Machine learning-empowered sleep staging classification using multi-modality signals.

The goal is to enhance an automated sleep staging system's performance by leveraging the diverse signals captured through multi-modal polysomnography recordings. Three modalities of PSG signals, namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), were considered to obtain the optimal fusions of the PSG signals, where 63 features were extracted. These include frequency-based, time-based, statistical-based, entropy-based, and non-linear-based features. We adopted the ReliefF (ReF) feature selection algorithms to find the suitable parts for each signal and superposition of PSG signals. Twelve top features were selected while correlated with the extracted feature sets' sleep stages. The selected features were fed into the AdaBoost with Random Forest (ADB + RF) classifier to validate the chosen segments and classify the sleep stages. This study's experiments were investigated by obtaining two testing schemes: epoch-wise testing and subject-wise testing. The suggested research was conducted using three publicly available datasets: ISRUC-Sleep subgroup1 (ISRUC-SG1), sleep-EDF(S-EDF), Physio bank CAP sleep database (PB-CAPSDB), and S-EDF-78 respectively. This work demonstrated that the proposed fusion strategy overestimates the common individual usage of PSG signals.

Evaluation of Static Displacement Based on Ambient Vibration for Bridge Safety Management.

The evaluation of bridge safety is closely related to structural stiffness, with dynamic characteristics and displacement being key indicators. Displacement is a significant factor as it is a physical phenomenon that bridge users can directly perceive. However, accurately measuring displacement generally necessitates the installation of displacement meters within the bridge substructure and conducting load tests that require traffic closure, which can be cumbersome. This paper proposes a novel method that uses wireless accelerometers to measure ambient vibration data from bridges, extracts mode shapes and natural frequencies through the time domain decomposition (TDD) technique, and estimates static displacement under specific loads using the flexibility matrix. A field test on a 442.0 m cable-stayed bridge was conducted to verify the proposed method. The estimated displacement was compared with the actual displacement measured by a laser displacement sensor, resulting in an error rate of 3.58%. Additionally, an analysis of the accuracy of displacement estimation based on the number of measurement points indicated that securing at least seven measurement points keeps the error rate within 5%. This study could be effective for evaluating the safety of bridges in environments where load testing is difficult or for bridges that require periodic dynamic characteristics and displacement analysis due to repetitive vibrations, and it is expected to be applicable to various types of bridge structures.

Camera-Based Dynamic Vibration Analysis Using Transformer-Based Model CoTracker and Dynamic Mode Decomposition.

Accelerometers are commonly used to measure vibrations for condition monitoring in mechanical and civil structures; however, their high cost and point-based measurement approach present practical limitations. With rapid advancements in computer vision and deep learning, research into tracking the motion of individual pixels with vision cameras has increased. The recently developed CoTracker, a transformer-based model, has demonstrated excellence in motion tracking, yet its performance in measuring structural vibrations has not been fully explored. This paper investigates the efficacy of the CoTracker model in extracting full-field structural vibrations using cameras. It is initially applied to capture the dense point movements in video sequences of a cantilever beam recorded using a high-speed camera. Subsequently, modal analysis using delay-embedding dynamic mode decomposition (DMD) is conducted to extract modal parameters including natural frequencies, damping ratios, and mode shapes. The results, benchmarked against those from a reference accelerometer and the Finite Element Method (FEM) result, demonstrate CoTracker's high potential for general applicability in structural vibration measurements.

Detection of Total Hip Replacement Loosening Based on Structure-Borne Sound: Influence of the Position of the Sensor on the Hip Stem.

