|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | 基于高斯过程建模的物联网数据不确定性度量与预测显示文摘物联网已经成为农业大数据最重要的数据源之一,自动观测数据的质量控制对农业生产分析以及基础科研数据应用非常重要。针对农业物联网观测的一类非平稳时间序列数据中的数据缺失、野值剔除、感知故障预警和长时间预测等问题,采用光滑弱假设高斯先验,构建了基于高斯过程的自回归模型表征的动态系统,并通过样本集学习,形成能考虑噪声干扰的传感变化规律建模,并可提供预测误差带用于预测数据的不确定性度量。针对原始数据的缺失和野值问题,采用基于高斯过程的短期预测,可补齐缺失数据,利用其不确定性度量可甄别数据野值,进行野值剔除与替换,并在此基础上判断感知故障;给出了基于输入数据不确定性传播的多步迭代预测方法,使长期预测仍可以跟踪农业数据的动态轨迹,并可为其预测值提供不确定性度量;将温室采集的真实传感数据用于分析试验,验证了高斯过程用于服务器端的农业时间序列数据采集质量控制的可行性。 | 苑进 胡敏 Kesheng Wang 刘雪美 侯加林 米庆华 | 2015 | 农业机械学报2015，46，5： | 15 |
| 2 | Landslide identification using machine learning显示文摘Landslide identification is critical for risk assessment and mitigation.This paper proposes a novel machinelearning and deep-learning method to identify natural-terrain landslides using integrated geodatabases.First,landslide-related data are compiled,including topographic data,geological data and rainfall-related data.Then,three integrated geodatabases are established;namely,Recent Landslide Database(Rec LD),Relict Landslide Database(Rel LD)and Joint Landslide Database(JLD).After that,five machine learning and deep learning algorithms,including logistic regression(LR),support vector machine(SVM),random forest(RF),boosting methods and convolutional neural network(CNN),are utilized and evaluated on each database.A case study in Lantau,Hong Kong,is conducted to demonstrate the application of the proposed method.From the results of the case study,CNN achieves an identification accuracy of 92.5%on Rec LD,and outperforms other algorithms due to its strengths in feature extraction and multi dimensional data processing.Boosting methods come second in terms of accuracy,followed by RF,LR and SVM.By using machine learning and deep learning techniques,the proposed landslide identification method shows outstanding robustness and great potential in tackling the landslide identification problem. | Haojie Wang Limin Zhang Kesheng Yin Hongyu Luo Jinhui Li | 2021 | Geoscience Frontiers2021，12，1： | 8 |
| 3 | A hybrid point cloud alignment method combining particle swarm optimization and iterative closest point method显示文摘 | Quan Yu Kesheng Wang | 2014 | Advances in Manufacturing2014，2，1： | 2 |
| 4 | The role of calpain in the regulation of ADAM17-dependent GPIbα ectodomain shedding显示文摘 | Zhicheng Wang Quanwei Shi Rong Yan Guanglei Liu Weilin Zhang Kesheng Dai | 2010 | Archives of Biochemistry and Biophysics2010，，2： | 1 |
| 5 | Particle swarm optimization (PSO) for the constrained portfolio opti- mization problem 显示文摘 | ZHU Hanhong WANG Yi WANG Kesheng | 2011 | Expert Systems with Applications2011，38，10： | 1 |
| 6 | Study on a new technological scheme for cold forging of spur gears 显示文摘 | Hu Chengliang Wang Kesheng Liu Quankun | 2007 | Materials processing technology2007，，187188： | 1 |
| 7 | Integrating relevance vector machines and genetic algorithms for optimization of seed-separating process 显示文摘 | Yuan Jin Wang Kesheng Yu Tao | 2007 | Engineering Applications of Ar- tificial Intelligence2007，20，7： | 1 |
| 8 | Particle Swarm Optimization(PSO)for the constrained portfolio optimization problem显示文摘 | Zhu Hanhong Wang Yi Wang Kesheng | 2011 | Expert Systems with Applications2011，38，10： | 1 |
| 9 | A hybrid intelligent method for modeling the EDM process 显示文摘 | Kesheng Wang Hirpa L Gelgele | 2003 | International Journal of Machine Tools and Manufacture2003，43，10： | 1 |
