Neural Networks and Random Forests: A Comparison Regarding Prediction of Propagation Path Loss for NB-IoT Networks

被引：18

作者：

Sotiroudis, Sotirios P. ^{[1
]}

Goudos, Sotirios K. ^{[1
]}

Siakavara, Katherine ^{[1
]}

机构：

[1] Aristotle Univ Thessaloniki, Phys Dept, Radiocommun Lab, Thessaloniki, Greece

来源：

2019 8TH INTERNATIONAL CONFERENCE ON MODERN CIRCUITS AND SYSTEMS TECHNOLOGIES (MOCAST) | 2019年

关键词：

artificial neural networks; random forests; path loss prediction; radio propagation;

D O I：

10.1109/mocast.2019.8741751

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The prediction of propagation path loss is of great importance for all aspects of mobile communication. Machine learning methods, such as Artificial Neural Networks and Random Forests, can play a key role for its estimation. A comparison between the two methods for the frequencies of 900 MHz and 1800 MHz is being carried out in the work at hand. Both methods led to similar results.

引用

页数：4

共 13 条

[1]

Breiman L., MACH LEARN, DOI [10.1023/A:10109334043242001, DOI 10.1023/A:10109334043242001]

[2] A Signal Strength Fluctuation Prediction Model Based on the Random Forest Algorithm [J].

Dohnalek, P. ;

Dvorsky, M. ;

Gajdos, P. ;

Michalek, L. ;

Sebesta, R. ;

Voznak, M. .

ELEKTRONIKA IR ELEKTROTECHNIKA, 2014, 20 (05) :123-126

[3]

EDX Wireless, 1996, EDX WIR MICR MOD REF

[4]

Hastie T., 2009, Springer Series in Statistics, DOI DOI 10.1007/B94608

[5]

Haykin S., 1999, Neural Networks: A Comprehensive Foundation

[6]

Imtiaz S., 2018, J WIRELESS COM NETWO, V2018, P142

[7]

Imtiaz S, 2018, IEEE WIREL COMMUNN, P326, DOI 10.1109/WCNCW.2018.8369028

[8]

Melin L., 1993, IEEE 43 VEH TECHN C

[9] Path loss prediction in urban environment using learning machines and dimensionality reduction techniques [J].

Piacentini M. ;

Rinaldi F. .

Computational Management Science, 2011, 8 (4) :371-385

[10]

Popescu I., 2005, P IEEE INT WIRELESS, V1, P44

← 1 2 →