Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.0
2.9
Journals
Electronics
Special Issues
Smart Mobile and Machine Learning Technologies for Home and Community...
electronics-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Electronics Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Smart Mobile and Machine Learning Technologies for Home and Community Healthcare

A Special Issue of Electronics (ISSN 2079-9292) belonging to the section "Bioelectronics".

Deadline for manuscript submissions: 15 March 2027 | Viewed by 2478

Editors

Dr. Ao Li

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, The University of Arizona, Tucson, AZ, USA
Interests: machine learning; deep learning; biomedical informatics; digital health
Dr. Geng Yuan

E-Mail Website
Guest Editor
School of Computing, University of Georgia, Athens, GA 30602, USA
Interests: deep learning; efficient AI system design; edge computing
Special Issues, Collections and Topics in MDPI journals
Dr. Na Gong

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, University of Alabama, Alabama, AL 35401, USA
Interests: artificial intelligence (AI) hardware; intelligent VLSI circuits and systems; hardware design for privacy; AI for biomedical applications

Special Issue Information

Dear Colleagues,

In recent years, the integration of smart mobile technologies and machine learning (ML) has emerged as a transformative force in healthcare delivery, especially in home and community settings. Rapid advancements in mobile devices, wearables, and ML-driven applications is enabling continuous remote monitoring, personalized care, and intelligent decision support, fundamentally transforming the delivery of healthcare services outside conventional clinical settings.

This convergence is crucial as global healthcare systems face increasing challenges, including aging populations, the management of chronic diseases, and the need for cost-effective, patient-centered solutions. Mobile systems equipped with sensors and IoT capabilities, combined with powerful artificial intelligence (AI) algorithms, can support early diagnosis, proactive intervention, and personalized health management at home and in the community. These technologies not only enhance patient outcomes, but also reduce the burden on healthcare facilities and providers.

The aim of this Special Issue is to gather cutting-edge research and innovative applications that demonstrate how smart mobile and ML technologies can advance home and community healthcare. This aligns with the Electronics journal’s scope by showcasing how emerging technologies, including wireless communications, bioelectronics, artificial intelligence, and signal processing, can be harnessed to address critical healthcare challenges.

In this Special Issue, original research articles and comprehensive reviews are welcome. Research areas may include, but are not limited to, the following topics:

  • Mobile health (mHealth) platforms for remote monitoring and telemedicine
  • Wearable sensor technologies for home healthcare
  • Machine learning applications for chronic disease management at home
  • IoT-enabled home healthcare systems
  • Edge AI and real-time signal processing for mobile health devices
  • Wireless communications and networks for remote health monitoring
  • AI-assisted diagnosis and decision support in community care
  • Smart rehabilitation and assistive technologies for home use
  • Integration of smart mobile devices with healthcare information systems
  • Privacy and security concerns related to healthcare and biomedical applications
  • Smart sensors, hardware accelerators, and wearable devices for home and community healthcare
  • Multidisciplinary research, such as the sociological dimensions of AI in healthcare

We believe this Special Issue will provide a timely and impactful platform for researchers, practitioners, and industry experts to share their latest developments, address challenges, and inspire future innovations in smart and AI-powered home and community healthcare.

We look forward to receiving your contributions.

Dr. Ao Li
Dr. Geng Yuan
Dr. Na Gong
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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized 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

  • smart healthcare
  • mobile health
  • machine learning
  • deep learning
  • internet of things

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 1973 KB  
Article
Evolutionary Synthesis of QRS Detection Algorithms for Wearable ECG-Based Heartbeat Classification
by Wojciech Reklewski, Jeremiasz Potoczny and Piotr Augustyniak
Electronics 2026, 15(18), 4269; https://doi.org/10.3390/electronics15184269 - 18 Sep 2026
Viewed by 44
Abstract
Existing evolutionary approaches to QRS detection are confined to the parametric tuning of rigid, human-designed pipelines or black-box neural architecture searches. This work applies evolutionary methods for the synthesis of QRS detection algorithms, evolving both the operational pipeline architecture and its underlying parameters [...] Read more.
Existing evolutionary approaches to QRS detection are confined to the parametric tuning of rigid, human-designed pipelines or black-box neural architecture searches. This work applies evolutionary methods for the synthesis of QRS detection algorithms, evolving both the operational pipeline architecture and its underlying parameters simultaneously. A three-class heartbeat classifier (Normal, Ventricular, Other classes) based on the parallel operation of seven QRS detectors was designed. The detectors comprise algorithms from the literature and evolutionary synthesized QRS detectors. The differences in the R-peak detection times served as the feature signal for a decision tree classifier, which performed the final heartbeat classification. The overall accuracy of the proposed classification method for the test dataset was 95.82%, sensitivity was 93.05%, specificity was 97.50%, and the F1-score was 91.74%. The results achieved confirm that synthesized detectors provide valuable complementary timing information on relative R-peak detection times in the proposed heartbeat classifier with seven parallel QRS detectors. Careful detector selection can provide an effective compromise between classification quality and system complexity. The proposed method is applicable for real-time mobile HRV analysis and ischemia detection. Full article
(This article belongs to the Special Issue Smart Mobile and Machine Learning Technologies for Home and Community Healthcare)
►▼ Show Figures

