Image Database Research Articles

A hybrid thyroid tumor type classification system using feature fusion, multilayer perceptron and bonobo optimization.

Thyroid tumor is considered to be a very rare form of cancer. But recent researches and surveys highlight the fact that it is becoming prevalent these days because of various factors. This paper proposes a novel hybrid classification system that is able to identify and classify the above said four different types of thyroid tumors using high end artificial intelligence techniques. The input data set is obtained from Digital Database of Thyroid Ultrasound Images through Kaggle repository and augmented for achieving a better classification performance using data warping mechanisms like flipping, rotation, cropping, scaling, and shifting. The input data after augmentation goes through preprocessing with the help of bilateral filter and is contrast enhanced using dynamic histogram equalization. The ultrasound images are then segmented using SegNet algorithm of convolutional neural network. The features needed for thyroid tumor classification are obtained from two different algorithms called CapsuleNet and EfficientNetB2 and both the features are fused together. This process of feature fusion is carried out to heighten the accuracy of classification. A Multilayer Perceptron Classifier is used for classification and Bonobo optimizer is employed for optimizing the results produced. The classification performance of the proposed model is weighted using metrics like accuracy, sensitivity, specificity, F1-score, and Matthew's correlation coefficient. It can be observed from the results that the proposed multilayer perceptron based thyroid tumor type classification system works in an efficient manner than the existing classifiers like CANFES, Spatial Fuzzy C means, Deep Belief Networks, Thynet and Generative adversarial network and Long Short-Term memory.

Towards the mechanical characterisation of unruptured intracranial aneurysms: Numerical modelling of interactions between a deformation device and the aneurysm wall

Intracranial aneurysm is a critical pathology related to the arterial wall deterioration. This work is an essential aspect of a large scale project aimed at providing clinicians with a non-invasive patient-specific decision support tool regarding the rupture risk assessment. A machine learning algorithm links the aneurysm shape observed and a database of UIA clinical images associated with in vivo wall mechanical properties and rupture characterisation. The database constitution is derived from a device prototype coupled with medical imaging. It provides the mechanical characterisation of the aneurysm from the wall deformation obtained by inverse analysis based on the variation of luminal volume. Before performing in vivo tests of the device on small animals, a numerical model was built to quantify the device’s impact on the aneurysm wall under natural blood flow conditions. As the clinician will never be able to precisely situate the device, several locations were considered. In preparation for the inverse analysis procedure, artery material laws of increasing complexity were studied (linear elastic, hyper elastic Fung-like).Considering all the device locations and material laws, the device induced relative displacements to the Systole peak (worst case scenario with the highest mechanical stimulus linked to the blood flow) ranging from 375 μm to 1.28 mm. The variation of luminal volume associated with the displacements was between 0.95 % and 4.3 % compared to the initial Systole volume of the aneurysm. Significant increase of the relative displacements and volume variations were found with the study of different cardiac cycle moments between the blood flow alone and the device application. For forthcoming animal model studies, Spectral Photon CT Counting, with a minimum spatial resolution of 250 μm, was selected as the clinical imaging technique. Based on this preliminary study, the displacements and associated volume variations (baseline for inverse analyse), should be observable and exploitable.

Comprehensive Analysis of the Expression of Cell Adhesion Molecules Genes in Hepatocellular Carcinoma and their Prognosis, and Biological Significance.

Collagen-related cell adhesion molecules (CAMs) are a major component of the extracellular matrix (ECM) and often accumulate in the liver during chronic liver disease or hepatocellular carcinoma (HCC). In this study we identified several promising collagens related to CAMs that may be of clinical use for the diagnosis and prognosis of HCC. We obtained multi-omics data including RNA sequencing (RNA-Seq) data, microarray data, proteomic data from the TCGA, GEO databases, GTEx, and NODE. Bioinformatics analyses were then performed to investigate correlations between the expression patterns of significant genes and HCC. Tumor tissue and para-cancerous tissue samples from HCC patients were also used to validate the results using RT-PCR. A literature research and LASSO-COX analysis identified three significant collagen-related CAM genes: SERPINH1, DCN, and ITGB1. Immunohistochemistry images in the Human Protein Atlas Project database showed that SERPINH1 and ITGB1 proteins were moderately or highly expressed in HCC tumor tissues compared to para-cancerous tissue, whereas DCN expression was lower in HCC tumor tissue. These results were validated by RT-PCR. Low- and high-risk groups of HCC patients were distinguished by the logistic panel in the TCGA database. These showed significantly different prognosis, clinicopathological features, and immune cell infiltration. Logistic regression was used to construct predictive models based on the individual expression levels of DCN, SERPINH1, and ITGB1. These showed highly accurate diagnostic ability (AUC = 0.987). The current findings suggest that the collagen-related CAMs DCN, SERPINH1, and ITGB1 may be potential therapeutic targets in HCC. Logistic panels of DCN, SERPINH1 and ITGB1 could serve as non-invasive and effective diagnostic biomarkers for HCC. Identifier: NCT03189992. Registered on June 4, 2017. Retrospectively registered (https://clinicaltrials.gov/).

New More Generic and Inclusive Regression Formulae for the Estimation of Stature from Long Bone Lengths in Children

Existing child stature estimation methods have a number of disadvantages. This paper addresses some of these limitations by developing regression-based stature estimation formulae that are more generic and inclusive. A sample of 142 individuals under 12 years of age from the Hamann—Todd Human Osteological Collection and the New Mexico Decedent Images Database were used to generate five least squares linear regression formulae to estimate stature from the diaphyseal length of long bones. All models showed excellent fits to the data (R2 close to or at 0.98), and internal validation confirmed the stability and accuracy of model parameters. External validation was performed using a sample of 14 individuals from the Lisbon Collection and the Victoria Institute of Forensic Medicine. Overall, the humerus provides the most accurate estimate of stature, but the femur and tibia showed the greatest coverage. These formulae can be used in a variety of contexts and are not dependent on group affiliation, including sex.

Artificial Intelligence Versus Human Focus Group Rating of Facial Attractiveness.

Background: Many open-access artificial intelligence (AI)-based websites that rate facial attractiveness are available, but none have been compared with human focus group outcomes. Objective: To compare human and AI-based websites scoring of facial attractiveness of adult female white faces. Methods: A 40-photograph database of AI-generated adult, white, female, expressionless, and frontal-view facial images were scored by otolaryngology residents and five AI-based facial rating websites: prettyscale.com, attractivenesstest.com, face-score.com/en, hotchat3000.com, and beautyscoretest.com. Sample t-test and bivariate correlation were performed for statistical analyses. Results: The focus group of 24 otolaryngology residents consisted of 62.5% males and 58.3% white participants. There was a strong positive correlation between average human score and average AI score for each photo (Pearson's correlation 0.84, p < 0.01). The average human raters' scores were significantly lower than the average AI scores (5.0 ± 1.8 vs. 6.9 ± 0.9, p < 0.01). Thirty images (75.0%) had statistically higher scores from the AI websites versus the focus group. On correlation analysis, all AI-based websites individually had scores that positively correlate with the human scores (all p < 0.05). Conclusion: AI-based websites and human focus-group scoring of facial attractiveness of adult white female faces were significantly correlated with the AI ratings biased toward higher values, encouraging their cautious utilization in future research.

Triplet-constrained deep hashing for chest X-ray image retrieval in COVID-19 assessment

