Sensors

16 pages, 1389 KiB

Open AccessArticle

Classification and Automated Interpretation of Spinal Posture Data Using a Pathology-Independent Classifier and Explainable Artificial Intelligence (XAI)

by Carlo Dindorf, Jürgen Konradi, Claudia Wolf, Bertram Taetz, Gabriele Bleser, Janine Huthwelker, Friederike Werthmann, Eva Bartaguiz, Johanna Kniepert, Philipp Drees, Ulrich Betz and Michael Fröhlich

Sensors 2021, 21(18), 6323; https://doi.org/10.3390/s21186323 - 21 Sep 2021

Cited by 32 | Viewed by 3933

Abstract

Clinical classification models are mostly pathology-dependent and, thus, are only able to detect pathologies they have been trained for. Research is needed regarding pathology-independent classifiers and their interpretation. Hence, our aim is to develop a pathology-independent classifier that provides prediction probabilities and explanations [...] Read more.

Clinical classification models are mostly pathology-dependent and, thus, are only able to detect pathologies they have been trained for. Research is needed regarding pathology-independent classifiers and their interpretation. Hence, our aim is to develop a pathology-independent classifier that provides prediction probabilities and explanations of the classification decisions. Spinal posture data of healthy subjects and various pathologies (back pain, spinal fusion, osteoarthritis), as well as synthetic data, were used for modeling. A one-class support vector machine was used as a pathology-independent classifier. The outputs were transformed into a probability distribution according to Platt’s method. Interpretation was performed using the explainable artificial intelligence tool Local Interpretable Model-Agnostic Explanations. The results were compared with those obtained by commonly used binary classification approaches. The best classification results were obtained for subjects with a spinal fusion. Subjects with back pain were especially challenging to distinguish from the healthy reference group. The proposed method proved useful for the interpretation of the predictions. No clear inferiority of the proposed approach compared to commonly used binary classifiers was demonstrated. The application of dynamic spinal data seems important for future works. The proposed approach could be useful to provide an objective orientation and to individually adapt and monitor therapy measures pre- and post-operatively. Full article

(This article belongs to the Special Issue Data Analytics for Mobile-Health)

► Show Figures

Figure 1

18 pages, 4383 KiB

Open AccessArticle

The Implementation and Evaluation of Individual Preference in Robot Facial Expression Based on Emotion Estimation Using Biological Signals

by Peeraya Sripian, Muhammad Nur Adilin Mohd Anuardi, Jiawei Yu and Midori Sugaya

Sensors 2021, 21(18), 6322; https://doi.org/10.3390/s21186322 - 21 Sep 2021

Cited by 4 | Viewed by 3132

Abstract

Recently, robot services have been widely applied in many fields. To provide optimum service, it is essential to maintain good acceptance of the robot for more effective interaction with users. Previously, we attempted to implement facial expressions by synchronizing an estimated human emotion [...] Read more.

Recently, robot services have been widely applied in many fields. To provide optimum service, it is essential to maintain good acceptance of the robot for more effective interaction with users. Previously, we attempted to implement facial expressions by synchronizing an estimated human emotion on the face of a robot. The results revealed that the robot could present different perceptions according to individual preferences. In this study, we considered individual differences to improve the acceptance of the robot by changing the robot’s expression according to the emotion of its interacting partner. The emotion was estimated using biological signals, and the robot changed its expression according to three conditions: synchronized with the estimated emotion, inversely synchronized, and a funny expression. During the experiment, the participants provided feedback regarding the robot’s expression by choosing whether they “like” or “dislike” the expression. We investigated individual differences in the acceptance of the robot expression using the Semantic Differential scale method. In addition, logistic regression was used to create a classification model by considering individual differences based on the biological data and feedback from each participant. We found that the robot expression based on inverse synchronization when the participants felt a negative emotion could result in impression differences among individuals. Then, the robot’s expression was determined based on the classification model, and the Semantic Differential scale on the impression of the robot was compared with the three conditions. Overall, we found that the participants were most accepting when the robot expression was calculated using the proposed personalized method. Full article

(This article belongs to the Collection Survey on Research of Sensors and Robot Control)

► Show Figures

Figure 1

11 pages, 22622 KiB

Open AccessArticle

On the Use of Dynamic Calibration to Correct Drop Counter Rain Gauge Measurements

by Mattia Stagnaro, Arianna Cauteruccio, Luca G. Lanza and Pak-Wai Chan

Sensors 2021, 21(18), 6321; https://doi.org/10.3390/s21186321 - 21 Sep 2021

Cited by 4 | Viewed by 2635

Abstract

Dynamic calibration was performed in the laboratory on two catching-type drop counter rain gauges manufactured as high-sensitivity and fast response instruments by Ogawa Seiki Co. Ltd. (Japan) and the Chilbolton Rutherford Appleton Laboratory (UK). Adjustment procedures were developed to meet the recommendations of [...] Read more.

Dynamic calibration was performed in the laboratory on two catching-type drop counter rain gauges manufactured as high-sensitivity and fast response instruments by Ogawa Seiki Co. Ltd. (Japan) and the Chilbolton Rutherford Appleton Laboratory (UK). Adjustment procedures were developed to meet the recommendations of the World Meteorological Organization (WMO) for rainfall intensity measurements at the one-minute time resolution. A dynamic calibration curve was derived for each instrument to provide the drop volume variation as a function of the measured drop releasing frequency. The trueness of measurements was improved using a post-processing adjustment algorithm and made compatible with the WMO recommended maximum admissible error. The impact of dynamic calibration on the rainfall amount measured in the field at the annual and the event scale was calculated for instruments operating at two experimental sites. The rainfall climatology at the site is found to be crucial in determining the magnitude of the measurement bias, with a predominant overestimation at the low to intermediate rainfall intensity range. Full article

(This article belongs to the Special Issue Rain Sensors)

► Show Figures

Figure 1

18 pages, 1916 KiB

Open AccessArticle

Acoustic Sensing Analytics Applied to Speech in Reverberation Conditions

by Piotr Odya, Jozef Kotus, Adam Kurowski and Bozena Kostek

Sensors 2021, 21(18), 6320; https://doi.org/10.3390/s21186320 - 21 Sep 2021

Cited by 6 | Viewed by 2484

Abstract

The paper aims to discuss a case study of sensing analytics and technology in acoustics when applied to reverberation conditions. Reverberation is one of the issues that makes speech in indoor spaces challenging to understand. This problem is particularly critical in large spaces [...] Read more.

