List Of Birds Research Articles

Learning From Human Attention for Attribute-Assisted Visual Recognition.

With prior knowledge of seen objects, humans have a remarkable ability to recognize novel objects using shared and distinct local attributes. This is significant for the challenging tasks of zero-shot learning (ZSL) and fine-grained visual classification (FGVC), where the discriminative attributes of objects have played an important role. Inspired by human visual attention, neural networks have widely exploited the attention mechanism to learn the locally discriminative attributes for challenging tasks. Though greatly promoted the development of these fields, existing works mainly focus on learning the region embeddings of different attribute features and neglect the importance of discriminative attribute localization. It is also unclear whether the learned attention truly matches the real human attention. To tackle this problem, this paper proposes to employ real human gaze data for visual recognition networks to learn from human attention. Specifically, we design a unified Attribute Attention Network (A 2 Net) that learns from human attention for both ZSL and FGVC tasks. The overall model consists of an attribute attention branch and a baseline classification network. On top of the image feature maps provided by the baseline classification network, the attribute attention branch employs attribute prototypes to produce attribute attention maps and attribute features. The attribute attention maps are converted to gaze-like attentions to be aligned with real human gaze attention. To guarantee the effectiveness of attribute feature learning, we further align the extracted attribute features with attribute-defined class embeddings. To facilitate learning from human gaze attention for the visual recognition problems, we design a bird classification game to collect real human gaze data using the CUB dataset via an eye-tracker device. Experiments on ZSL and FGVC tasks without/with real human gaze data validate the benefits and accuracy of our proposed model. This work supports the promising benefits of collecting human gaze datasets and automatic gaze estimation algorithms learning from human attention for high-level computer vision tasks.

Deep transfer learning-based bird species classification using mel spectrogram images.

The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342.

Bird names as critical communication infrastructure in the contexts of history, language, and culture

Standardized taxonomies and lists of birds were created to improve communication. They are linguistic infrastructure―biodiversity indices and dictionaries―that have been painstakingly built and maintained and that have enhanced regional and global participation in the study and enjoyment of birds. Inclusion of people has been a core objective in creating and maintaining these standardized lists, and dissatisfaction and desires to overwrite objectionable names have been associated with them for nearly two centuries. Suggestions that bird names should be changed are continuous. Today, these suggestions include the view that some bird names must be changed to make them more accurate, inoffensive, and culturally appropriate to further increase diversity and inclusion among ornithologists and bird watchers. The latter, meritorious goal has been largely successful thus far despite many ongoing objections. Historic examples indicate that large-scale name changes, however, are not needed to accomplish major societal goals of inclusion. Some barriers to inclusion likely remain, and some changes are likely needed for English names. Often overlooked or underappreciated in name change discussions are that: 1) standardized names lists have had numerically staggering success in fostering inclusion of diverse participants globally; 2) stability is vital in such systems, and destabilization has exclusionary effects; 3) dissatisfaction with such lists and the names they include has been ongoing since these naming systems began; 4) important flexibilities exist in conjunction with these communication systems that enhance local and regional communication (e.g., alternative names in English and other languages); and 5) cultural values, important as they are, are neither universally shared nor constant, and thus risk bringing divisiveness and instability when used as a central reason for change. Consideration of standardized lists of bird names as communication systems in the fuller context of history, language, and culture will improve our management of these systems and their continued utility in fostering inclusion. With standardized, stable naming systems acting as a skeleton, proactively building outwards, both within and among languages and cultures, offers a positive and productive way to increase inclusion and to improve cultural and biodiversity conservation.

Measuring and explaining disagreement in bird taxonomy

Species lists play an important role in biology and practical domains like conservation, legislation, biosecurity and trade regulation. However, their effective use by non-specialist scientific and societal users is sometimes hindered by disagreements between competing lists. While it is well-known that such disagreements exist, it remains unclear how prevalent they are, what their nature is, and what causes them. In this study, we argue that these questions should be investigated using methods based on taxon concept rather than methods based on Linnaean names, and use such a concept-based method to quantify disagreement about bird classification and investigate its relation to research effort. We found that there was disagreement about 38% of all groups of birds recognized as a species, more than three times as much as indicated by previous measures. Disagreement about the delimitation of bird groups was the most common kind of conflict, outnumbering disagreement about nomenclature and disagreement about rank. While high levels of conflict about rank were associated with lower levels of research effort, this was not the case for conflict about the delimitation of bird groups. This suggests that taxonomic disagreement cannot be resolved simply by increasing research effort.

