Improve correlation matrix of Discrete Fourier Transformation technique for finding the missing values of MRI images

Saeed, Soobia; Haron, Habibollah; Jhanjhi, N. Z.; Naqvi, Mehmood; Alhumyani, Hesham; Masud, Mehedi

doi:10.3934/mbe.2022420

Cited by 10 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discrete Fourier transform (DFT) is a form of Fourier transform that takes a discrete form in both the time and frequency domains. It is capable of transforming a sample of time domain signals into a sample in the discrete time Fourier transform (DTFT) frequency domain 35 , 36 .…”

Section: Methods Of Proposing Modelsmentioning

confidence: 99%

Multi-domain-fusion deep learning for automatic modulation recognition in spatial cognitive radio

Hou

Dong

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Automatic modulation recognition (AMR) is a critical technology in spatial cognitive radio (SCR), and building high-performance AMR model can achieve high classification accuracy of signals. AMR is a classification problem essentially, and deep learning has achieved excellent performance in various classification tasks. In recent years, joint recognition of multiple networks has become increasingly popular. In complex wireless environments, there are multiple signal types and diversity of characteristics between different signals. Also, the existence of multiple interference in wireless environment makes the signal characteristics more complex. It is difficult for a single network to accurately extract the unique features of all signals and achieve accurate classification. So, this article proposes a time–frequency domain joint recognition model that combines two deep learning networks (DLNs), to achieve higher accuracy AMR. A DLN named MCLDNN (multi-channel convolutional long short-term deep neural network) is trained on samples composed of in-phase and quadrature component (IQ) signals, to distinguish modulation modes that are relatively easy to identify. This paper proposes a BiGRU3 (three-layer bidirectional gated recurrent unit) network based on FFT as the second DLN. For signals with significant similarity in the time domain and significant differences in the frequency domain that are difficult to distinguish by the former DLN, such as AM-DSB and WBFM, FFT (Fast Fourier Transform) is used to obtain frequency domain amplitude and phase (FDAP) information. Experiments have shown that the BiGUR3 network has superior extraction performance for amplitude spectrum and phase spectrum features. Experiments are conducted on two publicly available datasets, the RML2016.10a and RML2016.10b, and the results show that the overall recognition accuracy of the proposed joint model reaches 94.94% and 96.69%, respectively. Compared to a single network, the recognition accuracy is significantly improved. At the same time, the recognition accuracy of AM-DSB and WBFM signals has been improved by 17% and 18.2%, respectively.

show abstract

Section: Methods Of Proposing Modelsmentioning

confidence: 99%

Multi-domain-fusion deep learning for automatic modulation recognition in spatial cognitive radio

Hou

Dong

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Data preprocessing includes missing values, outliers and data normalization. The missing value refers to the incomplete data caused by the lack of some data information in the original data [20]. Research the deletion of features with high and low missing values; For features with a moderate proportion of missing values, the missing feature is used as the target label; In this study, the RF model is trained by using non-missing features as variables.…”

Section: Establishment Of Mobile User English Learning Pattern Recogn...mentioning

confidence: 99%

Mobile User English Learning Pattern Recognition Model based on Integrated Learning

