Deep Learning Case Study for Automatic Bird Identification

Niemi, Juha; Tanttu, Juha T.

doi:10.3390/app8112089

Cited by 25 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition to the CNN model introduced above, we have tested the svm-on-top model, which has otherwise the same structure as this CNN model, but an svm classifier was connected to the second fully connected layer. 22 However, the tests for this study showed that the classification performance is the same or even slightly better when using only the CNN. Moreover, the svm-on-top model had significantly longer training time than the CNN model alone.…”

Section: Tested Cnn Structures and Hyperparameter Selectionmentioning

confidence: 61%

“…21 For more details, see previous studies. 19,22 A number of images for each species (classes) in the augmented dataset when s = 50 and s = 200, respectively, are presented in Table 2 .…”

Section: Data Augmentationmentioning

confidence: 99%

“…For more details, see Niemi and Tanttu. 22 In this paper, we have used merely convolution without a neural network for segmentation. 23 A kernel of a size 8 × 8 is used to convolve images.…”

Section: Image Segmentationmentioning

confidence: 99%

“…For more details, see Niemi and Tanttu. 22 Although the tests in our previous study were performed on the svm-on-…”

Section: Tested Cnn Structures and Hyperparameter Selectionmentioning

confidence: 99%

See 3 more Smart Citations

Deep learning–based automatic bird identification system for offshore wind farms

Niemi

Tanttu

2020

Wind Energy

Self Cite

View full text Add to dashboard Cite

Practical deterrent methods are needed to prevent collisions between birds and wind turbine blades for offshore wind farms. It is improbable that a single deterrent method would work for all bird species in a given area. An automatic bird identification system is required in order to develop bird species-level deterrent methods. This system is the first and necessary part of the entirety that is eventually able to automatically monitor bird movements, identify bird species, and launch deterrent measures. A prototype system has been built on Finnish west coast. In the proposed system, a separate radar system detects birds and provides WGS84 coordinates to a steering system of a camera. The steering system consists of a motorized video head and our software to control it. The steering system tracks flying birds in order to capture series of images by a digital single-lens reflex camera. Classification is based on these images, and it is implemented by convolutional neural network trained with a deep learning algorithm.We applied to the images our data augmentation method in which images are rotated and converted into different color temperatures. The results indicate that the proposed system has good performance to identify bird species in the test area. Aiming accuracy for the video head was 88.91 %. Image classification performance as true positive rate was 0.8688. KEYWORDSconvolutional neural networks, deep learning, image classification, intelligent surveillance systems, machine learning, wind farms 1 Identification of bird species is mainly based on morphology and vocalization of which vocalization is not a feasible method in the offshore environment because of long ranges and background noise. Images taken of birds in the test area (the wind farm) are used as a feasible method to study morphology. This turns the identification problem to an image classification problem. Thus, the problem of automatic bird identification in real-time is two-fold: How to successfully aim the camera to a target bird in order to collect images and how to classify (identify) the images? Wind Energy. 2020;23:1394-1407. wileyonlinelibrary.com/journal/we

show abstract

Section: Tested Cnn Structures and Hyperparameter Selectionmentioning

confidence: 61%

“…21 For more details, see previous studies. 19,22 A number of images for each species (classes) in the augmented dataset when s = 50 and s = 200, respectively, are presented in Table 2 .…”

Section: Data Augmentationmentioning

confidence: 99%

Section: Image Segmentationmentioning

confidence: 99%

“…For more details, see Niemi and Tanttu. 22 Although the tests in our previous study were performed on the svm-on-…”

Section: Tested Cnn Structures and Hyperparameter Selectionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning–based automatic bird identification system for offshore wind farms

Niemi

Tanttu

2020

Wind Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…AI which encapsulates Machine learning (ML) [14] and Deep leaning (DNN) [15] show up in countless articles out of the technology motivated ones. A Deep neural network as proposed by [15,16] has the potential of estimating both continuous and discrete function. Recently, various application areas such as speech recognition, computer vision and text processing [17] among other fields have experienced the potency of deep neural networks.…”

Section: Review Of Related Workmentioning

confidence: 99%

Simple and Efficient Computational Intelligence Strategies for Effective Collaborative Decisions

Aboagye

Kumar

2019

Future Internet

View full text Add to dashboard Cite

We approach scalability and cold start problems of collaborative recommendation in this paper. An intelligent hybrid filtering framework that maximizes feature engineering and solves cold start problem for personalized recommendation based on deep learning is proposed in this paper. Present e-commerce sites mainly recommend pertinent items or products to a lot of users through personalized recommendation. Such personalization depends on large extent on scalable systems which strategically responds promptly to the request of the numerous users accessing the site (new users). Tensor Factorization (TF) provides scalable and accurate approach for collaborative filtering in such environments. In this paper, we propose a hybrid-based system to address scalability problems in such environments. We propose to use a multi-task approach which represent multiview data from users, according to their purchasing and rating history. We use a Deep Learning approach to map item and user inter-relationship to a low dimensional feature space where item-user resemblance and their preferred items is maximized. The evaluation results from real world datasets show that, our novel deep learning multitask tensor factorization (NeuralFil) analysis is computationally less expensive, scalable and addresses the cold-start problem through explicit multi-task approach for optimal recommendation decision making.

show abstract