Sensors

18 pages, 1270 KiB

Open AccessArticle

Sampling Trade-Offs in Duty-Cycled Systems for Air Quality Low-Cost Sensors

by Pau Ferrer-Cid, Julio Garcia-Calvete, Aina Main-Nadal, Zhe Ye, Jose M. Barcelo-Ordinas and Jorge Garcia-Vidal

Sensors 2022, 22(10), 3964; https://doi.org/10.3390/s22103964 - 23 May 2022

Cited by 7 | Viewed by 2813

Abstract

The use of low-cost sensors in conjunction with high-precision instrumentation for air pollution monitoring has shown promising results in recent years. One of the main challenges for these sensors has been the quality of their data, which is why the main efforts have [...] Read more.

The use of low-cost sensors in conjunction with high-precision instrumentation for air pollution monitoring has shown promising results in recent years. One of the main challenges for these sensors has been the quality of their data, which is why the main efforts have focused on calibrating the sensors using machine learning techniques to improve the data quality. However, there is one aspect that has been overlooked, that is, these sensors are mounted on nodes that may have energy consumption restrictions if they are battery-powered. In this paper, we show the usual sensor data gathering process and we study the existing trade-offs between the sampling of such sensors, the quality of the sensor calibration, and the power consumption involved. To this end, we conduct experiments on prototype nodes measuring tropospheric ozone, nitrogen dioxide, and nitrogen monoxide at high frequency. The results show that the sensor sampling strategy directly affects the quality of the air pollution estimation and that each type of sensor may require different sampling strategies. In addition, duty cycles of 0.1 can be achieved when the sensors have response times in the order of two minutes, and duty cycles between 0.01 and 0.02 can be achieved when the sensor response times are negligible, calibrating with hourly reference values and maintaining a quality of calibrated data similar to when the node is connected to an uninterruptible power supply. Full article

(This article belongs to the Special Issue Air Quality Internet of Things Devices)

► Show Figures

Figure 1

13 pages, 3384 KiB

Open AccessArticle

A Hybrid Leak Localization Approach Using Acoustic Emission for Industrial Pipelines

by Yangde Gao, Farzin Piltan and Jong-Myon Kim

Sensors 2022, 22(10), 3963; https://doi.org/10.3390/s22103963 - 23 May 2022

Cited by 15 | Viewed by 2611

Abstract

Acoustic emission techniques are widely used to monitor industrial pipelines. Intelligent methods using acoustic emission signals can analyze acoustic waves and provide important information for leak detection and localization. To address safety and protect the operation of industrial pipelines, a novel hybrid approach [...] Read more.

Acoustic emission techniques are widely used to monitor industrial pipelines. Intelligent methods using acoustic emission signals can analyze acoustic waves and provide important information for leak detection and localization. To address safety and protect the operation of industrial pipelines, a novel hybrid approach based on acoustic emission signals is proposed to achieve reliable leak localization. The proposed method employs minimum entropy deconvolution using the maximization kurtosis norm of acoustic emission signals to remove noise and identify important feature signals. In addition, the damping frequency energy based on the dynamic differential equation with damping term is designed to extract important energy information, and a smooth envelope for the feature signals over time is generated. The zero crossing tracks the arrival time via the envelope changes and identifies the time difference of the acoustic waves from the two channels, each of which is installed at the end of a pipeline. Finally, the time data are combined with the velocity data to localize the leak. The proposed approach has better performance than the existing generalized cross-correlation and empirical mode decomposition combined with the generalized cross-correlation methods, providing proper leak localization in the industrial pipeline. Full article

(This article belongs to the Special Issue Sensing Technologies for Fault Diagnostics and Prognosis)

► Show Figures

Figure 1

16 pages, 2462 KiB

Open AccessArticle

Absolute Quantitation of Serum Antibody Reactivity Using the Richards Growth Model for Antigen Microspot Titration

by Krisztián Papp, Ágnes Kovács, Anita Orosz, Zoltán Hérincs, Judit Randek, Károly Liliom, Tamás Pfeil and József Prechl

Sensors 2022, 22(10), 3962; https://doi.org/10.3390/s22103962 - 23 May 2022

Cited by 3 | Viewed by 2961

Abstract

In spite of its pivotal role in the characterization of humoral immunity, there is no accepted method for the absolute quantitation of antigen-specific serum antibodies. We devised a novel method to quantify polyclonal antibody reactivity, which exploits protein microspot assays and employs a [...] Read more.

In spite of its pivotal role in the characterization of humoral immunity, there is no accepted method for the absolute quantitation of antigen-specific serum antibodies. We devised a novel method to quantify polyclonal antibody reactivity, which exploits protein microspot assays and employs a novel analytical approach. Microarrays with a density series of disease-specific antigens were treated with different serum dilutions and developed for IgG and IgA binding. By fitting the binding data of both dilution series to a product of two generalized logistic functions, we obtained estimates of antibody reactivity of two immunoglobulin classes simultaneously. These estimates are the antigen concentrations required for reaching the inflection point of thermodynamic activity coefficient of antibodies and the limiting activity coefficient of antigen. By providing universal chemical units, this approach may improve the standardization of serological testing, the quality control of antibodies and the quantitative mapping of the antibody–antigen interaction space. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

16 pages, 4108 KiB

Open AccessArticle

Deep-Learning-Based Algorithm for the Removal of Electromagnetic Interference Noise in Photoacoustic Endoscopic Image Processing

by Oleksandra Gulenko, Hyunmo Yang, KiSik Kim, Jin Young Youm, Minjae Kim, Yunho Kim, Woonggyu Jung and Joon-Mo Yang

Sensors 2022, 22(10), 3961; https://doi.org/10.3390/s22103961 - 23 May 2022

Cited by 13 | Viewed by 4128

Abstract

Despite all the expectations for photoacoustic endoscopy (PAE), there are still several technical issues that must be resolved before the technique can be successfully translated into clinics. Among these, electromagnetic interference (EMI) noise, in addition to the limited signal-to-noise ratio (SNR), have hindered [...] Read more.

Despite all the expectations for photoacoustic endoscopy (PAE), there are still several technical issues that must be resolved before the technique can be successfully translated into clinics. Among these, electromagnetic interference (EMI) noise, in addition to the limited signal-to-noise ratio (SNR), have hindered the rapid development of related technologies. Unlike endoscopic ultrasound, in which the SNR can be increased by simply applying a higher pulsing voltage, there is a fundamental limitation in leveraging the SNR of PAE signals because they are mostly determined by the optical pulse energy applied, which must be within the safety limits. Moreover, a typical PAE hardware situation requires a wide separation between the ultrasonic sensor and the amplifier, meaning that it is not easy to build an ideal PAE system that would be unaffected by EMI noise. With the intention of expediting the progress of related research, in this study, we investigated the feasibility of deep-learning-based EMI noise removal involved in PAE image processing. In particular, we selected four fully convolutional neural network architectures, U-Net, Segnet, FCN-16s, and FCN-8s, and observed that a modified U-Net architecture outperformed the other architectures in the EMI noise removal. Classical filter methods were also compared to confirm the superiority of the deep-learning-based approach. Still, it was by the U-Net architecture that we were able to successfully produce a denoised 3D vasculature map that could even depict the mesh-like capillary networks distributed in the wall of a rat colorectum. As the development of a low-cost laser diode or LED-based photoacoustic tomography (PAT) system is now emerging as one of the important topics in PAT, we expect that the presented AI strategy for the removal of EMI noise could be broadly applicable to many areas of PAT, in which the ability to apply a hardware-based prevention method is limited and thus EMI noise appears more prominently due to poor SNR. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Graphical abstract

16 pages, 45713 KiB

Open AccessArticle

A Novel Method Based on GAN Using a Segmentation Module for Oligodendroglioma Pathological Image Generation

by Juwon Kweon, Jisang Yoo, Seungjong Kim, Jaesik Won and Soonchul Kwon

Sensors 2022, 22(10), 3960; https://doi.org/10.3390/s22103960 - 23 May 2022

Cited by 7 | Viewed by 3344

Abstract

Digital pathology analysis using deep learning has been the subject of several studies. As with other medical data, pathological data are not easily obtained. Because deep learning-based image analysis requires large amounts of data, augmentation techniques are used to increase the size of [...] Read more.

Digital pathology analysis using deep learning has been the subject of several studies. As with other medical data, pathological data are not easily obtained. Because deep learning-based image analysis requires large amounts of data, augmentation techniques are used to increase the size of pathological datasets. This study proposes a novel method for synthesizing brain tumor pathology data using a generative model. For image synthesis, we used embedding features extracted from a segmentation module in a general generative model. We also introduce a simple solution for training a segmentation model in an environment in which the masked label of the training dataset is not supplied. As a result of this experiment, the proposed method did not make great progress in quantitative metrics but showed improved results in the confusion rate of more than 70 subjects and the quality of the visual output. Full article

(This article belongs to the Special Issue Recent Advances in Medical Image Processing Technologies)

► Show Figures

Figure 1

22 pages, 7588 KiB

Open AccessArticle

A Driver Gaze Estimation Method Based on Deep Learning

by Sayyed Mudassar Shah, Zhaoyun Sun, Khalid Zaman, Altaf Hussain, Muhammad Shoaib and Lili Pei

Sensors 2022, 22(10), 3959; https://doi.org/10.3390/s22103959 - 23 May 2022

Cited by 19 | Viewed by 4916

Abstract

Car crashes are among the top ten leading causes of death; they could mainly be attributed to distracted drivers. An advanced driver-assistance technique (ADAT) is a procedure that can notify the driver about a dangerous scenario, reduce traffic crashes, and improve road safety. [...] Read more.

Car crashes are among the top ten leading causes of death; they could mainly be attributed to distracted drivers. An advanced driver-assistance technique (ADAT) is a procedure that can notify the driver about a dangerous scenario, reduce traffic crashes, and improve road safety. The main contribution of this work involved utilizing the driver’s attention to build an efficient ADAT. To obtain this “attention value”, the gaze tracking method is proposed. The gaze direction of the driver is critical toward understanding/discerning fatal distractions, pertaining to when it is obligatory to notify the driver about the risks on the road. A real-time gaze tracking system is proposed in this paper for the development of an ADAT that obtains and communicates the gaze information of the driver. The developed ADAT system detects various head poses of the driver and estimates eye gaze directions, which play important roles in assisting the driver and avoiding any unwanted circumstances. The first (and more significant) task in this research work involved the development of a benchmark image dataset consisting of head poses and horizontal and vertical direction gazes of the driver’s eyes. To detect the driver’s face accurately and efficiently, the You Only Look Once (YOLO-V4) face detector was used by modifying it with the Inception-v3 CNN model for robust feature learning and improved face detection. Finally, transfer learning in the InceptionResNet-v2 CNN model was performed, where the CNN was used as a classification model for head pose detection and eye gaze angle estimation; a regression layer to the InceptionResNet-v2 CNN was added instead of SoftMax and the classification output layer. The proposed model detects and estimates head pose directions and eye directions with higher accuracy. The average accuracy achieved by the head pose detection system was 91%; the model achieved a RMSE of 2.68 for vertical and 3.61 for horizontal eye gaze estimations. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

10 pages, 2921 KiB

Open AccessCommunication

A Theoretical Study of the Sensing Mechanism of a Schiff-Based Sensor for Fluoride

by Sha Ding, Yong Xia, Xiaoqi Lin, Aokui Sun, Xianggang Li and Yuejun Liu

Sensors 2022, 22(10), 3958; https://doi.org/10.3390/s22103958 - 23 May 2022

Cited by 2 | Viewed by 1887

Abstract

In the current work, we studied the sensing process of the sensor (E)-2-((quinolin-8ylimino) methyl) phenol (QP) for fluoride anion (F^–) with a “turn on” fluorescent response by density functional theory (DFT) and time-dependent density functional theory (TDDFT) calculations. The proton transfer [...] Read more.

In the current work, we studied the sensing process of the sensor (E)-2-((quinolin-8ylimino) methyl) phenol (QP) for fluoride anion (F^–) with a “turn on” fluorescent response by density functional theory (DFT) and time-dependent density functional theory (TDDFT) calculations. The proton transfer process and the twisted intramolecular charge transfer (TICT) process of QP have been explored by using potential energy curves as functions of the distance of N-H and dihedral angle C-N=C-C both in the ground and the excited states. According to the calculated results, the fluorescence quenching mechanism of QP and the fluorescent response for F^– have been fully explored. These results indicate that the current calculations completely reproduce the experimental results and provide compelling evidence for the sensing mechanism of QP for F^–. Full article

(This article belongs to the Section Chemical Sensors)

► Show Figures

Figure 1

23 pages, 26641 KiB

Open AccessArticle

Distributed Fiber-Optic Strain Sensing of an Innovative Reinforced Concrete Beam–Column Connection

by Shenghan Zhang, Han Liu, Esam Darwish, Khalid M. Mosalam and Matthew J. DeJong

Sensors 2022, 22(10), 3957; https://doi.org/10.3390/s22103957 - 23 May 2022

Cited by 5 | Viewed by 3403

Abstract

Distributed fiber-optic sensing (DFOS) technologies have been used for decades to detect damage in infrastructure. One recent DFOS technology, Optical Frequency Domain Reflectometry (OFDR), has attracted attention from the structural engineering community because its high spatial resolution and refined accuracy could enable new [...] Read more.