Enhancing Semantic Interoperability in Bird Classification through XML/RDF and SPARQL

Classification of birds is the area that is quite complex and involved such a lot of varieties that demands the correct as well as the professional organization of the information. This study addresses the problem of semantic interoperability in the bird categorization process by means of constructing an ontology which covers all the words used in taxonomic descriptions. The paper exploits XML/RDF standards for semantic web compatibility and Open Link Virtuoso SPARQL Query Editor that enables simple interaction with its tools and visualization in the process of querying and presentation of results. Attempt to develop a specific ontology for bird identification for the purpose of optimizing the accessibility and retrieval of heterogeneous bird-oriented data that ultimately help in building effective knowledge management system in this field. The effectiveness of an ontology is evaluated by its ability to make possible classification of diverse information. This research methodology is proposed for implementation in a broad range of researches, education, and conservation programs that can targeted to enhance their output and increase accuracy.

Chewing lice (Psocodea, Phthiraptera: Amblycera and Ischnocera) in wild birds in Zungarococha, Iquitos (Peru)

The objective of this work was to identify the species of chewing lice collected from thirty wild birds from the town of Zungarococha, Iquitos (Peru). We identified 11 specimens from a total of 36 collected. The species Columbicola passerinae (Wilson, 1941) presented the largest number of hosts, and Motmotnirmus marginellus (Nitzsch, 1874) and Docophorus rufus (Kellogg, 1899) presented the highest prevalence, intensity, and average abundance. This study reports 11 species of lice for the first time, and new host associations, expanding the list of host birds in Peru.

Research for Drone Target Classification Method Using Deep Learning Techniques

Classification of drones and birds is challenging due to diverse flight patterns and limited data availability. Previous research has focused on identifying the flight patterns of unmanned aerial vehicles by emphasizing dynamic features such as speed and heading. However, this approach tends to neglect crucial spatial information, making accurate discrimination of unmanned aerial vehicle characteristics challenging. Furthermore, training methods for situations with imbalanced data among classes have not been proposed by traditional machine learning techniques. In this paper, we propose a data processing method that preserves angle information while maintaining positional details, enabling the deep learning model to better comprehend positional information of drones. Additionally, we introduce a training technique to address the issue of data imbalance.

Long-term changes in qualitative composition of the Buzuluk Pine Forest avifauna (Orenburg Province area) based on retrospective and present-time observations