| 10 | Stu- dy on a new technological scheme for cold forging of spur gears显示文摘 | Hu Chengliang Wang Kesheng Liu Quankun | 2007 | Journal of Materials Processing Tech- nology2007，，： | 1 |
| 11 | Studyon a New Technological Scheme for Cold Forging ofSpur Gears 显示文摘 | Hu Chengliang Wang Kesheng Liu Quankun | 2007 | Journal of Materials ProcessingTechnology2007，，： | 1 |
| 12 | Using B-spline neural network to extract fuzzy rules for a centrifugal pump monitoring显示文摘 | Kesheng Wang Bing Lei | 2001 | Journal of Intelligent Manufacturing2001，，1： | 1 |
| 13 | 酒精依赖的基于基因和基于通路的全基因组关联研究(英文)显示文摘背景:信号通路中风险基因的构成可能可以解释酒精依赖风险基因协同的神经生物学作用。目的:识别酒精依赖的风险基因和风险基因通路。方法:我们采用基因富集(gene-set-rich)分析方法对酒精依赖进行了基于通路的全基因组关联分析(GWAS)。在包括1409名欧裔美国人(European-American,EA)酒精依赖者和1518名EA健康对照者的探索性样本人群中检测了近一百万个基因标志物。此外,将681名非裔美国人(African-American,AA)病例和508名AA健康受试者作为重测样本。结果:我们发现了几个与酒精依赖显著相关的可重复的全基因组风险基因和风险通路。在多重比较Bonferroni校正后,'细胞-细胞外基质相互作用'通路(EA样本中p<2.0E-4)和该通路中PXN基因(编码桩蛋白paxillin)(EA样本中p=3.9E-7)是最有可能的酒精依赖的危险因素。在EA样本(0.015≤p≤0.035)和AA样本(0.025≤p≤0.050)中还有两条富含酒精依赖相关基因的可重复的通路:'Na+/Cl-依赖性神经递质转运体'通路和'其他聚糖降解'通路。结论:一些基因和生物信号传导过程可能与酒精依赖的风险相关,本研究的发现为此提供了新的证据。 | Lingjun ZUO Clarence K.ZHANG Frederick G.SAYWARD Kei-Hoi CHEUNG Kesheng WANG John H.KRYSTAL Hongyu ZHAO Xingguang LUO | 2015 | 上海精神医学2015，27，2： | 1 |
| 14 | A Hybrid Intelligent Method for Modeling the EDM Process显示文摘 | Wang Kesheng Hirpa L G Wang Yi | 2003 | International Journal of Machine Tools & Manufacture2003，43，10： | 1 |
| 15 | A hybrid intelligent method for modeling the EDM process显示文摘 | WANG Kesheng GELGELEE H L | 2003 | International Journal of Machine Tools & Manufacture2003，43，10： | 1 |
| 16 | Fault diagnosis and prognosis using wavelet packet decomposition Fourier transform and artificial neural network显示文摘 | ZHANG Zhenyou WANG Yi WANG Kesheng | 2013 | J Intell Manuf2013，24，6： | 1 |
| 17 | Particle Swarm Optimization(PSO) for the constrained portfolio optimization problem显示文摘 | Zhu Hanhong Wang Yi Wang Kesheng | 2011 | Expert Systems with Applica- tions2011，38，10： | 1 |
| 18 | Quantity Flexibility Contract Model for Emergency Procurement Considering Supply Disruption显示文摘Supply chain disruption risk usually poses a serious challenge to the management of emergency supplies procurement between the government and enterprises in cooperation.To research the impact of supply chain disruption on the supply and demand sides of emergency supplies for disaster relief,the emergency procurement model based on quantity flexibility contract is constructed.The model introduces a stockout disruption to measure the degree of supply chain disruption and uses per unit of material relief value to quantify government disaster relief benefits.Further,it analyzes the basic pricing strategy and the agreed order quantity between the government and enterprises,focusing on the negative impact of supply disruption on the government and enterprises.The model deduction and data analysis results show that supply disruption creates a“lose-lose”situation for governments and enterprises,reducing their benefits and willingness to cooperate.Finally,a sensitivity analysis is conducted on the case data to explain the decision-making changes in the contract price and flexibility parameters between the government and enterprises before and after the supply disruption. | Bin Wu Shuangwei Bai Bijina Rajbhandari Bangyuan Li Kesheng Wang | 2023 | Complex System Modeling and Simulation2023，3，2： | 0 |
| 19 | Microwave-Absorbing Properties of La_(1-x)Sr_xMn_ (1-y)Fe_yO_3显示文摘The experiment samples of La 1-xSrxMn 1-yFeyO3(x=0.15, 0.20, 0.23; y=0.10, 0.12, 0.14, 0.16) were prepared by sol-gel process, and the loss tangent and absorption coefficient in the range of 2~18 GHz were measured by HP8722 net analyzing apparatus. It is found that changing the content of Sr or Fe would effect the microwave absorbing. When the thickness of La 1-xSrxMn 1-yFeyO3 is 2 mm and x=0.20, y=0.14, the capability of microwave absorbing is the best one. There are two absorption peaks; the maximum is 34 dB and effective band width with 10 dB and more reaches 6.2 GHz. When the frequency between 2~12.5 GHz dielectric loss is considered as the major loss from the loss angle picture. When the frequency gets to near 12.5 GHz the loss angle tangent increases or decreases suddenly. When the frequency between 12.5~18 GHz magnetic loss is be considered as the major loss. The resistivity of La 0.8Sr 0.2Mn 0.86Fe 0.14O3 at room temperature presents its semiconductor character, which is more beneficial to absorbing microwave. | Wang Da Zhou Kesheng Yin Lisong Chen Mintao Deng Jianjie | 2006 | Journal of Rare Earths2006，24，3： | 0 |
| 20 | Quantum-Inspired Distributed Memetic Algorithm显示文摘This paper proposed a novel distributed memetic evolutionary model,where four modules distributed exploration,intensified exploitation,knowledge transfer,and evolutionary restart are coevolved to maximize their strengths and achieve superior global optimality.Distributed exploration evolves three independent populations by heterogenous operators.Intensified exploitation evolves an external elite archive in parallel with exploration to balance global and local searches.Knowledge transfer is based on a point-ring communication topology to share successful experiences among distinct search agents.Evolutionary restart adopts an adaptive perturbation strategy to control search diversity reasonably.Quantum computation is a newly emerging technique,which has powerful computing power and parallelized ability.Therefore,this paper further fuses quantum mechanisms into the proposed evolutionary model to build a new evolutionary algorithm,referred to as quantum-inspired distributed memetic algorithm(QDMA).In QDMA,individuals are represented by the quantum characteristics and evolved by the quantum-inspired evolutionary optimizers in the quantum hyperspace.The QDMA integrates the superiorities of distributed,memetic,and quantum evolution.Computational experiments are carried out to evaluate the superior performance of QDMA.The results demonstrate the effectiveness of special designs and show that QDMA has greater superiority compared to the compared state-of-the-art algorithms based on Wilcoxon’s rank-sum test.The superiority is attributed not only to good cooperative coevolution of distributed memetic evolutionary model,but also to superior designs of each special component. | Guanghui Zhang Wenjing Ma Keyi Xing Lining Xing Kesheng Wang | 2022 | Complex System Modeling and Simulation2022，2，4： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员