The proceedings contain 31 papers. The topics discussed include: enhanced monitoring using PCA-based GLR fault detection and multiscale filtering;a robust fault detection scheme with an application to mobile robots by...
ISBN:
(纸本)9781467358934
The proceedings contain 31 papers. The topics discussed include: enhanced monitoring using PCA-based GLR fault detection and multiscale filtering;a robust fault detection scheme with an application to mobile robots by using adaptive thresholds generated with locally linear models;fault diagnosis of induction motor using CWT and rough-set theory;a new eye gaze detection algorithm using PCA features and recurrent neural networks;path planning of a data mule in wireless sensor network using an improved implementation of clustering-based genetic algorithm;study on a combined scheme by using T-S fuzzy and TSMC approaches;robust output feedback control of T-S fuzzy time-delay systems;and optimization of fuzzy logic controllers with rule base size reduction using genetic algorithms.
The proceedings contain 25 papers. The topics discussed include: intelligent PD-type fuzzy controller design for mobile satellite antenna tracking system with parameter variations effect;L-infinity analysis of Hopfiel...
ISBN:
(纸本)9781424499038
The proceedings contain 25 papers. The topics discussed include: intelligent PD-type fuzzy controller design for mobile satellite antenna tracking system with parameter variations effect;L-infinity analysis of Hopfield networks;optimization of model predictive control by means of sequential parameter optimization;fuzzy adaptive control for a class of nonlinear systems with unknown control gain;on control-specific derivation of affine Takagi-Sugeno models from physical models: assessment criteria and modeling procedure;nonlinear modeling of an aerobic wastewater treatment process using Laguerre-based fuzzy system;decentralized direct I-term fuzzy-neural control of an anaerobic digestion bioprocess plant;a novel training method based on variable structure systems theory for fuzzy neural networks;generalized H2 filter design for T-S fuzzy systems with quantization and packet loss;and power system stabilizer tuning study of east-central power system in Saudi Arabia.
The proceedings contain 32 papers. The topics discussed include: extreme learning ANFIS for control applications;collaborative fuzzy rule learning for Mamdani type fuzzy inference system with mapping of cluster center...
ISBN:
(纸本)9781479945313
The proceedings contain 32 papers. The topics discussed include: extreme learning ANFIS for control applications;collaborative fuzzy rule learning for Mamdani type fuzzy inference system with mapping of cluster centers;real-time nonlinear modeling of a twin rotor MIMO system using evolving neuro-fuzzy network;adaptive dynamic output feedback control of Takagi-Sugeno fuzzy systems with immeasurable premise variables and disturbance;optimal robust control for generalized fuzzy dynamical systems: a novel use on fuzzy uncertainties;quadrotor control using dynamic feedback linearization based on piecewise bilinear models;ultra high frequency polynomial and sine artificial higher order neural networks for control signal generator;dissolved oxygen control of activated sludge biorectors using neural-adaptive control;and cascaded free search differential evolution applied to nonlinear system identification based on correlation functions and neural networks.
The proceedings contain 20 papers. The topics discussed include: tutorial CICA-T: computing with intelligence for identification and control of nonlinear systems;orthogonal-type robot with a CAD/CAM-based position/for...
ISBN:
(纸本)9781424427529
The proceedings contain 20 papers. The topics discussed include: tutorial CICA-T: computing with intelligence for identification and control of nonlinear systems;orthogonal-type robot with a CAD/CAM-based position/force controller;modeling and control of a nonholonomic wheeled mobile robot with wheel slip dynamics;adaptive robot manipulator control based on plant-controller model reference using soft computing and performance index analyzer;influencing customers through customers - simulation of herd behavior in supermarkets;redundancy approach for fuzzy Lyapunov stabilization of Takagi-Sugeno descriptors;effect of weighting parameters on dynamical behavior of Hopfield neural networks with logistic map activation functions;learning functions generated by randomly initialized MLPs and SRNs;and fuzzy differential inclusion in neural modeling.
The purpose of 2011 ieee symposium on computational intelligence in control and automation is to bring together researchers, engineers, practitioners, and students from around the world to discuss the latest advances ...
