Unmanned aerial vehicle (UAV)-based edge computing is an emerging technology that provides fast task processing for a wider area. To address the issues of limited computation resource of a single UAV and finite commun...Unmanned aerial vehicle (UAV)-based edge computing is an emerging technology that provides fast task processing for a wider area. To address the issues of limited computation resource of a single UAV and finite communication resource in multi-UAV networks, this paper joints consideration of task offloading and wireless channel allocation on a collaborative multi-UAV computing network, where a high altitude platform station (HAPS)is adopted as the relay device for communication between UAV clusters consisting of UAV cluster heads (ch-UAVs) and mission UAVs (m-UAVs). We propose an algorithm, jointing task offloading and wireless channel allocation to maximize the average service success rate (ASSR)of a period time. In particular,the simulated annealing(SA)algorithm with random perturbations is used for optimal channel allocation,aiming to reduce interference and minimize transmission delay.A multi-agent deep deterministic policy gradient (MADDPG) is proposed to get the best task offloading strategy. Simulation results demonstrate the effectiveness of the SA algorithm in channel allocation. Meanwhile,when jointly considering computation and channel resources,the proposed scheme effectively enhances the ASSR in comparison to other benchmark algorithms.展开更多
As the central nervous system controls whole-body motion, which involves multi-joint movement, certain problems with regard to the number of variables controlled by the central nervous system arise (i.e., the “degree...As the central nervous system controls whole-body motion, which involves multi-joint movement, certain problems with regard to the number of variables controlled by the central nervous system arise (i.e., the “degree of freedom problem”). The central nervous system solves these problems not by controlling joint movements, but rather by controlling only the task-dependent center of mass (COM) position of the whole body. Although uncontrolled joint movement should be organized in a coordinate manner to form the task-dependent COM position, it is unclear what kind of law joint coordination is organized by. Hence, in the present study, we aim to clarify the shape of joint coordination by elucidating the mutual relationship between the COM trajectory and joint movement during whole-body motion. Downward squatting motions with five trunk angles are recorded by using a 3-D motion analysis system in 8 healthy males. The COM trajectory shows a task-dependent path in all trunk conditions. The shank angle decreases with an increase in the trunk angle to produce the task-dependent COM trajectory, whereas the thigh showsd a constant angle. These findings demonstrate that the COM trajectory is constrained by biomechanical dynamics and minimum muscle torques, and that the joints are organized into a lawful coordinative structure to form the COM trajectory.展开更多
The goal of the present study was to investigate age-related changes in attentional allocation for shared task representations during joint performance;event-related potentials were recorded while participants perform...The goal of the present study was to investigate age-related changes in attentional allocation for shared task representations during joint performance;event-related potentials were recorded while participants performed a modified visual three-stimulus oddball task, both alone and together with another participant. Younger adults and older adults (14 each) participated in the study. Participants were required to identify rare target stimuli while