The paper aims to discuss a case study of sensing analytics and technology in acoustics when applied to reverberation conditions. Reverberation is one of the issues that makes speech in indoor spaces challenging to understand. This problem is particularly critical in large spaces with few absorbing or diffusing surfaces. One of the natural remedies to improve speech intelligibility in such conditions may be achieved through speaking slowly. It is possible to use algorithms that reduce the rate of speech (RoS) in real time. Therefore, the study aims to find recommended values of RoS in the context of STI (speech transmission index) in different acoustic environments. In the experiments, speech intelligibility for six impulse responses recorded in spaces with different STIs is investigated using a sentence test (for the Polish language). Fifteen subjects with normal hearing participated in these tests. The results of the analytical analysis enabled us to propose a curve specifying the maximum RoS values translating into understandable speech under given acoustic conditions. This curve can be used in speech processing control technology as well as compressive reverse acoustic sensing. Full article

(This article belongs to the Special Issue Analytics and Applications of Audio and Image Sensing Techniques)

► Show Figures

Figure 1

16 pages, 1028 KiB

Open AccessArticle

A New Approach to Predicting Cryptocurrency Returns Based on the Gold Prices with Support Vector Machines during the COVID-19 Pandemic Using Sensor-Related Data

by Esam Mahdi, Víctor Leiva, Saed Mara’Beh and Carlos Martin-Barreiro

Sensors 2021, 21(18), 6319; https://doi.org/10.3390/s21186319 - 21 Sep 2021

Cited by 29 | Viewed by 4964

Abstract

In a real-world situation produced under COVID-19 scenarios, predicting cryptocurrency returns accurately can be challenging. Such a prediction may be helpful to the daily economic and financial market. Unlike forecasting the cryptocurrency returns, we propose a new approach to predict whether the return [...] Read more.

In a real-world situation produced under COVID-19 scenarios, predicting cryptocurrency returns accurately can be challenging. Such a prediction may be helpful to the daily economic and financial market. Unlike forecasting the cryptocurrency returns, we propose a new approach to predict whether the return classification would be in the first, second, third quartile, or any quantile of the gold price the next day. In this paper, we employ the support vector machine (SVM) algorithm for exploring the predictability of financial returns for the six major digital currencies selected from the list of top ten cryptocurrencies based on data collected through sensors. These currencies are Binance Coin, Bitcoin, Cardano, Dogecoin, Ethereum, and Ripple. Our study considers the pre-COVID-19 and ongoing COVID-19 periods. An algorithm that allows updated data analysis, based on the use of a sensor in the database, is also proposed. The results show strong evidence that the SVM is a robust technique for devising profitable trading strategies and can provide accurate results before and during the current pandemic. Our findings may be helpful for different stakeholders in understanding the cryptocurrency dynamics and in making better investment decisions, especially under adverse conditions and during times of uncertain environments such as in the COVID-19 pandemic. Full article

(This article belongs to the Special Issue Modeling COVID-19 with Artificial Intelligence and Machine/Statistical Learning Techniques from Sensor Data and other Potential Applications)

► Show Figures

Figure 1

22 pages, 3803 KiB

Open AccessArticle

Inertial Measurement of Head Tilt in Rodents: Principles and Applications to Vestibular Research

by Romain Fayat, Viviana Delgado Betancourt, Thibault Goyallon, Mathieu Petremann, Pauline Liaudet, Vincent Descossy, Lionel Reveret and Guillaume P. Dugué

Sensors 2021, 21(18), 6318; https://doi.org/10.3390/s21186318 - 21 Sep 2021

Cited by 6 | Viewed by 3536

Abstract

Inertial sensors are increasingly used in rodent research, in particular for estimating head orientation relative to gravity, or head tilt. Despite this growing interest, the accuracy of tilt estimates computed from rodent head inertial data has never been assessed. Using readily available inertial [...] Read more.

Inertial sensors are increasingly used in rodent research, in particular for estimating head orientation relative to gravity, or head tilt. Despite this growing interest, the accuracy of tilt estimates computed from rodent head inertial data has never been assessed. Using readily available inertial measurement units mounted onto the head of freely moving rats, we benchmarked a set of tilt estimation methods against concurrent 3D optical motion capture. We show that, while low-pass filtered head acceleration signals only provided reliable tilt estimates in static conditions, sensor calibration combined with an appropriate choice of orientation filter and parameters could yield average tilt estimation errors below

1.5

^{\circ}

during movement. We then illustrate an application of inertial head tilt measurements in a preclinical rat model of unilateral vestibular lesion and propose a set of metrics describing the severity of associated postural and motor symptoms and the time course of recovery. We conclude that headborne inertial sensors are an attractive tool for quantitative rodent behavioral analysis in general and for the study of vestibulo-postural functions in particular. Full article

(This article belongs to the Special Issue Advances in Inertial Sensors)

► Show Figures

Figure 1

21 pages, 2624 KiB

Open AccessArticle

System Implementation Trade-Offs for Low-Speed Rotational Variable Reluctance Energy Harvesters

by Ye Xu, Sebastian Bader, Michele Magno, Philipp Mayer and Bengt Oelmann

Sensors 2021, 21(18), 6317; https://doi.org/10.3390/s21186317 - 21 Sep 2021

Cited by 6 | Viewed by 3201

Abstract

Low-power energy harvesting has been demonstrated as a feasible alternative for the power supply of next-generation smart sensors and IoT end devices. In many cases, the output of kinetic energy harvesters is an alternating current (AC) requiring rectification in order to supply the [...] Read more.

Low-power energy harvesting has been demonstrated as a feasible alternative for the power supply of next-generation smart sensors and IoT end devices. In many cases, the output of kinetic energy harvesters is an alternating current (AC) requiring rectification in order to supply the electronic load. The rectifier design and selection can have a considerable influence on the energy harvesting system performance in terms of extracted output power and conversion losses. This paper presents a quantitative comparison of three passive rectifiers in a low-power, low-voltage electromagnetic energy harvesting sub-system, namely the full-wave bridge rectifier (FWR), the voltage doubler (VD), and the negative voltage converter rectifier (NVC). Based on a variable reluctance energy harvesting system, we investigate each of the rectifiers with respect to their performance and their effect on the overall energy extraction. We conduct experiments under the conditions of a low-speed rotational energy harvesting application with rotational speeds of 5 rpm to 20 rpm, and verify the experiments in an end-to-end energy harvesting evaluation. Two performance metrics—power conversion efficiency (PCE) and power extraction efficiency (PEE)—are obtained from the measurements to evaluate the performance of the system implementation adopting each of the rectifiers. The results show that the FWR with PEEs of 20% at 5 rpm to 40% at 20 rpm has a low performance in comparison to the VD (40–60%) and NVC (20–70%) rectifiers. The VD-based interface circuit demonstrates the best performance under low rotational speeds, whereas the NVC outperforms the VD at higher speeds (>18 rpm). Finally, the end-to-end system evaluation is conducted with a self-powered rpm sensing system, which demonstrates an improved performance with the VD rectifier implementation reaching the system’s maximum sampling rate (40 Hz) at a rotational speed of approximately 15.5 rpm. Full article

(This article belongs to the Special Issue Energy Harvesting Technologies and Applications for the Internet of Things and Wireless Sensor Networks)

► Show Figures

Graphical abstract

19 pages, 2377 KiB

Open AccessArticle

Human Activity Recognition for Indoor Localization Using Smartphone Inertial Sensors

by Dinis Moreira, Marília Barandas, Tiago Rocha, Pedro Alves, Ricardo Santos, Ricardo Leonardo, Pedro Vieira and Hugo Gamboa

Sensors 2021, 21(18), 6316; https://doi.org/10.3390/s21186316 - 21 Sep 2021

Cited by 14 | Viewed by 4284

Abstract

With the fast increase in the demand for location-based services and the proliferation of smartphones, the topic of indoor localization is attracting great interest. In indoor environments, users’ performed activities carry useful semantic information. These activities can then be used by indoor localization [...] Read more.

With the fast increase in the demand for location-based services and the proliferation of smartphones, the topic of indoor localization is attracting great interest. In indoor environments, users’ performed activities carry useful semantic information. These activities can then be used by indoor localization systems to confirm users’ current relative locations in a building. In this paper, we propose a deep-learning model based on a Convolutional Long Short-Term Memory (ConvLSTM) network to classify human activities within the indoor localization scenario using smartphone inertial sensor data. Results show that the proposed human activity recognition (HAR) model accurately identifies nine types of activities: not moving, walking, running, going up in an elevator, going down in an elevator, walking upstairs, walking downstairs, or going up and down a ramp. Moreover, predicted human activities were integrated within an existing indoor positioning system and evaluated in a multi-story building across several testing routes, with an average positioning error of 2.4 m. The results show that the inclusion of human activity information can reduce the overall localization error of the system and actively contribute to the better identification of floor transitions within a building. The conducted experiments demonstrated promising results and verified the effectiveness of using human activity-related information for indoor localization. Full article

(This article belongs to the Special Issue Advances in Indoor Positioning Systems and Their Application to the Internet of Things (IoT))

► Show Figures

Figure 1

26 pages, 1351 KiB

Open AccessArticle

Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers

by Ivan Pisa, Antoni Morell, Ramón Vilanova and Jose Lopez Vicario

Sensors 2021, 21(18), 6315; https://doi.org/10.3390/s21186315 - 21 Sep 2021

Cited by 12 | Viewed by 2818

Abstract

In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be [...] Read more.

In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be directly obtained from input and output measurements without requiring a huge knowledge of the processes under control. However, ANNs have to be designed, implemented, and trained, which can become complex and time-demanding processes. This can be alleviated by means of Transfer Learning (TL) methodologies, where the knowledge obtained from a unique ANN is transferred to the remaining nets reducing the ANN design time. From the control viewpoint, the first ANN can be easily obtained and then transferred to the remaining control loops. In this manuscript, the application of TL methodologies to design and implement the control loops of a Wastewater Treatment Plant (WWTP) is analysed. Results show that the adoption of this TL-based methodology allows the development of new control loops without requiring a huge knowledge of the processes under control. Besides, a wide improvement in terms of the control performance with respect to conventional control structures is also obtained. For instance, results have shown that less oscillations in the tracking of desired set-points are produced by achieving improvements in the Integrated Absolute Error and Integrated Square Error which go from 40.17% to 94.29% and from 34.27% to 99.71%, respectively. Full article

(This article belongs to the Special Issue Advances in the Monitoring, Diagnosis, and Optimisation of Water Systems)

► Show Figures

Figure 1

22 pages, 1303 KiB

Open AccessArticle

The State Space Subdivision Filter for Estimation on SE(2)

by Florian Pfaff, Kailai Li and Uwe D. Hanebeck

Sensors 2021, 21(18), 6314; https://doi.org/10.3390/s21186314 - 21 Sep 2021

Cited by 1 | Viewed by 2572

Abstract

The

SE (2)

domain can be used to describe the position and orientation of objects in planar scenarios and is inherently nonlinear due to the periodicity of the angle. We present a novel filter that involves splitting up the joint density [...] Read more.

The

SE (2)

domain can be used to describe the position and orientation of objects in planar scenarios and is inherently nonlinear due to the periodicity of the angle. We present a novel filter that involves splitting up the joint density into a (marginalized) density for the periodic part and a conditional density for the linear part. We subdivide the state space along the periodic dimension and describe each part of the state space using the parameters of a Gaussian and a grid value, which is the function value of the marginalized density for the periodic part at the center of the respective area. By using the grid values as weighting factors for the Gaussians along the linear dimensions, we can approximate functions on the

SE (2)

domain with correlated position and orientation. Based on this representation, we interweave a grid filter with a Kalman filter to obtain a filter that can take different numbers of parameters and is in the same complexity class as a grid filter for circular domains. We thoroughly compared the filters with other state-of-the-art filters in a simulated tracking scenario. With only little run time, our filter outperformed an unscented Kalman filter for manifolds and a progressive filter based on dual quaternions. Our filter also yielded more accurate results than a particle filter using one million particles while being faster by over an order of magnitude. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

12 pages, 494 KiB

Open AccessArticle

On the Unification of Common Actigraphic Data Scoring Algorithms

by Piotr Biegański, Anna Stróż, Marian Dovgialo, Anna Duszyk-Bogorodzka and Piotr Durka

Sensors 2021, 21(18), 6313; https://doi.org/10.3390/s21186313 - 21 Sep 2021

Cited by 1 | Viewed by 2495

Abstract

Actigraphy is a well-known, inexpensive method to investigate human movement patterns. Sleep and circadian rhythm studies are among the most popular applications of actigraphy. In this study, we investigate seven common sleep-wake scoring algorithms designed for actigraphic data, namely Cole-Kripke algorithm, two versions [...] Read more.

Actigraphy is a well-known, inexpensive method to investigate human movement patterns. Sleep and circadian rhythm studies are among the most popular applications of actigraphy. In this study, we investigate seven common sleep-wake scoring algorithms designed for actigraphic data, namely Cole-Kripke algorithm, two versions of Sadeh algorithm, Sazonov algorithm, Webster algorithm, UCSD algorithm and Scripps Clinic algorithm. We propose a unified mathematical framework describing five of them. One of the observed novelties is that five of these algorithms are in fact equivalent to low-pass FIR filters with very similar characteristics. We also provide explanations about the role of some factors defining these algorithms, as none were given by their Authors who followed empirical procedures. Proposed framework provides a robust mathematical description of discussed algorithms, which for the first time allows one to fully understand their operation and basics. Full article

(This article belongs to the Special Issue Biomedical Sensors and Data Processing in Human Monitoring for E-health)

► Show Figures

Figure 1

22 pages, 15008 KiB

Open AccessArticle

State Observer for Linear Systems with Explicit Constraints: Orthogonal Decomposition Method

by Sergei Savin, Oleg Balakhnov, Ramil Khusainov and Alexandr Klimchik

Sensors 2021, 21(18), 6312; https://doi.org/10.3390/s21186312 - 21 Sep 2021

Cited by 2 | Viewed by 3077

Abstract

In this paper, an orthogonal decomposition-based state observer for systems with explicit constraints is proposed. State observers have been an integral part of robotic systems, reflecting the practicality and effectiveness of the dynamic state feedback control, but the same methods are lacking for [...] Read more.

In this paper, an orthogonal decomposition-based state observer for systems with explicit constraints is proposed. State observers have been an integral part of robotic systems, reflecting the practicality and effectiveness of the dynamic state feedback control, but the same methods are lacking for the systems with explicit mechanical constraints, where observer designs have been proposed only for special cases of such systems, with relatively restrictive assumptions. This work aims to provide an observer design framework for a general case linear time-invariant system with explicit constraints, by finding lower-dimensional subspaces in the state space, where the system is observable while giving sufficient information for both feedback and feed-forward control. We show that the proposed formulation recovers minimal coordinate representation when it is sufficient for the control law generation and retains non-minimal coordinates when those are required for the feed-forward control law. The proposed observer is tested on a flywheel inverted pendulum and on a quadruped robot Unitree A1. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Graphical abstract

12 pages, 2781 KiB

Open AccessArticle

Estimation of Continuous Blood Pressure from PPG via a Federated Learning Approach

by Eoin Brophy, Maarten De Vos, Geraldine Boylan and Tomás Ward

Sensors 2021, 21(18), 6311; https://doi.org/10.3390/s21186311 - 21 Sep 2021

Cited by 28 | Viewed by 5269

Abstract

Ischemic heart disease is the highest cause of mortality globally each year. This puts a massive strain not only on the lives of those affected, but also on the public healthcare systems. To understand the dynamics of the healthy and unhealthy heart, doctors [...] Read more.

Ischemic heart disease is the highest cause of mortality globally each year. This puts a massive strain not only on the lives of those affected, but also on the public healthcare systems. To understand the dynamics of the healthy and unhealthy heart, doctors commonly use an electrocardiogram (ECG) and blood pressure (BP) readings. These methods are often quite invasive, particularly when continuous arterial blood pressure (ABP) readings are taken, and not to mention very costly. Using machine learning methods, we develop a framework capable of inferring ABP from a single optical photoplethysmogram (PPG) sensor alone. We train our framework across distributed models and data sources to mimic a large-scale distributed collaborative learning experiment that could be implemented across low-cost wearables. Our time-series-to-time-series generative adversarial network (T2TGAN) is capable of high-quality continuous ABP generation from a PPG signal with a mean error of 2.95 mmHg and a standard deviation of 19.33 mmHg when estimating mean arterial pressure on a previously unseen, noisy, independent dataset. To our knowledge, this framework is the first example of a GAN capable of continuous ABP generation from an input PPG signal that also uses a federated learning methodology. Full article

(This article belongs to the Special Issue Feature Papers in Wearables Section 2021)

► Show Figures

Figure 1

21 pages, 3085 KiB

Open AccessArticle

A Blockchain-IoT Platform for the Smart Pallet Pooling Management

by Chun-Ho Wu, Yung-Po Tsang, Carman Ka-Man Lee and Wai-Ki Ching

Sensors 2021, 21(18), 6310; https://doi.org/10.3390/s21186310 - 21 Sep 2021

Cited by 11 | Viewed by 5625

Abstract

Pallet management as a backbone of logistics and supply chain activities is essential to supply chain parties, while a number of regulations, standards and operational constraints are considered in daily operations. In recent years, pallet pooling has been unconventionally advocated to manage pallets [...] Read more.

Pallet management as a backbone of logistics and supply chain activities is essential to supply chain parties, while a number of regulations, standards and operational constraints are considered in daily operations. In recent years, pallet pooling has been unconventionally advocated to manage pallets in a closed-loop system to enhance the sustainability and operational effectiveness, but pitfalls in terms of service reliability, quality compliance and pallet limitation when using a single service provider may occur. Therefore, this study incorporates a decentralisation mechanism into the pallet management to formulate a technological eco-system for pallet pooling, namely Pallet as a Service (PalletaaS), raised by the foundation of consortium blockchain and Internet of things (IoT). Consortium blockchain is regarded as the blockchain 3.0 to facilitate more industrial applications, except cryptocurrency, and the synergy of integrating a consortium blockchain and IoT is thus investigated. The corresponding layered architecture is proposed to structure the system deployment in the industry, in which the location-inventory-routing problem for pallet pooling is formulated. To demonstrate the values of this study, a case analysis to illustrate the human–computer interaction and pallet pooling operations is conducted. Overall, this study standardises the decentralised pallet management in the closed-loop mechanism, resulting in a constructive impact to sustainable development in the logistics industry. Full article

(This article belongs to the Collection Human-Computer Interaction in Pervasive Computing Environments)

► Show Figures

Figure 1

22 pages, 6997 KiB

Open AccessArticle

Combining Supervised and Unsupervised Learning Algorithms for Human Activity Recognition

by Elena-Alexandra Budisteanu and Irina Georgiana Mocanu

Sensors 2021, 21(18), 6309; https://doi.org/10.3390/s21186309 - 21 Sep 2021

Cited by 8 | Viewed by 3279

Abstract

Human activity recognition is an extensively researched topic in the last decade. Recent methods employ supervised and unsupervised deep learning techniques in which spatial and temporal dependency is modeled. This paper proposes a novel approach for human activity recognition using skeleton data. The [...] Read more.

Human activity recognition is an extensively researched topic in the last decade. Recent methods employ supervised and unsupervised deep learning techniques in which spatial and temporal dependency is modeled. This paper proposes a novel approach for human activity recognition using skeleton data. The method combines supervised and unsupervised learning algorithms in order to provide qualitative results and performance in real time. The proposed method involves a two-stage framework: the first stage applies an unsupervised clustering technique to group up activities based on their similarity, while the second stage classifies data assigned to each group using graph convolutional networks. Different clustering techniques and data augmentation strategies are explored for improving the training process. The results were compared against the state of the art methods and the proposed model achieved 90.22% Top-1 accuracy performance for NTU-RGB+D dataset (the performance was increased by approximately 9% compared with the baseline graph convolutional method). Moreover, inference time and total number of parameters stay within the same magnitude order. Extending the initial set of activities with additional classes is fast and robust, since there is no required retraining of the entire architecture but only to retrain the cluster to which the activity is assigned. Full article

(This article belongs to the Special Issue Machine Learning for Sensing and Healthcare 2020–2021)

► Show Figures

Figure 1

14 pages, 14458 KiB

Open AccessArticle

Experimental Results and Performance Analysis of a 1 × 2 × 1 UHF MIMO Passive RFID System

by Helio Augusto Muzamane and Hsin-Chin Liu

Sensors 2021, 21(18), 6308; https://doi.org/10.3390/s21186308 - 21 Sep 2021

Cited by 5 | Viewed by 3050

Abstract

Ultra-high frequency (UHF) multiple input multiple output (MIMO) passive radio frequency identification (RFID) systems have attracted the attention of many researchers in the last few years. The system modeling and theoretical performance analysis of these systems have been well investigated and revealed in [...] Read more.

Ultra-high frequency (UHF) multiple input multiple output (MIMO) passive radio frequency identification (RFID) systems have attracted the attention of many researchers in the last few years. The system modeling and theoretical performance analysis of these systems have been well investigated and revealed in many studies, yet the system prototype and the corresponding experimental results are scarce. In this study, measurements of a 1 × 2 × 1 UHF passive RFID system, including a MIMO UHF passive RFID tag prototype and its corresponding software-defined radio-based reader, taken in a microwave anechoic chamber, are presented. The experimental results are compared with theoretical values and computer simulations. The overall results demonstrate the consistency and the feasibility of UHF MIMO passive RFID systems. Full article

(This article belongs to the Special Issue RFID and Zero-Power Backscatter Sensors)

► Show Figures

Figure 1

20 pages, 6225 KiB

Open AccessArticle

Extension of the Rigid-Constraint Method for the Heuristic Suboptimal Parameter Tuning to Ten Sensor Fusion Algorithms Using Inertial and Magnetic Sensing

by Marco Caruso, Angelo Maria Sabatini, Marco Knaflitz, Ugo Della Croce and Andrea Cereatti

Sensors 2021, 21(18), 6307; https://doi.org/10.3390/s21186307 - 21 Sep 2021

Cited by 12 | Viewed by 2813

Abstract

The orientation of a magneto-inertial measurement unit can be estimated using a sensor fusion algorithm (SFA). However, orientation accuracy is greatly affected by the choice of the SFA parameter values which represents one of the most critical steps. A commonly adopted approach is [...] Read more.

The orientation of a magneto-inertial measurement unit can be estimated using a sensor fusion algorithm (SFA). However, orientation accuracy is greatly affected by the choice of the SFA parameter values which represents one of the most critical steps. A commonly adopted approach is to fine-tune parameter values to minimize the difference between estimated and true orientation. However, this can only be implemented within the laboratory setting by requiring the use of a concurrent gold-standard technology. To overcome this limitation, a Rigid-Constraint Method (RCM) was proposed to estimate suboptimal parameter values without relying on any orientation reference. The RCM method effectiveness was successfully tested on a single-parameter SFA, with an average error increase with respect to the optimal of 1.5 deg. In this work, the applicability of the RCM was evaluated on 10 popular SFAs with multiple parameters under different experimental scenarios. The average residual between the optimal and suboptimal errors amounted to 0.6 deg with a maximum of 3.7 deg. These encouraging results suggest the possibility to properly tune a generic SFA on different scenarios without using any reference. The synchronized dataset also including the optical data and the SFA codes are available online. Full article

(This article belongs to the Special Issue Sensors and IoT in Modern Healthcare Delivery and Applications)

► Show Figures

Figure 1

16 pages, 3687 KiB

Open AccessArticle

Automatic Separation of Respiratory Flow from Motion in Thermal Videos for Infant Apnea Detection

by Ilde Lorato, Sander Stuijk, Mohammed Meftah, Deedee Kommers, Peter Andriessen, Carola van Pul and Gerard de Haan

Sensors 2021, 21(18), 6306; https://doi.org/10.3390/s21186306 - 21 Sep 2021

Cited by 11 | Viewed by 2838

Abstract

Both Respiratory Flow (RF) and Respiratory Motion (RM) are visible in thermal recordings of infants. Monitoring these two signals usually requires landmark detection for the selection of a region of interest. Other approaches combine respiratory signals coming from both RF and RM, obtaining [...] Read more.

Both Respiratory Flow (RF) and Respiratory Motion (RM) are visible in thermal recordings of infants. Monitoring these two signals usually requires landmark detection for the selection of a region of interest. Other approaches combine respiratory signals coming from both RF and RM, obtaining a Mixed Respiratory (MR) signal. The detection and classification of apneas, particularly common in preterm infants with low birth weight, would benefit from monitoring both RF and RM, or MR, signals. Therefore, we propose in this work an automatic RF pixel detector not based on facial/body landmarks. The method is based on the property of RF pixels in thermal videos, which are in areas with a smooth circular gradient. We defined 5 features combined with the use of a bank of Gabor filters that together allow selection of the RF pixels. The algorithm was tested on thermal recordings of 9 infants amounting to a total of 132 min acquired in a neonatal ward. On average the percentage of correctly identified RF pixels was

84 %

. Obstructive Apneas (OAs) were simulated as a proof of concept to prove the advantage in monitoring the RF signal compared to the MR signal. The sensitivity in the simulated OA detection improved for the RF signal reaching

73 %

against the

23 %

of the MR signal. Overall, the method yielded promising results, although the positioning and number of cameras used could be further optimized for optimal RF visibility. Full article

(This article belongs to the Special Issue Contactless Sensors for Healthcare)

► Show Figures

Figure 1

18 pages, 3608 KiB

Open AccessArticle

Modular Robotic Limbs for Astronaut Activities Assistance

by Sikai Zhao, Jie Zhao, Dongbao Sui, Tianshuo Wang, Tianjiao Zheng, Chuanwu Zhao and Yanhe Zhu

Sensors 2021, 21(18), 6305; https://doi.org/10.3390/s21186305 - 21 Sep 2021

Cited by 8 | Viewed by 2961

Abstract

In order to meet the assist requirements of extravehicular activity (EVA) for astronauts, such as moving outside the international space station (ISS) or performing on-orbit tasks by a single astronaut, this paper proposes an astronaut robotic limbs system (AstroLimbs) for extravehicular activities assistance. [...] Read more.

In order to meet the assist requirements of extravehicular activity (EVA) for astronauts, such as moving outside the international space station (ISS) or performing on-orbit tasks by a single astronaut, this paper proposes an astronaut robotic limbs system (AstroLimbs) for extravehicular activities assistance. This system has two robotic limbs that can be fixed on the backpack of the astronaut. Each limb is composed of several basic module units with identical structure and function, which makes it modularized and reconfigurable. The robotic limbs can work as extra arms of the astronaut to assist them outside the space station cabin. In this paper, the robotic limbs are designed and developed. The reinforcement learning method is introduced to achieve autonomous motion planning capacity for the robot, which makes the robot intelligent enough to assist the astronaut in unstructured environment. In the meantime, the movement of the robot is also planned to make it move smoothly. The structure scene of the ISS for extravehicular activities is modeled in a simulation environment, which verified the effectiveness of the proposed method. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

27 pages, 28739 KiB

Open AccessArticle

Two-Dimensional Cartesian Coordinate System Educational Toolkit: 2D-CACSET

by Víctor H. Castañeda-Miranda, Luis F. Luque-Vega, Emmanuel Lopez-Neri, Jesús Antonio Nava-Pintor, Héctor A. Guerrero-Osuna and Gerardo Ornelas-Vargas

Sensors 2021, 21(18), 6304; https://doi.org/10.3390/s21186304 - 21 Sep 2021

Cited by 8 | Viewed by 4511

Abstract

Engineering education benefits from the application of modern technology, allowing students to learn essential Science, Technology, Engineering, and Mathematics (STEM) related concepts through hands-on experiences. Robotic kits have been used as an innovative tool in some educational fields, being readily accepted and adopted. [...] Read more.

Engineering education benefits from the application of modern technology, allowing students to learn essential Science, Technology, Engineering, and Mathematics (STEM) related concepts through hands-on experiences. Robotic kits have been used as an innovative tool in some educational fields, being readily accepted and adopted. However, most of the time, such kits’ knowledge level requires understanding basic concepts that are not always appropriate for the student. A critical concept in engineering is the Cartesian Coordinate System (CCS), an essential tool for every engineering, from graphing functions to data analysis in robotics and control applications and beyond. This paper presents the design and implementation of a novel Two-Dimensional Cartesian Coordinate System Educational Toolkit (2D-CACSET) to teach the two-dimensional representations as the first step to construct spatial thinking. This innovative educational toolkit is based on real-time location systems using Ultra-Wide Band technology. It comprises a workbench, four Anchors pinpointing

X +

,

X -

,

Y +

,

Y -

axes, seven Tags representing points in the plane, one listener connected to a PC collecting the position of the Tags, and a Graphical User Interface displaying these positions. The Educational Mechatronics Conceptual Framework (EMCF) enables constructing knowledge in concrete, graphic, and abstract levels. Hence, the students acquire this knowledge to apply it further down their career path. For this paper, three instructional designs were designed using the 2D-CACSET and the EMCF to learn about coordinate axes, quadrants, and a point in the CCS. Full article

(This article belongs to the Special Issue From Sensor Data to Educational Insights)

► Show Figures

Figure 1

28 pages, 5753 KiB

Open AccessReview

Analysis of Single Board Architectures Integrating Sensors Technologies

by José Luis Álvarez, Juan Daniel Mozo and Eladio Durán

Sensors 2021, 21(18), 6303; https://doi.org/10.3390/s21186303 - 21 Sep 2021

Cited by 22 | Viewed by 6344

Abstract

Development boards, Single-Board Computers (SBCs) and Single-Board Microcontrollers (SBMs) integrating sensors and communication technologies have become a very popular and interesting solution in the last decade. They are of interest for their simplicity, versatility, adaptability, ease of use and prototyping, which allow them [...] Read more.

Development boards, Single-Board Computers (SBCs) and Single-Board Microcontrollers (SBMs) integrating sensors and communication technologies have become a very popular and interesting solution in the last decade. They are of interest for their simplicity, versatility, adaptability, ease of use and prototyping, which allow them to serve as a starting point for projects and as reference for all kinds of designs. In this sense, there are innumerable applications integrating sensors and communication technologies where they are increasingly used, including robotics, domotics, testing and measurement, Do-It-Yourself (DIY) projects, Internet of Things (IoT) devices in the home or workplace and science, technology, engineering, educational and also academic world for STEAM (Science, Technology, Engineering and Mathematics) skills. The interest in single-board architectures and their applications have caused that all electronics manufacturers currently develop low-cost single board platform solutions. In this paper we realized an analysis of the most important topics related with single-board architectures integrating sensors. We analyze the most popular platforms based on characteristics as: cost, processing capacity, integrated processing technology and open-source license, as well as power consumption (mA@V), reliability (%), programming flexibility, support availability and electronics utilities. For evaluation, an experimental framework has been designed and implemented with six sensors (temperature, humidity, CO₂/TVOC, pressure, ambient light and CO) and different data storage and monitoring options: locally on a μSD (Micro Secure Digital), on a Cloud Server, on a Web Server or on a Mobile Application. Full article

(This article belongs to the Special Issue Sensors and Single-Board Open Source Architectures: Design and Applications)

► Show Figures

Figure 1

20 pages, 7136 KiB

Open AccessArticle

VIAE-Net: An End-to-End Altitude Estimation through Monocular Vision and Inertial Feature Fusion Neural Networks for UAV Autonomous Landing

by Xupei Zhang, Zhanzhuang He, Zhong Ma, Peng Jun and Kun Yang

Sensors 2021, 21(18), 6302; https://doi.org/10.3390/s21186302 - 20 Sep 2021

Cited by 4 | Viewed by 3297

Abstract

Altitude estimation is one of the fundamental tasks of unmanned aerial vehicle (UAV) automatic navigation, where it aims to accurately and robustly estimate the relative altitude between the UAV and specific areas. However, most methods rely on auxiliary signal reception or expensive equipment, [...] Read more.

Altitude estimation is one of the fundamental tasks of unmanned aerial vehicle (UAV) automatic navigation, where it aims to accurately and robustly estimate the relative altitude between the UAV and specific areas. However, most methods rely on auxiliary signal reception or expensive equipment, which are not always available, or applicable owing to signal interference, cost or power-consuming limitations in real application scenarios. In addition, fixed-wing UAVs have more complex kinematic models than vertical take-off and landing UAVs. Therefore, an altitude estimation method which can be robustly applied in a GPS denied environment for fixed-wing UAVs must be considered. In this paper, we present a method for high-precision altitude estimation that combines the vision information from a monocular camera and poses information from the inertial measurement unit (IMU) through a novel end-to-end deep neural network architecture. Our method has numerous advantages over existing approaches. First, we utilize the visual-inertial information and physics-based reasoning to build an ideal altitude model that provides general applicability and data efficiency for neural network learning. A further advantage is that we have designed a novel feature fusion module to simplify the tedious manual calibration and synchronization of the camera and IMU, which are required for the standard visual or visual-inertial methods to obtain the data association for altitude estimation modeling. Finally, the proposed method was evaluated, and validated using real flight data obtained during a fixed-wing UAV landing phase. The results show the average estimation error of our method is less than 3% of the actual altitude, which vastly improves the altitude estimation accuracy compared to other visual and visual-inertial based methods. Full article

(This article belongs to the Special Issue Sensors and Algorithms for Autonomous Navigation of Aircraft)

► Show Figures

Figure 1

22 pages, 6855 KiB

Open AccessArticle

Voltammetric Determination of Levodopa Using Mesoporous Carbon—Modified Screen-Printed Carbon Sensors

by Dorin Dăscălescu and Constantin Apetrei

Sensors 2021, 21(18), 6301; https://doi.org/10.3390/s21186301 - 20 Sep 2021

Cited by 10 | Viewed by 2859

Abstract

Levodopa is a precursor of dopamine, having important beneficial effects in the treatment of Parkinson’s disease. In this study, levodopa was accurately detected by means of cyclic voltammetry using carbon-based (C-SPCE), mesoporous carbon (MC-SPCE) and ordered mesoporous carbon (OMC-SPCE)-modified screen-printed sensors. Screen-printed carbon [...] Read more.

Levodopa is a precursor of dopamine, having important beneficial effects in the treatment of Parkinson’s disease. In this study, levodopa was accurately detected by means of cyclic voltammetry using carbon-based (C-SPCE), mesoporous carbon (MC-SPCE) and ordered mesoporous carbon (OMC-SPCE)-modified screen-printed sensors. Screen-printed carbon sensors were initially used for the electrochemical detection of levodopa in a 10⁻³ M solution at pH 7.0. The mesoporous carbon with an organized structure led to better electroanalysis results and to lower detection and quantification limits of the OMC-SPCE sensor as compared to the other two studied sensors. The range of linearity obtained and the low values of the detection (0.290 µM) and quantification (0.966 µM) limit demonstrate the high sensitivity and accuracy of the method for the determination of levodopa in real samples. Therefore, levodopa was detected by means of OMC-SPCE in three dietary supplements produced by different manufacturers and having various concentrations of the active compound, levodopa. The results obtained by cyclic voltammetry were compared with those obtained by using the FTIR method and no significant differences were observed. OMC-SPCE proved to be stable, and the electrochemical responses did not vary by more than 3% in repeated immersions in a solution with the same concentration of levodopa. In addition, the interfering compounds did not significantly influence the peaks related to the presence of levodopa in the solution to be analyzed. Full article

(This article belongs to the Special Issue State-of-the-Art Sensors Technology in Romania 2021)

► Show Figures

Figure 1

23 pages, 1674 KiB

Open AccessArticle

EEG Mental Stress Assessment Using Hybrid Multi-Domain Feature Sets of Functional Connectivity Network and Time-Frequency Features

by Ala Hag, Dini Handayani, Thulasyammal Pillai, Teddy Mantoro, Mun Hou Kit and Fares Al-Shargie

Sensors 2021, 21(18), 6300; https://doi.org/10.3390/s21186300 - 20 Sep 2021

Cited by 24 | Viewed by 5717

Abstract

Exposure to mental stress for long period leads to serious accidents and health problems. To avoid negative consequences on health and safety, it is very important to detect mental stress at its early stages, i.e., when it is still limited to acute or [...] Read more.

Exposure to mental stress for long period leads to serious accidents and health problems. To avoid negative consequences on health and safety, it is very important to detect mental stress at its early stages, i.e., when it is still limited to acute or episodic stress. In this study, we developed an experimental protocol to induce two different levels of stress by utilizing a mental arithmetic task with time pressure and negative feedback as the stressors. We assessed the levels of stress on 22 healthy subjects using frontal electroencephalogram (EEG) signals, salivary alpha-amylase level (AAL), and multiple machine learning (ML) classifiers. The EEG signals were analyzed using a fusion of functional connectivity networks estimated by the Phase Locking Value (PLV) and temporal and spectral domain features. A total of 210 different features were extracted from all domains. Only the optimum multi-domain features were used for classification. We then quantified stress levels using statistical analysis and seven ML classifiers. Our result showed that the AAL level was significantly increased (p < 0.01) under stress condition in all subjects. Likewise, the functional connectivity network demonstrated a significant decrease under stress, p < 0.05. Moreover, we achieved the highest stress classification accuracy of 93.2% using the Support Vector Machine (SVM) classifier. Other classifiers produced relatively similar results. Full article

(This article belongs to the Special Issue EEG Signal Processing for Biomedical Applications)

► Show Figures

Figure 1

10 pages, 1215 KiB

Open AccessCommunication

Can Frailty Be a Predictor of ICD Shock after the Implantation of a Cardioverter Defibrillator in Elderly Patients?

by Agnieszka Mlynarska, Rafal Mlynarski, Bartosz Uchmanowicz and Wioletta Mikuľáková

Sensors 2021, 21(18), 6299; https://doi.org/10.3390/s21186299 - 20 Sep 2021

Cited by 3 | Viewed by 2062

Abstract

Introduction: The aim of the study was to assess the prevalence of frailty among elderly patients who had an implanted cardioverter defibrillator, as well as the influence of frailty on the main endpoints during the follow-up. Methods: The study included 103 patients > [...] Read more.

Introduction: The aim of the study was to assess the prevalence of frailty among elderly patients who had an implanted cardioverter defibrillator, as well as the influence of frailty on the main endpoints during the follow-up. Methods: The study included 103 patients > 60 years of age (85M, aged 71.56–8.17 years). All of the patients had an implanted single or dual-chamber cardioverter-defibrillator. In the research, there was a 12-month follow-up. The occurrence of frailty syndrome was assessed using the Tilburg Frailty Indicator scale (TFI). Results: Frailty syndrome was diagnosed in 75.73% of the patients that were included in the study. The mean values of the TFI were 6.55 ± 2.67, in the physical domain 4.06 ± 1.79, in the psychological domain 2.06 ± 1.10, and in the social domain 0.44 ± 0.55. During the follow-up period, 27.2% of patients had a defibrillator cardioverter electric shock, which occurred statistically more often in patients with diagnosed frailty syndrome (34.6%) compared to the robust patients (4%); p = 0.0062. In the logistic regression, frailty (OR: 1.203, 95% CI:1.0126–1.4298; p < 0.030) was an independent predictor of a defibrillator cardioverter electric shock. Similarly, in the logistic regression, frailty (OR: 1.3623, 95% CI:1.0290–1.8035; p = 0.019) was also an independent predictor for inadequate electric shocks. Conclusion: About three-quarters of the elderly patients that had qualified for ICD implantation were affected by frailty syndrome. In the frailty subgroup, adequate and inadequate shocks occurred more often compared to the robust patients. Full article

(This article belongs to the Special Issue New Features beyond Sudden Cardiac Death Prevention in Wearable and Implantable Defibrillators)

► Show Figures

Figure 1

23 pages, 4158 KiB

Open AccessReview

A Systematic Mapping Study on Integration Proposals of the Personas Technique in Agile Methodologies

by Patricia Losana, John W. Castro, Xavier Ferre, Elena Villalba-Mora and Silvia T. Acuña

Sensors 2021, 21(18), 6298; https://doi.org/10.3390/s21186298 - 20 Sep 2021

Cited by 8 | Viewed by 4137

Abstract

Agile development processes are increasing their consideration of usability by integrating various user-centered design techniques throughout development. One such technique is Personas, which proposes the creation of fictitious users with real preferences to drive application design. Since applying this technique conflicts with the [...] Read more.

Agile development processes are increasing their consideration of usability by integrating various user-centered design techniques throughout development. One such technique is Personas, which proposes the creation of fictitious users with real preferences to drive application design. Since applying this technique conflicts with the time constraints of agile development, Personas has been adapted over the years. Our objective is to determine the adoption level and type of integration, as well as to propose improvements to the Personas technique for agile development. A systematic mapping study was performed, retrieving 28 articles grouped by agile methodology type. We found some common integration strategies regardless of the specific agile approach, along with some frequent problems, mainly related to Persona modelling and context representation. Based on these limitations, we propose an adaptation to the technique in order to reduce the creation time for a preliminary persona. The number of publications dealing with Personas and agile development is increasing, which reveals a growing interest in the application of this technique to develop usable agile software. Full article

(This article belongs to the Special Issue Recent Advances in Human-Computer Interaction)

► Show Figures

Figure 1

27 pages, 3686 KiB

Open AccessReview

Energy Harvesting Materials and Structures for Smart Textile Applications: Recent Progress and Path Forward

by Patricia I. Dolez

Sensors 2021, 21(18), 6297; https://doi.org/10.3390/s21186297 - 20 Sep 2021

Cited by 25 | Viewed by 8052

Abstract

A major challenge with current wearable electronics and e-textiles, including sensors, is power supply. As an alternative to batteries, energy can be harvested from various sources using garments or other textile products as a substrate. Four different energy-harvesting mechanisms relevant to smart textiles [...] Read more.

