Submit to Special Issue Submit Abstract to Special Issue Review for Electronics Propose a Special Issue

Journal Menu

Journal Browser

Machine Learning in Electronic and Biomedical Engineering, Volume II

Special Issue Editors
Special Issue Information
Keywords
Published Papers

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

Deadline for manuscript submissions: 31 May 2024 | Viewed by 20740

Share This Special Issue

Special Issue Editors

Dr. Laura Falaschetti

E-Mail Website
Guest Editor

Department of Information Engineering - DII, Università Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy
Interests: embedded systems; machine learning; neural networks; pattern recognition; tensor learning; system identification; signal processing; image processing; speech recognition/synthesis; speaker identification; bio-signal analysis and classification
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Turchetti Claudio

E-Mail Website
Guest Editor

Department of Information Engineering - DII, Università Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy
Interests: microelectronics; analog and mixed-signal integrated circuits; electronic device modeling; statistical IC design; machine learning signal processing; pattern recognition; bio-signal analysis and classification; system identification; neural networks; stochastic processes
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, machine learning techniques have proven to be extremely useful in a wide variety of applications and they are now rapidly gaining increasing interest, both in electronics and biomedical engineering.

The Special Issue seeks to collect contributions from researchers involved in developing and using machine learning techniques applied to:

Embedded systems for artificial intelligence (AI) applications, in which the interest is focused on implementing these algorithms directly in the devices, thus reducing latency, communication costs, and privacy concerns;
Edge computing, where the aim is to process AI algorithms locally on the device, i.e., where the data are generated, by focusing on compression techniques, dimensionality reduction, and parallel computation;
Wearable sensors for collecting biological data;
Human activity detection as well as the diagnosis and prognosis of patients is based on the investigation of data collected from sensors;
Intelligent decision systems and automatic computer-aided-diagnosis systems for early detection and classification of diseases;
Neuroimaging techniques, such as magnetic resonance, ultrasound imaging, and computed tomography to aid in the diagnosis and prediction of diseases.

The aim of this Special Issue is to publish original research articles that cover recent advances in the theory and application of machine learning for electronic and biomedical engineering.

The topics of interest include, but are not limited to:

Machine learning applications for embedded systems;
Machine learning for edge computation;
Deep learning model compression and acceleration;
Image classification, detection, and semantic segmentation;
Machine learning for autonomous guide;
Machine learning for agriculture;
Machine learning for industry;
Deep neural networks for biomedical image processing;
Machine learning methods for computer-aided diagnosis;
Machine learning-based healthcare applications, such as sensor-based behavior analysis, human activity recognition, disease prediction, biomedical signal processing, and data monitoring.

Dr. Laura Falaschetti
Prof. Dr. Turchetti Claudio
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
neural networks
edge computing
sensors for IoT
vision sensors
autonomous guide
medical image classification
computer-aided diagnosis
human activity recognition
biosignals

Published Papers (11 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

18 pages, 1543 KiB

Open AccessArticle

Exploring Machine Learning for Predicting Cerebral Stroke: A Study in Discovery

by Rajib Mia, Shapla Khanam, Amira Mahjabeen, Nazmul Hoque Ovy, Deepak Ghimire, Mi-Jin Park, Mst Ismat Ara Begum and A. S. M. Sanwar Hosen

Electronics 2024, 13(4), 686; https://doi.org/10.3390/electronics13040686 - 07 Feb 2024

Viewed by 1201

Abstract

Cerebral strokes, the abrupt cessation of blood flow to the brain, lead to a cascade of events, resulting in cellular damage due to oxygen and nutrient deprivation. Contemporary lifestyle factors, including high glucose levels, heart disease, obesity, and diabetes, heighten the risk of stroke. This research investigates the application of robust machine learning (ML) algorithms, including logistic regression (LR), random forest (RF), and K-nearest neighbor (KNN), to the prediction of cerebral strokes. Stroke data is collected from Harvard Dataverse Repository. The data includes—clinical, physiological, behavioral, demographic, and historical data. The Synthetic Minority Oversampling Technique (SMOTE), adaptive synthetic sampling (ADASYN), and the Random Oversampling Technique (ROSE) are used to address class imbalances to improve the accuracy of minority classes. To address the challenge of forecasting strokes from partial and imbalanced physiological data, this study introduces a novel hybrid ML approach by combining a machine learning method with an oversampling technique called ADASYN_RF. ADASYN is an oversampling technique used to resample the imbalanced dataset then RF is implemented on the resampled dataset. Also, other oversampling techniques and ML models are implemented to compare the results. Notably, the RF algorithm paired with ADASYN achieves an exceptional performance of 99% detection accuracy, exhibiting its dominance in stroke prediction. The proposed approach enables cost-effective, precise stroke prediction, providing a valuable tool for clinical diagnosis. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