Distributed fiber-optic sensing (DFOS) technologies have been used for decades to detect damage in infrastructure. One recent DFOS technology, Optical Frequency Domain Reflectometry (OFDR), has attracted attention from the structural engineering community because its high spatial resolution and refined accuracy could enable new monitoring possibilities and new insight regarding the behavior of reinforced concrete (RC) structures. The current research project explores the ability and potential of OFDR to measure distributed strain in RC structures through laboratory tests on an innovative beam–column connection, in which a partial slot joint was introduced between the beam and the column to control damage. In the test specimen, fiber-optic cables were embedded in both the steel reinforcement and concrete. The specimen was tested under quasi-static cyclic loading with increasing displacement demand at the structural laboratory of the Pacific Earthquake Engineering Research (PEER) Center of UC Berkeley. Different types of fiber-optic cables were embedded both in the concrete and the rebar. The influence of the cable coating and cable position are discussed. The DFOS results are compared with traditional measurements (DIC and LVDT). The high resolution of DFOS at small deformations provides new insights regarding the mechanical behavior of the slotted RC beam–column connection, including direct measurement of beam curvature, rebar deformation, and slot opening and closing. A major contribution of this work is the quantification of the performance and limitations of the DFOS system under large cyclic strains. Performance is quantified in terms of non-valid points (which occur in large strains when the DFOS analyzer does not return a strain value), maximum strain that can be reliably measured, crack width that causes cable rupture, and the effect of the cable coating on the measurements. Structural damage indices are also proposed based on the DFOS results. These damage indices correlate reasonably well with the maximum sustained drift, indicating the potential of using DFOS for RC structural damage assessment. The experimental data set is made publicly available. Full article

(This article belongs to the Special Issue Distributed Optical Fiber Sensors for Concrete Structure Monitoring)

► Show Figures

Figure 1

21 pages, 688 KiB

Open AccessArticle

Securing Fog Computing with a Decentralised User Authentication Approach Based on Blockchain

by Otuekong Umoren, Raman Singh, Zeeshan Pervez and Keshav Dahal

Sensors 2022, 22(10), 3956; https://doi.org/10.3390/s22103956 - 23 May 2022

Cited by 19 | Viewed by 4755

Abstract

The use of low-cost sensors in IoT over high-cost devices has been considered less expensive. However, these low-cost sensors have their own limitations such as the accuracy, quality, and reliability of the data collected. Fog computing offers solutions to those limitations; nevertheless, owning [...] Read more.

The use of low-cost sensors in IoT over high-cost devices has been considered less expensive. However, these low-cost sensors have their own limitations such as the accuracy, quality, and reliability of the data collected. Fog computing offers solutions to those limitations; nevertheless, owning to its intrinsic distributed architecture, it faces challenges in the form of security of fog devices, secure authentication and privacy. Blockchain technology has been utilised to offer solutions for the authentication and security challenges in fog systems. This paper proposes an authentication system that utilises the characteristics and advantages of blockchain and smart contracts to authenticate users securely. The implemented system uses the email address, username, Ethereum address, password and data from a biometric reader to register and authenticate users. Experiments showed that the proposed method is secure and achieved performance improvement when compared to existing methods. The comparison of results with state-of-the-art showed that the proposed authentication system consumed up to 30% fewer resources in transaction and execution cost; however, there was an increase of up to 30% in miner fees. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI)-Based Approaches for Developing Low-Cost Sensor (LCS) IoT Systems)

► Show Figures

Figure 1

29 pages, 19971 KiB

Open AccessArticle

Bluetooth Load-Cell-Based Support-Monitoring System for Safety Management at a Construction Site

by Haksun Kim, Sehwan Park, Minkyo Yeom, Hakbo Shim, Soonjeon Park and Junkyeong Kim

Sensors 2022, 22(10), 3955; https://doi.org/10.3390/s22103955 - 23 May 2022

Cited by 4 | Viewed by 2544

Abstract

At construction sites, temporary facilities have caused continuous collapse accidents, causing damage to human life. If the concrete placing height is high and the worker is pushed into one place at the time of placing, the working load may be exceeded and a [...] Read more.

At construction sites, temporary facilities have caused continuous collapse accidents, causing damage to human life. If the concrete placing height is high and the worker is pushed into one place at the time of placing, the working load may be exceeded and a collapse accident may occur. In order to solve this problem, in this research, we developed a monitoring load-measurement program based on a Bluetooth wireless load cell (load-cell sensor) so that the load can be converted to digital and the numerical value can be confirmed by the pressure sensor. The load cell using Bluetooth was designed and manufactured according to the support. Then, the performance was verified through 3D finite element analysis by modeling and experimental tests. In addition, we constructed a system to generate notifications and warnings step by step when the load is close to a dangerous load, confirmed the load distribution pattern by position, and established a method to confirm real-time data numerically and graphically. Finally, we evaluated the practical application of the load-monitoring system using field-test data using a wireless load-cell. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

16 pages, 17320 KiB

Open AccessArticle

Silicone-Textile Composite Resistive Strain Sensors for Human Motion-Related Parameters

by Joshua Di Tocco, Daniela Lo Presti, Alberto Rainer, Emiliano Schena and Carlo Massaroni

Sensors 2022, 22(10), 3954; https://doi.org/10.3390/s22103954 - 23 May 2022

Cited by 14 | Viewed by 2833

Abstract

In recent years, soft and flexible strain sensors have found application in wearable devices for monitoring human motion and physiological parameters. Conductive textile-based sensors are good candidates for developing these sensors. However, their robust electro-mechanical connection and susceptibility to environmental factors are still [...] Read more.

In recent years, soft and flexible strain sensors have found application in wearable devices for monitoring human motion and physiological parameters. Conductive textile-based sensors are good candidates for developing these sensors. However, their robust electro-mechanical connection and susceptibility to environmental factors are still an open challenge to date. In this work, the manufacturing process of a silicone-textile composite resistive strain sensor based on a conductive resistive textile encapsulated into a dual-layer of silicone rubber is reported. In the working range typical of biomedical applications (up to 50%), the proposed flexible, skin-safe and moisture resistant strain sensor exhibited high sensitivity (gauge factor of −1.1), low hysteresis (maximum hysteresis error 3.2%) and ease of shaping in custom designs through a facile manufacturing process. To test the developed flexible sensor, two applicative scenarios covering the whole working range have been considered: the recording of the chest wall expansion during respiratory activity and the capture of the elbow flexion/extension movements. Full article

(This article belongs to the Special Issue Novel Sensing Technologies for Digital Health)

► Show Figures

Figure 1

22 pages, 2418 KiB

Open AccessReview

A Review of Noninvasive Methodologies to Estimate the Blood Pressure Waveform

by Tasbiraha Athaya and Sunwoong Choi

Sensors 2022, 22(10), 3953; https://doi.org/10.3390/s22103953 - 23 May 2022

Cited by 23 | Viewed by 9027

Abstract

Accurate estimation of blood pressure (BP) waveforms is critical for ensuring the safety and proper care of patients in intensive care units (ICUs) and for intraoperative hemodynamic monitoring. Normal cuff-based BP measurements can only provide systolic blood pressure (SBP) and diastolic blood pressure [...] Read more.

