scholarly journals Deep learning-based methods for individual recognition in small birds

2019 ◽  
Author(s):  
André C. Ferreira ◽  
Liliana R. Silva ◽  
Francesco Renna ◽  
Hanja B. Brandl ◽  
Julien P. Renoult ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Collection ◽  
Individual Recognition ◽  
Bird Species ◽  
Training Data ◽  
Individual Identification ◽  
List Type ◽  
Major Advance ◽  
General Applicability ◽  
Automated Method

ABSTRACTIndividual identification is a crucial step to answer many questions in evolutionary biology and is mostly performed by marking animals with tags. Such methods are well established but often make data collection and analyses time consuming and consequently are not suited for collecting very large datasets.Recent technological and analytical advances, such as deep learning, can help overcome these limitations by automatizing data collection and analysis. Currently one of the bottlenecks preventing the application of deep learning for individual identification is the need of hundreds to thousands of labelled pictures required for training convolutional neural networks (CNNs).Here, we describe procedures that improve data collection and allow individual identification in captive and wild birds and we apply it to three small bird species, the sociable weaver Philetairus socius, the great tit Parus major and the zebra finch Taeniopygia guttata.First, we present an automated method that allows the collection of large samples of individually labelled images. Second, we describe how to train a CNN to identify individuals. Third, we illustrate the general applicability of CNN for individual identification in animal studies by showing that the trained CNN can predict the identity of birds from images collected in contexts that differ from the ones originally used to train the CNNs. Fourth, we present a potential solution to solve the issues of new incoming individuals.Overall our work demonstrates the feasibility of applying state-of-the-art deep learning tools for individual identification of birds, both in the lab and in the wild. These techniques are made possible by our approaches that allow efficient collection of training data. The ability to conduct individual identification of birds without requiring external markers that can be visually identified by human observers represents a major advance over current methods.

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

scholarly journals Unsupervised content-preserving transformation for optical microscopy

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Xinyang Li ◽  
Guoxun Zhang ◽  
Hui Qiao ◽  
Feng Bao ◽  
Yue Deng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optical Microscopy ◽  
Training Data ◽  
Fluorescence Labeling ◽  
Imaging Data ◽  
Image Transformation ◽  
General Applicability ◽  
Data Annotation ◽  
Biomedical Image ◽  
Wide Range

AbstractThe development of deep learning and open access to a substantial collection of imaging data together provide a potential solution for computational image transformation, which is gradually changing the landscape of optical imaging and biomedical research. However, current implementations of deep learning usually operate in a supervised manner, and their reliance on laborious and error-prone data annotation procedures remains a barrier to more general applicability. Here, we propose an unsupervised image transformation to facilitate the utilization of deep learning for optical microscopy, even in some cases in which supervised models cannot be applied. Through the introduction of a saliency constraint, the unsupervised model, named Unsupervised content-preserving Transformation for Optical Microscopy (UTOM), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. UTOM shows promising performance in a wide range of biomedical image transformation tasks, including in silico histological staining, fluorescence image restoration, and virtual fluorescence labeling. Quantitative evaluations reveal that UTOM achieves stable and high-fidelity image transformations across different imaging conditions and modalities. We anticipate that our framework will encourage a paradigm shift in training neural networks and enable more applications of artificial intelligence in biomedical imaging.

Sentiment Analysis of Fast Food Companies With Deep Learning Models

2020 ◽  
Author(s):  
Ghazi Abdalla ◽  
Fatih Özyurt
Keyword(s):  
Deep Learning ◽  
Data Collection ◽  
Sentiment Analysis ◽  
Customer Service ◽  
Fast Food ◽  
Training Data ◽  
Experimental Result ◽  
Learning Techniques ◽  
Daunting Task ◽  
Quality Of Products

Abstract In the modern era, Internet usage has become a basic necessity in the lives of people. Nowadays, people can perform online shopping and check the customer’s views about products that purchased online. Social networking services enable users to post opinions on public platforms. Analyzing people’s opinions helps corporations to improve the quality of products and provide better customer service. However, analyzing this content manually is a daunting task. Therefore, we implemented sentiment analysis to make the process automatically. The entire process includes data collection, pre-processing, word embedding, sentiment detection and classification using deep learning techniques. Twitter was chosen as the source of data collection and tweets collected automatically by using Tweepy. In this paper, three deep learning techniques were implemented, which are CNN, Bi-LSTM and CNN-Bi-LSTM. Each of the models trained on three datasets consists of 50K, 100K and 200K tweets. The experimental result revealed that, with the increasing amount of training data size, the performance of the models improved, especially the performance of the Bi-LSTM model. When the model trained on the 200K dataset, it achieved about 3% higher accuracy than the 100K dataset and achieved about 7% higher accuracy than the 50K dataset. Finally, the Bi-LSTM model scored the highest performance in all metrics and achieved an accuracy of 95.35%.