Radiology images of the chest, such as computer tomography scans and X-rays, have been prominently used in computer-aided COVID-19 analysis. Learning-based radiology image retrieval has attracted increasing attention recently, which generally involves image feature extraction and finding matches in extensive image databases based on query images. Many deep hashing methods have been developed for chest radiology image search due to the high efficiency of retrieval using hash codes. However, they often overlook the complex triple associations between images; that is, images belonging to the same category tend to share similar characteristics and vice versa. To this end, we develop a triplet-constrained deep hashing (TCDH) framework for chest radiology image retrieval to facilitate automated analysis of COVID-19. The TCDH consists of two phases, including (a) feature extraction and (b) image retrieval. For feature extraction, we have introduced a triplet constraint and an image reconstruction task to enhance discriminative ability of learned features, and these features are then converted into binary hash codes to capture semantic information. Specifically, the triplet constraint is designed to pull closer samples within the same category and push apart samples from different categories. Additionally, an auxiliary image reconstruction task is employed during feature extraction to help effectively capture anatomical structures of images. For image retrieval, we utilize learned hash codes to conduct searches for medical images. Extensive experiments on 30,386 chest X-ray images demonstrate the superiority of the proposed method over several state-of-the-art approaches in automated image search. The code is now available online.

Predictive cues elicit a liminal confirmation bias in the moral evaluation of real-world images.

Previous research suggested that predictive cues enhance the preference and reduce the response time for congruent targets during bivalent food evaluation, indicating a confirmation bias. Less is known about how prior processing affects subjective moral evaluation. Here, we used three different types of predictive cues to elicit directional vs. non-predictive prior processing and then asked the participants to perform moral evaluations on a continuous scale from -10 ("very immoral") to +10 ("very moral") with a diverse set of real-world images. Our experimental image database balanced the morality of image content and the volatility of the ratings based on the means and standard deviations in a preliminary study. Ratings, response times, and gaze positions were measured to examine the effects of predictive cues on the moral evaluation of real-world images. We found that the moral ratings were in line with the expectations induced by the cues. Compared to the non-predictive condition, the moral evaluation in the directional conditions was more polarized. For neutral images, the predictive cues tilted the evaluations to positive vs. negative, indicating a decisive liminal influence. High-volatility images were impacted more than low-volatility images in ratings as well as response times. Furthermore, the gaze positions during the interval between the predictive cue and the image showed a spatial displacement in line with the cue instruction, indicating a response bias. Together, the results show that predictive cues elicit a liminal confirmation bias in moral image evaluation, much in the same way as in bivalent food evaluation.

A124 A SYSTEMATIC REVIEW OF THE EFFICACY OF ARTIFICIAL INTELLIGENCE IN IDENTIFYING BARRETT'S ESOPHAGUS NEOPLASIA

Abstract Background Barrett’s Esophagus (BE) is a known precursor for esophageal adenocarcinoma and requires frequent surveillance with esophagogastroduodenoscopy. Due to tumour heterogeneity and logistical demands on endoscopists, identification of BE dysplasia is difficult and random biopsies are riddled with sampling error. Artificial Intelligence (AI), in the form of computer-aided detection, has entered the endoscopic realm to improve BE dysplasia detection. This systematic review aims to evaluate its efficacy in BE screening. Aims To survey the literature regarding the efficacy of machine learning tools in identifying BE dysplasia. The primary outcome was recognition of BE from a database of endoscopic images with histopathologic correlation utilizing a machine learning algorithm, with sensitivity and specificity reported. Methods Using the PRISMA framework, MEDLINE, EMBASE and Compendex databases were searched from inception to Sept 1, 2023. Of 1915 articles identified, 35 were selected for full-text review. Two reviewers, JB and JK, independently completed the literature review and discrepancies were reviewed by the PI. After applying inclusion and exclusion criteria, 20 studies were included in the systematic review. The quality of studies was assessed using the Newcastle-Ottawa Scale. Inclusion Criteria: -Must include Barrett's esophagus and / or EAC (esophageal adenocarcinoma) -Must include novel research (not a systematic review or MA) -Requires use of endoscopic images -English only, full text manuscripts Exclusion Criteria: -No prior surgery (esophagectomy) -Does not include esophageal squamous cell carcinoma Results Of the 20 articles selected, seven were published after 2021. All studies utilized a machine learning algorithm to aid in identification of BE dysplasia. Various imaging modalities were used, including white light imaging, narrow-band imaging, or volumetric laser endomicroscopy. A total of 3,886 patients were included with 5,605 images. Sensitivity ranged from 72 – 100%, specificity ranged from 64 – 94%. The overall quality of studies included was low. Conclusions Surveillance of BE dysplasia remains a difficult and time-intensive task. Computer-aided detection of BE dysplasia demonstrates strong performance independent of the machine learning algorithm or imaging modality. Meta-analyses are required to illustrate heterogeneity and power to bolster these preliminary findings. Funding Agencies None

RASNet: Renal automatic segmentation using an improved U-Net with multi-scale perception and attention unit

For the treatment of renal disease, the application of radioactive equipment has become one of the important methods. Accurate segmentation of renal contour plays an important role in clinical diagnosis. However, manual renal contour drawing is not only inefficient but also prone to inaccurate outlining results due to different manual proficiency and fatigue caused by long-term work. There is little research on automatic renal segmentation with renal dynamic imaging. To address this issue, an improved model based on a deep neural network called Renal Automatic Segmentation Network (RASNet) is proposed, to aid in the automatic segmentation of renal contours. Besides, a multi-scale spatial perception module and a decoding module with attention connection are introduced to enrich the semantic information and further improve the accuracy of network segmentation. Extensive experiments were conducted on a renal dynamic medical image database established in this paper. Analysis results show the superiority of the proposed RASNet to several existing segmentation frameworks.

Identification of Panoramic Photographic Image Composition Using Fuzzy Rules.

Making panoramic images has gradually become an essential function inside personal intelligent devices because panoramic images can provide broader and richer content than typical images. However, the techniques to classify the types of panoramic images are still deficient. This paper presents novel approaches for classifying the photographic composition of panoramic images into five types using fuzzy rules. A test database with 168 panoramic images was collected from the Internet. After analyzing the panoramic image database, the proposed feature model defined a set of photographic compositions. Then, the panoramic image was identified by using the proposed feature vector. An algorithm based on fuzzy rules is also proposed to match the identification results with that of human experts. The experimental results show that the proposed methods have demonstrated performance with high accuracy and this can be used for related applications in the future.

UC-stack: a deep learning computer automatic detection system for diabetic retinopathy classification.

Object. The existing diagnostic paradigm for diabetic retinopathy (DR) greatly relies on subjective assessments by medical practitioners utilizing optical imaging, introducing susceptibility to individual interpretation. This work presents a novel system for the early detection and grading of DR, providing an automated alternative to the manual examination.Approach. First, we use advanced image preprocessing techniques, specifically contrast-limited adaptive histogram equalization and Gaussian filtering, with the goal of enhancing image quality and module learning capabilities. Second, a deep learning-based automatic detection system is developed. The system consists of a feature segmentation module, a deep learning feature extraction module, and an ensemble classification module. The feature segmentation module accomplishes vascular segmentation, the deep learning feature extraction module realizes the global feature and local feature extraction of retinopathy images, and the ensemble module performs the diagnosis and classification of DR for the extracted features. Lastly, nine performance evaluation metrics are applied to assess the quality of the model's performance.Main results. Extensive experiments are conducted on four retinal image databases (APTOS 2019, Messidor, DDR, and EyePACS). The proposed method demonstrates promising performance in the binary and multi-classification tasks for DR, evaluated through nine indicators, including AUC and quadratic weighted Kappa score. The system shows the best performance in the comparison of three segmentation methods, two convolutional neural network architecture models, four Swin Transformer structures, and the latest literature methods.Significance. In contrast to existing methods, our system demonstrates superior performance across multiple indicators, enabling accurate screening of DR and providing valuable support to clinicians in the diagnostic process. Our automated approach minimizes the reliance on subjective assessments, contributing to more consistent and reliable DR evaluations.

Oral fluorescein angiography in the diagnosis of paediatric optic nerve abnormalities.

FFA is a well-established investigation for the diagnosis of optic nerve abnormalities, requiring an intravenous cannula and extended imaging acquisition time. Cannulation can present a challenge in paediatric patients and whilst oral FFA has been used for decades, it has been limited by imaging technology and unconfirmed image acquisition timings. For years, we have used a modern ultra-widefield retinal camera, and established imaging time-points to demonstrate dynamic optic nerve head changes upon ingestion of fluorescein and collected a database of oFFA images for various presentations. Using an established protocol, optic nerve colour images were obtained, followed by oral administration of fluorescein dye. The optic nerves are then imaged at established intervals. An interpretation of oFFA tutorial was delivered to consultant ophthalmologists and trainees. Subsequently, these groups were assessed using a series of fifteen cases with the sensitivity and specificity of the test determined. Our study presents a series of images and descriptions for common optic nerve abnormalities in paediatric populations. In the interpretation part of the study, overall sensitivity of 76.8% in the consultant group vs 63.3% in the combined consultant + trainees and specificity of 87.5% vs 68.4% in the combined group. This is the first study that describes characteristic features of several common, and serious, optic nerve abnormalities specifically for oFFA interpretation in a paediatric population. It also highlights the rapid accumulation of oFFA interpretation skills in non-specialist consultant and trainee ophthalmologists such as to obtain a high diagnostic accuracy with high sensitivity and specificity.

IMPROVING ULTRASOUND IMAGE EDGE ENHANCEMENT WITH AADFP METHOD

Image processing is a constantly evolving field that is actively seeking innovative solutions to improve the quality and accuracy of image analysis. Smoothing the edges of ultrasound images using filters is a common processing method that reduces noise and improves image clarity. The choice of filtering method and its parameters depends on the specific clinical or research requirements and the nature of the ultrasound images being processed. However, traditional image processing approaches, especially smoothing, have their limitations. An example is medical imaging, where the preservation of clear anatomical image structures is of paramount importance. Excessive smoothing in such cases leads to the erasure of important anatomical details, potentially affecting diagnostic accuracy. In "computer-aided imaging", excessive smoothing of the edges of the investigated objects may prevent their accurate recognition, which is particularly important when the object is characterised by a variety of features. Due to the limitations of traditional methods, the introduction of better approaches is required to address this problem. The AADFP (Adaptive Anisotropic Diffusion with Feature Priority) method is a technique for improving the quality of ultrasound images, which allows a new approach to their processing, by simultaneously smoothing edges and reducing noise, while preserving important anatomical features. The method is based on adaptive anisotropic diffusion, which adjusts the diffusion process depending on image filling, combined with the integration of features previously extracted from a database of annotated ultrasound images. The use of AADFP allows to significantly improve image quality by selectively smoothing out areas with noise while preserving the main structures in the image. Keywords: Ultrasound image processing, AADFP Method, Image Processing, Medical Imaging, Filtering methods, Feature recognition.

Octonion-based transform moments for innovative stereo image classification with deep learning

Recent advances in imaging technologies have led to a significant increase in the adoption of stereoscopic images. However, despite this proliferation, in-depth research into the complex analysis of the visual content of these stereoscopic images is still relatively rare. The advent of stereoscopic imaging has brought a new dimension to visual content. These images offer a higher level of visual detail, making them increasingly common in a variety of fields, including medicine and industrial applications. However, exploiting the full potential of stereoscopic images requires a deeper understanding. By exploiting the capabilities of octonion moments and the power of artificial intelligence, we aim to break new ground by introducing a novel method for classifying stereoscopic images. The proposed method is divided into two key stages: The first stage involves data preprocessing, during which we strive to construct a balanced database divided into three distinct categories. In addition, we extract the stable Octonion Krawtchouk moments (SOKM) for each image, leading to a database of moment images with dimensions of 128 × 128 × 1. In the second step, we train a convolutional neural network (CNN) model using this database, with the aim of discriminating between different categories. Standard measures such as precision, accuracy, recall, F1 score, and ROC curves are used to assess the effectiveness of our method. These measures provide a quantitative assessment of the performance of our object classification approach for stereoscopic images.

Leveraging coverless image steganography to hide secret information by generating anime characters using GAN

There has been a growing need for secure communication in recent years, particularly in the digital realm. Researchers have developed various text-hiding methods to address this need, but these methods often suffer from limitations such as low embedding capacity or high embedding distortion. However, current methods for information hiding require a large image database or have a low capacity for hiding information, which makes them impractical. To address these issues, we propose a coverless information-hiding method that generates anime characters through generative adversarial networks (GANs). This method converts secret information into an attribute label set for anime characters and uses the label set to generate anime characters directly. The quality of the generated anime characters was improved by the super-resolution GAN (SRGAN) model. The resulting images were used to communicate secret information on the digital channel. Numerous experiments were conducted to evaluate the performance of the proposed framework, including hiding capacity, image clarity, robustness and security. Results showed that the proposed framework outperforms existing text-hiding methods in terms of hiding capacity and robustness while maintaining image clarity and computation time. In conclusion, our proposed framework provides a secure and efficient solution for text encryption and decryption in feasible computation time using anime characters generated by a GAN. The framework has a high embedding capacity and low embedding distortion, making it a promising solution for secure communication in the digital world.

Classification Prediction of Alzheimer's Disease and Vascular Dementia Using Physiological Data and ECD SPECT Images.

Alzheimer's disease (AD) and vascular dementia (VaD) are the two most common forms of dementia. However, their neuropsychological and pathological features often overlap, making it difficult to distinguish between AD and VaD. In addition to clinical consultation and laboratory examinations, clinical dementia diagnosis in Taiwan will also include Tc-99m-ECD SPECT imaging examination. Through machine learning and deep learning technology, we explored the feasibility of using the above clinical practice data to distinguish AD and VaD. We used the physiological data (33 features) and Tc-99m-ECD SPECT images of 112 AD patients and 85 VaD patients in the Taiwanese Nuclear Medicine Brain Image Database to train the classification model. The results, after filtering by the number of SVM RFE 5-fold features, show that the average accuracy of physiological data in distinguishing AD/VaD is 81.22% and the AUC is 0.836; the average accuracy of training images using the Inception V3 model is 85% and the AUC is 0.95. Finally, Grad-CAM heatmap was used to visualize the areas of concern of the model and compared with the SPM analysis method to further understand the differences. This research method can quickly use machine learning and deep learning models to automatically extract image features based on a small amount of general clinical data to objectively distinguish AD and VaD.

Postoperative accurate pain assessment of children and artificial intelligence: A medical hypothesis and planned study.

Although the pediatric perioperative pain management has been improved in recent years, the valid and reliable pain assessment tool in perioperative period of children remains a challenging task. Pediatric perioperative pain management is intractable not only because children cannot express their emotions accurately and objectively due to their inability to describe physiological characteristics of feeling which are different from those of adults, but also because there is a lack of effective and specific assessment tool for children. In addition, exposure to repeated painful stimuli early in life is known to have short and long-term adverse sequelae. The short-term sequelae can induce a series of neurological, endocrine, cardiovascular system stress related to psychological trauma, while long-term sequelae may alter brain maturation process, which can lead to impair neurodevelopmental, behavioral, and cognitive function. Children's facial expressions largely reflect the degree of pain, which has led to the developing of a number of pain scoring tools that will help improve the quality of pain management in children if they are continually studied in depth. The artificial intelligence (AI) technology represented by machine learning has reached an unprecedented level in image processing of deep facial models through deep convolutional neural networks, which can effectively identify and systematically analyze various subtle features of children's facial expressions. Based on the construction of a large database of images of facial expressions in children with perioperative pain, this study proposes to develop and apply automatic facial pain expression recognition software using AI technology. The study aims to improve the postoperative pain management for pediatric population and the short-term and long-term quality of life for pediatric patients after operational event.

An efficient multimodal sentiment analysis in social media using hybrid optimal multi-scale residual attention network

Sentiment analysis is a key component of many social media analysis projects. Additionally, prior research has concentrated on a single modality in particular, such as text descriptions for visual information. In contrast to standard image databases, social images frequently connect to one another, making sentiment analysis challenging. The majority of methods now in use consider different images individually, rendering them useless for interrelated images. We proposed a hybrid Arithmetic Optimization Algorithm- Hunger Games Search (AOA-HGS)-optimized Ensemble Multi-scale Residual Attention Network (EMRA-Net) technique in this paper to explore the modal correlations including texts, audio, social links, and video for more effective multimodal sentiment analysis. The hybrid AOA-HGS technique learns complementary and comprehensive features. The EMRA-Net uses two segments, including Ensemble Attention CNN (EA-CNN) and Three-scale Residual Attention Convolutional Neural Network (TRA-CNN), to analyze the multimodal sentiments. The loss of spatial domain image texture features can be reduced by adding the Wavelet transform to TRA-CNN. The feature-level fusion technique known as EA-CNN is used to combine visual, audio, and textual information. The proposed method performs significantly better than the existing multimodel sentimental analysis techniques of HALCB, HDF, and MMLatch when evaluated using the Multimodal Emotion Lines Dataset (MELD) and EmoryNLP datasets. Also, even though the size of the training set varies, the proposed method outperformed other techniques in terms of recall, accuracy, F score, and precision and takes less time to compute in both datasets.

A Digital Survey Approach for Large-Scale Landscape Heritage Resource Exploration: Auxiliary Beacons, the Uncharted Signal Structure of the Great Wall in China

Following the completion of the Great Wall Resource Survey in 2012, numerous landscape heritage resources along the Great Wall remained undiscovered, highlighting the limitations of conventional survey methods. This study aimed to conduct in-depth investigations of Great Wall signal sites through digital fieldwork methods, unveiling a crucial signaling structure—the auxiliary beacon—and presenting genuine historical scenes of the Great Wall signal network. Through the retrieval of the image database of the entire Great Wall and the utilization of UAVs (drones) for low-altitude remote sensing surveys, 252 auxiliary beacon sites were identified in diverse environments (e.g., deserts, mountains, plains) in Xinjiang, Gansu, Inner Mongolia, Qinghai, Ningxia, and other 10 regions. These case studies enable the categorization of layout types and the proposal of reconstruction hypotheses for the signal network of the Great Wall of China. The findings demonstrate that the beacon fire signals are not lit on the beacon tower tops, but through the ignition of various signals by auxiliary beacons, expressing pre-arranged information. Beacon towers and auxiliary beacons together form an efficient signal network along the Great Wall. This study explores how to use digital survey methods to unearth unknown landscape heritage resources of the Great Wall, enhancing the accuracy of observation for cross-regional and large-scale cultural heritage.

Estimation of the subsurface electromagnetic velocity distribution from diffraction hyperbolas by means of a novel automated picking procedure: Theory and application to glaciological ground-penetrating radar data sets

We have developed an auto-picking algorithm that is designed to automatically detect subsurface diffractors within ground-penetrating radar (GPR) data sets, to accurately track the hyperbolic diffractions originating from the identified scatterers, and to recover the subsurface electromagnetic (EM) velocity distribution, among other possible analyses. Our procedure presents several advantages with respect to other commonly applied diffraction tracking techniques because it can be applied with minimal signal preprocessing, thus making it more versatile and adaptable to local conditions; it requires only limited input from the interpreter in the form of a few thresholds for the tracking parameters, thus making the results more objective; and it does not involve pretraining as opposed to machine-learning algorithms, thus removing the need to gather a large and comprehensive image database of all possible subsurface situations, which would not necessarily be limited to only examples of diffractions. The presented algorithm starts by identifying those signals that are likely to belong to diffraction apexes, which are then used as initial seeds by the auto-tracking process. The horizontal search window used during the auto-tracking process is locally adapted through a rough preliminary estimate of the size of each diffraction. In addition, multiple seeds within the same apex can produce several acceptable hyperbolas tracking the same diffraction phase. The algorithm thus selects the best-fitting ones by assessing several signal attributes while also removing redundant hyperbolas and the expected false positives. The algorithm is applied to two glaciological GPR profiles, and it is able to accurately track the vast majority of the recorded diffractions, with very few false positives and negatives. This produces a statistically sound EM velocity distribution, which was used to assess the state of the surveyed alpine glacier.