Accurate detection of implant loosening is crucial for early intervention in total hip replacements, but current imaging methods lack sensitivity and specificity. Vibration methods, already successful in dentistry, represent a promising approach. In order to detect loosening of the total hip replacement, excitation and measurement should be performed intracorporeally to minimize the influence of soft tissue on damping of the signals. However, only implants with a single sensor intracorporeally integrated into the implant for detecting vibrations have been presented in the literature. Considering different mode shapes, the sensor's position on the implant is assumed to influence the signals. In the work at hand, the influence of the position of the sensor on the recording of the vibrations on the implant was investigated. For this purpose, a simplified test setup was created with a titanium rod implanted in a cylinder of artificial cancellous bone. Mechanical stimulation via an exciter attached to the rod was recorded by three accelerometers at varying positions along the titanium rod. Three states of peri-implant loosening within the bone stock were simulated by extracting the bone material around the titanium rod, and different markers were analyzed to distinguish between these states of loosening. In addition, a modal analysis was performed using the finite element method to analyze the mode shapes. Distinct differences in the signals recorded by the acceleration sensors within defects highlight the influence of sensor position on mode detection and natural frequencies. Thus, using multiple sensors could be advantageous in accurately detecting all modes and determining the implant loosening state more precisely.

Stiffness-Based Evaluation of Hinge Joints in Prefabricated Assembled Multi-Girder Bridges under Operational Conditions.

Presently, the prevailing approaches to assessing hinge joint damage predominantly rely on predefined damage indicators or updating finite element models (FEMs). However, these methods possess certain limitations. The damage indicator method requires high-quality monitoring data and demonstrates variable sensitivities of distinct indicators to damage. On the other hand, the FEM approach mandates a convoluted FEM update procedure. Hinge joint damage represents a major kind of defect in prefabricated assembled multi-girder bridges (AMGBs). Therefore, effective damage detection methods are imperative to identify the damage state of hinge joints. To this end, a stiffness-based method for the performance evaluation of hinge joints of AMGBs is proposed in this paper. The proposed method estimates hinge joint stiffness by solving the characteristic equations of the multi-beam system. In addition, this study introduces a method for determining baseline joint stiffness using design data and FEM. Subsequently, a comprehensive evaluation framework for hinge joints is formulated, coupling a finite element model with the baseline stiffness, thereby introducing a damage indicator rooted in stiffness ratios. To verify the effectiveness of the proposed method, strain and displacement correlations are analyzed using actual bridge monitoring data, and articulation joint stiffness is identified. The results underscore the capability of the proposed method to accurately pinpoint the location and extent of hinge joint damage.

Estimating Bridge Natural Frequencies Based on Modal Analysis of Vehicle-Bridge Synchronized Vibration Data.

This paper presents a method for accurately estimating the natural frequencies of bridges by simultaneously measuring the acceleration vibration data of vehicles and bridges and applying modal analysis theory. Vibration sensors synchronized with GPS timing were installed on both vehicles and bridges, achieving stable and high-precision time synchronization. This enabled the computation of the bridge's Frequency Response Functions (FRFs) for each mode, leading to a refined estimation of natural frequencies. The validity of the theory was confirmed through numerical simulations and experimental tests. The simulations confirmed its effectiveness, and similar trends were observed in actual bridge measurements. Consequently, this method significantly enhances the feasibility of bridge health monitoring systems. The proposed method is suitable for road bridges with spans ranging from short- to medium-span length, where the vehicle is capable of exciting the bridge.

Augmented Reality-Based Real-Time Visualization for Structural Modal Identification.

In the era of aging civil infrastructure and growing concerns about rapid structural deterioration due to climate change, the demand for real-time structural health monitoring (SHM) techniques has been predominant worldwide. Traditional SHM methods face challenges, including delays in processing acquired data from large structures, time-intensive dense instrumentation, and visualization of real-time structural information. To address these issues, this paper develops a novel real-time visualization method using Augmented Reality (AR) to enhance vibration-based onsite structural inspections. The proposed approach presents a visualization system designed for real-time fieldwork, enabling detailed multi-sensor analyses within the immersive environment of AR. Leveraging the remote connectivity of the AR device, real-time communication is established with an external database and Python library through a web server, expanding the analytical capabilities of data acquisition, and data processing, such as modal identification, and the resulting visualization of SHM information. The proposed system allows live visualization of time-domain, frequency-domain, and system identification information through AR. This paper provides an overview of the proposed technology and presents the results of a lab-scale experimental model. It is concluded that the proposed approach yields accurate processing of real-time data and visualization of system identification information by highlighting its potential to enhance efficiency and safety in SHM by integrating AR technology with real-world fieldwork.