Figure 1

23 pages, 3824 KB  
Article
Comparative Performance of Classical Statistical and Machine Learning Models for Melanoma Classification
by Diego Pagnoncelli, Gian Luca Viganò and Veronica Cimolin
Electronics 2026, 15(17), 3944; https://doi.org/10.3390/electronics15173944 - 2 Sep 2026
Viewed by 155
Abstract
Early and accurate classification of melanoma is essential for improving patient outcomes and supporting clinical decision-making. Although numerous predictive models have been proposed, comparisons between classical statistical approaches and modern machine learning algorithms are often limited by heterogeneous analytical workflows and inconsistent validation [...] Read more.
Early and accurate classification of melanoma is essential for improving patient outcomes and supporting clinical decision-making. Although numerous predictive models have been proposed, comparisons between classical statistical approaches and modern machine learning algorithms are often limited by heterogeneous analytical workflows and inconsistent validation strategies. This study aimed to compare the predictive performance of classical statistical and machine learning models for melanoma classification using a fully reproducible analytical framework. A retrospective observational study was conducted using the publicly available BCN20000 dermoscopic dataset from the ISIC Archive. After standardized data preprocessing, four routinely available clinical variables (age, sex, anatomical site and melanocytic status) were used to develop Logistic Regression, Generalized Additive Models, Random Forest and Extreme Gradient Boosting (XGBoost) classifiers. All models were trained and evaluated using the same stratified training/testing split, and their performance was assessed through discrimination, calibration and SHAP explainability analysis. Machine learning models, particularly XGBoost and Random Forest, achieved superior predictive performance compared with conventional statistical approaches, while patient age emerged as the most influential predictor of malignancy. The proposed framework provides a transparent and reproducible approach for objectively comparing predictive models and supports the development of accurate, interpretable, and reproducible clinical decision-support systems for melanoma classification. Full article
(This article belongs to the Special Issue Smart Mobile and Machine Learning Technologies for Home and Community Healthcare)
►▼ Show Figures

Figure 1

15 pages, 3730 KB  
Article
A Lightweight Machine Learning-Based Visual Condition Estimation During Treadmill Use: The Effect of Blindfolding on Gait Stability During Different Walking Additional Tasks
by Yuan Bian, Xuan Huang, Bo Wu and Shoji Nishimura
Electronics 2026, 15(17), 3913; https://doi.org/10.3390/electronics15173913 - 31 Aug 2026
Viewed by 227
Abstract
When a subject’s visual condition is restricted (e.g., blindfolding), it is more difficult to walk while performing an additional task (e.g., drinking, a phone call, etc.) at the same time. However, previous research indicates that it remains unknown whether the restricted viewing condition [...] Read more.
When a subject’s visual condition is restricted (e.g., blindfolding), it is more difficult to walk while performing an additional task (e.g., drinking, a phone call, etc.) at the same time. However, previous research indicates that it remains unknown whether the restricted viewing condition affects the subjects’ gait stability with different additional tasks. This study developed a smart-insole-based analysis framework to identify which gait features differed between normal-vision and blindfolded walking across tasks and to assess whether the extracted features could predict visual condition. To be specific, a total of 12 healthy adults with normal vision were invited for a controlled treadmill-walking experiment under normal-vision and blindfolded conditions with smart insoles. They needed to complete the baseline walking and three tasks—drinking, a phone call, and photography. Task-specific differences were assessed using paired t-tests with within-domain Benjamini–Hochberg correction. The results showed task-specific gait differences between the two visual conditions, including a smaller mean plantar contact area during baseline walking, a longer mean stride time during drinking, and lower mean plantar pressure during the drinking and phone call tasks. Based on this, the three gait features showing the clearest differences between visual conditions were selected for machine learning prediction. The results show that the random forest model achieved the highest overall balanced accuracy of 0.646. Mean plantar pressure, mean stride time, and mean plantar contact area were repeatedly selected during model training, indicating that these features contained information relevant to distinguishing the two visual conditions. This study provides information that may support future treadmill safety assessment and supervision for people with limited visual information by characterizing task-specific gait differences under different visual conditions. Full article
(This article belongs to the Special Issue Smart Mobile and Machine Learning Technologies for Home and Community Healthcare)
►▼ Show Figures

