RESUMEN

Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders.

RESUMEN

Leguminous crops are vital to sustainable agriculture due to their ability to fix atmospheric nitrogen, improving soil fertility and reducing the need for synthetic fertilizers. Additionally, they are an excellent source of protein for both human consumption and animal feed. Antimicrobial peptides (AMPs), found in various leguminous seeds, exhibit broad-spectrum antimicrobial activity through diverse mechanisms, including interaction with microbial cell membranes and interference with cellular processes, making them valuable for enhancing crop resilience and food safety. In the field of plant sciences, computational biology methods have been instrumental in the discovery and optimization of AMPs. These methods enable rapid exploration of sequence space and the prediction of AMPs using deep learning technologies. Optimizing AMP annotations through computational design offers a strategic approach to enhance efficacy and minimize potential side effects, providing a viable alternative to conventional antimicrobial agents. However, the presence of overlapping sequences across multiple databases poses a challenge for creating a reliable dataset for AMP prediction. To address this, we conducted a comprehensive analysis of sequence redundancy across various AMP databases. These databases encompass a wide range of AMPs from different sources and with specific functions, including both naturally occurring and artificially synthesized AMPs. Our analysis revealed significant overlap, underscoring the need for a non-redundant AMP sequence database. We present the development of a new database that consolidates unique AMP sequences derived from leguminous seeds, aiming to create a more refined dataset for the binary classification and prediction of plant-derived AMPs. This database will support the advancement of sustainable agricultural practices by enhancing the use of plant-based AMPs in agroecology, contributing to improved crop protection and food security.

RESUMEN

PURPOSE: To investigate the contribution of demographic trends in countries' age and gender composition to value set validity and obsolescence. METHODS: Time-trade off (TTO) valuation data from 3 EQ-5D-3L value sets of 20 years or older from the United Kingdom, Japan, and the United States were re-analyzed using Bayesian heteroskedastic Tobit models with sex and age group-specific scale parameters. Original value sets were obtained by weighting the original preference structures with the countries' original demographic composition at the time of the data collection. Updated value sets were created using the original preference structure weighted using the countries' most recent demographic composition. The differences between the original and updated value sets were monitored and compared based on 95% credible intervals. RESULTS: The gender and age composition of the investigated countries changed in all 3 countries over time. The modelled health state preferences also depended on the respondents' gender and age. However, the overall impact of this demographic change on the investigated value sets was negligeable in all 3 countries and this finding was robust to accounting for the impact of ethnicity trends in the United States. CONCLUSION: Value sets may become redundant and obsolete for various reasons, but demographic change was not identified as a contributing factor.

RESUMEN

Ecosystems that experience elevated CO2 (eCO2) are crucial interfaces where intricate interactions between plants and microbes occur. This study addressed the impact of eCO2 and a N supply on faba bean (Vicia faba L.) growth and the soil microbial community in auto-controlled growth chambers. In doing so, two ambient CO2 concentrations (aCO2, daytime/nighttime = 410/460 ppm; eCO2, 550/610 ppm) and two N supplement levels (without a N supply-N0-and 100 mg N as urea per kg of soil-N100) were applied. The results indicated that eCO2 mitigated the inhibitory effects of a N deficiency on legume photosynthesis and affected the CO2 assimilation efficiency, in addition to causing reduced nodulation. While the N addition counteracted the reductions in the N concentrations across the faba beans' aboveground and belowground plant tissues under eCO2, the CO2 concentrations did not significantly alter the soil NH4+-N or NO3--N responses to a N supply. Notably, under both aCO2 and eCO2, a N supply significantly increased the relative abundance of Nitrososphaeraceae and Nitrosomonadaceae, while eCO2 specifically reduced the Rhizobiaceae abundance with no significant changes under aCO2. A redundancy analysis (RDA) highlighted that the soil pH (p < 0.01) had the most important influence on the soil microbial community. Co-occurrence networks indicated that the eCO2 conditions mitigated the impact of a N supply on the reduced structural complexity of the soil microbial communities. These findings suggest that a combination of eCO2 and a N supply to crops can provide potential benefits for managing future climate change impacts on crop production.

