LinkedPrime
Jobs

Articles by Frontiers of Information Technology & Electronic Engineering

5 articles found

A digital simulation platform with human-interactive immersive design for navigation, motion, and teleoperated manipulation of work-class remotely operated vehicle

Underwater tests of work-class remotely operated vehicles (ROVs) face huge difficulties, high equipment costs, and time-consuming processes. Digital simulation of the full operation of ROVs has become an economically feasible way for algorithm pretesting and operator training before actual underwater tasks. However, existing digital simulation platforms often lack comprehensive designs that simultaneously consider ROV navigation, motion control, and manipulator teleoperation, and fail to provide immersive feedback for operators, which limits their effectiveness in training and algorithm...

FedMcon: an adaptive aggregation method for federated learning via meta controller

Federated learning has emerged as a novel machine learning setting that enables collaborative training of deep models on decentralized clients while ensuring data privacy. However, the vanilla federated averaging algorithm (FedAvg) faces significant challenges when dealing with heterogeneous and unknown client data distributions. Its weighted linear combination-based aggregation approach often fails to address the varied dynamics of different scenarios, settings, and data distributions in federated learning, leading to slow convergence and compromised generalization performance.

A unified shared control architecture for underwater vehicle-manipulator systems using task priority

Underwater vehicle-manipulator systems (UVMSs) face great challenges in autonomous operation in unstructured underwater environments. Relying solely on teleoperation for both underwater vehicles and underwater manipulators imposes significant cognitive and physical burdens on operators, making it difficult to sustain during long-term tasks. Although some fully autonomous or semi-autonomous UVMSs have been developed, fully automated control is still inadequate for complex and delicate operations in open and unstructured underwater environments, and human intervention remains necessary.

Enhanced Hippopotamus Optimization Algorithm for Tuning Proportional-Integral-Derivative Controllers

In control engineering, effectively tuning the parameters of proportional-integral-derivative (PID) controllers has long been a persistent challenge. Traditional tuning methods and existing intelligent algorithms often face issues such as slow convergence, susceptibility to local optima, and insufficient optimization accuracy, which limit their performance in complex control systems.

Building accurate translation-tailored large language models with language-aware instruction tuning

Large language models exhibit remarkable capabilities in various natural language processing tasks such as machine translation, but the large number of parameters leads to significant inference costs. Previous studies have tried to train moderately sized translation-tailored large language models by fine-tuning on translation data, yet when dealing with zero-shot translation directions not present in the fine-tuning data, these models often ignore instructions and produce off-target translations in the wrong language, a problem that remains unsolved.