Figure 1

18 pages, 1717 KB  
Article
Smart Diaper Sensor-Based Voiding-Pattern Classification Using Label-Efficient Contrastive Time-Series Learning
by Hakjin Lee, Seung-Min Jeong, Chaelin Seok, Yeongje Park, Sijin Kim, Jae Heon Kim, Ui Cheol Lee, Byeong Hun Jeong and Eui Chul Lee
Electronics 2026, 15(16), 3657; https://doi.org/10.3390/electronics15163657 - 17 Aug 2026
Viewed by 297
Abstract
Smart-diaper signals collected during routine care are affected by sensor noise, transmission gaps, variable event durations, and limited labels, making normal voiding (NV) and urinary incontinence (UI) difficult to distinguish using threshold-based detection alone. We developed a label-efficient time-series classification framework based on [...] Read more.
Smart-diaper signals collected during routine care are affected by sensor noise, transmission gaps, variable event durations, and limited labels, making normal voiding (NV) and urinary incontinence (UI) difficult to distinguish using threshold-based detection alone. We developed a label-efficient time-series classification framework based on Context-Aware Temporal Contrastive Coding (CA-TCC) using the resistance (RVAL) channel of a smart-diaper sensor. Recordings from 97 older residents across three long-term care facilities were quality-filtered, aggregated at 3 min intervals, screened for candidate events, and interpolated to fixed-length inputs. CA-TCC was pre-trained on an unlabeled candidate-event pool and adapted using 4877 manually labeled events. The linear-probe, full fine-tuning, and class-aware pseudo-label retraining configurations were evaluated using participant-grouped five-fold cross-validation. The selected semi-supervised configuration achieved 82.12±2.33% accuracy, 82.12±2.32% macro-F1, and an AUC of 0.895±0.018 (mean ± 95% confidence interval), exceeding the strongest classical baseline by 4.80 macro-F1 percentage points. Its macro-F1 increased from 79.22±1.84% with 1000 labeled events to 81.97±1.82% with the full labeled set, whereas full fine-tuning showed greater fold-to-fold variability. Aggregated LIME analysis over 300 held-out events did not support localization of the model’s evidence to the event onset. These results indicate that contrastive pre-training can support smart-diaper voiding-pattern classification when labeled data are limited. Full article
(This article belongs to the Special Issue Smart Mobile and Machine Learning Technologies for Home and Community Healthcare)
►▼ Show Figures

Figure 1

12 pages, 2411 KB  
Article
Diabetes Prediction and Detection System Through a Recurrent Neural Network in a Sensor Device
by Md Fuyad Al Masud, Md Hasib Fakir, Luke Young, Na Gong and Danling Wang
Electronics 2025, 14(21), 4207; https://doi.org/10.3390/electronics14214207 - 28 Oct 2025
Cited by 6 | Viewed by 1100
Abstract
Diabetes is a significant global health issue that demands accurate, accessible, and non-invasive diagnostic methods for effective prevention and treatment. Conventional diagnostic systems are often expensive, painful, time-consuming, and not universally available. In this study, we present a smart system for acetone estimation [...] Read more.
Diabetes is a significant global health issue that demands accurate, accessible, and non-invasive diagnostic methods for effective prevention and treatment. Conventional diagnostic systems are often expensive, painful, time-consuming, and not universally available. In this study, we present a smart system for acetone estimation using simulated breath and a recurrent neural network (RNN) model. The detection system employs a new sensor fabricated from a composite of 1D nanostructured KWO (K2W7O22) and 2D nanosheet MXene (Ti3C2), designed to measure the chemiresistive response to acetone by mimicking human breath. Resistance data collected by the sensor are used to compute sensitivity values for each acetone concentration (in parts per million, PPM). These values serve as input features for the RNN model, which learns to evaluate health as healthy, high-risk, or diabetic. Trained on acetone concentrations ranging from 0.4 to 2 PPM, the RNN achieves an R2 of 99.41% in predicting potential for accurate breath acetone prediction. In future work, we aim to develop a smart device and mobile application based on this model to facilitate real-time diabetes monitoring and prediction. Full article
(This article belongs to the Special Issue Smart Mobile and Machine Learning Technologies for Home and Community Healthcare)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop