Open-Set Recognition of Individual Cows Based on Spatial Feature Transformation and Metric Learning

The automated recognition of individual cows is foundational for implementing intelligent farming. Traditional methods of individual cow recognition from an overhead perspective primarily rely on singular back features and perform poorly for cows with diverse orientation distributions and partial body visibility in the frame. This study proposes an open-set method for individual cow recognition based on spatial feature transformation and metric learning to address these issues. Initially, a spatial transformation deep feature extraction module, ResSTN, which incorporates preprocessing techniques, was designed to effectively address the low recognition rate caused by the diverse orientation distribution of individual cows. Subsequently, by constructing an open-set recognition framework that integrates three attention mechanisms, four loss functions, and four distance metric methods and exploring the impact of each component on recognition performance, this study achieves refined and optimized model configurations. Lastly, introducing moderate cropping and random occlusion strategies during the data-loading phase enhances the model's ability to recognize partially visible individuals. The method proposed in this study achieves a recognition accuracy of 94.58% in open-set scenarios for individual cows in overhead images, with an average accuracy improvement of 2.98 percentage points for cows with diverse orientation distributions, and also demonstrates an improved recognition performance for partially visible and randomly occluded individual cows. This validates the effectiveness of the proposed method in open-set recognition, showing significant potential for application in precision cattle farming management.

Characterizing Families of Spectral Similarity Scores and Their Use Cases for Gas Chromatography-Mass Spectrometry Small Molecule Identification

Metabolomics provides a unique snapshot into the world of small molecules and the complex biological processes that govern the human, animal, plant, and environmental ecosystems encapsulated by the One Health modeling framework. However, this "molecular snapshot" is only as informative as the number of metabolites confidently identified within it. The spectral similarity (SS) score is traditionally used to identify compound(s) in mass spectrometry approaches to metabolomics, where spectra are matched to reference libraries of candidate spectra. Unfortunately, there is little consensus on which of the dozens of available SS metrics should be used. This lack of standard SS score creates analytic uncertainty and potentially leads to issues in reproducibility, especially as these data are integrated across other domains. In this work, we use metabolomic spectral similarity as a case study to showcase the challenges in consistency within just one piece of the One Health framework that must be addressed to enable data science approaches for One Health problems. Here, using a large cohort of datasets comprising both standard and complex datasets with expert-verified truth annotations, we evaluated the effectiveness of 66 similarity metrics to delineate between correct matches (true positives) and incorrect matches (true negatives). We additionally characterize the families of these metrics to make informed recommendations for their use. Our results indicate that specific families of metrics (the Inner Product, Correlative, and Intersection families of scores) tend to perform better than others, with no single similarity metric performing optimally for all queried spectra. This work and its findings provide an empirically-based resource for researchers to use in their selection of similarity metrics for GC-MS identification, increasing scientific reproducibility through taking steps towards standardizing identification workflows.

A Siamese Network-Based Method for Improving the Performance of Sleep Staging with Single-Channel EEG

Sleep staging is of critical significance to the diagnosis of sleep disorders, and the electroencephalogram (EEG), which is used for monitoring brain activity, is commonly employed in sleep staging. In this paper, we propose a novel method for improving the performance of sleep staging models based on Siamese networks, based on single-channel EEG. Our proposed method consists of a Siamese network architecture and a redesigned loss with distance metrics. Two encoders are used in the Siamese network to generate latent features of the EEG epochs, and the contrastive loss, which is also a distance metric, is used to compare the similarity or differences between EEG epochs from the same or different sleep stages. We evaluated our method on single-channel EEGs from different channels (Fpz-Cz and F4-EOG (left)) from two public datasets SleepEDF and MASS-SS3 and achieved the overall accuracies MF1 and Cohen's kappa coefficient of 85.2%, 78.3% and 0.79 on SleepEDF and 87.2%, 82.1% and 0.81 on MASS-SS3. The results show that our method can significantly improve the performance of sleep staging models and outperform the state-of-the-art sleep staging methods. The performance of our method also confirms that the features captured by Siamese networks and distance metrics are useful for sleep staging.

Sage Insights Into the Phylogeny of Salvia: Dealing With Sources of Discordance Within and Across Genomes

Next-generation sequencing technologies have facilitated new phylogenomic approaches to help clarify previously intractable relationships while simultaneously highlighting the pervasive nature of incongruence within and among genomes that can complicate definitive taxonomic conclusions. Salvia L., with ∼1,000 species, makes up nearly 15% of the species diversity in the mint family and has attracted great interest from biologists across subdisciplines. Despite the great progress that has been achieved in discerning the placement of Salvia within Lamiaceae and in clarifying its infrageneric relationships through plastid, nuclear ribosomal, and nuclear single-copy genes, the incomplete resolution has left open major questions regarding the phylogenetic relationships among and within the subgenera, as well as to what extent the infrageneric relationships differ across genomes. We expanded a previously published anchored hybrid enrichment dataset of 35 exemplars of Salvia to 179 terminals. We also reconstructed nearly complete plastomes for these samples from off-target reads. We used these data to examine the concordance and discordance among the nuclear loci and between the nuclear and plastid genomes in detail, elucidating both broad-scale and species-level relationships within Salvia. We found that despite the widespread gene tree discordance, nuclear phylogenies reconstructed using concatenated, coalescent, and network-based approaches recover a common backbone topology. Moreover, all subgenera, except for Audibertia, are strongly supported as monophyletic in all analyses. The plastome genealogy is largely resolved and is congruent with the nuclear backbone. However, multiple analyses suggest that incomplete lineage sorting does not fully explain the gene tree discordance. Instead, horizontal gene flow has been important in both the deep and more recent history of Salvia. Our results provide a robust species tree of Salvia across phylogenetic scales and genomes. Future comparative analyses in the genus will need to account for the impacts of hybridization/introgression and incomplete lineage sorting in topology and divergence time estimation.

Elucidating the Beta-Diversity of the Microbiome: from Global Alignment to Local Alignment

Quantitative comparison among microbiomes can link microbial beta-diversity to environmental features, thus enabling prediction of ecosystem properties or dissection of host-microbiome interaction. However, to compute beta-diversity, current methods mainly employ the entire community profiles of taxa or functions, which can miss the subtle differences caused by low-abundance community members that may play crucial roles in the properties of interest. In this work, I review the distance metrics and search engines that we developed to match microbiomes at a large scale based on whole-community-level similarities, as well as their limitations in tackling the microbiome changes caused by less abundant community features. Then I propose the concept of microbiome "local alignment," including an algorithm to measure microbiome similarity on specific fractions of biodiversity and an indexing strategy for rapidly fetching microbiome local-alignment matches from the data repository.

Elucidating the Beta-Diversity of the Microbiome: from Global Alignment to Local Alignment

Quantitative comparison among microbiomes can link microbial beta-diversity to environmental features, thus enabling prediction of ecosystem properties or dissection of host-microbiome interaction. However, to compute beta-diversity, current methods mainly employ the entire community profiles of taxa or functions, which can miss the subtle differences caused by low-abundance community members that may play crucial roles in the properties of interest. In this work, I review the distance metrics and search engines that we developed to match microbiomes at a large scale based on whole-community-level similarities, as well as their limitations in tackling the microbiome changes caused by less abundant community features. Then I propose the concept of microbiome “local alignment,” including an algorithm to measure microbiome similarity on specific fractions of biodiversity and an indexing strategy for rapidly fetching microbiome local-alignment matches from the data repository.

Virtual Sensing and Sensors Selection for Efficient Temperature Monitoring in Indoor Environments

Real-time estimation of temperatures in indoor environments is critical for several reasons, including the upkeep of comfort levels, the fulfillment of legal requirements, and energy efficiency. Unfortunately, setting an adequate number of sensors at the desired locations to ensure a uniform monitoring of the temperature in a given premise may be troublesome. Virtual sensing is a set of techniques to replace a subset of physical sensors by virtual ones, allowing the monitoring of unreachable locations, reducing the sensors deployment costs, and providing a fallback solution for sensor failures. In this paper, we deal with temperature monitoring in an open space office, where a set of physical sensors is deployed at uneven locations. Our main goal is to develop a black-box virtual sensing framework, completely independent of the physical characteristics of the considered scenario, that, in principle, can be adapted to any indoor environment. We first perform a systematic analysis of various distance metrics that can be used to determine the best sensors on which to base temperature monitoring. Then, following a genetic programming approach, we design a novel metric that combines and summarizes information brought by the considered distance metrics, outperforming their effectiveness. Thereafter, we propose a general and automatic approach to the problem of determining the best subset of sensors that are worth keeping in a given room. Leveraging the selected sensors, we then conduct a comprehensive assessment of different strategies for the prediction of temperatures observed by physical sensors based on other sensors’ data, also evaluating the reliability of the generated outputs. The results show that, at least in the given scenario, the proposed black-box approach is capable of automatically selecting a subset of sensors and of deriving a virtual sensing model for an accurate and efficient monitoring of the environment.