Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.4
Journals
Sensors
Special Issues
Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing,...
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification

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

Deadline for manuscript submissions: closed (31 March 2020) | Viewed by 88918

Special Issue Editor

Prof. Dr. George Magoulas

E-Mail Website
Guest Editor
Department of Computer Science and Information Systems, Birkbeck College, University of London, London WC1E 7HX, UK
Interests: intelligent optimization; context awareness; neural computing; deep learning; data-driven modelling; intelligent systems; machine learning; nature-inspired computing; user modelling; computational models of learning and cognition
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Psycho-physiological signals have been demonstrated as being useful in several applications for assessing emotional experiences, modelling cognitive processes, user and player modelling, human activity recognition, classification of facial expressions, detection of behavioural changes and so on. Signals come from a wide range of sensors, such as wearable sensors, mobile sensors, cameras, heart rate monitoring devices, EEG headcaps and headbands, ECG sensors, breathing monitors, EMG sensors, and temperature sensors. However, the use of these signals poses several challenges for reliable data processing, modelling and classification, as it is influenced by different types of environmental and biological sources of noise, artefacts and interference. Methods that employ machine learning and deep learning appear eminently suitable for these challenging tasks.

This Special Issue will present state-of-the-art machine learning and deep learning approaches for data processing, modelling, pattern recognition, and the classification of psycho-physiological signals, and for the development of intelligent systems that use psycho-physiological signals.

Prof. Dr. George Magoulas
Guest Editor

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. 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 2600 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

(1) Processing of psycho-physiological signals and time-series: 
  • Data transformation 
  • Dimensionality reduction 
  • Feature selection 
  • Filtering

(2) Modelling, classification and pattern recognition methods: 

  • Bio-inspired computing 
  • Clustering 
  • Decision trees 
  • Deep networks 
  • Ensemble learning 
  • Fuzzy logic 
  • Genetic and evolution algorithms 
  • Kernel methods 
  • Machine learning 
  • Neural networks 
  • Random forests 
  • Support vectors
  • Tensors

(3) Visualisation of psycho-physiological signals and time-series

(4) Intelligent systems and human-machine systems that use psycho-physiological signals

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 (16 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

12 pages, 2325 KiB  
Article
A Lean and Performant Hierarchical Model for Human Activity Recognition Using Body-Mounted Sensors
by Isaac Debache, Lorène Jeantet, Damien Chevallier, Audrey Bergouignan and Cédric Sueur
Sensors 2020, 20(11), 3090; https://doi.org/10.3390/s20113090 - 29 May 2020
Cited by 17 | Viewed by 3126
Abstract
Here we propose a new machine learning algorithm for classification of human activities by means of accelerometer and gyroscope signals. Based on a novel hierarchical system of logistic regression classifiers and a relatively small set of features extracted from the filtered signals, the [...] Read more.
Here we propose a new machine learning algorithm for classification of human activities by means of accelerometer and gyroscope signals. Based on a novel hierarchical system of logistic regression classifiers and a relatively small set of features extracted from the filtered signals, the proposed algorithm outperformed previous work on the DaLiAc (Daily Life Activity) and mHealth datasets. The algorithm also represents a significant improvement in terms of computational costs and requires no feature selection and hyper-parameter tuning. The algorithm still showed a robust performance with only two (ankle and wrist) out of the four devices (chest, wrist, hip and ankle) placed on the body (96.8% vs. 97.3% mean accuracy for the DaLiAc dataset). The present work shows that low-complexity models can compete with heavy, inefficient models in classification of advanced activities when designed with a careful upstream inspection of the data. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

17 pages, 740 KiB  
Article
ECG Identification For Personal Authentication Using LSTM-Based Deep Recurrent Neural Networks
by Beom-Hun Kim and Jae-Young Pyun
Sensors 2020, 20(11), 3069; https://doi.org/10.3390/s20113069 - 29 May 2020
Cited by 62 | Viewed by 6402
Abstract
Securing personal authentication is an important study in the field of security. Particularly, fingerprinting and face recognition have been used for personal authentication. However, these systems suffer from certain issues, such as fingerprinting forgery, or environmental obstacles. To address forgery or spoofing identification [...] Read more.
Securing personal authentication is an important study in the field of security. Particularly, fingerprinting and face recognition have been used for personal authentication. However, these systems suffer from certain issues, such as fingerprinting forgery, or environmental obstacles. To address forgery or spoofing identification problems, various approaches have been considered, including electrocardiogram (ECG). For ECG identification, linear discriminant analysis (LDA), support vector machine (SVM), principal component analysis (PCA), deep recurrent neural network (DRNN), and recurrent neural network (RNN) have been conventionally used. Certain studies have shown that the RNN model yields the best performance in ECG identification as compared with the other models. However, these methods require a lengthy input signal for high accuracy. Thus, these methods may not be applied to a real-time system. In this study, we propose using bidirectional long short-term memory (LSTM)-based deep recurrent neural networks (DRNN) through late-fusion to develop a real-time system for ECG-based biometrics identification and classification. We suggest a preprocessing procedure for the quick identification and noise reduction, such as a derivative filter, moving average filter, and normalization. We experimentally evaluated the proposed method using two public datasets: MIT-BIH Normal Sinus Rhythm (NSRDB) and MIT-BIH Arrhythmia (MITDB). The proposed LSTM-based DRNN model shows that in NSRDB, the overall precision was 100%, recall was 100%, accuracy was 100%, and F1-score was 1. For MITDB, the overall precision was 99.8%, recall was 99.8%, accuracy was 99.8%, and F1-score was 0.99. Our experiments demonstrate that the proposed model achieves an overall higher classification accuracy and efficiency compared with the conventional LSTM approach. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Graphical abstract

19 pages, 16679 KiB  
Article
Prediction of Visual Memorability with EEG Signals: A Comparative Study
by Sang-Yeong Jo and Jin-Woo Jeong
Sensors 2020, 20(9), 2694; https://doi.org/10.3390/s20092694 - 9 May 2020
Cited by 8 | Viewed by 3549
Abstract
Visual memorability is a method to measure how easily media contents can be memorized. Predicting the visual memorability of media contents has recently become more important because it can affect the design principles of multimedia visualization, advertisement, etc. Previous studies on the prediction [...] Read more.
Visual memorability is a method to measure how easily media contents can be memorized. Predicting the visual memorability of media contents has recently become more important because it can affect the design principles of multimedia visualization, advertisement, etc. Previous studies on the prediction of the visual memorability of images generally exploited visual features (e.g., color intensity and contrast) or semantic information (e.g., class labels) that can be extracted from images. Some other works tried to exploit electroencephalography (EEG) signals of human subjects to predict the memorability of text (e.g., word pairs). Compared to previous works, we focus on predicting the visual memorability of images based on human biological feedback (i.e., EEG signals). For this, we design a visual memory task where each subject is asked to answer whether they correctly remember a particular image 30 min after glancing at a set of images sampled from the LaMemdataset. During the visual memory task, EEG signals are recorded from subjects as human biological feedback. The collected EEG signals are then used to train various classification models for prediction of image memorability. Finally, we evaluate and compare the performance of classification models, including deep convolutional neural networks and classical methods, such as support vector machines, decision trees, and k-nearest neighbors. The experimental results validate that the EEG-based prediction of memorability is still challenging, but a promising approach with various opportunities and potentials. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

17 pages, 497 KiB  
Article
Speech Emotion Recognition Based on Selective Interpolation Synthetic Minority Over-Sampling Technique in Small Sample Environment
by Zhen-Tao Liu, Bao-Han Wu, Dan-Yun Li, Peng Xiao and Jun-Wei Mao
Sensors 2020, 20(8), 2297; https://doi.org/10.3390/s20082297 - 17 Apr 2020
Cited by 17 | Viewed by 3252
Abstract
Speech emotion recognition often encounters the problems of data imbalance and redundant features in different application scenarios. Researchers usually design different recognition models for different sample conditions. In this study, a speech emotion recognition model for a small sample environment is proposed. A [...] Read more.
Speech emotion recognition often encounters the problems of data imbalance and redundant features in different application scenarios. Researchers usually design different recognition models for different sample conditions. In this study, a speech emotion recognition model for a small sample environment is proposed. A data imbalance processing method based on selective interpolation synthetic minority over-sampling technique (SISMOTE) is proposed to reduce the impact of sample imbalance on emotion recognition results. In addition, feature selection method based on variance analysis and gradient boosting decision tree (GBDT) is introduced, which can exclude the redundant features that possess poor emotional representation. Results of experiments of speech emotion recognition on three databases (i.e., CASIA, Emo-DB, SAVEE) show that our method obtains average recognition accuracy of 90.28% (CASIA), 75.00% (SAVEE) and 85.82% (Emo-DB) for speaker-dependent speech emotion recognition which is superior to some state-of-the-arts works. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

24 pages, 8129 KiB  
Article
Gait Rhythm Dynamics for Neuro-Degenerative Disease Classification via Persistence Landscape- Based Topological Representation
by Yan Yan, Kamen Ivanov, Olatunji Mumini Omisore, Tobore Igbe, Qiuhua Liu, Zedong Nie and Lei Wang
Sensors 2020, 20(7), 2006; https://doi.org/10.3390/s20072006 - 3 Apr 2020
Cited by 15 | Viewed by 4110
Abstract
Neuro-degenerative disease is a common progressive nervous system disorder that leads to serious clinical consequences. Gait rhythm dynamics analysis is essential for evaluating clinical states and improving quality of life for neuro-degenerative patients. The magnitude of stride-to-stride fluctuations and corresponding changes over time—gait [...] Read more.
Neuro-degenerative disease is a common progressive nervous system disorder that leads to serious clinical consequences. Gait rhythm dynamics analysis is essential for evaluating clinical states and improving quality of life for neuro-degenerative patients. The magnitude of stride-to-stride fluctuations and corresponding changes over time—gait dynamics—reflects the physiology of gait, in quantifying the pathologic alterations in the locomotor control system of health subjects and patients with neuro-degenerative diseases. Motivated by algebra topology theory, a topological data analysis-inspired nonlinear framework was adopted in the study of the gait dynamics. Meanwhile, the topological representation–persistence landscapes were used as input of classifiers in order to distinguish different neuro-degenerative disease type from healthy. In this work, stride-to-stride time series from healthy control (HC) subjects are compared with the gait dynamics from patients with amyotrophic lateral sclerosis (ALS), Huntington’s disease (HD), and Parkinson’s disease (PD). The obtained results show that the proposed methodology discriminates healthy subjects from subjects with other neuro-degenerative diseases with relatively high accuracy. In summary, our study is the first attempt to provide a topological representation-based method into the disease classification with gait rhythms measured from the stride intervals to visualize gait dynamics and classify neuro-degenerative diseases. The proposed method could be potentially used in earlier interventions and state monitoring. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

14 pages, 4897 KiB  
Article
Multi-Scale Spatio-Temporal Feature Extraction and Depth Estimation from Sequences by Ordinal Classification
by Yang Liu
Sensors 2020, 20(7), 1979; https://doi.org/10.3390/s20071979 - 1 Apr 2020
Cited by 4 | Viewed by 3010
Abstract
Depth estimation is a key problem in 3D computer vision and has a wide variety of applications. In this paper we explore whether deep learning network can predict depth map accurately by learning multi-scale spatio-temporal features from sequences and recasting the depth estimation [...] Read more.
Depth estimation is a key problem in 3D computer vision and has a wide variety of applications. In this paper we explore whether deep learning network can predict depth map accurately by learning multi-scale spatio-temporal features from sequences and recasting the depth estimation from a regression task to an ordinal classification task. We design an encoder-decoder network with several multi-scale strategies to improve its performance and extract spatio-temporal features with ConvLSTM. The results of our experiments show that the proposed method has an improvement of almost 10% in error metrics and up to 2% in accuracy metrics. The results also tell us that extracting spatio-temporal features can dramatically improve the performance in depth estimation task. We consider to extend this work to a self-supervised manner to get rid of the dependence on large-scale labeled data. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