A major challenge with current wearable electronics and e-textiles, including sensors, is power supply. As an alternative to batteries, energy can be harvested from various sources using garments or other textile products as a substrate. Four different energy-harvesting mechanisms relevant to smart textiles are described in this review. Photovoltaic energy harvesting technologies relevant to textile applications include the use of high efficiency flexible inorganic films, printable organic films, dye-sensitized solar cells, and photovoltaic fibers and filaments. In terms of piezoelectric systems, this article covers polymers, composites/nanocomposites, and piezoelectric nanogenerators. The latest developments for textile triboelectric energy harvesting comprise films/coatings, fibers/textiles, and triboelectric nanogenerators. Finally, thermoelectric energy harvesting applied to textiles can rely on inorganic and organic thermoelectric modules. The article ends with perspectives on the current challenges and possible strategies for further progress. Full article

(This article belongs to the Special Issue Textile-Based Sensors: E-textiles, Devices, and Integrated Systems)

► Show Figures

Figure 1

32 pages, 1082 KiB

Open AccessEditor’s ChoiceReview

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

by Chun-Hong Cheng, Kwan-Long Wong, Jing-Wei Chin, Tsz-Tai Chan and Richard H. Y. So

Sensors 2021, 21(18), 6296; https://doi.org/10.3390/s21186296 - 20 Sep 2021

Cited by 61 | Viewed by 15319

Abstract

Heart rate (HR) is one of the essential vital signs used to indicate the physiological health of the human body. While traditional HR monitors usually require contact with skin, remote photoplethysmography (rPPG) enables contactless HR monitoring by capturing subtle light changes of skin [...] Read more.

Heart rate (HR) is one of the essential vital signs used to indicate the physiological health of the human body. While traditional HR monitors usually require contact with skin, remote photoplethysmography (rPPG) enables contactless HR monitoring by capturing subtle light changes of skin through a video camera. Given the vast potential of this technology in the future of digital healthcare, remote monitoring of physiological signals has gained significant traction in the research community. In recent years, the success of deep learning (DL) methods for image and video analysis has inspired researchers to apply such techniques to various parts of the remote physiological signal extraction pipeline. In this paper, we discuss several recent advances of DL-based methods specifically for remote HR measurement, categorizing them based on model architecture and application. We further detail relevant real-world applications of remote physiological monitoring and summarize various common resources used to accelerate related research progress. Lastly, we analyze the implications of research findings and discuss research gaps to guide future explorations. Full article

(This article belongs to the Special Issue Contactless Sensors for Healthcare)

► Show Figures

Figure 1

13 pages, 3596 KiB

Open AccessArticle

Sinusoidal Phase-Modulated Angle Interferometer for Angular Vibration Measurement

by Xianfan Wang, Jianhua Yang, Meng Chen, Lijun Miao and Tengchao Huang

Sensors 2021, 21(18), 6295; https://doi.org/10.3390/s21186295 - 20 Sep 2021

Cited by 5 | Viewed by 2623

Abstract

Primary angular vibration calibration devices based on laser interferometers play a crucial role in evaluating the dynamic performance of inertial sensing devices. Here, we propose a sinusoidal phase-modulated angle interferometer (SPMAI) to realize angular vibration measurements over a frequency range of 1–1000 Hz, [...] Read more.

Primary angular vibration calibration devices based on laser interferometers play a crucial role in evaluating the dynamic performance of inertial sensing devices. Here, we propose a sinusoidal phase-modulated angle interferometer (SPMAI) to realize angular vibration measurements over a frequency range of 1–1000 Hz, in which the sinusoidal measurement retro-reflector (SMR) and the phase generation carrier (PGC) demodulation algorithm are adopted to track the dynamic angle variation. A comprehensive theoretical analysis is presented to reveal the relationship between demodulation performance of the SPMAI and several factors, such as phase modulation depth, carrier phase delay and sampling frequency. Both the simulated and experimental results demonstrate that the proposed SPMAI can achieve an angular vibration measurement with amplitude of sub-arcsecond under given parameters. Using the proposed SPMAI, the frequency bandwidth of an interferometric fiber-optic gyroscope (IFOG) is successfully determined to be 848 Hz. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

15 pages, 4933 KiB

Open AccessArticle

Development of a Finger-Ring-Shaped Hybrid Smart Stethoscope for Automatic S1 and S2 Heart Sound Identification

by Soomin Lee, Qun Wei, Heejoon Park, Yuri Na, Donghwa Jeong and Hongjoon Lim

Sensors 2021, 21(18), 6294; https://doi.org/10.3390/s21186294 - 20 Sep 2021

Cited by 6 | Viewed by 4088

Abstract

Cardiac auscultation is one of the most popular diagnosis approaches to determine cardiovascular status based on listening to heart sounds with a stethoscope. However, heart sounds can be masked by visceral sounds such as organ movement and breathing, and a doctor’s level of [...] Read more.

Cardiac auscultation is one of the most popular diagnosis approaches to determine cardiovascular status based on listening to heart sounds with a stethoscope. However, heart sounds can be masked by visceral sounds such as organ movement and breathing, and a doctor’s level of experience can more seriously affect the accuracy of auscultation results. To improve the accuracy of auscultation, and to allow nonmedical staff to conduct cardiac auscultation anywhere and anytime, a hybrid-type personal smart stethoscope with an automatic heart sound analysis function is presented in this paper. The device was designed with a folding finger-ring shape that can be worn on the finger and placed on the chest to measure photoplethysmogram (PPG) signals and acquire the heart sound simultaneously. The measured heart sounds are detected as phonocardiogram (PCG) signals, and the boundaries of the heart sound variation and the peaks of the PPG signal are detected in preprocessing by an advanced Shannon entropy envelope. According to the relationship between PCG and PPG signals, an automatic heart sound analysis algorithm based on calculating the time interval between the first and second heart sounds (S1, S2) and the peak of the PPG was developed and implemented via the manufactured prototype device. The prototype device underwent accuracy and usability testing with 20 young adults, and the experimental results showed that the proposed smart stethoscope could satisfactorily collect the heart sounds and PPG signals. In addition, within the developed algorithm, the device was as accurate in start-points of heart sound detection as professional physiological signal-acquisition systems. Furthermore, the experimental results demonstrated that the device was able to identify S1 and S2 heart sounds automatically with high accuracy. Full article

(This article belongs to the Section Wearables)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 21, Issue 18 (September-2 2021) – 337 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI