Cross Dataset Research Articles

Indigeneity in Context—Evolving Maya Ch’orti’ Notions of Cultural Identity: A Qualitative Study From 1993 to 2019

The Maya Ch’orti’ people are Indigenous to the border regions of Honduras and Guatemala. For a great number of years, they have faced structural racism and discrimination combined with continued land dispossession. In the contexts of colonization and the creation of the modern Honduran state, any identification with Indigenous groups has generally had negative connotations. Since the advent of the Indigenous Peoples’ Rights Discourses (IPRD), however, more communities have actively aligned with the Maya Ch’orti’ people. In our investigation of the ways in which cultural identity and belonging to a Maya Ch’orti’ community have shifted and evolved over time, we analyzed a total of 45 interview transcripts across three time points (1990s: n = 15, 2003–2004: n = 15, and 2018–2019: n = 15) using thematic analysis and a cross–data set analysis. Five major themes were developed: “Our land,” “In the past, we were oppressed and ashamed,” “Difficult present life: We are still oppressed,” “Maya Ch’orti’ revitalization and empowerment,” and “Being Indigenous.” As we compared these themes across our time points, it became apparent that notions of cultural identity have evolved in the Maya Ch’orti’ community from a negative appraisal to a positive, empowered, and confident notion. Our findings are being discussed in connection to the context of the IPRD and Indigenous peoples in other countries.

CME Velocity Field Calculation Model Based on an Unsupervised Transformer Optical Flow Network

The optical flow algorithm (OF) is one the main methods for calculating image velocity field and has many applications in space weather. Most OF calculations are applied to the motion of labeled rigid objects and are not suitable for velocity detection of high-energy particles, such as in a coronal mass ejection (CME). Fluctuations in exposure time and the influence of space weather will lead to inconsistent brightness of the same feature point at different times. To address this problem, we propose an unsupervised multiscale optical flow network based on Vision Transformer, named UTFlowNet. The network comprises a multiscale feature extraction module and a coarse-to-fine global optical flow calculation module. The movement of high-energy particles emitted during a CME eruption follows certain physical rules. Therefore, we apply fluid motion–based loss functions to analyze the motion of high-energy particles more effectively, addressing the problem of CME motion field extraction. Our method can be applied to the real-time automatic extraction of a CME’s velocity field and performs well with inconsistent brightness, large-scale motion, and strong CME noise. Additionally, we can estimate subpixel level fine-grained velocity. Our model may be affected by overfitting during cross–data set inference, so we encourage performing a small amount of transfer learning on new data sets to mitigate this issue. In order to verify the accuracy of our method, we conducted experiments and verification on the Solar and Heliospheric Observatory LASCO C2 data and the High Altitude Observatory MLSO data. We constructed a large-scale displacement simulation data set based on LASCO C2 data and tested on it, achieving the best results.

Early Prediction of Cardiac Arrest in the Intensive Care Unit Using Explainable Machine Learning: Retrospective Study.

Cardiac arrest (CA) is one of the leading causes of death among patients in the intensive care unit (ICU). Although many CA prediction models with high sensitivity have been developed to anticipate CA, their practical application has been challenging due to a lack of generalization and validation. Additionally, the heterogeneity among patients in different ICU subtypes has not been adequately addressed. This study aims to propose a clinically interpretable ensemble approach for the timely and accurate prediction of CA within 24 hours, regardless of patient heterogeneity, including variations across different populations and ICU subtypes. Additionally, we conducted patient-independent evaluations to emphasize the model's generalization performance and analyzed interpretable results that can be readily adopted by clinicians in real-time. Patients were retrospectively analyzed using data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) and the eICU-Collaborative Research Database (eICU-CRD). To address the problem of underperformance, we constructed our framework using feature sets based on vital signs, multiresolution statistical analysis, and the Gini index, with a 12-hour window to capture the unique characteristics of CA. We extracted 3 types of features from each database to compare the performance of CA prediction between high-risk patient groups from MIMIC-IV and patients without CA from eICU-CRD. After feature extraction, we developed a tabular network (TabNet) model using feature screening with cost-sensitive learning. To assess real-time CA prediction performance, we used 10-fold leave-one-patient-out cross-validation and a cross-data set method. We evaluated MIMIC-IV and eICU-CRD across different cohort populations and subtypes of ICU within each database. Finally, external validation using the eICU-CRD and MIMIC-IV databases was conducted to assess the model's generalization ability. The decision mask of the proposed method was used to capture the interpretability of the model. The proposed method outperformed conventional approaches across different cohort populations in both MIMIC-IV and eICU-CRD. Additionally, it achieved higher accuracy than baseline models for various ICU subtypes within both databases. The interpretable prediction results can enhance clinicians' understanding of CA prediction by serving as a statistical comparison between non-CA and CA groups. Next, we tested the eICU-CRD and MIMIC-IV data sets using models trained on MIMIC-IV and eICU-CRD, respectively, to evaluate generalization ability. The results demonstrated superior performance compared with baseline models. Our novel framework for learning unique features provides stable predictive power across different ICU environments. Most of the interpretable global information reveals statistical differences between CA and non-CA groups, demonstrating its utility as an indicator for clinical decisions. Consequently, the proposed CA prediction system is a clinically validated algorithm that enables clinicians to intervene early based on CA prediction information and can be applied to clinical trials in digital health.

Combined spatial and frequency dual stream network for face forgery detection.

With the development of generative model, the cost of facial manipulation and forgery is becoming lower and lower. Fraudulent data has brought numerous hidden threats in politics, privacy, and cybersecurity. Although many methods of face forgery detection focus on the learning of high frequency forgery traces and achieve promising performance, these methods usually learn features in spatial and frequency independently. In order to combine the information of the two domains, a combined spatial and frequency dual stream network is proposed for face forgery detection. Concretely, a cross self-attention (CSA) module is designed to improve frequency feature interaction and fusion at different scales. Moreover, to augment the semantic and contextual information, frequency guided spatial feature extraction module is proposed to extract and reconstruct the spatial information. These two modules deeply mine the forgery traces via a dual-stream collaborative network. Through comprehensive experiments on different datasets, we demonstrate the effectiveness of proposed method for both within and cross datasets.

Multi-scale nested UNet with transformer for colorectal polyp segmentation.

Polyp detection and localization are essential tasks for colonoscopy. U-shape network based convolutional neural networks have achieved remarkable segmentation performance for biomedical images, but lack of long-range dependencies modeling limits their receptivefields. Our goal was to develop and test a novel architecture for polyp segmentation, which takes advantage of learning local information with long-range dependenciesmodeling. A novel architecture combining with multi-scale nested UNet structure integrated transformer for polyp segmentation was developed. The proposed network takes advantage of both CNN and transformer to extract distinct feature information. The transformer layer is embedded between the encoder and decoder of a U-shape net to learn explicit global context and long-range semantic information. To address the challenging of variant polyp sizes, a MSFF unit was proposed to fuse features with multipleresolution. Four public datasets and one in-house dataset were used to train and test the model performance. Ablation study was also conducted to verify each component of the model. For dataset Kvasir-SEG and CVC-ClinicDB, the proposed model achieved mean dice score of 0.942 and 0.950 respectively, which were more accurate than the other methods. To show the generalization of different methods, we processed two cross dataset validations, the proposed model achieved the highest mean dice score. The results demonstrate that the proposed network has powerful learning and generalization capability, significantly improving segmentation accuracy and outperforming state-of-the-artmethods. The proposed model produced more accurate polyp segmentation than current methods on four different public and one in-house datasets. Its capability of polyps segmentation in different sizes shows the potential clinicalapplication.

Gut microbiome-metabolome interactions predict host condition

BackgroundThe effect of microbes on their human host is often mediated through changes in metabolite concentrations. As such, multiple tools have been proposed to predict metabolite concentrations from microbial taxa frequencies. Such tools typically fail to capture the dependence of the microbiome-metabolite relation on the environment.ResultsWe propose to treat the microbiome-metabolome relation as the equilibrium of a complex interaction and to relate the host condition to a latent representation of the interaction between the log concentration of the metabolome and the log frequencies of the microbiome. We develop LOCATE (Latent variables Of miCrobiome And meTabolites rElations), a machine learning tool to predict the metabolite concentration from the microbiome composition and produce a latent representation of the interaction. This representation is then used to predict the host condition. LOCATE’s accuracy in predicting the metabolome is higher than all current predictors. The metabolite concentration prediction accuracy significantly decreases cross datasets, and cross conditions, especially in 16S data. LOCATE’s latent representation predicts the host condition better than either the microbiome or the metabolome. This representation is strongly correlated with host demographics. A significant improvement in accuracy (0.793 vs. 0.724 average accuracy) is obtained even with a small number of metabolite samples (∼50\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim 50$$\\end{document}).ConclusionThese results suggest that a latent representation of the microbiome-metabolome interaction leads to a better association with the host condition than any of the two separated or the simple combination of the two.65xPsFnnFGsq3M5WjZwrxcVideo

On the representation and methodology for wide and short range head pose estimation

Head pose estimation (HPE) is a problem of interest in computer vision to improve the performance of face processing tasks in semi-frontal or profile settings. Recent applications require the analysis of faces in the full 360° rotation range. Traditional approaches to solve the semi-frontal and profile cases are not directly amenable for the full rotation case. In this paper we analyze the methodology for short- and wide-range HPE and discuss which representations and metrics are adequate for each case. We show that the popular Euler angles representation is a good choice for short-range HPE, but not at extreme rotations. However, the Euler angles’ gimbal lock problem prevents them from being used as a valid metric in any setting. We also revisit the current cross-data set evaluation methodology and note that the lack of alignment between the reference systems of the training and test data sets negatively biases the results of all articles in the literature. We introduce a procedure to quantify this misalignment and a new methodology for cross-data set HPE that establishes new, more accurate, SOTA for the 300W-LP/Biwi benchmark. We also propose a generalization of the geodesic angular distance metric that enables the construction of a loss that controls the contribution of each training sample to the optimization of the model. Finally, we introduce a wide range HPE benchmark based on the CMU Panoptic data set. code:https://github.com/pcr-upm/opal23_headpose

Data Augmentation for Genetic Programming-Driven Late Merging of HOG and Uniform LBP Features for Texture Classification

The categorization of texture images requires the identification and extraction of meaningful keypoints, a crucial step in ensuring the precise representation of textured images. The literature has introduced numerous descriptors in order to detect and capture both local and global texture characteristics. These descriptors vary in their effectiveness depending on the specific application. However, it is generally accepted that they complement each other by compensating for their strengths and weaknesses. Therefore, many approaches focused on combining different types of image descriptors generating robust features that are invariant to image transformations. These solutions mostly focused on one way to deal with information and faced more problems as they need human intervention and a large set of data. The acknowledged benefits of combining multiple types of descriptors are accompanied by challenges specially. These challenges arise due to differences in properties, such as locality and sparsity, as well as the heterogeneity exhibited by generated features. To address this issue comprehensively, we present an approach that benefits from genetic programming techniques to generate and combine two distinct texture classifiers. It incorporates histograms of oriented gradients and local binary patterns descriptors, which capture different textures. To effectively fuse the results of both classifiers, the proposed approach employs a late fusion process along with data augmentation methods while using a limited amount of training data. To evaluate the performance of the proposed approach in texture image classification tasks, we have conducted extensive experiments on six challenging datasets encompassing various variations. We have also investigated its performance in a cross dataset problem where the model has been trained on instances of a dataset before being tested on samples of another dataset. The obtained results clearly demonstrate that the proposed approach surpasses other relevant low-level approaches, as well as existing GP-based and CNN methods specifically designed for describing and classifying textures. Thanks to its ability to simultaneously leverage multiple descriptors, the suggested solution shows a high potential for real-world applications, particularly in handling various image changes with robustness.

Markov-based Neural Networks for Heart Sound Segmentation: Using domain knowledge in a principled way.

This work considers the problem of segmenting heart sounds into their fundamental components. We unify statistical and data-driven solutions by introducing Markov-based Neural Networks (MNNs), a hybrid end-to-end framework that exploits Markov models as statistical inductive biases for an Artificial Neural Network (ANN) discriminator. We show that an MNN leveraging a simple one-dimensional Convolutional ANN significantly outperforms two recent purely data-driven solutions for this task in two publicly available datasets: PhysioNet 2016 (Sensitivity: 0.947 ±0.02; Positive Predictive Value : 0.937 ±0.025) and the CirCor DigiScope 2022 (Sensitivity: 0.950 ±0.008; Positive Predictive Value: 0.943 ±0.012). We also propose a novel gradient-based unsupervised learning algorithm that effectively makes the MNN adaptive to unseen datum sampled from unknown distributions. We perform a cross dataset analysis and show that an MNN pre-trained in the CirCor DigiScope 2022 can benefit from an average improvement of 3.90% Positive Predictive Value on unseen observations from the PhysioNet 2016 dataset using this method.

Leakage diagnosis of district heating-network based on system simulation and PCA_BP neural network

To increase leakage diagnosis (LD) efficiency of heating-networks and overcome the lack of actual leakage data, a LD method is proposed based on system simulation and principal component analysis (PCA)_back propagation (BP) neural network that treats the LD problem as a pattern recognition one. In this method, a hydraulic working-condition (HWC) simulation model is constructed to obtain model datasets (MD) of heating-network operation and HWC experiments are conducted to obtain experimental datasets (ED), then cross datasets (CD) is constructed by mixing MD and ED with different ratio. These three datasets are handled through the PCA to unify data feature distribution and realize feature transfer learning in neural network. Then two BP neural networks are trained by ED and CD respectively and both tested with ED. Finally, four kinds of experimental heating-networks, including a branch network with single heat source (B-SHS), a branch network with double heat sources (B-DHS), a single-ring network with single heat source (SR-SHS) and a double-ring network with double heat sources (DR-DHS), are researched. The results indicate that the LD prediction accuracy of BP neural network trained by CD is higher than that one trained by ED. The LD prediction accuracy varies with the cross-data ratio: from 97.52% to 92.21% for B-SHS, from 97.23% to 92.02% for B-DHS, from 97.85% to 89.74% for SR-SHS, and from 95.89% to 92.50% for DR-DHS. Furthermore, the proposed LD method based on BP neural network has better transfer learning performance than that based on random forest or support vector machine.

Rethinking Training Strategy in Stereo Matching.

In stereo matching, various learning-based approaches have shown impressive performance in solving traditional difficulties on multiple datasets. While most progress is obtained on a specific dataset with a dataset-specific network design, the performance on the single dataset and cross dataset affected by training strategy is often ignored. In this article, we analyze the relationship between different training strategies and performance by retraining some representative state-of-the-art methods (e.g., geometry and context network (GC-Net), pyramid stereo matching network (PSM-Net), and guided aggregation network (GA-Net), etc.). According to our research, it is surprising that the performance of networks on single or cross datasets is significantly improved by pre-training and data augmentation without any particular structure acquirement. Based on this discovery, we improve our previous non-local context attention network (NLCA-Net) to NLCA-Net v2 and train it with the novel strategy and rethink the training strategy of stereo matching concurrently. The quantitative experiments demonstrate that: 1) our model is capable of reaching top performance on both the single dataset and the multiple datasets with the same parameters in this study, which also won the 2nd place in the stereo task of the ECCV Robust vision Challenge 2020 (RVC 2020); and 2) on small datasets (e.g., KITTI, ETH3D, and Middlebury), the model's generalization and robustness are significantly affected by pre-training and data augmentation, even exceeding the network structure's influence in some cases. These observations present a challenge to the conventional wisdom of network architectures in this stage. We expect these discoveries to encourage researchers to rethink the current paradigm of ``excessive attention on the performance of a single small dataset'' in stereo matching.

Towards Equitable Healthcare: A Cross Dataset Analysis of Healthcare and Telehealth Access

ABSTRACTHistory has repeatedly shown that when it comes to healthcare, there exist significant disparities across different sub‐populations. Part of this problem is challenges with access to healthcare services and providers. In recent years, we have seen solutions emerge that attempt to address this issue, namely telehealth. But little to no work has been done to glean insights into factors contributing to lower access and whether telehealth adequately supports populations that struggle with physical access issues. In this paper, we present findings from an exploratory, cross‐dataset analysis of healthcare access in Virginia, USA. We conducted quantitative and qualitative analyses lyses to determine correlations between socioeconomic factors and physical access. We found that population density significantly impacts physical access to healthcare. We also found that lower income communities in rural areas appear to be less satisfied with the quality of care and less likely to have adequate access to alternative options such as telehealth services. Our work has implications for research aimed at understanding healthcare access and practice that aims to derive solutions to close the healthcare access gap.

A Four-Point Camera Calibration Method for Sport Videos

The main objective of camera calibration is to estimate the homography between a sports field template and the corresponding field in a video frame. State-of-the-art approaches exploit deep-learning technologies to achieve this aim. However, the lack of large training datasets leads to unreliable results. Search-based approaches deliver better accuracy but at the expense of a very high computational cost. In this paper, a four-point camera calibration method is proposed to address these challenges. It consists of four stages: first, a conditional generative adversarial network (cGAN) is used to generate meaningfully segmented video frames. This cGAN is a general image-to-image translation technique which has robust performance even for small training datasets. The aim is to eliminate foreground objects that greatly impede accurate estimation of four suitable points for the subsequent stage. Then, a regression network which can estimate four points from a single segmented video frame is introduced. In this stage we aim at keeping the low computational cost. In the next processing stage, the estimated four points and the original selected four points are used to calculate the homography. In this third stage a Direct Linear Transformation (DLT) algorithm is applied. In the last processing stage, the accuracy of the estimated homography is refined by running an Enhanced Correlation Coefficient (ECC) module. The proposed method is extensively evaluated using a standard 2014 World Cup dataset. The obtained results are compared to the state-of-the-art approaches and its variations based on U-net, VGG-16, ResNet-50. The obtained results show that the proposed method is superior in terms of accuracy and computational efficiency. To demonstrate the effectiveness and robustness of the proposed method, it is also validated on National Basketball, 2018 World Cup and cross dataset. In these diverse environments, the proposed method still maintains the competitive performance.

Meta Generative Attack on Person Reidentification

Adversarial attacks have been recently investigated in person re-identification. These attacks perform well under cross dataset or cross model setting. However, the challenges present in cross-dataset cross-model scenario does not allow these models to achieve similar accuracy. To this end, we propose our method with the goal of achieving better transferability against different models and across datasets. We generate a mask to obtain better performance across models and use meta learning to boost the generalizability in the challenging cross-dataset cross-model setting. Experiments on Market-1501, DukeMTMC-reID and MSMT-17 demonstrate favorable results compared to other attacks.