30 pages, 18317 KiB

Open AccessArticle

High-Fidelity Synthetic Face Generation for Rosacea Skin Condition from Limited Data

by Anwesha Mohanty, Alistair Sutherland, Marija Bezbradica and Hossein Javidnia

Electronics 2024, 13(2), 395; https://doi.org/10.3390/electronics13020395 - 18 Jan 2024

Viewed by 548

Abstract

Similarly to the majority of deep learning applications, diagnosing skin diseases using computer vision and deep learning often requires a large volume of data. However, obtaining sufficient data for particular types of facial skin conditions can be difficult, due to privacy concerns. As a result, conditions like rosacea are often understudied in computer-aided diagnosis. The limited availability of data for facial skin conditions has led to the investigation of alternative methods of computer-aided diagnosis. In recent years, generative adversarial networks (GANs), mainly variants of StyleGANs, have demonstrated promising results in generating synthetic facial images. In this study, for the first time, a small dataset of rosacea with 300 full-face images was utilized to further investigate the possibility of generating synthetic data. Our experimentation demonstrated that the strength of

R_{1}

regularization is crucial for generating high-fidelity rosacea images using a few hundred images. This was complemented by various experimental settings to ensure model convergence. We successfully generated 300 high-quality synthetic images, significantly contributing to the limited pool of rosacea images for computer-aided diagnosis. Additionally, our qualitative evaluations by 3 expert dermatologists and 23 non-specialists highlighted the realistic portrayal of rosacea features in the synthetic images. We also provide a critical analysis of the quantitative evaluations and discuss the limitations of solely relying on validation metrics in the field of computer-aided clinical image diagnosis. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

24 pages, 9197 KiB

Open AccessArticle

Deep Feature Meta-Learners Ensemble Models for COVID-19 CT Scan Classification

by Jibin B. Thomas, Shihabudheen K. V., Sheik Mohammed Sulthan and Adel Al-Jumaily

Electronics 2023, 12(3), 684; https://doi.org/10.3390/electronics12030684 - 29 Jan 2023

Cited by 2 | Viewed by 1816

Abstract

The infectious nature of the COVID-19 virus demands rapid detection to quarantine the infected to isolate the spread or provide the necessary treatment if required. Analysis of COVID-19-infected chest Computed Tomography Scans (CT scans) have been shown to be successful in detecting the disease, making them essential in radiology assessment and screening of infected patients. Single-model Deep CNN models have been used to extract complex information pertaining to the CT scan images, allowing for in-depth analysis and thereby aiding in the diagnosis of the infection by automatically classifying the chest CT scan images as infected or non-infected. The feature maps obtained from the final convolution layer of the Deep CNN models contain complex and positional encoding of the images’ features. The ensemble modeling of these Deep CNN models has been proved to improve the classification performance, when compared to a single model, by lowering the generalization error, as the ensemble can meta-learn from a broader set of independent features. This paper presents Deep Ensemble Learning models to synergize Deep CNN models by combining these feature maps to create deep feature vectors or deep feature maps that are then trained on meta shallow and deep learners to improve the classification. This paper also proposes a novel Attentive Ensemble Model that utilizes an attention mechanism to focus on significant feature embeddings while learning the Ensemble feature vector. The proposed Attentive Ensemble model provided better generalization, outperforming Deep CNN models and conventional Ensemble learning techniques, as well as Shallow and Deep meta-learning Ensemble CNNs models. Radiologists can use the presented automatic Ensemble classification models to assist identify infected chest CT scans and save lives. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

15 pages, 3554 KiB

Open AccessArticle

Deep Learning-Based Approaches for Classifying Foraminal Stenosis Using Cervical Spine Radiographs

by Jiho Park, Jaejun Yang, Sehan Park and Jihie Kim

Electronics 2023, 12(1), 195; https://doi.org/10.3390/electronics12010195 - 31 Dec 2022

Cited by 1 | Viewed by 2866

Abstract

Various disease detection models, based on deep learning algorithms using medical radiograph images (MRI, CT, and X-ray), have been actively explored in relation to medicine and computer vision. For diseases related to the spine, primarily MRI-based or CT-based studies have been conducted, but most studies were associated with the lumbar spine, not the cervical spine. Foraminal stenosis offers important clues in diagnosing cervical radiculopathy, which is usually detected based on MRI data because it is difficult even for experts to diagnose using only an X-ray examination. However, MRI examinations are expensive, placing a potential burden on patients. Therefore, this paper proposes a novel model for diagnosing foraminal stenosis using only X-ray images. In addition, we propose methods suitable for cervical spine X-ray images to improve the performance of the proposed classification model. First, the proposed model adopts data preprocessing and augmentation methods, including Histogram Equalization, Flip, and Spatial Transformer Networks. Second, we apply fine-tuned transfer learning using a pre-trained ResNet50 with cervical spine X-ray images. Compared to the basic ResNet50 model, the proposed method improves the performance of foraminal stenosis diagnosis by approximately 5.3–6.9%, 5.2–6.5%, 5.4–9.2%, and 0.8–4.3% in Accuracy, F1 score, specificity, and sensitivity, respectively. We expect that the proposed model can contribute towards reducing the cost of expensive examinations by detecting foraminal stenosis using X-ray images only. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

19 pages, 872 KiB

Open AccessArticle

Deep Learning for Predicting Congestive Heart Failure

by Francesco Goretti, Busola Oronti, Massimo Milli and Ernesto Iadanza

Electronics 2022, 11(23), 3996; https://doi.org/10.3390/electronics11233996 - 02 Dec 2022

Cited by 2 | Viewed by 2496

Abstract

Congestive heart failure (CHF) is one of the most debilitating cardiac disorders. It is a costly disease in terms of both lives and financial outlays, given the high rate of hospital re-admissions and mortality. Heart failure (HF) is notoriously difficult to identify on time, and is frequently accompanied by additional comorbidities that further complicate diagnosis. Many decision support systems (DSS) have been developed to facilitate diagnosis and to raise the standard of screening and monitoring operations, even for non-expert staff. This is confirmed in the literature by records of highly performing diagnosis-aid systems, which are unfortunately not very relevant to expert cardiologists. In order to assist cardiologists in predicting the trajectory of HF, we propose a deep learning-based system which predicts severity of disease progression by employing medical patient history. We tested the accuracy of four models on a labeled dataset, composed of 1037 records, to predict CHF severity and progression, achieving results comparable to studies based on much larger datasets, none of which used longitudinal multi-class prediction. The main contribution of this work is that it demonstrates that a fairly complicated approach can achieve good results on a medium size dataset, providing a reasonably accurate means of determining the evolution of CHF well in advance. This potentially constitutes a significant aid for healthcare managers and expert cardiologists in designing different therapies for medication, healthy lifestyle changes and quality of life (QoL) management, while also promoting allocation of resources with an evidence-based approach. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Graphical abstract

18 pages, 2675 KiB

Open AccessArticle

End-to-End Decoupled Training: A Robust Deep Learning Method for Long-Tailed Classification of Dermoscopic Images for Skin Lesion Classification

by Arthur Cartel Foahom Gouabou, Rabah Iguernaissi, Jean-Luc Damoiseaux, Abdellatif Moudafi and Djamal Merad

Electronics 2022, 11(20), 3275; https://doi.org/10.3390/electronics11203275 - 12 Oct 2022

Cited by 6 | Viewed by 1783

Abstract

Due to its increasing incidence, skin cancer, and especially melanoma, is considered a major public health issue. Manually detecting skin lesions (SL) from dermoscopy images is a difficult and time-consuming process. Thus, researchers designed computer-aided diagnosis (CAD) systems to assist dermatologists in the early detection of skin cancer. Moreover, SL detection naturally exhibits a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Very limited research for handling this issue exists on SL detection. In this paper, we propose an end-to-end decoupled training for the long-tailed skin lesion classification task. Specifically, we initialized the training of a network with a novel loss function

L f

able to guide the model to a better representation of the features. Then, we fine-tuned the pretrained networks with a weighted variant of

L f

helping to improve the robustness of the network to class imbalance. We evaluated our model on the ISIC 2018 public dataset against existing methods for handling class imbalance and existing approaches for SL detection. The results demonstrated the superiority of our framework, outperforming all compared methods by a minimum margin of 2% with a single model. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

12 pages, 713 KiB

Open AccessArticle

Nonlinear Dynamic System Identification in the Spectral Domain Using Particle-Bernstein Polynomials

by Michele Alessandrini, Laura Falaschetti, Giorgio Biagetti, Paolo Crippa and Claudio Turchetti

Electronics 2022, 11(19), 3100; https://doi.org/10.3390/electronics11193100 - 28 Sep 2022

Cited by 1 | Viewed by 1129

Abstract

System identification (SI) is the discipline of inferring mathematical models from unknown dynamic systems using the input/output observations of such systems with or without prior knowledge of some of the system parameters. Many valid algorithms are available in the literature, including Volterra series expansion, Hammerstein–Wiener models, nonlinear auto-regressive moving average model with exogenous inputs (NARMAX) and its derivatives (NARX, NARMA). Different nonlinear estimators can be used for those algorithms, such as polynomials, neural networks or wavelet networks. This paper uses a different approach, named particle-Bernstein polynomials, as an estimator for SI. Moreover, unlike the mentioned algorithms, this approach does not operate in the time domain but rather in the spectral components of the signals through the use of the discrete Karhunen–Loève transform (DKLT). Some experiments are performed to validate this approach using a publicly available dataset based on ground vibration tests recorded from a real F-16 aircraft. The experiments show better results when compared with some of the traditional algorithms, especially for large, heterogeneous datasets such as the one used. In particular, the absolute error obtained with the prosed method is 63% smaller with respect to NARX and from 42% to 62% smaller with respect to various artificial neural network-based approaches. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

16 pages, 10239 KiB

Open AccessFeature PaperArticle

Robustness of Convolutional Neural Networks for Surgical Tool Classification in Laparoscopic Videos from Multiple Sources and of Multiple Types: A Systematic Evaluation

by Tamer Abdulbaki Alshirbaji, Nour Aldeen Jalal, Paul David Docherty, Thomas Neumuth and Knut Möller

Electronics 2022, 11(18), 2849; https://doi.org/10.3390/electronics11182849 - 09 Sep 2022

Cited by 4 | Viewed by 1550

Abstract

Deep learning approaches have been explored for surgical tool classification in laparoscopic videos. Convolutional neural networks (CNN) are prominent among the proposed approaches. However, concerns about the robustness and generalisability of CNN approaches have been raised. This paper evaluates CNN generalisability across different procedures and in data from different surgical settings. Moreover, generalisation performance to new types of procedures is assessed and insights are provided into the effect of increasing the size and representativeness of training data on the generalisation capabilities of CNN. Five experiments were conducted using three datasets. The DenseNet-121 model showed high generalisation capability within the dataset, with a mean average precision of 93%. However, the model performance diminished on data from different surgical sites and across procedure types (27% and 38%, respectively). The generalisation performance of the CNN model was improved by increasing the quantity of training videos on data of the same procedure type (the best improvement was 27%). These results highlight the importance of evaluating the performance of CNN models on data from unseen sources in order to determine their real classification capabilities. While the analysed CNN model yielded reasonably robust performance on data from different subjects, it showed a moderate reduction in performance for different surgical settings. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

16 pages, 3417 KiB

Open AccessArticle

Convolution Neural Networks for the Automatic Segmentation of 18F-FDG PET Brain as an Aid to Alzheimer’s Disease Diagnosis

by Elena Pasini, Dario Genovesi, Carlo Rossi, Lisa Anita De Santi, Vincenzo Positano, Assuero Giorgetti and Maria Filomena Santarelli

Electronics 2022, 11(14), 2260; https://doi.org/10.3390/electronics11142260 - 20 Jul 2022

