一种BPNNs识别算法的医学检测泛实时性问题研究  

Research on Pan-real-time Problem of Medical Detection Based on BPNNs Recognition Algorithm

作　　者：刘玉成[1] 理查德.丁 张颖超[3] LIU YuGcheng;Richard DING;ZHANGYingGchao(StateKeyLaboratory,NanjingUniversityofFinanceandEconomics,Nanjing210003,China;U.S.A.KronosResearchInstituteofBoston,Boston02101G02117,USA;SchoolofInformationandControl,NanjingUniversityofInformationScienceandTechnology,Nanjing210044,China)

机构地区：[1]南京财经大学国家级重点实验中心,南京210003 [2]美国波士顿克罗诺斯研究所,波士顿0210102117 [3]南京信息工程大学信息与控制学院,南京210044

出　　处：《计算机科学》2018年第6期301-307,共7页Computer Science

基　　金：江苏省六大人才高峰(2106-A-027);江苏省高校自然科学基金项目(12016KJD520122)资助

摘　　要：尿沉渣空间环境的复杂性,导致采集的有形成分图像存在较多冗余信息,提取有效的图像信息变得较为困难,进而使得识别系统需要处理的数据量十分巨大。虽然BP神经网络算法的串行版本DJ8000系统平台解决了细胞等有形成分的识别准确率问题,但其不能满足尿沉渣图像医学检验的实时性要求。为此,提出了基于BP神经网络算法优化的并行处理GPU框架的系统平台。它采用并行优化框架,同步高效地对数据进行加速处理;同时,以GPU计算和测试平台为硬件系统支持,无论是在硬件指标、数据传输及总线技术还是软硬件的兼容性方面,都有助于解决算法中时常出现的负载不均衡的问题。实验数据表明,BP神经网络尿沉渣识别算法在优化并行框架的GPU系统处理平台上显示的加速比、时效比和运行时间等相关性能参数值都有所提升。相比于DJ8000系统平台,优化的AMD HD7970和NVIDIAGTX680两个并行处理GPU框架系统平台相应的加速比参数值分别是前者的10.82~21.35个和7.63~15.28个标准当量。实验数据充分说明,优化并行框架的GPU处理系统中相关的逻辑数据、地址数据和线性寻程的函数映射关系均能相互动态分配对接并优化算法架构,实现软件到硬件系统的最优比映射,最终解决由于线程间负载不均衡导致的性能瓶颈问题,从而有效地化解了医学领域实时检测中的时效性这一难题。Due to the complexity of the urine sediment space environment,there is much redundant information of the collected tangible component image,and it also becomes difficult to extract effective image information.Therefore,the amount of data that need to be deal with is huge.Although the serial version DJ8000 system platform of BP neural network algorithm solves the problem of recognition accuracy of tangible components such as cells,it can't meet the realtime requirement of urine sediment image medical examination.To solve this problem,this paper presented a system platform of parallel processing GPU framework based on BP neural network algorithm optimization.It uses parallel optimization framework to synchronize and accelerate processing of data efficiently.At the same time,it supports the hardware platform based on GPU computing and test platform.Whether from the hardware indicators,data transmission and bus technology or hardware and software compatibility,it will help solve the problems,which often occur in the uneven load irregularities.Experimental data show that BP neural network algorithm for urinary sediment identification improve the performance parameters such as speedup,aging ratio and running time on GPU platform processing platform.Compared with DJ8000 system platform,the parallel processing GPU framework system platforms of AMD HD7970 and NVIDAGTX680 are optimized,and their corresponding acceleration ratio parameter values are 10.82~21.35 and 7.63~15.28 standard equivalents respectively.The data show that optimizing the mapping relationship between logical data,address data and linear seeking function in the GPU processing system of parallel frame can dynamically allocate and optimize the algorithm structure and optimize the mapping between software and hardware system.Finally,it solves theproblem of performance bottlenecks caused by load imbalance between threads.Thus,it effectively resolves the problem of real-time detection in urinary sediment environment.

关 键 词：BP神经网络 GPU平台 负载不均衡 并行优化 线程协调 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]