Multiscale residual gradient attention for face anti-spoofing

In the field of face anti-spoofing (FAS), how to extract the representative features to distinguish between real and spoof faces and train the corresponding deep networks are two vital issues. In this paper, we propose a simple but effective end-to-end FAS model based on an innovative texture extractor and a depth auxiliary supervision mechanism. In the feature extraction stage, we first design the residual gradient convolutions based on the redesigned gradient operators, which are used to extract fine-grained texture features. The extraction of texture features is based on multiple scales by dividing the texture differences between living and spoofing faces into three levels reasonably. Then we construct a multiscale residual gradient attention (MRGA) to obtain representative texture features from multiple levels texture features. By combining the proposed feature extractor MRGA and existing vision transformer (ViT), the MRGA-ViT is proposed to generate related semantics and obtain final classification results. In the training stage, we also propose a local depth auxiliary supervision based on a novel adjacent depth loss, which utilizes the correlation information of adjacent pixels adequately compared with traditional depth loss. The proposed MRGA-ViT model achieves competitive performance in generalization and stability ability, e.g., the ACER(%) values of intra testing on OULU-NPU database are 1.8, 2.6, 1.6 ± 1.2 and 1.9 ± 2.7 respectively, the AUC(%) of cross type testing attains 99.45 ± 0.57, the ACER(%) values of cross dataset testing are 28.1 and 36.7 respectively. Experimental results prove that the proposed model is competitive to other state-of-the-art works on generalization and stability performance.

CNN-based, contextualized, real-time fire detection in computational resource-constrained environments

The increasing occurrence of wildfires, amplified by the changing climate conditions and drought, poses threats to human lives, the environment and the geographically dispersed infrastructures. Such impact necessitates the prompt identification of wildfires so that appropriate countermeasures are taken. The availability of electronic equipment, such as Unmanned Aerial Vehicles, allows for images from dynamically changing, geographical areas, which must be directly processed for wildfire identification and contextualization. In this work, we identify the requirements and the constraints in terms of computational resources of this workflow, and investigate lightweight CNNs to be used. SqueezeNet, ShuffleNet, MobileNetv2 as well as ResNet50 are used for fire identification. To simulate the realistic conditions, we have investigated multiple datasets, selecting Forest-Fire and Fire-Flame datasets and images from 3rd party sources and performed cross-dataset identification evaluation. To rationalize the required computational resources and the operation cost, lightweight networks have been selected and compared with ResNet-50, which is more complex. The contextualization, i.e. the detection of elements related to energy infrastructures, has been based on image semantic segmentation, performed through ResNet-18. The identification results, expressed as classification accuracy has reached 96%, with satisfactory results in the cross dataset scenarios, while we have identified five classes from the CamVid dataset which can be used for the contextualization needs.

PDAtt-Unet: Pyramid Dual-Decoder Attention Unet for Covid-19 infection segmentation from CT-scans

Since the emergence of the Covid-19 pandemic in late 2019, medical imaging has been widely used to analyze this disease. Indeed, CT-scans of the lungs can help diagnose, detect, and quantify Covid-19 infection. In this paper, we address the segmentation of Covid-19 infection from CT-scans. To improve the performance of the Att-Unet architecture and maximize the use of the Attention Gate, we propose the PAtt-Unet and DAtt-Unet architectures. PAtt-Unet aims to exploit the input pyramids to preserve the spatial awareness in all of the encoder layers. On the other hand, DAtt-Unet is designed to guide the segmentation of Covid-19 infection inside the lung lobes. We also propose to combine these two architectures into a single one, which we refer to as PDAtt-Unet. To overcome the blurry boundary pixels segmentation of Covid-19 infection, we propose a hybrid loss function. The proposed architectures were tested on four datasets with two evaluation scenarios (intra and cross datasets). Experimental results showed that both PAtt-Unet and DAtt-Unet improve the performance of Att-Unet in segmenting Covid-19 infections. Moreover, the combination architecture PDAtt-Unet led to further improvement. To Compare with other methods, three baseline segmentation architectures (Unet, Unet++, and Att-Unet) and three state-of-the-art architectures (InfNet, SCOATNet, and nCoVSegNet) were tested. The comparison showed the superiority of the proposed PDAtt-Unet trained with the proposed hybrid loss (PDEAtt-Unet) over all other methods. Moreover, PDEAtt-Unet is able to overcome various challenges in segmenting Covid-19 infections in four datasets and two evaluation scenarios.

SANet-SI: A new Self-Attention-Network for Script Identification in scene images

Developing an automatic method for identifying scripts in natural scene text images is of great importance for improving performance of multilingual OCR. This paper presents a new Self-Attention Network (SANet-SI) for script identification in natural scene text images. The rationale behind proposing SANet-SI is that each script exhibits its own pattern because of different characteristics of scripts. To extract such observations, we explore self-attention-based CNN with a multi-scale feature extraction approach. The proposed multi-scale feature extraction involves local, global features extraction and fusion of both the features. Furthermore, to extract dominant features from the pool of features that contribute more for script identification, we explore Style-based Recalibration Module (SRM) in a new way. In addition, to improve the performance of the identification and reduce the model size, the proposed model uses the Global Average Pooling (GAP) layer, instead of Fully Connected(FC) layers in this work. The proposed model is evaluated on standard datasets, namely, RRC-MLT2017, SIW-13, and CVSI2015 to show effectiveness over state-of-the-art methods in terms of confusion matrix and classification rate. In addition, we also conducted experiments for Cross Dataset Validation to show that the proposed model is independent of the number of scripts and different datasets.

Consilience Across Multiple, Independent Genomic Data Sets Reveals Species in a Complex with Limited Phenotypic Variation.

Species delimitation in the genomic era has focused predominantly on the application of multiple analytical methodologies to a single massive parallel sequencing (MPS) data set, rather than leveraging the unique but complementary insights provided by different classes of MPS data. In this study, we demonstrate how the use of two independent MPS data sets, a sequence capture data set and a single-nucleotide polymorphism (SNP) data set generated via genotyping-by-sequencing, enables the resolution of species in three complexes belonging to the grass genus Ehrharta, whose strong population structure and subtle morphological variation limit the effectiveness of traditional species delimitation approaches. Sequence capture data are used to construct a comprehensive phylogenetic tree of Ehrharta and to resolve population relationships within the focal clades, while SNP data are used to detect patterns of gene pool sharing across populations, using a novel approach that visualizes multiple values of K. Given that the two genomic data sets are independent, the strong congruence in the clusters they resolve provides powerful ratification of species boundaries in all three complexes studied. Our approach is also able to resolve a number of single-population species and a probable hybrid species, both of which would be difficult to detect and characterize using a single MPS data set. Overall, the data reveal the existence of 11 and five species in the E. setacea and E. rehmannii complexes, with the E. ramosa complex requiring further sampling before species limits are finalized. Despite phenotypic differentiation being generally subtle, true crypsis is limited to just a few species pairs and triplets. We conclude that, in the absence of strong morphological differentiation, the use of multiple, independent genomic data sets is necessary in order to provide the cross-data set corroboration that is foundational to an integrative taxonomic approach. [Species delimitation; genotyping-by-sequencing; population structure; integrative taxonomy; cryptic species; Ehrharta (Poaceae).].

Cross Dataset Analysis for Generalizability of HRV-Based Stress Detection Models.

Stress is an increasingly prevalent mental health condition across the world. In Europe, for example, stress is considered one of the most common health problems, and over USD 300 billion are spent on stress treatments annually. Therefore, monitoring, identification and prevention of stress are of the utmost importance. While most stress monitoring is carried out through self-reporting, there are now several studies on stress detection from physiological signals using Artificial Intelligence algorithms. However, the generalizability of these models is only rarely discussed. The main goal of this work is to provide a monitoring proof-of-concept tool exploring the generalization capabilities of Heart Rate Variability-based machine learning models. To this end, two Machine Learning models are used, Logistic Regression and Random Forest to analyze and classify stress in two datasets differing in terms of protocol, stressors and recording devices. First, the models are evaluated using leave-one-subject-out cross-validation with train and test samples from the same dataset. Next, a cross-dataset validation of the models is performed, that is, leave-one-subject-out models trained on a Multi-modal Dataset for Real-time, Continuous Stress Detection from Physiological Signals dataset and validated using the University of Waterloo stress dataset. While both logistic regression and random forest models achieve good classification results in the independent dataset analysis, the random forest model demonstrates better generalization capabilities with a stable F1 score of 61%. This indicates that the random forest can be used to generalize HRV-based stress detection models, which can lead to better analyses in the mental health and medical research field through training and integrating different models.