Zhang,

Ren

2024

SCPE

View full text Add to dashboard Cite

The research in the field of mobile assisted language learning has a long history. It basically follows the route from theory to application practice, but there are few process studies on learners’ individual language skills learning behavior based on mobile platform data. This research takes vocabulary learning as the starting point, and constructs a mobile user English learning pattern recognition model with improved Stacking integration algorithm. The purpose of this study is to identify different learning modes by analyzing the learning behavior and learning data of mobile users, and to provide personalized learning suggestions for users. The evaluation goal of this study is the accuracy and robustness of the mobile users’ English learning pattern recognition model, and the accuracy is the classification accuracy of the model for different learning patterns. Robustness is the stability and consistency of the model in different situations. In order to evaluate the integrated English learning mode of mobile users, the study first divides the collected learning data set into training set and test set. In this step, the method used in the study is cross-validation, which aims to reduce the difference of evaluation results caused by different data sets. For the relevant features in mobile users’ learning data, the features extracted by the research include learning behavior and learning progress, which can accurately reflect the learning mode. Then, the integrated learning method is used to train the model, and the best parameter combination is selected through the training set. Finally, the study uses the test set to evaluate the trained model, and calculates the accuracy and recall index of the model on the test set. Through this evaluation method, the evaluation results of the integrated learning pattern recognition model in terms of accuracy and robustness are obtained, and reference is provided for the improvement of the model. The model proposed in this study is suitable for a large number of user data. Because the learning behavior of users is influenced by personal habits, there are limitations in obtaining enough high-quality data, so the labeling of data is subjective. It is still a challenge to select the most representative features of user learning behavior extracted from the model. The feature selection method can lead to different results, and the process requires a lot of human intervention. The experiment conducted mining and analysis on user learning behavior data of a domestic English vocabulary learning APP. Compared with the confusion matrix of the traditional Stacking model, the improved Stacking model has a stronger ability to distinguish user learning patterns. According to the formula, the accuracy of the improved Stacking model is 91.29%; The accuracy of traditional Stacking model is 90.71%. The ROC curve of the improved Stacking model is smoother than the three single models. Its AUC value is 0.85, which is the same as that of XGBoost. The function is also improved compared with the traditional Stacking model, Logistic Regression (LR) and Random Forest (RF) model. Therefore, the Stacking integrated model owns the best forecast performance and can accurately predict the long-term learning mode of users. In this study, the English learning patterns of mobile users are identified by the method of integrated learning, so that the prediction results of multiple basic learners can be integrated, and the complementarity between different learners can be effectively dealt with, thus improving the generalization ability of the model. This model aims at identifying the English learning patterns of mobile users, and can accurately identify the learning patterns of users by analyzing their learning behaviors on mobile devices. This is of great significance for personalized English learning recommendation. The English learning pattern recognition model for mobile users proposed in this study can identify users’ learning patterns by analyzing their learning behaviors, thus providing personalized learning support and suggestions. In the process of digital manufacturing, they can learn from the idea of learning pattern recognition model and identify the patterns and laws in the production process by analyzing production data and process parameters, so as to optimize the production process and improve production efficiency.

show abstract

“…Discrete Fourier Transform (DFT) is a form of Fourier Transform that takes a discrete form in both the time and frequency domains. It is capable of transforming a sample of time domain signals into a sample in the discrete time Fourier transform (DTFT) frequency domain [25,26].…”

Section: Discrete Fourier Transform and Fast Fourier Transformmentioning

confidence: 99%

Multi-domain-fusion Deep Learning for Automatic Modulation Recognition in Spatial Cognitive Radio

Hou

Dong

et al. 2023

Preprint

View full text Add to dashboard Cite

Automatic modulation recognition (AMR) is a critical technology in spatial cognitive radio(SCR), and building high-performance AMR model can achieve high classification accuracy of signals. AMR is a classification problem essentially, and deep learning has achieved excellent performance in various classification tasks. However, most deep learning models only use a single network. In complex wireless environments, due to the diversity of signal features, it is difficult for a single network to accurately extract the unique features of all signals and achieve accurate classification. So, this article proposes a time-frequency domain joint recognition model that combines two deep learning networks(DLNs), to achieve higher accuracy AMR. A DLN named MCLDNN(multi-channel convolutional long short-term deep neural network) is trained on samples composed of in-phase and quadrature component(IQ) signals, to distinguish modulation modes that are relatively easy to identify. This paper proposes a BiGRU3(three-layer bidirectional gated recurrent unit) network based on FFT as the second DLN. For signals with significant similarity in the time domain and significant differences in the frequency domain that are difficult to distinguish by the former DLN, such as AM-DSB and WBFM, FFT(Fast Fourier Transform) is used to obtain frequency domain amplitude and phase(FDAP) information. Experiments have shown that the BiGUR3 network has superior extraction performance for amplitude spectrum and phase spectrum features. Experiments are conducted on two publicly available datasets, the RML2016.10a and RML2016.10b, and the results show that the overall recognition accuracy of the proposed joint model reaches 94.94% and 96.69%, respectively. Compared to a single network, the recognition accuracy is significantly improved. At the same time, the recognition accuracy of AM-DSB and WBFM signals has been improved by 17% and 18.2%, respectively.

show abstract

Improve correlation matrix of Discrete Fourier Transformation technique for finding the missing values of MRI images

Cited by 10 publications

References 35 publications

Multi-domain-fusion deep learning for automatic modulation recognition in spatial cognitive radio

Multi-domain-fusion deep learning for automatic modulation recognition in spatial cognitive radio

Mobile User English Learning Pattern Recognition Model based on Integrated Learning

Multi-domain-fusion Deep Learning for Automatic Modulation Recognition in Spatial Cognitive Radio

Contact Info

Product

Resources

About