Map Features Research Articles

Typhoon localization detection algorithm based on TGE-YOLO

To address the problems of complex cloud features in satellite cloud maps, inaccurate typhoon localization, and poor target detection accuracy, this paper proposes a new typhoon localization algorithm, named TGE-YOLO. It is based on the YOLOv8n model with excellent high-low feature fusion capability and innovatively achieves the organic combination of feature fusion, computational efficiency, and localization accuracy. Firstly, the TFAM_Concat module is creatively designed in the neck network, which comprehensively utilizes the detailed information of shallow features and the semantic information of deeper features, enhancing the fusion ability of features at each layer. Secondly, the GSConv convolution is used to replace traditional convolution to reduce the computational cost of the model and effectively aggregate global information. Finally, the Efficient Intersection over Union (EIoU) loss function is improved to enhance its sensitivity to positional errors and optimize the error distribution, thereby improving the model’s accuracy in capturing the position at the center of the typhoon. The experimental results show that the proposed TGE-YOLO model outperforms Faster R-CNN, YOLOv5s, YOLOv9s, and YOLOv11n, with the typhoon identification mean average precision (mAP) reaching 87.8%, the mean square error (MSE) of typhoon center localization at 0.115, and the detection speed at 416.7 frames per second (FPS). The model’s rapid inference capability and efficient performance provide technical support for typhoon monitoring, which is expected to improve the timeliness and accuracy of typhoon warnings in practical applications.

MESSI: Task Mapping and Scheduling Strategy for FPGA-based Heterogeneous Real-Time Systems

Continuous demands for improved performance within constrained resource budgets are driving a move from homogeneous to heterogeneous processing platforms for the implementation of today’s Real-Time (RT) embedded systems. The applications executing on such systems are typically represented as a Precedence Task Graph (PTG), where a node represents a task or algorithm for one functionality and edges represent the complex interactions between multiple functionalities. Due to RT constraints, the task graph needs to be executed within a specified deadline. Although some existing studies have looked into solving this challenge, comprehensive studies that combine the theoretical features of RT task-graph mapping and scheduling with practical runtime architectural characteristics have mostly been ignored to date. Hence, in this paper, we consider the challenge of scheduling a RT application modelled as a single PTG, with the objective of minimizing the overall execution time under Hardware (HW) resource and deadline constraints for heterogeneous Central Processing Unit (CPU) + Field Programmable Gate Array (FPGA) architectures. First, we introduce an optimal solution using Integer Linear Programming (ILP). However, this ILP-based optimal solution suffers from computational complexity and does not scale well even for moderately large problem sizes. Hence, we additionally propose heuristic algorithms for task mapping and scheduling. The efficiency of the proposed scheme, named MESSI, has been evaluated through experiments using PTGs on a practical CPU+FPGA system regarding current technology restrictions. Our experiments demonstrate that performance gains of 55.6 % and area usage reductions of 46.3 % are possible compared to full Software SW and HW execution, respectively.

Detecting and Mapping Peatlands in the Tibetan Plateau Region Using the Random Forest Algorithm and Sentinel Imagery

The extensive peatlands of the Tibetan Plateau (TP) play a vital role in sustaining the global ecological balance. However, the distribution of peatlands across this region and the related environmental factors remain poorly understood. To address this issue, we created a high-resolution (10 m) map for peatland distribution in the TP region using 6146 Sentinel-1 and 23,730 Sentinel-2 images obtained through the Google Earth Engine platform in 2023. We employed a random forest algorithm that integrated spatiotemporal features with field training samples. The overall accuracy of the peatland distribution map produced is high, at 86.33%. According to the classification results, the total area of peatlands on the TP is 57,671.55 km2, and they are predominantly located in the northeast and southwest, particularly in the Zoige Protected Area. The classification primarily relied on the NDVI, NDWI, and RVI, while the DVI and MNDWI were also used in peatland mapping. B11, B12, NDWI, RVI, NDVI, and slope are the most significant features for peatland mapping, while roughness, correlation, entropy, and ASM have relatively slight significance. The methodology and peatland map developed in this work will enhance the conservation and management of peatlands on the TP while informing policy decisions and supporting sustainable development assessments.

Feature enhanced cascading attention network for lightweight image super-resolution

Attention mechanisms have been introduced to exploit deep-level information for image restoration by capturing feature dependencies. However, existing attention mechanisms often have limited perceptual capabilities and are incompatible with low-power devices due to computational resource constraints. Therefore, we propose a feature enhanced cascading attention network (FECAN) that introduces a novel feature enhanced cascading attention (FECA) mechanism, consisting of enhanced shuffle attention (ESA) and multi-scale large separable kernel attention (MLSKA). Specifically, ESA enhances high-frequency texture features in the feature maps, and MLSKA executes the further extraction. The rich and fine-grained high-frequency information are extracted and fused from multiple perceptual layers, thus improving super-resolution (SR) performance. To validate FECAN’s effectiveness, we evaluate it with different complexities by stacking different numbers of high-frequency enhancement modules (HFEM) that contain FECA. Extensive experiments on benchmark datasets demonstrate that FECAN outperforms state-of-the-art lightweight SR networks in terms of objective evaluation metrics and subjective visual quality. Specifically, at a × 4 scale with a 121 K model size, compared to the second-ranked MAN-tiny, FECAN achieves a 0.07 dB improvement in average peak signal-to-noise ratio (PSNR), while reducing network parameters by approximately 19% and FLOPs by 20%. This demonstrates a better trade-off between SR performance and model complexity.

ECMFGN: Extended Conditional Mapping Feature Generation Network for Severe Few-Shot Fault Diagnosis of Chillers

ECMFGN: Extended Conditional Mapping Feature Generation Network for Severe Few-Shot Fault Diagnosis of Chillers

Optimizing Irrigation Infrastructure Management with Web-Based Technologies and OpenStreetMap Integration

Irrigation is essential for increasing agricultural productivity in Indonesia, directly impacting national food security and farmer welfare by ensuring the sustainability of irrigation systems. Despite its importance, significant challenges persist, including damage to 46% of the irrigation infrastructure across 7.1 million hectares, with responsibilities divided among central, provincial, and city governments. These challenges are compounded by issues such as inadequate information access, limitations in real-time monitoring, and poor stakeholder coordination. To address these issues, integrating technological tools such as Geographic Information Systems (GIS) and platforms such as OpenStreetMap (OSM) is essential. These technologies offer real-time information, facilitate land change tracking, and enable spatial mapping, which supports proactive management and planning while improving decision making through data-driven insights. The adoption of Rapid Application Development (RAD) and Decision Support Systems (DSS) further enhances the efficiency of irrigation system management. The RAD methodology ensures swift development cycles with user interaction, while DSS provides structured decision-making capabilities. This approach supports robust system design, user interface development, and geographic data visualization. In practice, efficient data collection and stakeholder participation enable the system to effectively report and track irrigation conditions, promoting public participation, and fostering long-term infrastructure sustainability. The developed online monitoring system demonstrates its effectiveness by providing interactive map features and transparent reporting platforms, verified through successful implementation of testing scenarios. This system not only improves infrastructure management in areas like Batu City, but also sets a precedent for scalable participatory irrigation solutions, creating a foundation for future enhancements.

BEV Semantic Map Reconstruction for Self-Driving Cars with the Multi-Head Attention Mechanism

Environmental perception is crucial for safe autonomous driving, enabling accurate analysis of the vehicle’s surroundings. While 3D LiDAR is traditionally used for 3D environment reconstruction, its high cost and complexity present challenges. In contrast, camera-based cross-view frameworks can offer a cost-effective alternative. Hence, this manuscript proposes a new cross-view model to extract mapping features from camera images and then transfer them to a Bird’s-Eye View (BEV) map. Particularly, a multi-head attention mechanism in the decoder architecture generates the final semantic map. Each camera learns embedding information corresponding to its position and angle within the BEV map. Cross-view attention fuses information from different perspectives to predict top-down map features enriched with spatial information. The multi-head attention mechanism then globally performs dependency matches, enhancing long-range information and capturing latent relationships between features. Transposed convolution replaces traditional upsampling methods, avoiding high similarities of local features and facilitating semantic segmentation inference of the BEV map. Finally, we conduct numerous simulation experiments to verify the performance of our cross-view model.