20 pages, 4762 KiB  
Article
A Novel Outdoor Positioning Technique Using LTE Network Fingerprints
by Da Li, Yingke Lei and Haichuan Zhang
Sensors 2020, 20(6), 1691; https://doi.org/10.3390/s20061691 - 18 Mar 2020
Cited by 18 | Viewed by 3654
Abstract
In recent years, wireless-based fingerprint positioning has attracted increasing research attention owing to its position-related features and applications in the Internet of Things (IoT). In this paper, by leveraging long-term evolution (LTE) signals, a novel deep-learning-based fingerprint positioning approach is proposed to solve [...] Read more.
In recent years, wireless-based fingerprint positioning has attracted increasing research attention owing to its position-related features and applications in the Internet of Things (IoT). In this paper, by leveraging long-term evolution (LTE) signals, a novel deep-learning-based fingerprint positioning approach is proposed to solve the problem of outdoor positioning. Considering the outstanding performance of deep learning in image classification, LTE signal measurements are converted into location grayscale images to form a fingerprint database. In order to deal with the instability of LTE signals, prevent the gradient dispersion problem, and increase the robustness of the proposed deep neural network (DNN), the following methods are adopted: First, cross-entropy is used as the loss function of the DNN. Second, the learning rate of the proposed DNN is dynamically adjusted. Third, this paper adopted several data enhancement techniques. To find the best positioning fingerprint and method, three types of fingerprint and five positioning models are compared. Finally, by using a deep residual network (Resnet) and transfer learning, a hierarchical structure training method is proposed. The proposed Resnet is used to train with the united fingerprint image database to obtain a positioning model called a coarse localizer. By using the prior knowledge of the pretrained Resnet, feed-forward neural network (FFNN)-based transfer learning is used to train with the united fingerprint database to obtain a better positioning model, called a fine localizer. The experimental results convincingly show that the proposed DNN can automatically learn the location features of LTE signals and achieve satisfactory positioning accuracy in outdoor environments. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

11 pages, 1712 KiB  
Article
Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG
by Ali Raza Asif, Asim Waris, Syed Omer Gilani, Mohsin Jamil, Hassan Ashraf, Muhammad Shafique and Imran Khan Niazi
Sensors 2020, 20(6), 1642; https://doi.org/10.3390/s20061642 - 15 Mar 2020
Cited by 98 | Viewed by 9458
Abstract
Electromyography (EMG) is a measure of electrical activity generated by the contraction of muscles. Non-invasive surface EMG (sEMG)-based pattern recognition methods have shown the potential for upper limb prosthesis control. However, it is still insufficient for natural control. Recent advancements in deep learning [...] Read more.
Electromyography (EMG) is a measure of electrical activity generated by the contraction of muscles. Non-invasive surface EMG (sEMG)-based pattern recognition methods have shown the potential for upper limb prosthesis control. However, it is still insufficient for natural control. Recent advancements in deep learning have shown tremendous progress in biosignal processing. Multiple architectures have been proposed yielding high accuracies (>95%) for offline analysis, yet the delay caused due to optimization of the system remains a challenge for its real-time application. From this arises a need for optimized deep learning architecture based on fine-tuned hyper-parameters. Although the chance of achieving convergence is random, however, it is important to observe that the performance gain made is significant enough to justify extra computation. In this study, the convolutional neural network (CNN) was implemented to decode hand gestures from the sEMG data recorded from 18 subjects to investigate the effect of hyper-parameters on each hand gesture. Results showed that the learning rate set to either 0.0001 or 0.001 with 80-100 epochs significantly outperformed (p < 0.05) other considerations. In addition, it was observed that regardless of network configuration some motions (close hand, flex hand, extend the hand and fine grip) performed better (83.7% ± 13.5%, 71.2% ± 20.2%, 82.6% ± 13.9% and 74.6% ± 15%, respectively) throughout the course of study. So, a robust and stable myoelectric control can be designed on the basis of the best performing hand motions. With improved recognition and uniform gain in performance, the deep learning-based approach has the potential to be a more robust alternative to traditional machine learning algorithms. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Graphical abstract

19 pages, 3917 KiB  
Article
Wearable Emotion Recognition Using Heart Rate Data from a Smart Bracelet
by Lin Shu, Yang Yu, Wenzhuo Chen, Haoqiang Hua, Qin Li, Jianxiu Jin and Xiangmin Xu
Sensors 2020, 20(3), 718; https://doi.org/10.3390/s20030718 - 28 Jan 2020
Cited by 109 | Viewed by 17871
Abstract
Emotion recognition and monitoring based on commonly used wearable devices can play an important role in psychological health monitoring and human-computer interaction. However, the existing methods cannot rely on the common smart bracelets or watches for emotion monitoring in daily life. To address [...] Read more.
Emotion recognition and monitoring based on commonly used wearable devices can play an important role in psychological health monitoring and human-computer interaction. However, the existing methods cannot rely on the common smart bracelets or watches for emotion monitoring in daily life. To address this issue, our study proposes a method for emotional recognition using heart rate data from a wearable smart bracelet. A ‘neutral + target’ pair emotion stimulation experimental paradigm was presented, and a dataset of heart rate from 25 subjects was established, where neutral plus target emotion (neutral, happy, and sad) stimulation video pairs from China’s standard Emotional Video Stimuli materials (CEVS) were applied to the recruited subjects. Normalized features from the data of target emotions normalized by the baseline data of neutral mood were adopted. Emotion recognition experiment results approved the effectiveness of ‘neutral + target’ video pair simulation experimental paradigm, the baseline setting using neutral mood data, and the normalized features, as well as the classifiers of Adaboost and GBDT on this dataset. This method will promote the development of wearable consumer electronic devices for monitoring human emotional moods. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

20 pages, 3838 KiB  
Article
Classification of Motor Functions from Electroencephalogram (EEG) Signals Based on an Integrated Method Comprised of Common Spatial Pattern and Wavelet Transform Framework
by Norashikin Yahya, Huwaida Musa, Zhong Yi Ong and Irraivan Elamvazuthi
Sensors 2019, 19(22), 4878; https://doi.org/10.3390/s19224878 - 8 Nov 2019
Cited by 29 | Viewed by 4559
Abstract
In this work, an algorithm for the classification of six motor functions from an electroencephalogram (EEG) signal that combines a common spatial pattern (CSP) filter and a continuous wavelet transform (CWT), is investigated. The EEG data comprise six grasp-and-lift events, which are used [...] Read more.
In this work, an algorithm for the classification of six motor functions from an electroencephalogram (EEG) signal that combines a common spatial pattern (CSP) filter and a continuous wavelet transform (CWT), is investigated. The EEG data comprise six grasp-and-lift events, which are used to investigate the potential of using EEG as input signals with brain computer interface devices for controlling prosthetic devices for upper limb movement. Selected EEG channels are the ones located over the motor cortex, C3, Cz and C4, as well as at the parietal region, P3, Pz and P4. In general, the proposed algorithm includes three main stages, band pass filtering, CSP filtering, and wavelet transform and training on GoogLeNet for feature extraction, feature learning and classification. The band pass filtering is performed to select the EEG signal in the band of 7 Hz to 30 Hz while eliminating artifacts related to eye blink, heartbeat and muscle movement. The CSP filtering is applied on two-class EEG signals that will result in maximizing the power difference between the two-class dataset. Since CSP is mathematically developed for two-class events, the extension to the multiclass paradigm is achieved by using the approach of one class versus all other classes. Subsequently, continuous wavelet transform is used to convert the band pass and CSP filtered signals from selected electrodes to scalograms which are then converted to images in grayscale format. The three scalograms from the motor cortex regions and the parietal region are then combined to form two sets of RGB images. Next, these RGB images become the input to GoogLeNet for classification of the motor EEG signals. The performance of the proposed classification algorithm is evaluated in terms of precision, sensitivity, specificity, accuracy with average values of 94.8%, 93.5%, 94.7%, 94.1%, respectively, and average area under the receiver operating characteristic (ROC) curve equal to 0.985. These results indicate a good performance of the proposed algorithm in classifying grasp-and-lift events from EEG signals. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

12 pages, 570 KiB  
Article
FusionAtt: Deep Fusional Attention Networks for Multi-Channel Biomedical Signals
by Ye Yuan and Kebin Jia
Sensors 2019, 19(11), 2429; https://doi.org/10.3390/s19112429 - 28 May 2019
Cited by 27 | Viewed by 3611
Abstract
Recently, pervasive sensing technologies have been widely applied to comprehensive patient monitoring in order to improve clinical treatment. Various types of biomedical signals collected by different sensing channels provide different aspects of patient health information. However, due to the uncertainty and variability in [...] Read more.
Recently, pervasive sensing technologies have been widely applied to comprehensive patient monitoring in order to improve clinical treatment. Various types of biomedical signals collected by different sensing channels provide different aspects of patient health information. However, due to the uncertainty and variability in clinical observation, not all the channels are relevant and important to the target task. Thus, in order to extract informative representations from multi-channel biosignals, channel awareness has become a key enabler for deep learning in biosignal processing and has attracted increasing research interest in health informatics. Towards this end, we propose FusionAtt—a deep fusional attention network that can learn channel-aware representations of multi-channel biosignals, while preserving complex correlations among all the channels. FusionAtt is able to dynamically quantify the importance of each biomedical channel, and relies on more informative ones to enhance feature representation in an end-to-end manner. We empirically evaluated FusionAtt in two clinical tasks: multi-channel seizure detection and multivariate sleep stage classification. Experimental results showed that FusionAtt consistently outperformed the state-of-the-art models in four different evaluation measurements, demonstrating the effectiveness of the proposed fusional attention mechanism. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