Accurate estimation of blood pressure (BP) waveforms is critical for ensuring the safety and proper care of patients in intensive care units (ICUs) and for intraoperative hemodynamic monitoring. Normal cuff-based BP measurements can only provide systolic blood pressure (SBP) and diastolic blood pressure (DBP). Alternatively, the BP waveform can be used to estimate a variety of other physiological parameters and provides additional information about the patient’s health. As a result, various techniques are being proposed for accurately estimating the BP waveforms. The purpose of this review is to summarize the current state of knowledge regarding the BP waveform, three methodologies (pressure-based, ultrasound-based, and deep-learning-based) used in noninvasive BP waveform estimation research and the feasibility of employing these strategies at home as well as in ICUs. Additionally, this article will discuss the physical concepts underlying both invasive and noninvasive BP waveform measurements. We will review historical BP waveform measurements, standard clinical procedures, and more recent innovations in noninvasive BP waveform monitoring. Although the technique has not been validated, it is expected that precise, noninvasive BP waveform estimation will be available in the near future due to its enormous potential. Full article

(This article belongs to the Special Issue Advances in Intelligent Sensing Devices and Microsystems for Medical Applications)

► Show Figures

Figure 1

9 pages, 2146 KiB

Open AccessCommunication

µRA—A New Compact Easy-to-Use Raman System for All Hydrogen Isotopologues

by Florian Priester, Alexander Marsteller, Simon Niemes, Nancy Tuchscherer and Stefan Welte

Sensors 2022, 22(10), 3952; https://doi.org/10.3390/s22103952 - 23 May 2022

Cited by 4 | Viewed by 2283

Abstract

We have developed a new compact and cost-efficient Laser-Raman system for the simultaneous measurement of all six hydrogen isotopologues. The focus of this research was set on producing a tool that can be implemented in virtually any existing setup providing in situ process [...] Read more.

We have developed a new compact and cost-efficient Laser-Raman system for the simultaneous measurement of all six hydrogen isotopologues. The focus of this research was set on producing a tool that can be implemented in virtually any existing setup providing in situ process control and analytics. The “micro Raman (µRA)” system is completely fiber-coupled for an easy setup consisting of (i) a spectrometer/CCD unit, (ii) a 532 nm laser, and (iii) a commercial Raman head coupled with a newly developed, tritium-compatible all-metal sealed DN16CF flange/Raman window serving as the process interface. To simplify the operation, we developed our own software suite for instrument control, data acquisition, and data evaluation in real-time. We have given a detailed description of the system, showing the system’s capabilities in terms of the lower level of detection, and presented the results of a dedicated campaign using the accurate reference mixtures of all of the hydrogen isotopologues benchmarking µRA against two of the most sensitive Raman systems for tritium operation. Due to its modular nature, modifications that allow for the detection of various other gas species can be easily implemented. Full article

(This article belongs to the Section Chemical Sensors)

► Show Figures

Figure 1

19 pages, 878 KiB

Open AccessArticle

Graph Layer Security: Encrypting Information via Common Networked Physics

by Zhuangkun Wei, Liang Wang, Schyler Chengyao Sun, Bin Li and Weisi Guo

Sensors 2022, 22(10), 3951; https://doi.org/10.3390/s22103951 - 23 May 2022

Cited by 5 | Viewed by 2650

Abstract

The proliferation of low-cost Internet of Things (IoT) devices has led to a race between wireless security and channel attacks. Traditional cryptography requires high computational power and is not suitable for low-power IoT scenarios. Whilst recently developed physical layer security (PLS) can exploit [...] Read more.

The proliferation of low-cost Internet of Things (IoT) devices has led to a race between wireless security and channel attacks. Traditional cryptography requires high computational power and is not suitable for low-power IoT scenarios. Whilst recently developed physical layer security (PLS) can exploit common wireless channel state information (CSI), its sensitivity to channel estimation makes them vulnerable to attacks. In this work, we exploit an alternative common physics shared between IoT transceivers: the monitored channel-irrelevant physical networked dynamics (e.g., water/oil/gas/electrical signal-flows). Leveraging this, we propose, for the first time, graph layer security (GLS), by exploiting the dependency in physical dynamics among network nodes for information encryption and decryption. A graph Fourier transform (GFT) operator is used to characterise such dependency into a graph-bandlimited subspace, which allows the generation of channel-irrelevant cipher keys by maximising the secrecy rate. We evaluate our GLS against designed active and passive attackers, using IEEE 39-Bus system. Results demonstrate that GLS is not reliant on wireless CSI, and can combat attackers that have partial networked dynamic knowledge (realistic access to full dynamic and critical nodes remains challenging). We believe this novel GLS has widespread applicability in secure health monitoring and for digital twins in adversarial radio environments. Full article

(This article belongs to the Topic Cyber Security and Critical Infrastructures)

► Show Figures

Figure 1

21 pages, 4858 KiB

Open AccessArticle

Solar Energy Harvesting to Improve Capabilities of Wearable Devices

by Alba Páez-Montoro, Mario García-Valderas, Emilio Olías-Ruíz and Celia López-Ongil

Sensors 2022, 22(10), 3950; https://doi.org/10.3390/s22103950 - 23 May 2022

Cited by 22 | Viewed by 6019

Abstract

The market of wearable devices has been growing over the past decades. Smart wearables are usually part of IoT (Internet of things) systems and include many functionalities such as physiological sensors, processing units and wireless communications, that are useful in fields like healthcare, [...] Read more.