RESUMEN

The redundancy present within the musculoskeletal system may offer a non-invasive source of signals for movement augmentation, where the set of muscle activations that do not produce force/torque (muscle-to-force null-space) could be controlled simultaneously to the natural limbs. Here, we investigated the viability of extracting movement augmentation control signals from the muscles of the wrist complex. Our study assessed (i) if controlled variation of the muscle activation patterns in the wrist joint's null-space is possible; and (ii) whether force and null-space cursor targets could be reached concurrently. During the null-space target reaching condition, participants used muscle-to-force null-space muscle activation to move their cursor towards a displayed target while minimising the exerted force as visualised through the cursor's size. Initial targets were positioned to require natural co-contraction in the null-space and if participants showed a consistent ability to reach for their current target, they would rotate 5 ∘ incrementally to generate muscle activation patterns further away from their natural co-contraction. In contrast, during the concurrent target reaching condition participants were required to match a target position and size, where their cursor position was instead controlled by their exerted flexion-extension and radial-ulnar deviation, while its size was changed by their natural co-contraction magnitude. The results collected from 10 participants suggest that while there was variation in each participant's co-contraction behaviour, most did not possess the ability to control this variation for muscle-to-force null-space virtual reaching. In contrast, participants did show a direction and target size dependent ability to vary isometric force and co-contraction activity concurrently. Our results indicate the limitations of using the muscle-to-force null-space activity of joints with a low level of redundancy as a possible command signal for movement augmentation.

Asunto(s)

RESUMEN

Introduction: In tractography, redundancy poses a significant challenge, often resulting in tractograms that include anatomically implausible streamlines or those that fail to represent the brain's white matter architecture accurately. Current filtering methods aim to refine tractograms by addressing these issues, but they lack a unified measure of redundancy and can be computationally demanding. Methods: We propose a novel framework to quantify tractogram redundancy based on filtering tractogram subsets without endorsing a specific filtering algorithm. Our approach defines redundancy based on the anatomical plausibility and diffusion signal representation of streamlines, establishing both lower and upper bounds for the number of false-positive streamlines and the tractogram redundancy. Results: We applied this framework to tractograms from the Human Connectome Project, using geometrical plausibility and statistical methods informed by the streamlined attributes and ensemble consensus. Our results establish bounds for the tractogram redundancy and the false-discovery rate of the tractograms. Conclusion: This study advances the understanding of tractogram redundancy and supports the refinement of tractography methods. Future research will focus on further validating the proposed framework and exploring tractogram compression possibilities.

RESUMEN

Myelin-forming oligodendrocytes in the vertebrate nervous system co-express the transcription factor Sox10 and its paralog Sox8. While Sox10 plays crucial roles throughout all stages of oligodendrocyte development, including terminal differentiation, the loss of Sox8 results in only mild and transient perturbations. Here, we aimed to elucidate the roles and interrelationships of these transcription factors in fully differentiated oligodendrocytes and myelin maintenance in adults. For that purpose, we conducted targeted deletions of Sox10, Sox8, or both in the brains of two-month-old mice. Three weeks post-deletion, none of the resulting mouse mutants exhibited significant alterations in oligodendrocyte numbers, myelin sheath counts, myelin ultrastructure, or myelin protein levels in the corpus callosum, despite efficient gene inactivation. However, differences were observed in the myelin gene expression in mice with Sox10 or combined Sox8/Sox10 deletion. RNA-sequencing analysis on dissected corpus callosum confirmed substantial alterations in the oligodendrocyte expression profile in mice with combined deletion and more subtle changes in mice with Sox10 deletion alone. Notably, Sox8 deletion did not affect any aspects of the expression profile related to the differentiated state of oligodendrocytes or myelin integrity. These findings extend our understanding of the roles of Sox8 and Sox10 in oligodendrocytes into adulthood and have important implications for the functional relationship between the paralogs and the underlying molecular mechanisms.

Asunto(s)

RESUMEN

The environmental changes from climatic, terrestrial and anthropogenic drivers can significantly influence the groundwater quality that may pose a threat to human health. However, the driving mechanism of groundwater quality and potential health risk still remains to be studied. In this paper, 165 groundwater samples were analyzed to evaluate the groundwater quality, driving mechanism, and probabilistic health risk in the central Yinchuan Plain by applying fuzzy comprehensive evaluation method (FCEM), redundance analysis (RDA) and Monte Carlo simulation. The results showed that hydrochemical evolution of groundwater were strongly influenced by water-rock interaction, evaporation and human activities. While 55.2% of groundwater samples reached the drinking water quality standard (Class I, II and III), 44.8% of samples exceeded the standard limits of Class III water quality (Class IV and V), indicating a high pollution level of groundwater. Mn, TDS, NH4+, NO3-, Fe, F-, NO2-, As were among major indicators that influence the groundwater quality due to the natural and anthropogenic processes. The RDA analysis revealed that climatic factors (PE: 10.9%, PRE: 1.1%), GE chemical properties (ORP: 20.7%, DO: 2.4%), hydrogeological factors (BD: 16.5%, K: 4.1%), and terrestrial factors (elevation: 1.2%; distanced: 5.6%, distancerl: 1.5%, NDVI: 1.2%) were identified as major driving factors influencing the groundwater quality in the study area. The HHRA suggested that TCR values of arsenic in infants, children and teens greatly exceeded the acceptable risk threshold of 1E-4, indicating a high cancer risk with a basic trend: infants > children > teens, while TCR values of adults were within the acceptable risk level. THI values of four age groups in the RME scenario were nearly ten times higher than those in the CTE scenario, displaying a great health effect on all age groups (HQ > 1). The present study provides novel insights into the driving mechanism of groundwater quality and potential health hazard in arid and semi-arid regions.

Asunto(s)

RESUMEN

Lentic small water bodies (LSWBs) deteriorate owing to anthropogenic activities, such as untreated domestic and agricultural waste disposal. Moreover, different turnover mechanisms occur during different seasons, contributing to nutrient enrichment and consequent degradation of LSWBs. However, understanding their spatial, temporal, and vertical variations during different seasons is understudied. In addition, studies on the variation in water quality under varying rainfall and land-use conditions are limited. Therefore, in this study, three LSWBs located in Northern India were studied during the pre-monsoon and monsoon seasons (December 2022 to October 2023). Total nitrogen (TN), chlorophyll-a (Chl-a), total phosphorus (TP), temperature, pH, dissolved oxygen (DO), total dissolved solids (TDS), chemical oxygen demand (COD), secchi disk depth (SDD), and water level (WL) were measured monthly. Sentinel-2 and CHIRPS pentad data were used for land use, land cover classification, and rainfall analysis. The spatial analysis indicates that the seasonal shift affects the water quality distribution, especially near the inlets and at the edges. The overall concentrations of TN and TP decreased during the monsoon season; however, they increased significantly at the inlets of the LSWBs. On the other hand, the Chl-a concentration shifted towards the edges due to the inflow during the monsoon. Temporal analysis also suggests that the arrival of the monsoon lowers pH, DO, and TDS. However, the concentrations of TN and TP increased because of agricultural runoff. Chl-a and COD show distinct variations due to the individual LSWBs' local conditions. Vertical variability analysis demonstrated pH, temperature, and TN stratification during the pre-monsoon period. However, during the monsoon, stratification is less significant due to intermixing. Redundancy analysis (RDA) showed that land use and rainfall patterns affected the water quality of LSWB 1, 2, and 3 by 53.49%, 81.62%, and 92.64%, respectively. This shows that land use, land cover, and rainfall changes affect the water quality of LSWBs. This study highlights the negative impact of runoff from agricultural land use as the main factor responsible for increased nutrient levels in the LSWBs.

RESUMEN

Phytoplankton functional groups have been increasingly utilized in elucidating and predicting the response of phytoplankton species to environmental conditions and seasonal succession in various aquatic systems including lakes, rivers and reservoirs. However, it is still unclear whether the trait-based functional classification can be applied to spring-type lakes. To understand the temporal and spatial characteristics of phytoplankton functional groups and their responses to environmental factors in spring-type urban lake in northern China, an investigation was conducted in Daming Lake from May 2020 to September 2021. The findings revealed the identification of 98 phytoplankton taxa belonging to 6 phyla, predominantly being Chlorophyta (39.8%), Bacillariophyta (35.7%) and Cyanophyta (15.3%). The dominant species were Microcystis sp., Merismopedia minima, Synedra acus and Scenedesmus quadricauda. These phytoplankton taxa were categorized into 21 functional groups, with 6 dominant functional groups (abbreviated as D, MP, P, J, Lo, and W1). Among them, the functional group D, primarily constituted by S. acus, exhibited absolute predominance. The seasonal succession sequence of the dominant functional groups was as follows: D/P/J/MP/ Lo →→ D/P/W1/MP/Lo/J → D/P/J → D/MP → D/P/MP. Throughout the investigation period, the trophic level index (TLI) ranged from 39.10 to 71.13, and the Q index was from 1.91 to 2.91, both indicating a medium health state for Daming Lake, which was consistent with the evaluation results of the diversity index. The results of redundancy analysis revealed that the main driving factors of phytoplankton FG biomass and composition were water temperature (WT), total nitrogen (TN), transparency (SD), TN:TP (N:P), redox potential (ORP), chemical oxygen demand (CODMn) and pH. The dominance of the functional group D positively correlated with water temperature, TN, CODMn, pH and N:P but negatively correlated with SD. It was observed that functional groups and the Q index can objectively indicate the seasonal succession of phytoplankton and the water quality status of Daming Lake. Our discoveries have significant implications for the comprehension of the effects of urbanization on phytoplankton dynamics and for enhancing lake management practices to foster sustainable urban development.

RESUMEN

The risk of information leaks increases as images become a crucial medium for information sharing. There is a great need to further develop the versatility of image encryption technology to protect confidential and sensitive information. Herein, using high spatial redundancy (strong correlation of neighboring pixels) of the image and the in situ encryption function of a quantum dot functionalized encryption camera, in situ image encryption is achieved by designing quantum dot films (size, color, and full width at half maximum) to modify the correlation and reduce spatial redundancy of the captured image during encryption processing. The correlation coefficients of simulated encrypted image closely apporach to 0. High-quality decrypted images are achieved with a PSNR of more than 35 dB by a convolutional neural network-based algorithm that meets the resolution requirements of human visual perception. Compared with the traditional image encryption algorithms, chaotic image encryption algorithms and neural network-based encryption algorithms described previously, it provides a universal, efficient and effective in situ image encryption method.

RESUMEN

Heavy metal pollution mainly caused by human activities is becoming increasingly prominent and threatening human health and ecosystem safety in soil, which is a non-renewable natural resource that humans rely on for survival and development. Assessment and analysis of soil heavy metal health risk is significant for protecting human health, preventing soil pollution, and maintaining ecosystem security. Based on the investigation of heavy metals, including Cr, Pb, Cd, As, and Hg, in cultivated soil in Liuhe District, the health risk assessment model was used to identify the health risk characteristics of heavy metals, and the spatial distribution, main sources, and responses to landscape patterns were explored by using inverse distance weight interpolation, positive definite matrix factorization, landscape pattern index, and redundancy analysis. The results showed that the coefficients of variation corresponding to Cr, Pb, Cd, As, and Hg in the study area were 0.19, 0.36, 0.23, 0.52, and 1.16, respectively, all of which belonged to moderate or high variability, indicating that they had high spatial heterogeneity and were susceptible to human factors. Cr, Pb, and As were the main health risk characteristic factors in the study area, with the carcinogenic risks to children ranging from 13.307×10-6 to 38.400×10-6, 0.839×10-6 to 3.250×10-6, and 4.548×10-6 to 16.680×10-6, respectively, which were higher than those in adults. Agricultural production activities, industrial production, and transportation activities were the main sources of heavy metals, with carcinogenic risks to children of 17.946×10-6 and 12.941×10-6, respectively. Furthermore, high-risk areas caused by agricultural production activities were mainly concentrated in the northern area of Liuhe District and showed an increasing trend from south to north and from the center to the periphery. The surrounding areas caused by industrial production activities and transportation were mainly concentrated in the chemical industry park and economic development zone of Liuhe District and showed a spatial agglomeration feature of decreasing from south to north and from the core to the periphery. The cumulative explanatory value of the landscape pattern index for the comprehensive carcinogenic risk to children was 0.463, and patch density, patch proportion in landscape area, patch aggregation degree, and maximum patch index had significant effects on the comprehensive carcinogenic risk in children, and the corresponding explanatory values were 0.422, 0.274, 0.351, and 0.232, respectively. This study had important theoretical and practical significance for expanding the perspective of environmental health research, promoting the transformation of soil heavy metal management methods and safeguarding regional population health.

