Performance improvement for machine learning‐based cooperative spectrum sensing by feature vector selection

Wu, Wen; Li, Zan; Ma, Shuai; Shi, Jia

doi:10.1049/iet-com.2019.0579

Cited by 9 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…be the eigenvalue of R and 12 , ,..., m a a a be the corresponding eigenvector [16], a set of principal components can be obtained with:  is called the cumulative contribution rate of the first K principal components. When it is ≥85%, it is enough to extract the first K principal components, and the next MK − principal components can be ignored.…”

Section: Coordinated Development Of Civic Education and Student Manag...mentioning

confidence: 99%

Coordinated Development of Civic Education and Student Management in Colleges and Universities Incorporating Principal Component Analysis Approach

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper observes the relationship between variables that cannot be explained through the structure of variable explanatory variance-covariance and explores the method of applying the theoretical model of principal component analysis and factor analysis by using the method of hypothesis. After studying the scope of application of the principal component analysis method and factor analysis method, both of which can be used in the general model of comprehensive evaluation of variables, the scientific management approach of planned behavior for student management in the classroom of college and university civic education is proposed. By empirically analyzing the Civics learning management and education evaluation of students and teachers in L colleges and universities, the experimental results show that the cumulative contribution rate of the three principal components, namely, high moral character, perfect personality and good communication, is 87.4% as the main observed variables. In the cluster analysis of the Civics performance, the best Civics performance was found in the category 2 and category 1 students in college L, with a total of 9 students conforming to it. The four principal component factors of the first-ranked teachers did not differ much, respectively 1.6485, 0.4653, 1.7463, −0.645, except for the teacher numbered 1, who had a big difference in the ranking place under the two evaluation methods, and the rest of the teachers did not have any difference, and on the whole, the quality of Civic and Political education in College L was better, and the harmonization with the student management was good.

show abstract

Section: Coordinated Development Of Civic Education and Student Manag...mentioning

confidence: 99%

Coordinated Development of Civic Education and Student Management in Colleges and Universities Incorporating Principal Component Analysis Approach

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…One limitation of the segmentation-based approach is that it faces challenges in accurately determining the optimal sub-segmentation based on probability values, potentially affecting the overall performance and accuracy of the spectrum sensing process. The authors of [24] proposed a CSS framework and explored different feature vector combinations with supervised machine learning methods. The disadvantage of the approach is that it does not provide a comprehensive analysis of the drawbacks or limitations of the proposed CSS framework, such as potential challenges in real-world implementation, scalability, or robustness to varying network conditions.…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, this method may not be effective in poor signal conditions and fewer user scenarios compared to energy detectorbased methods. Another research paper, [24], proposed a cognitive radio performance fuzzy logic and Naïve bayes classifier for detection in the vehicle Ad-hoc network (VANET) platform, achieving a detection rate of 0.5 and a probability of false alarm set at 0.1.…”

Section: Training Duration For Different Classifiersmentioning

confidence: 99%

Optimizing Spectrum Sensing in Cognitive Radio Networks Using Bayesian-Optimized Random Forest Classifier

2023

IJIES

View full text Add to dashboard Cite

Achieving high spectral efficiency is a fundamental objective in cognitive radio (CR) networks, where fast and precise spectrum sensing plays a vital role. The cognitive radios rely on spectrum sensing to detect available frequencies, identify idle channels, and utilize them for transmitting data. A new approach to spectrum sensing (SS) is presented in this study, using a machine learning-based model. The model leverages different techniques for feature extraction and separates redundant and non-redundant features to enhance detection performance and reduce training overhead. A hybrid approach is introduced, combining energy, MME, and cyclostationary features extracted from sample data with NCA. The selected features are then trained with a Bayesian-optimized random forest classifier (RF) as a machine learning model. The proposed algorithms are evaluated in terms of average training time, classification speed, and accuracy. The experimental results demonstrate that the proposed bayesian-optimized random forest classifier (RF) achieved a probability of detection of 0.94.

show abstract

“…Substituting equations ( 18), ( 19), ( 22), (23), and (24) into equation (26), the detailed expression for the missed detection probability is obtained in…”

Section: Theory Performance Of the Algorithmmentioning

confidence: 99%

“…Utilizing kennel functionbased support vector machine (SVM), a spectrum mapping scheme is proposed in [24] and a boundary CR user searching algorithm is adopted to improve the performance of this scheme. The machine learning methods are all utilized in [25,26] to improve the spectrum sensing performance. Article [27] is aimed at improving CR spectrum sensing by utilizing techniques such as real-valued FFT, Sparse Fast Fourier Transform, and collaborative spectrum sensing.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Double-Threshold Cooperative Spectrum Sensing Algorithm Based on History Energy Detection

Liu

Wang

et al. 2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Spectrum sensing is one of the key technologies in the field of cognitive radio, which has been widely studied. Among all the sensing methods, energy detection is the most popular because of its simplicity and no requirement of any prior knowledge of the signal. In the case of low signal-to-noise ratio (SNR), the traditional double-threshold energy detection method employs fixed thresholds and there is no detection result when the energy is between high and low thresholds, which leads to poor detection performance such as lower detection probability and longer spectrum sensing time. To address these problems, we proposed an adaptive double-threshold cooperative spectrum sensing algorithm based on history energy detection. In each sensing period, we calculate the weighting coefficient of thresholds according to the SNR of all cognitive nodes; thus, the upper and lower thresholds can be adjusted adaptively. Furthermore, in a single cognitive node, once the current energy is within the high and low thresholds, we utilize the average energy of history sensing times to rejudge. To ensure the real-time performance, if the average history energy is still between two thresholds, the single-threshold method will be used for the end decision. Finally, the fusion center aggregates the detection results of each node and obtains the final cooperative conclusion through “or” criteria. Theoretical analysis and simulation results show that the algorithm proposed in this paper improved detection performance significantly compared with the other four different double-threshold algorithms.

show abstract

Performance improvement for machine learning‐based cooperative spectrum sensing by feature vector selection

Cited by 9 publications

References 28 publications

Coordinated Development of Civic Education and Student Management in Colleges and Universities Incorporating Principal Component Analysis Approach

Coordinated Development of Civic Education and Student Management in Colleges and Universities Incorporating Principal Component Analysis Approach

Optimizing Spectrum Sensing in Cognitive Radio Networks Using Bayesian-Optimized Random Forest Classifier

Adaptive Double-Threshold Cooperative Spectrum Sensing Algorithm Based on History Energy Detection

Contact Info

Product

Resources

About