https://www.mdu.se/

mdu.sePublikationer
Ändra sökning
Länk till posten
Permanent länk

Direktlänk
Valieva, Inna
Publikationer (10 of 13) Visa alla publikationer
Valieva, I., Shashidhar, B., Björkman, M., Åkerberg, J., Ekström, M. & Voitenko, I. (2023). Machine Learning-Based Coarse Frequency Bands Classification For Cognitive Radio Applications. In: Int. Conf. Electr. Eng./Electron., Comput., Telecommun. Inf. Technol., ECTI-CON: . Paper presented at 2023 20th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023. Institute of Electrical and Electronics Engineers Inc.
Öppna denna publikation i ny flik eller fönster >>Machine Learning-Based Coarse Frequency Bands Classification For Cognitive Radio Applications
Visa övriga...
2023 (Engelska)Ingår i: Int. Conf. Electr. Eng./Electron., Comput., Telecommun. Inf. Technol., ECTI-CON, Institute of Electrical and Electronics Engineers Inc. , 2023Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper is focused on multiple supervised machine learning algorithms' performance evaluation in terms of classification accuracy and speed for the blind frequency bands classification into three occupancy classes: white, gray, and black spaces for potential implementation in cognitive radio application. Training and validation data sets consisting of 180 000 samples, including 60 000 samples per class, have been collected in the controlled experiment. Data samples have been generated using a hardware signal generator and recorded on the receiver's front end as the time-domain complex signals. Gray space data samples contain one, two, or three signals modulated into 2FSK, BPSK, or QPSK with symbol rates 10, 100, or 1000 kSymbol/s. White space data samples contain no own generated signals. Black space data samples contain two signals with the symbol rate of 22.5 MSymbol/s and offset +14 MHz and -14 MHz from the central frequency occupying the entire observation band. Training and validation of twenty supervised machine learning algorithms have been performed offline in the Matlab Classification Learner application using the collected data set. Fine decision trees have demonstrated the highest classification accuracy of 87.8 %, the observed classification speed of 630000 Objects/s is also higher than the required 2000 Objects/s. Medium decision trees and ensemble boosted trees have demonstrated 87.5 % and 87.7 % accuracy and classification speeds of 950000 and 230000 Objects/s respectively. Therefore, ensemble boosted trees, and fine and medium decision trees have been selected for the deployment on the target radio application in the scope of future work.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers Inc., 2023
Nyckelord
cognitive radio, decision trees, machine learning, vacant frequency channels, Classification (of information), Learning algorithms, Signal receivers, Classification accuracy, Data sample, Data set, Frequency channels, Machine learning algorithms, Machine-learning, Radio applications, Space data, Supervised machine learning, Vacant frequency channel
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
urn:nbn:se:mdh:diva-63918 (URN)10.1109/ECTI-CON58255.2023.10153155 (DOI)2-s2.0-85164912117 (Scopus ID)9798350310467 (ISBN)
Konferens
2023 20th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023
Tillgänglig från: 2023-07-26 Skapad: 2023-07-26 Senast uppdaterad: 2023-07-26Bibliografiskt granskad
Valieva, I. & Voitenko, I. (2023). Shallow Neural Networks for Unmanned Aerial Vehicles Data Traffic Classification. In: Proceedings - 2023 IEEE Future Networks World Forum: Future Networks: Imagining the Network of the Future, FNWF 2023: . Paper presented at 6th IEEE Future Networks World Forum, FNWF 2023, Baltimore, November 13-15, 2023. Institute of Electrical and Electronics Engineers Inc.