Asunto(s)

RESUMEN

Both the metabolic theory of ecology and dynamic energy budget theory predict that climate influences body size through its effects on first-order determinants of energetics: reactive temperatures, carbon resources and oxygen availability. Although oxygen is seldom limiting in terrestrial systems, temperature and resources vary spatially. We used redundancy analyses and variation partitioning to evaluate the influence of climatic temperature, precipitation and their seasonalities on multivariate body size across the distributions of four species of the western rattlesnake group in North America (Crotalus pyrrhus, C. scutulatus, C. oreganus and C. viridis). Most species showed a pattern of increased body size in cooler, mesic climates and decreased body size in warmer, xeric climates. Exceptions to the pattern provided additional context through climatic idiosyncrasies in the distributions of each species. For example, the general pattern of a negative influence of temperature on body size was not apparent for C. oreganus, which ranges across the mildest climates overall among the four species. In contrast to previous studies, we found that seasonality had negligible effects on body size. We suggest that precipitation gradients correlate positively with resource availability in driving intraspecific body size and that temperature compounds this gradient by increasing baseline metabolic demands and restricting activity in particularly warm or otherwise extreme climates.

RESUMEN

The biogenesis of functional forms of chloroplast ribosomal RNAs (rRNAs) is crucial for the translation of chloroplast mRNAs into polypeptides. However, the molecular mechanisms underlying the proper processing and maturation of chloroplast rRNA species are poorly understood. Through a genetic approach, we isolated and characterized an Arabidopsis mutant, α1-4, harboring a missense mutation in the plastid chaperonin-60α1 gene. Using allelism tests and transgenic manipulation, we determined functional redundancy among ptCPN60 subunits. The ptCPN60α1S57F mutation caused specific defects in the formation of chloroplast rRNA species, including 23S, 5S, and 4.5S rRNAs, but not 16S rRNAs. Allelism tests suggested that the dysfunctional ptCPN60α1S57F competes with other members of the ptCPN60 family. Indeed, overexpression of the ptCPN60α1S57F protein in wild-type plants mimicked the phenotypes observed in the α1-4 mutant, while increasing the endogenous transcriptional levels of ptCPN60α2, ß1, ß2, and ß3 in the α1-4 mutant partially mitigated the abnormal fragmentation processing of chloroplast 23S, 5S, and 4.5S rRNAs. Furthermore, we demonstrated functional redundancy between ptCPN60ß1 and ptCPN60ß2 in chloroplast rRNA processing through double-mutant analysis. Collectively, our data reveal a novel physiological role of ptCPN60 subunits in generating the functional rRNA species of the large 50S ribosomal subunit in Arabidopsis chloroplasts.

RESUMEN

Autonomous vehicles (AVs) rely heavily on sensors to perceive their surrounding environment and then make decisions and act on them. However, these sensors have weaknesses, and are prone to failure, resulting in decision errors by vehicle controllers that pose significant challenges to their safe operation. To mitigate sensor failures, it is necessary to understand how they occur and how they affect the vehicle's behavior so that fault-tolerant and fault-masking strategies can be applied. This survey covers 108 publications and presents an overview of the sensors used in AVs today, categorizes the sensor's failures that can occur, such as radar interferences, ambiguities detection, or camera image failures, and provides an overview of mitigation strategies such as sensor fusion, redundancy, and sensor calibration. It also provides insights into research areas critical to improving safety in the autonomous vehicle industry, so that new or more in-depth research may emerge.

RESUMEN

Numerous factors can contribute to a difficult colonoscopy, potentially leading to an incomplete procedure and overlooked lesions. Alternative strategies for handling difficult and incomplete colonoscopies should be considered. We present the case of an 85-year-old male who underwent a difficult colonoscopy, during which two expert endoscopists spent 1.5 h attempting various techniques but failed to intubate the cecum. Subsequently, colonic transendoscopic enteral tubing (TET) was performed. Abdominal plain film revealed tortuosity of the TET tube in the left abdomen corresponding to the distribution of the descending colon. Retrograde colon imaging was conducted by injecting a mixture of contrast medium and air into the colon via the TET tube. X-ray demonstrated well-developed visualization of the entire colon and terminal ileum. And evident elongation and tortuosity of the descending colon resembled an N-type folding pattern. The final diagnosis was determined as descending colon redundancy. Colonic TET combined with retrograde colon imaging through the TET tube may serve as an effective supplementary approach for identifying causes of difficult colonoscopy and improving diagnostic accuracy for bowel diseases when complete visualization is not achieved.

RESUMEN

Duplicated genes are thought to follow one of three evolutionary trajectories that resolve their redundancy: neofunctionalization, subfunctionalization or pseudogenization. Differences in expression patterns have been documented for many duplicated gene pairs and interpreted as evidence of subfunctionalization and a loss of redundancy. However, little is known about the functional impact of such differences and about their molecular basis. Here, we investigate the genetic and molecular basis for the partial loss of redundancy between the two BLADE-ON-PETIOLE genes BOP1 and BOP2 in Red Shepherd's Purse (Capsella rubella) compared to Arabidopsis (Arabidopsis thaliana). While both genes remain almost fully redundant in A. thaliana, BOP1 in C. rubella can no longer ensure wild-type floral organ numbers and suppress bract formation, due to an altered expression pattern in the region of the cryptic bract primordium. We use two complementary approaches, transgenic rescue of A. thaliana atbop1 atbop2 double mutants and deletions in the endogenous AtBOP1 promoter, to demonstrate that several BOP1 promoter regions containing conserved non-coding sequences interact in a non-additive manner to control BOP1 expression in the bract primordium, and that changes in these interactions underlie the evolutionary divergence between C. rubella and A. thaliana BOP1 expression and activity. Similarly, altered interactions between cis-regulatory regions underlie the divergence in functional promoter architecture related to the control of floral organ abscission by BOP1. These findings highlight the complexity of promoter architecture in plants and suggest that changes in the interactions between cis-regulatory elements are key drivers for evolutionary divergence in gene expression and the loss of redundancy.

RESUMEN

Rapid environmental change poses unprecedented challenges to species persistence. To understand the extent that continued change could have, genomic offset methods have been used to forecast maladaptation of natural populations to future environmental change. However, while their use has become increasingly common, little is known regarding their predictive performance across a wide array of realistic and challenging scenarios. Here, we evaluate the performance of currently available offset methods (gradientForest, the Risk-Of-Non-Adaptedness, redundancy analysis with and without structure correction and LFMM2) using an extensive set of simulated data sets that vary demography, adaptive architecture and the number and spatial patterns of adaptive environments. For each data set, we train models using either all, adaptive or neutral marker sets and evaluate performance using in silico common gardens by correlating known fitness with projected offset. Using over 4,849,600 of such evaluations, we find that (1) method performance is largely due to the degree of local adaptation across the metapopulation (LA), (2) adaptive marker sets provide minimal performance advantages, (3) performance within the species range is variable across gardens and declines when offset models are trained using additional non-adaptive environments and (4) despite (1) performance declines more rapidly in globally novel climates (i.e. a climate without an analogue within the species range) for metapopulations with greater LA than lesser LA. We discuss the implications of these results for management, assisted gene flow and assisted migration.

RESUMEN

Objective: A patient-independent approach for continuous estimation of vital signs using robust spectro-temporal features derived from only photoplethysmogram (PPG) signal. Methods: In the pre-processing stage, we remove baseline shifts and artifacts of the PPG signal using Incremental Merge Segmentation with adaptive thresholding. From the cleaned PPG, we extract multiple parameters independent of individual patient PPG morphology for both Respiration Rate (RR) and Blood Pressure (BP). In addition, we derived a set of novel spectral and statistical features strongly correlated to BP. We proposed robust correlation-based feature selection methods for accurate RR estimates. For fewer computations and accurate measurements of BP, the most significant features are selected using correlation and mutual information measures in the feature engineering part. Finally, RR and BP are estimated using breath counting and a neural network regression model, respectively. Results: The proposed approach outperforms the current state-of-the-art in both RR and BP. The RR algorithm results in mean absolute errors (median, 25th-75th percentiles) of 0.4 (0.1-0.7) for CapnoBase dataset and 0.5(0.3-2.8) for BIDMC dataset without discarding any data window. Similarly, BP approach has been validated on a large dataset derived from MIMIC-II ([Formula: see text]1700 records) which has errors (mean absolute, standard deviation) of 5.0(6.3) and 3.0(4.0) for systolic and diastolic BP, respectively. The results meet the American Association for the Advancement of Medical Instrumentation (AAMI) and British Hypertension Society (BHS) Class A criteria. Conclusion: By using robust features and feature selection methods, we alleviated patient dependency to have reliable estimates of vitals.