|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | 一种基于高斯混合模型的轨迹预测算法显示文摘在智能交通控制系统、军事数字化战场、辅助驾驶系统中,实时、精确、可靠的移动对象不确定性轨迹预测具有极高的应用价值.智能轨迹预测不仅可以提供精准的基于位置的服务,而且可以提前监测和预判交通状况,进而推荐最佳路线,已经成为移动对象数据库研究的热点,亟需设计准确而高效的位置预测方法.针对现有方法的不足,提出了基于高斯混合模型的轨迹预测方法 GMTP,主要步骤包括:(1)针对复杂运动模式利用高斯混合模型建模;(2)利用高斯混合模型计算不同运动模式的概率分布,进而将轨迹数据划分为不同分量;(3)利用高斯过程回归预测移动对象最可能的运动轨迹.GMTP是高斯非线性概率统计模型,其优势在于:计算结果不仅是位置预测值,更是关于移动对象未来所有可能运动轨迹的概率分布,可以利用概率统计分布特性获得某种运动模式(如匀加速运动)下的位置预测.大量真实轨迹数据集上的实验结果表明:与相同参数设置下的高斯回归预测和卡尔曼滤波预测法相比,GMTP的预测准确性平均提高了22.2%和23.8%,预测时间平均缩减了92.7%和95.9%. | 乔少杰 金琨 韩楠 唐常杰 格桑多吉 Louis Alberto GUTIERREZ | 2015 | 软件学报2015，26，5： | 111 |
| 2 | 复杂网络大数据中重叠社区检测算法显示文摘提出一种新的面向复杂网络大数据的重叠社区检测算法DOC(detecting overlapping communities over complex network big data),时间复杂度为O(nlog2(n)),算法基于模块度聚类和图计算思想,应用新的节点和边的更新方法,利用平衡二叉树对模块度增量建立索引,基于模块度最优的思想设计一种新的重叠社区检测算法.相对于传统的重叠节点检测算法,对每个节点分析的频率大为降低,可以在较低的算法运行时间下获得较高的识别准确率.复杂网络大数据集上的算法测试结果表明:DOC算法能够有效地检测出网络重叠社区,社区识别准确率较高,在大规模LFR基准数据集上其重叠社区检测标准化互信息指标NMI最高能达到0.97,重叠节点检测指标F-score的平均值在0.91以上,且复杂网络大数据下的运行时间明显优于传统算法. | 乔少杰 韩楠 张凯峰 邹磊 王宏志 Louis Alberto GUTIERREZ | 2017 | 软件学报2017，28，3： | 47 |
| 3 | 一种基于样本空间的类别不平衡数据采样方法显示文摘不平衡数据是机器学习中普遍存在的问题并得到广泛研究,即少数类的样本数量远远小于多数类样本的数量.传统基于最小化错误率方法的不足在于:分类结果会倾向于多数类,造成少数类的精度降低,通常还存在时间复杂度较高的问题.为解决上述问题,提出一种基于样本空间分布的数据采样方法,伪负样本采样方法.伪负样本指被标记为负样本(多数类)但与正样本(少数类)有很大相关性的样本.算法主要包括3个关键步骤:1)计算正样本的空间分布中心并得到每个正样本到空间中心的平均距离;2)以同样的距离计算方法计算每个负样本到空间分布中心的距离,并与平均距离进行比较,将其距离小于平均距离的负样本标记为伪负样本;3)将伪负样本从负样本集中删除并加入到正样本集中.算法的优势在于不改变原始数据集的数量,因此不会引入噪声样本或导致潜在信息丢失;在不降低整体分类精度的情况下,提高少数类的精确度.此外,其时间复杂度较低.经过13个数据进行多角度实验,表明伪负样本采样方法具有较高的预测准确性. | 张永清 卢荣钊 乔少杰 韩楠 GUTIERREZ Louis Alberto 周激流 | 2022 | 自动化学报2022，48，10： | 8 |
| 4 | 基于前缀投影技术的大规模轨迹预测模型显示文摘智能手机、车载GPS终端、可穿戴设备产生了海量的轨迹数据,这些数据不仅描述了移动对象的历史轨迹,而且精确地反映出移动对象的运动特点.已有轨迹预测方法的不足在于:不能同时兼具预测的准确性和时效性,有效的轨迹预测受限于路网等局部空间范围,无法处理复杂、大规模位置数据.为了解决上述问题,针对海量移动对象轨迹数据,结合频繁序列模式发现的思想,提出了基于前缀投影技术的轨迹预测模型PPTP(prefix projection based trajectory prediction model),包含两个关键步骤:(1)挖掘频繁轨迹模式,构造投影数据库并递归挖掘频繁前序轨迹模式;(2)轨迹匹配,以不同频繁序列模式作为前缀增量式扩展生成频繁后序轨迹,将大于最小支持度阈值的最长连续轨迹作为结果输出.算法的优势在于:可以通过较短的频繁序列模式,增量式生成长轨迹模式;不会产生无用的候选轨迹,弥补频繁模式挖掘计算代价较高的不足.利用真实大规模轨迹数据进行多角度实验,表明PPTP轨迹预测算法具有较高的预测准确性,相对于1阶马尔可夫链预测算法,其平均预测准确率可以提升39.8%.基于所提出的轨迹预测模型,开发了一个通用的轨迹预测系统,能够可视化输出完整的轨迹路线,为用户路径规划提供辅助决策支持. | 乔少杰 韩楠 李天瑞 李荣华 李斌勇 王晓腾 Louis Alberto GUTIERREZ | 2017 | 软件学报2017，28，11： | 6 |
| 5 | 基于数据场聚类的共享单车需求预测模型显示文摘共享单车系统日益普及,积累了海量的出行轨迹数据.在共享单车系统中,用户的借车和还车行为是随机的,且受天气、时间等动态因素影响,使得共享单车调度不平衡,影响单车用户体验,并给运营商造成巨大经济损失.提出了新型基于站点聚类的共享单车需求预测算法,通过构建单车转移网络计算站点活跃度,充分考虑站点地理位置和单车转移模式因素,基于数据场聚类思想,将距离相近和用车模式相似的站点聚合到一个聚簇中,给出最佳簇中心个数求取方法.充分分析时间和天气因素对站点单车需求的影响,利用皮尔逊相关系数,从真实天气数据中选择相关性最大的天气特征,结合历史聚簇内单车需求量,将其转化为三维向量,利用多特征长短时记忆深度神经网络LSTM(long short-term memory)对向量内的特征信息进行学习和训练,以30分钟为长时间间隔,对每个聚簇内的单车需求量进行预测分析.与传统机器学习算法和当前主流方法进行对比,实验结果表明,所提单车需求模型预测性能得到显著提升. | 乔少杰 韩楠 岳昆 易玉根 黄发良 元昌安 丁鹏 Louis Alberto GUTIERREZ | 2022 | 软件学报2022，33，4： | 5 |
| 6 | Pathogenesis of glomerular haematuria显示文摘Haematuria was known as a benign hallmark of some glomerular diseases, but over the last decade, new evidences pointed its negative implications on kidney disease progression. Cytotoxic effects of oxidative stress induced by hemoglobin, heme, or iron released from red blood cells may account for the tubular injury observed in human biopsy specimens. However, the precise mechanisms responsible for haematuria remain unclear. The presence of red blood cells(RBCs) with irregular contours and shape in the urine indicates RBCs egression from the glomerular capillary into the urinary space. Therefore glomerular haematuria may be a marker of glomerular filtration barrier dysfunction or damage. In this review we describe some key issues regarding epidemiology and pathogenesis of haematuric diseases as well as their renal morphological findings. | Claudia Yuste Eduardo Gutierrez Angel Manuel Sevillano Alfonso Rubio-Navarro Juan Manuel Amaro-Villalobos Alberto Ortiz Jesus Egido Manuel Praga Juan Antonio Moreno | 2015 | World Journal of Nephrology2015，4，2： | 3 |
| 7 | Thermal bridging of graphene nanosheets via covalent molecular junctions: A non-equilibrium Green's functions-density functional tightbinding study显示文摘Despite the uniquely high thermal conductivity of graphene is well known,the exploitation of graphene into thermally conductive nanomaterials and devices is limited by the inefficiency of thermal contacts between the individual nanosheets.A fascinating yet experimentally challenging route to enhance thermal conductance at contacts between graphene nanosheets is through molecular junctions,allowing covalently connecting nanosheets,otherwise interacting only via weak Van der Waals forces.Beside the bare existence of covalent connections,the choice of molecular structures to be used as thermal junctions should be guided by their vibrational properties,in terms of phonon transfer through the molecular junction.In this paper,density functional tight-binding combined with Green's functions formalism was applied for the calculation of thermal conductance and phonon spectra of several different aliphatic and aromatic molecular junctions between graphene nanosheets.Effects of molecular junction length,conformation,and aromaticity were studied in detail and correlated with phonon tunnelling spectra.The theoretical insight provided by this work can guide future experimental studies to select suitable molecular junctions,in order to enhance the thermal transport by suppressing the interfacial thermal resistances.This is attractive for various systems,including graphene nanopapers and graphene polymer nanocomposites,as well as related devices.In a broader view,the possibility to design molecular junctions to control phonon transport currently appears as an efficient way to produce phononic devices and controlling heat management in nanostructures. | Diego Martinez Gutierrez Alessa ndro Di Pierro Alessa ndro Pecchia Leon ardo Medra no San donas Rafael Gutierrez Mar Bernal Bohayra Mortazavi Gianaurelio Cuniberti Guido Saracco Alberto Fina | 2019 | Nano Research2019，12，4： | 2 |
| 8 | 面向多维稀疏数据仓库的欺诈销售行为挖掘显示文摘分销渠道系统中,产品制造商会分配给销售额较大的分销商更多返点利润鼓励销售,而分销商之间可能会联合起来将多个分销商的销售业绩累计在其中一个分销商上,获取高额利润,这种商业欺诈行为被称为挂单或窜货.由于数据中大量正常极值点的存在,使得传统异常探测算法很难区分正常极值和由挂单导致的异常极值;另外,多维销售数据本身就存在的稀疏性导致多维数据异常探测算法无法有效运行.为了克服上述问题,将人工智能和数据库技术结合起来,提出了基于分割率的特征提取方法和基于张量重构的挂单行为挖掘算法.同时,由于分销商之间存在多种挂单行为,设计了基于挂单模式偏序格的特征提取方法来对销售数据集中存在的挂单行为进行分类.在合成数据的实验中,所提出的挂单点挖掘算法能达到65%的平均AUC值,而传统特征提取方法仅达到36%和30%的平均AUC值.在真实数据上的实验结果表明,挂单行为探测方法能区分正常销售极值和挂单行为产生的异常极值. | 郑皎凌 乔少杰 舒红平 应广华 Louis Alberto GUTIERREZ | 2020 | 软件学报2020，31，3： | 2 |
| 9 | 基于贡献度证明共识机制的去中心化联邦学习框架显示文摘在大数据背景下,保证数据可信共享是数据联邦的基本要求.区块链技术代替传统的主从架构,可以提高联邦学习(federated learning,FL)的安全性.然而,现有工作中,模型参数验证与数据持久化所产生的巨大通信成本和存储消耗,已经成为数据联邦中亟待解决的问题.针对上述问题,设计了一种高效的去中心化联邦学习框架(efficient decentralized federated learning framework,EDFL),能够降低存储开销,并显著提升FL的学习效率.首先,提出了一种基于贡献度证明(proof-of-contribution)的共识机制,使得区块生成者的选举基于历史贡献度而不采用竞争机制,从而有效发避免了挖矿过程产生的区块生成延迟,并以异步方式缓解模型参数验证中的阻塞问题;其次,提出了一种角色自适应激励算法,因为该算法基于节点的工作强度和EDFL所分配的角色,所以能够激励合法节点更积极地进行模型训练,并有效地识别出恶意节点;再者,提出一种区块链分区存储策略,使得多重局部修复编码块(local reconstruction code)可被均匀地分布到网络的各个节点上,进而降低节点的本地存储代价,并实现了较高的数据恢复效率;最后,在真实的FEMNIST数据集上,对EDFL的学习效率、存储可扩展性和安全性进行了评估.实验结果表明,EDFL在以上3个方面均优于主流的基于区块链的FL框架. | 乔少杰 林羽丰 韩楠 杨国平 李贺 袁冠 毛睿 元昌安 Louis Alberto GUTIERREZ | 2023 | 软件学报2023，34，3： | 1 |
| 10 | Cystatin C and cardiac hypertrophy in primary hypertension显示文摘 | Merche Prats Ramon Font Alfredo Bardají Cristina Gutierrez Marta Lalana Angels Vilanova Alberto Martinez-Vea | 2010 | Blood Pressure2010，，1： | 1 |
| 11 | Long-Term Results of Anterior Sphincteroplasty显示文摘 | Alberto Bravo Gutierrez M.D. Robert D. Madoff M.D. Ann C. Lowry M.D. Susan Congilosi Parker M.D. M.Sc. W. Donald Buie M.D. Nancy N. Baxter M.D. Ph.D | 2004 | Diseases of the Colon & Rectum2004，，5： | 1 |
| 12 | 情景感知驱动的移动对象多模式轨迹预测技术综述显示文摘如何利用多源异构时空数据进行准确的轨迹预测并且反映移动对象的移动特性是轨迹预测领域的核心问题.现有的大多数轨迹预测方法是长序列轨迹模式预测模型,根据历史轨迹的特点进行预测,或将当前移动对象的轨迹位置放入时空语义场景根据历史移动对象轨迹预测位置.综述当前常用的轨迹预测模型和算法,涉及不同的研究领域.首先,阐述了多模式轨迹预测的主流工作,轨迹预测的基本模型类;其次,对不同类的预测模型进行总结,包括数学统计类、机器学习类、滤波算法,以及上述领域具有代表性的算法;再次,对情景感知技术进行了介绍,描述了不同领域的学者对情景感知的定义,阐述了情景感知技术所包含的关键技术点,诸如情景感知计算、情景获取和情景推理的不同类模型,分析了情景感知的不同分类、过滤、存储和融合以及它们的实现方法等.详细介绍了情景感知驱动的轨迹预测模型技术路线及各阶段任务的工作原理.给出了情景感知技术在真实场景中的应用,包括位置推荐,兴趣点推荐等,通过与传统算法对比,分析情景感知技术在此类应用中的优劣.详细介绍了情景感知结合LSTM(long short-term memory)技术应用于行人轨迹预测领域的新方法.最后,总结了轨迹预测和情景感知研究的当前问题和未来发展趋势. | 乔少杰 吴凌淳 韩楠 黄发良 毛睿 元昌安 Louis Alberto GUTIERREZ | 2023 | 软件学报2023，34，1： | 1 |
| 13 | Variable-angle scanning fluorescence spectrometry for the simultaneous determination of three diuretic drugs显示文摘 | Francisco Garcia Sanchez Alberto Fernandez Gutierrez Carmen Cruces Blanco | 1995 | Analytica Chimica Acta1995，306，： | 1 |
| 14 | DNA methylation of multiple promoter-associated CpG islands in meningiomas: relationship with the allelic status at 1p and 22q显示文摘 | M. Josefa Bello Cinthia Ami?oso Isabel Lopez-Marin Dolores Arjona Pilar Gonzalez-Gomez M. Eva Alonso Jesus Lomas Jose M. Campos M. Elena Kusak Jesus Vaquero Alberto Isla Manuel Gutierrez Jose L. Sarasa Juan A. Rey | 2004 | Acta Neuropathologica2004，，5： | 1 |
| 15 | Temporomandibular compression due to condylar osteochondroma显示文摘 | Junquera Gutierrez LM Lopez Arranz JS | 1994 | Rev Stomatol Chir Maxillofac1994，95，1： | 1 |
| 16 | Detection of circulating tumor cells in blood of pancreatic ductal adenocarcinoma patients显示文摘Aim:Previous studies suggest that circulating tumor cells(CTC)are present at very low frequencies in blood of pancreatic cancer(PC)patients.However,no technique has proven efficient for their detection,in part due to the lack of accurate tumor markers.Here,we evaluated the potential utility of two marker candidates-Mucin 16(MUC16)and Tetraspanin 1(TSPAN1)-identified through a detailed review of the literature.Methods:To evaluate the pattern of expression of both markers in pancreatic tumor cells vs.normal blood,we used cell lines derived from pancreatic cancer patients and blood from healthy adults.Results:Antibodies against both MUC16 and TSPAN1 showed expression in three pancreatic cancer(PC)cell lines while they were absent in blood cells.To evaluate the efficiency of isolating tumor cells from blood,PC cell lines were spiked at different frequencies in blood,sequentially stained with biotin-conjugated TSPAN1 and MUC16 antibodies and a streptavidin ferrofluids,followed by immunomagnetic enrichment.The recovery of spiked TSPAN1+tumor cells was high with limited contamination by leukocytes.In contrast,no PC cells were isolated when the biotin MUC16 reagent was used because the biotin-conjugated clone did not recognize PC cells.Conclusion:The combination of MUC16,TSPAN1,and epithelial cell adhesion molecule(EpCAM)antibodies will likely increase the efficiency of capturing circulating tumor cell in blood of pancreatic ductal adenocarcinoma.To further develop a protocol for isolation of circulating tumor cell in blood of PC patients,high amounts of antibodies(5-10 mg)against EpCAM,MUC16,and TSPAN1 will be needed. | Andrea Mayado Alberto Orfao Anouk Mentink Maria Laura Gutierrez Luis Muñoz-Bellvis Leon W.M.M.Terstappen | 2020 | Cancer Drug Resistance2020，3，1： | 0 |
| 17 | 危险的诊断?基因组时代的监管改革显示文摘分子诊断正在迅速发展,但许多尚未得到外部评价。Kelly Holloway及其同事发现目前监管体系的不足,并报告了近期做出的一些改革举措。最近曝光的关于医疗器械监管失败案例主要集中在植入性器械上幕但诊断性设备也存在相应的问题,例如,2016年美国政府对总部位于硅谷的知名诊断制造商Theranos公司展开的调查行动:在政府调查发现该公司的专利诊断技术存在问题后,Theranos公司运营的病理实验室被关停。 | Kelly Holloway Fiona A Miller Alberto Gutierrez Stuart Hogarth 石琪(译) 漆洪波(审校) | 2021 | 英国医学杂志中文版2021，24，7： | 0 |
| 18 | Design and Implementation of a Rehabilitation Upper-limb Exoskeleton Robot Controlled by Cognitive and Physical Interfaces显示文摘This paper presents an upper limb exoskeleton that allows cognitive(through electromyography signals)and physical user interaction(through load cells sensors)for passive and active exercises that can activate neuroplasticity in the rehabilitation process of people who suffer from a neurological injury.For the exoskeleton to be easily accepted by patients who suffer from a neurological injury,we used the ISO9241-210:2010 as a methodology design process.As the first steps of the design process,design requirements were collected from previous usability tests and literature.Then,as a second step,a technological solution is proposed,and as a third step,the system was evaluated through performance and user testing.As part of the technological solution and to allow patient participation during the rehabilitation process,we have proposed a hybrid admittance control whose input is load cell or electromyography signals.The hybrid admittance control is intended for active therapy exercises,is easily implemented,and does not need musculoskeletal modeling to work.Furthermore,electromyography signals classification models and features were evaluated to identify the best settings for the cognitive human–robot interaction. | Arturo Gonzalez‑Mendoza Ivett Quinones‑Uriostegui Sergio Salazar‑Cruz Alberto‑Isaac Perez‑Sanpablo Ricardo Lopez‑Gutierrez Rogelio Lozano | 2022 | Journal of Bionic Engineering2022，19，5： | 0 |
| 19 | A BiLSTM cardinality estimator in complex database systems based on attention mechanism显示文摘An excellent cardinality estimation can make the query optimiser produce a good execution plan.Although there are some studies on cardinality estimation,the prediction results of existing cardinality estimators are inaccurate and the query efficiency cannot be guaranteed as well.In particular,they are difficult to accurately obtain the complex relationships between multiple tables in complex database systems.When dealing with complex queries,the existing cardinality estimators cannot achieve good results.In this study,a novel cardinality estimator is proposed.It uses the core techniques with the BiLSTM network structure and adds the attention mechanism.First,the columns involved in the query statements in the training set are sampled and compressed into bitmaps.Then,the Word2vec model is used to embed the word vectors about the query statements.Finally,the BiLSTM network and attention mechanism are employed to deal with word vectors.The proposed model takes into consideration not only the correlation between tables but also the processing of complex predicates.Extensive experiments and the evaluation of BiLSTM-Attention Cardinality Estimator(BACE)on the IMDB datasets are conducted.The results show that the deep learning model can significantly improve the quality of cardinality estimation,which is a vital role in query optimisation for complex databases. | Qiang Zhou Guoping Yang Haiquan Song Jin Guo Yadong Zhang Shengjie Wei Lulu Qu Louis Alberto Gutierrez Shaojie Qiao | 2022 | CAAI Transactions on Intelligence Technology2022，7，3： | 0 |
| 20 | 阿梅格尔巴克/哥本山显示文摘垃圾焚烧发电厂阿梅格尔巴克/哥本山位于工业区,多年来,该工业区已成为冒险者们的极限运动目的地。原始的工业设施为各种极限运动活动提供了场所,如缆绳滑水、卡丁车和攀岩等。阿梅格尔巴克/哥本山是该地区最重要的地标,其建筑亟须更新。我们提出了一种新型的垃圾焚烧发电厂,这种工厂能产生经济、环保和社会效益。 | Nanna Gyldholm M■ller Alberto Cumerlato Aleksander Wadas Alexander Codda Alexander Ejsing Alexandra Gustafsson Alina Tamosiunaite Armor Gutierrez Anders Hjortn■s Andreas Klok Pedersen Annette Jensen Ariel Wallner Ask Andersen Balaj IIulian Blake Smith Borko Nikolic Brygida Zawadzka Buster Christensen Chris Falla Chris Zhongtian Yuan Daniel Selensky Dennis Rasmussen Espen Vik Finn N■rkj■r Franck Fdida Gonzalo Castro Gül Ertekin George Abraham Helen Chen Henrick Poulsen Henrik R■mer Kania Horia Spirescu Jakob Ohm Laursen Jelena Vucic Jeppe Ecklon Ji-young Yoon Jing Xu Joanna Jakubowska Johanna Nenander Kamilla Heskje Katarzyna Siedlecka Krzysztof Marciszewski Laura W■tte Liang Wang Lise Jessen Long Zuo Maciej Zawadzki Mads Enggaard Stidsen Marcelina Kolasinska Marcos Bano Maren Allen Mathias Bank Matti N■rgaard Michael Andersen Narisara Ladawal Schr■der Niklas A.Rasch Nynne Madsen ■ssur Nols■ Pero Vukovic Richard Howis Ryohei Koike Se Hyeon Kim Simon Masson Sunming Lee Toni Mateu Xing Xiong Zoltan David Kalaszi Rasmus Hjortshoj 陈子钰(译) | 2019 | 城市环境设计2019，0，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员