The market of wearable devices has been growing over the past decades. Smart wearables are usually part of IoT (Internet of things) systems and include many functionalities such as physiological sensors, processing units and wireless communications, that are useful in fields like healthcare, activity tracking and sports, among others. The number of functions that wearables have are increasing all the time. This result in an increase in power consumption and more frequent recharges of the battery. A good option to solve this problem is using energy harvesting so that the energy available in the environment is used as a backup power source. In this paper, an energy harvesting system for solar energy with a flexible battery, a semi-flexible solar harvester module and a BLE (Bluetooth^® Low Energy) microprocessor module is presented as a proof-of-concept for the future integration of solar energy harvesting in a real wearable smart device. The designed device was tested under different circumstances to estimate the increase in battery lifetime during common daily routines. For this purpose, a procedure for testing energy harvesting solutions, based on solar energy, in wearable devices has been proposed. The main result obtained is that the device could permanently work if the solar cells received a significant amount of direct sunlight for 6 h every day. Moreover, in real-life scenarios, the device was able to generate a minimum and a maximum power of 27.8 mW and 159.1 mW, respectively. For the wearable system selected, Bindi, the dynamic tests emulating daily routines has provided increases in the state of charge from 19% (winter cloudy days, 4 solar cells) to 53% (spring sunny days, 2 solar cells). 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

Figure 1

11 pages, 863 KiB

Open AccessArticle

Automatic Personality Assessment through Movement Analysis

by David Delgado-Gómez, Antonio Eduardo Masó-Besga, David Aguado, Victor J. Rubio, Aaron Sujar and Sofia Bayona

Sensors 2022, 22(10), 3949; https://doi.org/10.3390/s22103949 - 23 May 2022

Cited by 3 | Viewed by 3153

Abstract

Obtaining accurate and objective assessments of an individual’s personality is vital in many areas including education, medicine, sports and management. Currently, most personality assessments are conducted using scales and questionnaires. Unfortunately, it has been observed that both scales and questionnaires present various drawbacks. [...] Read more.

Obtaining accurate and objective assessments of an individual’s personality is vital in many areas including education, medicine, sports and management. Currently, most personality assessments are conducted using scales and questionnaires. Unfortunately, it has been observed that both scales and questionnaires present various drawbacks. Their limitations include the lack of veracity in the answers, limitations in the number of times they can be administered, or cultural biases. To solve these problems, several articles have been published in recent years proposing the use of movements that participants make during their evaluation as personality predictors. In this work, a multiple linear regression model was developed to assess the examinee’s personality based on their movements. Movements were captured with the low-cost Microsoft Kinect camera, which facilitates its acceptance and implementation. To evaluate the performance of the proposed system, a pilot study was conducted aimed at assessing the personality traits defined by the Big-Five Personality Model. It was observed that the traits that best fit the model are Extroversion and Conscientiousness. In addition, several patterns that characterize the five personality traits were identified. These results show that it is feasible to assess an individual’s personality through his or her movements and open up pathways for several research. Full article

(This article belongs to the Special Issue Kinect Sensor and Its Application)

► Show Figures

Figure 1

19 pages, 3212 KiB

Open AccessArticle

Implementation of Omni-D Tele-Presence Robot Using Kalman Filter and Tricon Ultrasonic Sensors

by Hassan Tariq, Muhammad Rashid, Asfa Javed, Muhammad Aaqib Riaz, Mohammed Sinky and Muhammad Yousuf Irfan Zia

Sensors 2022, 22(10), 3948; https://doi.org/10.3390/s22103948 - 23 May 2022

Cited by 2 | Viewed by 2642

Abstract

The tele-presence robot is designed to set forth an economic solution to facilitate day-to-day normal activities in almost every field. There are several solutions to design tele-presence robots, e.g., Skype and team viewer, but it is pretty inappropriate to use Skype and extra [...] Read more.

The tele-presence robot is designed to set forth an economic solution to facilitate day-to-day normal activities in almost every field. There are several solutions to design tele-presence robots, e.g., Skype and team viewer, but it is pretty inappropriate to use Skype and extra hardware. Therefore, in this article, we have presented a robust implementation of the tele-presence robot. Our proposed omnidirectional tele-presence robot consists of (i) Tricon ultrasonic sensors, (ii) Kalman filter implementation and control, and (iii) integration of our developed WebRTC-based application with the omnidirectional tele-presence robot for video transmission. We present a new algorithm to encounter the sensor noise with the least number of sensors for the estimation of Kalman filter. We have simulated the complete model of robot in Simulink and Matlab for the tough paths and critical hurdles. The robot successfully prevents the collision and reaches the destination. The mean errors for the estimation of position and velocity are 5.77% and 2.04%. To achieve efficient and reliable video transmission, the quality factors such as resolution, encoding, average delay and throughput are resolved using the WebRTC along with the integration of the communication protocols. To protect the data transmission, we have implemented the SSL protocol and installed it on the server. We tested three different cases of video resolutions (i.e.,

320 \times 280

,

820 \times 460

and

900 \times 590

) for the performance evaluation of the video transmission. For the highest resolution, our TPR takes 3.5 ms for the encoding, and the average delay is 2.70 ms with 900 × 590 pixels. Full article

(This article belongs to the Special Issue Robotic Systems and Automatic Control: Mathematical Models, Technologies, Applications and Challenges)

► Show Figures

Figure 1

19 pages, 4382 KiB

Open AccessArticle

Applied Machine Learning in Industry 4.0: Case-Study Research in Predictive Models for Black Carbon Emissions

by Javier Rubio-Loyola and Wolph Ronald Shwagger Paul-Fils

Sensors 2022, 22(10), 3947; https://doi.org/10.3390/s22103947 - 23 May 2022

Cited by 6 | Viewed by 2836

Abstract

Industry 4.0 constitutes a major application domain for sensor data analytics. Industrial furnaces (IFs) are complex machines made with special thermodynamic materials and technologies used in industrial production applications that require special heat treatment cycles. One of the most critical issues while operating [...] Read more.

Industry 4.0 constitutes a major application domain for sensor data analytics. Industrial furnaces (IFs) are complex machines made with special thermodynamic materials and technologies used in industrial production applications that require special heat treatment cycles. One of the most critical issues while operating IFs is the emission of black carbon (EoBC), which is due to a large number of factors such as the quality and amount of fuel, furnace efficiency, technology used for the process, operation practices, type of loads and other aspects related to the process conditions or mechanical properties of fluids at furnace operation. This paper presents a methodological approach to predict EoBC during the operation of IFs with the use of predictive models of machine learning (ML). We make use of a real data set with historical operation to train ML models, and through evaluation with real data we identify the most suitable approach that best fits the characteristics of the data set and implementation constraints in real production environments. The evaluation results confirm that it is possible to predict the undesirable EoBC well in advance, by means of a predictive model. To the best of our knowledge, this paper is the first approach to detail machine-learning concepts for predicting EoBC in the IF industry. Full article

(This article belongs to the Special Issue Smart Sensors Application in Predictive Maintenance)

► Show Figures

Figure 1

18 pages, 5523 KiB

Open AccessArticle

Research on an Improved Segmentation Recognition Algorithm of Overlapping Agaricus bisporus

by Shuzhen Yang, Bowen Ni, Wanhe Du and Tao Yu

Sensors 2022, 22(10), 3946; https://doi.org/10.3390/s22103946 - 23 May 2022

Cited by 13 | Viewed by 2424

Abstract

The accurate identification of overlapping Agaricus bisporus in a factory environment is one of the challenges faced by automated picking. In order to better segment the complex adhesion between Agaricus bisporus, this paper proposes a segmentation recognition algorithm for overlapping Agaricus bisporus [...] Read more.

The accurate identification of overlapping Agaricus bisporus in a factory environment is one of the challenges faced by automated picking. In order to better segment the complex adhesion between Agaricus bisporus, this paper proposes a segmentation recognition algorithm for overlapping Agaricus bisporus. This algorithm calculates the global gradient threshold and divides the image according to the image edge gradient feature to obtain the binary image. Then, the binary image is filtered and morphologically processed, and the contour of the overlapping Agaricus bisporus area is obtained by edge detection in the Canny operator, the convex hull and concave area are extracted for polygon simplification, and the vertices are extracted using Harris corner detection to determine the segmentation point. After dividing the contour fragments by the dividing point, the branch definition algorithm is used to merge and group all the contours of the same Agaricus bisporus. Finally, the least squares ellipse fitting algorithm and the minimum distance circle fitting algorithm are used to reconstruct the outline of Agaricus bisporus, and the demand information of Agaricus bisporus picking is obtained. The experimental results show that this method can effectively overcome the influence of uneven illumination during image acquisition and be more adaptive to complex planting environments. The recognition rate of Agaricus bisporus in overlapping situations is more than 96%, and the average coordinate deviation rate of the algorithm is less than 1.59%. Full article

(This article belongs to the Special Issue AI-Based Sensors and Sensing Systems for Smart Agriculture)

► Show Figures

Figure 1

13 pages, 9066 KiB

Open AccessCommunication

Metamaterial Vivaldi Antenna Array for Breast Cancer Detection

by Marwa Slimi, Bassem Jmai, Hugo Dinis, Ali Gharsallah and Paulo Mateus Mendes

Sensors 2022, 22(10), 3945; https://doi.org/10.3390/s22103945 - 23 May 2022

Cited by 17 | Viewed by 3290

Abstract

The objective of this work is the design and validation of a directional Vivaldi antenna to detect tumor cells’ electromagnetic waves with a frequency of around 5 GHz. The proposed antenna is 33% smaller than a traditional Vivaldi antenna due to the use [...] Read more.

The objective of this work is the design and validation of a directional Vivaldi antenna to detect tumor cells’ electromagnetic waves with a frequency of around 5 GHz. The proposed antenna is 33% smaller than a traditional Vivaldi antenna due to the use of metamaterials in its design. It has an excellent return loss of 25 dB at 5 GHz and adequate radiation characteristics as its gain is 6.2 dB at 5 GHz. The unit cell size of the proposed metamaterial is 0.058λ × 0.054λ at the operation frequency of 5 GHz. The proposed antenna was designed and optimized in CST microwave software, and the measured and simulated results were in good agreement. The experimental study demonstrates that an array composed with the presented antennas can detect the existence of tumors in a liquid breast phantom with positional accuracy through the analysis of the minimum amplitude of S_ii. Full article

(This article belongs to the Special Issue Metamaterial-Based Microwave Sensors)

► Show Figures

Figure 1

11 pages, 2191 KiB

Open AccessArticle

Surface Properties of CVD-Grown Graphene Transferred by Wet and Dry Transfer Processes

by Min-Ah Yoon, Chan Kim, Jae-Hyun Kim, Hak-Joo Lee and Kwang-Seop Kim

Sensors 2022, 22(10), 3944; https://doi.org/10.3390/s22103944 - 23 May 2022

Cited by 11 | Viewed by 3900

Abstract

Graphene, an atomically thin material, has unique electrical, mechanical, and optical properties that can enhance the performance of thin film-based flexible and transparent devices, including gas sensors. Graphene synthesized on a metallic catalyst must first be transferred onto a target substrate using wet [...] Read more.

Graphene, an atomically thin material, has unique electrical, mechanical, and optical properties that can enhance the performance of thin film-based flexible and transparent devices, including gas sensors. Graphene synthesized on a metallic catalyst must first be transferred onto a target substrate using wet or dry transfer processes; however, the graphene surface is susceptible to chemical modification and mechanical damage during the transfer. Defects on the graphene surface deteriorate its excellent intrinsic properties, thus reducing device performance. In this study, the surface properties of transferred graphene were investigated according to the transfer method (wet vs. dry) and characterized using atomic force microscopy, Raman spectroscopy, and contact angle measurements. After the wet transfer process, the surface properties of graphene exhibited tendencies similar to the poly(methyl methacrylate) residue remaining after solvent etching. The dry-transferred graphene revealed a surface closer to that of pristine graphene, regardless of substrates. These results provide insight into the utilization of wet and dry transfer processes for various graphene applications. Full article

(This article belongs to the Special Issue State-of-the Art in Gas Sensors based on Nanomaterials)

► Show Figures

Figure 1

14 pages, 16940 KiB

Open AccessArticle

Multi-Domain Neumann Network with Sensitivity Maps for Parallel MRI Reconstruction

by Jun-Hyeok Lee, Junghwa Kang, Se-Hong Oh and Dong Hye Ye

Sensors 2022, 22(10), 3943; https://doi.org/10.3390/s22103943 - 23 May 2022

Cited by 4 | Viewed by 2552

Abstract

MRI is an imaging technology that non-invasively obtains high-quality medical images for diagnosis. However, MRI has the major disadvantage of long scan times which cause patient discomfort and image artifacts. As one of the methods for reducing the long scan time of MRI, [...] Read more.

MRI is an imaging technology that non-invasively obtains high-quality medical images for diagnosis. However, MRI has the major disadvantage of long scan times which cause patient discomfort and image artifacts. As one of the methods for reducing the long scan time of MRI, the parallel MRI method for reconstructing a high-fidelity MR image from under-sampled multi-coil k-space data is widely used. In this study, we propose a method to reconstruct a high-fidelity MR image from under-sampled multi-coil k-space data using deep-learning. The proposed multi-domain Neumann network with sensitivity maps (MDNNSM) is based on the Neumann network and uses a forward model including coil sensitivity maps for parallel MRI reconstruction. The MDNNSM consists of three main structures: the CNN-based sensitivity reconstruction block estimates coil sensitivity maps from multi-coil under-sampled k-space data; the recursive MR image reconstruction block reconstructs the MR image; and the skip connection accumulates each output and produces the final result. Experiments using the fastMRI T1-weighted brain image dataset were conducted at acceleration factors of 2, 4, and 8. Qualitative and quantitative experimental results show that the proposed MDNNSM method reconstructs MR images more accurately than other methods, including the generalized autocalibrating partially parallel acquisitions (GRAPPA) method and the original Neumann network. Full article

(This article belongs to the Special Issue Machine Learning Techniques for Medical Imaging, Sensing, and Analysis)

► Show Figures

Figure 1

13 pages, 1714 KiB

Open AccessTechnical Note

Application of the Differential Evolutionary Algorithm to the Estimation of Pipe Embedding Parameters

by Ping Lu, Shuang Chen, Xiaozhen Sheng and Yan Gao

Sensors 2022, 22(10), 3942; https://doi.org/10.3390/s22103942 - 23 May 2022

Cited by 3 | Viewed by 1454

Abstract

The time-delay estimation (TDE) method is the primary method for predicting leakage locations in buried water distribution pipelines. The accuracy of TDE depends on the acoustic speed and attenuation of the leakage signal propagating along the pipeline. The analytical prediction model is the [...] Read more.