11 pages, 949 KiB  
Article
A Novel Eye Movement Data Transformation Technique that Preserves Temporal Information: A Demonstration in a Face Processing Task
by Michał Król and Magdalena Ewa Król
Sensors 2019, 19(10), 2377; https://doi.org/10.3390/s19102377 - 23 May 2019
Cited by 9 | Viewed by 3502
Abstract
Existing research has shown that human eye-movement data conveys rich information about underlying mental processes, and that the latter may be inferred from the former. However, most related studies rely on spatial information about which different areas of visual stimuli were looked at, [...] Read more.
Existing research has shown that human eye-movement data conveys rich information about underlying mental processes, and that the latter may be inferred from the former. However, most related studies rely on spatial information about which different areas of visual stimuli were looked at, without considering the order in which this occurred. Although powerful algorithms for making pairwise comparisons between eye-movement sequences (scanpaths) exist, the problem is how to compare two groups of scanpaths, e.g., those registered with vs. without an experimental manipulation in place, rather than individual scanpaths. Here, we propose that the problem might be solved by projecting a scanpath similarity matrix, obtained via a pairwise comparison algorithm, to a lower-dimensional space (the comparison and dimensionality-reduction techniques we use are ScanMatch and t-SNE). The resulting distributions of low-dimensional vectors representing individual scanpaths can be statistically compared. To assess if the differences result from temporal scanpath features, we propose to statistically compare the cross-validated accuracies of two classifiers predicting group membership: (1) based exclusively on spatial metrics; (2) based additionally on the obtained scanpath representation vectors. To illustrate, we compare autistic vs. typically-developing individuals looking at human faces during a lab experiment and find significant differences in temporal scanpath features. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

16 pages, 3690 KiB  
Article
A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks
by Hüseyin Kutlu and Engin Avcı
Sensors 2019, 19(9), 1992; https://doi.org/10.3390/s19091992 - 28 Apr 2019
Cited by 86 | Viewed by 8200
Abstract
Rapid classification of tumors that are detected in the medical images is of great importance in the early diagnosis of the disease. In this paper, a new liver and brain tumor classification method is proposed by using the power of convolutional neural network [...] Read more.
Rapid classification of tumors that are detected in the medical images is of great importance in the early diagnosis of the disease. In this paper, a new liver and brain tumor classification method is proposed by using the power of convolutional neural network (CNN) in feature extraction, the power of discrete wavelet transform (DWT) in signal processing, and the power of long short-term memory (LSTM) in signal classification. A CNN–DWT–LSTM method is proposed to classify the computed tomography (CT) images of livers with tumors and to classify the magnetic resonance (MR) images of brains with tumors. The proposed method classifies liver tumors images as benign or malignant and then classifies brain tumor images as meningioma, glioma, and pituitary. In the hybrid CNN–DWT–LSTM method, the feature vector of the images is obtained from pre-trained AlexNet CNN architecture. The feature vector is reduced but strengthened by applying the single-level one-dimensional discrete wavelet transform (1-D DWT), and it is classified by training with an LSTM network. Under the scope of the study, images of 56 benign and 56 malignant liver tumors that were obtained from Fırat University Research Hospital were used and a publicly available brain tumor dataset were used. The experimental results show that the proposed method had higher performance than classifiers, such as K-nearest neighbors (KNN) and support vector machine (SVM). By using the CNN–DWT–LSTM hybrid method, an accuracy rate of 99.1% was achieved in the liver tumor classification and accuracy rate of 98.6% was achieved in the brain tumor classification. We used two different datasets to demonstrate the performance of the proposed method. Performance measurements show that the proposed method has a satisfactory accuracy rate at the liver tumor and brain tumor classifying. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

20 pages, 4496 KiB  
Article
Open Database for Accurate Upper-Limb Intent Detection Using Electromyography and Reliable Extreme Learning Machines
by Vinicius Horn Cene, Mauricio Tosin, Juliano Machado and Alexandre Balbinot
Sensors 2019, 19(8), 1864; https://doi.org/10.3390/s19081864 - 18 Apr 2019
Cited by 42 | Viewed by 6492
Abstract
Surface Electromyography (sEMG) signal processing has a disruptive technology potential to enable a natural human interface with artificial limbs and assistive devices. However, this biosignal real-time control interface still presents several restrictions such as control limitations due to a lack of reliable signal [...] Read more.
Surface Electromyography (sEMG) signal processing has a disruptive technology potential to enable a natural human interface with artificial limbs and assistive devices. However, this biosignal real-time control interface still presents several restrictions such as control limitations due to a lack of reliable signal prediction and standards for signal processing among research groups. Our paper aims to present and validate our sEMG database through the signal classification performed by the reliable forms of our Extreme Learning Machines (ELM) classifiers, used to maintain a more consistent signal classification. To perform the signal processing, we explore the use of a stochastic filter based on the Antonyan Vardan Transform (AVT) in combination with two variations of our Reliable classifiers (denoted R-ELM and R-Regularized ELM (RELM), respectively), to derive a reliability metric from the system, which autonomously selects the most reliable samples for the signal classification. To validate and compare our database and classifiers with related papers, we performed the classification of the whole of Databases 1, 2, and 6 (DB1, DB2, and DB6) of the NINAProdatabase. Our database presented consistent results, while the reliable forms of ELM classifiers matched or outperformed related papers, reaching average accuracies higher than 99 % for the IEEdatabase, while average accuracies of 75.1 %, 79.77 %, and 69.83 % were achieved for NINAPro DB1, DB2, and DB6, respectively. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

24 pages, 3660 KiB  
Article
Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor
by Yanmin Niu, Lan Qin and Xuchu Wang
Sensors 2019, 19(8), 1766; https://doi.org/10.3390/s19081766 - 13 Apr 2019
Cited by 4 | Viewed by 2997
Abstract
Automatic detection of left ventricle myocardium is essential to subsequent cardiac image registration and tissue segmentation. However, it is considered challenging mainly because of the complex and varying shape of the myocardium and surrounding tissues across slices and phases. In this study, a [...] Read more.
Automatic detection of left ventricle myocardium is essential to subsequent cardiac image registration and tissue segmentation. However, it is considered challenging mainly because of the complex and varying shape of the myocardium and surrounding tissues across slices and phases. In this study, a hybrid model is proposed to detect myocardium in cardiac magnetic resonance (MR) images combining region proposal and deep feature classification and regression. The model firstly generates candidate regions using new structural similarity-enhanced supervoxel over-segmentation plus hierarchical clustering. Then it adopts a deep stacked sparse autoencoder (SSAE) network to learn the discriminative deep feature to represent the regions. Finally, the features are fed to train a novel nonlinear within-class neighborhood preserved soft margin support vector (C-SVC) classifier and multiple-output support vector ( ε -SVR) regressor for refining the location of myocardium. To improve the stability and generalization, the model also takes hard negative sample mining strategy to fine-tune the SSAE and the classifier. The proposed model with impacts of different components were extensively evaluated and compared to related methods on public cardiac data set. Experimental results verified the effectiveness of proposed integrated components, and demonstrated that it was robust in myocardium localization and outperformed the state-of-the-art methods in terms of typical metrics. This study would be beneficial in some cardiac image processing such as region-of-interest cropping and left ventricle volume measurement. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

12 pages, 2324 KiB  
Article
Predicting Depth from Single RGB Images with Pyramidal Three-Streamed Networks
by Songnan Chen, Mengxia Tang and Jiangming Kan
Sensors 2019, 19(3), 667; https://doi.org/10.3390/s19030667 - 6 Feb 2019
Cited by 13 | Viewed by 3714
Abstract
Predicting depth from a monocular image is an ill-posed and inherently ambiguous issue in computer vision. In this paper, we propose a pyramidal third-streamed network (PTSN) that recovers the depth information using a single given RGB image. PTSN uses pyramidal structure images, which [...] Read more.
Predicting depth from a monocular image is an ill-posed and inherently ambiguous issue in computer vision. In this paper, we propose a pyramidal third-streamed network (PTSN) that recovers the depth information using a single given RGB image. PTSN uses pyramidal structure images, which can extract multiresolution features to improve the robustness of the network as the network input. The full connection layer is changed into fully convolutional layers with a new upconvolution structure, which reduces the network parameters and computational complexity. We propose a new loss function including scale-invariant, horizontal and vertical gradient loss that not only helps predict the depth values, but also clearly obtains local contours. We evaluate PTSN on the NYU Depth v2 dataset and the experimental results show that our depth predictions have better accuracy than competing methods. Full article
(This article belongs to the Special Issue Advanced Machine Learning and Deep Networks for Psycho-Physiological Signals Processing, Modelling, and Classification)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-16
Back to TopTop