检索结果-南通市图书馆

在线全文

学校读者我要写书评

暂无评论

监督式主题模型及其应用综述

计算机工程与应用 2024年第8期60卷 56-68页

作者：王振彪徐贞顺刘纳张文豪唐增金王正安北方民族大学计算机科学与工程学院银川750021 北方民族大学图像图形智能处理国家民委重点实验室银川750021

主题模型是一种数据挖掘的方法,可以自动地从大量文件或数据中提取潜在的模式或主题,并将对应的数据分配到相应的模式或主题中。主题模型已广泛应用于文本聚类或分类、主题抽取、主题演变、情感分析和摘要总结等领域。监督式主题模型和... 详细信息

主题模型是一种数据挖掘的方法,可以自动地从大量文件或数据中提取潜在的模式或主题,并将对应的数据分配到相应的模式或主题中。主题模型已广泛应用于文本聚类或分类、主题抽取、主题演变、情感分析和摘要总结等领域。监督式主题模型和非监督主题模型的区别在于是否依赖标注信息。近年来,监督式主题模型在数据挖掘任务中逐渐兴起,使得越来越多的任务倾向于采用监督式方法进行优化。陈述了监督式主题模型相关内容,介绍常用的数据集和评价指标;分别从模型和应用的角度对各种类型的监督式主题模型进行了深入对比分析。最后,阐述了主题模型当前研究所面临的挑战,并对未来监督式主题模型的研究方向进行展望。

关键词：数据挖掘监督式主题模型主题预测主题演变

在线全文

学校读者我要写书评

暂无评论

知识图谱补全方法研究综述

计算机工程与应用 2024年第12期60卷 61-73页

作者：张文豪徐贞顺刘纳王振彪唐增金王正安北方民族大学计算机科学与工程学院银川750021 北方民族大学图像图形智能处理国家民委重点实验室银川750021

知识图谱是用来描述世界中存在的各种实体和概念以及他们之间的关系的一种语义网络,近年来被广泛应用于智能问答、智能推荐和信息检索等领域。目前,大多数知识图谱都具有不完整性,因此,知识图谱补全成为一项重要的任务。根据模型构造方... 详细信息

知识图谱是用来描述世界中存在的各种实体和概念以及他们之间的关系的一种语义网络,近年来被广泛应用于智能问答、智能推荐和信息检索等领域。目前,大多数知识图谱都具有不完整性,因此,知识图谱补全成为一项重要的任务。根据模型构造方法的不同,将知识图谱补全模型分为传统知识图谱补全模型、基于神经网络的知识图谱补全模型和基于元学习的知识图谱补全模型三类,对这三种知识图谱补全模型的分类情况进行介绍;总结知识图谱补全方法所使用的数据集和评价指标,并从各个模型优点和不足等方面对各类模型进行详细的对比分析。最后,对知识图谱补全进行归纳与总结,并展望未来的研究方向。

关键词：知识图谱翻译模型张量分解神经网络元学习知识图谱补全

在线全文

学校读者我要写书评

暂无评论

基于特征选择的风机检修流程预测性监控方法

计算机集成制造系统 2024年第8期30卷 2745-2755页

作者：郭娜刘聪李彩虹刘文娟王雷曾庆田山东理工大学电气与电子工程学院山东淄博255000 山东理工大学计算机科学与技术学院山东淄博255000 山东科技大学计算机科学与工程学院山东青岛266590

针对风机检修业务流程中存在的操作失误和工作延期等问题,应用业务流程预测性监控方法,预测业务的下一事件、下一事件执行时间和剩余时间,以提醒工作人员预防和避免风险的发生。首先,针对不同预测任务,提出一种基于优先级的特征自选取策... 详细信息

针对风机检修业务流程中存在的操作失误和工作延期等问题,应用业务流程预测性监控方法,预测业务的下一事件、下一事件执行时间和剩余时间,以提醒工作人员预防和避免风险的发生。首先,针对不同预测任务,提出一种基于优先级的特征自选取策略,并使用LightGBM(Light Gradient Boosting Machine)算法作为特征选择策略的依托预测模型,得到对预测结果有积极影响的输入特征;然后,针对不同预测任务分别采用LightGBM算法和LSTM(Long Short Term Memory)神经网络构建预测模型;最后,经实验评估和分析,在风机检修业务流程中,特征选择策略能够为不同的预测任务提供有效特征,确保预测的准确率,具有实际应用价值。对于不同预测任务而言,LightGBM算法更适用于下一事件任务预测,LSTM模型更适用于时间方面的任务预测。

关键词：流程预测性监控风机检修特征选择下一事件剩余时间

Multi-Attribute Preferences Mining Method for Group Users with the Process of Noise Reduction

在线全文

学校读者我要写书评

暂无评论

Journal of computer science & Technology 2021年第4期36卷 944-960页

作者： Qing-Mei Tan Xu-na wang college of Economic and Management Nanjing University of Aeronautics and AstronauticsNanjing 211106China Research Base for Civilian-Military Integration Development in Jiangsu Province Nanjing 211106China

Traditional researches on user preferences mining mainly explore the user’s overall preferences on the project,but ignore that the fundamental motivation of user preferences comes from their attitudes on some attributes of the *** addition,traditional researches seldom consider the typical preferences combination of group users,which may have influence on the personalized service for group *** solve this problem,a method with noise reduction for group user preferences mining is proposed,which focuses on mining the multi-attribute preference tendency of group ***,both the availability of data and the noise interference on preferences mining are considered in the algorithm *** the process of generating group user preferences,a new path is used to generate preference keywords so as to reduce the noise ***,the Gibbs sampling algorithm is used to estimate the parameters of the ***,using the user comment data of several online shopping websites as experimental objects,the method is used to mine the multi-attribute preferences of different *** proposed method is compared with other methods from three aspects of predictive ability,preference mining ability and preference topic *** results show that the method is significantly better thap other existing methods.

关键词： preferences mining group user multi-attribute noise reduction noise interference

Efficacy and safety of anlotinib combined with the STUPP regimen in patients with newly diagnosed glioblastoma: a multicenter, single-arm, phase Ⅱ trial

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

Cancer Biology & Medicine 2024年第5期21卷 433-444页

作者： Shuzhen Lai Peijing Li Xiaohui Liu Guihong Liu Tieming Xie Xing Zhang Xiaoxuan wang Jing Huang Yiqiang Tang Zhigang Liu Guoping Shen Chaoming Li Fangxiao Lu Lei wang Fagui Jiang Caixing Sun Yuanyuan Chen Ming Chen Department of Radiation Oncology The Second Affiliated Hospital of Soochow UniversitySuzhou 215000China Department of Radiation Oncology Yuebei People’s Hospital Affiliated to the Medical College of Shantou UniversityShaoguan 512026China Chinese Academy of SciencesHangzhou 310022China Department of Radiation Oncology The Second Clinical Medical College of Zhejiang Chinese Medical UniversityHangzhou 311403China Department of Radiation Oncology The Affiliated Hospital of Xuzhou Medical UniversityXuzhou 221004China Chinese Academy of SciencesHangzhou 310022China State Key Laboratory of Translational Medicine and Innovative Drug Development Jiangsu Simcere Diagnostics Co.LtdNanjing 210000China Department of Radiation Oncology The Affiliated Huai’an First People’s Hospital of Nanjing Medical UniversityHuai’an 223399China Department of Radiation Oncology Jiangxi Cancer Hospital of Nanchang UniversityNanchang 330029China Department of Radiotherapy Dongguan Institute of Clinical Cancer ResearchDongguan Key Laboratory of Precision Diagnosis and Treatment for TumorsAffiliated Dongguan HospitalSouthern Medical UniversityDongguan 523059China The Cancer Center The Fifth Affiliated Hospital of Sun Yat-Sen UniversityZhuhai 519000China Department of Radiation Oncology The First Affiliated Hospital of Sun Yat-Sen UniversityGuangzhou 510080China Department of Oncology Maoming People’s HospitalMaoming 525000China Department of Radiation Oncology Kecheng District People’s HospitalQuzhou 324003China Chinese Academy of SciencesHangzhou 310022China Department of Radiation Oncology State Key Laboratory of Oncology in South ChinaSun Yat-sen University Cancer CenterGuangzhou 510060China United Laboratory of Frontier Radiotherapy Technology of Sun Yat-sen university&Chinese Academy of sciences Ion Medical Technology Co. LtdGuangzhou 510060China

Objective:Glioblastomas are highly vascularized malignant *** determined the efficacy and safety of the anti-angiogenic multi-kinase inhibitor,anlotinib,for a newly diagnosed ***:This multicenter,single-arm trial(NCT04119674)enrolled 33 treatment-naïve patients with histologically proven glioblastomas between March 2019 and November *** underwent treatment with the standard STUPP regimen[fractionated focal irradiation in daily fractions of 1.8-2 Gy given 5 d/w×6 w(total=54-60 Gy)]or radiotherapy plus continuous daily temozolomide(TMZ)(75 mg/m^(2)of body surface area/d,7 d/w from the first to the last day of radiotherapy),followed by 6 cycles of adjuvant TMZ(150-200 mg/m^(2)×5 d during each 28-d cycle)plus anlotinib(8 mg/d on d 1-14 of each 3-w cycle for 2 cycles during concomitant chemoradiotherapy,8 maximal cycles as adjuvant therapy,followed by maintenance at 8 mg/*** primary endpoint was progression-free survival(PFS).Secondary endpoints included overall survival(OS)and adverse events(AEs).Results:Thirty-three patients received the planned *** median PFS was 10.9 months(95%CI,9.9-18.7 months)and the 12-month PFS rate was 48.5%.The median OS was 17.4 months(95%CI,14.5-21.1 months)and the 12-month OS rate was 81.8%.The most common AEs included hypertriglyceridemia[58%(n=19)],hypoalbuminemia[46%(n=15)],and hypercholesterolemia[46%(n=15)]during concurrent chemoradiotherapy and leukopenia[73%(n=24)],hypertriglyceridemia[67%(n=22)],and neutropenia[52%(n=17)]during adjuvant *** patients discontinued treatment due to ***1(HR,5.6;95%CI,1.3-23.7;P=0.021)and RP1L1 alterations(HR,11.1;95%CI,2.2-57.2;P=0.004)were associated with a significantly shorter ***:Anlotinib plus the STUPP regimen has promising anti-tumor activity against glioblastoma and manageable ***1 and RP1L1 alterations might be novel predictive biomarkers of the response to anlotinib.

关键词： Glioblastoma anti-angiogenesis multi-kinase inhibitor anlotinib temozolomide progression-free survival

人工智能在胃癌诊治中的研究趋势:20年的文献计量学分析

在线全文

学校读者我要写书评

暂无评论

中国全科医学 2024年第4期27卷 493-501页

作者：董娜崔婷王露露师荣慧冯洁黄晓俊兰州大学第二临床医学院甘肃省兰州市730000 兰州大学第二医院消化科甘肃省兰州市730000

背景近年来有关将人工智能(AI)应用于胃癌诊治的研究日益增多,但目前尚未有研究者使用文献计量学分析法对其进行系统的分析。目的对将AI应用于胃癌诊治的相关研究进行分析,探讨2003-2022年研究的热点及发展趋势。方法于2022-11-06,计算... 详细信息

背景近年来有关将人工智能(AI)应用于胃癌诊治的研究日益增多,但目前尚未有研究者使用文献计量学分析法对其进行系统的分析。目的对将AI应用于胃癌诊治的相关研究进行分析,探讨2003-2022年研究的热点及发展趋势。方法于2022-11-06,计算机检索Web of science(WOS)核心合集数据库,获取将AI应用于胃癌诊治的相关研究。通过文献计量学分析法,采用VOSviewer 1.6.18软件对国家(地区)间、机构间、作者间的合作情况、共被引作者情况、关键词共现与叠加情况进行可视化分析,采用CiteSpace 5.7.R5软件进行机构中介中心性分析、期刊双图叠加分析、近6年共被引文献聚类分析、共被引文献聚类时间线图分析及参考文献突现分析。采用Excel 2019软件绘制发文量条形图,以及国家(地区)、机构、期刊、作者、共被引作者、引用参考文献和关键词的描述性分析表格。结果共纳入703篇文献,2003-2022年将AI应用于胃癌诊治的相关研究年发文量整体呈上升趋势,2017年后年发文量快速增长,其中2019-2021年增长最为迅速。发文量最多的国家(地区)、机构和作者分别为中国、中国科学院和TADA TOMOHIRO。共被引次数排在前3的作者BRAY FREDDIE、HIRASAWA TOSHIAKI和JIANG YUMING对该领域做出了重要贡献。Frontiers in Oncology是发文量最多的期刊,Gastrointestinal Endoscopy是刊载将AI应用于胃癌诊治相关研究、发文量排在前10的期刊中最具影响力的期刊。施引期刊的所属领域主要集中在“Medicine,Medical,Clinical”(“药物,医学,临床”)、“Molecular,Biology,Immunology”(“分子,生物学,免疫学”)2个领域;被引期刊的所属领域主要集中在“Molecular,Biology,Genetics”(“分子,生物学,遗传学”)、“Health,Nursing,Medicine”(“健康,护理,药物”)2个领域。共被引次数排在首位的参考文献为Global cancer statistics 2018:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries。根据关键词聚类结果可将所有关键词分为4类:AI辅助胃癌的生物学研究、AI辅助胃癌的内镜诊断、AI辅助胃癌的病理诊断和AI辅助胃癌的非内镜治疗及预后预测。深度学习、卷积神经网络、影像组学、消化道内镜、病理学和免疫治疗是目前的研究热点。结论AI在胃癌诊治中具有广阔的应用前景,越来越多的学者致力于开展胃癌诊治的AI研究。目前,AI在胃癌的生物学、诊断、分期、疗效评估和预后预测方面得到了广泛的研究。本研究结果可为从事AI与胃癌相关研究工作的学者提供参考。

关键词：胃癌人工智能诊断治疗可视化分析文献计量学分析 VOSviewer CiteSpace

维普期刊数据库博看期刊

Collusion detector based on G-N algorithm for trust model

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2016年第4期27卷 926-935页

作者： Lin Zhang na Yin Jingwen Liu Ruchuan wang college of computer Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing 210003China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nangjing University of Posts and TelecommunicationsNangjing 210003China

In the open network environment, malicious attacks to the trust model have become increasingly serious. Compared with single node attacks, collusion attacks do more harm to the trust model. To solve this problem, a collusion detector based on the GN algorithm for the trust evaluation model is proposed in the open Internet environment. By analyzing the behavioral characteristics of collusion groups, the concept of flatting is defined and the G-N community mining algorithm is used to divide suspicious communities. On this basis, a collusion community detector method is proposed based on the breaking strength of suspicious communities. Simulation results show that the model has high recognition accuracy in identifying collusion nodes, so as to effectively defend against malicious attacks of collusion nodes.

关键词： trust model collusion detector G-N algorithm

在线全文

学校读者我要写书评

暂无评论

频繁时序模式挖掘方法综述

计算机工程与应用 2024年第17期60卷 48-61页

作者：唐增金徐贞顺苏梦瑶刘纳王振彪张文豪北方民族大学计算机科学与工程学院银川750021 北方民族大学图像图形智能处理国家民委重点实验室银川750021

频繁时序模式挖掘是指从时间序列数据中发现频繁出现的模式或规律的过程,其目的是可以帮助理解时间序列数据中的重要特征,例如周期性、趋势和异常等,有助于预测未来的发展趋势和识别异常情况等。根据近年来的频繁时序模式挖掘方法的相... 详细信息

频繁时序模式挖掘是指从时间序列数据中发现频繁出现的模式或规律的过程,其目的是可以帮助理解时间序列数据中的重要特征,例如周期性、趋势和异常等,有助于预测未来的发展趋势和识别异常情况等。根据近年来的频繁时序模式挖掘方法的相关文献调研,按照关键技术和代表性算法将其分为三类,即基于结构约束的频繁时序模式挖掘方法、基于参数约束的频繁时序模式挖掘方法和基于窗口的频繁时序模式挖掘方法。陈述了频繁时序模式挖掘方法的背景以及各方法的特点;分别介绍了三类挖掘方法的发展以及分类,并从优缺点和性能等方面对各类改进方法进行了详细的对比分析;对频繁时序模式挖掘方法进行归纳和总结,并对频繁时序模式挖掘方法的未来研究方向进行了展望。

关键词：时序数据频繁时序模式结构约束参数约束窗口数据挖掘

Accelerating Asteroidal Period and Pole Inversion from Multiple Lightcurves Using Parallel Differential Evolution and Cellinoid Shape Model

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第4期24卷 271-286页

作者： Yong-Xiong Zhang Wen-Xiu Guo Xiao-Ping Lu Hua Zheng Hai-Bin Zhao Jun Tian Wei-Lin wang School of Engineering Guangzhou College of Technology and BusinessGuangzhou 510850China School of computer science and Engineering Macao University of Science and TechnologyTaipaMacao 999078China School of Mathematics and Statistics Shaoguan UniversityShaoguan 512099China State Key Laboratory of Lunar and Planetary sciences Macao University of Science and TechnologyMacao 999078China Key Laboratory of Planetary sciences Purple Mountain ObservatoryCASNanjing 210023China

Determining asteroid properties provides valuable physical insights but inverting them from photometric lightcurves remains computationally *** paper presents a new approach that combines a simplified Cellinoid shape model with the Parallel Differential Evolution(PDE)algorithm to accelerate *** PDE algorithm is more efficient than the Differential Evolution algorithm,achieving an extraordinary speedup of 37.983 with 64 workers on multicore *** PDE algorithm accurately derives period and pole values from simulated *** analysis of real asteroid lightcurves validates the method’s reliability:in comparison with results published elsewhere,the PDE algorithm accurately recovers the rotational periods and,given adequate viewing geometries,closely matches the pole *** PDE approach converges to solutions within 20,000 iterations and under one hour,demonstrating its potential for large-scale data *** work provides a promising new tool for unveiling asteroid physical properties by overcoming key computational bottlenecks.

关键词： methods:numerical minor planets asteroids:general techniques:photometric astrom