CAJ | 학술논문

随着移动互联网与物联网的迅猛发展，个人无线设备的数量呈现指数级增长，随之产生的海量频谱数据与日俱增，频谱大数据的存在已成事实。同时，频谱赤字也日益严峻。为提高频谱利用率，有效的频谱大数据处理显得十分重要。本文从无线通信的角度，首先给出了频谱大数据的定义并分析了它的基本特征；然后总结了一些对于频谱大数据分析与利用颇具前景的机器学习方法，如分布式和并行式学习、极速学习、核学习、深度学习、强化学习、博弈学习和迁移学习；最后给出了几个开放性话题和研究趋势。
수착이동호련망여물련망적신맹발전，개인무선설비적수량정현지수급증장，수지산생적해량빈보수거여일구증，빈보대수거적존재이성사실。동시，빈보적자야일익엄준。위제고빈보이용솔，유효적빈보대수거처리현득십분중요。본문종무선통신적각도，수선급출료빈보대수거적정의병분석료타적기본특정；연후총결료일사대우빈보대수거분석여이용파구전경적궤기학습방법，여분포식화병행식학습、겁속학습、핵학습、심도학습、강화학습、박혁학습화천이학습；최후급출료궤개개방성화제화연구추세。
With the rapid development of the mobile Internet and the Internet of Things ,the number of personal wireless devices has grown exponentially ,resulting in the increase of massive spectrum data . Therefore ,the big spectrum data are literally formed .Meanwhile ,the spectrum deficit is also increasing‐ly precarious .Effective big spectrum data processing is significant in improving the spectrum utilization . Firstly ,from a perspective of wireless communication ,a definition of big spectrum data is presented and its characteristics are also analyzed .Then ,promising machine learning methods to analyze and utilize the big spectrum data are summarized ,such as ,the distributed and parallel learning ,extreme learning ma‐chine ,kernel‐based learning ,deep learning ,reinforcement learning ,game learning ,and transfer learn‐ing .Finally ,several open issues and research trends are addressed .