Pig Face Recognition Model Based on a Cascaded Network

2021 ◽  
Vol 37 (5) ◽  
pp. 879-890
Author(s):  
Rong Wang ◽  
ZaiFeng Shi ◽  
Qifeng Li ◽  
Ronghua Gao ◽  
Chunjiang Zhao ◽  
...  
Keyword(s):  
Face Recognition ◽  
Face Detection ◽  
Individual Recognition ◽  
Recognition Performance ◽  
Individual Identification ◽  
List Type ◽  
Recognition Model ◽  
Model Based ◽  
Face Images ◽  
Cascaded Model

HighlightsA pig face recognition model that cascades the pig face detection network and pig face recognition network is proposed.The pig face detection network can automatically extract pig face images to reduce the influence of the background.The proposed cascaded model reaches accuracies of 99.38%, 98.96% and 97.66% on the three datasets.An application is developed to automatically recognize individual pigs.Abstract. The identification and tracking of livestock using artificial intelligence technology have been a research hotspot in recent years. Automatic individual recognition is the key to realizing intelligent feeding. Although RFID can achieve identification tasks, it is expensive and easily fails. In this article, a pig face recognition model that cascades a pig face detection network and a pig face recognition network is proposed. First, the pig face detection network is utilized to crop the pig face images from videos and eliminate the complex background of the pig shed. Second, batch normalization, dropout, skip connection, and residual modules are exploited to design a pig face recognition network for individual identification. Finally, the cascaded network model based on the pig face detection and recognition network is deployed on a GPU server, and an application is developed to automatically recognize individual pigs. Additionally, class activation maps generated by grad-CAM are used to analyze the performance of features of pig faces learned by the model. Under free and unconstrained conditions, 46 pigs are selected to make a positive pig face dataset, original multiangle pig face dataset and enhanced multiangle pig face dataset to verify the pig face recognition cascaded model. The proposed cascaded model reaches accuracies of 99.38%, 98.96%, and 97.66% on the three datasets, which are higher than those of other pig face recognition models. The results of this study improved the recognition performance of pig faces under multiangle and multi-environment conditions. Keywords: CNN, Deep learning, Pig face detection, Pig face recognition.

scholarly journals Research on emitter individual identification technology based on Automatic Dependent Surveillance–Broadcast signal

2021 ◽  
Vol 17 (2) ◽  
pp. 155014772199262
Author(s):  
Shiwen Chen ◽  
Junjian Yuan ◽  
Xiaopeng Xing ◽  
Xin Qin
Keyword(s):  
Individual Recognition ◽  
Evidence Theory ◽  
Field Measurements ◽  
Training Data ◽  
Individual Identification ◽  
Identification System ◽  
Individual Feature ◽  
Data Set ◽  
Theoretical Simulation ◽  
The Individual

Aiming at the shortcomings of the research on individual identification technology of emitters, which is primarily based on theoretical simulation and lack of verification equipment to conduct external field measurements, an emitter individual identification system based on Automatic Dependent Surveillance–Broadcast is designed. On one hand, the system completes the individual feature extraction of the signal preamble. On the other hand, it realizes decoding of the transmitter’s individual identity information and generates an individual recognition training data set, on which we can train the recognition network to achieve individual signal recognition. For the collected signals, six parameters were extracted as individual features. To reduce the feature dimensions, a Bessel curve fitting method is used for four of the features. The spatial distribution of the Bezier curve control points after fitting is taken as an individual feature. The processed features are classified with multiple classifiers, and the classification results are fused using the improved Dempster–Shafer evidence theory. Field measurements show that the average individual recognition accuracy of the system reaches 88.3%, which essentially meets the requirements.

scholarly journals DeepForest: A Python package for RGB deep learning tree crown delineation

2020 ◽  
Author(s):  
Ben. G. Weinstein ◽  
Sergio Marconi ◽  
Mélaine Aubry-Kientz ◽  
Gregoire Vincent ◽  
Henry Senyondo ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Training Data ◽  
Fine Tuning ◽  
List Type ◽  
Crown Delineation ◽  
Using Data ◽  
Individual Trees ◽  
Tree Crown Delineation ◽  
Python Package

AbstractRemote sensing of forested landscapes can transform the speed, scale, and cost of forest research. The delineation of individual trees in remote sensing images is an essential task in forest analysis. Here we introduce a new Python package, DeepForest, that detects individual trees in high resolution RGB imagery using deep learning.While deep learning has proven highly effective in a range of computer vision tasks, it requires large amounts of training data that are typically difficult to obtain in ecological studies. DeepForest overcomes this limitation by including a model pre-trained on over 30 million algorithmically generated crowns from 22 forests and fine-tuned using 10,000 hand-labeled crowns from 6 forests.The package supports the application of this general model to new data, fine tuning the model to new datasets with user labeled crowns, training new models, and evaluating model predictions. This simplifies the process of using and retraining deep learning models for a range of forests, sensors, and spatial resolutions.We illustrate the workflow of DeepForest using data from the National Ecological Observatory Network, a tropical forest in French Guiana, and street trees from Portland, Oregon.

Deep-Learning-Based Automated Sedimentary Geometry Characterization From Borehole Images

2021 ◽  
Vol 62 (6) ◽  
pp. 636-650
Author(s):  
Marie Lefranc ◽  
◽  
Zikri Bayraktar ◽  
Morten Kristensen ◽  
Hedi Driss ◽  
...  
Keyword(s):  
Deep Learning ◽  
Flow Direction ◽  
Synthetic Data ◽  
Network Models ◽  
Training Data ◽  
Proper Class ◽  
Neural Network Models ◽  
Data Set ◽  
Sedimentary Structures ◽  
Automated Method

Sedimentary geometry on borehole images usually summarizes the arrangement of bed boundaries, erosive surfaces, crossbedding, sedimentary dip, and/or deformed beds. The interpretation, very often manual, requires a good level of expertise, is time consuming, can suffer from user bias, and becomes very challenging when dealing with highly deviated wells. Bedform geometry interpretation from crossbed data is rarely completed from a borehole image. The purpose of this study is to develop an automated method to interpret sedimentary structures, including the bedform geometry resulting from the change in flow direction from borehole images. Automation is achieved in this unique interpretation methodology using deep learning (DL). The first task comprised the creation of a training data set of 2D borehole images. This library of images was then used to train deep neural network models. Testing different architectures of convolutional neural networks (CNN) showed the ResNet architecture to give the best performance for the classification of the different sedimentary structures. The validation accuracy was very high, in the range of 93 to 96%. To test the developed method, additional logs of synthetic data were created as sequences of different sedimentary structures (i.e., classes) associated with different well deviations, with the addition of gaps. The model was able to predict the proper class in these composite logs and highlight the transitions accurately.

Deep Learning Enhances the Detection of Breeding Birds in UAV Images

2021 ◽  
Author(s):  
Benjamin Kellenberger ◽  
Thor Veen ◽  
Eelke Folmer ◽  
Devis Tuia
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Large Scale ◽  
Bird Species ◽  
Decision Fusion ◽  
Training Data ◽  
Seabird Species ◽  
Uav Images

<p>Recently, Unmanned Aerial Vehicles (UAVs) equipped with high-resolution imaging sensors have become a viable alternative for ecologists to conduct wildlife censuses, compared to foot surveys. They cause less disturbance by sensing remotely, they provide coverage of otherwise inaccessible areas, and their images can be reviewed and double-checked in controlled screening sessions. However, the amount of data they generate often makes this photo-interpretation stage prohibitively time-consuming.</p><p>In this work, we automate the detection process with deep learning [4]. We focus on counting coastal seabirds on sand islands off the West African coast, where species like the African Royal Tern are at the top of the food chain [5]. Monitoring their abundance provides invaluable insights into biodiversity in this area [7]. In a first step, we obtained orthomosaics from nadir-looking UAVs over six sand islands with 1cm resolution. We then fully labelled one of them with points for four seabird species, which required three weeks for five annotators to do and resulted in over 21,000 individuals. Next, we further labelled the other five orthomosaics, but in an incomplete manner; we aimed for a low number of only 200 points per species. These points, together with a few background polygons, served as training data for our ResNet-based [2] detection model. This low number of points required multiple strategies to obtain stable predictions, including curriculum learning [1] and post-processing by a Markov random field [6]. In the end, our model was able to accurately predict the 21,000 birds of the test image with 90% precision at 90% recall (Fig. 1) [3]. Furthermore, this model required a mere 4.5 hours from creating training data to the final prediction, which is a fraction of the three weeks needed for the manual labelling process. Inference time is only a few minutes, which makes the model scale favourably to many more islands. In sum, the combination of UAVs and machine learning-based detectors simultaneously provides census possibilities with unprecedentedly high accuracy and comparably minuscule execution time.</p><p><img src="https://contentmanager.copernicus.org/fileStorageProxy.php?f=gnp.bc5211f4f60067568601161/sdaolpUECMynit/12UGE&app=m&a=0&c=eeda7238e992b9591c2fec19197f67dc&ct=x&pn=gnp.elif&d=1" alt=""></p><p><em>Fig. 1: Our model is able to predict over 21,000 birds in high-resolution UAV images in a fraction of time compared to weeks of manual labelling.</em></p><p> </p><p>References</p><p>1. Bengio, Yoshua, et al. "Curriculum learning." Proceedings of the 26th annual international conference on machine learning. 2009.</p><p>2. He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.</p><p>3. Kellenberger, Benjamin, et al. “21,000 Birds in 4.5 Hours: Efficient Large-scale Seabird Detection with Machine Learning.” Remote Sensing in Ecology and Conservation. Under review.</p><p>4. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." nature 521.7553 (2015): 436-444.</p><p>5. Parsons, Matt, et al. "Seabirds as indicators of the marine environment." ICES Journal of Marine Science 65.8 (2008): 1520-1526.</p><p>6. Tuia, Devis, Michele Volpi, and Gabriele Moser. "Decision fusion with multiple spatial supports by conditional random fields." IEEE Transactions on Geoscience and Remote Sensing 56.6 (2018): 3277-3289.</p><p>7. Veen, Jan, Hanneke Dallmeijer, and Thor Veen. "Selecting piscivorous bird species for monitoring environmental change in the Banc d'Arguin, Mauritania." Ardea 106.1 (2018): 5-18.</p>

scholarly journals Automatic extraction of 12 cardiovascular concepts from German discharge letters using pre-trained language models

2021 ◽  
Vol 7 ◽  
pp. 205520762110576
Author(s):  
Phillip Richter-Pechanski ◽  
Nicolas A Geis ◽  
Christina Kiriakou ◽  
Dominic M Schwab ◽  
Christoph Dieterich
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Training Data ◽  
Language Models ◽  
University Hospital ◽  
Data Driven ◽  
Learning Methods ◽  
Concept Extraction ◽  
Automated Method ◽  
Learning Projects

Objective A vast amount of medical data is still stored in unstructured text documents. We present an automated method of information extraction from German unstructured clinical routine data from the cardiology domain enabling their usage in state-of-the-art data-driven deep learning projects. Methods We evaluated pre-trained language models to extract a set of 12 cardiovascular concepts in German discharge letters. We compared three bidirectional encoder representations from transformers pre-trained on different corpora and fine-tuned them on the task of cardiovascular concept extraction using 204 discharge letters manually annotated by cardiologists at the University Hospital Heidelberg. We compared our results with traditional machine learning methods based on a long short-term memory network and a conditional random field. Results Our best performing model, based on publicly available German pre-trained bidirectional encoder representations from the transformer model, achieved a token-wise micro-average F1-score of 86% and outperformed the baseline by at least 6%. Moreover, this approach achieved the best trade-off between precision (positive predictive value) and recall (sensitivity). Conclusion Our results show the applicability of state-of-the-art deep learning methods using pre-trained language models for the task of cardiovascular concept extraction using limited training data. This minimizes annotation efforts, which are currently the bottleneck of any application of data-driven deep learning projects in the clinical domain for German and many other European languages.

scholarly journals U-Infuse: Democratization of Customizable AI for Object Detection

2020 ◽  
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Image Data ◽  
Camera Trap ◽  
Learning Technologies ◽  
Training Data ◽  
List Type ◽  
Learning Models ◽  
Ecological Data ◽  
Large Numbers

SummaryImage data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. There is a strong need to democratise access to deep learning technologies by providing an easy to use software application allowing non-technical users to custom train custom object detectors.U-Infuse addresses this issue by putting the power of AI into the hands of ecologists. U-Infuse provides ecologists with the ability to train customised models using publicly available images and/or their own camera trap images, without the constraints of annotating and pre-processing large numbers of images, or specific technical expertise. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and inference, allowing ecologists to access state of the art AI on their own device, customised to their application without sharing IP or sensitive data.U-Infuse provides ecological practitioners with the ability to (i) easily achieve camera trap object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets.Broad adoption of U-Infuse by ecological practitioners will improve camera trap image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources. Ease of training and reliance on transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

Sign in / Sign up

Export Citation Format

Share Document