Results 51 to 60 of about 10,964,931 (140)

Specialized Deep Residual Policy Reinforcement Learning Framework for Safe and Adaptive Continuous Control

IET Control Theory &Applications, Volume 20, Issue 1, January/December 2026.
This article presents a novel hybrid control framework that combines conventional controllers with deep reinforcement learning (DRL) to enhance safety and adaptability in safety‐critical continuous control tasks. By integrating residual policy learning, a cycle of learning strategy using expert trajectories, and a specialized DRL agent with an input ...
Ammar N. Abbas, Georgios C. Chasparis, John D. Kelleher   +2 more
wiley   +1 more source

Transition‐Aware Q‐Learning for Robust Tracking in Networked Control Systems with Fading Channels: Application to Leader−Follower Vehicle Control

IET Control Theory &Applications, Volume 20, Issue 1, January/December 2026.
Maintaining reliable tracking control in networked control systems over fading wireless channels is difficult due to the stochastic and time‐correlated nature of wireless links. This work proposes a transition‐aware Q‐learning (TA‐QL) method that learns robust control policies directly from networked data without requiring explicit models, while ...
Ehsan Badfar, Babak Tavassoli
wiley   +1 more source

Non-identifiability of the two state Markovian Arrival process [PDF]

In this paper we consider the problem of identifiability of the two-state Markovian Arrival process (MAP2). In particular, we show that the MAP2 is not identifiable and conditions are given under which two different sets of parameters, induce identical ...
Michael P. Wiper, Rosa E. Lillo, Pepa Ramirez   +2 more
core  

Dual‐Path Control With Data‐Driven Latent Residual Modelling for Nonlinear Systems

IET Control Theory &Applications, Volume 20, Issue 1, January/December 2026.
This paper presents a unified dual‐path control framework that combines a nominal primary controller with a data‐driven latent residual model to handle nonlinearities, disturbances, delays, and parameter uncertainties. The real‐nominal mismatch is represented in latent coordinates and compensated by a secondary controller implemented as latent‐space ...
Zenghui Wang, Lin Meng, Shijian Cang, Jigang Tong, Yanxia Sun   +4 more
wiley   +1 more source

On identifiability of MAP processes [PDF]

Two types of transitions can be found in the Markovian Arrival process or MAP: with and without arrivals. In transient transitions the chain jumps from one state to another with no arrival; in effective transitions, a single arrival occurs.
Michael P. Wiper, Rosa E. Lillo, Pepa Ramirez   +2 more
core  

Defect Repair of Murals Guided by Fusion Structural and Textural Feature

IET Image Processing, Volume 20, Issue 1, January/December 2026.
ABSTRACT To address the challenge of insufficient restoration accuracy for large‐area damaged murals, this paper proposes a two‐stage generative adversarial network model based on Fourier convolution, employing a progressive coarse‐to‐fine restoration strategy. In the coarse restoration stage, the Fourier convolution module endows the network with high‐
Guangya Li, Xiaoliang Li, Zhilin Meng
wiley   +1 more source

Modeling and Predicting the Spatiotemporal Dynamics of Construction Waste Hauling Trucks Using an Input–Output Hidden Markov Approach

Journal of Advanced Transportation, Volume 2026, Issue 1, 2026.
Construction waste hauling (CWH) trucks are a significant source of air pollution and particulate emissions in urban environments, prompting strict regulatory controls and monitoring. Accurate prediction of their transportation activities, including destinations and arrival times, is critical for improving environmental management and regulatory ...
Xiang Liu, Boyi Lei, Hongtai Yang, Ke Han, Lee D. Han, Young-Jin Cha   +5 more
wiley   +1 more source

Batch process monitoring using an assumption-free modeling methodology [PDF]

, 2022
openAn assumption-free model is developed for the monitoring of batch processes. The model is based on variable-wise unfolded multy-way principal component analysis (MPCA) and avoids the problem of batch alignment, which is necessary in the case of a ...
FRACASSETTO, ALICE
core  

Some descriptors of the Markovian arrival process

, 1991
The Markovian Arrival Process (MAP) is a tractable, versatile class of Markov renewal processes which has been extensively used to model arrival (or service) processes in queues.
Narayana, Surya, 1962-
core   +4 more sources

EIGENVALUE EXPRESSION FOR A BATCH MARKOVIAN ARRIVAL PROCESS [PDF]

, 1995
Consider a batch Markovian arrival process (BMAP) as the counting process of an underlying Markov process representing the state of environment. Such a process is useful for representing correlated inputs for example.
Shoichi Nishimura, Hajime Sat
core