Machine Learning Applications to Signal Processing

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (31 August 2023) | Viewed by 16541

Special Issue Editors

Department of Electrical Engineering, Colorado School of Mines, Golden, CO 80401, USA
Interests: signal processing; compressed sensing; machine learning; computer vision
Computer Science Division, Clemson University, Clemson, SC 29634, USA
Interests: machine learning; computer vision; natural language processing; speech recognition; data mining; bioinformatics
Department of Electrical and Computer Engineering, University of Denver, Denver, CO 80208, USA
Interests: data science; machine learning; signal processing; optimization
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine learning has emerged as a competitive approach, compared to traditional methods, for solving a broad range of signal processing problems including line spectral estimation, matrix completion, feature selection, dictionary learning, and so on. Advances in machine learning and deep learning techniques hold the potential to significantly accelerate information extraction and recovery. Thus, there is a growing interest in applying machine learning to facilitate understanding and solving signal processing problems.

The aim of this Special Issue is to seek submissions of original works that address the above and other important challenges of applying machine learning to signal processing problems. Topics covered in this Special Issue include but are not limited to:

• Applications of machine learning in signal processing;

• Deep learning techniques for signal processing;

• Model-based deep learning for inverse problems;

• Machine learning for signal processing in compressed sensing;

• Matrix factorization/completion;

• Learning from multimodal data;

• Medical imaging analysis;

• Signal denoising;

• Structure/unstructured data processing.

Dr. Youye Xie
Dr. Kai Liu
Dr. Zhihui Zhu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Machine learning
  • Deep learning
  • Signal processing
  • Compressed sensing
  • Matrix completion
  • Inverse problem
  • Image analysis
  • Data mining

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 3610 KiB  
Article
Analysis of the S-ANFIS Algorithm for the Detection of Blood Infections Using Hybrid Computing
by Harsh Khatter, Amit Kumar Gupta, Ruchi Rani Garg and Mangal Sain
Electronics 2022, 11(22), 3733; https://doi.org/10.3390/electronics11223733 - 14 Nov 2022
Cited by 5 | Viewed by 1752
Abstract
Environment and climate change have caused a rise in a wide range of diseases and infections. In countries where overpopulation is a problem, many infections spread severely. The main focus of this paper is the detection and identification of blood diseases. An automated [...] Read more.
Environment and climate change have caused a rise in a wide range of diseases and infections. In countries where overpopulation is a problem, many infections spread severely. The main focus of this paper is the detection and identification of blood diseases. An automated system that examines all potential diseases using patient information and data is needed to deal with unpredictable circumstances. Having an automated and intelligent system that evaluates the reports and counsels doctors in any other area or nation is a demand of the time. The same solutions can be identified by the proposed system. To apply the adaptive neuro-fuzzy inference system (ANFIS) and related techniques to predict chronic diseases early, the authors have gone through various existing models and case studies on diabetics and other patients. The proposed approach, called S-ANFIS which is using the hybrid approach, is based on ANFIS and includes content curation and intelligence analysis in addition to comparison with current models. As a result, the suggested model outperforms other approaches in terms of disease prediction accuracy, with a score of 88.6%. Full article
(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
Show Figures

Figure 1

14 pages, 560 KiB  
Communication
Single-Frequency Network Terrestrial Broadcasting with 5GNR Numerology Using Recurrent Neural Network
by Majid Mosavat and Guido Montorsi
Electronics 2022, 11(19), 3130; https://doi.org/10.3390/electronics11193130 - 29 Sep 2022
Cited by 1 | Viewed by 1667
Abstract
We explore the feasibility of Terrestrial Broadcasting in a Single-Frequency Network (SFN) with standard 5G New Radio (5GNR) numerology designed for uni-cast transmission. Instead of the classical OFDM symbol-by-symbol detector scheme or a more complex equalization technique, we designed a Recurrent-Neural-Network (RNN)-based detector [...] Read more.
We explore the feasibility of Terrestrial Broadcasting in a Single-Frequency Network (SFN) with standard 5G New Radio (5GNR) numerology designed for uni-cast transmission. Instead of the classical OFDM symbol-by-symbol detector scheme or a more complex equalization technique, we designed a Recurrent-Neural-Network (RNN)-based detector that replaces the channel estimation and equalization blocks. The RNN is a bidirectional Long Short-Term Memory (bi-LSTM) that computes the log-likelihood ratios delivered to the LDPC decoder starting from the received symbols affected by strong intersymbol/intercarrier interference (ISI/ICI) on time-varying channels. To simplify the RNN receiver and reduce the system overhead, pilot and data signals in our proposed scheme are superimposed instead of interspersed. We describe the parameter optimization of the RNN and provide end-to-end simulation results, comparing them with those of a classical system, where the OFDM waveform is specifically designed for Terrestrial Broadcasting. We show that the system outperforms classical receivers, especially in challenging scenarios associated with large intersite distance and large mobility. We also provide evidence of the robustness of the designed RNN receiver, showing that an RNN receiver trained on a single signal-to-noise ratio and user velocity performs efficiently also in a large range of scenarios with different signal-to-noise ratios and velocities. Full article
(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
Show Figures

Figure 1

16 pages, 4607 KiB  
Article
LPAdaIN: Light Progressive Attention Adaptive Instance Normalization Model for Style Transfer
by Qing Zhu, Huang Bai, Junmei Sun, Chen Cheng and Xiumei Li
Electronics 2022, 11(18), 2929; https://doi.org/10.3390/electronics11182929 - 15 Sep 2022
Cited by 3 | Viewed by 1721
Abstract
To improve the generation quality of image style transfer, this paper proposes a light progressive attention adaptive instance normalization (LPAdaIN) model that combines the adaptive instance normalization (AdaIN) layer and the convolutional block attention module (CBAM). In the construction of the [...] Read more.
To improve the generation quality of image style transfer, this paper proposes a light progressive attention adaptive instance normalization (LPAdaIN) model that combines the adaptive instance normalization (AdaIN) layer and the convolutional block attention module (CBAM). In the construction of the model structure, first, a lightweight autoencoder is built to reduce the information loss in the encoding process by reducing the number of network layers and to alleviate the distortion of the stylized image structure. Second, each AdaIN layer is progressively applied after the three relu layers in the encoder to obtain the fine-grained stylized feature maps. Third, the CBAM is added between the last AdaIN layer and the decoder, ensuring that the main objects in the stylized image are clearly visible. In the model optimization, a reconstruction loss is designed to improve the decoder’s ability to decode stylized images with more precise constraints and refine the structure of the stylized images. Compared with five classical style transfer models, the LPAdaIN is visually shown to more finely apply the texture of the style image to the content image, in order to obtain a stylized image, in which the main objects are clearly visible and the structure can be maintained. In terms of quantitative metrics, the LPAdaIN achieved good results in running speed and structural similarity. Full article
(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
Show Figures

Figure 1

12 pages, 12633 KiB  
Article
Deep Learning-Based Multiple Co-Channel Sources Localization Using Bernoulli Heatmap
by Meiyan Lin, Yonghui Huang, Baozhu Li, Zhen Huang, Zihan Zhang and Wenjie Zhao
Electronics 2022, 11(10), 1551; https://doi.org/10.3390/electronics11101551 - 12 May 2022
Cited by 3 | Viewed by 1571
Abstract
Multiple sources localization (MSL) has received considerable attention in scenarios of commercial, industrial, and defense areas. In this paper, a novel deep learning-based approach with observations of received signal strength (RSS) is proposed for the localization of multiple co-channel sources. The proposed method, [...] Read more.
Multiple sources localization (MSL) has received considerable attention in scenarios of commercial, industrial, and defense areas. In this paper, a novel deep learning-based approach with observations of received signal strength (RSS) is proposed for the localization of multiple co-channel sources. The proposed method, named MSLocNet, formulates the MSL problem as a Bernoulli heatmap regression problem, solved by a fully convolutional network (FCN). The proposed MSLocNet enables simultaneous localization of variable numbers of sources, and exhibits better localization performance. Simulations, under complex environments with shadow fading, are conducted to validate the improved localization accuracy of the proposed method over other benchmark schemes. Moreover, experiments are carried out in a real environment to verify the feasibility of the proposed method. Full article
(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
Show Figures