Combining OpenStreetMap with Satellite Imagery to Enhance Cross-View Geo-Localization

Cross-view geo-localization (CVGL) aims to determine the capture location of street-view images by matching them with corresponding 2D maps, such as satellite imagery. While recent bird’s eye view (BEV)-based methods have advanced this task by addressing viewpoint and appearance differences, the existing approaches typically rely solely on either OpenStreetMap (OSM) data or satellite imagery, limiting localization robustness due to single-modality constraints. This paper presents a novel CVGL method that fuses OSM data with satellite imagery, leveraging their complementary strengths to enhance localization robustness. We integrate the semantic richness and structural information from OSM with the high-resolution visual details of satellite imagery, creating a unified 2D geospatial representation. Additionally, we employ a transformer-based BEV perception module that utilizes attention mechanisms to construct fine-grained BEV features from street-view images for matching with fused map features. Compared to state-of-the-art methods that utilize only OSM data, our approach achieves substantial improvements, with 12.05% and 12.06% recall enhancements on the KITTI benchmark for lateral and longitudinal localization within a 1-m error, respectively.

A USABILITY STUDY OF THE AUDIO-TACTILE MAP FOR VISUALLY IMPAIRED USERS AT THE MALAYSIAN ASSOCIATION FOR THE BLIND (MAB)

At the Malaysian Association for the Blind (MAB) building, the audio-tactile map has been installed on the ground floor to help and guide visual impairments in wayfinding. However, the usability of the audio-tactile map in helping them in wayfinding at the MAB has not been tested yet. In fact, the understanding of the users’ motivation for using the audio-tactile map has still not been studied. Thus, this research aims to describe the usability and to understand users’ motivation in using the audio-tactile map for visually impaired users in wayfinding at the MAB. Furthermore, a qualitative method study will be conducted by doing a user test and an interview with six participants from the MAB, focusing on the usability and users’ motivation in using the audio-tactile map to help them in wayfinding. Nielson Usability Model and Thematic Analysis with Affinity Diagram tools were applied in this research to analyze the data. The findings from this research have described the usability of the audio-tactile map among visually impaired users at the MAB, which includes efficiency, learnability, satisfaction, errors, and memorability. Also, the findings showed that the audio-tactile map features affected the users’ motivation to use the audio-tactile map for wayfinding at the MAB.

Geospatial technology for assessment of soil erosion prone areas of the Pulappatti Sub-basin, Dharmapuri District, South India

Soil erosion poses serious threats to agricultural production, hydraulic structures, and the world’s ecosystem. Scientific management of soil, water and vegetation resources on a watershed basis is very important for arresting erosion in order to retain the nutrient levels. A number of parametric models have been developed to predict soil erosion prone zones in structural terrains. Normalized Weight is the most widely used empirical equation for estimating soil erosion. A comprehensive methodology using Normalized Weight method and Geographic Information System (GIS) techniques was adopted to identify soil erosion prone zones in parts of the Pulappatti Sub-basin, Dharmapuri District, Tamil Nadu, India. Various thematic maps on soil erosion such as slope (%), geology, geomorphology, drainage density, soil, elevation and land use/land cover maps were prepared and the GIS analyses method used to understand the situation of soil erosion. These parameters under various thematic maps were integrated with ArcGIS. A probability weighted approach has been adopted that allows a linear combination of probability weights of each thematic map (Wt) and ranking for different features in the thematic maps were assigned and final scores were obtained (Sc), depending upon their role in soil erosion. The integrated soil erosion map is reclassified into five zones as very low, low, moderate, high and very high soil erosion prone zones. Terrains associated with moderate slope, high elevation, high drainage density and agricultural land are more prone to soil erosion. This factor increases the vulnerability of land degradation in the region. Qualitative results are generated in this study which would be helpful to generate quantitative intensity and to control soil erosion process. The final output in this study provides important tools for researchers and engineers to plan for control of soil erosion in the study area. They should take active and meaningful decisions to avoid this hazard in high and very high areas prone to soil erosion. The results also revealed that soil conservation measures can be considered in this area for sustainable development.

Application of Quantum GIS in the Development of 3D Maps in the Tourism Bakunjangan Application

This research explores the use of Quantum GIS (QGIS) in developing 3D maps for the Bakunjangan tourism application in Banjarmasin City. The integration of spatial data, sensors, and open data sources such as OpenStreetMap (OSM) aims to improve accuracy, consistency, and visitor experience. The development of 3D maps follows the System Development Life Cycle (SDLC) method, which outlines strategies and processes for developing, designing, and maintaining software projects, ensuring that all goals, objectives, functionalities, and user needs are met. The urgency of this research lies in its ability to support the Banjarmasin City government in managing and developing local tourism, especially with the increase in tourist visits from 2,487 in 2022 to 3,895 in 2023. The 3D map feature in the Bakunjangan Application is expected to provide accurate information and a more satisfying experience for tourists, as well as enhance the competitiveness of tourism at the national level. The development of the 3D maps was conducted after a survey of 55 Ground Control Points (GCP) in various tourist areas. The QGIS application, with the help of the Qgis2threejs plugin, facilitates the creation of 3D map animations, although five tourist attractions could not be animated. To optimally display the 3D maps, an internet connection with a minimum speed of 10 Mbps is required. As a result, the Bakunjangan Application produced 65 interactive user interfaces and 50 3D animations of tourist attractions, with an application feasibility rating of 89%, placing it in the excellent category.

A Neural Network Based on Supervised Multi-View Contrastive Learning and Two-Stage Feature Fusion for Face Anti-Spoofing

As one of the most crucial parts of face detection, the accuracy and the generalization of face anti-spoofing are particularly important. Therefore, it is necessary to propose a multi-branch network to improve the accuracy and generalization of the detection of unknown spoofing attacks. These branches consist of several frequency map encoders and one depth map encoder. These encoders are trained together. It leverages multiple frequency features and generates depth map features. High-frequency edge texture is beneficial for capturing moiré patterns, while low-frequency features are sensitive to color distortion. Depth maps are more discriminative than RGB images at the visual level and serve as useful auxiliary information. Supervised Multi-view Contrastive Learning enhances multi-view feature learning. Moreover, a two-stage feature fusion method effectively integrates multi-branch features. Experiments on four public datasets, namely CASIA-FASD, Replay–Attack, MSU-MFSD, and OULU-NPU, demonstrate model effectiveness. The average Half Total Error Rate (HTER) of our model is 4% (25% to 21%) lower than the Adversarial Domain Adaptation method in inter-set evaluations.

Multi-channel fused vision transformer network for bearing fault diagnosis under different working conditions

Abstract Many of the current fault diagnosis methods rely on time-domain signals. While the richest information are contained in these signals, their complexity poses challenges to network learning and limits the ability to fully characterize them. To address these issues, a novel multi-channel fused vision transformer network (MFVTN) is proposed in this paper. Firstly, the overlapping patch embedding module is introduced to overlap the time-domain map with edge information, preserving the global continuous features of the time-domain map and adding positional encoding for sorting. This integration helps the vision transformer merge detailed features and construct the global mapping. Secondly, multiple dimensional time domain signal features are extracted and fused in parallel, enabling multi-domain fault diagnosis of bearings. In order to enhance the network ability to extract domain-invariant features, an adversarial training strategy combined with Wasserstein distance is utilized. The results demonstrate that the diagnostic accuracy of the proposed MFVTN can reach 98.2%.

Development of web based data-driven recommendation system for house rental via hierarchical fuzzy axiomatic design

PurposeIn the real estate business, identifying the ideal property for a user poses a difficult task due to the many factors involved in the decision-making process. Moreover, users often struggle to find platforms that facilitate effective communication of their preferences. To tackle this issue, a web-based data-driven recommendation system has been devised for the real estate business.Design/methodology/approachThe process of identifying the most suitable rental property for a user hinges greatly on how the user prioritizes each criterion and the analysis of unstructured data. In this research, a novel recommendation system for house rentals is developed by utilizing the Weighted Hierarchical Fuzzy Axiomatic Design (WFAD) approach. Techniques for extracting pertinent information from unstructured house descriptions are employed. The user’s preferences are captured through an interactive web application equipped with a map feature to highlight key locations.FindingsData on various available rental properties are gathered using web scraping techniques. The efficacy of the proposed rental house recommendation system is demonstrated through multiple case studies. It is observed that the developed system provides more informed and reliable decisions.Originality/valueFirst time in the related literature, we applied the weighted fuzzy axiomatic design procedure (WFAD) to the product recommendation problem and developed a comprehensive web-based system for recommending rental houses based on it in the real estate business.

Driver Cognitive Distraction Detection based on eye movement behavior and integration of multi-view space-channel feature

The significance of Driver Distraction Detection (DDD) in enhancing road safety is immense and undeniable. While numerous DDD methods concentrate on conventional distractions, such as driving behavior, gaze direction, or hand movements, they often overlook cognitive distractions owing to their intricate nature. This study aims to bridge this gap by leveraging driver eye movement data to detect cognitive distractions. To achieve this, we introduce the Driver Cognitive Distraction Detection (DCDD) model. This model incorporates the driver’s gaze points, captured by an eye tracker, and the DashCam Image (DCI) as inputs. To capture the temporal dynamics of the driver’s eye movements, we devise a preprocessing technique that generates an eye movement heat Map (Map), which highlights the driver’s areas of focus within the DCI. Then, a Fusion Adversarial Network (FAN) is designed by utilizing the Sigmoid activation function to blend DCI features with those of the Map. Subsequently, a shared parameter network is employed for adversarial learning, focusing on the inversely activated features. To further achieve the extraction of DCI and Map features, we propose the Multi-View Space Channel Network (MSCN). This network can integrate low-dimensional spatial features and high-dimensional channel features from different views of DCI and Map to help Transformer capture DCI and Map features more comprehensively in the temporal dimension. By effectively integrating DCI and Map data and recursively extracting time information, our DCDD model achieves remarkable accuracy while controlling model Params and FLOPs, attaining a high score of 96.42%.

A salient feature establishment tactic for cassava disease recognition

Accurate classification of cassava disease, particularly in field scenarios, relies on object semantic localization to identify and precisely locate specific objects within an image based on their semantic meaning, thereby enabling targeted classification while suppressing irrelevant noise and focusing on key semantic features. The advancement of deep convolutional neural networks (CNNs) paved the way for identifying cassava diseases by leveraging salient semantic features and promising high returns. This study proposes an approach that incorporates three innovative elements to refine feature representation for cassava disease classification. First, a mutualattention method is introduced to highlight semantic features and suppress irrelevant background features in the feature maps. Second, instance batch normalization (IBN) was employed after the residual unit to construct salient semantic features using the mutualattention method, representing high-quality semantic features in the foreground. Finally, the RSigELUD activation method replaced the conventional ReLU activation, enhancing the nonlinear mapping capacity of the proposed neural network and further improving fine-grained leaf disease classification performance. This approach significantly aided in distinguishing subtle disease manifestations in cassava leaves. The proposed neural network, MAIRNet-101 (Mutualattention IBN RSigELUD Neural Network), achieved an accuracy of 95.30 % and an F1-score of 0.9531, outperforming EfficientNet-B5 and RepVGG-B3g4. To evaluate the generalization capability of MAIRNet, the FGVC-Aircraft dataset was used to train MAIRNet-50, which achieved an accuracy of 83.64 %. These results suggest that the proposed algorithm is well suited for cassava leaf disease classification applications and offers a robust solution for advancing agricultural technology.

Adaptive and soft constrained vision-map vehicle localization using Gaussian processes and instance segmentation

The accurate and reliable localization is crucial for the safe performance of autonomous vehicles in uncertain and complex environments such as urban areas. Thus, this paper contributes by presenting a feature-based localization framework for autonomous vehicles where segmented map features are used for designing soft and adaptive constraints for Particle Filtering. After obtaining features of landmarks (light poles) in instance-based segmented images acquired from a monocular camera, vehicle-to-landmark distances are predicted using Gaussian Process Regression models (GPR). Both mean and variance (uncertainty) outputs of Gaussian Process models were used to implement adaptive soft constraints. Experimental results over the WATonoBus from the University of Waterloo confirm that the use of the proposed constraints improves the vehicle states estimation. Using instance segmentation increases the vehicle-to-landmark distance prediction accuracy by 27% and keeps the real-time processing capability of the proposed approach. Besides, the proposed approach reliably localizes the vehicle in very noisy conditions using only a monocular camera, even with a reduced number of landmarks, reducing the localization Euclidean error from 2.55 m to 0.97 m when compared to an unconstrained Particle Filter.

A 30 Arcsec Resolution VS30 Map for Mainland China Using Refined Topographic Slope-Based Cokriging (SCK) Model

ABSTRACT In 2022, we proposed a VS30 proxy model based on the Cokriging method, integrating local VS30 measurements with topographic slope data (SCK model, Zhou et al., 2022). Utilizing this model, a VS30 map for mainland China was developed based on 7797 local boreholes. However, the initial VS30 map was produced with a coarse grid resolution of 360 arcsec and did not comprehensively cover mainland China due to sparse distribution of boreholes in certain areas. In this study, we refined the SCK model by explicitly accounting for the influence of surrounding topographic slopes, incorporating more distant VS30 measurements, and improving the spatial distribution of VS30 measurements used in the model calculation. Tests based on virtual cases were conducted to evaluate the characteristics of the refined SCK model. In addition, 142 VS30 measurements from strong-motion stations in western China were added to enhance spatial coverage and model accuracy in these regions. Employing the refined SCK model and the expanded VS30 data set, a new VS30 map for mainland China was generated. This updated map features a higher grid resolution of 30 arcsec and covers the entirety of mainland China, showing reduced estimation errors and improved continuity. Comparisons with the U.S. Geological Survey Global VS30 Mosaic indicate that the results from the refined SCK model are more reasonable, as evidenced by local topography, VS profiles, lithologic profiles, and geology map, which better capture the impact of local geomorphological differences and climatic conditions on VS30 values.

Secondary Structure Detection and Structure Modeling for Cryo-EM.

Rapid advancements in cryogenic electron microscopy (cryo-EM) have revolutionized the field of structural biology by enabling the determination of complex macromolecular structures at unprecedented resolutions. When cryo-EM density maps have a resolution around 3Å, the atomic structure can be modeled manually. However, as the resolution decreases, analyzing these density maps becomes increasingly challenging. For modeling structures in lower resolution maps, deep learning can be used to identify structural features in the maps to assist in structure modeling.Here, we present a suite of deep learning-based tools developed by our lab that enable structural biologists to work with cryo-EM maps of a wide range of resolutions. For cryo-EM maps at near-atomic resolution (5Å or better), DeepMainmast automatically models all-atom structures by tracing the main chain from local map features of amino acids and atoms detected by deep learning; DAQ score quantifies map-model fit and indicates potential misassignments in protein models. In intermediate resolution maps (5-10Å), Emap2sec and Emap2sec+ can accurately detect protein secondary structures and nucleic acids. These tools and more are available at our web server: https://em.kiharalab.org/ .

Radiomics analysis of dual-energy CT-derived iodine maps for differentiating malignant from benign thyroid nodules.

Many thyroid nodules are detected incidentally with the widespread use of sensitive imaging techniques; however, only a fraction of these nodules are malignant, resulting in unnecessary medical expenditures and anxiety. The major challenge is to differentiate benign thyroid nodules from malignant ones. The application of dual-energy computed tomography (DECT) and radiomics provides a new diagnostic approach. Studies applying radiomics from primary tumours on iodine maps to differentiate malignant from benign thyroid nodules are still lacking. To determine the ability of an iodine map-based radiomic nomogram in the venous phase for differentiating malignant thyroid nodules from benign nodules. A total of 141 patients with thyroid nodules who underwent DECT were enrolled and randomly assigned to the training and test cohorts between January 2018 and January 2019. The radiomic score (Rad-score) was derived from nine quantitative features of the iodine maps. Stepwise logistic regression analysis was used to develop radiomic, clinical and combined models. Age, normalized iodine concentration (NIC), and cyst changes were used to construct the clinical model. Receiver operating characteristic (ROC) curve analysis, sensitivity and specificity were performed to analyse the ability of the models to predict malignant thyroid nodules. Calibration analysis was used to test the fitness of the models. Decision curve analysis (DCA) and nomogram construction were also performed. According to the clinical model, age (0.989 [0.984, 0.995]; p<0.001), NIC (0.778 [0.640, 0.995]; p=0.01), and cyst changes (0.617 [0.507, 0.751]; p<0.001) were independently associated with malignant thyroid nodules. According to the combined model, age (0.994 [0.989, 0.999]; p=0.01), NIC (0.797 [0.674, 0.941]; p=0.008), cyst changes (0.786 [0.653, 0.947]; p=0.01), and the rad-score (1.106 [1.070, 1.143]; p<0.001) were independently associated with malignant thyroid nodules. The combined model achieved satisfactory discrimination in predicting malignant thyroid nodules and had greater predictive value in the training (AUC [areas under the curve], 0.96vs. 0.87; p=0.01) and test (AUC, 0.90vs. 0.79; p=0.04) cohorts than did the clinical model. The radiomics nomogram based on iodine maps is useful to distinguish malignant thyroid nodules from benign thyroid nodules.