Semantic communication refers to a novel approach to wireless data transmission that focuses on exchanging the meaning or the underlying semantic representations of multimodal data, rather than the raw data itself. This is achieved by utilizing advanced generative AI techniques, such as semantic encoders and generators, which learn the semantic representations of the data and enable local rendering of scenes. We believe that by implementing semantic communication and semantic protocol models, we improve the efficiency of data transmission by reducing the amount of information needed to be exchanged, while still maintaining the overall meaning and context of the transmitted data, enabling seamless integration and collaboration among human and machine agents.
Our research focuses on the concept of "Collective Intelligence" in the context of wireless communication and networking technologies. We investigate the development of novel protocols, frameworks, and algorithms that facilitate efficient communication and collaboration in various applications, such as sematic communications, sensor networks, and robotic networks.
In sensor networks, our primary goal is to manage and conserve energy, particularly for continuous natural disaster monitoring systems. We aim to develop self-sustaining systems that balance energy conservation with maintained service quality. We have designed and showcased an algorithm that employs robots and drones for disaster monitoring purposes. Ultimately, our research seeks to overcome the limitations of existing wireless communication and sensor network technologies by utilizing collective intelligence, leading to innovative, efficient, and adaptable solutions for the future.