scholarly journals Towards the Acoustic Monitoring of Birds Migrating at Night

2019 ◽  
Vol 3 ◽  
Author(s):  
Hanna Pamula ◽  
Agnieszka Pocha ◽  
Maciej Klaczynski
Keyword(s):  
Deep Learning ◽  
Direct Observation ◽  
Bird Species ◽  
Acoustic Monitoring ◽  
Detection Accuracy ◽  
Learning Methods ◽  
Important Indicator ◽  
Bird Calls ◽  
Bird Detection

Every year billions of birds migrate between their breeding and wintering areas. As birds are an important indicator in nature conservation, migratory bird studies have been conducted for many decades, mostly by bird-ringing programmes and direct observation. However, most birds migrate at night, and therefore much information about their migration is lost. Novel methods have been developed to overcome this difficulty; including thermal imaging, radar, geolocation techniques, and acoustic recognition of bird calls. Many bird species are detected by their characteristic sounds. This method of identification occurs more often than by direct observation, and therefore recordings are widely used in avian research. The commonly used approach is to record the birds automatically, and to manually study the bird sounds in the recordings afterwards (Furnas and Callas 2015, Frommolt 2017). However, the tagging of recordings is a tedious and time-consuming process that requires expert knowledge, and, as a result, automatic detection of flight calls is in high demand. The first experiments towards this used energy thresholds or template matching (Bardeli et al. 2010, Towsey et al. 2012), and later on the machine and deep learning methods were applied (Stowell et al. 2018). Nevertheless, not many studies have focused specifically on night flight calls (Salamon et al. 2016, Lostanlen et al. 2018). Such acoustic monitoring could complement daytime avian research, especially when the field recording station is close to the bird-ringing station, as it is in our project. In this study, we present the initial results of a long-term bird audio monitoring project using automatic methods for bird detection. Passive acoustic recorders were deployed at a narrow spit between a lake and the Baltic sea in Dąbkowice, West Pomeranian Voivodeship, Poland . We recorded bird calls nightly from sunset till sunrise during the passerine autumn migration for 3 seasons. As a result, we collected over 3000 hours of recordings each season. We annotated a subset of over 50 hours, from different nights with various weather conditions. As avian flight calls are sporadic and short, we created a balanced set for training - recordings were divided into partially overlapping 500-ms clips, and we retained all clips containing calls and created about the same number of clips without bird sounds. Different signal representations were then examined (e.g. mel-spectrograms and multitaper). Afterwards, various convolutional neural networks were checked and their performance was compared using the area under the receiver operating characteristic curve (AUC) measure. Moreover, an initial attempt was made to take advantage of the transfer learning from image classification models. The results obtained by the deep learning methods are promising (AUC exceeding 80%), but higher bird detection accuracy is still needed. For a chosen bird species – Song thrush (Turdus philomelos) – we observed a correlation between calls recorded at night and birds caught in the nets during the day. This fact, as well as the promising results from the detection of calls from long-term recordings, indicate that acoustic monitoring of nocturnal birds has great potential and could be used to supplement the research of the phenomenon of seasonal bird migration.

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 ​Behavior Recognition of Group-ranched Cattle from Video Sequences using Deep Learning

2021 ◽  
Author(s):  
Rotimi-Williams Bello ◽  
Ahmad Sufril Azlan Mohamed ◽  
Abdullah Zawawi Talib ◽  
Salisu Sani ◽  
Mohd Nadhir Ab Wahab
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
State Of The Art ◽  
The State ◽  
Video Sequences ◽  
Detection Accuracy ◽  
Behavior Recognition ◽  
Learning Methods ◽  
Important Indicator ◽  
Daily Behavior

Background: One important indicator for the wellbeing status of livestock is their daily behavior. More often than not, daily behavior recognition involves detecting the heads or body gestures of the livestock using conventional methods or tools. To prevail over such limitations, an effective approach using deep learning is proposed in this study for cattle behavior recognition. