FHSS Signals Classification by Linear Discriminant in a Multi-signal Environment

Khan, Muhammad Turyalai; Sha’ameri, Ahmad Zuri; Zabidi, Muhammad Mun'im Ahmad; Chia, Chun Choon

doi:10.1007/978-981-16-2123-9_11

Cited by 5 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FB methods are based on the identification of defining features capable of discriminating between the analyzed signals. The most used features in FB scenarios are given by instantaneous features (Yu et al, 2019), high-order statistical features (Xiao-Ming and Zhong-Zhao, 2006), wavelet features (Huang et al, 2010) and time-frequency representations (Lee et al, 2020;Khan et al, 2022). But the performance of these FB methods largely depends on empirical feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Spread spectrum modulation recognition based on phase diagram entropy

Stanescu

Digulescu

Ioana

et al. 2023

Front. Signal Process.

View full text Add to dashboard Cite

Wireless communication technologies are undergoing intensive study and are experiencing accelerated progress which leads to a large increase in the number of end-users. Because of this, the radio spectrum has become more crowded than ever. These previously mentioned aspects lead to the urgent need for more reliable and intelligent communication systems that can improve the spectrum efficiency. Specifically, modulation scheme recognition occupies a crucial position in the civil and military application, especially with the emergence of Software Defined Radio (SDR). The modulation recognition is an indispensable task while performing spectrum sensing in Cognitive Radio (CR). Spread spectrum (SS) techniques represent the foundation for the design of Cognitive Radio systems. In this work, we propose a new method of characterization of Spread spectrum modulations capable of providing relevant information for the process of recognition of this type of modulations. Using the proposed approach, results higher than 90% are obtained in the modulation classification process, thus bringing an advantage over the classical methods, whose performance is below 75%.

show abstract

Section: Introductionmentioning

confidence: 99%

Spread spectrum modulation recognition based on phase diagram entropy

Stanescu

Digulescu

Ioana

et al. 2023

Front. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Furthermore, Table VI shows the comparison of the average classification accuracy at 0 dB of SNR of the ANN-SMOTE with related works. The classification performance of the ANN-SMOTE is better than [24], [29], and [31], whereas close to [26].…”

Section: ) Case 4: Fhssmentioning

confidence: 85%

“…The correlation among variables within data in the form of mathematical expressions is known as statistical modeling [21]. Statistical classifiers include: rule-based classifier [16], distance classifier using linear discriminant (LD) function [22], [23], [24], and maximum likelihood classifier [25]. In [24], FHSS signals classification is computed by the LD method that uses the Euclidean distance-based classifier.…”

Section: Introductionmentioning

confidence: 99%

“…Statistical classifiers include: rule-based classifier [16], distance classifier using linear discriminant (LD) function [22], [23], [24], and maximum likelihood classifier [25]. In [24], FHSS signals classification is computed by the LD method that uses the Euclidean distance-based classifier. It has attained 90% probability of correct classification (PCC) at the SNR range of -1.6 to 3.5 dB in the existence of AWGN only, whereas its performance is declined to 0.9 to 12 dB with the existence of the background signal.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of FHSS Signals in a Multi-Signal Environment by Artificial Neural Network

Khan¹,

Sha’ameri²,

Zabidi³

2022

IJCDS

View full text Add to dashboard Cite

“…In [11], the principles of frequency hopping spectrum (Frequency Hopping Spread Spectrum, FHSS) method are considered. According to the principles of the FHSS method, the station at each moment transmits information only along one of the n sub-channels, regularly switching to another sub-channel.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Development of methods and models to improve the noise immunity of wireless communication channels

Knyazev

Кравченко

Lazurenko

et al. 2022

EEJET

View full text Add to dashboard Cite

It has been shown that existing methods and models for improving the noise immunity of communication channels are not capable of meeting requirements for the quality of information in mobile infocommunication systems. In addition, the compromised quality of information fails to protect it and provide the speed of information transmission and density of access channels. It has been proven that reducing the level of electromagnetic radiation is the main method of ensuring noise immunity in wireless mobile communication systems of infocommunication systems. Therefore, one way to ensure the stable interference-free operation is to reduce the level of the information signal at the receiver input to the noise level when the signal/noise ratio is equal to one. This paper reports the results of studying methods and models with correlation reception of ultra-wideband signals. It is proved that according to the level of potential noise immunity, the best indicators are shown by the model of encoding an ultra-wideband information signal by phase manipulation, followed by the coding model with opposite chips, and the code-time manipulation model. It is shown that with a large base of the signal B>300 when the intensity of the received signals is below the level of interference, reliable transmission of information is carried out with a probability of error of less than 10-6. This proves that the use of ultra-wide signal technology allows for wireless hidden transmission of information with low radiation power and a low probability of error. Thus, at a speed of 12 Mb/s, it is possible to chain the transmission of information with a probability of error less than 10-6 if there is a large signal base used, B =500‒1000.

show abstract

FHSS Signals Classification by Linear Discriminant in a Multi-signal Environment

Cited by 5 publications

References 13 publications

Spread spectrum modulation recognition based on phase diagram entropy

Spread spectrum modulation recognition based on phase diagram entropy

Classification of FHSS Signals in a Multi-Signal Environment by Artificial Neural Network

Development of methods and models to improve the noise immunity of wireless communication channels

Contact Info

Product

Resources

About