Sensory Networks Research Articles

Deviations in Traffic Flow Characteristics Caused by the Impact of the Covid-19 Pandemic

Abstract Changes in traffic flows in cities occur over time due to several circumstances. Regulation and proper coordination of transport is conditioned by sufficient input data. The sensor network ranks among the resources that provide an overview of operation in road traffic. The city of Žilina was chosen to support the building of a sensory network with applied research of available data with subsequent use in practice. The sensor network offers a database for the subsequent evaluation of inputs from several points of view. The COVID-19 pandemic was associated with restrictions and many block measures that changed the dynamics of traffic journeys. The aim of this paper was to evaluate traffic flow deviations in connection with the continuation of the third wave of the COVID-19 pandemic.

The Evolution and Future Development of Attention Networks.

The goal of this paper is to examine how the development of attention networks has left many important issues unsolved and to propose possible directions for solving them by combining human and animal studies. The paper starts with evidence from citation mapping that indicates attention has played a central role in integrating cognitive and neural studies into Cognitive Neuroscience. The integration of the fields depends in part upon similarities and differences in performance over a wide variety of animals. In the case of exogenous orienting of attention primates, rodents and humans are quite similar, but this is not so with executive control. In humans, attention networks continue to develop at different rates during infancy and childhood and into adulthood. From age four on, the Attention Network Test (ANT) allows measurement of individual differences in the alerting, orienting and executive networks. Overt and covert orienting do overlap in their anatomy, but there is evidence of some degree of functional independence at the cellular level. The attention networks frequently work together with sensory, memory and other networks. Integration of animal and human studies may be advanced by examining common genes involved in individual attention networks or their integration with other brain networks. Attention networks involve widely scattered computation nodes in different brain areas, both cortical and subcortical. Future studies need to attend to the white matter that connects them and the direction of information flow during task performance.

Nociceptor activity induces nonionotropic NMDA receptor signaling to enable spinal reconsolidation and reverse pathological pain.

Chronic, pathological pain is a highly debilitating condition that can arise and be maintained through central sensitization. Central sensitization shares mechanistic and phenotypic parallels with memory formation. In a sensory model of memory reconsolidation, plastic changes underlying pain hypersensitivity can be dynamically regulated and reversed following the reactivation of sensitized sensory pathways. However, the mechanisms by which synaptic reactivation induces destabilization of the spinal "pain engram" are unclear. We identified nonionotropic N-methyl-d-aspartate receptor (NI-NMDAR) signaling as necessary and sufficient for the reactive destabilization of dorsal horn long-term potentiation and the reversal of mechanical sensitization associated with central sensitization. NI-NMDAR signaling engaged directly or through the reactivation of sensitized sensory networks was associated with the degradation of excitatory postsynaptic proteins. Our findings identify NI-NMDAR signaling as a putative synaptic mechanism by which engrams are destabilized in reconsolidation and as a potential means of treating underlying causes of chronic pain.

Toward a more informative representation of the fetal-neonatal brain connectome using variational autoencoder.

Recent advances in functional magnetic resonance imaging (fMRI) have helped elucidate previously inaccessible trajectories of early-life prenatal and neonatal brain development. To date, the interpretation of fetal-neonatal fMRI data has relied on linear analytic models, akin to adult neuroimaging data. However, unlike the adult brain, the fetal and newborn brain develops extraordinarily rapidly, far outpacing any other brain development period across the life span. Consequently, conventional linear computational models may not adequately capture these accelerated and complex neurodevelopmental trajectories during this critical period of brain development along the prenatal-neonatal continuum. To obtain a nuanced understanding of fetal-neonatal brain development, including nonlinear growth, for the first time, we developed quantitative, systems-wide representations of brain activity in a large sample (>500) of fetuses, preterm, and full-term neonates using an unsupervised deep generative model called variational autoencoder (VAE), a model previously shown to be superior to linear models in representing complex resting-state data in healthy adults. Here, we demonstrated that nonlinear brain features, that is, latent variables, derived with the VAE pretrained on rsfMRI of human adults, carried important individual neural signatures, leading to improved representation of prenatal-neonatal brain maturational patterns and more accurate and stable age prediction in the neonate cohort compared to linear models. Using the VAE decoder, we also revealed distinct functional brain networks spanning the sensory and default mode networks. Using the VAE, we are able to reliably capture and quantify complex, nonlinear fetal-neonatal functional neural connectivity. This will lay the critical foundation for detailed mapping of healthy and aberrant functional brain signatures that have their origins in fetal life.

Resting-state functional connectivity in deaf and hearing individuals and its link to executive processing

Sensory experience shapes brain structure and function, and it is likely to influence the organisation of functional networks of the brain, including those involved in cognitive processing. Here we investigated the influence of early deafness on the organisation of resting-state networks of the brain and its relation to executive processing. We compared resting-state connectivity between deaf and hearing individuals across 18 functional networks and 400 ROIs. Our results showed significant group differences in connectivity between seeds of the auditory network and most large-scale networks of the brain, in particular the somatomotor and salience/ventral attention networks. When we investigated group differences in resting-state fMRI and their link to behavioural performance in executive function tasks (working memory, inhibition and switching), differences between groups were found in the connectivity of association networks of the brain, such as the salience/ventral attention and default-mode networks. These findings indicate that sensory experience influences not only the organisation of sensory networks, but that it also has a measurable impact on the organisation of association networks supporting cognitive processing. Overall, our findings suggest that different developmental pathways and functional organisation can support executive processing in the adult brain.

A Physics-Aware MIQP Approach to Harmonic State Estimation in Low-Observable Power Distribution Systems Using Harmonic Phasor Measurement Units

In this paper, a novel physics-aware harmonic state estimation (HSE) method is developed for power distribution systems with low-observability. The only available measurements are the harmonic synchrophasors from a small number of Harmonic Phasor Measurement Units (H-PMUs) on a power distribution feeder. The proposed HSE method provides a novel and practical application of H-PMUs, which are an emerging class of smart grid sensors, in order to address an important and challenging problem in power distribution system monitoring. More importantly, the proposed HSE method can address the highly challenging scenario, in which, not only the network has a low-observability condition, but also the number and the location(s) of the harmonic sources are unknown. The proposed HSE method captures physics-based sparsity pattern in the analysis of harmonic phasors, and then it incorporates such sparsity pattern in the formulation of a novel mixed-integer quadratic programming (MIQP) optimization which can be solved by standard solvers. The method that is proposed in this paper to address low-observability is innovative and it is specific to HSE. It does not have any similar counterpart in the literature, whether for harmonic state estimation for in ordinary (i.e., not harmonic) distribution system state estimation. The effectiveness of the proposed method is tested and confirmed in multiple case studies and compared with the existing methods.

The Role of Executive Functions in Fluent Reading: Lessons from Reading Acquisition and Remediation

ABSTRACTThis review paper aims to define the involvement of Executive Functions (EF) in reading fluency in typically developing children and those with reading difficulties (RD)/dyslexia using neuroimaging and cognitive measurements. The data presented in this review demonstrate how training reading fluency with EF principles improved reading fluency and associated neural circuits. The possible mechanism for this fluency improvement points to the utilization of EF during reading remediation and its relation to the synchronization between the auditory and visual modalities in RD. Overall, the studies reviewed in the current paper suggest that reading fluency is achieved through a better synchronization of EF‐brain regions with sensory networks, which are linked to decreased neural noise. These results support embedding EF principles in reading training and point to the need to include the fluency component in the Simple View of Reading model and open up possible opportunities to improve reading in children.

Individualized Real-Time fMRI Neuromodulation for the Alleviation of Cranial Nerve IX and XII Neuropathy (S38.004)

<h3>Objective:</h3> The goal is to alleviate lower cranial neuropathy following radiation (head and neck cancer treatment) for which no treatment is available. Current pharmacotherapeutics (steroids and opioids) cannot be tolerated, due to their side-effects and the drug-drug interactions. <h3>Background:</h3> The Papageorgiou lab has developed an individualized real-time fMRI closed-loop-neuromodulation (iRTfMRI-cNMT) to upregulate sensorimotor brain networks that regulate tongue motor and sensory control (TMSC). We elucidate the spatiotemporal mechanisms involved in the brain’s modularity when targeting sensorimotor networks. <h3>Design/Methods:</h3> Participants (n=30) underwent a two-day-study, consisting of iRTfMRI-cNMT and control-No-cNMT conditions. We decoded the cortical patterns generated by TMSC, interleaved with periods of tongue-rest (baseline) and swallow. Our innovation is the neuromodulation of the activity’s magnitude and extent in individualized networks. We quantify the BOLD magnitude for each network, using the area under the curve (AUC), variance, and dynamic causal modeling. <h3>Results:</h3> The mechanisms associated with <b>sensorimotor</b> iRTfMRI-cNMT-induced modulation are statistically significant: 1. 45% increase in the BOLD’s magnitude AUC; 2. 14% decrease in the BOLD’s intensity variance; and 3. 20% increase in the networks’ spatial expansion. We elucidated the dynamic brain states during TSMC: 1. a dominant state, characterized by TMSC in 95% of iRTfMRI-cNMT trials (76% of control trials); and 2. a non-dominant state identified as swallowing in 5% of cNMT trials (24% of control trials). The dominant state induced by cNMT was driven by: 1. Within (60%) motor (M1, motor cerebellum, basal ganglia) areas and motor to sensory (54%) networks; and 2. Within (47%) sensory (intraparietal lobule, insula, claustrum, sensory cerebellum, cingulate) areas and sensory to motor (52%) networks. iRTfMRI-cNMT increased consistency in the decoded networks’ spatial extents compared to control (94.3% vs. 89.6%, p&lt;0.001). <h3>Conclusions:</h3> These findings show that modularity of the individualized networks via iRTfMRI-cNMT is a treatment intervention that can be used to treat neuropathic pain, but also other neurologic disorders. <b>Disclosure:</b> Mr. Allam has nothing to disclose. Dr. Froudarakis has nothing to disclose. The institution of Dr. Papageorgiou has received research support from McNair Foundation. The institution of Dr. Papageorgiou has received research support from TIRR - Mission Connect. The institution of Dr. Papageorgiou has received research support from McNair Medical Institute. The institution of Dr. Papageorgiou has received research support from Center for Alzheimer’s and Neurodegenerative Disease. The institution of Dr. Papageorgiou has received research support from Naman Basic Science Faculty Award .

A Digital-Analog Bimodal Memristor Based on CsPbBr3 for Tactile Sensory Neuromorphic Computing.

Memristor with digital and analog bipolar bimodal resistive switching offers a promising opportunity for the information-processing component. However, it still remains a huge challenge that the memristor enables bimodal digital and analog types and fabrication of artificial sensory neural network system. Here, a proposed CsPbBr3 -based memristor demonstrates a high ON/OFF ratio (>103 ), long retention (>104 s), stable endurance (100 cycles), and multilevel resistance memory, which acts as an artificial synapse to realize fundamental biological synaptic functions and neuromorphic computing based on controllable resistance modulation. Moreover, a 5× 5 spinosum-structured piezoresistive sensor array (sensitivity of 22.4 kPa-1 , durability of 1.5×104 cycles, and fast response time of 2.43ms) is constructed as a tactile sensory receptor to transform mechanical stimuli into electrical signals, which can be further processed by the CsPbBr3 -based memristor with synaptic plasticity. More importantly, this artificial sensory neural network system combined the artificial synapse with 5×5 tactile sensing array based on piezoresistive sensors can recognize the handwritten patterns of different letters with high accuracy of 94.44% under assistance of supervised learning. Consequently, the digital-analog bimodal memristor would demonstrate potential application in human-machine interaction, prosthetics, and artificial intelligence.

Theoretical upper bound of multiplexing in biological sensory receptors

Biological sensory receptors provide excellent examples of microscopic scale information transduction amidst stochastic noise. We argue that stochasticity is not always a hindrance to sensing. Instead, it could allow a single stochastic sensor to perform multiplexing: simultaneously transducing multiple types of environmental information to the downstream sensory network. Through a Langevin dynamics simulation of a ligand-receptor sensor in a bath of ligands, we demonstrate that a binary-state receptor can simultaneously encode multiple independent environmental variables, such as ligand concentration and the speed of media flow. We develop a general theory of stochastic sensory multiplexing and suggest two theoretical upper bounds. Furthermore, we conjecture that randomly generated sensors typically saturate the tighter upper bound. The theoretical framework developed in this study, which involves a rank-deficient maximum likelihood analysis (rd-MLE), provides a systematic approach to comprehensively assess a sensor's sensory ability without any initial assumptions. This theoretical framework can inspire the design of more efficient artificial sensors.

A Novel IoT-Enabled Wireless Sensor Grid for Spatial and Temporal Evaluation of Tracer Gas Dispersion.

Current IoT applications in indoor air focus mainly on general monitoring. This study proposed a novel IoT application to evaluate airflow patterns and ventilation performance using tracer gas. The tracer gas is a surrogate for small-size particles and bioaerosols and is used in dispersion and ventilation studies. Prevalent commercial tracer-gas-measuring instruments, although highly accurate, are relatively expensive, have a long sampling cycle, and are limited in the number of sampling points. To enhance the spatial and temporal understanding of tracer gas dispersion under the influence of ventilation, a novel application of an IoT-enabled, wireless R134a sensing network using commercially available small sensors was proposed. The system has a detection range of 5-100 ppm and a sampling cycle of 10 s. Using Wi-Fi communication, the measurement data are transmitted to and stored in a cloud database for remote, real-time analysis. The novel system provides a quick response, detailed spatial and temporal profiles of the tracer gas level, and a comparable air change rate analysis. With multiple units deployed as a wireless sensing network, the system can be applied as an affordable alternative to traditional tracer gas systems to identify the dispersion pathway of the tracer gas and the general airflow direction.

The neural addiction of cancer.

The recently uncovered key role of the peripheral and central nervous systems in controlling tumorigenesis and metastasis has opened a new area of research to identify innovative approaches against cancer. Although the 'neural addiction' of cancer is only partially understood, in this Perspective we discuss the current knowledge and perspectives on peripheral and central nerve circuitries and brain areas that can support tumorigenesis and metastasis and the possible reciprocal influence that the brain and peripheral tumours exert on one another. Tumours can build up local autonomic and sensory nerve networks and are able to develop a long-distance relationship with the brain through circulating adipokines, inflammatory cytokines, neurotrophic factors or afferent nerve inputs, to promote cancer initiation, growth and dissemination. In turn, the central nervous system can affect tumour development and metastasis through the activation or dysregulation of specific central neural areas or circuits, as well as neuroendocrine, neuroimmune or neurovascular systems. Studying neural circuitries in the brain and tumours, as well as understanding how the brain communicates with the tumour or how intratumour nerves interplay with the tumour microenvironment, can reveal unrecognized mechanisms that promote cancer development and progression and open up opportunities for the development of novel therapeutic strategies. Targeting the dysregulated peripheral and central nervous systems might represent a novel strategy for next-generation cancer treatment that could, in part, be achieved through the repurposing of neuropsychiatric drugs in oncology.

Dynamic evolution of brain structural patterns in liver transplantation recipients: a longitudinal study based on 3D convolutional neuronal network model.

To evaluate the dynamic evolution process of overall brain health in liver transplantation (LT) recipients, we employed a deep learning-based neuroanatomic biomarker to measure longitudinal changes of brain structural patterns before and 1, 3, and 6months after surgery. Because of the ability to capture patterns across all voxels from a brain scan, the brain age prediction method was adopted. We constructed a 3D-CNN model through T1-weighted MRI of 3609 healthy individuals from 8 public datasets and further applied it to a local dataset of 60 LT recipients and 134 controls. The predicted age difference (PAD) was calculated to estimate brain changes before and after LT, and the network occlusion sensitivity analysis was used to determine the importance of each network in age prediction. The PAD of patients with cirrhosis increased markedly at baseline (+ 5.74years) and continued to increase within one month after LT (+ 9.18years). After that, the brain age began to decrease gradually, but it was still higher than the chronological age. The PAD values of the OHE subgroup were higher than those of the no-OHE, and the discrepancy was more obvious at 1-month post-LT. High-level cognition-related networks were more important in predicting the brain age of patients with cirrhosis at baseline, while the importance of primary sensory networks increased temporarily within 6-month post-LT. The brain structural patterns of LT recipients showed inverted U-shaped dynamic change in the early stage after transplantation, and the change in primary sensory networks may be the main contributor. • The recipients' brain structural pattern showed an inverted U-shaped dynamic change after LT. • The patients' brain aging aggravated within 1month after surgery, and the subset of patients with a history of OHE was particularly affected. • The change of primary sensory networks is the main contributor to the change in brain structural patterns.

Enhancing Industrial Agriculture Efficiency through Sensor Network Integration

Despite being pivotal in global food provision, industrial agriculture grapples with sustainability and efficiency challenges exacerbated by climate change and population growth. The paper focuses on the ability of sensor networks to mitigate these issues and how countering strategies are developed. A case study will be used to explain how sensor networks can be put into practice to monitor industrial agriculture and, thus, give farmers real-time data information for correct action-taking. An analysis was done on a small-scale farm specializing in growing staple crops. The study used diverse sensors, including moisture, temperature, and pest incidence rates. The implementation strategies we addressed excelled, supported by joint efforts that preserved its achievements. The data analysis revealed patterns and critical insights that are very useful to farming practices through which the crucial part of sensor networks about optimizing resources and sustainability is highlighted. The implication is that industrial agriculture’s major efficiency, eco-friendliness, and profit gains are very high. Still, the potential for applicability is a subject for thought at a small scale. Another possible development channel is to improve access to current advances in analytics and sensors to achieve higher agricultural productivity. During the last sentence, it is worth stressing that sensory networks have huge opportunities to drive advances in agriculture and lead it toward a friendly environment.

Analysis of the Improvement of Engineering Mechanics Experimental Methods Based on IoT and Machine Learning

With the rapid development of sensor technology, machine learning, and the Internet of Things, wireless sensor networks have gradually become a research hotspot. In order to improve the data fusion performance of wireless sensor networks and ensure network security in the event of external attacks, this paper proposes a wireless sensor optimization algorithm model, involving wireless sensor networks, the Internet of Things, and other related fields. This paper first analyzes the role of the Internet of Things in wireless sensor networks, studies the localization mechanism and hierarchy of the Internet of Things based on wireless sensor networks, and improves the LE-RLPCCA (Position Estimation Robust Local Retention Criteria Correlation Analysis) localization algorithm model based on sensor grids. This paper discusses the problems of machine learning in wireless sensor networks, constructs a sensor-based machine learning model, and designs a data fusion algorithm for a wireless sensor networks' machine learning model. The application of wireless sensors in engineering mechanics experiments is summarized, and the optimization algorithm model of the wireless sensor in engineering mechanics experiments is proposed. The analysis results show that the average accuracy of the DKFCM-FSVM (Density aware Kernel-based Fuzzy C-means Clustering algorithm Fuzzy Support Vector Machine) algorithm in detecting five behaviors is 0.997, 0.992, 0.904, 0.996, and 0.946, respectively, and the accuracy in detecting different behaviors is the best, 0.005, 0.01, 0.003, and 0.006 respectively. It achieves the lowest false positive rate in the detection of different behaviors, and the average false positive rate is 0.004, 0.003, 0.003, 0.008, and 0.005, respectively, which shows that the DKFCM-FSVM algorithm model of wireless sensor networks in engineering mechanics experiments is the optimal solution. The work of this paper has good reference value for the application of wireless sensor networks and the optimization of engineering mechanics experimental methods and is helpful for further research of sensor technology.

Functional connectivity between medial pulvinar and cortical networks as a predictor of arousal to noxious stimuli during sleep.

The interruption of sleep by a nociceptive stimulus is favoured by an increase in the pre-stimulus functional connectivity between sensory and higher level cortical areas. In addition, stimuli inducing arousal also trigger a widespread electroencephalographic (EEG) response reflecting the coordinated activation of a large cortical network. Because functional connectivity between distant cortical areas is thought to be underpinned by trans-thalamic connections involving associative thalamic nuclei, we investigated the possible involvement of one principal associative thalamic nucleus, the medial pulvinar (PuM), in the sleeper's responsiveness to nociceptive stimuli. Intra-cortical and intra-thalamic signals were analysed in 440 intracranial electroencephalographic (iEEG) segments during nocturnal sleep in eight epileptic patients receiving laser nociceptive stimuli. The spectral coherence between the PuM and 10 cortical regions grouped in networks was computed during 5s before and 1 s after the nociceptive stimulus and contrasted according to the presence or absence of an arousal EEG response. Pre- and post-stimulus phase coherence between the PuM and all cortical networks was significantly increased in instances of arousal, both during N2 and paradoxical (rapid eye movement [REM]) sleep. Thalamo-cortical enhancement in coherence involved both sensory and higher level cortical networks and predominated in the pre-stimulus period. The association between pre-stimulus widespread increase in thalamo-cortical coherence and subsequent arousal suggests that the probability of sleep interruption by a noxious stimulus increases when it occurs during phases of enhanced trans-thalamic transfer of information between cortical areas.

Neuro-imaging characteristics of sensory impairment in cerebral palsy; a systematic review.

