Types Of Features Research Articles

Geothermal ecosystems on Mt. Erebus, Antarctica, support diverse and taxonomically novel biota.

Mt. Erebus, Antarctica, is the southernmost active volcano in the world and harbors diverse geothermally unique ecosystems, including 'Subglacial' and 'Exposed' features, surrounded by a vast desert of ice and snow. Previous studies, while limited in scope, have highlighted the unique and potentially endemic biota of Mt. Erebus. Here, we provide an amplicon-based biodiversity study across all domains of life and all types of geothermal features, with physicochemical and biological data from 48 samples (39 Exposed and 9 Subglacial) collected through various field seasons. We found potentially high taxonomic novelty among prokaryotes and fungi, supporting past hypotheses of high endemism due to the distinctive and isolated environment; in particular, the large number of taxonomically divergent fungal sequences was surprising. We found that different site types had unique physicochemistry and biota; Exposed sites were warmer than Subglacial (median: 40 vs 10°C for Exposed and Subglacial, respectively) and tended to have more photosynthetic organisms (Cyanobacteria and Chlorophyta). Subglacial sites had more Actinobacteriota, correlated with greater concentrations of Ca and Mg present. Our results also suggest potential human impacts on these remote, highly significant sites, finding evidence for fungal taxa normally associated with wood decay. In this study, we provide a blueprint for future work aimed at better understanding the novel biota of Mt. Erebus.

Wetland mapping in the Liaohe River Estuary using multi-source remote sensing image feature selection

ABSTRACT As a crucial node in the East Asia–Australasia migratory bird network, the Liaohe River Estuary Wetland (LREW) contributes significantly to coastal ecological balance and biodiversity. Accurate and timely mapping of the LREW is essential for monitoring ecological changes and understanding shifts in the wetland’s ecosystem structure and functions. In this study, an innovative approach that integrates radar (Sentinel-1), optical (Sentinel-2), and DEM data on Google Earth Engine (GEE) is proposed to achieve a more optimized and accurate wetland mapping. Recursive Feature Elimination (RFE) is employed to improve feature collection, facilitating the construction of an optimal feature set for Random Forest (RF) classification to extract detailed LREW information. Mapping conducted from 2017 to 2023 using the proposed approach demonstrates its effectiveness and stability in mapping the LREW, achieving overall accuracies ranging from 89.84% to 93.73% and Kappa from 0.85 to 0.91. Compared to single-source methods, the integration of multi-source data substantially enhances mapping accuracy, while RF-RFE effectively eliminates redundant features, further refining classification precision. Texture features (Sum Average, SAVG) and the Water Index 2019 (WI2019) were found to significantly influence wetland mapping. The importance of different feature types is ranked as follows: spectral features > vegetation/water body index > PCA features > SAR texture features > red-edge index > other spectral index > spectral texture features > backscatter coefficient > H-Alpha. During the study period, the wetland area increased from 849.60 km2 to 979.49 km2. This expansion was caused primarily by wetland protection policies that led to the dismantling of coastal aquaculture ponds, resulting in a reduction of 90.28 km2 in waterbodies over 7 years, with many areas transitioning to tidal flats and Suaeda salsa habitats. In conclusion, the proposed method is effective in mapping the LRE wetlands and provides reliable data support for wetland ecological protection and restoration.

Image manipulation localization via dynamic cross-modality fusion and progressive integration

Image manipulation localization aims at distinguishing forged regions from the whole test image. Though many outstanding prior arts have been proposed for this task, there are still two issues that need to be further studied: (1) how to fuse diverse types of features with forgery clues; (2) how to progressively integrate multistage features for better localization performance. In this paper, we propose a tripartite progressive integration network (TriPINet) for end-to-end image manipulation localization. First, we extract both visual perception information, e.g., RGB input images, and visual imperceptible features, e.g., frequency and noise traces for forensic feature learning. Second, we develop a guided cross-modality dual-attention (gCMDA) module to fuse different types of forged clues. Third, we design a set of progressive integration squeeze-and-excitation (PI-SE) modules to improve localization performance by appropriately incorporating multiscale features in the decoder. Extensive experiments are conducted to compare our method with state-of-the-art image forensics approaches. The proposed TriPINet obtains competitive results on several benchmark datasets.

