Radio Access Technology characterisation through object detection
نویسندگان
چکیده
Radio Access Technology (RAT) classification and monitoring are essential for efficient coexistence of different communication systems in shared spectrum. Shared spectrum, including operation license-exempt bands, is envisioned the fifth generation wireless technology (5G) standards (e.g., 3GPP Rel. 16). In this paper, we propose a Machine Learning (ML) approach to characterise spectrum utilisation facilitate dynamic access it. Recent advances Convolutional Neural Networks (CNNs) enable us perform waveform by processing spectrograms as images. contrast other ML methods that can only provide class monitored RATs, solution recognise not RATs but also identify critical parameters such inter-frame duration, frame centre frequency, signal bandwidth using object detection feature extraction module extract features from spectrograms. We have implemented evaluated our dataset commercial transmissions, well Software-Defined (SDR) testbed environment. The scenario was WiFi LTE transmissions Our results show has an accuracy 96% captures regular user communications. It shows extracted be precise within margin 2%, detect above 94% objects under broad range transmission power levels interference conditions.
منابع مشابه
Optimal Radio Access Technology Selection Algorithm for LTE-WiFi Network
A Heterogeneous Network (HetNet) comprises of multiple Radio Access Technologies (RATs) allowing a user to associate with a specific RAT and steer to other RATs in a seamless manner. To cope up with the unprecedented growth of data traffic, mobile data can be offloaded to Wireless Fidelity (WiFi) in a Long Term Evolution (LTE) based HetNet. In this paper, an optimal RAT selection problem is con...
متن کاملOptimal radio access technology selection on heterogeneous networks
The joint management of radio resources in heterogeneous networks is considered to improve their capacity. We propose joint schemes for admission control and access technology selection with vertical handoffs. Optimal policies are found for wireless networks that support two access techniques and cover the same geographical area. In addition, the system under study also supports heterogeneous t...
متن کاملCharacterisation of Mist Generation through Cloud Chamber Technology
This paper develops understanding and appropriate techniques for characterising mist generation from super-saturated liquid-air systems. Whilst the technology for this technique originates from Wilson (1897), to date mainly a qualitative understanding of the relationship between mist characteristics and initial control conditions exists. Here, an improved design of cloud chamber, which facilita...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer Communications
سال: 2021
ISSN: ['1873-703X', '0140-3664']
DOI: https://doi.org/10.1016/j.comcom.2020.12.021