中国科学院机构知识库网格系统: 检索

Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures 期刊论文 OAI收割
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 12, 页码: 8191-8208
作者: Yang, Ziduo; Zhong, Weihe; Lv, Qiujie; Dong, Tiejun; Chen, Guanxing

|

收藏 | 浏览/下载：11/0 | 提交时间：2025/01/14

Proteins Programmable logic arrays Three-dimensional displays Predictive models Graph neural networks Data models Convolution Protein-ligand binding affinity graph neural networks inductive bias drug-target interaction structure-based virtual screening

Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data 期刊论文 OAI收割
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 11, 页码: 7136-7153
作者: Cao, Yukun; Feng, Yuan; Wang, Hairu; Xie, Xike; Zhou, S. Kevin

|

收藏 | 浏览/下载：13/0 | 提交时间：2024/12/06

sketches meta-learning Neural data structure memory-augmented neural networks memory-augmented neural networks meta-learning memory-augmented neural networks

Artificial neural network based response surface for data-driven dimensional analysis 期刊论文 OAI收割
JOURNAL OF COMPUTATIONAL PHYSICS, 2022, 卷号: 459, 页码: 19
作者: Xu, Zhaoyue; Zhang, Xinlei; Wang, Shizhao; He, Guowei; He GW(何国威)

|

收藏 | 浏览/下载：55/0 | 提交时间：2022/07/18

Artificial neural network Response surface Data-driven dimensional analysis Machine learning Fluid-structure interaction

Adaptive Slide Window-Based Feature Cognition for Deceptive Information Identification 期刊论文 OAI收割
IEEE ACCESS, 2020, 卷号: 8, 页码: 134311-134323
作者: Yang, Haolin; Xu, Zhiwei; Liu, Limin; Tian, Jie; Zhang, Yujun

|

收藏 | 浏览/下载：25/0 | 提交时间：2020/12/10

Feature extraction Semantics Adaptation models Data mining Cognition Convolutional neural networks Business Deceptive information cognition adaptive slide window semantic structure representation trivial sentence element elimination convolutional neural network

Data-driven design of the extended fuzzy neural network having linguistic outputs 期刊论文 OAI收割
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 卷号: 34, 期号: 1, 页码: 349-360
作者: Li, Chengdong; Ding, Zixiang; Qian, Dianwei; Lv, Yisheng

|

收藏 | 浏览/下载：36/0 | 提交时间：2018/10/10

Data-driven Method Fuzzy Neural Network Multi-objective Optimization Structure Reduction

Design of controlling system in multi-function durability testing device for vehicle vacuum booster with brake master cylinder (EI CONFERENCE) 会议论文 OAI收割
2012 International Conference on Mechanical and Electronic Engineering, ICMEE 2012, June 23, 2012 - June 24, 2012, Hefei, China
Hao X.; Zhang R.; Li X.; Wang M.

收藏 | 浏览/下载：38/0 | 提交时间：2013/03/25

The quality of vehicle vacuum booster with brake master cylinder is related to the safe of drivers and automobiles. The testing experiment must be executed strictly before leaving factory based on the national standards.The paper introduces the controlling system of multi-function durability testing device which is designed for doing durable testing experiments and Anti-lock braking system (ABS) performance experiments. The structure and theory of device is presented. The controlling system is illuminated in detail. To test the dynamic property this system was identified by a recursive BP neural network. According to the character of a great deal of sensors and actuators the high precision capabilities and reliability the distributed control mode (DCS) including the computer and PLC by RS-485 bus is utilized. The four channels testing experiments are achieved at the same time. The test data is directly memorized into the computer. The results of general endurance and ABS endurance testing experiments are shown to demonstrate the excellent performance of the testing device. 2012 Springer-Verlag Berlin Heidelberg.

Double inverted pendulum control based on three-loop PID and improved BP neural network (EI CONFERENCE) 会议论文 OAI收割
2011 2nd International Conference on Digital Manufacturing and Automation, ICDMA 2011, August 5, 2011 - August 7, 2011, Zhangjiajie, Hunan, China
作者: Fan Y.