Öppna denna publikation i ny flik eller fönster >>Shallow Neural Networks for Unmanned Aerial Vehicles Data Traffic Classification
2023 (Engelska)Ingår i: Proceedings - 2023 IEEE Future Networks World Forum: Future Networks: Imagining the Network of the Future, FNWF 2023, Institute of Electrical and Electronics Engineers Inc. , 2023Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In this paper, the classification of Unmanned Aerial Vehicles (UAV) data traffic into three distinct classes: analog video, digital OFDM-modulated video, and Additive White Gaus-sian Noise (AWGN) has been performed employing six neural network classifiers including Feed Forward Neural Network (FFNN), Generalized Regression Neural Network (GRNN), and Probabilistic Neural Network (PNN); and Cascade Forward Neural Network (CFNN), Recurrent Neural Network (RNN) and multilayer perceptron neural network (NN). The data set composed of the time domain signal samples for classifiers' training, validation, and testing has been collected in the controlled exper-iment conducted in the office/lab environment with the stationary signal source and receiver. The subset of twenty-four extracted features has been used as input to the neural network classifiers. Feature reduction has been performed using four popular in literature feature selection algorithms: Minimum Redundancy Maximum Relevance (MRMR), Neighborhood Component Anal-ysis (NCA), Relief, and Laplacian score to enhance computational efficiency and prediction speed for hardware implementation and real-time operation on the target CPU. Four features including mean, standard deviation, and median absolute deviation of the time domain signal, and RSSI have been selected. Six neural network classifiers have been trained using both the full and reduced feature sets. Also, two validation algorithms: k-fold cross-validation and hold-out validation have been evaluated. The Recurrent Neural Network (RNN) has demonstrated the highest accuracy using the full feature set and employing cross-validation. The feature reduction has led to a 3 % decrease in accuracy for RNN. Feedforward Neural Network (FFNN) has demonstrated the highest accuracy of 93.51 % with the reduced feature set input using cross-validation on PC in Matlab environment. It has been prototyped on our target hardware CPU using Mathworks Embedded Coder; the generated C code has been deployed on ARM Cortex CPU. FFNN using four feature inputs has demonstrated an accuracy of 91.23 % in real-time testing.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers Inc., 2023
Nyckelord
feed-forward neu-ral network, Supervised machine learning, UAV data traffic classification, Antennas, C (programming language), Classification (of information), Computational efficiency, Recurrent neural networks, Signal receivers, Statistical tests, Support vector machines, Unmanned aerial vehicles (UAV), Aerial vehicle, Data traffic, Features sets, Feed forward, Neural networks classifiers, Neural-networks, Traffic classification, Unmanned aerial vehicle data traffic classification, Multilayer neural networks
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
urn:nbn:se:mdh:diva-67207 (URN)10.1109/FNWF58287.2023.10520364 (DOI)2-s2.0-85194161600 (Scopus ID)9798350324587 (ISBN)
Konferens
6th IEEE Future Networks World Forum, FNWF 2023, Baltimore, November 13-15, 2023
Tillgänglig från: 2024-06-05 Skapad: 2024-06-05 Senast uppdaterad: 2024-06-05Bibliografiskt granskad
Valieva, I. (2023). Spectrum Sensing for Cognitive Radio. (Doctoral dissertation). Västerås: Mälardalens universitet
Öppna denna publikation i ny flik eller fönster >>Spectrum Sensing for Cognitive Radio
2023 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