ignoring frequent standards, as well as rare non-targets assigned to a partner’s action (<i>i.e</i>., no-go stimuli for one’s own task). ERP component, nogo-P3 and P3b were measured to investigate the inhibition and the attentional allocation to the partner’s stimuli. Results showed that younger adults elicited larger frontal nogo P3 and parietal P3b for non-targets in the joint than in the individual condition. Contrary to expectation, older adults induced frontal no-go P3 in the joint condition not in the individual condition. In the sharing of the task with another, the result suggested that the efficiency of matching of incoming information with the representation of the other’s task declined with age, whereas aging did not affect the suppression of incorrect preparation of motor responses instigated by this representation.</i.i.e.<>展开更多
对文本中诸如实体与关系、事件及其论元等要素及其特定关系的联合抽取是自然语言处理的一项关键任务.现有研究大多采用统一编码或参数共享的方式隐性处理任务间的交互,缺乏对任务之间特定关系的显式建模,从而限制模型充分利用任务间的...对文本中诸如实体与关系、事件及其论元等要素及其特定关系的联合抽取是自然语言处理的一项关键任务.现有研究大多采用统一编码或参数共享的方式隐性处理任务间的交互,缺乏对任务之间特定关系的显式建模,从而限制模型充分利用任务间的关联信息并影响任务间的有效协同.为此,提出了一种基于任务协作表示增强的要素及关系联合抽取模型(Task-Collaboration Representation Enhanced model for joint extraction of elements and relationships,TCRE).该模型旨在从多个阶段处理任务间的特定关系,帮助子任务进行更细致的调节和优化,促进整体性能的提升.在三个关系抽取和一个事件抽取数据集上进行实验,TCRE在实体识别和关系提取任务上平均性能分别提高0.57%和0.77%,在触发词识别和论元角色分类任务上分别提高0.7%和1.4%.此外,TCRE还显示出在缓解“跷跷板现象”方面的作用.展开更多
片段抽取式阅读理解是机器阅读理解任务中的一项重要研究内容,现有的相关研究主要关注单片段抽取,然而,实际应用中很多阅读理解问题的答案由文本的多处不连续片段组成,这使得多片段抽取式阅读理解研究受到越来越多的关注。已有的多片段...片段抽取式阅读理解是机器阅读理解任务中的一项重要研究内容,现有的相关研究主要关注单片段抽取,然而,实际应用中很多阅读理解问题的答案由文本的多处不连续片段组成,这使得多片段抽取式阅读理解研究受到越来越多的关注。已有的多片段抽取式阅读理解研究大都采用序列标注的方法,该方法不能有效识别多片段问题类型,常常对不同类型的问题给出多个答案片段。为此,该文提出一种结合动态预测片段数量和序列标注的多任务联合学习方法。其中,动态预测片段数量能较为准确地识别出多片段问题类型;序列标注能够实现多个答案片段的有效定位。同时,为了进一步增强现有模型的泛化能力,该文在模型训练中构造了对抗训练和两阶段训练方式。在2021中国法律智能技术评测(Challenge of AI in Law 2021,CAIL2021)数据集和QUOREF数据集上的实验结果表明,该文提出的方法相比基线模型取得了更好的效果。展开更多
在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和...在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和答案抽取任务耦合性不强的问题.为了解决以上问题,本文提出一种结合门控机制和多级残差结构的多任务联合训练模型GMRT(Gated Mechanism and Multi-level Residual Structure for Multi-task Joint Training),以提升机器阅读理解任务中答案预测的准确性.GMRT构建门控机制来筛选交互后的关联特征,从而控制信息的流动.采用多级残差结构分别连接注意力机制和门控机制,保证每个阶段都保留原始语义信息.同时,通过边缘损失函数对问题分类任务和答案抽取任务联合训练,确保预测答案过程中任务之间的强耦合性.在SQuAD2.0数据集上的实验结果表明,GMRT模型的EM值和F1值均优于对比模型.展开更多
基金supported in part by the National Natural Science Foundation of China under Grants 62341104,62201085,62325108,and 62341131.
文摘Unmanned aerial vehicle (UAV)-based edge computing is an emerging technology that provides fast task processing for a wider area. To address the issues of limited computation resource of a single UAV and finite communication resource in multi-UAV networks, this paper joints consideration of task offloading and wireless channel allocation on a collaborative multi-UAV computing network, where a high altitude platform station (HAPS)is adopted as the relay device for communication between UAV clusters consisting of UAV cluster heads (ch-UAVs) and mission UAVs (m-UAVs). We propose an algorithm, jointing task offloading and wireless channel allocation to maximize the average service success rate (ASSR)of a period time. In particular,the simulated annealing(SA)algorithm with random perturbations is used for optimal channel allocation,aiming to reduce interference and minimize transmission delay.A multi-agent deep deterministic policy gradient (MADDPG) is proposed to get the best task offloading strategy. Simulation results demonstrate the effectiveness of the SA algorithm in channel allocation. Meanwhile,when jointly considering computation and channel resources,the proposed scheme effectively enhances the ASSR in comparison to other benchmark algorithms.
