Automatic Identification Model Research Articles

The mining of China's policies against COVID-19 based on a policy target and tool co-evolution framework

Mining all COVID-19 policies issued by China can provide valuable lessons for both China and other countries in future pandemic control efforts. In this paper, we introduce a novel framework for mining the co-evolution of policy targets and policy tools. We employ bibliometric methods, text mining, and network analysis to explore the entire evolution of China's COVID-19 policies. Examining 1154 central government policies, (a) we extract policy targets from each policy, uncovering their evolution across different stages of the pandemic; (b) propose to identify the policy tool used in each policy unit by integrating an automatic identification model and active learning. We also reveal the categorical structure of these tools; (c) characterize the co-evolution pattern between policy targets and policy tools, shedding light on their dynamic relationship. Our findings indicate that policy targets have shifted across various stages, revealing unique characteristics in China's COVID-19 prevention and control efforts. Notably, there is a self-paradox between prevention measures and economic development. We identify the inadequateness in the distribution and utilization of policy tools. Ensuring the alignment of policy targets with appropriate tools is crucial. This synchronization and co-evolution between policy targets and tools are essential for enhancing the functional approach to policy implementation. This paper is the first systematic mining and review about the COVID-19 policies issued by the Chinese government, and our policy target and tool co-evolution mining framework provides a new quantitative framework for policy mining, especially an improved large language model and active learning theory are integrated to identify the policy tools automatically.

EEGDepressionNet: A Novel Self Attention-Based Gated DenseNet With Hybrid Heuristic Adopted Mental Depression Detection Model Using EEG Signals.

World Health Organization (WHO) has identified depression as a significant contributor to global disability, creating a complex thread in both public and private health. Electroencephalogram (EEG) can accurately reveal the working condition of the human brain, and it is considered an effective tool for analyzing depression. However, manual depression detection using EEG signals is time-consuming and tedious. To address this, fully automatic depression identification models have been designed using EEG signals to assist clinicians. In this study, we propose a novel automated deep learning-based depression detection system using EEG signals. The required EEG signals are gathered from publicly available databases, and three sets of features are extracted from the original EEG signal. Firstly, spectrogram images are generated from the original EEG signal, and 3-dimensional Convolutional Neural Networks (3D-CNN) are employed to extract deep features. Secondly, 1D-CNN is utilized to extract deep features from the collected EEG signal. Thirdly, spectral features are extracted from the collected EEG signal. Following feature extraction, optimal weights are fused with the three sets of features. The selection of optimal features is carried out using the developed Chaotic Owl Invasive Weed Search Optimization (COIWSO) algorithm. Subsequently, the fused features undergo analysis using the Self-Attention-based Gated Densenet (SA-GDensenet) for depression detection. The parameters within the detection network are optimized with the assistance of the same COIWSO. Finally, implementation results are analyzed in comparison to existing detection models. The experimentation findings of the developed model show 96% of accuracy. Throughout the empirical result, the findings of the developed model show better performance than traditional approaches.

Automatic recognition system for concrete cracks with support vector machine based on crack features

Cracks are a common problem in concrete surfaces. With the continuous optimization of machine vision-based inspection systems, effective crack detection and recognition is the core of the entire system. In this study, support vector machine (SVM) was used to distinguish cracks from other regions. To complete the recognition system of the SVM, a framework consisting of an image processing and recognition model was proposed. An algorithm combining the Prewitt operator with the Otsu threshold was proposed for image segmentation. The binary image processed by the new algorithm combined with mathematical morphology can result in a more complete crack zone and fewer interference regions. After the initial parameter extraction, most of the impurity areas were screened by preliminary discrimination, removing 99% of the impurities. This processing step ensured the balance and effectiveness of the samples. To establish an automatic identification model based on SVM with a radial basis function, compactness, occupancy rate, and length–width ratio were selected as input parameters after comparing these three features with all six features of the crack. The recognition accuracy of this system reaches 97.14%, demonstrating that the proposed method is effective and satisfies practical requirements.

Improved localization and segmentation of spinal bone metastases in MRI with nnUNet radiomics

ObjectiveVariability exists in the subjective delineation of tumor areas in MRI scans of patients with spinal bone metastases. This research aims to investigate the efficacy of the nnUNet radiomics model for automatic segmentation and identification of spinal bone metastases. MethodsA cohort of 118 patients diagnosed with spinal bone metastases at our institution between January 2020 and December 2023 was enrolled. They were randomly divided into a training set (n = 78) and a test set (n = 40). The nnUNet radiomics segmentation model was developed, employing manual delineations of tumor areas by physicians as the reference standard. Both methods were utilized to compute tumor area measurements, and the segmentation performance and consistency of the nnUNet model were assessed. ResultsThe nnUNet model demonstrated effective localization and segmentation of metastases, including smaller lesions. The Dice coefficients for the training and test sets were 0.926 and 0.824, respectively. Within the test set, the Dice coefficients for lumbar and thoracic vertebrae were 0.838 and 0.785, respectively. Strong linear correlation was observed between the nnUNet model segmentation and physician-delineated tumor areas in 40 patients (R2 = 0.998, P < 0.001). ConclusionsThe nnUNet model exhibits efficacy in automatically localizing and segmenting spinal bone metastases in MRI scans.

Deep Learning Model for Automatic Identification and Classification of Distal Radius Fracture.

Distal radius fracture (DRF) is one of the most common types of wrist fractures. We aimed to construct a model for the automatic segmentation of wrist radiographs using a deep learning approach and further perform automatic identification and classification of DRF. A total of 2240 participants with anteroposterior wrist radiographs from one hospital between January 2015 and October 2021 were included. The outcomes were automatic segmentation of wrist radiographs, identification of DRF, and classification of DRF (type A, type B, type C). The Unet model and Fast-RCNN model were used for automatic segmentation. The DenseNet121 model and ResNet50 model were applied to DRF identification of DRF. The DenseNet121 model, ResNet50 model, VGG-19 model, and InceptionV3 model were used for DRF classification. The area under the curve (AUC) with 95% confidence interval (CI), accuracy, precision, and F1-score was utilized to assess the effectiveness of the identification and classification models. Of these 2240 participants, 1440 (64.3%) had DRF, of which 701 (48.7%) were type A, 278 (19.3%) were type B, and 461 (32.0%) were type C. Both the Unet model and the Fast-RCNN model showed good segmentation of wrist radiographs. For DRF identification, the AUCs of the DenseNet121 model and the ResNet50 model in the testing set were 0.941 (95%CI: 0.926-0.965) and 0.936 (95%CI: 0.913-0.955), respectively. The AUCs of the DenseNet121 model (testing set) for classification type A, type B, and type C were 0.96, 0.96, and 0.96, respectively. The DenseNet121 model may provide clinicians with a tool for interpreting wrist radiographs.

AI-based model for automatic identification of multiple sclerosis based on enhanced sea-horse optimizer and MRI scans

This study aims to develop an AI-enhanced methodology for the expedited and accurate diagnosis of Multiple Sclerosis (MS), a chronic disease affecting the central nervous system leading to progressive impairment. Traditional diagnostic methods are slow and require substantial expertise, underscoring the need for innovative solutions. Our approach involves two phases: initially, extracting features from brain MRI images using first-order histograms, the gray level co-occurrence matrix, and local binary patterns. A unique feature selection technique combining the Sine Cosine Algorithm with the Sea-horse Optimizer is then employed to identify the most significant features. Utilizing the eHealth lab dataset, which includes images from 38 MS patients (mean age 34.1 ± 10.5 years; 17 males, 21 females) and matched healthy controls, our model achieved a remarkable 97.97% detection accuracy using the k-nearest neighbors classifier. Further validation on a larger dataset containing 262 MS cases (199 females, 63 males; mean age 31.26 ± 10.34 years) and 163 healthy individuals (109 females, 54 males; mean age 32.35 ± 10.30 years) demonstrated a 92.94% accuracy for FLAIR images and 91.25% for T2-weighted images with the Random Forest classifier, outperforming existing MS detection methods. These results highlight the potential of the proposed technique as a clinical decision-making tool for the early identification and management of MS.

Pixel-Level Crack Identification for Bridge Concrete Structures Using Unmanned Aerial Vehicle Photography and Deep Learning

Traditional manual inspection technology has the problems of high risk, low efficiency, and being time-consuming in bridge safety management. The unmanned aerial vehicle (UAV)-based detection technology is widely used in bridge structure safety monitoring. However, the existing deep learning-based concrete crack identification method has great limitations in dealing with complex background and tiny cracks in bridge structures. To address these problems, this study designs a crack pixel-level high-performance segmentation model for bridge concrete cracks that is suitable for UAV detection scenarios using machine vision (MV) and deep learning (DL) algorithms. First, considering the high requirements for the computing performance of the MV-based model for UAV-based detection, the ResNet-18-based lightweight convolutional neural network is used to represent the traditional large-scale backbone network of the pyramid scene parsing network (PSPNet) to develop a high-performance crack automatic identification model. Then, considering that bridge concrete cracks have the characteristics of subtle shapes and complex backgrounds, the spatial position self-attention module is inserted into the PSPNet to improve its detection accuracy. A concrete bridge is used for the case study, and a dataset of cracks in bridge concrete structures collected by UAVs is constructed and used for model training. The experimental results show that the loss function of the developed method in the training process results in a smooth decline, and the developed algorithm achieves the evaluation indicators of 0.9008 precision, 0.8750 recall, 0.8820 accuracy, and 0.9012 IOU on the bridge concrete crack dataset, which are significantly higher than other state-of-the-art baseline methods. In addition, four common UAV bridge detection scenarios, including low light, complex crack forms, high background roughness, and complex background scenes, are used to further test the crack detection ability of the developed crack identification model. The experimental results show that the proposed crack identification method can effectively overcome interference and real-size pixel-level segmentation of crack morphology. In addition, it also achieved a detection efficiency of 35.04 FPS, which shows that the real-time detection ability of the method has good applicability in the UAV detection scene.

An automatic humor identification model with novel features from Berger’s typology and ensemble models

Humor identification in text is essential for natural language understanding, impacting human–computer interactions and emotion recognition. This study introduces a novel approach to automatic humor identification in text using ensemble learning techniques. The objective is to classify text into two categories: humor and not humor. This research delves into humor detection in customer reviews, focusing on specific domains, and leverages diverse text features, including novel features derived from Berger’s typology. State-of-the-art machine learning models, such as Support Vector Machine, Multilayer Perceptron, and Naïve Bayes, are employed. The study conducts an in-depth analysis of the Yelp review dataset, evaluating the performance of various ensemble learning methods. The proposed approach demonstrates exceptional results, achieving an 83.32% F-score with the Support Vector Machine classifier and an 85.68% accuracy using the stacking-based ensemble learning method with Random Forest on the Yelp Review dataset. Furthermore, this research includes an ablation study to assess the effectiveness of Berger’s novel typology-based features in humor identification. This research contributes to the advancement of humor identification in text and highlights the effectiveness of ensemble learning techniques, especially when incorporating novel features inspired by Berger’s typology.

GFSegNet: A multi-scale segmentation model for mining area ground fissures

Precise identification of ground fissures is of paramount importance for the safety and environmental management of coal mining areas. However, the surface environment in coal mining regions is complex, and, to date, the efficiency of artificial fissure detection has been relatively low. Therefore, we have proposed a ground fissure automatic identification model based on an encoder–decoder architecture known as the Ground Fissure Segmentation Network (GFSegNet). The encoder adopts a deep-shallow decoupled mode. The shallow network achieves spatial and spectral domain interaction by introducing adaptive Fourier convolution. The deep network adopts a hierarchical Transformer with an efficient self-attention mechanism for global modeling of fine-grained semantics. The decoder is designed as a multi-scale feature fusion structure embedded in pyramid pooling modules, aiming to efficiently utilize multi-scale ground fissure information. To advance the application of deep learning in ground fissure identification, we created a coal mining area ground fissure segmentation dataset from drone imagery, known as the mine ground fissure unmanned aerial vehicle dataset (MGF-UAV). On this dataset, the overall performance of GFSegNet surpasses the current leading segmentation models, and its reliability and generalization capabilities are further validated on additional datasets (Crack500, DeepCrack, CrackForest and ISPRS-Postdam). This research has brought expansion and innovation to the field of automatic ground fissure recognition in coal mining areas, offering new perspectives and methodologies for the application of deep learning techniques in this domain.

Research on automatic recognition radiomics algorithm for early sacroiliac arthritis based on sacroiliac MRI imaging

ObjectiveTo create an automated machine learning model using sacroiliac joint MRI imaging for early sacroiliac arthritis detection, aiming to enhance diagnostic accuracy.MethodsWe conducted a retrospective analysis involving 71 patients with early sacroiliac arthritis and 85 patients with normal sacroiliac joint MRI scans. Transverse T1WI and T2WI sequences were collected and subjected to radiomics analysis by two physicians. Patients were randomly divided into training and test groups at a 7:3 ratio. Initially, we extracted the region of interest on the sacroiliac joint surface using ITK-SNAP 3.6.0 software and extracted radiomic features. We retained features with an Intraclass Correlation Coefficient > 0.80, followed by filtering using max-relevance and min-redundancy (mRMR) and LASSO algorithms to establish an automatic identification model for sacroiliac joint surface injury. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was calculated. Model performance was assessed by accuracy, sensitivity, and specificity.ResultsWe evaluated model performance, achieving an AUC of 0.943 for the SVM-T1WI training group, with accuracy, sensitivity, and specificity values of 0.878, 0.836, and 0.943, respectively. The SVM-T1WI test group exhibited an AUC of 0.875, with corresponding accuracy, sensitivity, and specificity values of 0.909, 0.929, and 0.875, respectively. For the SVM-T2WI training group, the AUC was 0.975, with accuracy, sensitivity, and specificity values of 0.933, 0.889, and 0.750. The SVM-T2WI test group produced an AUC of 0.902, with accuracy, sensitivity, and specificity values of 0.864, 0.889, and 0.800. In the SVM-bimodal training group, we achieved an AUC of 0.974, with accuracy, sensitivity, and specificity values of 0.921, 0.889, and 0.971, respectively. The SVM-bimodal test group exhibited an AUC of 0.964, with accuracy, sensitivity, and specificity values of 0.955, 1.000, and 0.875, respectively.ConclusionThe radiomics-based detection model demonstrates excellent automatic identification performance for early sacroiliitis.

Sleep arousal detection for monitoring of sleep disorders using one-dimensional convolutional neural network-based U-Net and bio-signals

PurposeSleep arousal detection is an important factor to monitor the sleep disorder.Design/methodology/approachThus, a unique nth layer one-dimensional (1D) convolutional neural network-based U-Net model for automatic sleep arousal identification has been proposed.FindingsThe proposed method has achieved area under the precision–recall curve performance score of 0.498 and area under the receiver operating characteristics performance score of 0.946.Originality/valueNo other researchers have suggested U-Net-based detection of sleep arousal.Research limitations/implicationsFrom the experimental results, it has been found that U-Net performs better accuracy as compared to the state-of-the-art methods.Practical implicationsSleep arousal detection is an important factor to monitor the sleep disorder. Objective of the work is to detect the sleep arousal using different physiological channels of human body.Social implicationsIt will help in improving mental health by monitoring a person's sleep.

A Novel Convolutional Neural Network Model for Automatic Speaker Identification From Speech Signals

A Novel Convolutional Neural Network Model for Automatic Speaker Identification From Speech Signals

Automatic detection of ischemic necrotic sites in small intestinal tissue using hyperspectral imaging and transfer learning.

Acquiring large amounts of hyperspectral data of small intestinal tissue with real labels in the clinic is difficult, and the data shows inter-patient variability. Building an automatic identification model using a small dataset presents a crucial challenge in obtaining a strong generalization of the model. This study aimed to explore the performance of hyperspectral imaging and transfer learning techniques in the automatic identification of normal and ischemic necrotic sites in small intestinal tissue. Hyperspectral data of small intestinal tissues were collected from eight white rabbit samples. The transfer component analysis (TCA) method was performed to transfer learning on hyperspectral data between different samples and the variability of data distribution between samples was reduced. The results showed that the TCA transfer learning method improved the accuracy of the classification model with less training data. This study provided a reliable method for single-sample modelling to detect necrotic sites in small intestinal tissue .

MRI-based automatic identification and segmentation of extrahepatic cholangiocarcinoma using deep learning network

BackgroundAccurate identification of extrahepatic cholangiocarcinoma (ECC) from an image is challenging because of the small size and complex background structure. Therefore, considering the limitation of manual delineation, it’s necessary to develop automated identification and segmentation methods for ECC. The aim of this study was to develop a deep learning approach for automatic identification and segmentation of ECC using MRI.MethodsWe recruited 137 ECC patients from our hospital as the main dataset (C1) and an additional 40 patients from other hospitals as the external validation set (C2). All patients underwent axial T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Manual delineations were performed and served as the ground truth. Next, we used 3D VB-Net to establish single-mode automatic identification and segmentation models based on T1WI (model 1), T2WI (model 2), and DWI (model 3) in the training cohort (80% of C1), and compared them with the combined model (model 4). Subsequently, the generalization capability of the best models was evaluated using the testing set (20% of C1) and the external validation set (C2). Finally, the performance of the developed models was further evaluated.ResultsModel 3 showed the best identification performance in the training, testing, and external validation cohorts with success rates of 0.980, 0.786, and 0.725, respectively. Furthermore, model 3 yielded an average Dice similarity coefficient (DSC) of 0.922, 0.495, and 0.466 to segment ECC automatically in the training, testing, and external validation cohorts, respectively.ConclusionThe DWI-based model performed better in automatically identifying and segmenting ECC compared to T1WI and T2WI, which may guide clinical decisions and help determine prognosis.

Research on digital design and experience of urban landscape based on parametric model

Abstract In this paper, according to the characteristics of parametric landscape design, practical landscape architecture is selected for parameter and rule sets, and then the program calculation is established by parametric software to realize the digital design of urban landscapes. The parametric model of urban architectural design is designed for site factor indexing, construction, and management of space and form. The automatic identification model based on the building plan for the construction of building functions is carried out to generate candidate target areas and location refinement analysis, and the parametric generation of the urban landscape is optimized for design. Compared to the initial scheme, the economic and technical indicators increased the volume ratio by 11.2%, the building density by 17.3%, and the green area ratio by 3.6%. The three performance indicators 1/VG̅, CHIS̅ and 1/VB̅ of Rop are 8.5%, 35.6% and 20.8%, respectively.

Automatic identification of posteroanterior cephalometric landmarks using a novel deep learning algorithm: a comparative study with human experts

This study aimed to propose a fully automatic posteroanterior (PA) cephalometric landmark identification model using deep learning algorithms and compare its accuracy and reliability with those of expert human examiners. In total, 1032 PA cephalometric images were used for model training and validation. Two human expert examiners independently and manually identified 19 landmarks on 82 test set images. Similarly, the constructed artificial intelligence (AI) algorithm automatically identified the landmarks on the images. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the performance of the model. The performance of the model was comparable with that of the examiners. The MRE of the model was 1.87 ± 1.53 mm, and the SDR was 34.7%, 67.5%, and 91.5% within error ranges of < 1.0, < 2.0, and < 4.0 mm, respectively. The sphenoid points and mastoid processes had the lowest MRE and highest SDR in auto-identification; the condyle points had the highest MRE and lowest SDR. Comparable with human examiners, the fully automatic PA cephalometric landmark identification model showed promising accuracy and reliability and can help clinicians perform cephalometric analysis more efficiently while saving time and effort. Future advancements in AI could further improve the model accuracy and efficiency.

Automated model for identification on mastoid of temporal bone image

Mastoiditis occurs due to inflammation that can affect the structure of the mastoid bone. The mastoid bone consists of the mastoid air cell system (MACS) which protects the ear structures and regulates air pressure in the ear and has different sizes and characteristics, making it very difficult to identify precisely. This study aims to identify and find the right MACS size by developing an automatic identification model and obtaining the optimal threshold value in the segmentation process using the extended adaptive threshold (eAT) method. The research dataset uses computed tomography (CT)-scan images of 308 slices of 12 patients indicated for mastoiditis. The results of this study provide identification that has the right MACS accuracy and size. Overall, the optimal segmentation process obtained the smallest threshold value of 57 and the largest threshold value of 63, the smallest MACS size is 4.025 cm2 and the largest is 8.816 cm2 with an accuracy rate of 93.4%. The smaller MACS size indicates inflammation in the mastoid area and these patients require more intensive treatment.

Combining Deep Learning and Handcrafted Radiomics for Classification of Suspicious Lesions on Contrast-enhanced Mammograms.

Background Handcrafted radiomics and deep learning (DL) models individually achieve good performance in lesion classification (benign vs malignant) on contrast-enhanced mammography (CEM) images. Purpose To develop a comprehensive machine learning tool able to fully automatically identify, segment, and classify breast lesions on the basis of CEM images in recall patients. Materials and Methods CEM images and clinical data were retrospectively collected between 2013 and 2018 for 1601 recall patients at Maastricht UMC+ and 283 patients at Gustave Roussy Institute for external validation. Lesions with a known status (malignant or benign) were delineated by a research assistant overseen by an expert breast radiologist. Preprocessed low-energy and recombined images were used to train a DL model for automatic lesion identification, segmentation, and classification. A handcrafted radiomics model was also trained to classify both human- and DL-segmented lesions. Sensitivity for identification and the area under the receiver operating characteristic curve (AUC) for classification were compared between individual and combined models at the image and patient levels. Results After the exclusion of patients without suspicious lesions, the total number of patients included in the training, test, and validation data sets were 850 (mean age, 63 years ± 8 [SD]), 212 (62 years ± 8), and 279 (55 years ± 12), respectively. In the external data set, lesion identification sensitivity was 90% and 99% at the image and patient level, respectively, and the mean Dice coefficient was 0.71 and 0.80 at the image and patient level, respectively. Using manual segmentations, the combined DL and handcrafted radiomics classification model achieved the highest AUC (0.88 [95% CI: 0.86, 0.91]) (P < .05 except compared with DL, handcrafted radiomics, and clinical features model, where P = .90). Using DL-generated segmentations, the combined DL and handcrafted radiomics model showed the highest AUC (0.95 [95% CI: 0.94, 0.96]) (P < .05). Conclusion The DL model accurately identified and delineated suspicious lesions on CEM images, and the combined output of the DL and handcrafted radiomics models achieved good diagnostic performance. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bahl and Do in this issue.

An automatic identification system for citrus greening disease (Huanglongbing) using a YOLO convolutional neural network.

Huanglongbing (HLB), or citrus greening disease, has complex and variable symptoms, making its diagnosis almost entirely reliant on subjective experience, which results in a low diagnosis efficiency. To overcome this problem, we constructed and validated a deep learning (DL)-based method for detecting citrus HLB using YOLOv5l from digital images. Three models (Yolov5l-HLB1, Yolov5l-HLB2, and Yolov5l-HLB3) were developed using images of healthy and symptomatic citrus leaves acquired under a range of imaging conditions. The micro F1-scores of the Yolov5l-HLB2 model (85.19%) recognising five HLB symptoms (blotchy mottling, "red-nose" fruits, zinc-deficiency, vein yellowing, and uniform yellowing) in the images were higher than those of the other two models. The generalisation performance of Yolov5l-HLB2 was tested using test set images acquired under two photographic conditions (conditions B and C) that were different from that of the model training set condition (condition A). The results suggested that this model performed well at recognising the five HLB symptom images acquired under both conditions B and C, and yielded a micro F1-score of 84.64% and 85.84%, respectively. In addition, the detection performance of the Yolov5l-HLB2 model was better for experienced users than for inexperienced users. The PCR-positive rate of Candidatus Liberibacter asiaticus (CLas) detection (the causative pathogen for HLB) in the samples with five HLB symptoms as classified using the Yolov5l-HLB2 model was also compared with manual classification by experts. This indicated that the model can be employed as a preliminary screening tool before the collection of field samples for subsequent PCR testing. We also developed the 'HLBdetector' app using the Yolov5l-HLB2 model, which allows farmers to complete HLB detection in seconds with only a mobile phone terminal and without expert guidance. Overall, we successfully constructed a reliable automatic HLB identification model and developed the user-friendly 'HLBdetector' app, facilitating the prevention and timely control of HLB transmission in citrus orchards.

A Deep Learning Based Method to Delineate the Wet/Dry Shoreline and Compute Its Elevation Using High-Resolution UAS Imagery

Automatically detecting the wet/dry shoreline from remote sensing imagery has many benefits for beach management in coastal areas by enabling managers to take measures to protect wildlife during high water events. This paper proposes the use of a modified HED (Holistically-Nested Edge Detection) architecture to create a model for automatic feature identification of the wet/dry shoreline and to compute its elevation from the associated DSM (Digital Surface Model). The model is generalizable to several beaches in Texas and Florida. The data from the multiple beaches was collected using UAS (Uncrewed Aircraft Systems). UAS allow for the collection of high-resolution imagery and the creation of the DSMs that are essential for computing the elevations of the wet/dry shorelines. Another advantage of using UAS is the flexibility to choose locations and metocean conditions, allowing to collect a varied dataset necessary to calibrate a general model. To evaluate the performance and the generalization of the AI model, we trained the model on data from eight flights over four locations, tested it on the data from a ninth flight, and repeated it for all possible combinations. The AP and F1-Scores obtained show the success of the model’s prediction for the majority of cases, but the limitations of a pure computer vision assessment are discussed in the context of this coastal application. The method was also assessed more directly, where the average elevations of the labeled and AI predicted wet/dry shorelines were compared. The absolute differences between the two elevations were, on average, 2.1 cm, while the absolute difference of the elevations’ standard deviations for each wet/dry shoreline was 2.2 cm. The proposed method results in a generalizable model able to delineate the wet/dry shoreline in beach imagery for multiple flights at several locations in Texas and Florida and for a range of metocean conditions.