Sensors

23 pages, 3488 KiB

Open AccessArticle

VBlock: A Blockchain-Based Tamper-Proofing Data Protection Model for Internet of Vehicle Networks

by Collins Sey, Hang Lei, Weizhong Qian, Xiaoyu Li, Linda Delali Fiasam, Seth Larweh Kodjiku, Isaac Adjei-Mensah and Isaac Osei Agyemang

Sensors 2022, 22(20), 8083; https://doi.org/10.3390/s22208083 - 21 Oct 2022

Cited by 8 | Viewed by 2474

Abstract

The rapid advancement of the Internet of Vehicles (IoV) has led to a massive growth in data received from IoV networks. The cloud storage has been a timely service that provides a vast range of data storage for IoV networks. However, existing data [...] Read more.

The rapid advancement of the Internet of Vehicles (IoV) has led to a massive growth in data received from IoV networks. The cloud storage has been a timely service that provides a vast range of data storage for IoV networks. However, existing data storage and access models used to manage and protect data in IoV networks have proven to be insufficient. They are centralized and usually accompanied by a lack of trust, transparency, security, immutability, and provenance. In this paper, we propose VBlock, a blockchain-based system that addresses the issues of illegal modification of outsourced vehicular data for smart city management and improvement. We introduce a novel collusion-resistant model for outsourcing data to cloud storage that ensures the network remains tamper-proof, has good data provenance and auditing, and solves the centralized problems prone to the single point of failure. We introduced a key revocation mechanism to secure the network from malicious nodes. We formally define the system model of VBlock in the setting of a consortium blockchain. Our simulation results and security analysis show that the proposed model provides a strong security guarantee with high efficiency and is practicable in the IoV environment. Full article

(This article belongs to the Special Issue Blockchain for Internet of Things Applications)

► Show Figures

Figure 1

16 pages, 4329 KiB

Open AccessArticle

Improving the Sensing Properties of Graphene MEMS Pressure Sensor by Low-Temperature Annealing in Atmosphere

by Daosen Liu, Shengsheng Wei and Dejun Wang

Sensors 2022, 22(20), 8082; https://doi.org/10.3390/s22208082 - 21 Oct 2022

Cited by 3 | Viewed by 1566

Abstract

The high demand for pressure devices with miniaturization and a wide bearing range has encouraged researchers to explore new high-performance sensors from different approaches. In this study, a sensitive element based on graphene in-plane compression properties for realizing pressure sensing is experimentally prepared [...] Read more.

The high demand for pressure devices with miniaturization and a wide bearing range has encouraged researchers to explore new high-performance sensors from different approaches. In this study, a sensitive element based on graphene in-plane compression properties for realizing pressure sensing is experimentally prepared using microelectromechanical systems (MEMS) fabrication technology; it consists of a 50 µm thick, 1400 µm wide square multilayer component membrane and a graphene monolayer with a meander pattern. The prepared sample is extensively characterized and analyzed by using various techniques, including atomic force microscopy, Raman spectroscopy, infrared spectroscopy, X-ray photoelectron spectroscopy, COMSOL finite element method, and density functional theory. The sensing performance of the new pressure sensor based on the sensitive element are obtained by theoretical analysis for electromechanical measurements of the sensitive element before and after low-temperature annealing in atmosphere. Results demonstrate that atmospheric annealing at 300 °C enhances the pressure sensing sensitivity by 4 times compared to pristine graphene without annealing, which benefits from the desorption of hydroxyl groups on the graphene surface during annealing. The sensitivity is comparable and even better than that of previous sensors based on graphene in-plane properties. Our results provide new insights into realizing high-performance MEMS devices based on 2D sensitive materials. Full article

(This article belongs to the Section Sensor Materials)

► Show Figures

Figure 1

16 pages, 7102 KiB

Open AccessArticle

Measurement of Cable Force through a Fiber Bragg Grating-Type Thin Rod Vibration Sensor and Its Application

by Wanxu Zhu, Wei Teng, Fengrong Liu, Dongwen Wu and Yujiao Wu

Sensors 2022, 22(20), 8081; https://doi.org/10.3390/s22208081 - 21 Oct 2022

Cited by 1 | Viewed by 1485

Abstract

The key to evaluating the health status of cable-stayed bridges lies in the accuracy of cable force measurement. When measuring the cable force using the conventional frequency method, the clearance between the bracing cable and the protective tube is typically disregarded. Moreover, due [...] Read more.

The key to evaluating the health status of cable-stayed bridges lies in the accuracy of cable force measurement. When measuring the cable force using the conventional frequency method, the clearance between the bracing cable and the protective tube is typically disregarded. Moreover, due to their large size, existing vibration sensors are difficult to install into protective tubes for steel strand-type bracing cables to measure the cable force. To address the above difficulties, a type of thin rod vibration sensor only 5 mm in diameter was designed based on the high sensitivity of Fiber Bragg grating (FBG), and high-throughput data processing software for engineering calculation (EC) was self-developed. Then, the recognition principle of the thin rod vibration sensor was theoretically analyzed and a step-by-step tension test was carried out. The results demonstrated that the relative error of the cable force measured by the thin rod vibration sensor within 12.865 Hz was less than 5% and the sensitivity reached 28.7 pm/Hz, indicating its high measurement precision. Upon subsequent application of the thin rod vibration sensor to a monitoring test in the field, the relative error of the fundamental frequency between artificial and natural excitations was less than 4%. In addition, the error relative to both the theoretical frequency and the third-party sampling frequency was less than 5%, further verifying the accuracy and applicability for monitoring the cable force of bridges under natural excitation. Compared with the traditional cantilever FBG sensor, the improved sensor with supporting data processing software has the advantages of small cross-section, high reliability, and good sensitivity. The research results can provide a reference for the subsequent accurate measurement of cable force and the development of a supporting sensor data processing system. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

16 pages, 3618 KiB

Open AccessArticle

Polarization Calibration of a Microwave Polarimeter with Near-Infrared Up-Conversion for Optical Correlation and Detection

by Francisco J. Casas, Patricio Vielva, R. Belen Barreiro, Enrique Martínez-González and G. Pascual-Cisneros

Sensors 2022, 22(20), 8080; https://doi.org/10.3390/s22208080 - 21 Oct 2022

Cited by 4 | Viewed by 1330

Abstract

This paper presents a polarization calibration method applied to a microwave polarimeter demonstrator based on a near-infrared (NIR) frequency up-conversion stage that allows both optical correlation and signal detection at a wavelength of 1550 nm. The instrument was designed to measure the polarization [...] Read more.

This paper presents a polarization calibration method applied to a microwave polarimeter demonstrator based on a near-infrared (NIR) frequency up-conversion stage that allows both optical correlation and signal detection at a wavelength of 1550 nm. The instrument was designed to measure the polarization of cosmic microwave background (CMB) radiation from the sky, obtaining the Stokes parameters of the incoming signal simultaneously, in a frequency range from 10 to 20 GHz. A linearly polarized input signal with a variable polarization angle is used as excitation in the polarimeter calibration setup mounted in the laboratory. The polarimeter systematic errors can be corrected with the proposed calibration procedure, achieving high levels of polarization efficiency (low polarization percentage errors) and low polarization angle errors. The calibration method is based on the fitting of polarization errors by means of sinusoidal functions composed of additive or multiplicative terms. The accuracy of the fitting increases with the number of terms in such a way that the typical error levels required in low-frequency CMB experiments can be achieved with only a few terms in the fitting functions. On the other hand, assuming that the calibration signal is known with the required accuracy, additional terms can be calculated to reach the error levels needed in ultrasensitive B-mode polarization CMB experiments. Full article

(This article belongs to the Special Issue Towards Optoelectronic Technology: From Basic Research to Applications)

► Show Figures

Figure 1

16 pages, 4240 KiB

Open AccessArticle

Multi-Center Evaluation of Gel-Based and Dry Multipin EEG Caps

by Chuen Rue Ng, Patrique Fiedler, Levin Kuhlmann, David Liley, Beatriz Vasconcelos, Carlos Fonseca, Gabriella Tamburro, Silvia Comani, Troby Ka-Yan Lui, Chun-Yu Tse, Indhika Fauzhan Warsito, Eko Supriyanto and Jens Haueisen

Sensors 2022, 22(20), 8079; https://doi.org/10.3390/s22208079 - 21 Oct 2022

Cited by 9 | Viewed by 3030

Abstract

Dry electrodes for electroencephalography (EEG) allow new fields of application, including telemedicine, mobile EEG, emergency EEG, and long-term repetitive measurements for research, neurofeedback, or brain–computer interfaces. Different dry electrode technologies have been proposed and validated in comparison to conventional gel-based electrodes. Most previous [...] Read more.

Dry electrodes for electroencephalography (EEG) allow new fields of application, including telemedicine, mobile EEG, emergency EEG, and long-term repetitive measurements for research, neurofeedback, or brain–computer interfaces. Different dry electrode technologies have been proposed and validated in comparison to conventional gel-based electrodes. Most previous studies have been performed at a single center and by single operators. We conducted a multi-center and multi-operator study validating multipin dry electrodes to study the reproducibility and generalizability of their performance in different environments and for different operators. Moreover, we aimed to study the interrelation of operator experience, preparation time, and wearing comfort on the EEG signal quality. EEG acquisitions using dry and gel-based EEG caps were carried out in 6 different countries with 115 volunteers, recording electrode-skin impedances, resting state EEG and evoked activity. The dry cap showed average channel reliability of 81% but higher average impedances than the gel-based cap. However, the dry EEG caps required 62% less preparation time. No statistical differences were observed between the gel-based and dry EEG signal characteristics in all signal metrics. We conclude that the performance of the dry multipin electrodes is highly reproducible, whereas the primary influences on channel reliability and signal quality are operator skill and experience. Full article

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

► Show Figures

Figure 1

16 pages, 2505 KiB

Open AccessArticle

Novel Fuzzy Logic Scheme for Push-Based Critical Data Broadcast Mitigation in VNDN

by Sajjad Ahmad Khan and Huhnkuk Lim

Sensors 2022, 22(20), 8078; https://doi.org/10.3390/s22208078 - 21 Oct 2022

Cited by 4 | Viewed by 1357

Abstract

Vehicular Named Data Networking (VNDN) is one of the potential and future networking architectures that allow Connected and Autonomous Vehicles (CAV) to exchange data by simply disseminating the content over the network. VNDN only supports a pull-based data forwarding model, where the content [...] Read more.

Vehicular Named Data Networking (VNDN) is one of the potential and future networking architectures that allow Connected and Autonomous Vehicles (CAV) to exchange data by simply disseminating the content over the network. VNDN only supports a pull-based data forwarding model, where the content information is forwarded upon request. However, in critical situations, it is essential to design a push-based data forwarding model in order to broadcast the critical data packets without any requests. One of the challenges of push-based data forwarding in VNDN is the broadcasting effect, which occurs when every vehicle broadcasts critical information over the network. For instance, in emergency situations such as accidents, road hazards, and bad weather conditions, the producer generates a critical data packet and broadcasts it to all the nearby vehicles. Subsequently, all vehicles broadcast the same critical data packet to each other, which leads to a broadcast storm on the network. Therefore, this paper proposes a Fuzzy Logic-based Push Data Forwarding (FLPDF) scheme to mitigate the broadcast storm effect. The novelty of this paper is the suggestion and application of a fuzzy logic approach to mitigate the critical data broadcast storm effect in VNDN. In the proposed scheme, vehicles are grouped into clusters using the K-means clustering algorithm, and then Cluster Heads (CHs) are selected using a fuzzy logic approach. A CH is uniquely responsible for broadcasting the critical data packets to all other vehicles in a cluster. A Gateway (GW) has the role of forwarding the critical data packets to the nearest clusters via their GWs. The simulation results show that the proposed scheme outperforms the naive method in terms of transmitted data packets and efficiency. The proposed scheme generates five times fewer data packets and achieves six times higher efficiency than the naive scheme. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

22 pages, 4357 KiB

Open AccessArticle

Brain Age Prediction: A Comparison between Machine Learning Models Using Brain Morphometric Data

by Juhyuk Han, Seo Yeong Kim, Junhyeok Lee and Won Hee Lee

Sensors 2022, 22(20), 8077; https://doi.org/10.3390/s22208077 - 21 Oct 2022

Cited by 10 | Viewed by 5736

Abstract

Brain structural morphology varies over the aging trajectory, and the prediction of a person’s age using brain morphological features can help the detection of an abnormal aging process. Neuroimaging-based brain age is widely used to quantify an individual’s brain health as deviation from [...] Read more.

Brain structural morphology varies over the aging trajectory, and the prediction of a person’s age using brain morphological features can help the detection of an abnormal aging process. Neuroimaging-based brain age is widely used to quantify an individual’s brain health as deviation from a normative brain aging trajectory. Machine learning approaches are expanding the potential for accurate brain age prediction but are challenging due to the great variety of machine learning algorithms. Here, we aimed to compare the performance of the machine learning models used to estimate brain age using brain morphological measures derived from structural magnetic resonance imaging scans. We evaluated 27 machine learning models, applied to three independent datasets from the Human Connectome Project (HCP, n = 1113, age range 22–37), the Cambridge Centre for Ageing and Neuroscience (Cam-CAN, n = 601, age range 18–88), and the Information eXtraction from Images (IXI, n = 567, age range 19–86). Performance was assessed within each sample using cross-validation and an unseen test set. The models achieved mean absolute errors of 2.75–3.12, 7.08–10.50, and 8.04–9.86 years, as well as Pearson’s correlation coefficients of 0.11–0.42, 0.64–0.85, and 0.63–0.79 between predicted brain age and chronological age for the HCP, Cam-CAN, and IXI samples, respectively. We found a substantial difference in performance between models trained on the same data type, indicating that the choice of model yields considerable variation in brain-predicted age. Furthermore, in three datasets, regularized linear regression algorithms achieved similar performance to nonlinear and ensemble algorithms. Our results suggest that regularized linear algorithms are as effective as nonlinear and ensemble algorithms for brain age prediction, while significantly reducing computational costs. Our findings can serve as a starting point and quantitative reference for future efforts at improving brain age prediction using machine learning models applied to brain morphometric data. Full article

(This article belongs to the Special Issue Biomedical Data in Human-Machine Interaction)

► Show Figures

Figure 1

19 pages, 2729 KiB

Open AccessArticle

Construction of VGG16 Convolution Neural Network (VGG16_CNN) Classifier with NestNet-Based Segmentation Paradigm for Brain Metastasis Classification

by Abdulaziz Alshammari

Sensors 2022, 22(20), 8076; https://doi.org/10.3390/s22208076 - 21 Oct 2022

Cited by 11 | Viewed by 1990

Abstract

Brain metastases (BMs) happen often in patients with metastatic cancer (MC), requiring initial and precise diagnosis of BMs, which remains important for medical care preparation and radiotherapy prognostication. Nevertheless, the susceptibility of automated BM (ABMS) diagnosis is unfairly great for minute BMs, and [...] Read more.