文摘As the central nervous system controls whole-body motion, which involves multi-joint movement, certain problems with regard to the number of variables controlled by the central nervous system arise (i.e., the “degree of freedom problem”). The central nervous system solves these problems not by controlling joint movements, but rather by controlling only the task-dependent center of mass (COM) position of the whole body. Although uncontrolled joint movement should be organized in a coordinate manner to form the task-dependent COM position, it is unclear what kind of law joint coordination is organized by. Hence, in the present study, we aim to clarify the shape of joint coordination by elucidating the mutual relationship between the COM trajectory and joint movement during whole-body motion. Downward squatting motions with five trunk angles are recorded by using a 3-D motion analysis system in 8 healthy males. The COM trajectory shows a task-dependent path in all trunk conditions. The shank angle decreases with an increase in the trunk angle to produce the task-dependent COM trajectory, whereas the thigh showsd a constant angle. These findings demonstrate that the COM trajectory is constrained by biomechanical dynamics and minimum muscle torques, and that the joints are organized into a lawful coordinative structure to form the COM trajectory.
文摘The goal of the present study was to investigate age-related changes in attentional allocation for shared task representations during joint performance;event-related potentials were recorded while participants performed a modified visual three-stimulus oddball task, both alone and together with another participant. Younger adults and older adults (14 each) participated in the study. Participants were required to identify rare target stimuli while ignoring frequent standards, as well as rare non-targets assigned to a partner’s action (<i>i.e</i>., no-go stimuli for one’s own task). ERP component, nogo-P3 and P3b were measured to investigate the inhibition and the attentional allocation to the partner’s stimuli. Results showed that younger adults elicited larger frontal nogo P3 and parietal P3b for non-targets in the joint than in the individual condition. Contrary to expectation, older adults induced frontal no-go P3 in the joint condition not in the individual condition. In the sharing of the task with another, the result suggested that the efficiency of matching of incoming information with the representation of the other’s task declined with age, whereas aging did not affect the suppression of incorrect preparation of motor responses instigated by this representation.</i.i.e.<>
文摘对文本中诸如实体与关系、事件及其论元等要素及其特定关系的联合抽取是自然语言处理的一项关键任务.现有研究大多采用统一编码或参数共享的方式隐性处理任务间的交互,缺乏对任务之间特定关系的显式建模,从而限制模型充分利用任务间的关联信息并影响任务间的有效协同.为此,提出了一种基于任务协作表示增强的要素及关系联合抽取模型(Task-Collaboration Representation Enhanced model for joint extraction of elements and relationships,TCRE).该模型旨在从多个阶段处理任务间的特定关系,帮助子任务进行更细致的调节和优化,促进整体性能的提升.在三个关系抽取和一个事件抽取数据集上进行实验,TCRE在实体识别和关系提取任务上平均性能分别提高0.57%和0.77%,在触发词识别和论元角色分类任务上分别提高0.7%和1.4%.此外,TCRE还显示出在缓解“跷跷板现象”方面的作用.
文摘片段抽取式阅读理解是机器阅读理解任务中的一项重要研究内容,现有的相关研究主要关注单片段抽取,然而,实际应用中很多阅读理解问题的答案由文本的多处不连续片段组成,这使得多片段抽取式阅读理解研究受到越来越多的关注。已有的多片段抽取式阅读理解研究大都采用序列标注的方法,该方法不能有效识别多片段问题类型,常常对不同类型的问题给出多个答案片段。为此,该文提出一种结合动态预测片段数量和序列标注的多任务联合学习方法。其中,动态预测片段数量能较为准确地识别出多片段问题类型;序列标注能够实现多个答案片段的有效定位。同时,为了进一步增强现有模型的泛化能力,该文在模型训练中构造了对抗训练和两阶段训练方式。在2021中国法律智能技术评测(Challenge of AI in Law 2021,CAIL2021)数据集和QUOREF数据集上的实验结果表明,该文提出的方法相比基线模型取得了更好的效果。
文摘在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和答案抽取任务耦合性不强的问题.为了解决以上问题,本文提出一种结合门控机制和多级残差结构的多任务联合训练模型GMRT(Gated Mechanism and Multi-level Residual Structure for Multi-task Joint Training),以提升机器阅读理解任务中答案预测的准确性.GMRT构建门控机制来筛选交互后的关联特征,从而控制信息的流动.采用多级残差结构分别连接注意力机制和门控机制,保证每个阶段都保留原始语义信息.同时,通过边缘损失函数对问题分类任务和答案抽取任务联合训练,确保预测答案过程中任务之间的强耦合性.在SQuAD2.0数据集上的实验结果表明,GMRT模型的EM值和F1值均优于对比模型.