Graphical abstract

23 pages, 3485 KiB  
Article
A Machine Learning Method for Classification of Cervical Cancer
by Jesse Jeremiah Tanimu, Mohamed Hamada, Mohammed Hassan, Habeebah Kakudi and John Oladunjoye Abiodun
Electronics 2022, 11(3), 463; https://doi.org/10.3390/electronics11030463 - 4 Feb 2022
Cited by 49 | Viewed by 5851
Abstract
Cervical cancer is one of the leading causes of premature mortality among women worldwide and more than 85% of these deaths are in developing countries. There are several risk factors associated with cervical cancer. In this paper, we developed a predictive model for [...] Read more.
Cervical cancer is one of the leading causes of premature mortality among women worldwide and more than 85% of these deaths are in developing countries. There are several risk factors associated with cervical cancer. In this paper, we developed a predictive model for predicting the outcome of patients with cervical cancer, given risk patterns from individual medical records and preliminary screening. This work presents a decision tree (DT) classification algorithm to analyze the risk factors of cervical cancer. Recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) feature selection techniques were fully explored to determine the most important attributes for cervical cancer prediction. The dataset employed here contains missing values and is highly imbalanced. Therefore, a combination of under and oversampling techniques called SMOTETomek was employed. A comparative analysis of the proposed model has been performed to show the effectiveness of feature selection and class imbalance based on the classifier’s accuracy, sensitivity, and specificity. The DT with the selected features from RFE and SMOTETomek has better results with an accuracy of 98.72% and sensitivity of 100%. DT classifier is shown to have better performance in handling classification problems when the features are reduced, and the problem of high class imbalance is addressed. Full article
(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
Show Figures

Figure 1

22 pages, 8972 KiB  
Article
Cam Mechanisms Reverse Engineering Based on Evolutionary Algorithms
by Monica Tiboni, Cinzia Amici and Roberto Bussola
Electronics 2021, 10(24), 3073; https://doi.org/10.3390/electronics10243073 - 9 Dec 2021
Cited by 1 | Viewed by 2656
Abstract
Cam follower mechanisms are widely used in automated manufacturing machinery to transform a rotary stationary motion into a more general required movement. Reverse engineering of cams has been studied, and some solutions based on different approaches have been identified in the literature. This [...] Read more.
Cam follower mechanisms are widely used in automated manufacturing machinery to transform a rotary stationary motion into a more general required movement. Reverse engineering of cams has been studied, and some solutions based on different approaches have been identified in the literature. This article proposes an innovative method based on the use of an evolutionary algorithm for the identification of a law of motion that allows for approximating in the best way the motion or the sampled profile on the physical device. Starting from the acquired data, through a genetic algorithm, a representation of the movement (and therefore of the cam profile) is identified based on a type of motion law traditionally used for this purpose, i.e., the modified trapezoidal (better known as modified seven segments). With this method it is possible to estimate the coefficients of the parametric motion law, thus allowing the designer to further manipulate them according to the usual motion planning techniques. In a first phase, a study of the method based on simulations is carried out, considering sets of simulated experimental measures, obtained starting from different laws of motion, and verifying whether the developed genetic algorithm allows for identifying the original law or approximating one. For the computation of the objective function, the Euclidean norm and the Dynamic Time Warping (DTW) algorithm are compared. The performed analysis establishes in which situations each of them is more appropriate. Implementation of the method on experimental data validates its effectiveness. Full article
(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
Show Figures

Graphical abstract

Back to TopTop