This work focuses on the improvement of spectrum utilization by evaluating and proposing a subset of radio scene analysis algorithms for opportunistic spectrum access deployment in a cognitive radio network. The proposed algorithms aim to solve two problems: detecting vacant frequency channels and estimating the waveform, including modulation type, symbol rate, and central frequency. To test and prove the hypothesis three research questions related to radio scene observation, classification, and estimation have been formulated, studied, and answered. A two-step spectrum sensing algorithm has been proposed. The first step covers the coarse classification of the observed band into three broad categories: white, gray, or black space, commonly used in the literature to describe spectrum occupancy. Various machine learning algorithms were applied and tested for the coarse classification step. Fine decision trees demonstrated the highest classification accuracy and speed. The second step covers the detailed gray space analysis performed to detect vacant channels and waveforms of the signals present in the observed band. Algorithms such as cyclostationary, energy detection, and wavelet transform were employed for solving the vacant channel detection. The hypothesis has been proven by demonstrating the possibility of blind real-time vacant frequency channel detection using discrete wavelet transform and energy detection within the time compatible with real-time operation and 5G latency requirements on the test hardware.

Ort, förlag, år, upplaga, sidor
Västerås: Mälardalens universitet, 2023
Serie
Mälardalen University Press Dissertations, ISSN 1651-4238 ; 373
Nationell ämneskategori
Teknik och teknologier Elektroteknik och elektronik
Forskningsämne
elektronik
Identifikatorer
urn:nbn:se:mdh:diva-61898 (URN)978-91-7485-583-8 (ISBN)
Disputation
2023-04-12, Gamma, Mälardalens universitet, Västerås, 09:15 (Engelska)
Opponent
Tillgänglig från: 2023-02-14 Skapad: 2023-02-13 Senast uppdaterad: 2023-03-22Bibliografiskt granskad
Valieva, I., Voitenko, I., Björkman, M., Åkerberg, J. & Ekström, M. (2022). Blind Symbol Rate Estimation Using Wavelet Transform and Deep Learning for FSK Modulated Signals. In: 2022 International Conference on Advanced Technologies for Communications (ATC): . Paper presented at 2022 International Conference on Advanced Technologies for Communications (ATC), 20-22 October 2022.
Öppna denna publikation i ny flik eller fönster >>Blind Symbol Rate Estimation Using Wavelet Transform and Deep Learning for FSK Modulated Signals
Visa övriga...
2022 (Engelska)Ingår i: 2022 International Conference on Advanced Technologies for Communications (ATC), 2022Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper is focused on the blind symbol rate estimation for the digital FSK modulated signals, based on the classification between three symbol rate classes: 10, 100, and 1000 KSymbol/second using the scalogram images obtained from continuous wavelet transform with Morse wavelet. Pretrained deep learning AlexNet has been transfer learned to classify between symbol rate classes. Training, testing, and validation data sets have been composed of the artificial data generated using Bernoulli binary random signal generator modulated into FSK signal corrupted by additive white Gaussian noise (AWGN) noise with SNR ranging from 1 to 30 dB. Training and validation data sets have been augmented to obtain twice more extensive data set i.e 1800 scalogram images, compared to the original size of 900 samples. The average classification accuracy during validation has reached 99.7 % and during testing 100 % and 96.3 % for the data sets with SNR 25–30 dB and 20–25 dB respectively. The proposed algorithm has been compared with cyclostationary and has shown improved classification accuracy, especially in conditions of low SNR.

Nationell ämneskategori
Telekommunikation
Identifikatorer
urn:nbn:se:mdh:diva-61136 (URN)10.1109/atc55345.2022.9943051 (DOI)2-s2.0-85142741268 (Scopus ID)
Konferens
2022 International Conference on Advanced Technologies for Communications (ATC), 20-22 October 2022
Tillgänglig från: 2022-12-07 Skapad: 2022-12-07 Senast uppdaterad: 2023-03-10Bibliografiskt granskad
Valieva, I., Shashidhar, B., Björkman, M., Åkerberg, J., Ekström, M. & Voitenko, I. (2022). Blind Vacant Frequency Channels Detection for Cognitive Radio. In: 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022: . Paper presented at 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc.
Öppna denna publikation i ny flik eller fönster >>Blind Vacant Frequency Channels Detection for Cognitive Radio
Visa övriga...
2022 (Engelska)Ingår i: 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, Institute of Electrical and Electronics Engineers Inc. , 2022Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper is focused on the blind vacant frequency channels detection in 56 MHz observation band divided into 56 channels (1 MHz each) implemented on in-house developed hardware based on the AD9364 transceiver operating in automatic gain control (AGC) mode. Vacant channel detection has been modeled as a binary hypothesis testing problem. Three signal detection algorithms widely used in the literature including energy detection, wavelets, and cyclostationary have been tested and evaluated for potential use in our target application. Primary, offline testing has been performed in the Matlab environment using the data samples captured on the target receiver's front end as a time-domain complex signal. Data samples containing one, two, or three signals generated by hardware signal generator and modulated into 2FSK, BPSK, or QPSK with symbol rate 10, 100, or 1000 kSymbol/s. The highest accuracy of 91.0 % has been observed in the offline detection for continuous wavelet transform, while energy detection has demonstrated 86.4 % accuracy. Cyclostationary detection has shown no distinguishable difference in the spectrum correlation values calculated for the AWGN noise sample and the sample containing BPSK and 2FSK modulated signals. Energy detection and discrete wavelet transform have been implemented on our target hardware and tested in the office environment in conditions that could be approximated by AWGN channel. Test sequences containing one or two signals have been generated by the signal generator and received and processed by our target radio node. Discrete wavelet transform has demonstrated 85.73 % and energy detection 85.25 % accuracy in real-time testing. © 2022 IEEE.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers Inc., 2022
Nyckelord
cognitive radio, energy detection, vacant frequency channels, wavelet transform
Nationell ämneskategori
Elektroteknik och elektronik
Identifikatorer
urn:nbn:se:mdh:diva-58205 (URN)10.1109/ICEIC54506.2022.9748704 (DOI)000942023400111 ()2-s2.0-85128807098 (Scopus ID)9781665409346 (ISBN)
Konferens
2022 International Conference on Electronics, Information, and Communication, ICEIC 2022
Tillgänglig från: 2022-05-11 Skapad: 2022-05-11 Senast uppdaterad: 2023-03-22Bibliografiskt granskad
Valieva, I., Shashidhar, B., Björkman, M., Åkerberg, J., Ekström, M. & Voitenko, I. (2022). Machine Learning-Based Frequency Bands Classification for Efficient Frequency Hopping Spread Spectrum Applications. In: Proceedings - IEEE Military Communications Conference MILCOM: . Paper presented at 2022 IEEE Military Communications Conference, MILCOM 2022, Rockville, 28 November 2022 through 2 December 2022 (pp. 72-77). Institute of Electrical and Electronics Engineers Inc.
Öppna denna publikation i ny flik eller fönster >>Machine Learning-Based Frequency Bands Classification for Efficient Frequency Hopping Spread Spectrum Applications
Visa övriga...
2022 (Engelska)Ingår i: Proceedings - IEEE Military Communications Conference MILCOM, Institute of Electrical and Electronics Engineers Inc. , 2022, s. 72-77Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper is focused on the performance evaluation of nine supervised machine learning algorithms in terms of classification accuracy applied to perform two radio scene analysis tasks: 1. blind binary frequency band occupancy classification: vacant or occupied; 2. interference type classification: sine wave interference, or modulated signal or additive white Gaussian noise (AWGN) for the frequency hopping spread spectrum cognitive radio application. Twenty-nine features derived from the time-, frequency-domain and RSSI, have been used as classification inputs to the evaluated machine learning classifiers. Classifiers training and validation have been performed offline in Matlab Classification Learner and Neural Networks applications using four data sets, generated in the controlled experiment, covering both classification tasks in AWGN and mixed channel propagation conditions (AWGN and Rician fading). Data samples have been generated using a hardware signal generator and recorded on the target application receivers' front end as the time-domain complex signals. The highest classification accuracy of 98.71 % has been demonstrated by Feed Forward Neural Network (FFNN) for the binary occupancy classification in K-fold validation for the mixed data set containing both AWGN and Rician fading channel samples. For the interference type classification, FFNN has demonstrated classification accuracy of 99.82 % for K-fold validation and 99.71 % for hold-out validation. FFNN has been concluded as an acceptable algorithm for further adaptation and embedded deployment on our target radio application for both binary classification between occupied or vacant frequency bands and interference type classification. 

