sensors-logo

Journal Browser

Journal Browser

Special Issue "Explainable and Augmented Machine Learning for Biosignals and Biomedical Images"

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: 30 June 2021.

Special Issue Editors

Dr. Cosimo Ieracitano
E-Mail Website
Guest Editor
DICEAM Department, Mediterranea University of Reggio Calabria, Via Graziella Feo di Vito, 89060 Reggio Calabria, Italy
Interests: information theory; machine learning; deep learning; explainable machine learning; biomedical signal processing; brain computer interface; cybersecurity; computer vision; material informatics
Dr. Mufti Mahmud
E-Mail Website
Guest Editor
School of Science and Technology, Nottingham Trent University, Clifton, NG11 8NS Nottingham, UK
Interests: brain informatics; data analytics; brain–machine interfacing; Internet of Healthcare Things
Special Issues and Collections in MDPI journals
Dr. Maryam Doborjeh
E-Mail Website
Guest Editor
Maryam Doborjeh, Auckland University of Technology, Auckland 1010, New Zealand
Interests: Neuroinformatics and Neurocomputational Modelling; Artificial Intelligence; Machine Learning; advanced Deep Learning techniques; Spiking Neural Networks and applications in Brain Diseases and Cognitive Impairment (Dementia, MCI, Stroke); Mental Health Information Technology and Spatiotemporal Brain Data Modelling; Personalised Predictive Modelling of static and dynamic data streams; Data Science
Prof. Dr. Aime' Lay-Ekuakille
E-Mail Website
Guest Editor
Department of Innovation Engineering, University of Salento, 73100 Lecce, Italy
Interests: environmental and biomedical instrumentation and measurements even using nanotechnology for devices; advanced signal processing; sensors and sensing systems; machine learning
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

In recent decades, machine learning (ML) techniques have been providing encouraging breakthroughs in the biomedical research field, reporting outstanding predictive and classification performance.

However, ML algorithms are often perceived as black boxes with no explanation about the final decision process. In this context, explainable machine learning (XML) techniques intend to “open” the black box and provide further insight into the inner working mechanisms underlying artificial intelligence algorithms. Hence, the goal of XML is to explain and interpret outcomes, predictions, decisions, and recommendations automatically achieved by ML models in order to create more comprehensible and transparent machine decisions.

In medical application, such additional understanding, alongside the augmented availability of medical/clinical data acquired from even more interconnected biosensors (based on the Internet of Things (IoT) paradigm) as well as the recent advances in augmented techniques (e.g., generative adversarial network) able to generate synthetic samples, could play a significant role for clinicians, specifically, in the final human decision.

The proposed Special Issue aims to collate innovative explainable ML-based approaches and augmented ML-based methodologies, as well as comprehensive survey papers, applied to problems in medicine and healthcare in order to develop the next generation of systems that can potentially lead to relevant advances in clinical and biomedical research.

Dr. Cosimo Ieracitano
Dr. Mufti Mahmud
Dr. Maryam Doborjeh
Dr. Aime' Lay-Ekuakille
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 papers will be 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. Sensors 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 2200 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

  • Artificial Intelligence
  • Pattern recognition
  • Explainable machine learning
  • Explainable deep learning
  • Interpretability
  • Explainability
  • Classification
  • Augmented machine learning
  • IoT and biosensors
  • Sensing technology for biomedical applications
  • Biomedical signal processing
  • Biosignals (EEG, ECG, EMG, etc.)
  • Imaging technology for biomedical applications
  • Biomedical image processing
  • Biomedical images (MRI, RX, PET, etc.)

Published Papers (2 papers)