收藏 | 浏览/下载：37/0 | 提交时间：2013/03/25

To deal with the defects of BP neural networks used in balance control of inverted pendulum such as longer train time and converging in partial minimum this article reaLizes the control of double inverted pendulum with improved BP algorithm of artificial neural networks(ANN) builds up a training model of test simulation and the BP network is 6-10-1 structure. Tansig function is used in hidden layer and PureLin function is used in output layer LM is used in training algorithm. The training data is acquried by three-loop PID algorithm. The model is learned and trained with Matlab calculating software and the simuLink simulation experiment results prove that improved BP algorithm for inverted pendulum control has higher precision better astringency and lower calculation. This algorithm has wide appLication on nonLinear control and robust control field in particular. 2011 IEEE.

Research on the identification for a nonlinear system (EI CONFERENCE) 会议论文 OAI收割
International Conference on Optical, Electronic Materials and Applications 2011, OEMA 2011, March 4, 2011 - March 6, 2011, Chongqing, China
作者: Liu J.; Jia P.; Liu J.; Liu J.

收藏 | 浏览/下载：32/0 | 提交时间：2013/03/25

The characteristic of the drift error of inertial platform is a high-order nonlinear dynamic system using the neural networks' abilities of universal approximation of differentiable trajectory and capturing system dynamic information this paper presents the drift error identifying project of inertial platform based on Elman networks structure. First the drift error model of inertial platform is established after selecting the input and output for network momentum and alterable speed algorithm is used to speed up the network convergence. On the basis of the algorithm the extended nonlinear node function in the hidden network does not only improve the learning speed of network but also satisfies the need of accuracy on system identification. Through the drift error data measured on inertial platform the training result shows that the scheme achieves satisfied identification results. (2011) Trans Tech Publications.

Prediction model of molten iron endpoint temperature in AOD furnace based on RBF neural network (EI CONFERENCE) 会议论文 OAI收割
2010 International Conference on Logistics Systems and Intelligent Management, ICLSIM 2010, January 9, 2010 - January 10, 2010, Harbin, China
Ma H.-T.; You W.; Chen T.

收藏 | 浏览/下载：28/0 | 提交时间：2013/03/25

According to Jilin Ferroalloy Factory 10-ton AOD furnace actual smelting condition analyzes the impact factor of AOD furnace molten iron endpoint temperature by optimizing the neural network connection weights and structure design prediction model of molten iron endpoint temperature based on RBF neural network using LM algorithm and 50 furnaces actual production data to train the model and predicts another 50 furnaces molten iron temperature Result shows that prediction model of molten iron endpoint temperature based on RBF neural network has a high accuracy when the error of endpoint temperature is 12 C hit rate of temperature is 82.4%. 2010 IEEE.

Study on color model conversion for camera with neural network based on the combination between second general revolving combination design and genetic algorithm (EI CONFERENCE) 会议论文 OAI收割
ICO20: Illumination, Radiation, and Color Technologies, August 21, 2005 - August 26, 2005, Changchun, China
作者: Li Z.; Zhou F.; Wang C.; Li Z.

收藏 | 浏览/下载：36/0 | 提交时间：2013/03/25

Munsell color system is selected to establish the mutual conversion between RGB and L*a*b* color model for camera. The color luminance meter and CCD camera synchronously measure the same color card XYZ value is gotten from the color luminance meter the training error is 0.000748566 it can show that the method combining second general revolving combination design with genetic algorithm can optimize the hidden-layer structure of neural network. Using the data of testing set to test this network and calculating the color difference between forecast value and true value the color picture captured from CCD camera is expressed for RGB value as the input of neural network and the L*a*b* value converted from XYZ value is regarded as the real color value of target card which the difference is not obvious comparing with forecast result the maximum is 5.6357 NBS namely the output of neural network. The neural network of two hidden-layers is considered the minimum is 0.5311 NBS so the second general revolving combination design is introduced into optimizing the structure of neural network and the average of color difference is 3.1744 NBS. which can carry optimization through unifying project design data processing and the precision of regression equation. Their mathematics model of encoding space is gained and the significance inspection shows the confidence degree of regression equation is 99%. The mathematics model is optimized by genetic algorithm optimization solution is gotten and function value of the goal is 0.0007168. The neural network of the optimization solution is trained