首页|Researcher from Sam Houston State University Reports Details of New Studies and Findings in the Area of Machine Learning (Identifying Tampered Radio-Frequency T ransmissions in LoRa Networks Using Machine Learning)
Researcher from Sam Houston State University Reports Details of New Studies and Findings in the Area of Machine Learning (Identifying Tampered Radio-Frequency T ransmissions in LoRa Networks Using Machine Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-New research on artificial intelligenc e is the subject of a new report. According tonews originating from Huntsville, Texas, by NewsRx correspondents, research stated, "Long-range networks,renowne d for their long-range, low-power communication capabilities, form the backbone of many Internetof Things systems, enabling efficient and reliable data transmi ssion."Financial supporters for this research include King Saud University, Riyadh, Sau di Arabia.Our news correspondents obtained a quote from the research from Sam Houston Stat e University:"However, detecting tampered frequency signals poses a considerabl e challenge due to the vulnerabilityof LoRa devices to radio-frequency interfer ence and signal manipulation, which can undermine both dataintegrity and securi ty. This paper presents an innovative method for identifying tampered radio freq uencytransmissions by employing five sophisticated anomaly detection algorithms -Local Outlier Factor, IsolationForest, Variational Autoencoder, traditional Au toencoder, and Principal Component Analysis within theframework of a LoRa-based Internet of Things network structure. The novelty of this work lies in applyingimage-based tampered frequency techniques with these algorithms, offering a new perspective on securingLoRa transmissions. We generated a dataset of over 26,0 00 images derived from real-world experimentswith both normal and manipulated f requency signals by splitting video recordings of LoRa transmissionsinto frames to thoroughly assess the performance of each algorithm."
Sam Houston State UniversityHuntsvilleTexasUnited StatesNorth and Central AmericaCybersecurityCyborgsEmerg ing TechnologiesMachine Learning
NETL
NSTL
