Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning
Blind spectrum sensing (BSS) is crucial for identifying unknown signals in scenarios with limited prior knowledge. Traditional methods face challenges with unknown and timevarying signals, especially in the presence of noise interference. This paper addresses these issues by introducing a statistica...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Croatian Communications and Information Society (CCIS)
2024-03-01
|
| Series: | Journal of Communications Software and Systems |
| Subjects: | |
| Online Access: | https://jcoms.fesb.unist.hr/10.24138/jcomss-2023-0175/ |
| _version_ | 1797315280114810880 |
|---|---|
| author | Jakub Nikonowicz Mieczysław Jessa Łukasz Matuszewski |
| author_facet | Jakub Nikonowicz Mieczysław Jessa Łukasz Matuszewski |
| author_sort | Jakub Nikonowicz |
| collection | DOAJ |
| description | Blind spectrum sensing (BSS) is crucial for identifying unknown signals in scenarios with limited prior knowledge. Traditional methods face challenges with unknown and timevarying signals, especially in the presence of noise interference. This paper addresses these issues by introducing a statistical signal processing framework that extends the use of machine learning (ML) features. Our approach improves BSS by incorporating cumulative distribution functions (CDFs) into unsupervised ML, enabling effective clustering of diverse transmission states without assumptions about specific noise distributions. Additionally, we introduce a temporal decomposition technique using shorter Fast Fourier Transforms (FFTs), enhancing the learning process, reducing system inertia, and minimizing data requirements for retraining under dynamic conditions. We evaluate our method, focusing on various features/approaches for incorporating CDFs into ML, including centroid, linear approximation, and low-order statistics. Simulation results demonstrate robust detection in a standard transmission scenario with a Gaussian pulse amidst additive white Gaussian noise, maintaining a consistently low false alarm rate. These findings highlight our BSS approach’s effectiveness and practical potential in handling unknown signals in challenging environments. This research provides valuable insights, laying the groundwork for practical implementation in real-world scenarios. |
| first_indexed | 2024-03-08T02:59:28Z |
| format | Article |
| id | doaj.art-db423a31b6b5401db58c640def40c633 |
| institution | Directory Open Access Journal |
| issn | 1845-6421 1846-6079 |
| language | English |
| last_indexed | 2024-03-08T02:59:28Z |
| publishDate | 2024-03-01 |
| publisher | Croatian Communications and Information Society (CCIS) |
| record_format | Article |
| series | Journal of Communications Software and Systems |
| spelling | doaj.art-db423a31b6b5401db58c640def40c6332024-02-13T11:50:52ZengCroatian Communications and Information Society (CCIS)Journal of Communications Software and Systems1845-64211846-60792024-03-01201384610.24138/jcomss-2023-0175Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine LearningJakub NikonowiczMieczysław JessaŁukasz MatuszewskiBlind spectrum sensing (BSS) is crucial for identifying unknown signals in scenarios with limited prior knowledge. Traditional methods face challenges with unknown and timevarying signals, especially in the presence of noise interference. This paper addresses these issues by introducing a statistical signal processing framework that extends the use of machine learning (ML) features. Our approach improves BSS by incorporating cumulative distribution functions (CDFs) into unsupervised ML, enabling effective clustering of diverse transmission states without assumptions about specific noise distributions. Additionally, we introduce a temporal decomposition technique using shorter Fast Fourier Transforms (FFTs), enhancing the learning process, reducing system inertia, and minimizing data requirements for retraining under dynamic conditions. We evaluate our method, focusing on various features/approaches for incorporating CDFs into ML, including centroid, linear approximation, and low-order statistics. Simulation results demonstrate robust detection in a standard transmission scenario with a Gaussian pulse amidst additive white Gaussian noise, maintaining a consistently low false alarm rate. These findings highlight our BSS approach’s effectiveness and practical potential in handling unknown signals in challenging environments. This research provides valuable insights, laying the groundwork for practical implementation in real-world scenarios.https://jcoms.fesb.unist.hr/10.24138/jcomss-2023-0175/blind detectioncumulative distribution functionmachine learningspectrum sensingunknown signals |
| spellingShingle | Jakub Nikonowicz Mieczysław Jessa Łukasz Matuszewski Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning Journal of Communications Software and Systems blind detection cumulative distribution function machine learning spectrum sensing unknown signals |
| title | Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning |
| title_full | Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning |
| title_fullStr | Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning |
| title_full_unstemmed | Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning |
| title_short | Computationally Efficient Wideband Spectrum Sensing through Cumulative Distribution Function and Machine Learning |
| title_sort | computationally efficient wideband spectrum sensing through cumulative distribution function and machine learning |
| topic | blind detection cumulative distribution function machine learning spectrum sensing unknown signals |
| url | https://jcoms.fesb.unist.hr/10.24138/jcomss-2023-0175/ |
| work_keys_str_mv | AT jakubnikonowicz computationallyefficientwidebandspectrumsensingthroughcumulativedistributionfunctionandmachinelearning AT mieczysławjessa computationallyefficientwidebandspectrumsensingthroughcumulativedistributionfunctionandmachinelearning AT łukaszmatuszewski computationallyefficientwidebandspectrumsensingthroughcumulativedistributionfunctionandmachinelearning |