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers Inc., 2022
Nyckelord
decision trees, frequency hopping spread spectrum, neural networks, supervised machine learning, vacant frequency bands
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:mdh:diva-61925 (URN)10.1109/MILCOM55135.2022.10017912 (DOI)000968304600013 ()2-s2.0-85147333248 (Scopus ID)9781665485340 (ISBN)
Konferens
2022 IEEE Military Communications Conference, MILCOM 2022, Rockville, 28 November 2022 through 2 December 2022
Tillgänglig från: 2023-02-15 Skapad: 2023-02-15 Senast uppdaterad: 2023-05-17Bibliografiskt granskad
Valieva, I., Voitenko, I., Björkman, M., Åkerberg, J. & Ekström, M. (2021). Multiple machine learning algorithms comparison for modulation type classification based on instantaneous values of the time domain signal and time series statistics derived from wavelet transform. Advances in Science, Technology and Engineering Systems, 6(1), 658-671
Öppna denna publikation i ny flik eller fönster >>Multiple machine learning algorithms comparison for modulation type classification based on instantaneous values of the time domain signal and time series statistics derived from wavelet transform
Visa övriga...
2021 (Engelska)Ingår i: Advances in Science, Technology and Engineering Systems, ISSN 2415-6698, Vol. 6, nr 1, s. 658-671Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Modulation type classification is a part of waveform estimation required to employ spectrum sharing scenarios like dynamic spectrum access that allow more efficient spectrum utilization. In this work multiple classification features, feature extraction, and classification algorithms for modulation type classification have been studied and compared in terms of classification speed and accuracy to suggest the optimal algorithm for deployment on our target application hardware. The training and validation of the machine learning classifiers have been performed using artificial data. The possibility to use instantaneous values of the time domain signal has shown acceptable performance for the binary classification between BPSK and 2FSK: Both ensemble boosted trees with 30 decision trees learners trained using AdaBoost sampling and fine decision trees have shown optimal performance in terms of both an average classification accuracy (86.3 % and 86.0 %) and classification speed (120 0000 objects per second) for additive white gaussian noise (AWGN) channel with signal-to-noise ratio (SNR) ranging between 1 and 30 dB. However, for the classification between five modulation classes demonstrated average classification accuracy has reached only 78.1 % in validation. Statistical features: Mean, Standard Deviation, Kurtosis, Skewness, Median Absolute Deviation, Root-Mean-Square level, Zero Crossing Rate, Interquartile Range and 75th Percentile derived from the wavelet transform of the received signal observed during 100 and 500 microseconds were studied using fractional factorial design to determine the features with the highest effect on the response variables: classification accuracy and speed for the additive white gaussian noise and Rician line of sight multipath channel. The highest classification speed of 170 000 objects/second and 100 % classification accuracy has been demonstrated by fine decision trees using as an input Kurtosis derived from the wavelet coefficients derived from signal observed during 100 microseconds for AWGN channel. For the line of sight fading Rician channel with AWGN demonstrated classification speed is slower 130 000 objects/s.

Ort, förlag, år, upplaga, sidor
ASTES Publishers, 2021
Nyckelord
Cognitive radio, Machine learning, Modulation classification
Nationell ämneskategori
Elektroteknik och elektronik
Identifikatorer
urn:nbn:se:mdh:diva-53579 (URN)10.25046/aj060172 (DOI)2-s2.0-85101023812 (Scopus ID)
Anmärkning

Export Date: 5 March 2021; Article; Correspondence Address: Valieva, I.; School of Innovation, Sweden; email: inna.valieva@mdh.se

Tillgänglig från: 2021-03-05 Skapad: 2021-03-05 Senast uppdaterad: 2023-03-10Bibliografiskt granskad
Valieva, I. (2020). Spectrum Sensing for Dynamic Spectrum Access in Cognitive Radio. (Licentiate dissertation). Västerås: Mälardalen University
Öppna denna publikation i ny flik eller fönster >>Spectrum Sensing for Dynamic Spectrum Access in Cognitive Radio
2020 (Engelska)Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

