检索结果-南通市图书馆

Semi-supervised Software Defect Prediction Using Task-Driven Dictionary Learning

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第6期25卷 1089-1096页

作者： CHENG Ming WU Guoqing yuan mengting WAN Hongyan School of Computer Wuhan University State Key Laboratory of Software Engineering Wuhan University

We present a semi-supervised approach for software defect prediction. The proposed method is designed to address the special problematic characteristics of software defect datasets, namely, lack of labeled samples and class-imbalanced data. To alleviate these problems, the proposed method features the following components. Being a semi-supervised approach, it exploits the wealth of unlabeled samples in software systems by evaluating the confidence probability of the predicted labels, for each unlabeled sample. And we propose to jointly optimize the classifier parameters and the dictionary by a task-driven formulation, to ensure that the learned features(sparse code) are optimal for the trained classifier. Finally, during the dictionary learning process we take the different misclassification costs into consideration to improve the prediction performance. Experimental results demonstrate that our method outperforms several representative stateof-the-art defect prediction methods.

关键词： Software defect prediction Task-driven dictionary learning Cost-sensitive Semi-supervised learning Sparse representation

Fast and efficient parallel breadth-first search with power-law graph transformation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2022年第5期16卷 225-227页

作者： Zite JIANG Tao LIU Shuai ZHANG mengting yuan Haihang YOU School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China School of Comptuer Science Wuhan UniversityWuhan 430072China

1 Introduction Most real-world graphs are large-scale but unstructured and *** of the most notable characteristics of real-world graphs is the skewed power law degree distribution[1]:most vertices have a few neighbors while a few own a large number of *** characteristics present challenges for efficient parallel graph processing,such as load imbalance,poor locality,and redundant *** from modifying the graph programming abstraction or changing the execution models on different architectures,reducing the irregularity of graph data also improves the performance of graph processing[2].For example,it is wellknown that BFS has a bad temporal locality,but it is possible to transform irregular graphs to more regular ones to improve spatial locality and gain more performance.

关键词： neighbor programming redundant

Climate warming restructures seasonal dynamics of grassland soil microbial communities

在线全文

学校读者我要写书评

暂无评论

mLife 2022年第3期1卷 245-256页

作者： Xue Guo mengting yuan Jiesi Lei Zhou Shi Xishu Zhou Jiabao Li Ye Deng Yunfeng Yang Liyou Wu Yiqi Luo James MTiedje Jizhong Zhou State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijingChina Institute for Environmental Genomics and Department of Microbiology and Plant Biology University of OklahomaNormanOklahomaUSA Department of Environmental Science Policyand ManagementUniversity of CaliforniaBerkeleyCaliforniaUSA Gladstone Institutes and Chan‐Zuckerberg Biohub San FranciscoCaliforniaUSA School of Minerals Processing and Bioengineering Central South UniversityChangshaChina Key Laboratory of Environmental and Applied Microbiology Chinese Academy of Sciences and Environmental Microbiology&Key Laboratory of Sichuan ProvinceChengdu Institute of BiologyChinese Academy of SciencesChengduChina Key Laboratory of Environmental Biotechnology Research Center for Eco‐Environmental SciencesChinese Academy of SciencesBeijingChina Department of Biological Sciences Center for Ecosystem Science and SocietyNorthern Arizona UniversityFlagstaffArizonaUSA Center for Microbial Ecology Michigan State UniversityEast LansingMichiganUSA School of Civil Engineering and Environmental Sciences University of OklahomaNormanOklahomaUSA Earth and Environmental Sciences Lawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA School of Computer Sciences University of OklahomaNormanOklahomaUSA.

Soil microbial community's responses to climate warming alter the global carbon *** temperate ecosystems,soil microbial communities function along seasonal ***,little is known about how the responses of soil microbial communities to warming vary when the season *** this study,we investigated the seasonal dynamics of soil bacterial community under experimental warming in a temperate tall‐grass prairie *** results showed that warming significantly(p=0.001)shifted community structure,such that the differences of microbial communities between warming and control plots increased nonlinearly(R^(2)=0.578,p=0.021)from spring to ***,warming significantly(p<0.050)increased microbial network complexity and robustness,especially during the colder seasons,despite large variations in network size and complexity in different *** addition,the relative importance of stochastic processes in shaping the microbial community decreased by warming in fall and winter but not in spring and *** study indicates that climate warming restructures the seasonal dynamics of soil microbial community in a temperate *** seasonality of microbial responses to warming may enlarge over time and could have significant impacts on the terrestrial carbon cycle.

关键词： climate warming microbial community microbial network seasonal dynamics

Computed tomography-based delta-radiomics enabling early prediction ofshort-term responses to concurrent chemoradiotherapy for patients withnon-small cell lung cancer

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Radiation Medicine and Protection 2023年第4期4卷 227-235页

作者： Fengqin Zhou Jianping Bi Shen Wu Yi Ding Jun Chen mengting yuan Yaoyao He Guang Han Zilong yuan Department of Radiology Hubei Cancer HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430079China Department of Radiation Oncology Hubei Cancer HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430079China GE Healthiness Shanghai 200126China

Objective:To explore the potential of computed tomography(CT)-based delta-radiomics in predicting early shortterm responses to concurrent chemoradiotherapy for patients with non-small cell lung cancer(NSCLC),in order to determine the optimal time point for the ***:A total of 20 patients with pathologically confirmed NSCLC were prospectively enrolled in this study,who did not receive surgical treatment between February 2021 and February *** each case,a total of 1,210 radiomic features(RFs)were extracted from both planning CT(pCT)images along with each of the subsequent three weeks of CT ***ΔRFs were selected using intra-class correlation coefficient(ICC)analysis,Pearson's correlation,ANOVA test(or Mann-Whitney U-test),and univariate logistic *** area under the curve(AUC)of the receiver operating characteristic(ROC)curve was used to evaluate the potential to predict short-term responses of different time ***:Among the 1,210ΔRFs for 1-3 weeks,121 common features were retained after processing using ICC analysis and Pearson's *** retained features included 54 and 58 of all time points that differed significantly between the response and non-response groups for the first and third months,respectively(P<0.05).After univariate logistic regression,11 and 44 features remained for the first and third months,***,eightΔRFs(P<0.05,AUC=0.77-0.91)that can discriminate short-term responses in both at 1 and 3 months with statistical accuracy were ***:CT-based delta-radiomics has the potential to provide reasonable biomarkers of short-term responses to concurrent chemoradiotherapy for NSCLC patients,and it can help improve clinical decisions for early treatment adaptation.

关键词： Non-small cell lung cancer Delta-radiomics Short-term response Computed tomography Concurrent chemoradiotherapy

基于ADS-B的无人机感知与规避蚁群算法模型

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

西北工业大学学报 2021年第4期39卷 761-769页

作者：袁梦婷时宏伟四川大学计算机学院四川成都610065

在空域融合背景下,为了提高无人机安全性能、防止空中碰撞事故的发生,提出一种基于ADS-B监视技术的无人机感知与规避蚁群算法模型。该模型主要由两部分组成:确定型冲突探测模型和冲突解脱模型。前者充分利用ADS-B信息从水平和垂直面进... 详细信息

在空域融合背景下,为了提高无人机安全性能、防止空中碰撞事故的发生,提出一种基于ADS-B监视技术的无人机感知与规避蚁群算法模型。该模型主要由两部分组成:确定型冲突探测模型和冲突解脱模型。前者充分利用ADS-B信息从水平和垂直面进行几何距离判定来确定冲突目标,后者则基于引入了综合启发函数和排序机制的蚁群算法进行航路重规划来实现避撞。经仿真实验验证,该探测模型能有效识别可能威胁目标,而解脱模型不仅适用于典型的双机冲突场景,也能为复杂的多机冲突场景提供较优质的解脱策略。

关键词：无人机感知与规避蚁群算法 ADS-B

在线全文

学校读者我要写书评

暂无评论

非确定有限自动机的最短D1-同步字求解

华中科技大学学报（自然科学版） 2021年第2期49卷 68-73页

作者：朱凯毋国庆袁梦霆杨磊武汉大学计算机学院湖北武汉430072 华南农业大学数学与信息学院广东广州510642

研究了非确定有限自动机的最短D1-同步字的计算问题。针对这种自动机定义了D1W问题及其参数化版本问题p-D1W和最优问题shortest-p-D1W,证明了p-D1W和shortest-p-D1W分别属于para-NP和para-DP。利用均匀分布模型随机生成大量的非确定的... 详细信息

研究了非确定有限自动机的最短D1-同步字的计算问题。针对这种自动机定义了D1W问题及其参数化版本问题p-D1W和最优问题shortest-p-D1W,证明了p-D1W和shortest-p-D1W分别属于para-NP和para-DP。利用均匀分布模型随机生成大量的非确定的有限自动机进行实验,结果表明:在定长的参数下几乎所有随机产生的自动机实例都不是D1-可同步的,一旦将自动机上每个状态和字母的变迁函数的像数量限制在2以内,会出现少量的D1-可同步的自动机,且绝大多数最短同步字长不超过状态数的2倍。

关键词：非确定有限自动机同步字固定参数易解的归约可满足问题参数化复杂性参数化算法

在线全文

学校读者我要写书评

暂无评论

侵袭性纤维瘤的靶向治疗进展

中国肿瘤临床 2021年第13期48卷 695-699页

作者：袁梦婷(综述) 韩光(审校) 华中科技大学同济医学院附属湖北肿瘤医院放疗中心武汉市430079

侵袭性纤维瘤(aggressive fibromatosis,AF),又称韧带样型纤维瘤病、韧带样肿瘤(desmoid tumor,DT)、肌肉腱膜纤维瘤病等。AF是一种介于良、恶性之间的肿瘤,虽然无包膜,局部浸润周围组织,可能是多灶性的,并且在术后易复发,但不易发生转... 详细信息

侵袭性纤维瘤(aggressive fibromatosis,AF),又称韧带样型纤维瘤病、韧带样肿瘤(desmoid tumor,DT)、肌肉腱膜纤维瘤病等。AF是一种介于良、恶性之间的肿瘤,虽然无包膜,局部浸润周围组织,可能是多灶性的,并且在术后易复发,但不易发生转移。目前,对于AF的治疗方法主要包括积极监测、手术、放疗、化疗、靶向治疗、内分泌与非甾体类药物治疗等。靶向治疗AF在过去的研究进展较为缓慢,疗效有限,因此通常被应用于其他常规治疗方法失败之后,作为补救治疗手段。但近年来随着靶向治疗基础研究的快速进展,一些新的靶向药物越来越多的用于AF的临床治疗,并且获得了较好的疗效。因此,如何预测这些靶向药物对AF治疗的疗效,其治疗机制又是如何,均是目前靶向治疗AF研究的热点。本文将就AF的靶向治疗新进展进行综述。

关键词：侵袭性纤维瘤靶向治疗酪氨酸激酶抑制剂

在线全文

学校读者我要写书评

暂无评论

有限自动机重置问题的算法研究进展

华中科技大学学报（自然科学版） 2021年第2期49卷 20-27页

作者：朱凯毋国庆梁早清袁梦霆武汉大学计算机学院湖北武汉430072 华南农业大学数学与信息学院广东广州510642

论述了最近10多年有限自动机重置问题在算法方面的研究进展。首先形式定义一些基本概念和四个有关重置的问题,给出这些问题的计算复杂性结果;然后回顾了2008年前的算法发展历程和若干结论;接着将2008年后的算法分为判定自动机是否可重... 详细信息

论述了最近10多年有限自动机重置问题在算法方面的研究进展。首先形式定义一些基本概念和四个有关重置的问题,给出这些问题的计算复杂性结果;然后回顾了2008年前的算法发展历程和若干结论;接着将2008年后的算法分为判定自动机是否可重置的基本算法、短重置字求解算法和最短重置字求解算法三类,分别对各个算法背后的思想、复杂度、生产的重置字的质量和存在的问题等进行分析;最后总结了这些算法的评估标准和优化策略,给出了理论上须要进一步探讨的问题。

关键词：有限自动机重置字广度优先搜索双向搜索近似比计算复杂性

在线全文

学校读者我要写书评

暂无评论

面向软件行为的多视点需求建模方法

武汉大学学报（理学版） 2014年第3期60卷 211-218页

作者：程铭黄勃毋国庆姚昱袁梦霆武汉大学计算机学院湖北武汉430072 武汉大学深圳研究院广东深圳518057

面向软件行为的多视点需求建模从视点需求出发,提出了基于软件行为描述语言(Behavior Description Language,BDL)的多视点需求模型、需求验证及生成形式化需求文档方法.首先划分目标系统构建多视点,然后利用BDL建立视点行为模型,所有视... 详细信息

面向软件行为的多视点需求建模从视点需求出发,提出了基于软件行为描述语言(Behavior Description Language,BDL)的多视点需求模型、需求验证及生成形式化需求文档方法.首先划分目标系统构建多视点,然后利用BDL建立视点行为模型,所有视点行为模型组合构成系统行为模型.在多视点行为模型框架下,利用BDL所构建行为模型进行语法、语义以及系统特性的检测,保证系统行为模型的正确性.最后,介绍了基于上述方法的多视点需求建模工具RMTS.

关键词：需求建模软件行为多视点模型检测