Objective: To identify and examine neural reorganization of the sensory network in terms of lesion type, somatotopic organization of the primary somatosensory area, and functional connectivity in relation to sensory function in children and young adults with cerebral palsy (CP). Design: systematic review, Prospero registration ID 342570. Data sources: PubMed; Cochrane; Web of Science; Embase; CINAHL and PEDro from inception to March 13, 2021. Eligibility criteria: All types of original studies, concerning sensory connectivity in relation to sensory outcome in patients with spastic CP, <30 years of age. No publication status or date restrictions were applied. Data extraction and synthesis: Two authors independently determined the eligibility of studies. Quality assessment was performed by a third author. Neuro-imaging/neurophysiological techniques, sensory outcomes and patient characteristics were extracted. Children and young adults with periventricular leucomalacia (PVL) lesions have significantly better hand function and sensation scores than patients with cortical-subcortical/middle cerebral artery (MCA) lesions. Ipsilesional reorganization of the S1 (primary somatosensory cortex) area appears to be the primary compensation mechanism after a unilateral early brain lesion, regardless of the timing of the lesion. Interhemispheric reorganization of the sensory system after early brain lesions is rare and, when it occurs, poorly effective. Diffusion tractography shows a positive correlation between the ascending sensory tract (AST) diffusivity metrics of the more affected hemisphere and sensory test outcomes. Because of the large variability in study design, patient characteristics, neuroimaging/neurophysiological techniques and parameters as well as sensory assessment methods used, it is difficult to draw definite inferences on the relationship between the reorganization of the sensory network following early brain damage and sensory function in children and young adults with CP. In general, sensory function seems to be worse in cortical as opposed to white matter tract (PVL) lesions. International consensus on a clinically relevant sensory test battery is needed to enhance understanding of the intriguing compensatory mechanisms of sensory network following early brain damage and potential consequences for rehabilitation strategies. https://www.crd.york.ac.uk/prospero/.

Linear regression based indoor daylight illuminance estimation with simple measurements for daylight-linked lighting control

Accurate prediction of indoor daylight illuminance is crucial for daylight-based lighting controls. However, determining the illuminance using physics-based simulation tools requires significant amounts of information, e.g. grid of sensors, sky model, 3D geometry of a target building and surroundings, etc. In this study, the authors suggest a daylight illuminance estimation method with minimal data of two reference sensors and two prior measurements. It is shown that the daylight coefficient and sky luminance distribution can be substituted by the illuminance of the reference points and illuminance of two or more target points at past times. The method was validated on a large open space with north-facing skylight windows and showed an 11.9% mean absolute percentage error. Additionally, a reference point selection method is presented. The proposed method is practical for daylight-based lighting control applications.

Reduced Voltage Sensors Based UPQC Tied Solar PV System Enabling Power Quality Improvement

This work presents an enhanced second-order generalized integrator (ESOGI) based control method for the grid integrated unified power quality conditioner (UPQC) with a solar photovoltaic (PV) system. The objective of this work is to improve the power quality (PQ) indices in the grid by eliminating voltage sensors (grid side) in the overall control. Moreover, presented control method effectively eliminates the DC offset from the input signals and estimates the fundamental element (FE), which is processed to compute the reference signals. The UPQC-PV system comprises two voltage source converters, one connected in a parallel at the point of common coupling for load compensation and the other connected in series via an injecting transformer for voltage compensation. The comparative performance is demonstrated in this work to validate the effectiveness of presented control over state-of-art control algorithms. Moreover, the cost analysis of the presented control is also discussed with the traditional controllers. The UPQC-PV system is simulated in Simulink tool of MATLAB and the performances are analyzed at various dynamic scenarios such as load unbalancing; distorted grid voltages; symmetrical and asymmetrical voltages swell and sag; and change in solar insolation, etc. Experimental results illustrate the superior performance under various operating conditions. The harmonics and magnitudes of load side voltages are restricted as per the IEEE standard 1159. The grid currents and load voltages are well sinusoidal with their total harmonic distortions in the permissible range state in the IEEE standard 519.

Structural health monitoring for corrosion induced thickness loss in marine plates subjected to random loads

In the highly corrosive environment where marine structures operate, the current industry practice is to overcompensate for corrosion induced thickness loss (CITL) and replace any parts that score below specified allowable limits during scheduled maintenance. Hence, there would be immediate benefits from the implementation of a Structural Health Monitoring (SHM) system that would allow for predictive, condition-based maintenance. The objective of this study is to investigate and assess the effectiveness of state-of-the-art statistical pattern recognition (SPR) and machine learning (ML) methods in association with alternative sensor grid architectures as an SHM scheme for detecting CITL, under highly variable operational conditions. For this purpose, a simple rectangular plate at different corrosion levels (uniform and pitting) was considered as a reference structural element, which was subjected to a stochastic pressure load. Strain response data were produced using Finite Element (FE) simulations and were treated under a probabilistic framework. Elements from detection theory and ML were taken under consideration in order to construct alternative detectors and assess their performance.