RNAfcg: RNA Flexibility Prediction Based on Topological Centrality and Global Features.

The dynamics of RNAs are related intimately to their functions. Molecular flexibility, as a starting point for understanding their dynamics, has been utilized to predict many characteristics associated with their functions. Since the experimental measurement methods are time-consuming and labor-intensive, it is urgently needed to develop reliable theoretical methods to predict RNA flexibility. In this work, we develop an effective machine learning method, RNAfcg, to predict RNA flexibility, where the Random Forest (RF) is trained by features including the topological centralities, flexibility-rigidity index, and global characteristics first introduced by us, as well as some traditional sequence and structural features. The analyses show that the three types of features introduced first have significant contributions to RNA flexibility prediction, among which the topological type contributes the most, which indicates the importance of structural topology in determining RNA flexibility. The performance comparison indicates that RNAfcg outperforms the state-of-the-art machine learning methods and the commonly used Gaussian Network Model (GNM) models, achieving a much higher Pearson correlation coefficient (PCC) of 0.6619 on the test data set. This work is helpful for understanding RNA dynamics and can be used to predict RNA function information. The source code is available at https://github.com/ChunhuaLab/RNAfcg/.

Prediction of air compressor faults with feature fusion and machine learning

Air compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study’s input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.

Detecting and rationalizing concept drift: A feature-level approach for understanding cause–effect relationships in dynamic environments

Concept drift detection is essential for data-driven models to adapt to changing data patterns, ensuring accuracy and reliability in dynamic environments. Explaining drift can be even more important for gaining insights into root causes to facilitate informed decision-making. This paper presents a method to detect and rationalize drift, explaining it at the feature level by identifying impactful changes in the feature-outcome relationship from a cause–effect perspective. Drift occurrences therefore fall into four categories, including changes in the cause–effect relationship, comprising two subcategories: Type 1, where specific features no longer act as causes in the new environment, while Type 2 entails previously non-causal features becoming causes in the new environment. If the cause–effect relationship remains unchanged, it indicates changes in the importance of causal features (Type 3) or variations in the intensity of the cause–effect relationship (Type 4). The F1 score is employed to validate the proposed method for detecting and rationalizing recurring sudden drift in both real and virtual drift contexts. The average F1 scores on the Stagger and Agrawal datasets are 89.5% and 74.8%, respectively. The method is then applied to coalmine pressure data to investigate and rationalize changes in the causal relationship between strut pressure and microseismic energy.

Raman characterization of lunar highlands simulants for in-situ resource utilization in a lunar setting

Lunar regolith simulants from the NU-LHT series were characterized using different configurations for performing Raman spectroscopy measurements, including with different excitation wavelengths and spot sizes. This testing was performed to explore various Raman measurement configurations for analyzing lunar regolith, especially in terms of capturing distinctive fluorescence features that can provide more information about the composition of the regolith. Results obtained utilizing configurations having a 785 nm laser for excitation showed relatively narrow, intense fluorescence signals between 870 and 890 nm, which, to the best of our knowledge, has not been observed before in lunar regolith or lunar simulant samples. These distinctive fluorescence features, attributed to a specific rare earth element (REE) impurity, adds further support that these types of features can be utilized for identification and potentially quantification of the amount of REE or transition metal impurities in lunar regolith. Further, other aspects of these Raman instrument configurations and their advantages were explored, especially those applicable for use in a lunar environment in support of in-situ resource utilization (ISRU).

Hierarchical Progressive Image Forgery Detection and Localization Method Based on UNet

The rapid development of generative technologies has made the production of forged products easier, and AI-generated forged images are increasingly difficult to accurately detect, posing serious privacy risks and cognitive obstacles to individuals and society. Therefore, constructing an effective method that can accurately detect and locate forged regions has become an important task. This paper proposes a hierarchical and progressive forged image detection and localization method called HPUNet. This method assigns more reasonable hierarchical multi-level labels to the dataset as supervisory information at different levels, following cognitive laws. Secondly, multiple types of features are extracted from AI-generated images for detection and localization, and the detection and localization results are combined to enhance the task-relevant features. Subsequently, HPUNet expands the obtained image features into four different resolutions and performs detection and localization at different levels in a coarse-to-fine cognitive order. To address the limited feature field of view caused by inconsistent forgery sizes, we employ three sets of densely cross-connected hierarchical networks for sufficient interaction between feature images at different resolutions. Finally, a UNet network with a soft-threshold-constrained feature enhancement module is used to achieve detection and localization at different scales, and the reliance on a progressive mechanism establishes relationships between different branches. We use ACC and F1 as evaluation metrics, and extensive experiments on our method and the baseline methods demonstrate the effectiveness of our approach.

