Non-invasive Inspection Research Articles

Decay detection in historic buildings through image-based deep learning

Nowadays, built heritage condition assessment is realized through on-site or photo-aided visual inspections, reporting pathologies manually on drawings, photographs, notes. The knowledge of the state of conservation goes through subjective and time or cost consuming procedures. This is even relevant for a historic building characterized by geometrical and morphological complexity and huge extension, or at risk of collapse. In this context, advancements in the field of Computer Vision and Artificial Intelligence provide an opportunity to address these criticalities. The proposed methodology is based on a Mask R-CNN model, for the detection of decay morphologies on built heritages, and, particularly on historic buildings. The experimentation has been carried out and validated on a highly heterogeneous dataset of images of historic buildings, representative of the regional Architectural Heritage, such as: castles, monasteries, noble buildings, rural buildings. The outcomes highlighted the significance of this remote, non-invasive inspection technique, in support of the technicians in the preliminary knowledge of the building state of conservation, and, most of all, in the decay mapping of some particular classes of alterations (moist area, biological colonization).

Characterizing an Optically Induced Sub-micrometer Gigahertz Acoustic Wave in a Silicon Thin Plate.

Optically induced GHz-THz guided acoustic waves have been intensively studied because of the potential to realize noninvasive and noncontact material inspection. Although the generation of photoinduced guided acoustic waves utilizing nanostructures, such as ultrathin plates, nanowires, and materials interfaces, is being established, experimental characterization of these acoustic waves in consideration of the finite size effect has been difficult due to the lack of experimental methods with nm × ps resolution. Here we experimentally observe the sub-micrometer guided acoustic waves in a nanofabricated ultrathin silicon plate by ultrafast transmission electron microscopy with nm × ps precision. We successfully characterize the excited guided acoustic wave in frequency-wavenumber space by applying Fourier-transformation analysis on the bright-field movie. These results suggest the great potential of ultrafast transmission electron microscopy to characterize the acoustic modes realized in various nanostructures.

Tracking tumor heterogeneity and progression with near-infrared II fluorophores.

Heterogeneous cells are the main feature of tumors with unique genetic and phenotypic characteristics, which can stimulate differentially the progression, metastasis, and drug resistance. Importantly, heterogeneity is pervasive in human malignant tumors, and identification of the degree of tumor heterogeneity in individual tumors and progression is a critical task for tumor treatment. However, current medical tests cannot meet these needs; in particular, the need for noninvasive visualization of single-cell heterogeneity. Near-infrared II (NIR-II, 1000-1700 nm) imaging exhibits an exciting prospect for non-invasive monitoring due to the high temporal-spatial resolution. More importantly, NIR-II imaging displays more extended tissue penetration depths and reduced tissue backgrounds because of the significantly lower photon scattering and tissue autofluorescence than traditionalthe near-infrared I (NIR-I) imaging. In this review, we summarize systematically the advances made in NIR-II in tumor imaging, especially in the detection of tumor heterogeneity and progression as well as in tumor treatment. As a non-invasive visual inspection modality, NIR-II imaging shows promising prospects for understanding the differences in tumor heterogeneity and progression and is envisioned to have the potential to be used clinically.

Machine-Learning Methods for Material Identification Using mmWave Radar Sensor

In recent years, radar sensors are gaining a paramount role in noninvasive inspection of different objects and materials. In this article, we present a framework for using machine learning in material identification based on their reflected radar signature. We employ multiple receiving (RX) channels of the radar module to capture the signatures of the reflected signal from different target materials. Within the proposed framework, we present three approaches suitable for material classification, namely: 1) convolutional neural networks (CNNs); 2) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> -nearest neighbor ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> -NN); and 3) dynamic time warping (DTW). The proposed framework is tested using extensive experimentation and found to provide near-ideal classification accuracy in classifying six distinct material types. Furthermore, we explore the possibility of utilizing the framework to detect the volume of the identified material, where the obtained classification accuracy is above 98% in distinguishing three different volume levels.

Anomaly Detection in Network Traffic using Machine Learning for Early Threat Detection

Due to advances in network technologies, the amount of people using networks is rising rapidly. This has resulted in a large amount of transmission information being generated and moved across the network. However, this data is vulnerable to attacks and intrusions. To prevent network intrusions, security measures must be implemented, which can detect anomalies and identify potential threats. Network security researchers and labs have done extensive research in network security. The purpose of this study was to perform a noninvasive inspection to give a large general mechanism on recent advances in abnormality detection. The study reviewed recent research published in the past five years, which examined new technologies and potential future opportunities in anomaly detection. The literature review focused specifically on anomaly detection systems used in network traffic. This included various applications such as Wireless Sensor Networks (WSN), Internet of Things (IoT), High Performance Computing, Industrial Control Systems (ICS), and Software Defined Networking (SDN) environments. The review concludes by highlighting several unresolved issues that need to be addressed in order to improve anomaly detection systems.

Surface H‐field mapping of a GaAs single pole double throw switch chip based on quantum diamond probe

With the improvement of design capability and manufacture technology, the integration as well as the complexity of chips have also increased dramatically, and it becomes critical to realize noninvasive electromagnetic inspection of chips at higher resolutions. In this paper, we propose a submicron-resolution microwave near-field imaging system based on the nitrogen-vacancy center (NV) in diamond, which mainly consists of an optical hardware system and a software control system, and can be used for nondestructive imaging of microwave fields on the surface of integrated circuits with submicron resolution. We applied this technique to scan the surface microwave field distribution of a GaAs single pole double throw switch chip. The scanning imaging system can image the near-field magnetic distribution for the chip, which provides a new solution for analyzing the current distribution on the chip surface and thus addressing problems such as excessive current or crosstalk. It is worth mentioning that the diamond NV color center-based sensor has a very high-spatial resolution and magnetic field detection sensitivity at room temperature, while the dielectric constant of natural diamond is 5.5, which also provides the possibility of diamond as a sensor in complex radiation environments and is an ideal detector material for near-field imaging of electromagnetic fields.

Vibration-Based Approach to Measure Rail Stress: Modeling and First Field Test.

This paper describes a non-invasive inspection technique for the estimation of longitudinal stress in continuous welded rails (CWR) to infer the rail neutral temperature (RNT), i.e., the temperature at which the net longitudinal force in the rail is zero. The technique is based on the use of finite element method (FEM), vibration measurements, and machine learning (ML). FEM is used to model the relationship between the boundary conditions and the longitudinal stress of any given CWR to the vibration characteristics (mode shapes and frequencies) of the rail. The results of the numerical analysis are used to train a ML algorithm that is then tested using field data obtained by an array of accelerometers polled on the track of interest. In the study presented in this article, the proposed technique was proven in the field during an experimental campaign conducted in Colorado. A commercial FEM software was used to model the rail track as a short rail segment repeated indefinitely and under varying boundary conditions and stress. Three datasets were prepared and fed to ML models developed using hyperparameter search optimization techniques and k-fold cross validation to infer the stress or the RNT. The frequencies of vibration were extracted from the time waveforms obtained from two accelerometers temporarily attached to the rail. The results of the experiments demonstrated that the success of the technique is dependent on the accuracy of the model and the ability to properly identify the modeshapes. The results also proved that the ML was also able to predict successfully the neutral temperature of the tested rail by using only a limited number of experimental data for the training.

Exosome-Derived microRNAs from Mouthrinse Have the Potential to Be Novel Biomarkers for Sjögren Syndrome.

Sjögren syndrome (SS) is diagnosed based on invasive tissue biopsies and blood sampling. Therefore, a novel non-invasive and simple inspection diagnostic marker of SS is required. Here, we identified exosome-derived microRNAs (miRNAs) as biomarkers for SS using non-invasive mouthrinse samples collected from patients with SS and healthy volunteers. We compared miRNAs derived from exosomes in mouthrinse samples from the two groups using microarrays and real-time polymerase chain reaction (PCR) and identified 12 miRNAs as biomarker candidates. The expression ratios of four miRNAs were significantly increased in the SS group compared to the control group. Logistic regression analysis revealed a more significant influence of miR-1290 and let-7b-5p in the SS group than that in the control group. We combined these miRNAs to create a diagnostic prediction formula using logistic regression analysis. The combination of miR-1290 and let-7b-5p distinguished SS from the control samples with an AUC, sensitivity, specificity, positive predictive value, and negative predictive value of 0.856, 91.7%, 83.3%, 84.6%, and 90.9%, respectively. These results indicated that an increased ratio of these miRNAs could serve as a novel and non-invasive diagnostic marker for SS. This is the first report of diagnosis and screening of SS by adopting a non-invasive method using mouthrinse.

Near-infrared Imaging for Information Embedding and Extraction with Layered Structures

Non-invasive inspection and imaging techniques are used to acquire non-visible information embedded in samples. Typical applications include medical imaging, defect evaluation, and electronics testing. However, existing methods have specific limitations, including safety risks (e.g., X-ray), equipment costs (e.g., optical tomography), personnel training (e.g., ultrasonography), and material constraints (e.g., terahertz spectroscopy). Such constraints make these approaches impractical for everyday scenarios. In this article, we present a method that is low-cost and practical for non-invasive inspection in everyday settings. Our prototype incorporates a miniaturized near-infrared spectroscopy scanner driven by a computer-controlled 2D-plotter. Our work presents a method to optimize content embedding, as well as a wavelength selection algorithm to extract content without human supervision. We show that our method can successfully extract occluded text through a paper stack of up to 16 pages. In addition, we present a deep-learning-based image enhancement model that can further improve the image quality and simultaneously decompose overlapping content. Finally, we demonstrate how our method can be generalized to different inks and other layered materials beyond paper. Our approach enables a wide range of content embedding applications, including chipless information embedding, physical secret sharing, 3D print evaluations, and steganography.

NIR laser-based imaging techniques to monitor quality attributes of apple slices during the drying process: Laser-light backscattering & biospeckle imaging techniques

This paper seeks to investigate the potential use of laser-based imaging techniques in non-invasive quality inspection of apple slices during drying. For this purpose, Laser-light Backscattering (LLBI) and Biospeckle (BSI) Imaging techniques were investigated. Images at 980 nm and 1450 nm were captured. The data was used to develop Gaussian Process Regression (GPR) and Partial Least Square Regression (PLSR) models in order to estimate quality attributes of moisture content, vitamin C, and soluble solids content (SSC). Overall, the predictions accuracies were slightly in favor of GPR models. Moisture content was best estimated with R-squared = 0.92 and RMSE = 7%, and R-squared = 0.93 and RMSE = 6.54% when GPR models were trained on 1450/980 nm data acquired by LLBI or 980 nm data acquired by BSI, respectively. LLBI-based GPR models predicted vitamin C with R-squared ≥ 0.79 and RMSE ≤ 0.83 mg/100 g fresh weight (FW), slightly better than that of BSI (R-squared = 0.80 and RMSE ≤ 1.01 mg/100 g). The most accurate predictions of SSC for LLBI (R-squared = 0.88 and RMSE = 6.39%) and BSI (R-squared = 0.82 and RMSE = 7.99%) were achieved at 980 nm. Furthermore, BSI monitoring system was embedded into an experimental dryer to study the interaction between sample temperature and biospeckle activity. Results showed an increase in biospeckle activity at the beginning of drying followed by a gradual decrease towards the end of drying. The findings of present study indicate the potential use of simple and promising monochrome imaging systems in monitoring of the drying process that can be considered as alternatives to more expensive imaging sensors such as hyperspectral imaging.

Automatic flower cluster estimation in apple orchards using aerial and ground based point clouds

Chemical and mechanical thinning processes have long been used in stone and pome fruit production. During the thinning of apple flowers, growers use chemicals to regulate the tree load. Hand thinning is applied after the June drop to prune trees with excess crop load. The process of thinning can be unpredictable especially in biennial bearing cultivars. Thus, incentives to optimise chemical usage and to reduce expensive manual labour is ever increasing. Ground based machine vision systems have grown in popularity in orchard management due to the level of detail as well as plant coverage they can inspect with. Additionally, unmanned aerial vehicles (UAV) -based remote sensing technology is becoming a popular non-invasive quality inspection solution. This work proposes a framework for combining UAV and ground based RGB image data to detect flowering intensity in a Dutch Elstar apple orchard. The framework, based on point cloud reconstruction, presents automatic point cloud handling techniques as well as automated unsupervised flowering intensity estimation methods. Two linear regression models based on unsupervised machine learning methods were trained and validated from the framework that estimate flowering intensity in the orchard with both models having R 2 > 0.65, RRMSE < 20% and p-stat < 0.005 for the correlation between the image derived flower index and the flower cluster number counted in field. The proposed methods provide a novel strategy for guiding flower thinning using simple RGB images and location data only. Moreover, the proposed methods also reveal the flexibility of intra-tree inspection by checking its sub-volumes. • Automatic flower cluster estimation at the tree level with a R 2 = 0.7, RMSE < 20. • Ground and aerial point clouds have better performance when combined. • Novel strategy developed for guiding flower thinning in orchard management. • Dataset with aerial and ground images, and field sampling data released.

Application of point-of-care ultrasound in patients receiving enteral nutrition.

Enteral nutrition (EN) is the first-choice nutritional support, as it is more in line with normal physiological processes. During EN, the major goals to achieve include accurate confirmation of the feeding tube position, monitoring the gastric residual volume, assessing gastrointestinal motility, and monitoring the nutritional status of patients. With rapid development in technology, point-of-care ultrasound (POCUS) has become a more convenient and effective technical tool for monitoring critically ill patients receiving EN. In this review, we have summarized and discussed the value of POCUS in the implementation, monitoring, and evaluation of EN therapy to provide a reference for nutritional support of critically ill patients in critical care settings. This is a narrative review. A literature search for Scopus-indexed articles was performed randomly using PubMed and MEDLINE databases as the primary sources. No specific term was used for the search. POCUS can be used for positioning of nasogastric and nasointestinal tubes, evaluation of gastric residuals and gastrointestinal motility as well as monitoring of nutritional status. POCUS is a real-time, highly repeatable, radiation-free, and non-invasive visual inspection technique, with high application value in assessing the nutritional status of patients receiving EN and guiding the development of further nutritional treatment plans. It is an important diagnostic and monitoring tool that can be used by the clinicians in the ICU.

Novel infrared-terahertz fusion 3D non-invasive imaging of plant fibre-reinforced polymer composites

The reinforcement of polymer composites using plant fibres has received vast and growing attention for investigation owing to their capability to serve as semi-structural materials, especially as a substitute for fiberglass. However, in this type of research, the structural complexity, due to geometrical mismatches and inherent variability to the properties of vegetable fibres and plant fibre composites would benefit from more effective non-invasive inspection techniques. In this work, a novel infrared-terahertz fused approach was proposed, and a new unsupervised deep residual fusion algorithm was developed in order to combine the outputs from two different physical mechanisms. Specifically, infrared imaging provided the details of the defects and the morphological information from the surface and subsurface, while terahertz imaging recorded the distribution of the fibres and the resin. Finally, the fused infrared-terahertz slices were reconstructed into a form of 3D exhibition for inspection and evaluation of two plant fibre-reinforced polymer composites in first time using multiphysical imaging and fusion.

Diagnostic feasibility of time domain features for detecting and characterizing cry cause factors - an investigation

ABSTRACT The very first cry of an infant gives vital information about the health of infant, and as they grow the acoustics change with the development of their vocal tract system. This reflects the learning mechanism of infant cry-cause factors, which upon solving will give a huge impact in the areas of medical and household. The behaviour of infant cry records is frequently used for non-invasive infant health inspection and monitoring. Automated approaches for forecasting health status, on the other hand, are highly dependent on the features extracted. In this paper, the diagnostic feasibility of the time domain features to detect and discriminate various cry-cause factors of cry signals is investigated. Mean, peak value, RMS, crest factor, Impulse factor, shape factor, energy, and clearance factor are the features employed in this work. It is discovered that, among the features investigated, RMS is more effective than all other features in detecting cry-cause factors with a Probability value (P) of 2.23307 × 10−6 and it offers an accuracy of 91.67%, sensitivity of 90%, and specificity of 93.33%.

Utilization of Both Machine Vision and Robotics Technologies in Assisting Quality Inspection and Testing

Inspecting the smoothness and durability of the exterior and interior surfaces of manufactured products such as large passenger aircraft requires utilizing manufacturing precision instruments. Manual techniques are mainly adopted in inspections, which are, however, much costly and have low efficiency. Moreover, manual operation is more prone to missing and false inspections. To cope with these issues, effective precision instruments have been needed to devise intelligent inspections for impalpable damages as necessary tools. When many inspection tasks are investigated, very few public datasets are available to recognize the intelligent inspection of precision instruments. On the other hand, precision instruments can be applied to a wide variety of damages. YOLO V3 was proposed based on acquiring and processing the image appearances, which deal with the surface inspection of the precision instrument in this study. The image dataset of the impalpable damage was initially established. More specifically, the YOLO V3 detection network is leveraged to roughly calculate the location of the damage appearances and identify the damage type. Afterward, the designed level set algorithm was employed to obtain more accurate damage locations in the image block utilizing the characteristics of different types of damages. Finally, a quantitative analysis was performed employing the refined detection results. A deep architecture that can intelligently conduct damage detection was proposed. Besides, the proposed method exhibited a strong tolerance for unknown types of damages and excellent flexibility and adaptability. Extensive experimental results demonstrated that the proposed method can alleviate the shortcomings of the traditional inspection methods. Thus, it provided technical guidance for the applications of the intelligent orbital inspection of the robots. The proposed method with a more precise and noninvasive inspection technique remarkably accelerates the inspection time of impalpable damages on surfaces.

A van der Waals heterostructure based on nickel telluride and graphene with spontaneous high-frequency photoresponse

Terahertz detectors have potential applications in various fields including security inspection, biomedicine, and noninvasive quality inspection due to their ability to detect terahertz radiation. However, traditional detection materials have reached their bottlenecks due to difficulties in the breakthrough of fundamental principles for terahertz light. In this work, a terahertz detector based on a NiTe2–graphene van der Waals heterostructure has been developed to inhibit the dark current and thermal-agitation noise at room temperature. The hetero-integration of NiTe2 and graphene exhibits enhanced photon-absorption ability and its downconversion into a direct current. The experimental results show that the peak photoresponsivity of our photodetector is 1.31 A W−1 at 0.28 THz, and the corresponding noise equivalent power is 17.56 pW Hz−1/2, which rivals commercially thermal-based photodetectors. Our device has already shown capabilities of large-area imaging, fast speed, and high signal-to-noise ratio, which can be rendered as an important step for exploring topological semimetal optoelectronics.

Non-destructive Testing and Geophysical Exploration

It is important to evaluate materials' strength and damage state in material mechanics. A series of inspection techniques called non-destructive testing is used to examine the state of such materials non-destructively. Non-destructive testing is an inspection technique that examines harmful damage to the interior or surface of an object without destroying the object. It can be broadly classified into methods to detect internal flaws by injecting radiation or ultrasonic waves into the object and methods to detect surface flaws by passing an electric current or magnetic flux near the surface. Non-invasive inspection is a method similar to non-destructive testing—however, non-invasive inspection targets humans, not objects. Non-destructive testing is used for our safety and security, and non-invasive testing is used for our health. Although non-destructive testing and non-invasive inspection are not directly related to geophysical exploration, they share many of the same underlying principles. Geophysical exploration targets subsurface structures, including underground resources such as oil, natural gas, and metal deposits, and is used for our wealth and comfort. Geophysical exploration can be thought of as an inspection technology for the subsurface. In this paper, geophysical exploration for the exploration of subsurface structures and resources is reviewed, and its relevance to nondestructive testing for material mechanics is explained. This paper provides an overview of non-destructive testing and geophysical exploration concerning the mechanics of materials. While non-destructive testing focuses only on flaws within a material, geophysical exploration focuses on the physical properties of the material as a whole, which may be useful for investigating material heterogeneity. I hope this paper has stimulated your interest in non-destructive testing and geophysical exploration.

A Computer-Aided Inspection System to Predict Quality Characteristics in Food Technology

Physicochemical and sensory analyses are commonly used to determine the quality characteristics of food samples in Food Industries. These methods are tedious, laborious, produce chemical residues, and involve the destruction of the samples. For the meat industries, this work proposes a non-invasive and non-destructive computer-aided inspection system, based on computer vision and ensemble machine learning techniques. The paper presents all the possibilities for the development of the system, making an exhaustive comparison of different algorithms used to extract features from the images of the samples, and various machine learning approaches, studying up to 6160 different models, and selecting the top 110 for the ensemble proposal. The system determines all the physicochemical, textural, and sensory quality characteristics of pork and beef loins in four meat states (fresh, thawed, cooked, and cured) with good precision, being a real alternative to the usual methods for the Food Industry.

Activatable NIR-II organic fluorescent probes for bioimaging.

NIR-II imaging is developed rapidly for noninvasive deep tissue inspection with high spatio-temporal resolution, taking advantage of diminished autofluorescence and light attenuation. Activatable NIR‐II fluorescence probes are widely developed to report pathological changes with accurate targeting, among which organic fluorescent probes achieve significant progress. Furthermore, the activatable NIR‐II fluorescent probes exhibited appealing characteristics like tunable physicochemical and optical properties, easy processability, and excellent biocompatibility. In the present review, we highlight the advances of activatable NIR-II fluorescence probes in design, synthesis and applications for imaging pathological changes like reactive oxygen species (ROS), reactive nitrogen species (RNS), reactive sulfur species (RSS), pH, hypoxia, viscosity as well as abnormally expressed enzymes. This non-invasive optical imaging modality shows a promising prospect in targeting the pathological site and is envisioned for potential clinical translation.

Virtual unrolling technology based on terahertz computed tomography

Due to the shape diversity and the occlusion problem, non-invasive inspection of cultural relic with special-shaped structures has always been the bottleneck of the existing imaging technology. We propose a virtual unrolling technique that can extract content from structures similar to folded paper and scroll, exploiting the three-dimensional imaging capability provided by terahertz computed tomography (THz CT). The method performs THz CT imaging on the object and obtains several slice images of its cross section. Considering the morphological properties of the slice image, the cross-sectional profile of the object is obtained by an improved single-pixel ridgeline extraction algorithm after suppressing the severe metal artifact on the slice images with our segmentation and inpainting-based scheme. And then a match-graft approach based on dynamic exemplar (MGDE) is developed to stitch lines of different layers into the final image. To illustrate, the occluding text content is successfully extracted from a mimic oil painting scroll samples with a thickness of sub-wavelength level. The method makes it possible for THz non-destructive inspection of similar structure that widely exist in industry, security, and especially heritage conservation.