We conducted a comparative analysis of qualitative composition of the Buzuluk Pine Forest avifauna, mainly based on data collected by ornithologist E.P. Knorre for the period 1928–1941, and modern observations done between 2000 and the present. Retrospective data were obtained from the now-defunct Buzuluk Bor Reserve with an area of 10 503 hectares (now Borovoye-Opytnoe Forestry in the Orenburg Province). Present-time personal avifaunistic observations (using standard methods with referring to literature sources) were carried out on an area of 49 000 hectares, both in Borovoye-Opytnoe and in several adjacent forestries that were part of the Buzuluk Bor National Park within the Orenburg Province. Comparing the historical and current bird lists, we used a relative assessment of changes in the composition of various bird groups based on the observed and expected frequencies according to the χ2 test. Long-term data on average annual temperatures and precipitation from a nearby state weather station were also used. As a result, it is shown that by now the list of birds of E.P. Knorre decreased from 153 to 109 species (28.8%). When comparing by orders, the water birds were found to be the most affected group. The number of species in orders Podicipediformes, Ciconiiformes, Gruiformes decreased by 80–100%, and it dropped by more than 50% in orders Anseriformes and Charadriiformes. There was also a slightly smaller decrease in the number of species in orders Falconiformes and Strigiformes – by about 40%. An assessment of the relative changes in various bird groups from Knorre’s list based on expected and observed frequencies showed significant differences in the portion of avifauna associated with water. It decreased between 23.5% and 9% in the group ‘Limnophiles’ (χ2 = 11.7, df = 1, p = 0.0006) and between 24.8% and 9% in the group of orders represented by waterfowl and waterbird species (χ2 = 13.4, df = 1, p = 0.0002). The change in the portion of birds of prey was statistically non-significant. The same portion assessment method did not statistically confirm the decrease in the rest ecological and order groups. Comparison of groups by occurrence status found no significant changes in the portions of all groups of birds in the past and present, but the largest reduction was recorded in the group of migrating species. The portion of migrants decreased from 8.7% to 3.0% (χ2 = 3.2, df = 1, p = 0.07, Yates corrected χ2 = 2.2, p = 0.1). A dramatic decline in group of bird species associated with wetlands was suggested to be due, among other factors, to the progressive desiccation of the Buzuluk Pine Forest, as E. Knorre himself wrote in his report. The ongoing aridization of the climate, as shown by the graph of average annual air temperatures, has been taking place since at least the 20s of the twentieth century and led to the drying-up of wetlands, and also to migration of groundwater to deeper horizons. The emerging trend towards a reduction in the portion of migrants could be explained by the fact that a number of migratory bird species, mainly ducks and waders, disappeared in the study area, and several other migrants began breeding species. In addition, large-scale fires and logging led to formation of burned wasteland areas inside the forest at the beginning of the twentieth century and also probably contributed to fragmentation and desiccation of this biome.

A New Efficient Classifier for Bird Classification Based on Transfer Learning

The problem of classification of different species of birds in the images is relevant in the modern world. The essence is to automatically determine the species of birds depicted in the photo using artificial intelligence. It is important for several areas of human life, in particular for nature conservation, environmental research, education, and ecotourism. The development of a classifier, based on deep learning methods, can help to effectively solve the problem of classifying different species of birds, ensuring high accuracy. The work developed a new effective algorithm for the classification of different species of birds in the images. An optimal model architecture was built using the transfer learning approach. A dataset of 525 bird species was analyzed and preprocessed in detail. The model training process was carried out, which includes two phases: only the upper layers are deactivated and the last 92 layers of the pretrained EfficientNetB5 model (not including BatchNormalization layers) and the top layers are activated. As a result, efficacy indicators were obtained: accuracy = 98.86%, precision = 0.99, recall = 0.99, and F1 score = 0.99, which showed improvement in comparison with modern research. The developed classifier is best suited for such areas of human life as education and ecotourism because for them the number of different species of birds that the classifier can determine is very important.

Вклад Михаила Дмитриевича Рузского в изучение фауны птиц Волжско-Камского края

Mikhail Dmitrievich Ruzsky is one of the last encyclopedic scientists of the 20th century, known for his works on zoology, ichthyology and ornithology, hydrobiology, and entomology. Professor Mikhail Dmitrievich Ruzsky (1864-1948) is one of the country outstanding biologists and founders of the national science of ants, the first researcher of the myrmecofauna of Russia and neighboring countries. He made a significant contribution to the development of not only individual sciences, but also the formation of university education in Russia. The Kazan period of his biography is significant for his life and career. Mikhail Dmitrievich began his bird watching in Kazan and its surroundings while still being a very young researcher. His formation as a scientist began in Kazan Imperial University. Ruzsky had his first publications on birds in 1889, although he began conducting ornithological observations from the first years of university. The significant coverage of the territory allowed him not only to obtain new data on the distribution of birds in these areas, but also compare the lists of species and changes in their composition. His interest in studying fauna was influenced by the works of his predecessors - famous local historians and scientists of Russia - Pallas, Eversman, Bogdanov, and others. Ruzky gave the first list of birds of the Kazan province. In 1893, he presented his master’s thesis, Materials for the Study of Birds of the Kazan Province, whose results were published in the Proceedings of the Society of Naturalists of Kazan University. Ruzsky was the curator and collector of the Zoological Museum of Kazan University; within just one decade (from 1887 to 1896), he delivered 439 specimens of birds to the museum. His works made it possible to compile the first list of the avifauna of Kazan. He noted 56 species of birds directly inhabiting the city, and about 50 species found in the vicinity. A comparison of Ruzsky’s regional avi-faunistic lists with the data from recent years made it possible to present the dynamics and main changes that occurred in the composition of the bird fauna of the Volga-Kama Region over two hundred years. He was one of the organizers of the Kazan City Museum (now the National Museum of the Republic of T atarstan), chairman of its Council (1912), and having received the title of honorary member of the museum staff, he became director of the Natural History Department (1908-1913). Mikhail Dmitrievich was directly involved in the formation of the third Zoological Museum in Kazan located in the Veterinary Institute (now the Kazan State Academy of Veterinary Medicine), where he also worked for some time. The studies conducted on the avifauna of the Volga-Kama Region laid the foundation for subsequent large-scale work on both zoogeography, species distribution, and species ecology. In 1913, Mikhail Dmitrievich Ruzsky was elected professor of the Department of Zoology in Kiev and Tomsk Universities. He faced the choice and gave his preference to Tomsk devoting next 35 years of his life to working for the benefit of science in Tomsk University. The article contains 2 Figures, 13 References. The Authors declare no conflict of interest.

Improving national bird population estimates in Europe: insights from comparisons with atlas abundance data

Summary In Europe, population estimates of breeding birds are produced nationally and are periodically compiled at EU or pan-European scales. Until now, no other source was available to explore the robustness of these estimates. In this study, we compared population sizes reported in the latest edition of the European Red List of Birds (ERLoB) with those produced using data from the second European Breeding Bird Atlas (EBBA2) to assess their consistency and determine parameters behind variability in population estimates that deserve further attention in the future. In general, European population estimates derived from summing local abundance data from EBBA2 were similar to those obtained from ERLoB, although for some species they differed considerably, particularly in those distributed mainly in southern Europe. National population estimates from EBBA2 also did not differ markedly from those in ERLoB. However, we found that EBBA2 provided larger national population sizes than ERLoB for widespread species, suggesting that spatial information is more relevant for properly assessing their population size than for localised species. Our analysis also showed that, in general, population estimates based on robust methodological protocols (e.g. complete counts, statistical inference) contributed to reducing differences between ERLoB and EBBA2 values. Interestingly, EBBA2 and ERLoB estimates were quite similar for species classified in Europe as “Threatened” or “Near Threatened”, whereas the values for “Least Concern” species were consistently different between these two sources. Our results indicate which type of species would benefit from additional efforts to improve national population estimates and their consistency across countries, issues that are of paramount importance for guiding conservation strategies in Europe.

Assessment of long-term trends in a threatened grassland bird community using daily bird lists

Summary Open natural ecosystems (ONEs), such as tropical grasslands, are among the most threatened habitats on Earth today. The long-term monitoring of ONEs is an important research domain that is essential for understanding anthropogenic impacts and facilitating conservation action. Using a simple day-listing method over a 13-year period, we studied species trends in a central Indian grassland–agriculture mosaic experiencing several land-use changes. Our results indicate that some grassland species (such as the Great Indian Bustard Ardeotis nigriceps) showed steep declines during the study period, while other generalist species (such as the Indian Peafowl Pavo cristatus) showed an increasing trend. Daily listing also revealed distinct seasonal patterns, and we discuss the Great Indian Bustard and Western Marsh Harrier Circus aeruginosus as examples. Our study highlights the utility of consistent checklist surveys to monitor population trends of bird communities within a changing landscape.

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.

Classification of Unmanned Aerial Vehicle and Bird Images Using Deep Transfer Learning Methods

The increasing accessibility and affordability of unmanned aerial vehicles (UAVs), commonly known as drones, have led to the emergence of malicious users. In precaution to this perceived threat, various anti-UAV systems are being developed, including electro-optical systems utilizing cameras. It is possible to detect UAVs from images using various machine learning methods. However, the similarity between UAVs and birds poses a challenge, as birds can be mistakenly identified as UAVs, leading to false alarms in a security system. In order to avoid this problem, this study provided the classification of birds and unmanned aerial vehicles over images using deep learning methods. In this study, a data set consisting of 400 birds and 428 UAV images was used. The data were divided into 70% for training, 30% for testing and validation purposes. Three different deep learning models, based on DenseNet, VGG16, and VGG19 architectures, were trained using transfer learning techniques, and their performances were compared. Experimental results on the test data showed an accuracy of 94.64% with the DenseNet model, 89.67% with the VGG16 model, and 90.67% with the VGG19 model.

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.

Biocultural salient birds: which biological and cultural factors define them?

People’s interests and needs, as well as biological characteristics of species, determine human perception and interaction with biodiversity. Thus, both cultural and biological factors should be considered to understand biocultural salient species. We studied the cultural and biological traits that influence bird salience for an indigenous community in Mexico. Firstly, we used bird lists mentioned by local people to compute salient indexes for species. Then, we constructed seven cultural association categories to represent the local significance of birds (recreation, beliefs, environment, food, crop damage, economy, pets) and compiled biological information about species (color, size, vocal activity, detectability, abundance, daily activity pattern, habitat, residence status, taxonomic family). Finally, we determined the relations of cultural associations and biological traits with bird salience using hierarchical clusters. We observed a strong link between salient birds and human feeding, as these animals were locally recognized as food and threat to crops. Salient and non-salient birds were differentiated by their residence status and vocal activity, as local awareness was greater towards year-round resident and vocal species. Salience related the most with abundance, followed by color and detectability. Our study provides a route to identify cultural and biological factors influencing biocultural salience, which might prove useful for establishing conservation initiatives, public policies, and environmental education actions.

Biodiversity of Migrant Birds in the Limboto Lake Region, Gorontalo Province

The bird population in Indonesia is rich in diversity, this is based on the number of bird populations and environmental conditions that are still maintained so as to allow the birds to live. This study aims to describe the types of migratory birds in Lake Limboto. The method used in this study is the count point method and with 4 observation points for 7 days on different days. The starting point of the observations is carried out alternately for each station so that there are variations in the observation time at each station. Overall, the classification of migratory birds in the Limboto Lake area is classified as moderate with an index carbon index value of 1.79. Migratory birds found in the Lake Limboto area are 9 species of migratory birds belonging to 7 families with a total of 706 individuals. The highest index value H'= 1.63 is at station 1, the diversity index value is moderate and the lowest hidden index H'= 0 is at station 4, the index value is relatively low.

Observations of birds of prey in Eastern Nimba Nature Reserve, Liberia between 2015 and 2017

Abstract Distribution and biology of birds of prey species have been well-documented in most parts of the globe. Knowledge gaps are continuously shrinking due to more research, new technologies and increasing possibilities to reach remote areas. However, there are still some regions where data on birds of prey are scarce due to various reasons. Some parts of West Africa are such places, mostly because civil wars and the outbreak of Ebola prevented any kind of research. In the period 2015–2017, a butterfly research project in Nimba Mountains, Liberia offered opportunity to collect data also on birds of prey species. This article aims to provide a comprehensive list of birds of prey species in the area and compare it to other available historic and recent lists. In the frame of the project, 20 species were recorded. The results of comparing historic and recent records show that species of dry open habitats appeared and even settled in Nimba Mountains’ predominantly rainforest habitat. That suggests a habitat shift likely due to both climate change and human land transformation activities.

Classification and Discrimination of Birds and Small Drones Using Radar Micro-Doppler Spectrogram Images

This paper investigates the use of micro-Doppler spectrogram signatures of flying targets, such as drones and birds, to aid in their remote classification. Using a custom-designed 10-GHz continuous wave (CW) radar system, measurements from different scenarios on a variety of targets were recorded to create datasets for image classification. Time/velocity spectrograms generated for micro-Doppler analysis of multiple drones and birds were used for target identification and movement classification using TensorFlow. Using support vector machines (SVMs), the results showed an accuracy of about 90% for drone size classification, about 96% for drone vs. bird classification, and about 85% for individual drone and bird distinction between five classes. Different characteristics of target detection were explored, including the landscape and behavior of the target.