Brain metastases (BMs) happen often in patients with metastatic cancer (MC), requiring initial and precise diagnosis of BMs, which remains important for medical care preparation and radiotherapy prognostication. Nevertheless, the susceptibility of automated BM (ABMS) diagnosis is unfairly great for minute BMs, and integrating into medical exercises to distinguish true metastases (MtS) from false positives remains difficult. For enhancing BM classification execution, MtS localization is performed through the NestNet framework. Subsequent to segmentation, classification is performed by employing the VGG16 convolution neural network. A novel loss function is computed by employing the weighted softmax function (WSF) for enhancing minute MtS diagnosis and for calibrating susceptibility and particularity. The aim of this study was to merge temporal prior data for ABMS detection. The proffered VGG16_CNN is capable of differentiating positive MtS among MtS candidates with high confidence, which typically needs distinct specialist analysis or additional investigation, remaining specifically apt for specialist reinforcement in actual medical practice. The proffered VGG16_CNN framework can be correlated with three advanced methodologies (moU-Net, DSNet, and U-Net) concerning diverse criteria. It was observed that the proffered VGG16_CNN attained 93.74% accuracy, 92% precision, 92.1% recall, and 67.08% F1-score. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Sensing Techniques for Complex Structural Health Monitoring)

► Show Figures

Figure 1

24 pages, 6024 KiB

Open AccessArticle

ST-DeepGait: A Spatiotemporal Deep Learning Model for Human Gait Recognition

by Latisha Konz, Andrew Hill and Farnoush Banaei-Kashani

Sensors 2022, 22(20), 8075; https://doi.org/10.3390/s22208075 - 21 Oct 2022

Cited by 5 | Viewed by 2174

Abstract

Human gait analysis presents an opportunity to study complex spatiotemporal data transpiring as co-movement patterns of multiple moving objects (i.e., human joints). Such patterns are acknowledged as movement signatures specific to an individual, offering the possibility to identify each individual based on unique [...] Read more.

Human gait analysis presents an opportunity to study complex spatiotemporal data transpiring as co-movement patterns of multiple moving objects (i.e., human joints). Such patterns are acknowledged as movement signatures specific to an individual, offering the possibility to identify each individual based on unique gait patterns. We present a spatiotemporal deep learning model, dubbed ST-DeepGait, to featurize spatiotemporal co-movement patterns of human joints, and accordingly classify such patterns to enable human gait recognition. To this end, the ST-DeepGait model architecture is designed according to the spatiotemporal human skeletal graph in order to impose learning the salient local spatial dynamics of gait as they occur over time. Moreover, we employ a multi-layer RNN architecture to induce a sequential notion of gait cycles in the model. Our experimental results show that ST-DeepGait can achieve recognition accuracy rates over 90%. Furthermore, we qualitatively evaluate the model with the class embeddings to show interpretable separability of the features in geometric latent space. Finally, to evaluate the generalizability of our proposed model, we perform a zero-shot detection on 10 classes of data completely unseen during training and achieve a recognition accuracy rate of 88% overall. With this paper, we also contribute our gait dataset captured with an RGB-D sensor containing approximately 30 video samples of each subject for 100 subjects totaling 3087 samples. While we use human gait analysis as a motivating application to evaluate ST-DeepGait, we believe that this model can be simply adopted and adapted to study co-movement patterns of multiple moving objects in other applications such as in sports analytics and traffic pattern analysis. Full article

(This article belongs to the Special Issue Biometrics Recognition Based on Sensor Technology)

► Show Figures

Figure 1

23 pages, 4599 KiB

Open AccessArticle

IIB–CPE: Inter and Intra Block Processing-Based Compressible Perceptual Encryption Method for Privacy-Preserving Deep Learning

by Ijaz Ahmad and Seokjoo Shin

Sensors 2022, 22(20), 8074; https://doi.org/10.3390/s22208074 - 21 Oct 2022

Cited by 2 | Viewed by 1569

Abstract

Perceptual encryption (PE) of images protects visual information while retaining the intrinsic properties necessary to enable computation in the encryption domain. Block–based PE produces JPEG-compliant images with almost the same compression savings as that of the plain images. The methods represent an input [...] Read more.

Perceptual encryption (PE) of images protects visual information while retaining the intrinsic properties necessary to enable computation in the encryption domain. Block–based PE produces JPEG-compliant images with almost the same compression savings as that of the plain images. The methods represent an input color image as a pseudo grayscale image to benefit from a smaller block size. However, such representation degrades image quality and compression savings, and removes color information, which limits their applications. To solve these limitations, we proposed inter and intra block processing for compressible PE methods (IIB–CPE). The method represents an input as a color image and performs block-level inter processing and sub-block-level intra processing on it. The intra block processing results in an inside–out geometric transformation that disrupts the symmetry of an entire block thus achieves visual encryption of local details while preserving the global contents of an image. The intra block-level processing allows the use of a smaller block size, which improves encryption efficiency without compromising compression performance. Our analyses showed that IIB–CPE offers 15% bitrate savings with better image quality than the existing PE methods. In addition, we extended the scope of applications of the proposed IIB–CPE to the privacy-preserving deep learning (PPDL) domain. Full article

(This article belongs to the Special Issue Advances in Coding, Sensing, and Processing for CFA Images, Light Field Images, and Point Cloud)

► Show Figures

Figure 1

34 pages, 1365 KiB

Open AccessSystematic Review

E-Cardiac Care: A Comprehensive Systematic Literature Review

by Umara Umar, Sanam Nayab, Rabia Irfan, Muazzam A. Khan and Amna Umer

Sensors 2022, 22(20), 8073; https://doi.org/10.3390/s22208073 - 21 Oct 2022

Cited by 4 | Viewed by 2498

Abstract

The Internet of Things (IoT) is a complete ecosystem encompassing various communication technologies, sensors, hardware, and software. IoT cutting-edge technologies and Artificial Intelligence (AI) have enhanced the traditional healthcare system considerably. The conventional healthcare system faces many challenges, including avoidable long wait times, [...] Read more.

The Internet of Things (IoT) is a complete ecosystem encompassing various communication technologies, sensors, hardware, and software. IoT cutting-edge technologies and Artificial Intelligence (AI) have enhanced the traditional healthcare system considerably. The conventional healthcare system faces many challenges, including avoidable long wait times, high costs, a conventional method of payment, unnecessary long travel to medical centers, and mandatory periodic doctor visits. A Smart healthcare system, Internet of Things (IoT), and AI are arguably the best-suited tailor-made solutions for all the flaws related to traditional healthcare systems. The primary goal of this study is to determine the impact of IoT, AI, various communication technologies, sensor networks, and disease detection/diagnosis in Cardiac healthcare through a systematic analysis of scholarly articles. Hence, a total of 104 fundamental studies are analyzed for the research questions purposefully defined for this systematic study. The review results show that deep learning emerges as a promising technology along with the combination of IoT in the domain of E-Cardiac care with enhanced accuracy and real-time clinical monitoring. This study also pins down the key benefits and significant challenges for E-Cardiology in the domains of IoT and AI. It further identifies the gaps and future research directions related to E-Cardiology, monitoring various Cardiac parameters, and diagnosis patterns. Full article

(This article belongs to the Special Issue Artificial Neural Networks for IoT-Enabled Smart Applications)

► Show Figures

Figure 1

20 pages, 4814 KiB

Open AccessReview

A Step toward Next-Generation Advancements in the Internet of Things Technologies

by Farhan Amin, Rashid Abbasi, Abdul Mateen, Muhammad Ali Abid and Salabat Khan

Sensors 2022, 22(20), 8072; https://doi.org/10.3390/s22208072 - 21 Oct 2022

Cited by 18 | Viewed by 3114

Abstract

The Internet of Things (IoT) devices generate a large amount of data over networks; therefore, the efficiency, complexity, interfaces, dynamics, robustness, and interaction need to be re-examined on a large scale. This phenomenon will lead to seamless network connectivity and the capability to [...] Read more.

The Internet of Things (IoT) devices generate a large amount of data over networks; therefore, the efficiency, complexity, interfaces, dynamics, robustness, and interaction need to be re-examined on a large scale. This phenomenon will lead to seamless network connectivity and the capability to provide support for the IoT. The traditional IoT is not enough to provide support. Therefore, we designed this study to provide a systematic analysis of next-generation advancements in the IoT. We propose a systematic catalog that covers the most recent advances in the traditional IoT. An overview of the IoT from the perspectives of big data, data science, and network science disciplines and also connecting technologies is given. We highlight the conceptual view of the IoT, key concepts, growth, and most recent trends. We discuss and highlight the importance and the integration of big data, data science, and network science along with key applications such as artificial intelligence, machine learning, blockchain, federated learning, etc. Finally, we discuss various challenges and issues of IoT such as architecture, integration, data provenance, and important applications such as cloud and edge computing, etc. This article will provide aid to the readers and other researchers in an understanding of the IoT’s next-generation developments and tell how they apply to the real world. Full article

(This article belongs to the Special Issue IoT Enabling Technologies for Smart Cities: Challenges and Approaches)

► Show Figures

Figure 1

19 pages, 6371 KiB

Open AccessArticle

Augmented Analytics Driven by AI: A Digital Transformation beyond Business Intelligence

by Noorah A. Alghamdi and Heyam H. Al-Baity

Sensors 2022, 22(20), 8071; https://doi.org/10.3390/s22208071 - 21 Oct 2022

Cited by 6 | Viewed by 5410

Abstract

Lately, Augmented Analytics (AA) has increasingly been introduced as a tool for transforming data into valuable insights for decision-making, and it has gained attention as one of the most advanced methods to facilitate modern analytics for different types of users. AA can be [...] Read more.

Lately, Augmented Analytics (AA) has increasingly been introduced as a tool for transforming data into valuable insights for decision-making, and it has gained attention as one of the most advanced methods to facilitate modern analytics for different types of users. AA can be defined as a combination of Business Intelligence (BI) and the advanced features of Artificial Intelligence (AI). With the massive growth in data diversity, the traditional approach to BI has become less useful and requires additional work to obtain timely results. However, the power of AA that uses AI can be leveraged in BI platforms with the use of Machine Learning (ML) and natural language comprehension to automate the cycle of business analytics. Despite the various benefits for businesses and end users in converting from BI to AA, research on this trend has been limited. This study presents a comparison of the capabilities of the traditional BI and its augmented version in the business analytics cycle. Our findings show that AA enhances analysis, reduces time, and supports data preparation, visualization, modelling, and generation of insights. However, AI-driven analytics cannot fully replace human decision-making, as most business problems cannot be solved purely by machines. Human interaction and perspectives are essential, and decision-makers still play an important role in sharing and operationalizing findings. Full article

(This article belongs to the Special Issue Machine Learning for IoT Applications and Digital Twins II)

► Show Figures

Figure 1

16 pages, 1757 KiB

Open AccessSystematic Review

Network Meta-Analysis of Trials Testing If Home Exercise Programs Informed by Wearables Measuring Activity Improve Peripheral Artery Disease Related Walking Impairment

by Shivshankar Thanigaimani, Harry Jin, Munasinghe Tharindu Silva and Jonathan Golledge

Sensors 2022, 22(20), 8070; https://doi.org/10.3390/s22208070 - 21 Oct 2022

Cited by 1 | Viewed by 1903

Abstract

Background: This study aimed to investigate whether home exercise programs informed by wearable activity monitors improved walking ability of patients with peripheral artery disease (PAD). Methods: A systematic literature search was performed to identify randomised controlled trials (RCT) testing home exercise that were [...] Read more.

Background: This study aimed to investigate whether home exercise programs informed by wearable activity monitors improved walking ability of patients with peripheral artery disease (PAD). Methods: A systematic literature search was performed to identify randomised controlled trials (RCT) testing home exercise that were or were not informed by wearable activity monitors. The primary outcome was the change in walking distance measured by a six-minute walking test or treadmill test over the course of the trial. Network meta-analysis (NMA) was performed using the gemtc R statistical package. The risk of bias was assessed using Cochrane tool for assessing risk of bias in RCTs (RoB 2.0). Results: A total of 14 RCTs involving 1544 participants were included. Nine trials used wearable activity monitors to inform the home exercise program tested, while five trials did not use wearable activity monitors to inform the home exercise program tested. Overall quality assessment showed 12 trials to be at low risk of bias and two trials at high risk of bias. Home exercise programs informed by wearable activity monitors significantly improved walking distance compared to non-exercise controls (Mean difference, MD: 32.8 m [95% credible interval, CrI: 6.1, 71.0]) but not compared to home exercise programs not informed by wearable activity monitors (MD: 4.7 m [95% CrI: −38.5, 55.4]). Conclusions: Home exercise informed by wearable activity monitors improve walking ability of patients with PAD. It is, however, unclear if activity monitoring informed exercise programs are more effective than exercise programs not using activity monitors. Full article

(This article belongs to the Special Issue Applications of Body Worn Sensors and Wearables)

► Show Figures

Figure 1

15 pages, 1835 KiB

Open AccessArticle

Effects of Resistance Training as a Behavioural Preventive Measure on Musculoskeletal Complaints, Maximum Strength and Ergonomic Risk in Dentists and Dental Assistants

by Fabian Holzgreve, Laura Fraeulin, Christian Maurer-Grubinger, Werner Betz, Christina Erbe, Tim Weis, Keno Janssen, Lisa Schulte, Amaya de Boer, Albert Nienhaus, David A. Groneberg and Daniela Ohlendorf

Sensors 2022, 22(20), 8069; https://doi.org/10.3390/s22208069 - 21 Oct 2022

Cited by 6 | Viewed by 2212

Abstract

Introduction: For dental professionals, musculoskeletal disorders (MSD) are common health hazards and resistance training programmes have been promising approaches in the quest for a reduction in the pain intensity of these professionals. Therefore, the aim of the current study was to investigate the [...] Read more.

