Observer-invariant histopathology using genetics-based machine learning

Prostate cancer accounts for one-third of noncutaneous cancers diagnosed in US men and is a leading cause of cancer-related death. Advances in Fourier transform infrared spectroscopic imaging now provide very large data sets describing both the structural and local chemical properties of cells within prostate tissue. Uniting spectroscopic imaging data and computer-aided diagnoses (CADx), our long term goal is to provide a new approach to pathology by automating the recognition of cancer in complex tissue. The first step toward the creation of such CADx tools requires mechanisms for automatically learning to classify tissue types—a key step on the diagnosis process. Here we demonstrate that genetics-based machine learning (GBML) can be used to approach such a problem. However, to efficiently analyze this problem there is a need to develop efficient and scalable GBML implementations that are able to process very large data sets. In this paper, we propose and validate an efficient GBML technique——based on an incremental genetics-based rule learner. exploits massive parallelisms via the message passing interface (MPI) and efficient rule-matching using hardware-implemented operations. Results demonstrate that is capable of performing prostate tissue classification efficiently, making a compelling case for using GBML implementations as efficient and powerful tools for biomedical image processing.     

数据挖掘技术在高校课堂教学评价中的应用

数据挖掘技术目前在商业、金融业等方面都得到了广泛的应用,而在教育领域应用较少。数据挖掘中的关联规则挖掘能够发现大量数据中项集之间有趣的关联或相关联系,特别是随着大量数据不停地收集和存储,从数据库中挖掘关联规则就越来越有其必要性。文中从滁州学院教师档案数据库提取相关教师的记录,并结合课堂教学质量评估中的实际数据,利用改进的Apriori算法找出教师本身的素质与学生评价结果之间的内在关系。     

改进的基于底层虚拟机混淆器的指令混淆框架

针对底层虚拟机混淆器（OLLVM）在指令混淆层面只支持指令替换一种算法,且仅支持5种运算符和13种替换方案的问题,设计了一种改进版的指令混淆框架InsObf,以加强OLLVM指令层面的混淆效果。InsObf包含指令加花和指令替换,其中指令加花首先对基本块的指令进行依赖分析,然后插入叠加跳转和虚假循环两种花指令;指令替换在OLLVM的基础上,拓展至13种运算符,共计52种指令替换方案。在底层虚拟机（LLVM）上实现了框架原型后,通过实验表明,与OLLVM相比,InsObf在时间开销增长约10个百分点,空间开销增长约20个百分点的情况下,圈复杂度和抗逆向能力均可提高近4倍;与同样基于OLLVM改进的Armariris和Hikari相比,InsObf在同一量级的时空开销下,可以提供更高的代码复杂度。因此,InsObf可提供指令层级的有效保护。     

基于K Framework的向量化机器学习指令语义形式化

ARM针对ARMv8.1-M微处理器架构推出基于M-Profile向量化扩展方案的技术,并命名为ARM Helium,声明能为ARM Cortex-M处理器提升达15倍的机器学习性能.随着物联网的高速发展,微处理器指令执行正确性尤为重要.指令集的官方手册作为芯片模拟程序,片上应用程序开发的依据,是程序正确性基本保障.主要介绍利用可执行语义框架K Framework对ARMv8.1-M官方参考手册中向量化机器学习指令的语义正确性研究.基于ARMv8.1-M的官方参考手册自动提取指令集中描述向量化机器学习指令执行过程的伪代码,并将其转换为形式化语义转换规则.通过K Framework提供的可执行框架利用测试用例,验证机器学习指令算数运算执行的正确性.     

基于PID神经网络的多轮轮毂电机协调控制研究

多轮轮毂电机运行参数具有不确定性,因此难以精准计算电机协调控制量,所以设计基于PID神经网络的多轮轮毂电机协调控制方法。搭建多轮轮毂电机数学模型,在该模型下实时采集多轮轮毂电机转速、位置等运行参数,并计算电机协调控制量。装设PID神经网络协调控制器,利用PID神经网络算法生成协调控制指令,从转速、转矩等方面实现多轮轮毂电机的协调控制。测试结果表明,在所提方法的协调控制下,多轮轮毂电机在空载和负载工况下的转矩控制误差降低了21.25r/min和25.7r/min,转矩控制误差降低了6.55N·m和17.45N·m,电机运行平衡度有所提升,多轮轮毂电机协调控制效果更好。     

一种嵌入式硬件辅助调试机制研究与实现

某自主指令架构系列芯片（简称为GCXP）主要使用基于扫描链重用的硬件调试机制,与主流商用嵌入式芯片产品相比,该硬件调制机制安全性较低且不具备用户交互、程序下载等功能,同时缺乏嵌入式调试软件生态,不利于嵌入式产品的推广与应用。参考ARM CoreSight、RISCV Debug SPEC及SiFive开源芯片Debug Module的实现细节,结合GCXP特权架构,提出一种软硬件协同的调试中断陷入机制。使用自主特权架构中的特权程序替代部分调试中断硬件逻辑,使得在调试模块设计时无需进行CPU协同修改以及操作系统软件接口和上位机调试软件的二次开发,从而避免CPU硬件逻辑修改后大量的验证工作,同时无缝兼容历史CPU IP。分析结果表明,该中断陷入机制与RISCV Debug SPEC协议能够实现良好的协同,可以与SiFive参考开源调试模块协同工作,支持主流交互式调试软件及硬件工具,且调试模块的代码及功能覆盖率都能达到100%,可以满足流片需求。     

美术院校课堂教学的地位和作用

课堂教学是学校教育的主体,高等美术院校也不例外。上好课,是包括美术院校在内的每一个教师的神圣职责。本文仅就美术类专业课堂教学的作用、教师知识的掌握及有关专家教授的授课艺术等问题加以分析和讨论     

Computer-assisted techniques to enhance transformative learning in first-year literature courses

When students use computers as learning tools, the whole process of learning, and, indeed, the learners themselves, are transformed. This article illustrates some techniques that foster transformative learning in computer-assisted first-year literature classes: first, a lesson plan on A Valediction: Forbidding Mourning that uses Microsoft Word functions, including format painter, tables, and annotation to explore meaning in context; second, a plan for learners to use subconference options in the Daedalus Interactive Writing Environment to analyze Oedipus Rex; finally, a demonstration of how students engage in a meta-reflection process as they explore Barn Burning with Freelance Graphics.Marguerite Jamieson is an English instructor at Anne Arundel Community College in Arnold, Maryland, and a doctoral student at George Mason University. Her research interests include forming bridges between adult learning theory and contemporary literary theory — especially drawing on transformational learning theory and the work of Mikhail Bakhtin and Lev Vygotsky.Rebecca Kajs holds a doctorate in English from Texas Woman's University with a concentration in rhetoric. For ten years, she taught the use of heuristic tools for reading analysis at the University of Texas at Arlington. She is currently an associate professor of English and Philosophy at Anne Arundel Community College.Anne Agee holds a doctorate in rhetoric from The Catholic University of America. A professor of English and formerly director of the Humanities Computer Center at Anne Arundel Community College, she is currently the college's Coordinator of Instructional Technology. Dr. Agee and Professor Jamieson have collaborated in a study of the learning environment in a computer classroom, the results of which were published in the Fall 1995 issue of Teaching/Learning Conversations. Dr. Agee has also published Using [Daedalus] InterChange as a Teachers' Journal in the Fall 1995 issue of Wings.     

SPARC体系结构处理器测试方法研究与实现

处理器离线测试广泛采用随机测试技术,但是随机测试技术生成大量测试代码,并且测试覆盖率不高;主要针对随机测试的不足,借鉴基于软件内建自测试方法建立处理器模块级于系统级功能模型,后分析功能模型可能发生错误,针对错误模型开发测试代码来提高错误覆盖率;经测试,模块级测试覆盖到所有功能点,达到功能模块100%测试,系统级的测试覆盖到SPARC V8的所有指令异常、正常测试用例;测试结果表明,所采取的测试方案对提高错误覆盖率是行之有效的.     

职业学校课程项目化教学改革

项目化教学是一种面向就业市场的新型教学模式,正逐步走进职业学校的课堂。在获得师生认可的同时,该教学方式在教学改革中体现出的矛盾也十分突出。本文对当前职业学校课程项目化教学改革中的诸多问题进行系统分析,提出比较现实的解决对策及具体的实施过程。