|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Deep forest显示文摘Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines,we conjecture that the success of deep neural networks owes much to three characteristics, i.e.layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand,our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation. | Zhi-Hua Zhou Ji Feng | 2019 | National Science Review2019，6，1： | 52 |
| 2 | Autonomous air combat maneuver decision using Bayesian inference and moving horizon optimization显示文摘To reach a higher level of autonomy for unmanned combat aerial vehicle(UCAV) in air combat games, this paper builds an autonomous maneuver decision system. In this system,the air combat game is regarded as a Markov process, so that the air combat situation can be effectively calculated via Bayesian inference theory. According to the situation assessment result,adaptively adjusts the weights of maneuver decision factors, which makes the objective function more reasonable and ensures the superiority situation for UCAV. As the air combat game is characterized by highly dynamic and a significant amount of uncertainty,to enhance the robustness and effectiveness of maneuver decision results, fuzzy logic is used to build the functions of four maneuver decision factors. Accuracy prediction of opponent aircraft is also essential to ensure making a good decision; therefore, a prediction model of opponent aircraft is designed based on the elementary maneuver method. Finally, the moving horizon optimization strategy is used to effectively model the whole air combat maneuver decision process. Various simulations are performed on typical scenario test and close-in dogfight, the results sufficiently demonstrate the superiority of the designed maneuver decision method. | HUANG Changqiang DONG Kangsheng HUANG Hanqiao TANG Shangqin ZHANG Zhuoran | 2018 | Journal of Systems Engineering and Electronics2018，29，1： | 49 |
| 3 | 动态规划算法的原理及应用显示文摘动态规划算法通过将待求解的问题分解成若干个相互联系的子问题,先求解子问题,然后从这些子问题的解的方法得到原问题的解;对于重复 出现的子问题.只在第一次遇到的时候对它进行求解,并把答案保存起来,让以后再次遇到时直接引用答案,不必重新求解。 | 廖慧芬 邵小兵 | 2005 | 中国科技信息2005，，21A： | 25 |
| 4 | Critical Thinking Ⅰ: Seeking Conceptual Clarity显示文摘this first paper focuses on seeking conceptual clarity;the second paper will focus on how nurses use critical thinking in clinical cases;and the third paper will focus on how advanced nurse practitioners use critical thinking to provide safe and high quality care to patients and families.We welcome nursing colleagues in China respond our paper. | ZHAN Lin LEE Shirleatha FLEMING Belinda | 2014 | 护理学报2014，21，1： | 23 |
| 5 | The necessary and sufficient conditions for returns to scale properties in generalized data envelopment analysis model显示文摘We give definitions on increasing, constant and decreasing returns to scale under thegeneralized data envelopment analysis (GDEA) model. The GDEA model possesses cone structures fordescribing evaluators' preferences toward different decision making units (DMU) and toward differentinput/output categories. The GDEA model contains many important DEA models as its subclasses.Based upon the definition, we discuss and rigorously prove the necessary and sufficient conditionsfor a DMU to have increasing, constant and decreasing returns to scale under a GDEA model, anddiscuss and clarify the differences and relationships of these conditions under different subclasses ofthe GDEA model. Furthermore, we describe a method based on a two-stage linear program to testreturns to scale properties. | 魏权龄 于刚 陆剑受 | 2002 | Science China(Technological Sciences)2002，45，5： | 21 |
| 6 | 主动性人格、自我监控与大学毕业生职业决策自我效能感的关系显示文摘为探讨主动性人格、自我监控与大学毕业生职业决策自我效能感的关系,采用主动性人格量表、职业决策自我效能感量表和自我监控量表对339名大学毕业生进行了测查。结果表明:大学毕业生在自我监控上的得分与主动性人格得分呈显著正相关;主动性人格与自我监控与职业决策自我效能感部分及五个维度均显著正相关;主动性人格和自我监控能显著预测职业决策自我效能感,其中主动性人格能够单独预测职业决策自我效能感的34%变异,自我监控对职业决策自我效能感及其4个分量表有显著预测作用,能解释2%左右的增益方差。 | 梁凤华 程肇基 | 2015 | 心理与行为研究2015，13，1： | 17 |