Introduction: For dental professionals, musculoskeletal disorders (MSD) are common health hazards and resistance training programmes have been promising approaches in the quest for a reduction in the pain intensity of these professionals. Therefore, the aim of the current study was to investigate the effect of a trunk-oriented 10-week resistance training programme. Method: In total, the study was conducted with 17 dentists and dental assistants (3 m/14 f) over a course of 10 weeks, with workouts being performed 2 times a week using a 60 min intervention programme consisting of 11 resistance training exercises. The outcome values that were collected were the pain intensity (visual analogue scale (VAS) combined with a modified version of the Nordic Questionnaire), the MVIC and the rapid upper limb assessment (RULA) score (based on data from inertial motion units) during a standardised dental treatment protocol. Results: A significant reduction in pain intensity was found for each queried body region: the neck, upper back, lower back and the right and left shoulders. The maximum voluntary isometric contraction (MVIC) improved significantly in all outcome measures: flexion, extension, right and left lateral flexion and right and left rotation. Conclusions: A 10-week resistance training programme for dentists and dental assistants had significant effects on pain intensity reduction and the MVIC of the musculature of the trunk and is, therefore, suitable as a behavioural preventive measure against MSD in dental professionals. Full article

(This article belongs to the Special Issue Technology and Methods to Monitor Resistance Training: Applications in Health, Disease and Performance in Sport)

► Show Figures

Figure 1

42 pages, 6895 KiB

Open AccessReview

A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System

by Ruey-Kai Sheu and Mayuresh Sunil Pardeshi

Sensors 2022, 22(20), 8068; https://doi.org/10.3390/s22208068 - 21 Oct 2022

Cited by 16 | Viewed by 8699

Abstract

The emerging field of eXplainable AI (XAI) in the medical domain is considered to be of utmost importance. Meanwhile, incorporating explanations in the medical domain with respect to legal and ethical AI is necessary to understand detailed decisions, results, and current status of [...] Read more.

The emerging field of eXplainable AI (XAI) in the medical domain is considered to be of utmost importance. Meanwhile, incorporating explanations in the medical domain with respect to legal and ethical AI is necessary to understand detailed decisions, results, and current status of the patient’s conditions. Successively, we will be presenting a detailed survey for the medical XAI with the model enhancements, evaluation methods, significant overview of case studies with open box architecture, medical open datasets, and future improvements. Potential differences in AI and XAI methods are provided with the recent XAI methods stated as (i) local and global methods for preprocessing, (ii) knowledge base and distillation algorithms, and (iii) interpretable machine learning. XAI characteristics details with future healthcare explainability is included prominently, whereas the pre-requisite provides insights for the brainstorming sessions before beginning a medical XAI project. Practical case study determines the recent XAI progress leading to the advance developments within the medical field. Ultimately, this survey proposes critical ideas surrounding a user-in-the-loop approach, with an emphasis on human–machine collaboration, to better produce explainable solutions. The surrounding details of the XAI feedback system for human rating-based evaluation provides intelligible insights into a constructive method to produce human enforced explanation feedback. For a long time, XAI limitations of the ratings, scores and grading are present. Therefore, a novel XAI recommendation system and XAI scoring system are designed and approached from this work. Additionally, this paper encourages the importance of implementing explainable solutions into the high impact medical field. Full article

(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Sensors and Applications)

► Show Figures

Figure 1

33 pages, 12814 KiB

Open AccessArticle

Development of an Online Adaptive Parameter Tuning vSLAM Algorithm for UAVs in GPS-Denied Environments

by Chieh-Li Chen, Rong He and Chao-Chung Peng

Sensors 2022, 22(20), 8067; https://doi.org/10.3390/s22208067 - 21 Oct 2022

Cited by 3 | Viewed by 1667

Abstract

In recent years, unmanned aerial vehicles (UAVs) have been applied in many fields owing to their mature flight control technology and easy-to-operate characteristics. No doubt, these UAV-related applications rely heavily on location information provided by the positioning system. Most UAVs nowadays use a [...] Read more.

In recent years, unmanned aerial vehicles (UAVs) have been applied in many fields owing to their mature flight control technology and easy-to-operate characteristics. No doubt, these UAV-related applications rely heavily on location information provided by the positioning system. Most UAVs nowadays use a global navigation satellite system (GNSS) to obtain location information. However, this outside-in 3rd party positioning system is particularly susceptible to environmental interference and cannot be used in indoor environments, which limits the application diversity of UAVs. To deal with this problem, in this paper, a stereo-based visual simultaneous localization and mapping technology (vSLAM) is applied. The presented vSLAM algorithm fuses onboard inertial measurement unit (IMU) information to further solve the navigation problem in an unknown environment without the use of a GNSS signal and provides reliable localization information. The overall visual positioning system is based on the stereo parallel tracking and mapping architecture (S-PTAM). However, experiments found that the feature-matching threshold has a significant impact on positioning accuracy. Selection of the threshold is based on the Hamming distance without any physical meaning, which makes the threshold quite difficult to set manually. Therefore, this work develops an online adaptive matching threshold according to the keyframe poses. Experiments show that the developed adaptive matching threshold improves positioning accuracy. Since the attitude calculation of the IMU is carried out based on the Mahony complementary filter, the difference between the measured acceleration and the gravity is used as the metric to online tune the gain value dynamically, which can improve the accuracy of attitude estimation under aggressive motions. Moreover, a static state detection algorithm based on the moving window method and measured acceleration is proposed as well to accurately calculate the conversion mechanism between the vSLAM system and the IMU information; this initialization mechanism can help IMU provide a better initial guess for the bundle adjustment algorithm (BA) in the tracking thread. Finally, a performance evaluation of the proposed algorithm is conducted by the popular EuRoC dataset. All the experimental results show that the developed online adaptive parameter tuning algorithm can effectively improve the vSLAM accuracy and robustness. Full article

(This article belongs to the Special Issue Simultaneous Localization and Mapping (SLAM) for Mobile Robot Navigation)

► Show Figures

Graphical abstract

21 pages, 5598 KiB

Open AccessArticle

Kids’ Emotion Recognition Using Various Deep-Learning Models with Explainable AI

by Manish Rathod, Chirag Dalvi, Kulveen Kaur, Shruti Patil, Shilpa Gite, Pooja Kamat, Ketan Kotecha, Ajith Abraham and Lubna Abdelkareim Gabralla

Sensors 2022, 22(20), 8066; https://doi.org/10.3390/s22208066 - 21 Oct 2022

Cited by 10 | Viewed by 4818

Abstract

Human ideas and sentiments are mirrored in facial expressions. They give the spectator a plethora of social cues, such as the viewer’s focus of attention, intention, motivation, and mood, which can help develop better interactive solutions in online platforms. This could be helpful [...] Read more.

Human ideas and sentiments are mirrored in facial expressions. They give the spectator a plethora of social cues, such as the viewer’s focus of attention, intention, motivation, and mood, which can help develop better interactive solutions in online platforms. This could be helpful for children while teaching them, which could help in cultivating a better interactive connect between teachers and students, since there is an increasing trend toward the online education platform due to the COVID-19 pandemic. To solve this, the authors proposed kids’ emotion recognition based on visual cues in this research with a justified reasoning model of explainable AI. The authors used two datasets to work on this problem; the first is the LIRIS Children Spontaneous Facial Expression Video Database, and the second is an author-created novel dataset of emotions displayed by children aged 7 to 10. The authors identified that the LIRIS dataset has achieved only 75% accuracy, and no study has worked further on this dataset in which the authors have achieved the highest accuracy of 89.31% and, in the authors’ dataset, an accuracy of 90.98%. The authors also realized that the face construction of children and adults is different, and the way children show emotions is very different and does not always follow the same way of facial expression for a specific emotion as compared with adults. Hence, the authors used 3D 468 landmark points and created two separate versions of the dataset from the original selected datasets, which are LIRIS-Mesh and Authors-Mesh. In total, all four types of datasets were used, namely LIRIS, the authors’ dataset, LIRIS-Mesh, and Authors-Mesh, and a comparative analysis was performed by using seven different CNN models. The authors not only compared all dataset types used on different CNN models but also explained for every type of CNN used on every specific dataset type how test images are perceived by the deep-learning models by using explainable artificial intelligence (XAI), which helps in localizing features contributing to particular emotions. The authors used three methods of XAI, namely Grad-CAM, Grad-CAM++, and SoftGrad, which help users further establish the appropriate reason for emotion detection by knowing the contribution of its features in it. Full article

(This article belongs to the Special Issue Deep Learning Methods for Human Activity Recognition and Emotion Detection)

► Show Figures

Figure 1

20 pages, 9493 KiB

Open AccessArticle

A Metamaterial Inspired AMC Backed Dual Band Antenna for ISM and RFID Applications

by Md. Najumunnisa, Ambadapudi Srinivasa Chandrasekhara Sastry, Boddapati Taraka Phani Madhav, Sudipta Das, Niamat Hussain, Syed Samser Ali and Muhammad Aslam

Sensors 2022, 22(20), 8065; https://doi.org/10.3390/s22208065 - 21 Oct 2022

Cited by 12 | Viewed by 2262

Abstract

This work presents the design and fabrication of a metamaterial-based stimulated dual band antenna on FR4 material (dielectric constant 4.3) to operate in Industrial, Scientific and Medical (ISM) and Radio-frequency Identification (RFID) applications. The antenna model had an overall dimension of 70 × [...] Read more.

This work presents the design and fabrication of a metamaterial-based stimulated dual band antenna on FR4 material (dielectric constant 4.3) to operate in Industrial, Scientific and Medical (ISM) and Radio-frequency Identification (RFID) applications. The antenna model had an overall dimension of 70 × 31 × 1.6 mm³ with etched T-slots and L-slots for dual band resonance. The main objective of this work was to enhance the gain performance characteristic at the selected dual band frequencies of 0.915 GHz and 2.45 GHz. Initially, it achieved a narrow bandwidth of 0.018 GHz with a gain of 1.53 dBi at a lower frequency, and 0.13 GHz of bandwidth featuring 4.49 dBi of gain at a higher frequency. The antenna provided an impedance bandwidth of 2% (0.905–0.923 GHz) and 5% (2.382–2.516 GHz) at two resonating frequencies. The antenna was integrated with a designed novel AMC structure to enhance the gain in CST Microwave Studio software with the finite integration method. The characteristic features of the AMC unit cell were observed at 0.915 GHz and 2.45 GHz frequencies and after antenna integration, the final prototype achieved a gain of 2.87 dBi at 0.915 GHz and 6.8 dBi at 2.45 GHz frequencies. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

18 pages, 4262 KiB

Open AccessArticle

Dingo Optimization Based Cluster Based Routing in Internet of Things

by Kalavagunta Aravind and Praveen Kumar Reddy Maddikunta

Sensors 2022, 22(20), 8064; https://doi.org/10.3390/s22208064 - 21 Oct 2022

Cited by 8 | Viewed by 1507

Abstract

The Wireless Sensor Network (WSN) is a collection of distinct, geographically distributed, Internet-connected sensors, which is capable of processing, analyzing, storing, and exchanging collected information. However, the Internet of Things (IoT) devices in the network are equipped with limited resources and minimal computing [...] Read more.

The Wireless Sensor Network (WSN) is a collection of distinct, geographically distributed, Internet-connected sensors, which is capable of processing, analyzing, storing, and exchanging collected information. However, the Internet of Things (IoT) devices in the network are equipped with limited resources and minimal computing capability, resulting in energy conservation problems. Although clustering is an efficient method for energy saving in network nodes, the existing clustering algorithms are not effective due to the short lifespan of a network, an unbalanced load among the network nodes, and increased end-to-end delays. Hence, this paper proposes a novel cluster-based approach for IoT using a Self-Adaptive Dingo Optimizer with Brownian Motion (SDO-BM) technique to choose the optimal cluster head (CH) considering the various constraints such as energy, distance, delay, overhead, trust, Quality of Service (QoS), and security (high risk, low risk, and medium risk). If the chosen optimal CH is defective, then fault tolerance and energy hole mitigation techniques are used to stabilize the network. Eventually, analysis is done to ensure the progression of the SADO-BM model. The proposed model provides optimal results compared to existing models. Full article

(This article belongs to the Special Issue Advanced Technologies in Sensor Networks and Internet of Things)

► Show Figures

Figure 1

17 pages, 1865 KiB

Open AccessArticle

Efficient Top-K Identical Frequent Itemsets Mining without Support Threshold Parameter from Transactional Datasets Produced by IoT-Based Smart Shopping Carts

by Saif Ur Rehman, Noha Alnazzawi, Jawad Ashraf, Javed Iqbal and Shafiullah Khan

Sensors 2022, 22(20), 8063; https://doi.org/10.3390/s22208063 - 21 Oct 2022

Cited by 4 | Viewed by 1691

Abstract

Internet of Things (IoT)-backed smart shopping carts are generating an extensive amount of data in shopping markets around the world. This data can be cleaned and utilized for setting business goals and strategies. Artificial intelligence (AI) methods are used to efficiently extract meaningful [...] Read more.

Internet of Things (IoT)-backed smart shopping carts are generating an extensive amount of data in shopping markets around the world. This data can be cleaned and utilized for setting business goals and strategies. Artificial intelligence (AI) methods are used to efficiently extract meaningful patterns or insights from such huge amounts of data or big data. One such technique is Association Rule Mining (ARM) which is used to extract strategic information from the data. The crucial step in ARM is Frequent Itemsets Mining (FIM) followed by association rule generation. The FIM process starts by tuning the support threshold parameter from the user to produce the number of required frequent patterns. To perform the FIM process, the user applies hit and trial methods to rerun the aforesaid routine in order to receive the required number of patterns. The research community has shifted its focus towards the development of top-K most frequent patterns not using the support threshold parameter tuned by the user. Top-K most frequent patterns mining is considered a harder task than user-tuned support-threshold-based FIM. One of the reasons why top-K most frequent patterns mining techniques are computationally intensive is the fact that they produce a large number of candidate itemsets. These methods also do not use any explicit pruning mechanism apart from the internally auto-maintained support threshold parameter. Therefore, we propose an efficient TKIFIs Miner algorithm that uses depth-first search strategy for top-K identical frequent patterns mining. The TKIFIs Miner uses specialized one- and two-itemsets-based pruning techniques for topmost patterns mining. Comparative analysis is performed on special benchmark datasets, for example, Retail with 16,469 items, T40I10D100K and T10I4D100K with 1000 items each, etc. The evaluation results have proven that the TKIFIs Miner is at the top of the line, compared to recently available topmost patterns mining methods not using the support threshold parameter. Full article

(This article belongs to the Special Issue Artificial Intelligence and Advances in Smart IoT)

► Show Figures

Figure 1

21 pages, 2238 KiB

Open AccessArticle

Soil Moisture Sensor Information Enhanced by Statistical Methods in a Reclaimed Water Irrigation Framework

by Anthony Giorgio, Nicoletta Del Buono, Marco Berardi, Michele Vurro and Gaetano Alessandro Vivaldi

Sensors 2022, 22(20), 8062; https://doi.org/10.3390/s22208062 - 21 Oct 2022

Cited by 2 | Viewed by 1408

Abstract

Time series modeling and forecasting play important roles in many practical fields. A good understanding of soil water content and salinity variability and the proper prediction of variations in these variables in response to changes in climate conditions are essential to properly plan [...] Read more.