Optimal Sensor Placement for Enhanced Efficiency in Structural Health Monitoring of Medium-Rise Buildings.

Output-only modal analysis using ambient vibration testing is ubiquitous for the monitoring of structural systems, especially for civil engineering structures such as buildings and bridges. Nonetheless, the instrumented nodes for large-scale structural systems need to cover a significant portion of the spatial volume of the test structure to obtain accurate global modal information. This requires considerable time and resources, which can be challenging in large-scale projects, such as the seismic vulnerability assessment over a large number of facilities. In many instances, a simple center-line (stairwell case) topology is generally used due to time, logistical, and economic constraints. The latter, though a fast technique, cannot provide complete modal information, especially for torsional modes. In this research, corner-line instrumented nodes layouts using only a reference and a roving sensor are proposed, which overcome this issue and can provide maximum modal information similar to that from 3D topologies for medium-rise buildings. Parametric studies are performed to identify the most appropriate locations for sensor placement at each floor of a medium-rise building. The results indicate that corner locations at each floor are optimal. The proposed procedure is validated through field experiments on two medium-rise buildings.

Efficient Vibration Measurement and Modal Shape Visualization Based on Dynamic Deviations of Structural Edge Profiles.

As a non-contact method, vision-based measurement for vibration extraction and modal parameter identification has attracted much attention. In most cases, artificial textures are crucial elements for visual tracking, and this feature limits the application of vision-based vibration measurement on textureless targets. As a computation technique for visualizing subtle variations in videos, the video magnification technique can analyze modal responses and visualize modal shapes, but the efficiency is low, and the processing results contain clipping artifacts. This paper proposes a novel method for the application of a modal test. In contrast to the deviation magnification that exaggerates subtle geometric deviations from only a single image, the proposed method extracts vibration signals with sub-pixel accuracy on edge positions by changing the perspective of deviations from space to timeline. Then, modal shapes are visualized by decoupling all spatial vibrations following the vibration theory of continuous linear systems. Without relying on artificial textures and motion magnification, the proposed method achieves high operating efficiency and avoids clipping artifacts. Finally, the effectiveness and practical value of the proposed method are validated by two laboratory experiments on a cantilever beam and an arch dam model.

Autonomous Sensor System for Low-Capacity Wind Turbine Blade Vibration Measurement.

This paper presents the design, implementation, and validation of an on-blade sensor system for remote vibration measurement for low-capacity wind turbines. The autonomous sensor system was deployed on three wind turbines, with one of them operating in harsh weather conditions in the far south of Chile. The system recorded the acceleration response of the blades in the flapwise and edgewise directions, data that could be used for extracting the dynamic characteristics of the blades, information useful for damage diagnosis and prognosis. The proposed sensor system demonstrated reliable data acquisition and transmission from wind turbines in remote locations, proving the ability to create a fully autonomous system capable of recording data for monitoring and evaluating the state of health of wind turbine blades for extended periods without human intervention. The data collected by the sensor system presented in this study can serve as a foundation for developing vibration-based strategies for real-time structural health monitoring.

A Wireless Data Acquisition System Based on MEMS Accelerometers for Operational Modal Analysis of Bridges.