Abstract. The number of mobile devices is constantly growing, and the exclusivestatic spectrum allocation approach is leading to the spectrum scarcity problem whensome of the licensed bands are heavily occupied and others are nearly unused.Spectrum sharing and opportunistic spectrum access allow achieving more efficientspectrum utilization. Radio scene analysis is a first step in the cognitive radiooperation required to employ opportunistic spectrum access scenarios such as thedynamic spectrum access or frequency hopping spread spectrum. The objective of thiswork is to develop and virtual prototype the subset of radio scene analysis algorithmsintended to be used for deployment of opportunistic spectrum access in our targetapplication: a cognitive radio network consisting of multiple software-defined radionodes BitSDR. The proposed radio scene analysis algorithms are devoted to solvingtwo radio scene analysis problems: 1. detection of vacant frequency channels toimplement spectrum sharing scenarios; 2. waveform estimation including modulationtype, symbol rate, and central frequency estimation. From the subset of two radioscene analysis problems two hypotheses are formulated: the first is related to thevacant band identification and the second to waveform estimation. Then sevenresearch questions related to the trade-off between the sensing accuracy and real-time operation requirement for the proposed radio scene analysis algorithms, the nature of the noise, and assumptions used to model the radio scene environment such as the AWGN channel. In the scope of this work, Hypothesis 1, dedicated to vacant frequency band detection, has been proven. Research questions related to the selection of the observation bandwidth, vacant channels detection threshold, and the optimal algorithm have been answered. We have proposed, prototyped, and tested a vacant frequency channels detection algorithm based on wavelet transform performing multichannel detection in the wide band of 56 MHz based on the received signal observed during500 microseconds. Detection accuracy of 91 % has been demonstrated. Detection has been modeled as a binary hypothesis testing problem. Also, energy detection and cyclostationary feature extraction algorithms have been prototyped and tested, however, they have shown lower classification accuracy than wavelets. Answering research question 7 revealed the advantage of using wavelets due to the potential of the results of wavelet transform to be applied for solving the waveform estimation problem including symbol rate and modulation type. Test data samples have been generated during the controlled experiment by the hardware signal generator and received by proprietary hardware based on AD9364 Analog Devices transceiver. To test Hypothesis 2 research questions related to the waveform estimation have been elaborated. We could not fully prove Hypothesis 2 in the scope of this work. The algorithm and features that have been chosen for modulation type classification have not met the required classification accuracy to classify between five studied modulation classes 2FSK, BPSK, QPSK, 8PSK, and 16PSK. To capture more of the fine differences between the received signal modulated into different linear modulations it has been suggested to use the spectral features derived from the time-series signal observed during 500 microseconds or less observation time in the scope of the future work. However, the binary classification between 2FSK and BPSKpresented in Paper 1 could be performed based on instantaneous values and SNRinput: ensemble boosted trees and decision trees have shown an average classification accuracy of 86.3 % and 86.0 % respectively and classification speed of 1200000objects per second, what is faster than required 2000 objects per second.3The prototyping and testing of the proposed algorithm for symbol rate estimation based on deep learning have been performed to answer research question 2. Wavelet transform feature extraction has been proposed to be applied as a preprocessing step for deep learning-based estimation of the symbol rate for 2FSK modulated signals. This algorithm has shown an improvement in the accuracy of the symbol rate estimation in comparison with cyclostationary based detection. The validation accuracy of the symbol rate classification has reached 99.7 %. During testing, the highest average classification accuracy of 100 % has been observed for the signals with SNR levels 25-30 dB, while for signals with SNR 20-25 dB it was 96.3 %.

Ort, förlag, år, upplaga, sidor
Västerås: Mälardalen University, 2020
Serie
Mälardalen University Press Licentiate Theses, ISSN 1651-9256 ; 300
Nationell ämneskategori
Elektroteknik och elektronik
Identifikatorer
urn:nbn:se:mdh:diva-52881 (URN)978-91-7485-493-0 (ISBN)
Presentation
2021-01-22, U2-024 and virtually via Zoom, Mälardalens högskola, Västerås, 09:15 (Engelska)
Handledare
Tillgänglig från: 2020-12-31 Skapad: 2020-12-21 Senast uppdaterad: 2022-11-08Bibliografiskt granskad
Valieva, I., Björkman, M., Åkerberg, J., Ekström, M. & Voitenko, I. (2019). Multiple Machine Learning Algorithms Comparison for Modulation Type Classification for Efficient Cognitive Radio. In: MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM): . Paper presented at 2019 IEEE Military Communications Conference, MILCOM 2019; Norfolk; United States; 12 November 2019 through 14 November 2019; Category numberCFP19MIL-ART; Code 158374. Norfolk, USA: IEEE, Article ID 9020735.
Öppna denna publikation i ny flik eller fönster >>Multiple Machine Learning Algorithms Comparison for Modulation Type Classification for Efficient Cognitive Radio
Visa övriga...
2019 (Engelska)Ingår i: MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM), Norfolk, USA: IEEE, 2019, artikel-id 9020735Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In this paper the potential of improving channel utilization by signal modulation type classification based on machine learning algorithms has been studied. The classification has been performed between two popular digital modulations: BPSK and FSK in target application. Classification was based on three features available on a popular software defined radio transceiver AD9361: In-phase and quadrature components of the digital time domain signal and signal-to-noise ratio (SNR), measured as RSSI value. Data used for network training, validation and testing was generated by the Simulink model consisting mainly of modulator, transceiver AD9361 and AWGN to generate the signal with SNR ranging from 1 to 30 dB. Twenty-three supervised machine learning algorithms including K-nearest neighbor, Support Vector Machines, Decision Trees and Ensembles have been studied, evaluated and verified against the target application's requirements in terms of classification accuracy and speed. The highest average classification accuracy of 86.9% was achieved by Support Vector Machines with Fine Gaussian kernel, however with demonstrated classification speed of 790 objects per second it was considered unable to meet target application's real-time operation requirement of 2000 objects per second. Fine Decision Trees and Ensemble Boosted Trees have shown optimal performance in terms of both reaching classification speed of 1200000 objects per second and average classification accuracy of 86.0% and 86.3% respectively. Classification accuracy has been also studied as a function of SNR to determine the most accurate classifier for each SNR level. At the target application's demodulation threshold of 12 dB 87.0% classification accuracy has been observed for the Fine Decision Trees, 87.5% for both Fine Gaussian SVM and Coarse KNN. At SNR higher than 27 dB Fine Trees, Coarse KNN have reached 97.5% classification accuracy. The effects of data set size and number of classification features on classification speed and accuracy have been studied too.

Ort, förlag, år, upplaga, sidor
Norfolk, USA: IEEE, 2019
Nationell ämneskategori
Telekommunikation
Identifikatorer
urn:nbn:se:mdh:diva-52713 (URN)10.1109/MILCOM47813.2019.9020735 (DOI)000554849700087 ()2-s2.0-85082395256 (Scopus ID)
Konferens
2019 IEEE Military Communications Conference, MILCOM 2019; Norfolk; United States; 12 November 2019 through 14 November 2019; Category numberCFP19MIL-ART; Code 158374
Tillgänglig från: 2020-11-22 Skapad: 2020-11-22 Senast uppdaterad: 2021-03-16Bibliografiskt granskad
Valieva, I., Björkman, M., Åkerberg, J., Ekström, M., Shashidhar, B. & Voitenko, I.AUTONOMOUS DETECTION OF VACANT FREQUENCY BANDS FOR COGNITIVE RADIO.
Öppna denna publikation i ny flik eller fönster >>AUTONOMOUS DETECTION OF VACANT FREQUENCY BANDS FOR COGNITIVE RADIO
Visa övriga...
(Engelska)Manuskript (preprint) (Övrigt vetenskapligt)
Abstract [en]

This This paper is focused on thea utonomous detection of the vacant frequency channels in the wide observation band of 60MHz. Vacant channel detection has been modeled as a binary hypothesis testing problem. Three signal detection algorithms including energy detection, wavelets, and cyclostationary have been tested and evaluated in terms of accuracy.Testing has been performed offline on the data samples collected during the controlled experiment. Data samples consisting of AWGN noise and FSK, BPSK, QPSK modulated signals have been generated using thehardware signal generator and received on our targetapplication's receiver (AD9364) front end as a time domain complex signal. The optimal threshold value hasbeen determined as an optimal value between the hitrate and the false positive rate. The highest accuracy of 91.0% has been reached the wavelet transform feature extraction, energy detection has shown 86.4% accuracy. Cyclostationary detection has shown no distinguishable difference in the spectrum correlation values calculatedfor the AWGN noise sample and samples containing BPSK and 2FSK modulated signals captured with -20dB power.

Nationell ämneskategori
Telekommunikation
Identifikatorer
urn:nbn:se:mdh:diva-52714 (URN)
Tillgänglig från: 2020-11-22 Skapad: 2020-11-22 Senast uppdaterad: 2021-03-16Bibliografiskt granskad
Organisationer

Sök vidare i DiVA

Visa alla publikationer