Reconfigurable array architecture has become an important hardware platform for edge-side deployment of convolutional neural networks due to their high parallelism and flexible programmability.However,traditional mult...Reconfigurable array architecture has become an important hardware platform for edge-side deployment of convolutional neural networks due to their high parallelism and flexible programmability.However,traditional multi-branch convolutional networks suffer from computational redundancy,high memory access overhead,and inefficient branch fusion.Therefore,this paper proposes an adaptive multi-branch convolutional module(AMBC)that integrates software-hardware co-optimization.During training,the learnable fusion coefficients are introduced to enable adaptive fusion of multi-scale features,while in the inference phase,the multiple branches and their normalization parameters are merged with the fusion coefficients into a single 3×3 convolutional kernel through operator fusion.On the SIREA-288 reconfigurable platform,compared with unoptimized multi-branch networks,the proposed AMBC reduces external memory accesses by 47.91%and inference latency by 47.20%,achieving a 1.90×speedup.This approach maximizes the utilization of the reconfigurable logic while minimizing both reconfiguration and data-movement overheads in edge inference.展开更多
In ordet to maintain the dependability of system and meet the functional needof users dtsire, this paper introduces a survivability mechanism into embedded real-time system,and proposes a general comprehensive, approa...In ordet to maintain the dependability of system and meet the functional needof users dtsire, this paper introduces a survivability mechanism into embedded real-time system,and proposes a general comprehensive, approach based on a rigorous definition of survivability. Thisapproach permits a trade-off between the function and the cost of system development. It emphasizesthe ultradependable implementation of crucial function without demanding that of entire system.展开更多
Background Within healthcare environments, the emerging field of evidence-based design (EBD) explores the links between wellbeing and good design practice of the built environment. Aim By optimising both design proces...Background Within healthcare environments, the emerging field of evidence-based design (EBD) explores the links between wellbeing and good design practice of the built environment. Aim By optimising both design processes and design outcomes, knowledge produced wrthin this field seeks to improve staff performance, augment patient healing and enhance service outcomes and experiences. Methods In a prior study by the author, a mental health service building design was developed which integrated feedback from mental health service users relative to what aspects of the built environments of their care would enhance their service outcomes and experiences, encourage them to avail themselves of services and/or engage in therapy, and those that would reduce their willingness to avail themselves of services. Results The research project protocol detailed here is the final testing stage of this body of work, where service users are invited to evaluate the final building design, experienced through virtual reality. This study addresses a gap in the literature, and aims to advance the field of EBD, and codesign with mental health service users, using virtual reality. Conclusions This research method details the aims, study design, methods and limitations of the study, with recommendations for future researchers.展开更多
在网络控制中,基于网络服务质量(Quality of services, QoS)的网络控制器的优化问题是网络控制研究中一个非常重要的问题,但到目前为止该问题的研究还不够深入．本文首先给出了网络环境下控制器与网络调度协作过程模型,然后在此模型基...在网络控制中,基于网络服务质量(Quality of services, QoS)的网络控制器的优化问题是网络控制研究中一个非常重要的问题,但到目前为止该问题的研究还不够深入．本文首先给出了网络环境下控制器与网络调度协作过程模型,然后在此模型基础上提出了控制器设计及网络特性相关的综合性能指标,接着以优化此指标为目的,利用离散LQR(Linear quadratic regulator)方法完成网络控制器与网络的交互设计过程．仿真结果说明了协作设计过程的有效性．展开更多
基金Supported by the National Science and Technology Major Project of China(2022ZD0119005)the Natural Science Project of Shaanxi Province(2025JC-YBMS-754,2024JC-YBMS-539)。
文摘Reconfigurable array architecture has become an important hardware platform for edge-side deployment of convolutional neural networks due to their high parallelism and flexible programmability.However,traditional multi-branch convolutional networks suffer from computational redundancy,high memory access overhead,and inefficient branch fusion.Therefore,this paper proposes an adaptive multi-branch convolutional module(AMBC)that integrates software-hardware co-optimization.During training,the learnable fusion coefficients are introduced to enable adaptive fusion of multi-scale features,while in the inference phase,the multiple branches and their normalization parameters are merged with the fusion coefficients into a single 3×3 convolutional kernel through operator fusion.On the SIREA-288 reconfigurable platform,compared with unoptimized multi-branch networks,the proposed AMBC reduces external memory accesses by 47.91%and inference latency by 47.20%,achieving a 1.90×speedup.This approach maximizes the utilization of the reconfigurable logic while minimizing both reconfiguration and data-movement overheads in edge inference.
文摘In ordet to maintain the dependability of system and meet the functional needof users dtsire, this paper introduces a survivability mechanism into embedded real-time system,and proposes a general comprehensive, approach based on a rigorous definition of survivability. Thisapproach permits a trade-off between the function and the cost of system development. It emphasizesthe ultradependable implementation of crucial function without demanding that of entire system.
文摘Background Within healthcare environments, the emerging field of evidence-based design (EBD) explores the links between wellbeing and good design practice of the built environment. Aim By optimising both design processes and design outcomes, knowledge produced wrthin this field seeks to improve staff performance, augment patient healing and enhance service outcomes and experiences. Methods In a prior study by the author, a mental health service building design was developed which integrated feedback from mental health service users relative to what aspects of the built environments of their care would enhance their service outcomes and experiences, encourage them to avail themselves of services and/or engage in therapy, and those that would reduce their willingness to avail themselves of services. Results The research project protocol detailed here is the final testing stage of this body of work, where service users are invited to evaluate the final building design, experienced through virtual reality. This study addresses a gap in the literature, and aims to advance the field of EBD, and codesign with mental health service users, using virtual reality. Conclusions This research method details the aims, study design, methods and limitations of the study, with recommendations for future researchers.