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

Research

Open AccessArticle
A Novel Coupled Reaction-Diffusion System for Explainable Gene Expression Profiling
Sensors 2021, 21(6), 2190; https://0-doi-org.brum.beds.ac.uk/10.3390/s21062190 - 21 Mar 2021
Viewed by 406
Abstract
Machine learning (ML)-based algorithms are playing an important role in cancer diagnosis and are increasingly being used to aid clinical decision-making. However, these commonly operate as ‘black boxes’ and it is unclear how decisions are derived. Recently, techniques have been applied to help [...] Read more.
Machine learning (ML)-based algorithms are playing an important role in cancer diagnosis and are increasingly being used to aid clinical decision-making. However, these commonly operate as ‘black boxes’ and it is unclear how decisions are derived. Recently, techniques have been applied to help us understand how specific ML models work and explain the rational for outputs. This study aims to determine why a given type of cancer has a certain phenotypic characteristic. Cancer results in cellular dysregulation and a thorough consideration of cancer regulators is required. This would increase our understanding of the nature of the disease and help discover more effective diagnostic, prognostic, and treatment methods for a variety of cancer types and stages. Our study proposes a novel explainable analysis of potential biomarkers denoting tumorigenesis in non-small cell lung cancer. A number of these biomarkers are known to appear following various treatment pathways. An enhanced analysis is enabled through a novel mathematical formulation for the regulators of mRNA, the regulators of ncRNA, and the coupled mRNA–ncRNA regulators. Temporal gene expression profiles are approximated in a two-dimensional spatial domain for the transition states before converging to the stationary state, using a system comprised of coupled-reaction partial differential equations. Simulation experiments demonstrate that the proposed mathematical gene-expression profile represents a best fit for the population abundance of these oncogenes. In future, our proposed solution can lead to the development of alternative interpretable approaches, through the application of ML models to discover unknown dynamics in gene regulatory systems. Full article
Show Figures

Figure 1

Open AccessArticle
Interpretability of Spatiotemporal Dynamics of the Brain Processes Followed by Mindfulness Intervention in a Brain-Inspired Spiking Neural Network Architecture
Sensors 2020, 20(24), 7354; https://0-doi-org.brum.beds.ac.uk/10.3390/s20247354 - 21 Dec 2020
Cited by 1 | Viewed by 849
Abstract
Mindfulness training is associated with improvements in psychological wellbeing and cognition, yet the specific underlying neurophysiological mechanisms underpinning these changes are uncertain. This study uses a novel brain-inspired artificial neural network to investigate the effect of mindfulness training on electroencephalographic function. Participants completed [...] Read more.
Mindfulness training is associated with improvements in psychological wellbeing and cognition, yet the specific underlying neurophysiological mechanisms underpinning these changes are uncertain. This study uses a novel brain-inspired artificial neural network to investigate the effect of mindfulness training on electroencephalographic function. Participants completed a 4-tone auditory oddball task (that included targets and physically similar distractors) at three assessment time points. In Group A (n = 10), these tasks were given immediately prior to 6-week mindfulness training, immediately after training and at a 3-week follow-up; in Group B (n = 10), these were during an intervention waitlist period (3 weeks prior to training), pre-mindfulness training and post-mindfulness training. Using a spiking neural network (SNN) model, we evaluated concurrent neural patterns generated across space and time from features of electroencephalographic data capturing the neural dynamics associated with the event-related potential (ERP). This technique capitalises on the temporal dynamics of the shifts in polarity throughout the ERP and spatially across electrodes. Findings support anteriorisation of connection weights in response to distractors relative to target stimuli. Right frontal connection weights to distractors were associated with trait mindfulness (positively) and depression (inversely). Moreover, mindfulness training was associated with an increase in connection weights to targets (bilateral frontal, left frontocentral, and temporal regions only) and distractors. SNN models were superior to other machine learning methods in the classification of brain states as a function of mindfulness training. Findings suggest SNN models can provide useful information that differentiates brain states based on distinct task demands and stimuli, as well as changes in brain states as a function of psychological intervention. Full article
Show Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Explainable transfer learning of brain signals using brain-inspired spiking neural networks
Authors: Nik Kasabov
Affiliation: FIEEE, FRSNZ, FINNS College of Fellows. Professor of Knowledge Engineering, School of Engineering, Comp. and Mathem. Sciences, Faculty DCT. Founding Director of KEDRI, Auckland University of Technology, Auckland 1010.

Title: Quantitative Interpretation of CNN in Depression Identification
Authors: Hengjin Ke1 and Fengqin Wang2 and Fang Hu3 and Xinhua Zhang4
Affiliation: 1 HuBei Polytechnic University and Wuhan University, 2 Hubei Normal University, 3 Huangshi Central Hospital, 4 Peking University People's Hospital
Abstract: Online EEG classification can accurately assess the brain status of patients with Major Depression Disable (MDD) and track their development status in time, which can minimize the risk of falling into danger and suicide. However, it remains a grand research due to (1) the embedded intensive noises and the intrinsic non-stationarity determined by the evolution of brain states, (2) the lack of effective decoupling of the complex relationship between brain region and neural network during the attack of brain diseases. This study design a CNN to classify the EEG data and then provide the quantitative interpretation why the classifier is suitable.

Back to TopTop