Auction-Driven Spectrum Allocation With AutoEncoder-Based Compression in Rural Wireless Networks: A Novel Framework for Reliable Telemedicine

Rural healthcare faces numerous challenges, including limited access to specialized medical services and diagnostic equipment, which delays patient care. Enhancing the ability to transmit medical images and data from rural areas to urban hospitals via wireless networks is critical. However, bandwidth limitations, unreliable networks, and concerns over data security and privacy hinder efficient transmission. Additionally, the high data volume of medical content and the limited battery life of IoT devices pose further challenges. To address these challenges, data compression techniques such as Autoencoders (AEs) offer promising solutions by significantly reducing the communication overhead without sacrificing essential image quality or details. Additionally, spectrum allocation mechanisms in rural areas are often inefficient, leading to poor resource utilization. Auction theory presents a dynamic and adaptive approach to optimize spectrum allocation. This paper proposes a novel hybrid framework that integrates AE-based data compression with auction-based spectrum allocation, addressing both communication efficiency and spectrum utilization in rural wireless networks. Extensive simulations validate the framework's ability to improve spectrum utilization, transmission efficiency, and overall connectivity, offering a practical solution for enhancing rural telemedicine infrastructure. Accepted at 1st International Conference on Cyber Security and Artificial Intelligence Applications (I2CSAI 2025), Algeria