Cited by 2 | Viewed by 1892

Abstract

Our work aims to exploit deep learning (DL) models to automatically segment diagnostic regions involved in Alzheimer’s disease (AD) in 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) volumetric scans in order to provide a more objective diagnosis of this disease and to reduce the variability induced by manual segmentation. The dataset used in this study consists of 102 volumes (40 controls, 39 with established Alzheimer’s disease (AD), and 23 with established mild cognitive impairment (MCI)). The ground truth was generated by an expert user who identified six regions in original scans, including temporal lobes, parietal lobes, and frontal lobes. The implemented architectures are the U-Net3D and V-Net networks, which were appropriately adapted to our data to optimize performance. All trained segmentation networks were tested on 22 subjects using the Dice similarity coefficient (DSC) and other similarity indices, namely the overlapping area coefficient (AOC) and the extra area coefficient (EAC), to evaluate automatic segmentation. The results of each labeled brain region demonstrate an improvement of 50%, with DSC from about 0.50 for V-Net-based networks to about 0.77 for U-Net3D-based networks. The best performance was achieved by using U-Net3D, with DSC on average equal to 0.76 for frontal lobes, 0.75 for parietal lobes, and 0.76 for temporal lobes. U-Net3D is very promising and is able to segment each region and each class of subjects without being influenced by the presence of hypometabolic regions. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

15 pages, 3394 KiB

Open AccessArticle

Machine Learning Approach for Care Improvement of Children and Youth with Type 1 Diabetes Treated with Hybrid Closed-Loop System

by Sara Campanella, Luisiana Sabbatini, Valentino Cherubini, Valentina Tiberi, Monica Marino, Paola Pierleoni, Alberto Belli, Giada Boccolini and Lorenzo Palma

Electronics 2022, 11(14), 2227; https://doi.org/10.3390/electronics11142227 - 16 Jul 2022

Cited by 1 | Viewed by 2133

Abstract

Type 1 diabetes is a disease affecting beta cells of the pancreas and it’s responsible for a decreased insulin secretion, leading to an increased blood glucose level. The traditional method for glucose treatment is based on finger-stick measurement of the blood glucose concentration and consequent manual insulin injection. Nowadays insulin pumps and continuous glucose monitoring systems are replacing them, being simpler and automatized. This paper focuses on analyzing and improving the knowledge about which Machine Learning algorithms can work best with glycaemic data and tries to find out the relation between insulin pump settings and glycaemic control. The dataset is composed of 90 days of recordings taken from 16 children and adolescents. Three Machine Learning approaches, two for classification, Logistic Regression (LR) and Random Forest (RL), and one for regression, Multivariate Linear Regression (MLR), have been used for the purpose. Specifically, the pump settings analysis was performed based on the Time In Range (TIR) computation and comparison consequent to pump setting changes. RF and MLR have shown the best results, while, for the settings’ analysis, the data show a discrete correlation between changes and TIRs. This study provides an interesting closer look at the data recorded by the insulin pump and a suitable starting point for a thorough and complete analysis of them. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Figure 1

Review

Jump to: Research

10 pages, 489 KiB

Open AccessReview

A Systematic Review on Machine Learning Techniques for Early Detection of Mental, Neurological and Laryngeal Disorders Using Patient’s Speech

by Mohammadjavad Sayadi, Vijayakumar Varadarajan, Mostafa Langarizadeh, Gholamreza Bayazian and Farhad Torabinezhad

Electronics 2022, 11(24), 4235; https://doi.org/10.3390/electronics11244235 - 19 Dec 2022

Cited by 2 | Viewed by 1904

Abstract

There is a substantial unmet need to diagnose speech-related disorders effectively. Machine learning (ML), as an area of artificial intelligence (AI), enables researchers, physicians, and patients to solve these issues. The purpose of this study was to categorize and compare machine learning methods in the diagnosis of speech-based diseases. In this systematic review, a comprehensive search for publications was conducted on the Scopus, Web of Science, PubMed, IEEE and Cochrane databases from 2002–2022. From 533 search results, 48 articles were selected based on the eligibility criteria. Our findings suggest that the diagnosing of speech-based diseases using speech signals depends on culture, language and content of speech, gender, age, accent and many other factors. The use of machine-learning models on speech sounds is a promising pathway towards improving speech-based disease diagnosis and treatments in line with preventive and personalized medicine. Full article

(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)

► Show Figures

Journal Menu

Journal Browser

Machine Learning in Electronic and Biomedical Engineering, Volume II

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (11 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI