@inproceedings{46abbf08b43d436cbec9e979add65cd7,
title = "Deep Learning-Based QoS Prediction for Optimization of Robotic Communication",
abstract = "The robustness of quality of service (QoS) in robotic communications is essential for operational efficiency and reliability. This paper presents an innovative deep learningbased methodology specifically designed for QoS prediction in robotic networks. A predictive model was developed by extensively analyzing communication data, including aspects such as latency and bandwidth, along with environmental factors. This model accurately predicts important QoS parameters. The results show a significant improvement in QoS prediction accuracy and overall network performance over traditional machine learning methods. The implications of this study are important for the development of autonomous robot operations and provide scalable and efficient solutions for realtime communication coordination that are pivotal to managing the complexity of adaptive robot systems.",
keywords = "adaptive systems, Attention, autonomous robots, CNN, GNN, LSTM, predictive modeling, QoS, robotic communication",
author = "Kim, {Tae Hyun} and Lee, {Jong Hyuk} and Lee, {Jin Hyuk} and Kim, {Min Young}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024 ; Conference date: 19-02-2024 Through 22-02-2024",
year = "2024",
doi = "10.1109/ICAIIC60209.2024.10463315",
language = "English",
series = "6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "301--306",
booktitle = "6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024",
address = "United States",
}