Time series modeling and forecasting play important roles in many practical fields. A good understanding of soil water content and salinity variability and the proper prediction of variations in these variables in response to changes in climate conditions are essential to properly plan water resources and appropriately manage irrigation and fertilization tasks. This paper provides a 48-h forecast of soil water content and salinity in the peculiar context of irrigation with reclaimed water in semi-arid environments. The forecasting was performed based on (i) soil water content and salinity data from 50 cm beneath the soil surface with a time resolution of 15 min, (ii) hourly atmospheric data and (iii) daily irrigation amounts. Exploratory data analysis and data pre-processing phases were performed and then statistical models were constructed for time series forecasting based on the set of available data. The obtained prediction models showed good forecasting accuracy and good interpretability of the results. Full article

(This article belongs to the Special Issue Sensors and Data Analysis Applied in Environmental Monitoring)

► Show Figures

Figure 1

14 pages, 514 KiB

Open AccessArticle

Altitude Optimization and Task Allocation of UAV-Assisted MEC Communication System

by Shuqi Huang, Jun Zhang and Yi Wu

Sensors 2022, 22(20), 8061; https://doi.org/10.3390/s22208061 - 21 Oct 2022

Cited by 5 | Viewed by 1477

Abstract

Unmanned aerial vehicles (UAVs) are widely used in wireless communication systems due to their flexible mobility and high maneuverability. The combination of UAVs and mobile edge computing (MEC) is regarded as a promising technology to provide high-quality computing services for latency-sensitive applications. In [...] Read more.

Unmanned aerial vehicles (UAVs) are widely used in wireless communication systems due to their flexible mobility and high maneuverability. The combination of UAVs and mobile edge computing (MEC) is regarded as a promising technology to provide high-quality computing services for latency-sensitive applications. In this paper, a novel UAV-assisted MEC uplink maritime communication system is proposed, where an MEC server is equipped on UAV to provide flexible assistance to maritime user. In particular, the task of user can be divided into two parts: one portion is offloaded to UAV and the remaining portion is offloaded to onshore base station for computing. We formulate an optimization problem to minimize the total system latency by designing the optimal flying altitude of UAV and the optimal task allocation ratio. We derive a semi closed-form expression of the optimal flying altitude of UAV and a closed-form expression of the optimal task allocation ratio. Simulation results demonstrate the precision of the theoretical analyses and show some interesting insights. Full article

(This article belongs to the Special Issue Enabling Technologies for 6G Maritime Communications)

► Show Figures

Figure 1

25 pages, 1607 KiB

Open AccessArticle

Matched Filter Interpretation of CNN Classifiers with Application to HAR

by Mohammed M. Farag

Sensors 2022, 22(20), 8060; https://doi.org/10.3390/s22208060 - 21 Oct 2022

Cited by 5 | Viewed by 1984

Abstract

Time series classification is an active research topic due to its wide range of applications and the proliferation of sensory data. Convolutional neural networks (CNNs) are ubiquitous in modern machine learning (ML) models. In this work, we present a matched filter (MF) interpretation [...] Read more.

Time series classification is an active research topic due to its wide range of applications and the proliferation of sensory data. Convolutional neural networks (CNNs) are ubiquitous in modern machine learning (ML) models. In this work, we present a matched filter (MF) interpretation of CNN classifiers accompanied by an experimental proof of concept using a carefully developed synthetic dataset. We exploit this interpretation to develop an MF CNN model for time series classification comprising a stack of a Conv1D layer followed by a GlobalMaxPooling layer acting as a typical MF for automated feature extraction and a fully connected layer with softmax activation for computing class probabilities. The presented interpretation enables developing superlight highly accurate classifier models that meet the tight requirements of edge inference. Edge inference is emerging research that addresses the latency, availability, privacy, and connectivity concerns of the commonly deployed cloud inference. The MF-based CNN model has been applied to the sensor-based human activity recognition (HAR) problem due to its significant importance in a broad range of applications. The UCI-HAR, WISDM-AR, and MotionSense datasets are used for model training and testing. The proposed classifier is tested and benchmarked on an android smartphone with average accuracy and

F 1

scores of 98% and 97%, respectively, which outperforms state-of-the-art HAR methods in terms of classification accuracy and run-time performance. The proposed model size is less than 150 KB, and the average inference time is less than 1 ms. The presented interpretation helps develop a better understanding of CNN operation and decision mechanisms. The proposed model is distinguished from related work by jointly featuring interpretability, high accuracy, and low computational cost, enabling its ready deployment on a wide set of mobile devices for a broad range of applications. Full article

(This article belongs to the Special Issue Human Activity Recognition Using Sensors and Machine Learning)

► Show Figures

Figure 1

20 pages, 4738 KiB

Open AccessArticle

Electrical Disturbances in Terms of Methods to Reduce False Activation of Aerial Fire Protection Systems

by Andrzej Żyluk, Mariusz Zieja, Andrzej Szelmanowski, Justyna Tomaszewska, Magdalena Perlińska and Krzysztof Głyda

Sensors 2022, 22(20), 8059; https://doi.org/10.3390/s22208059 - 21 Oct 2022

Cited by 2 | Viewed by 1523

Abstract

The paper presents an analysis of false triggers of fire protection systems installed on aircraft. They not only cause task interruption but also have a direct impact on flight safety, forcing the crew to land in a risky area. Simulation models of electronic [...] Read more.

The paper presents an analysis of false triggers of fire protection systems installed on aircraft. They not only cause task interruption but also have a direct impact on flight safety, forcing the crew to land in a risky area. Simulation models of electronic actuators were developed to determine the conditions under which false alarms occur. Testing of the simulation models was carried out in the computational package Matlab-Simulink and Circum-Maker for different electrical disturbance generation conditions. The simulation of overvoltage, voltage drops and voltage decays in the on-board electrical network supplying the fire protection system, occurring during the start-up of aircraft engines and during the switching on and off of on-board high-power devices, was studied. The conducted studies have practical applications since the simulation results are an important element for planning experimental tests of the SSP-FK-BI executive blocks under electrical disturbance conditions. Based on the simulation and experimental studies, the conditions causing false tripping of the fire protection system and the parameters for selected disturbance factors have been determined. Full article

(This article belongs to the Special Issue Monitoring System for Aircraft, Vehicle and Transport Systems)

► Show Figures

Figure 1

4 pages, 174 KiB

Open AccessEditorial

Sensor Data Fusion Based on Deep Learning for Computer Vision Applications and Medical Applications

by Rizwan Ali Naqvi, Muhammad Arsalan, Talha Qaiser, Tariq Mahmood Khan and Imran Razzak

Sensors 2022, 22(20), 8058; https://doi.org/10.3390/s22208058 - 21 Oct 2022

Cited by 4 | Viewed by 1495

Abstract

Sensor fusion is the process of merging data from many sources, such as radar, lidar and camera sensors, to provide less uncertain information compared to the information collected from single source [...] Full article

(This article belongs to the Special Issue Sensor Data Fusion Based on Deep Learning for Computer Vision and Medical Applications)

22 pages, 996 KiB

Open AccessArticle

Performance Improvement of a Vehicle Equipped with Active Aerodynamic Surfaces Using Anti-Jerk Preview Control Strategy

by Ejaz Ahmad and Iljoong Youn

Sensors 2022, 22(20), 8057; https://doi.org/10.3390/s22208057 - 21 Oct 2022

Cited by 1 | Viewed by 1655

Abstract

This paper presents a formulation of a preview optimal control strategy for a half-car model equipped with active aerodynamic surfaces. The designed control strategy consists of two parts: a feed-forward controller to deal with the future road disturbances and a feedback controller to [...] Read more.

This paper presents a formulation of a preview optimal control strategy for a half-car model equipped with active aerodynamic surfaces. The designed control strategy consists of two parts: a feed-forward controller to deal with the future road disturbances and a feedback controller to deal with tracking error. An anti-jerk functionality is employed in the design of preview control strategy that can reliably reduce the jerk of control inputs to improve the performance of active aerodynamic surfaces and reduce vehicle body jerk to enhance the ride comfort without degrading road holding capability. The proposed control scheme determines proactive control action against oncoming potential road disturbances to mitigate the effect of deterministically known road disturbances. The performance of proposed anti-jerk optimal control strategy is compared with that of optimal control without considering jerk. Simulation results considering frequency and time domain characteristics are carried out using MATLAB to demonstrate the effectiveness of the proposed scheme. The frequency domain characteristics are discussed only for the roll inputs, while time domain characteristics are discussed for the corresponding ground velocity inputs of bump and asphalt road, respectively. The results show that using anti-jerk optimal preview control strategy improves the performance of vehicle dynamics by reducing jerk of aerodynamic surfaces and vehicle body jerk simultaneously. Full article

(This article belongs to the Special Issue Sensors and Systems for Automotive and Road Safety)

► Show Figures

Figure 1

16 pages, 5455 KiB

Open AccessArticle

Using Aerial Thermal Imagery to Evaluate Water Status in Vitis vinifera cv. Loureiro

by Cláudio Araújo-Paredes, Fernando Portela, Susana Mendes and M. Isabel Valín

Sensors 2022, 22(20), 8056; https://doi.org/10.3390/s22208056 - 21 Oct 2022

Cited by 7 | Viewed by 1955

Abstract

The crop water stress index (CWSI) is a widely used analytical tool based on portable thermography. This method can be useful in replacing the traditional stem water potential method obtained with a Scholander chamber (PMS Model 600) because the latter is not feasible [...] Read more.

The crop water stress index (CWSI) is a widely used analytical tool based on portable thermography. This method can be useful in replacing the traditional stem water potential method obtained with a Scholander chamber (PMS Model 600) because the latter is not feasible for large-scale studies due to the time involved and the fact that it is invasive and can cause damage to the plant. The present work had three objectives: (i) to understand if CWSI estimated using an aerial sensor can estimate the water status of the plant; (ii) to compare CWSI from aerial-thermographic and portable thermal cameras with stem water potential; (iii) to estimate the capacity of an unmanned aerial vehicle (UAV) to calculate and spatialize CWSI. Monitoring of CWSI (CWSI_P) using a portable device was performed directly in the canopy, by measuring reference temperatures (T_dry, T_wet, and canopy temperature (T_c)). Aerial CWSI calculation was performed using two models: (i) a simplified CWSI model (CWSI_S), where the T_dry and T_wet were estimated as the average of 1% of the extreme temperature, and (ii) an air temperature model (CWSI_Tair) where air temperatures (T_air + 7 °C) were recorded as T_dry and in the T_wet, considering the average of the lowest 33% of histogram values. In these two models, the T_c value corresponded to the temperature value in each pixel of the aerial thermal image. The results show that it was possible to estimate CWSI by calculating canopy temperatures and spatializing CWSI using aerial thermography. Of the two models, it was found that for CWSI_Tair, CWSI_S (R² = 0.55) evaluated crop water stress better than stem water potential. The CWSI_S had good correlation compared with the portable sensor (R² = 0.58), and its application in field measurements is possible. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

22 pages, 33035 KiB

Open AccessArticle

A Decision-Making Strategy for Car Following Based on Naturalist Driving Data via Deep Reinforcement Learning

by Wenli Li, Yousong Zhang, Xiaohui Shi and Fanke Qiu

Sensors 2022, 22(20), 8055; https://doi.org/10.3390/s22208055 - 21 Oct 2022

Cited by 4 | Viewed by 1641

Abstract

To improve the satisfaction and acceptance of automatic driving, we propose a deep reinforcement learning (DRL)-based autonomous car-following (CF) decision-making strategy using naturalist driving data (NDD). This study examines the traits of CF behavior using 1341 pairs of CF events taken from the [...] Read more.

To improve the satisfaction and acceptance of automatic driving, we propose a deep reinforcement learning (DRL)-based autonomous car-following (CF) decision-making strategy using naturalist driving data (NDD). This study examines the traits of CF behavior using 1341 pairs of CF events taken from the Next Generation Simulation (NGSIM) data. Furthermore, in order to improve the random exploration of the agent’s action, the dynamic characteristics of the speed-acceleration distribution are established in accordance with NDD. The action’s varying constraints are achieved via a normal distribution 3σ boundary point-to-fit curve. A multiobjective reward function is designed considering safety, efficiency, and comfort, according to the time headway (THW) probability density distribution. The introduction of a penalty reward in mechanical energy allows the agent to internalize negative experiences. Next, a model of agent-environment interaction for CF decision-making control is built using the deep deterministic policy gradient (DDPG) method, which can explore complicated environments. Finally, extensive simulation experiments validate the effectiveness and accuracy of our proposal, and the driving strategy is learned through real-world driving data, which is better than human data. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

14 pages, 551 KiB

Open AccessCommunication

A Novel Expectation-Maximization-Based Blind Receiver for Low-Complexity Uplink STLC-NOMA Systems

by Ki-Hun Lee and Bang Chul Jung

Sensors 2022, 22(20), 8054; https://doi.org/10.3390/s22208054 - 21 Oct 2022

Viewed by 1385

Abstract

In this paper, we revisit a two-user space-time line coded uplink non-orthogonal multiple access (STLC-NOMA) system for Internet-of-things (IoT) networks and propose a novel low-complexity STLC-NOMA system. The basic idea is that both IoT devices (stations: STAs) employ amplitude-shift keying (ASK) modulators and [...] Read more.

In this paper, we revisit a two-user space-time line coded uplink non-orthogonal multiple access (STLC-NOMA) system for Internet-of-things (IoT) networks and propose a novel low-complexity STLC-NOMA system. The basic idea is that both IoT devices (stations: STAs) employ amplitude-shift keying (ASK) modulators and align their modulated symbols to in-phase and quadrature axes, respectively, before the STLC encoding. The phase distortion caused by wireless channels becomes compensated at the receiver side with the STLC, and thus each STA’s signals are still aligned on their axes at the access point (AP) in the proposed uplink STLC-NOMA system. Then, the AP can decode the signals transmitted from STAs via a single-user maximum-likelihood (ML) detector with low-complexity, while the conventional uplink STLC-NOMA system exploits a multi-user joint ML detector with relatively high-complexity. We mathematically analyze the exact BER performance of the proposed uplink STLC-NOMA system. Furthermore, we propose a novel expectation-maximization (EM)-based blind energy estimation (BEE) algorithm to jointly estimate both transmit power and effective channel gain of each STA without the help of pilot signals at the AP. Somewhat interestingly, the proposed BEE algorithm works well even in short-packet transmission scenarios. It is worth noting that the proposed uplink STLC-NOMA architecture outperforms the conventional STLC-NOMA technique in terms of bit-error-rate (BER), especially with high-order modulation schemes, even though it requires lower computation complexity than the conventional technique at the receiver. Full article

(This article belongs to the Special Issue Advanced Antenna Techniques for IoT and 5G Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 22, Issue 20 (October-2 2022) – 389 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI