Bird Dataset Research Articles

Impact of Sliding Window Variation and Neuronal Time Constants on Acoustic Anomaly Detection Using Recurrent Spiking Neural Networks in Automotive Environment

Acoustic perception of the automotive environment has the potential to advance driving potentials with enhanced safety. The challenge arises when these acoustic perception systems need to perform under resource and power constraints on edge devices. Neuromorphic computing has introduced spiking neural networks in the context of ultra-low power sensory edge devices. Spiking architectures leverage biological plausibility to achieve computational capabilities, accurate performance, and great compatibility with neuromorphic hardware. In this work, we explore the depths of spiking neurons and feature components with the acoustic scene analysis task for siren sounds. This research work aims to address the qualitative analysis of sliding windows’ variation on the feature extraction front of the preprocessing pipeline. Optimization of the parameters to exploit the feature extraction stage facilitates the advancement of the performance of the acoustics anomaly detection task. We exploit the parameters for mel spectrogram features and FFT calculations, prone to be suitable for computations in hardware. We conduct experiments with different window sizes and the overlapping ratio within the windows. We present our results for performance measures like accuracy and onset latency to provide an insight on the choice of optimal window. The non-trivial motivation of this research is to understand the effect of encoding behavior of spiking neurons with different windows. We further investigate the heterogeneous nature of membrane and synaptic time constants and their impact on the accuracy of anomaly detection. On a large scale audio dataset comprising of siren sounds and road traffic noises, we obtain accurate predictions of siren sounds using a recurrent spiking neural network. The baseline dataset comprising siren and noise sequences is enriched with a bird dataset to evaluate the model with unseen samples.

Investigating the relative role of dispersal and demographic traits in predictive phylogeography

Many studies suggest that aside from environmental variables, such as topography and climate, species‐specific ecological traits are relevant to explain the geographic distribution of intraspecific genetic lineages. Here, we investigated whether and to what extent incorporating such traits systematically improves the accuracy of random forest models in predicting genetic differentiation among pairs of localities. We leveraged available ecological datasets for birds and tested the inclusion of two categories of ecological traits: dispersal‐related traits (i.e. morphology and foraging ecology) and demographic traits (such as species survival rate and generation length). We estimated genetic differentiation from published mitochondrial DNA sequences for 28 species of birds (1578 total genetic samples, 391 localities) in the Atlantic Forest of South America. Aside from the aforementioned ecological traits, we included geographic, topographic and climatic distances between localities as environmental predictors. We then created models using all available data to evaluate model uncertainty both across space and across the different categories of predictors. Finally, we investigated model uncertainty in predicting genetic differentiation individually for each species (a common challenge in conservation biology). Our results show that while environmental conditions are the most important predictors of genetic differentiation, model accuracy largely increases with the addition of ecological traits. Additionally, the inclusion of dispersal traits improves model accuracy to a larger extent than the inclusion of demographic traits. Similar results are observed in models for individual species, although model accuracy is highly variable. We conclude that ecological traits improve predictive models of genetic differentiation, refining our ability to predict phylogeographic patterns from existing data. Additionally, demographic traits may not be as informative as previously hypothesized. Finally, prediction of genetic differentiation for species with conservation concerns may require further careful assessment of the environmental and ecological variation within the species range.

Accounting for nonlinear responses to traits improves range shift predictions

AbstractAccurately predicting species' range shifts in response to environmental change is paramount for understanding ecological processes and global change. In synthetic analyses, traits emerge as significant but weak predictors of species' range shifts across recent climate change. These studies assume linear responses to traits, while detailed empirical work often reveals trait responses that are unimodal and contain thresholds or other nonlinearities. We hypothesize that the use of linear modeling approaches fails to capture these nonlinearities and, therefore, may be under‐powering traits to predict range shifts. We evaluate the predictive performance of approaches that can capture nonlinear relationships (ridge‐regularized linear regression, support vector regression with linear and nonlinear kernels, and random forests). We apply our models using six multidecadal range shift datasets for plants, moths, marine fish, birds, and small mammals. We show that nonlinear approaches can perform better than least‐squares linear modeling in reproducing historical range shifts. Consistent with expectations, we identify dispersal and climatic niche traits as primary determinants of distribution shifts. Traits identified as important predictors and the direction of trait effects are generally consistent across models, but there are notable exceptions. Among important predictors, there are more consistent responses to climatic niches than dispersal ability. Modest improvements in predictability when accounting for nonlinearities and interactions, and the overall low amount of variance accounted for by trait predictors suggest limits to trait‐based statistical predictive frameworks.

Ocurrence dataset of birds in university campuses of Nanjing, Juangsu Province China.

The protection of urban biodiversity plays a critical role in maintaining urban ecological security. As a unique taxon of urban wildlife, birds have been intensively used as an indicator of our surrounding environment. Although the diversity of urban bird species has received increasing attention, present studies are mainly focused on urban parks. As one of the important components of the urban ecosystem, the university campus also plays a critical role in maintaining bird diversity. Due to the lack of observation data, it is a challenge to evaluate the impact of the environmental conditions on campus bird diversity. Given the most concentrated higher education resources in China, Nanjing has a large number of universities, covering a wide area of the urban landscape. The landscape of these universities usually has a high percentage of green space as well as waterbodies, which is conducive to attracting various bird species to inhabit. Here, we conducted a one-year bird survey from January 2019 to December 2019 in 12 universities in Nanjing and provided an occurrence dataset containing detailed species and geographical information, providing a good source to study the ecological and anthropogenic factors on urban bird diversity on a local and larger scale. This dataset represents the first annual record of birds publicly released by 12 universities in Nanjing, Jiangsu Province. It includes classification information, population, distribution and survey details. All data have been published on GBIF.

Multimodal bird information retrieval system

Multimodal bird information retrieval system can help people popularize bird knowledge and help bird conservation. In this paper, we use the self-built bird dataset, the ViT-B/32 model in CLIP model as the training model, python as the development language, and PyQT5 to complete the interface development. The system mainly realizes the uploading and displaying of bird pictures, the multimodal retrieval function of bird information, and the introduction of related bird information. The results of the trial run show that the system can accomplish the multimodal retrieval of bird information, retrieve the species of birds and other related information through the pictures uploaded by the user, or retrieve the most similar bird information through the text content described by the user.

BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes

Automatic recognition of bird behavior from long-term, un controlled outdoor imagery can contribute to conservation efforts by enabling large-scale monitoring of bird populations. Current techniques in AI-based wildlife monitoring have focused on short-term tracking and monitoring birds individually rather than in species-rich flocks. We present Bird-Collect, a comprehensive benchmark dataset for monitoring dense bird flock attributes. It includes a unique collection of more than 6,000 high-resolution images of Demoiselle Cranes (Anthropoides virgo) feeding and nesting in the vicinity of Khichan region of Rajasthan. Particularly, each image contains an average of 190 individual birds, illustrating the complex dynamics of densely populated bird flocks on a scale that has not previously been studied. In addition, a total of 433 distinct pictures captured at Keoladeo National Park, Bharatpur provide a comprehensive representation of 34 distinct bird species belonging to various taxonomic groups. These images offer details into the diversity and the behaviour of birds in vital natural ecosystem along the migratory flyways. Additionally, we provide a set of 2,500 point-annotated samples which serve as ground truth for benchmarking various computer vision tasks like crowd counting, density estimation, segmentation, and species classification. The benchmark performance for these tasks highlight the need for tailored approaches for specific wildlife applications, which include varied conditions including views, illumination, and resolutions. With around 46.2 GBs in size encompassing data collected from two distinct nesting ground sets, it is the largest birds dataset containing detailed annotations, showcasing a substantial leap in bird research possibilities. We intend to publicly release the dataset to the research community. The database is available at: https://iab-rubric.org/resources/wildlife-dataset/birdcollect

Functional constraints on the number and shape of flight feathers

As a fundamental ecological aspect of most organisms, locomotor function significantly constrains morphology. At the same time, the evolution of novel locomotor abilities has produced dramatic morphological transformations, initiating some of the most significant diversifications in life history. Despite significant new fossil evidence, it remains unclear whether volant locomotion had a single or multiple origins in pennaraptoran dinosaurs and the volant abilities of individual taxa are controversial. The evolution of powered flight in modern birds involved exaptation of feathered surfaces extending off the limbs and tail yet most studies concerning flight potential in pennaraptorans do not account for the structure and morphology of the wing feathers themselves. Analysis of the number and shape of remex and rectrix feathers across a large dataset of extant birds indicates that the number of remiges and rectrices and the degree of primary vane asymmetry strongly correlate with locomotor ability revealing important functional constraints. Among these traits, phenotypic flexibility varies reflected by the different rates at which morphological changes evolve, such that some traits reflect the ancestral condition, whereas others reflect current locomotor function. While Mesozoic birds and Microraptor have remex morphologies consistent with extant volant birds, that of anchiornithines deviate significantly providing strong evidence this clade was not volant. The results of these analyses support a single origin of dinosaurian flight and indicate the early stages of feathered wing evolution are not sampled by the currently available fossil record.

PPA‐ResNet: An Airport Bird Recognition Model Based on Improved ResNet

With the development of air transport and improved ecological environment, bird strikes on aircraft have become a significant threat to flight safety. Accurate and efficient identification of airport birds can enhance the efficiency of airport staff in bird strike prevention. Public datasets for bird classification are typically limited in size and not specifically tailored for airport birds. Therefore, this paper introduces a self‐built airport bird dataset, ADB‐20, and proposes an image recognition method based on an improved ResNet model. First, this paper replaces traditional convolution in the residual structure with the Pyramidal Convolution method, ensuring the extraction of multiscale features. Second, it introduces the Parallel Convolutional Block Attention Moduleto the backbone network, considering features in both channel and spatial dimensions. Last, the Atrous Spatial Pyramid Pooling module is incorporated to capture contextual information at various scales. Experimental results show that the PPA‐ResNet model achieves an accuracy of 95.2%, with a recall of 93.7%, a precision of 96.8%, and an F1 score of 95.2% on the ADB‐20 dataset. The proposed algorithm significantly enhances classification performance compared to other mainstream image classification algorithms. These indicators confirm that the results of this study can precisely identify airport birds, aid airport personnel in making informed decisions, and guarantee the safety of aviation transport.

Trends and Spatiotemporal Patterns of Avian Influenza Outbreaks in Italy: A Data-Driven Approach.

In recent years, the unprecedented spread of the Avian Influenza Viruses (AIVs) among birds and mammals has caused devastation in animal populations, including poultry, wild birds, and some mammals, damaging farmers' livelihoods and the food trade. Given the urgency of the situation, it is particularly important that scientists and the public can access research results and data as soon as possible. The main aim of this study is to present a global open-access dataset of Avian Influenza outbreaks to enable researchers and policymakers (i) to rapidly detect, and respond to animal outbreaks as the first line of defense; (ii) to conduct epidemiological and virological investigations around animal outbreaks and human infections; and (iii) to communicate the risk. We show the potential use of this dataset to the research community by analyzing the most updated information on past and current Highly Pathogenic Avian Influenza (HPAI) outbreaks in domestic poultry and wild birds over the period from October 2021 to July 2023 in Italy. In addition, we applied indices borrowed from Economics (such as Homogeneity, Specialization, and Location Index) to the wild birds dataset to show their possible usage in epidemiology.

Occurrence dataset of birds in Sihong Hongze Lake Wetlands National Nature Reserve in China.

Hongze Lake is China's fourth largest freshwater lake and is also an important habitat for hundreds of thousands of migratory birds on the East Asian-Australian Flyway (EAAF). Sihong Hongze Lake Wetlands National Nature Reserve is located on the northwest of Hongze Lake, Sihong County, Jiangsu Province. The Reserve is a protected large area of natural lake wetlands, marsh wetlands and riverine wetlands and used as a stopover and wintering habitats for migratory birds. Previous studies have conducted bird diversity and temporal-spatial variation in this Reserve, but only for species of Anseriformes. There is still a lack of a comprehensive dataset on the number of bird species and individuals in this Reserve throughout the year. Our study was conducted from July 2020 to June 2021 to observe bird species composition and individual numbers at Sihong Hongze Lake Wetlands National Nature Reserve and provides an occurrence dataset with detailed species and geographic information. This occurrence dataset is the first public record of birds in Sihong Hongze Lake Wetlands National Nature Reserve for a whole year, which includes the taxonomic information, location information, number, investigation date and endangered level for each species. All data have been published on GBIF.

SPARSE 1.0: a template for databases of species inventories, with an open example of Czech birds.

Here, we introduce SPARSE (acronym for "SPecies AcRoss ScalEs"), a simple and portable template for databases that can store data on species composition derived from ecological inventories, surveys and checklists, with emphasis on metadata describing sampling effort and methods. SPARSE can accommodate resurveys and time series and data from different spatial scales, as well as complex sampling designs. SPARSE focuses on inventories that report multiple species for a given site, together with sampling methods and effort, which can be used in statistical models of true probability of occurrence of species. SPARSE is spatially explicit and can accommodate nested spatial structures from multiple spatial scales, including sampling designs where multiple sites within a larger area have been surveyed and the larger area can again be nested in an even larger region. Each site in SPARSE is represented either by a point, line (for transects) or polygon, stored in an ESRI shapefile. SPARSE implements a new combination of our own field definitions with Darwin Core biodiversity data standard and its Humboldt core extension. The use of Humboldt core also makes SPARSE suitable for biodiversity data with temporal replication. We provide an example use of the SPARSE framework by digitising data on birds from the Czech Republic, from 348 sites and 524 sampling events, with 15,969 unique species-per-event observations of presence, abundance or population density. To facilitate use without the need for a high-level database expertise, the Czech bird example is implemented as MS Access .accdb file, but can be ported to other database engines. The example of Czech birds complements other bird datasets from the Czech Republic, specifically the four gridded national atlases and the breeding bird survey which cover a similar temporal extent, but different locations and spatial scales.

Bird Object Detection: Dataset Construction, Model Performance Evaluation, and Model Lightweighting.

The application of object detection technology has a positive auxiliary role in advancing the intelligence of bird recognition and enhancing the convenience of bird field surveys. However, challenges arise due to the absence of dedicated bird datasets and evaluation benchmarks. To address this, we have not only constructed the largest known bird object detection dataset, but also compared the performances of eight mainstream detection models on bird object detection tasks and proposed feasible approaches for model lightweighting in bird object detection. Our constructed bird detection dataset of GBDD1433-2023, includes 1433 globally common bird species and 148,000 manually annotated bird images. Based on this dataset, two-stage detection models like Faster R-CNN and Cascade R-CNN demonstrated superior performances, achieving a Mean Average Precision (mAP) of 73.7% compared to one-stage models. In addition, compared to one-stage object detection models, two-stage object detection models have a stronger robustness to variations in foreground image scaling and background interference in bird images. On bird counting tasks, the accuracy ranged between 60.8% to 77.2% for up to five birds in an image, but this decreased sharply beyond that count, suggesting limitations of object detection models in multi-bird counting tasks. Finally, we proposed an adaptive localization distillation method for one-stage lightweight object detection models that are suitable for offline deployment, which improved the performance of the relevant models. Overall, our work furnishes an enriched dataset and practice guidelines for selecting suitable bird detection models.

Pairwise Guided Multilayer Cross-Fusion Network for Bird Image Recognition

Bird identification is the first step in collecting data on bird diversity and abundance, which also helps research on bird distribution and population measurements. Most research has built end-to-end training models for bird detection task via CNNs or attentive models, but many perform unsatisfactorily in fine-grained bird recognition. Bird recognition tasks are highly influenced by factors, including the similar appearance of different subcategories, diverse bird postures, and other interference factors such as tree branches and leaves from the background. To tackle this challenge, we propose the Progressive Cross-Union Network (PC-Net) to capture more subtle parts with low-level attention maps. Based on cross-layer information exchange and pairwise learning, the proposed method uses two modules to improve feature representation and localization. First, it utilizes low- and high-level information for cross-layer feature fusion, which enables the network to extract more comprehensive and discriminative features. Second, the network incorporates deep semantic localization to identify and enhance the most relevant regions in the images. In addition, the network is designed with a semantic guidance loss to improve its generalization for variable bird poses. The PC-Net was evaluated on an extensively used birds dataset (CUB-200-2011), which contains 200 birds subcategories. The results demonstrate that the PC-Net achieved an impressive recognition accuracy of 89.2%, thereby outperforming maintained methods in bird subcategory identification. We also achieved competitive results on two other datasets with data on cars and airplanes. The results indicated that the PC-Net improves the accuracy of diverse bird recognition, as well as other fine-grained recognition scenarios.

NEAL: an open-source tool for audio annotation.

Passive acoustic monitoring is used widely in ecology, biodiversity, and conservation studies. Data sets collected via acoustic monitoring are often extremely large and built to be processed automatically using artificial intelligence and machine learning models, which aim to replicate the work of domain experts. These models, being supervised learning algorithms, need to be trained on high quality annotations produced by experts. Since the experts are often resource-limited, a cost-effective process for annotating audio is needed to get maximal use out of the data. We present an open-source interactive audio data annotation tool, NEAL (Nature+Energy Audio Labeller). Built using R and the associated Shiny framework, the tool provides a reactive environment where users can quickly annotate audio files and adjust settings that automatically change the corresponding elements of the user interface. The app has been designed with the goal of having both expert birders and citizen scientists contribute to acoustic annotation projects. The popularity and flexibility of R programming in bioacoustics means that the Shiny app can be modified for other bird labelling data sets, or even to generic audio labelling tasks. We demonstrate the app by labelling data collected from wind farm sites across Ireland.

Variable-length sequence model for attribute detection in the image

Holistic scene understanding is a challenging problem in computer vision. Most recent researches in this field were focusing on the object detection, the semantic segmentation and the relationship detection tasks. The attribute can provide meaningful information for the object instance, thus the object instance can be expressed more detail in the scene understanding. However, most researches in this field have been limited to several special conditions. Such as, several researches were just focusing on the attribute of special object class, because their solutions were aimed at a limited-scenarios, their methods are hardly to generalize in other scenarios. We also find that most of the research for multi-attribute detection task were only regarding each attribute as binary class and simply use the multi-binary-classifier method for the attribute detection. But these strategies above not consider the relation between each pair of the attributes, they will fall into trouble in the “imperfect” attribute dataset (which is labeled with the missing and incomplete annotations), and they will have low performance in the long-tail attribute class (which has lower rank of annotation and more missing labels). In this paper, we focus on the multi-attribute detection for a variant of object classes and take the relation between attributes into consideration. We propose a GRU-based model to detect a variable-length attribute sequence with a customized loss compute method to solve the “imperfect” attribute dataset problem. Furthermore, we perform ablative studies to prove the effectiveness of each part of our method. Finally, we compare our model with several existed multi-attribute detection methods on VG (Visual Genome) and CUB200 bird datasets to prove the superior performance of the proposed model.

Characterizing bird species for achieving the win-wins of conserving biodiversity and enhancing regulating ecosystem services in urban green spaces

Urban green spaces provide regulating ecosystem services (RS) to humans and contribute to biodiversity conservation under urbanization pressure. However, trade-offs arise while making development decisions in urban green space planning, as the prioritization of enhancing RS may not always contribute to biodiversity conservation and vice versa. Therefore, achieving a balance between these trade-offs becomes essential in promoting conservation strategies that maximize win-win outcomes for both biodiversity and RS, ultimately leading to sustainable urban development. A practical approach to strike this balance is to prioritize specific species as surrogates for population protection, thereby benefiting co-occurring species and promoting the maintenance of a high RS level. To explore this approach, we conducted monthly bird surveys in green spaces over five years along an urbanization gradient in Shanghai, China. Based on the monthly bird dataset, to begin, we used indicator species analysis to identify bird indicators for the monthly RS (which were calculated from an economic perspective). Following from that, the umbrella index was used to prioritize umbrella species for biodiversity conservation. Finally, surrogate species were selected on the basis of their identification as both RS indicators and umbrella species. Consequently, seven common species were identified as surrogates in Shanghai. The RS indicator species were mainly omnivores and tree-nesting, with most umbrella species belonging to this subset. Furthermore, understanding the population dynamics of surrogate species could provide information on overall biodiversity and RS status, facilitating the optimization of management strategies and policies in cities. Our integrated approach, which combines indicator and umbrella species, provides a tool for establishing connections between ecosystem service maintenance and biodiversity conservation. This approach is useful in promoting planning strategies to conserve biodiversity while ensuring sustainable provision of ecosystem services and can be applied in the sustainable management of human-dominated landscapes.

SiulMalaya: an annotated bird audio dataset of Malaysia lowland forest birds for passive acoustic monitoring

The laborious point count method of conducting bird surveys is still a common practice in Malaysia. An alternative method known as passive acoustic monitoring (PAM) is deployed in many countries by placing sound recorders at surveying sites to collect bird sounds. Studies revealed that the number of bird densities counted by human observers was agreeable with those obtained using PAM. However, one of the most essential gaps in conducting PAM is the lack of expert-verified bird-call databases. Therefore, the aim of this study is to construct the first annotated Malaysia lowland forest bird sounds called SiulMalaya to be used as ground-truth datasets for PAM-related activities. The raw bird sounds dataset was downloaded from Macaulay Library using the eBird platform. Data pre-processing was done to produce annotated audio tracks that can be used as training datasets for bird classification. SiulMalaya dataset was further validated by two bird experts from the Department of Wildlife and National Parks, Malaysia. A bird identification experiment was carried out to assess and validate SiulMalaya dataset using a convolutional neural network (CNN) learning model. Even though the accuracy of bird identification is slightly above 50%, the annotated dataset is shown to be viable for PAM-related operations.

SiulMalaya: an annotated bird audio dataset of Malaysia lowland forest birds for passive acoustic monitoring

The laborious point count method of conducting bird surveys is still a common practice in Malaysia. An alternative method known as passive acoustic monitoring (PAM) is deployed in many countries by placing sound recorders at surveying sites to collect bird sounds. Studies revealed that the number of bird densities counted by human observers was agreeable with those obtained using PAM. However, one of the most essential gaps in conducting PAM is the lack of expert-verified bird-call databases. Therefore, the aim of this study is to construct the first annotated Malaysia lowland forest bird sounds called SiulMalaya to be used as ground-truth datasets for PAM-related activities. The raw bird sounds dataset was downloaded from Macaulay Library using the eBird platform. Data pre-processing was done to produce annotated audio tracks that can be used as training datasets for bird classification. SiulMalaya dataset was further validated by two bird experts from the Department of Wildlife and National Parks, Malaysia. A bird identification experiment was carried out to assess and validate SiulMalaya dataset using a convolutional neural network (CNN) learning model. Even though the accuracy of bird identification is slightly above 50%, the annotated dataset is shown to be viable for PAM-related operations.

RCVNet: A bird damage identification network for power towers based on fusion of RF images and visual images

The technology for identifying birds around power towers using cameras alone is still susceptible to environmental interference. This paper proposes a new bird damage recognition network, RCVNet, which addresses this issue by fusing radio-frequency (RF) images and visual images. The network employs a feature layer fusion approach that accurately identifies bird damages in the monitoring area. Initially, RCVNet takes a group of RF and visual images as input. Then, through a series of convolutional neural networks (CNNs), birds are identified and located. To overcome challenges in recognizing small targets, several improved modules such as cross-supervised fusion network (CSF-net), posture deformable convolution (PDF), small-target attention fusion mechanism (SAFM), and Tiny-YOLOHead are introduced throughout RCVNet, improving surface information utilization and small feature retention rates. Finally, a bird damage discrimination strategy is developed based on the recognition outcomes of birds. As there is currently no public dataset available for RCVNet training, a new bird dataset called CRB2022, which includes RF and visual images, was gathered. Through large-scale experiments utilizing these methods, RCVNet effectively identifies birds, achieving a mean average precision of 79.34% and a mean average recall of 83.29%. Additionally, the discrimination rate of the utilized strategy can reach up to 98%.

Identification of taxon through classification with partial reject options

Abstract Identification of taxa can significantly be assisted by statistical classification based on trait measurements either individually or by phylogenetic (clustering) methods. In this article, we present a general Bayesian approach for classifying species individually based on measurements of a mixture of continuous and ordinal traits, and any type of covariates. The trait vector is derived from a latent variable with a multivariate Gaussian distribution. Decision rules based on supervised learning are presented that estimate model parameters through blocked Gibbs sampling. These decision regions allow for uncertainty (partial rejection), so that not necessarily one specific category (taxon) is output when new subjects are classified, but rather a set of categories including the most probable taxa. This type of discriminant analysis employs reward functions with a set-valued input argument, so that an optimal Bayes classifier can be defined. We also present a way of safeguarding against outlying new observations, using an analogue of a p-value within our Bayesian setting. We refer to our Bayesian set-valued classifier as the Karlsson–Hössjer method, and it is illustrated on an original ornithological data set of birds. We also incorporate model selection through cross-validation, exemplified on another original data set of birds.