A Data Preprocessing Method for Automatic Modulation Classification Based on CNN

Zhang, Haozheng; Huang, Ming; Yang, Jingjing; Sun, Wei

doi:10.1109/lcomm.2020.3044755

Cited by 46 publications

(21 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since a large amount of complex data will be generated during the construction of high-rise buildings, NoSQL, Sybase, Oracle and other databases can be selected for data storage of the information of buildings and mechanical equipment on the construction site obtained by RFID technology in the data acquisition part [13]; At the same time, due to the non-standard data form, data conflict, data duplication and other situations in the obtained information, in order to effectively manage the construction progress and quality of high-rise buildings in the digital intelligent management platform, it is necessary to analyze and clean such complex and diverse information data. Through the statistical analysis and network analysis of such information data, the classification and standardized processing of such information can be realized [14]; The cleaned and re selected data cannot be directly applied to the intelligent management platform. It is necessary to sort out such data forms through data integration, so that the BIM model layer in the intelligent management platform can directly extract and use these data, and use these data to obtain various corresponding BIM models, so as to lay a foundation for the application and implementation of the management platform.…”

Section: B Design Of Data Acquisition and Processing Layer In Digital...mentioning

confidence: 99%

Digital Intelligent Management Platform for High-Rise Building Construction Based on BIM Technology

Deng¹,

Li²

2022

IJACSA

View full text Add to dashboard Cite

In this study, the digital intelligent management platform of high-rise building construction based on BIM technology is used for real-time monitoring and management of construction progress and quality. In the data acquisition and processing layer, construction site data is obtained through RFID technology. After processing such as cleaning and integration, it is input to the BIM model layer to dynamically generate various real-time BIM models, and these real-time BIM model information is input to the application layer to query, monitor and correct the construction progress and quality. The results are presented by the display layer. The actual application results show that the real-time BIM models generated by the platform have clear details and can realize the query, monitoring and correction functions for the construction progress of high-rise buildings, and effectively correct the construction progress according to the construction progress monitoring query results to achieve the unification with the planned progress. It can effectively realize the visual measurement of the size of each component in construction and monitor the construction quality in real time.

show abstract

Section: B Design Of Data Acquisition and Processing Layer In Digital...mentioning

confidence: 99%

Digital Intelligent Management Platform for High-Rise Building Construction Based on BIM Technology

Deng¹,

Li²

2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…In [171] the authors were able to outperform state-of-the-art work on AMR based on the well-known RadioML2016.10a dataset, by proposing a novel data preprocessing on the signal samples to improve CNN-based AMR.…”

Section: Radio Spectrum Analysismentioning

confidence: 99%

A Survey on Machine Learning-Based Performance Improvement of Wireless Networks: PHY, MAC and Network Layer

et al. 2021

View full text Add to dashboard Cite

This paper presents a systematic and comprehensive survey that reviews the latest research efforts focused on machine learning (ML) based performance improvement of wireless networks, while considering all layers of the protocol stack: PHY, MAC and network. First, the related work and paper contributions are discussed, followed by providing the necessary background on data-driven approaches and machine learning to help non-machine learning experts understand all discussed techniques. Then, a comprehensive review is presented on works employing ML-based approaches to optimize the wireless communication parameters settings to achieve improved network quality-of-service (QoS) and quality-of-experience (QoE). We first categorize these works into: radio analysis, MAC analysis and network prediction approaches, followed by subcategories within each. Finally, open challenges and broader perspectives are discussed.

show abstract

“…Yogesh et al [15] propose a constellation density matrix-based DNN algorithm to classify different orders of ASK, PSK and QAM. A data preprocessing method combined with a CNN classifier is presented in [16] to improve automatic modulation classification accuracy markedly. A detector of symbol detection and modulation classification is designed which can simultaneously recover transmitted symbols and classify modulation formats for mixed blind signals [17].…”

Section: Introductionmentioning

confidence: 99%

Probability density function based data augmentation for deep neural network automatic modulation classification with limited training data

Hao

Dang

et al. 2023

IET Communications

View full text Add to dashboard Cite

Deep neural networks (DNN) based automatic modulation classification (AMC) has achieved high accuracy performance. However, DNNs are data‐hungry models, and training such a model requires a large volume of data. Insufficient training data will cause DNN models to experience overfitting and severe performance degradation. In practical AMC tasks, training the deep model with sufficient data is challenging due to the costly data collection. To this end, a novel probability density function (PDF) based data augmentation scheme and a method to determine the required minimum sampling size for data enlargement is proposed. Compared with the known image‐based augmentation scheme, the proposed waveform‐based PDF technique has low complexity and is easy to implement. Experimental results show that the required size of the training dataset is one order of magnitude smaller than the sufficient dataset in the additive white Gaussian noise channel, and effective recognition can be achieved using around 60% of the total examples under the Rayleigh channel. Moreover, the presented scheme can expand training data under frequency and phase offsets.

show abstract

A Data Preprocessing Method for Automatic Modulation Classification Based on CNN

Cited by 46 publications

References 14 publications

Digital Intelligent Management Platform for High-Rise Building Construction Based on BIM Technology

Digital Intelligent Management Platform for High-Rise Building Construction Based on BIM Technology

A Survey on Machine Learning-Based Performance Improvement of Wireless Networks: PHY, MAC and Network Layer

Probability density function based data augmentation for deep neural network automatic modulation classification with limited training data

Contact Info

Product

Resources

About