育的普及使得学习者面临课程选择困难,个性化学习路径推荐面临依赖单一模态数据导致语义表征局限,以及静态知识图谱难以生成动态可解释推荐逻辑的挑战。为解决上述问题,提出一种基于动态注意力强化学习的可解释学习路径推荐(explainable learning path recommendation based on dynamic attention reinforcement learning,ELPRDARL)框架。首先,构建了异构协同知识图谱,集成课程文本、视觉内容及知识依赖关系,增强跨模态语义对齐能力;其次,设计了邻接节点动态注意力聚合机制,通过偏置修正策略调整实体关系权重,并利用双向交互聚合器融合多阶邻域特征,提升知识推理的细粒度表达能力;最后,提出知识图谱感知的强化学习策略,基于路径连通性奖励函数显式建模用户行为与知识拓扑的关联,生成包含全局奖励与局部注意力权重的可解释路径。基于MOOC数据集上的实验表明,本方法在NDCG、Recall、HR和Precision指标上分别达到22.85%、33.81%、52.01%和6.34%,较次优模型提升2.88%、3.55%、2.42%和3.26%。用户调研显示,80.36%的学习者认为路径解释显著提升了推荐透明度。本研究验证了动态注意力机制与强化学习的协同优化能有效平衡推荐精度与可解释性。
文摘针对传统基于二部图的物质扩散算法难以适应用户偏好异质性和物品属性多样性的问题,提出了一种自适应属性协同的物质扩散算法(adaptive attribute-collaborative material diffusion,AACD)。首先引入属性竞争力系数,对用户偏好进行差异化捕捉;其次构建用户-属性耦合结构,自适应调控扩散路径与强度,从而挖掘高阶协同信号并提升资源传递的灵活性;最后通过稳态解分析保证算法的收敛性。通过在Ciao等三个公开数据集上的实验显示,在MovieLens-1M数据集上,recall@N、precision@N和NDCG@N较最优基准模型分别提升了6.57%、7.03%和11.37%,其结果验证了AACD在缓解资源分配偏差问题和流行度偏移问题的有效性。