The time-delay estimation (TDE) method is the primary method for predicting leakage locations in buried water distribution pipelines. The accuracy of TDE depends on the acoustic speed and attenuation of the leakage signal propagating along the pipeline. The analytical prediction model is the typical approach for obtaining the propagation speed and attenuation of leakage waves. However, the embedding parameters of the buried pipe in this model must be measured using soil tests, which are very difficult, costly, and time-consuming. These factors restrict the application of the TDE method in pinpointing pipeline leakage. A method for inverse identification of pipe embedding parameters using discrete wavenumbers obtained in field testing is presented in this paper, and the differential evolution algorithm is introduced as an optimization solution. A field experiment is conducted to validate the method, and the test wavenumbers are measured in a cast-iron pipeline. The estimated sensitive parameters in the analytical model using the method are soil elastic modulus, Poisson’s ratio, and pipe–soil contact coefficient, while the conventional soil test is used to measure the soil density due to the character of the optimization algorithm and the soil properties. The application effects show that the estimated parameters are close to those measured from a conventional soil test. The wave speed based on the estimated parameters was an excellent match for the on-site test in the engineering application. This work provides a less costly and more straightforward way to apply the TDE method for leak localization in buried pipelines. Full article

(This article belongs to the Topic Advances in Non-Destructive Testing Methods)

► Show Figures

Figure 1

14 pages, 2119 KiB

Open AccessArticle

A Single Subject, Feasibility Study of Using a Non-Contact Measurement to “Visualize” Temperature at Body-Seat Interface

by Zhuofu Liu, Vincenzo Cascioli and Peter W. McCarthy

Sensors 2022, 22(10), 3941; https://doi.org/10.3390/s22103941 - 23 May 2022

Cited by 4 | Viewed by 2065

Abstract

Measuring temperature changes at the body-seat interface has been drawing increased attention from both industrial and scientific fields, due to the increasingly sedentary nature from daily leisure activity to routine work. Although contact measurement is considered the gold standard, it can affect the [...] Read more.

Measuring temperature changes at the body-seat interface has been drawing increased attention from both industrial and scientific fields, due to the increasingly sedentary nature from daily leisure activity to routine work. Although contact measurement is considered the gold standard, it can affect the local micro-environment and the perception of sitting comfort. A non-contact temperature measurement system was developed to determine the interface temperature using data gathered unobtrusively and continuously from an infrared sensor (IRs). System performance was evaluated regarding linearity, hysteresis, reliability and accuracy. Then a healthy participant sat for an hour on low/intermediate density foams with thickness varying from 0.5–8 cm while body-seat interface temperature was measured simultaneously using a temperature sensor (contact) and an IRs (non-contact). IRs data were filtered with empirical mode decomposition and fractal scaling indices before a data-driven artificial neural network was utilized to estimate the contact surface temperature. A strong correlation existed between non-contact and contact temperature measurement (

ρ

> 0.85) and the estimation results showed a low root mean square error (RMSE) (<0.07 for low density foam and <0.16 for intermediate density foam) and high Nash-Sutcliff efficiency (NSE) values (≈1 for both types of foam materials). Full article

(This article belongs to the Special Issue Biosignal Sensing and Analysis for Healthcare Monitoring)

► Show Figures

Figure 1

3 pages, 165 KiB

Open AccessEditorial

Special Issue “EUV and X-ray Wavefront Sensing”

by Mourad Idir, Daniele Cocco and Lei Huang

Sensors 2022, 22(10), 3940; https://doi.org/10.3390/s22103940 - 23 May 2022

Cited by 1 | Viewed by 1537

Abstract

X-ray optics are extensively used in synchrotron radiation and free-electron laser facilities, as well as in table-top laboratory sources [...] Full article

(This article belongs to the Special Issue EUV and X-ray Wavefront Sensing)

22 pages, 13200 KiB

Open AccessArticle

Nonlinear Predictive Motion Control for Autonomous Mobile Robots Considering Active Fault-Tolerant Control and Regenerative Braking

by Peng Hang, Baichuan Lou and Chen Lv

Sensors 2022, 22(10), 3939; https://doi.org/10.3390/s22103939 - 23 May 2022

Cited by 8 | Viewed by 2407

Abstract

To further advance the performance and safety of autonomous mobile robots (AMRs), an integrated chassis control framework is proposed. In the longitudinal motion control module, a velocity-tracking controller was designed with the integrated feedforward and feedback control algorithm. Besides, the nonlinear model predictive [...] Read more.

To further advance the performance and safety of autonomous mobile robots (AMRs), an integrated chassis control framework is proposed. In the longitudinal motion control module, a velocity-tracking controller was designed with the integrated feedforward and feedback control algorithm. Besides, the nonlinear model predictive control (NMPC) method was applied to the four-wheel steering (4WS) path-tracking controller design. To deal with the failure of key actuators, an active fault-tolerant control (AFTC) algorithm was designed by reallocating the driving or braking torques of the remaining normal actuators, and the weighted least squares (WLS) method was used for torque reallocation. The simulation results show that AMRs can advance driving stability and braking safety in the braking failure condition with the utilization of AFTC and recapture the braking energy during decelerations. Full article

(This article belongs to the Special Issue Advanced Sensing and Safety Control for Connected and Automated Vehicles)

► Show Figures

Figure 1

16 pages, 407 KiB

Open AccessArticle

Deep Learning-Based Channel Estimation for mmWave Massive MIMO Systems in Mixed-ADC Architecture

by Rui Zhang, Weiqiang Tan, Wenliang Nie, Xianda Wu and Ting Liu

Sensors 2022, 22(10), 3938; https://doi.org/10.3390/s22103938 - 23 May 2022

Cited by 6 | Viewed by 4070

Abstract

Millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems can significantly reduce the number of radio frequency (RF) chains by using lens antenna arrays, because it is usually the case that the number of RF chains is often much smaller than the number of antennas, [...] Read more.

Millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems can significantly reduce the number of radio frequency (RF) chains by using lens antenna arrays, because it is usually the case that the number of RF chains is often much smaller than the number of antennas, so channel estimation becomes very challenging in practical wireless communication. In this paper, we investigated channel estimation for mmWave massive MIMO system with lens antenna array, in which we use a mixed (low/high) resolution analog-to-digital converter (ADC) architecture to trade-off the power consumption and performance of the system. Specifically, most antennas are equipped with low-resolution ADC and the rest of the antennas use high-resolution ADC. By utilizing the sparsity of the mmWave channel, the beamspace channel estimation can be expressed as a sparse signal recovery problem, and the channel can be recovered by the algorithm based on compressed sensing. We compare the traditional channel estimation scheme with the deep learning channel-estimation scheme, which has a better advantage, such as that the estimation scheme based on deep neural network is significantly better than the traditional channel-estimation algorithm. Full article

(This article belongs to the Special Issue Cell-Free Ultra Massive MIMO in 6G and Beyond Networks)

► Show Figures

Figure 1

16 pages, 2082 KiB

Open AccessArticle

A Message Passing-Assisted Iterative Noise Cancellation Method for Clipped OTFS-BFDM Systems

by Tingyao Wu, Hongxia Bie and Jinfang Wen

Sensors 2022, 22(10), 3937; https://doi.org/10.3390/s22103937 - 23 May 2022

Cited by 1 | Viewed by 1969

Abstract

Compared with orthogonal frequency division multiplexing (OFDM) systems, orthogonal time frequency space systems based on bi-orthogonal frequency division multiplexing (OTFS-BFDM) have lower out-of-band emission (OOBE) and better robustness to high-mobility scenarios, but suffer from a higher peak-to-average ratio (PAPR) in large data packets. [...] Read more.

Compared with orthogonal frequency division multiplexing (OFDM) systems, orthogonal time frequency space systems based on bi-orthogonal frequency division multiplexing (OTFS-BFDM) have lower out-of-band emission (OOBE) and better robustness to high-mobility scenarios, but suffer from a higher peak-to-average ratio (PAPR) in large data packets. In this paper, one-iteration clipping and filtering (OCF) is adopted to reduce the PAPR of OTFS-BFDM signals. However, the extra noise introduced by the clipping process, i.e., clipping noise, will distort the desired signal and increase the bit error rate (BER). We propose a message passing (MP)-assisted iterative cancellation (MP-AIC) method to cancel the clipping noise based on the traditional MP decoding at the receiver, which incorporates with the (OCF) at the transmitter to keep the sparsity of the effective channel matrix. The main idea of MP-AIC is to extract the residual signal fed to the MP detector by iteratively constructing reference clipping noise at the receiver. During each iteration, the variance of residual signal and channel noise are taken as input parameters of MP decoding to improve the BER. Moreover, the convergence probability of the modulation alphabet after MP decoding in the current iteration is used as the initial probability of MP decoding in the next iteration to accelerate the convergence rate of MP decoding. Simulation results show that the proposed MP-AIC method significantly improves MP-decoding accuracy while accelerating the BER convergence in the clipped OTFS-BFDM system. In the clipped OTFS-BFDM system with rectangular pulse shaping, the BER of MP-AIC with two iterations can be reduced by 72% more than that without clipping noise cancellation. Full article

(This article belongs to the Special Issue Advances in Dense 5G/6G Wireless Networks)

► Show Figures

Figure 1

15 pages, 6392 KiB

Open AccessArticle

Rolling Bearing Fault Diagnosis Based on Markov Transition Field and Residual Network

by Jialin Yan, Jiangming Kan and Haifeng Luo

Sensors 2022, 22(10), 3936; https://doi.org/10.3390/s22103936 - 23 May 2022

Cited by 45 | Viewed by 3778

Abstract

Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the [...] Read more.

Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the raw vibration signals of rolling bearings as the network input results in incomplete feature extraction. In order to efficiently represent the state characteristics of vibration signals in image form and improve the feature learning capability of the network, this paper proposes fault diagnosis model MTF-ResNet based on a Markov transition field and deep residual network. First, the data of raw vibration signals are augmented by using a sliding window. Then, vibration signal samples are converted into two-dimensional images by MTF, which retains the time dependence and frequency structure of time-series signals, and a deep residual neural network is established to perform feature extraction, and identify the severity and location of the bearing faults through image classification. Lastly, experiments were conducted on a bearing dataset to verify the effectiveness and superiority of the MTF-ResNet model. Features learned by the model are visualized by t-SNE, and experimental results indicate that MTF-ResNet showed better average accuracy compared with several widely used diagnostic methods. Full article

(This article belongs to the Special Issue Machine Health Monitoring and Fault Diagnosis Techniques)

► Show Figures

Figure 1

15 pages, 4310 KiB

Open AccessArticle

3D Object Detection Based on Attention and Multi-Scale Feature Fusion

by Minghui Liu, Jinming Ma, Qiuping Zheng, Yuchen Liu and Gang Shi

Sensors 2022, 22(10), 3935; https://doi.org/10.3390/s22103935 - 23 May 2022

Cited by 17 | Viewed by 3723

Abstract

Three-dimensional object detection in the point cloud can provide more accurate object data for autonomous driving. In this paper, we propose a method named MA-MFFC that uses an attention mechanism and a multi-scale feature fusion network with ConvNeXt module to improve the accuracy [...] Read more.

Three-dimensional object detection in the point cloud can provide more accurate object data for autonomous driving. In this paper, we propose a method named MA-MFFC that uses an attention mechanism and a multi-scale feature fusion network with ConvNeXt module to improve the accuracy of object detection. The multi-attention (MA) module contains point-channel attention and voxel attention, which are used in voxelization and 3D backbone. By considering the point-wise and channel-wise, the attention mechanism enhances the information of key points in voxels, suppresses background point clouds in voxelization, and improves the robustness of the network. The voxel attention module is used in the 3D backbone to obtain more robust and discriminative voxel features. The MFFC module contains the multi-scale feature fusion network and the ConvNeXt module; the multi-scale feature fusion network can extract rich feature information and improve the detection accuracy, and the convolutional layer is replaced with the ConvNeXt module to enhance the feature extraction capability of the network. The experimental results show that the average accuracy is 64.60% for pedestrians and 80.92% for cyclists on the KITTI dataset, which is 1.33% and 2.1% higher, respectively, compared with the baseline network, enabling more accurate detection and localization of more difficult objects. Full article

(This article belongs to the Topic Information Sensing Technology for Intelligent/Driverless Vehicle)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 22, Issue 10 (May-2 2022) – 361 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI