TY - GEN
T1 - Generative Artificial Intelligence for Wireless Communications
T2 - 8th International Conference on Wireless Communications, Networking and Applications, WCNA 2024
AU - Chui, Kwok Tai
AU - Cheung, Simon K.S.
AU - Liu, Jiaqi
AU - Ng, Kwan Keung
N1 - Publisher Copyright:
© The Author(s) 2026.
PY - 2026
Y1 - 2026
N2 - Generative models have been immersed in various artificial intelligence applications. This field of research is also known as generative artificial intelligence (GenAI). Any form of data (e.g., videos, images, audio, text, and time-series data) can be generated, providing additional and useful data to enhance the performance of machine learning models. GenAI features the ability to address various issues, such as rare event collection, high cost of data labelling, bias mitigation, privacy, and data scarcity. Wireless communications have become a vital part of today’s digital era, offering flexibility, accessibility, ease of maintenance, and cost-effectiveness. Smartphones, tablets, notebooks, and smartwatches are common tools that rely on wireless communications. In this research, we conducted a literature review to analyze the 1180 latest relevant works (published in 2015–2024) employing GenAI for wireless communications. The algorithms, applications, and results were discussed and compared. The analysis focused on fundamental characteristics such as the yearly publication count, the various subject areas of these publications, the leading ten journals and conferences, as well as a visual representation of keywords in a word cloud. This was succeeded by a thorough examination of the ten most frequently cited publications. Additionally, two significant open challenges were highlighted, along with recommendations for possible future research avenues.
AB - Generative models have been immersed in various artificial intelligence applications. This field of research is also known as generative artificial intelligence (GenAI). Any form of data (e.g., videos, images, audio, text, and time-series data) can be generated, providing additional and useful data to enhance the performance of machine learning models. GenAI features the ability to address various issues, such as rare event collection, high cost of data labelling, bias mitigation, privacy, and data scarcity. Wireless communications have become a vital part of today’s digital era, offering flexibility, accessibility, ease of maintenance, and cost-effectiveness. Smartphones, tablets, notebooks, and smartwatches are common tools that rely on wireless communications. In this research, we conducted a literature review to analyze the 1180 latest relevant works (published in 2015–2024) employing GenAI for wireless communications. The algorithms, applications, and results were discussed and compared. The analysis focused on fundamental characteristics such as the yearly publication count, the various subject areas of these publications, the leading ten journals and conferences, as well as a visual representation of keywords in a word cloud. This was succeeded by a thorough examination of the ten most frequently cited publications. Additionally, two significant open challenges were highlighted, along with recommendations for possible future research avenues.
KW - Data Augmentation Algorithms
KW - Data Generation Algorithms
KW - Generative Adversarial Networks
KW - Generative Artificial Intelligence
KW - Wireless Communications
UR - https://www.scopus.com/pages/publications/105031909185
U2 - 10.1007/978-981-95-6946-5_1
DO - 10.1007/978-981-95-6946-5_1
M3 - Conference contribution
AN - SCOPUS:105031909185
SN - 9789819569458
T3 - Lecture Notes in Electrical Engineering
SP - 1
EP - 13
BT - Proceedings of the 2024 International Conference on Wireless Communications, Networking and Applications
A2 - Siarry, Patrick
A2 - Cheung, Simon King Sing
A2 - Jabbar, M.A.
A2 - Li, Xiaolong
Y2 - 20 December 2024 through 22 December 2024
ER -