| 7 | Artificial intelligence in gastrointestinal endoscopy:The future is almost here显示文摘Artificial intelligence(AI) enables machines to provide unparalleled value in a myriad of industries and applications. In recent years, researchers have harnessed artificial intelligence to analyze large-volume, unstructured medical data and perform clinical tasks, such as the identification of diabetic retinopathy or the diagnosis of cutaneous malignancies. Applications of artificial intelligence techniques, specifically machine learning and more recently deep learning, are beginning to emerge in gastrointestinal endoscopy. The most promising of these efforts have been in computeraided detection and computer-aided diagnosis of colorectal polyps, with recent systems demonstrating high sensitivity and accuracy even when compared to expert human endoscopists. AI has also been utilized to identify gastrointestinal bleeding, to detect areas of inflammation, and even to diagnose certain gastrointestinal infections. Future work in the field should concentrate on creating seamless integration of AI systems with current endoscopy platforms and electronic medical records, developing training modules to teach clinicians how to use AI tools, and determining the best means for regulation and approval of new AI technology. | Muthuraman Alagappan Jeremy R Glissen Brown Yuichi Mori Tyler M Berzin | 2018 | World Journal of Gastrointestinal Endoscopy2018，10，10： | 14 |
| 8 | A novel image segmentation approach for wood plate surface defect classification through convex optimization显示文摘Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains different kinds of defects. In order to obtain complete defect images, we used convex optimization(CO) with different weights as a pretreatment method for smoothing and the Otsu segmentation method to obtain the target defect area images. Structural similarity(SSIM) results between original image and defect image were calculated to evaluate the performance of segmentation with different convex optimization weights. The geometric and intensity features of defects were extracted before constructing a classification and regression tree(CART) classifier. The average accuracy of the classifier is 94.1% with four types of defects on Xylosma congestum wood plate surface: pinhole, crack,live knot and dead knot. Experimental results showed that CO can save the edge of target defects maximally, SSIM can select the appropriate weight for CO, and the CART classifier appears to have the advantages of good adaptability and high classification accuracy. | Zhanyuan Chang Jun Cao Yizhuo Zhang | 2018 | Journal of Forestry Research2018，29，6： | 14 |
| 9 | Feature-Based Aggregation and Deep Reinforcement Learning:A Survey and Some New Implementations显示文摘In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller 'aggregate' Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement. | Dimitri P.Bertsekas | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，1： | 12 |
| 10 | A self-organizing multimodal multi-objective pigeon-inspired optimization algorithm显示文摘Multi-objective optimization algorithms have recently attracted much attention as they can solve problems involving two or more conflicting objectives effectively and efficiently. However, most existing studies focus on improving the performance of the solutions in the objective spaces. This paper proposes a novel multimodal multi-objective pigeon-inspired optimization(MMOPIO) algorithm where some mechanisms are designed for the distribution of the solutions in the decision spaces. First, MMOPIO employs an improved pigeon-inspired optimization(PIO) based on consolidation parameters for simplifying the structure of the standard PIO. Second, the self-organizing map(SOM) is combined with the improved PIO for better control of the decision spaces, and thus, contributes to building a good neighborhood relation for the improved PIO.Finally, the elite learning strategy and the special crowding distance calculation mechanisms are used to prevent premature convergence and obtain solutions with uniform distribution, respectively. We evaluate the performance of the proposed MMOPIO in comparison to five state-of-the-art multi-objective optimization algorithms on some test instances, and demonstrate the superiority of MMOPIO in solving multimodal multi-objective optimization problems. | Yi HU Jie WANG Jing LIANG Kunjie YU Hui SONG Qianqian GUO Caitong YUE Yanli WANG | 2019 | Science China(Information Sciences)2019，62，7： | 10 |
| 11 | 基于ANP和Super Decision的通信链路威胁评估排序显示文摘运用ANP(网络层次分析)方法对通信链路威胁进行评估排序,建立了ANP控制层和网络层的模型,并使用Super Decision计算极限超矩阵,得到最终目标排序。由于考虑到了评估指标的相互影响关系,ANP法比传统AHP方法更为接近实际情况。 | 胡琦 严建钢 陈琪 董浩 | 2009 | 海军航空工程学院学报2009，24，2： | 10 |
| 12 | Weapons system portfolio selection based on the contribution rate evaluation of system of systems显示文摘The weapons system portfolio selection problem arises at the equipment demonstration stage and deals with the military application requirements.Further,the contribution rate of the system is one of the important indicators to evaluate the role of a system,which can facilitate the weapons system portfolio selection.Therefore,combining the system contribution rate with system portfolio selection is the focus of this study.It also focuses on calculating the contribution rates of multiple equipment systems with various types of capabilities.The contribution rate is measured by establishing a hierarchical multi-criteria value model from three dimensions.Based on the value model,the feasible portfolios are developed under certain cost constraints and the optimal weapons system portfolios are obtained by using the classification optimization selection strategy.Finally,an illustrative example is presented to verify the feasibility of the proposed model. | DOU Yajie ZHOU Zhexuan ZHAO Danling WEI Yong | 2019 | Journal of Systems Engineering and Electronics2019，30，5： | 10 |
| 13 | Management of gastroesophageal reflux disease: Patient and physician communication challenges and shared decision making显示文摘Gastroesophageal reflux disease(GERD) is a common upper esophageal condition and typical symptoms can include heartburn and sensation of regurgitation while atypical symptoms include chronic cough, asthma, hoarseness, dyspepsia and nausea. Typically, diag-nosis is presumptive given the presence of typical and atypical symptoms and is an indication for empiric therapy. Treatment management can include lifestyle modifications and/or medication therapy with proton pump inhibitor(PPI) class being the preferred and most effective. Complete symptom resolution is not always achieved and long-term PPI therapy can put patients at risk for serious side effects and needless expense. The brain-gut connection and hypervigilance plays an important role in symptom resolution and treatment success, especially in the case of non-PPI responders. Hypervigilance is a combination of increased esophageal sensory sensitivity in combination with exaggerated threat perception surrounding esophageal symptoms. Hypervigilance requires a different approach to GERD managements, where continued PPI therapy and surgery are usually not recommended. Rather, helping physicians and patients understand the brain-gut connection can guide and improve care.Education and reassurance should be the main pillars or treatment. However, it is important not to suggest the symptoms are due to anxiety alone, this often leads to patient dissatisfaction. Patient dissatisfaction with treatment reveals the need for a more patient-centered approach to GERD management and better communication between patients and providers. Shared decision making(SDM) with the incorporation of patient-reported outcomes(PRO) promotes patient adherence and satisfaction. SDM is a joint discussion between clinician and patient in which a mutually shared solution is explored for GERD symptoms. For SDM to work the physician needs to capture patients' perceptions which may not be obtained in the standard interview. This can be done through the use of PROs which promote a dialogue with patients about their symptoms and treatment priorities in the context of the SDM patient encounter. SDM could potentially help in the management of patient expectations for GERD treatment, ultimately positively impacting their health-related quality of life. | Scott Klenzak Igor Danelisen Grace D Brannan Melissa A Holland Miranda AL van Tilburg | 2018 | World Journal of Clinical Cases2018，6，15： | 10 |
| 14 | ARIMA模型在门诊人次预测中的应用显示文摘目的 探讨ARlMA模型在门诊人次预测中的应用,阐述建模过程,建立预测模型,验证模型的适用性,为医院管理决策服务.方法 数据源于HIS集成统计与管理决策支持系统门诊报表,采集范围选自1999年~2005年逐月门诊人次数据,其中1999年~2004年各月数据用于建立时间序列模型,2005年数据用于验证所建立的模型,统计软件用SPSS13.0完成.结果 通过模型识别、参数估计、检验诊断、模型评价,建立ARIMA(1,0,1)(0,1,1)12模型,具有较高地拟和精度,全年门诊人次相对误差是6.84%,各月相对误差在-3.15%~9.80%之间.实际值都在预测的95%上下限范围之内.讨论 本研究验证了ARIMA模型适用于门诊人次预测,同时在预测门诊人次时也要考虑到数据量、就医环境、患者满意度等因素. | 杨帆 秦银河 刘丽华 | 2009 | 中华医院管理杂志2009，25，1： | 9 |
| 15 | Two New Methods for Multiattribute Decision Makings with Information Partially Known | LI Dengfeng Department of Basics, Dalian Naval Academy, Dalian 116018,Liaoning,China | 1998 | Systems Science and Systems Engineering1998，8，1： | 9 |
| 16 | Mortality outcomes of low-dose computed tomography screening for lung cancer in urban China:a decision analysis and implications for practice显示文摘Background: Mortality outcomes in trials of low-dose computed tomography(CT) screening for lung cancer are inconsistent. This study aimed to evaluate whether CT screening in urban areas of China could reduce lung cancer mortality and to investigate the factors that associate with the screening effect.Methods: A decision tree model with three scenarios(low-dose CT screening, chest X-ray screening, and no screening) was developed to compare screening results in a simulated Chinese urban cohort(100,000 smokers aged45-80 years). Data of participant characteristics were obtained from national registries and epidemiological surveys for estimating lung cancer prevalence. The selection of other tree variables such as sensitivities and specificities of low-dose CT and chest X-ray screening were based on literature research. Differences in lung cancer mortality(primary outcome), false diagnoses, and deaths due to false diagnosis were calculated. Sensitivity analyses were performed to identify the factors that associate with the screening results and to ascertain worst and optimal screening effects considering possible ranges of the variables.Results: Among the 100,000 subjects, there were 448,541, and 591 lung cancer deaths in the low-dose CT, chest X-ray, and no screening scenarios, respectively(17.2% reduction in low-dose CT screening over chest X-ray screening and 24.2% over no screening). The costs of the two screening scenarios were 9387 and 2497 false diagnoses and 7and 2 deaths due to false diagnosis among the 100,000 persons, respectively. The factors that most influenced death reduction with low-dose CT screening over no screening were lung cancer prevalence in the screened cohort, lowdose CT sensitivity, and proportion of early-stage cancers among low-dose CT detected lung cancers. Considering all possibilities, reduction in deaths(relative numbers) with low-dose CT screening in the worst and optimal cases were16(5.4%) and 288(40.2%) over no screening, respectively.Conclusions: In terms of mortality outcomes, our findings favor conducting low-dose CT screening in urban China.However, approaches to reducing false diagnoses and optimizing important screening conditions such as enrollment criteria for screening are highly needed. | Zixing Wang Wei Han Weiwei Zhang Fang Xue Yuyan Wang Yaoda Hu Lei Wang Chunwu Zhou Yao Huang Shijun Zhao Wei Song Xin Sui Ruihong Shi Jingmei Jiang | 2017 | Chinese Journal of Cancer2017，36，8： | 9 |
| 17 | Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree,random forest and information value models显示文摘This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR. | CHEN Tao ZHU Li NIU Rui-qing TRINDER C John PENG Ling LEI Tao | 2020 | Journal of Mountain Science2020，17，3： | 7 |
| 18 | 电子商务环境下企业物流配送模式选择显示文摘基于系统工程的思想,分析了电子商务环境下国内外企业物流配送模式的现状、优势和劣势,提出了企业物流配送模式选择的思路,构建了企业物流配送模式选择评价模型,建立了基于德尔菲法、层次分析法和Super Decision计算功能的系统选择方法,并对一大型电商企业进行了实证分析。研究结果为相关企业决策和政府政策导向提供了有益的启示和借鉴。 | 李存芳 杜沈悦 王维 吴琼 | 2018 | 物流技术2018，37，7： | 7 |
| 19 | Using the Method of Maximizing Deviation to Make Decision for M ultiindices显示文摘UsingtheMethodofMaximizingDeviationtoMakeDecisionforMultindicesWangYingmingDepartmentofAutomation,XiamenUniversity,361005,P.... | Wang Yingming Department of Automation, Xiamen University, 361005, P. R. China | 1997 | Journal of Systems Engineering and Electronics1997，8，3： | 7 |
| 20 | A Hybrid MCDM Approach Based on ANP and TOPSIS for Facility Layout Selection显示文摘Facility layout selection is a multi-criteria decision making (MCDM) problem,since it has a strategic impact on the efficiency of manufacturing system.In view of the interdependency among selection criteria,analytic network process (ANP) is proposed to analyze the structure of the facility layout selection problem and determine the weights for each criterion.A network structure is constructed that shows all elements and clusters and their interactions.Limit priorities are also calculated which help decision maker evaluate the relative importance among criterion in the alternative selection process.Moreover,a hybrid MCDM approach that employs ANP and technique for order preference by similarity to an ideal solution (TOPSIS)method to rank the optimal facility layout alternatives.Finally,an application of a new aeronautic component assembly workshop facility layout selection is conducted.To further illustrate the advantage of the proposed approach,the difference between ANP-TOPSIS and AHP-TOPSIS methods are compared and discussed.Results have demonstrated the effectiveness and feasibility of the proposed method. | Zha Shanshan Guo Yu Huang Shaohua Tang Pengzhou | 2018 | Transactions of Nanjing University of Aeronautics and Astronautics2018，35，6： | 7 |
您所在的机构暂未开通此部分的功能，请联系管理员