This paper illustrates a novel and cost-effective wireless monitoring system specifically developed for operational modal analysis of bridges. The system employs battery-powered wireless sensors based on MEMS accelerometers that dynamically balance power consumption with high processing features and a low-power, low-cost Wi-Fi module that ensures operation for at least five years. The paper focuses on the system's characteristics, stressing the challenges of wireless communication, such as data preprocessing, synchronization, system lifetime, and simple configurability, achieved through the integration of a user-friendly, web-based graphical user interface. The system's performance is validated by a lateral excitation test of a model structure, employing dynamic identification techniques, further verified through FEM modeling. Later, a system composed of 30 sensors was installed on a concrete arch bridge for continuous OMA to assess its behavior. Furthermore, emphasizing its versatility and effectiveness, displacement is estimated by employing conventional and an alternative strategy based on the Kalman filter.

SecureVision: Advanced Cybersecurity Deepfake Detection with Big Data Analytics.

SecureVision is an advanced and trustworthy deepfake detection system created to tackle the growing threat of 'deepfake' movies that tamper with media, undermine public trust, and jeopardize cybersecurity. We present a novel approach that combines big data analytics with state-of-the-art deep learning algorithms to detect altered information in both audio and visual domains. One of SecureVision's primary innovations is the use of multi-modal analysis, which improves detection capabilities by concurrently analyzing many media forms and strengthening resistance against advanced deepfake techniques. The system's efficacy is further enhanced by its capacity to manage large datasets and integrate self-supervised learning, which guarantees its flexibility in the ever-changing field of digital deception. In the end, this study helps to protect digital integrity by providing a proactive, scalable, and efficient defense against the ubiquitous threat of deepfakes, thereby establishing a new benchmark for privacy and security measures in the digital era.

Smartphone Prospects in Bridge Structural Health Monitoring, a Literature Review.

Bridges are critical components of transportation networks, and their conditions have effects on societal well-being, the economy, and the environment. Automation needs in inspections and maintenance have made structural health monitoring (SHM) systems a key research pillar to assess bridge safety/health. The last decade brought a boom in innovative bridge SHM applications with the rise in next-generation smart and mobile technologies. A key advancement within this direction is smartphones with their sensory usage as SHM devices. This focused review reports recent advances in bridge SHM backed by smartphone sensor technologies and provides case studies on bridge SHM applications. The review includes model-based and data-driven SHM prospects utilizing smartphones as the sensing and acquisition portal and conveys three distinct messages in terms of the technological domain and level of mobility: (i) vibration-based dynamic identification and damage-detection approaches; (ii) deformation and condition monitoring empowered by computer vision-based measurement capabilities; (iii) drive-by or pedestrianized bridge monitoring approaches, and miscellaneous SHM applications with unconventional/emerging technological features and new research domains. The review is intended to bring together bridge engineering, SHM, and sensor technology audiences with decade-long multidisciplinary experience observed within the smartphone-based SHM theme and presents exemplary cases referring to a variety of levels of mobility.

Differentiating single cervical cells by mitochondrial fluorescence imaging and deep learning-based label-free light scattering with multi-modal static cytometry.

Cervical cancer is a high-risk disease that threatens women's health globally. In this study, we developed the multi-modal static cytometry that adopted different features to classify the typical human cervical epithelial cells (H8) and cervical cancer cells (HeLa). With the light-sheet static cytometry, we obtain brightfield (BF) images, fluorescence (FL) images and two-dimensional (2D) light scattering (LS) patterns of single cervical cells. Three feature extraction methods are used to extract multi-modal features based on different data characteristics. Analysis and classification of morphological and textural features demonstrate the potential of intracellular mitochondria in cervical cancer cell classification. The deep learning method is used to automatically extract deep features of label-free LS patterns, and an accuracy of 76.16% for the classification of the above two kinds of cervical cells is obtained, which is higher than the other two single modes (BF and FL). Our multi-modal static cytometry uses a variety of feature extraction and analysis methods to provide the mitochondria as promising internal biomarkers for cervical cancer diagnosis, and to show the promise of label-free, automatic classification of early cervical cancer with deep learning-based 2D light scattering.

Development and validation of an intuitive biomechanics-based method for intraocular pressure measurement: a modal analysis approach.

BACKGROUND: Current intraocular pressure (IOP) measurements based on non-contact tonometry are derived from statistics-driven equations and lack biomechanical significance, which often leads to under-estimation in post-refractive surgery cornea. This study aims to introduce and validate modal analysis-derived intraocular pressure (mIOP) as a novel method generated through Legendre-based modal decomposition of the anterior corneal contour; it provides an accurate and intuitive IOP measurement from an energy-based perspective. METHODS: This retrospective study included 680 patients. Healthy participants were divided into reference (n = 385) and validation (n = 142) datasets, and the others underwent either femtosecond-assisted laser in situ keratomileusis (FS-LASIK, n = 58) or transepithelial photorefractive keratectomy (TPRK, n = 55). Corneal curvature of the right eyes was extracted from raw serial cross-sectional images of the cornea generated by Corvis ST, a noncontact tonometer with a high-speed Scheimpflug-camera. Legendre expansion was then applied to the corneal curvature to obtain the modal profiles (i.e., temporal changes of the coefficient for each basis polynomial [modes]). Using the reference dataset, feature selection on the modal profiles generated a final mIOP model consisting of a single parameter: total area under curve (frames 1-140) divided by the area under curve of the rising phase (frames 24-40) in the fourth mode, i.e. the M4 ratio. Validation was performed in both the healthy validation and postoperative datasets. IOP-Corvis, pachymetry-corrected IOP, biomechanically corrected IOP, and mIOP values were compared. For the FS-LASIK and TPRK groups, pairwise postoperative IOP changes were analyzed through repeated measures analysis of variance, and agreement was examined through Bland-Altman analysis. Using a finite element analysis based three-dimensional model of the human cornea, we further compared the M4 ratio with the true intraocular pressure within the physiological range. RESULTS: The M4 ratio-based mIOP demonstrated weak to negligible association with age, radius of corneal curvature, and central corneal thickness (CCT) in all validation analyses, and performed comparably with biomechanically corrected IOP (bIOP) in the refractive surgery groups. Both remained nearly constant postoperatively and were not influenced by CCT changes. Additionally, M4 ratio accurately represented true intraocular pressure in the in silico model. CONCLUSIONS: mIOP is a reliable IOP measurement in healthy and postrefractive surgery populations. This energy-based, ratio-derived approach effectively filters out pathological, rotational, misaligned movements and serves as an interpatient self-calibration index. Modal analysis of corneal deformation dynamics provides novel insights into regional corneal responses against pressure loading.

Extended Tromograph Surveys for a Full Experimental Characterisation of the San Giorgio Cathedral in Ragusa (Italy).

Geophysical surveys are widely used to reconstruct subsoil seismo-stratigraphic structures with a non-invasive approach. In this study the geophysical surveys were carried out with the aim to characterise the San Giorgio Cathedral in Ragusa (Italy) and the area on which it is built from a dynamic point of view. A 3D subsoil model was realised through the integration of two active (i.e., seismic tomography and multichannel analysis of surface waves) and one passive seismic technique (horizontal to vertical spatial ratio). The instrumentation used for the latter method consists of a tromograph (Tromino®), which is also employed for the characterisation of the building, focusing on the façade and the dome, by means of an ambient vibration test, processed through the standard spectral ratio and frequency domain decomposition methods. Integration of the 3D model, showing the distribution of areas with different physicomechanical characteristics, enables identifying anomalies that are likely attributable to the remains of the ancient Byzantine church of San Nicola. Four lower modes mainly involving the two investigated macroelements are identified. The experimental results outline the advantages of the use of the tromograph both for soil and structural characterisation, especially for massive masonry buildings located in areas with high seismic hazard.

Health Monitoring of Serial Structures Applying Piezoelectric Film Sensors and Modal Passport.

Health monitoring of critical structures, that form parts of serial operating objects, is a pressing task. The Operational Modal Analysis (OMA) techniques could be the optimal solution. An inexpensive measurement system, such as the OMA, uses a lot of sensors for structural response assessment. The health monitoring of serial structures has to also consider possible deviations between samples. A solution providing the OMA application includes the compact measurement system based on piezoelectric film sensors and modal passport (MP) techniques. For validation of the proposed approach, a series of five similar composite cylinders, with a network of piezoelectric film sensors, was used. Applying modal tests on the specimens, and using OMA with MP methods, the set of typical modal parameters was determined and analyzed. The results of the study confirmed the feasibility of the sensor network and its applicability for structural health monitoring of serial samples using OMA methods. The proven effectiveness of OMA/MP techniques, combined with a sensor network, provides a prototype of intelligent sensor technology, which can be used for health monitoring of structures, including those that are part of an operating facility.

Single-Point and Surface Quality Assessment Algorithm in Continuous Production with the Use of 3D Laser Doppler Scanning Vibrometry System.

In the current economic situation of many companies, the need to reduce production time is a critical element. However, this cannot usually be carried out with a decrease in the quality of the final product. This article presents a possible solution for reducing the time needed for quality management. With the use of modern solutions such as optical measurement systems, quality control can be performed without additional stoppage time. In the case of single-point measurement with the Laser Doppler Vibrometer, the measurement can be performed quickly in a matter of milliseconds for each product. This article presents an example of such quality assurance measurements, with the use of fully non-contact methods, together with a proposed evaluation criterion for quality assessment. The proposed quality assurance algorithm allows the comparison of each of the products' modal responses with the ideal template and stores this information in the cloud, e.g., in the company's supervisory system. This makes the presented 3D Laser Vibrometry System an advanced instrumentation and data acquisition system which is the perfect application in the case of a factory quality management system based on the Industry 4.0 concept.

Automated Operational Modal Analysis for Rotating Machinery Based on Clustering Techniques.

Many parameters can be used to express a machine's condition and to track its evolution through time, such as modal parameters extracted from vibration signals. Operational Modal Analysis (OMA), commonly used to extract modal parameters from systems under operating conditions, was successfully employed in many monitoring systems, but its application in rotating machinery is still in development due to the distinct characteristics of this system. To implement efficient monitoring systems based on OMA, it is essential to automatically extract the modal parameters, which several studies have proposed in the literature. However, these algorithms are usually developed to deal with structures that have different characteristics when compared to rotating machinery, and, therefore, work poorly or do not work with this kind of system. Thus, this paper proposes, and has as its main novelty in, a new automated algorithm to carry out modal parameter identification on rotating machinery through OMA. The proposed technique was applied in two different datasets to enable the evaluation of the robustness to different systems and test conditions. It is revealed that the proposed algorithm is suitable for the accurate extraction of frequencies and damping ratios from the stabilization diagram, for both the rotor and the foundation, and only one user defined parameter is required.

Static Loads Influence on Modal Properties of the Composite Cylindrical Shells with Integrated Sensor Network.

This paper presents the results of experimental and numerical studies of the dynamic parameters of composite cylindrical shells loaded under axial tension. Five composite structures were manufactured and loaded up to 4817 N. The static load test was carried out by hanging the load to the lower part of a cylinder. The natural frequencies and mode shapes were measured during testing using a network of 48 piezoelectric sensors that measure the strains of composite shells. The primary modal estimates were calculated with ARTeMIS Modal 7 software using test data. The methods of modal passport, including modal enhancement, were used to improve the accuracy of the primary estimates and reduce the influence of random factors. To estimate the effect of a static load on the modal properties of a composite structure, a numerical calculation and a comparative analysis of experimental and numerical data was carried out. The results of the numerical study confirmed that natural frequency increases with increasing tensile load. The data obtained from experimental results were not fully consistent with the results of numerical analysis, but showed a consistent pattern, repeating for all samples.