PHIGrader: Evaluating the effectiveness of Manifest file components in Android malware detection using Multi Criteria Decision Making techniques

The popularity of the Android operating system has itself become a reason for privacy concerns. To deal with such malware threats, researchers have proposed various detection approaches using static and dynamic features. Static analysis approaches are the most convenient for practical detection. However, several patterns of feature usage were found to be similar in the normal and malware datasets. Such high similarity in both datasets’ feature patterns motivates us to rank and select only the distinguishing set of features. Hence, in this study, we present a novel Android malware detection system, termed as PHIGrader for ranking and evaluating the efficiency of the three most commonly used static features, namely permissions, intents, and hardware components, when used for Android malware detection. To meet our goals, we individually rank the three feature types using frequency-based Multi-Criteria Decision Making (MCDM) techniques, namely TOPSIS and EDAS. Then, the system applies a novel detection algorithm to the rankings involving machine learning and deep learning classifiers to present the best set of features and feature type with higher detection accuracy as an output. The experimental results highlight that our proposed approach can effectively detect Android malware with 99.10% detection accuracy, achieved with the top 46 intents when ranked using TOPSIS, which is better than permissions, hardware components, or even the case where other popular MCDM techniques are used. Furthermore, our experiments demonstrate that the proposed system with frequency-based MCDM rankings is better than other statistical tests such as mutual information, Pearson correlation coefficient, and t-test. In addition, our proposed model outperforms various popularly used feature ranking methods such as Chi-square, Principal Component Analysis (PCA), Entropy-based Category Coverage Difference (ECCD), and other state-of-the-art Android malware detection techniques in terms of detection accuracy.

The SoCAP (Social Communication, Affiliation, and Presence) Taxonomy of Social Features: Scoping Review of Commercially Available eHealth Apps.

eHealth interventions have proven to be valuable resources for users with diverse mental and behavioral health concerns. As these technologies continue to proliferate, both academic researchers and commercial app creators are leveraging the use of features that foster a sense of social connection on these digital platforms. Yet, the literature often insufficiently represents the functionality of these key social features, resulting in a lack of understanding of how they are being implemented. This study aimed to conduct a methodical review of commercially available eHealth apps to establish the SoCAP (social communication, affiliation, and presence) taxonomy of social features in eHealth apps. Our goal was to examine what types of social features are being used in eHealth apps and how they are implemented. A scoping review of commercially available eHealth apps was conducted to develop a taxonomy of social features. First, a shortlist of the 20 highest-rated eHealth apps was derived from One Mind PsyberGuide, a nonprofit organization with trained researchers who rate apps based on their (1) credibility, (2) user experience, and (3) transparency. Next, both mobile- and web-based versions of each app were double-coded by 2 trained raters to derive a list of social features. Subsequently, the social features were organized by category and tested on other apps to ensure their completeness. Four main categories of social features emerged: (1) communication features (videoconferencing, discussion boards, etc), (2) social presence features (chatbots, reminders, etc), (3) affiliation and identity features (avatars, profiles, etc), and (4) other social integrations (social network and other app integrations). Our review shows that eHealth apps frequently use resource-intensive interactions (eg, videoconferencing with a clinician and phone calls from a facilitator), which may be helpful for participants with high support needs. Furthermore, among commercially available eHealth apps, there is a strong reliance on automated features (eg, avatars, personalized multimedia, and tailored content) that enhance a sense of social presence without requiring a high level of input from a clinician or staff member. The SoCAP taxonomy includes a comprehensive list of social features and brief descriptions of how these features work. This classification system will provide academic and commercial eHealth app creators with an understanding of the various social features that are commonly implemented, which will allow them to apply these features to enhance their own apps. Future research may include comparing the synergistic effects of various combinations of these social features.