详细信息
The purpose of 2011 ieee symposium on computational intelligence in control and automation is to bring together researchers, engineers, practitioners, and students from around the world to discuss the latest advances in the theory and application of computationalintelligence in control and automation. It is very glad to see the symposium has received many new research results from various topics and applications of computationalintelligence in control and automation, including new theories and methods of model based fuzzy systems and control, CI based predictive and adaptive control, neural networks and evolutionary computation for system learning and control, decision analysis and support systems, with applications ranging from robots, energy systems, industrial automations, wastewater treatment process, secure communication system, to human behaviors modeling.
Traditional cognitive travel modeling typically employs a unified cognitive model to simulate representative travel behaviors, which may usually result in a weak characterization of user heterogeneity in paths, modes,...
详细信息
Traditional cognitive travel modeling typically employs a unified cognitive model to simulate representative travel behaviors, which may usually result in a weak characterization of user heterogeneity in paths, modes, and other factors. Large language model (LLM), by contrast, has significantly enhanced the anthropomorphic and personalized features of intelligent systems. To integrate their advantages, this article proposes LLM-driven cognitive modeling to generate more diverse and personalized travel demands. The new method sufficiently exploits LLM such as the llama as a basis and provides personalized travel plans so that more heterogenous travel demands could be generated. Additionally, introducing LLM into cognitive modeling can significantly reduce the time of model development, thus accelerating the research or engineering deployment. By calibrating and testing with one month's data from public transportation (buses and subways) in Beijing, our method, compared to traditional cognitive models, not only achieves better accuracy in reproducing typical travel patterns, but also generates more diverse ones, providing a more comprehensive input for computational experiments on traffic management and control strategies.
computational knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief...
详细信息
computational knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.
作者:
Huang, WenjunCui, YunduanLi, HuiyunWu, XinyuUniv Chinese Acad Sci
Sch Artificial Intelligence Beijing 101408 Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol Guangdong Hong Kong Macao Joint Lab Human Machine Shenzhen 518055 Guangdong Peoples R China
Gaussian process (GP) offers a robust solution for modeling the dynamics of unmanned surface vehicles (USV) in model-based reinforcement learning (MBRL). However, the rapidly increasing computational complexity with a...
详细信息
Gaussian process (GP) offers a robust solution for modeling the dynamics of unmanned surface vehicles (USV) in model-based reinforcement learning (MBRL). However, the rapidly increasing computational complexity with a large sample capacity of GP limits its application in complex scenarios that require substantial samples to cover the state space. In this article, a novel probabilistic MBRL approach, probabilistic neural networks model predictive control (PNMPC) is proposed to tackle this issue. With an iterative learning framework, PNMPC properly models the USV dynamics using neural networks from a probabilistic perspective to avoid the computational complexity associated with sample capacity. Employing this model to effectively propagate system uncertainties, a model predictive control (MPC) policy is developed to robustly control the USV against external disturbances. Evaluated by position-keeping and multiple targets-tracking scenarios on a real USV data-driven simulation, the proposed method consistently demonstrates its significant superiority in both model accuracy and control performance compared to not only GP model-based approaches but also the probabilistic neural networks-based MBRL baselines, across various scales of external disturbances.
In this paper, the skewed output noise is considered and we propose a lightweight robust algorithm for nonlinear state-space system identification based on the generalized hyperbolic variance gamma (GHVG) distribution...
详细信息
In this paper, the skewed output noise is considered and we propose a lightweight robust algorithm for nonlinear state-space system identification based on the generalized hyperbolic variance gamma (GHVG) distribution, which enhances the robustness of the proposed algorithm. To facilitate the realization of the proposed algorithm, the hidden variables are introduced to decompose the GHVG distribution into the Gaussian gamma mixture (GGM) distribution, which improves the computational efficiency of the proposed algorithm. The expectation maximization (EM) and the particle smoothing (PS) approaches are combined to solve the hidden variables and unknown states problems, which contributes to derive the estimation formulas of the model parameters and noise parameters simultaneously. To further reduce the computational burden of PS method for estimating the nonlinear states, a novel nearest neighbor idea is used in the identification process which ensures the performance of the proposed algorithm while reducing the number of particles involved in the calculation of the cost function. Finally, the verification results are fairly carried out to demonstrate the effectiveness of the proposed algorithm.
暂无评论