MCMVDRP: a multi-channel multi-view deep learning framework for cancer drug response prediction.

Drug therapy remains the primary approach to treating tumours. Variability among cancer patients, including variations in genomic profiles, often results in divergent therapeutic responses to analogous anti-cancer drug treatments within the same cohort of cancer patients. Hence, predicting the drug response by analysing the genomic profile characteristics of individual patients holds significant research importance. With the notable progress in machine learning and deep learning, many effective methods have emerged for predicting drug responses utilizing features from both drugs and cell lines. However, these methods are inadequate in capturing a sufficient number of features inherent to drugs. Consequently, we propose a representational approach for drugs that incorporates three distinct types of features: the molecular graph, the SMILE strings, and the molecular fingerprints. In this study, a novel deep learning model, named MCMVDRP, is introduced for the prediction of cancer drug responses. In our proposed model, an amalgamation of these extracted features is performed, followed by the utilization of fully connected layers to predict the drug response based on the IC50 values. Experimental results demonstrate that the presented model outperforms current state-of-the-art models in performance.

Non-invasive multimodal CT deep learning biomarker to predict pathological complete response of non-small cell lung cancer following neoadjuvant immunochemotherapy: a multicenter study

ObjectivesAlthough neoadjuvant immunochemotherapy has been widely applied in non-small cell lung cancer (NSCLC), predicting treatment response remains a challenge. We used pretreatment multimodal CT to explore deep learning-based immunochemotherapy response...

H-Net: Heterogeneous Neural Network for Multi-Classification of Neuropsychiatric Disorders.

Clinical studies have proved that both structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) are implicitly associated with neuropsychiatric disorders (NDs), and integrating multi-modal to the binary classification of NDs has been thoroughly explored. However, accurately classifying multiple classes of NDs remains a challenge due to the complexity of disease subclass. In our study, we develop a heterogeneous neural network (H-Net) that integrates sMRI and fMRI modes for classifying multi-class NDs. To account for the differences between the two modes, H-Net adopts a heterogeneous neural network strategy to extract information from each mode. Specifically, H-Net includes an multi-layer perceptron based (MLP-based) encoder, a graph attention network based (GAT-based) encoder, and a cross-modality transformer block. The MLP-based and GAT-based encoders extract semantic features from sMRI and features from fMRI, respectively, while the cross-modality transformer block models the attention of two types of features. In H-Net, the proposed MLP-mixer block and cross-modality alignment are powerful tools for improving the multi-classification performance of NDs. H-Net is validate on the public dataset (CNP), where H-Net achieves 90% classification accuracy in diagnosing multi-class NDs. Furthermore, we demonstrate the complementarity of the two MRI modalities in improving the identification of multi-class NDs. Both visual and statistical analyses show the differences between ND subclasses.

Support Vector Machine Framework for Detecting Ambiguous Contours of Space Debris Cloud

Operational spacecraft are prepared for collisions with space debris by installing protective walls (bumpers). A group of vaporized and liquefied microparticles generated by debris collisions is called a debris cloud. To evaluate the protective performance of bumpers, it is important to measure the spread velocity and angle of the debris cloud. However, debris cloud images exhibit ambiguous contours of debris clouds. Consequently, measurement errors in the spread velocity and spread angles occur because of the observer’s subjectivity. Commonly used derivative-based methods can detect steep contours; however, they cannot detect ambiguous contours such as those of debris clouds. In this study, a method for uniquely detecting the ambiguous contours of a debris cloud based on supervised machine learning and a continuous wavelet transform (CWT) is proposed. Feature points that indicate candidate points of the debris cloud contour are extracted using a method based on CWT. Four types of specific features for debris cloud contours were assigned to the feature points. Supervised machine learning using a support vector machine can detect the debris cloud contours. The proposed method enables the evaluation of the ambiguous contours of a debris cloud and the protection performance of a bumper without observer subjectivity.

EGCN++: A New Fusion Strategy for Ensemble Learning in Skeleton-Based Rehabilitation Exercise Assessment.

Skeleton-based exercise assessment focuses on evaluating the correctness or quality of an exercise performed by a subject. Skeleton data provide two groups of features (i.e., position and orientation), which existing methods have not fully harnessed. We previously proposed an ensemble-based graph convolutional network (EGCN) that considers both position and orientation features to construct a model-based approach. Integrating these types of features achieved better performance than available methods. However, EGCN lacked a fusion strategy across the data, feature, decision, and model levels. In this paper, we present an advanced framework, EGCN++, for rehabilitation exercise assessment. Based on EGCN, a new fusion strategy called MLE-PO is proposed for EGCN++; this technique considers fusion at the data and model levels. We conduct extensive cross-validation experiments and investigate the consistency between machine and human evaluations on three datasets: UI-PRMD, KIMORE, and EHE. Results demonstrate that MLE-PO outperforms other EGCN ensemble strategies and representative baselines. Furthermore, the MLE-PO's model evaluation scores are more quantitatively consistent with clinical evaluations than other ensemble strategies.

Characterizing Solar Center-to-limb Radial-velocity Variability with SDO

Stellar photospheric inhomogeneities are a significant source of noise, which currently precludes the discovery of Earth-mass planets orbiting Sun-like stars with the radial-velocity (RV) method. To complement several previous studies that have used ground- and spaced-based facilities to characterize the RV of the Sun, here we characterize the center-to-limb variability (CLV) of solar RVs arising from various solar-surface inhomogeneities observed by the Solar Dynamics Observatory (SDO)/Helioseismic Magnetic Imager and SDO/Atmospheric Imaging Assembly. By using various SDO observables to classify pixels and calculate line-of-sight velocities as a function of pixel classification and limb angle, we show that each identified feature type, including the umbrae and penumbrae of sunspots, quiet-Sun magnetoconvective cells, magnetic network, and plage, exhibit distinct and complex CLV signatures, including a notable limb-angle dependence in the observed suppression of convective blueshift for magnetically active regions. We discuss the observed distributions of velocities by identified region type and limb angle, offer interpretations of the physical phenomena that shape these distributions, and emphasize the need to understand the RV signatures of these regions as astrophysical signals, rather than simple (un)correlated noise processes.

Intrinsic mode ensembled statistical cepstral coefficients for feature extraction of ship-radiated noise

Effective analysis of ship underwater acoustic signals requires accurately capturing and distinguishing subtle differences between various types of signal features. This paper introduces a multi-objective feature extraction method based on intrinsic mode decomposition and statistical parameterized cepstral coefficients, aimed at identifying different ship signals. Firstly, the original sample signals are preprocessed and converted into multiple frame signals. Each acoustic signal frame is then decomposed into intrinsic mode functions (IMFs) using variational mode decomposition (VMD). Cepstral coefficients are extracted from each IMF, and the statistical parameter features of each IMF are integrated to enhance the differentiation of various types of ship-radiated noise. These features also form unique “fingerprints” for each ship type, facilitating identity accurate authentication. The performance of the proposed method is evaluated using both K-nearest neighbors (KNN) and support vector machine (SVM) classification models. Experimental results demonstrate that the synergy between the proposed method and SVM significantly outperforms KNN, effectively distinguishing between 12 types of signals, including 11 ship-radiated signals and background noise, achieving an accuracy rate exceeding 89% across 1000 random tests. This method significantly increases the number of classifiable ship targets, demonstrating its considerable potential in distinguishing various underwater acoustic signals.

Data-knowledge co-driven feature based prediction model via photoplethysmography for evaluating blood pressure

Background:Knowledge feature (KF) with clear physiological significance of photoplethysmography are widely used in predicting blood pressure. However, KF primarily focus on local information of photoplethysmography, which may struggle to capture the overall characteristics. Methods:Firstly, functional data analysis (FDA) was introduced to extract two types of data feature (DF). Furthermore, data-knowledge co-driven feature (DKCF) was proposed by combining FDA and constraints of KF. Finally, random forest, ada boost, gradient boosting, support vector machine and deep neural network were adopted, to compare the abilities of KF, DFs and DKCF in predicting blood pressure with two datasets (A published dataset and a self-collected dataset). Results:Under the premise of extracting only 9 features, the average mean absolute errors (MAE) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) obtained by DKCF are both the smallest in dataset 1. In dataset 2, DKCF acquires the smallest MAE in predicting SBP and obtains the second smallest MAE in predicting DBP. Conclusions:The results demonstrate that low-dimensional DKCF of photoplethysmography is closely correlated with blood pressure, which may serve as an important indicator for health assessment.

Classifying Unconscious, Psychedelic, and Neuropsychiatric Brain States with Functional Connectivity, Graph Theory, and Cortical Gradient Analysis.

Accurate and generalizable classification of brain states is essential for understanding their neural underpinnings and improving clinical diagnostics. Traditionally, functional connectivity patterns and graph-theoretic metrics have been utilized. However, cortical gradient features, which reflect global brain organization, offer a complementary approach. We hypothesized that a machine learning model integrating these three feature sets would effectively discriminate between baseline and atypical brain states across a wide spectrum of conditions, even though the underlying neural mechanisms vary. To test this, we extracted features from brain states associated with three meta-conditions including unconsciousness (NREM2 sleep, propofol deep sedation, and propofol general anesthesia), psychedelic states induced by hallucinogens (subanesthetic ketamine, lysergic acid diethylamide, and nitrous oxide), and neuropsychiatric disorders (attention-deficit hyperactivity disorder, bipolar disorder, and schizophrenia). We used support vector machine with nested cross-validation to construct our models. The soft voting ensemble model marked the average balanced accuracy (average of specificity and sensitivity) of 79% (62-98% across all conditions), outperforming individual base models (70-76%). Notably, our models exhibited varying degrees of transferability across different datasets, with performance being dependent on the specific brain states and feature sets used. Feature importance analysis across meta-conditions suggests that the underlying neural mechanisms vary significantly, necessitating tailored approaches for accurate classification of specific brain states. This finding underscores the value of our feature-integrated ensemble models, which leverage the strengths of multiple feature types to achieve robust performance across a broader range of brain states. While our approach offers valuable insights into the neural signatures of different brain states, future work is needed to develop and validate even more generalizable models that can accurately classify brain states across a wider array of conditions.

TopoRoot+: computing whorl and soil line traits of field-excavated maize roots from CT imaging

BackgroundThe use of 3D imaging techniques, such as X-ray CT, in root phenotyping has become more widespread in recent years. However, due to the complexity of the root structure, analyzing the resulting 3D volumes to obtain detailed architectural root traits remains a challenging computational problem. When it comes to image-based phenotyping of excavated maize root crowns, two types of root features that are notably missing from existing methods are the whorls and soil line. Whorls refer to the distinct areas located at the base of each stem node from which roots sprout in a circular pattern (Liu S, Barrow CS, Hanlon M, Lynch JP, Bucksch A. Dirt/3D: 3D root phenotyping for field-grown maize (zea mays). Plant Physiol. 2021;187(2):739–57. https://doi.org/10.1093/plphys/kiab311.). The soil line is where the root stem meets the ground. Knowledge of these features would give biologists deeper insights into the root system architecture (RSA) and the below- and above-ground root properties.ResultsWe developed TopoRoot+, a computational pipeline that produces architectural traits from 3D X-ray CT volumes of excavated maize root crowns. Building upon the TopoRoot software (Zeng D, Li M, Jiang N, Ju Y, Schreiber H, Chambers E, et al. Toporoot: A method for computing hierarchy and fine-grained traits of maize roots from 3D imaging. Plant Methods. 2021;17(1). https://doi.org/10.1186/s13007-021-00829-z.) for computing fine-grained root traits, TopoRoot + adds the capability to detect whorls, identify nodal roots at each whorl, and compute the soil line location. The new algorithms in TopoRoot + offer an additional set of fine-grained traits beyond those provided by TopoRoot. The addition includes internode distances, root traits at every hierarchy level associated with a whorl, and root traits specific to above or below the ground. TopoRoot + is validated on a diverse collection of field-grown maize root crowns consisting of nine genotypes and spanning across three years. TopoRoot + runs in minutes for a typical volume size of \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:40{0}^{3}$$\\end{document} on a desktop workstation. Our software and test dataset are freely distributed on Github.ConclusionsTopoRoot + advances the state-of-the-art in image-based phenotyping of excavated maize root crowns by offering more detailed architectural traits related to whorls and soil lines. The efficiency of TopoRoot + makes it well-suited for high-throughput image-based root phenotyping.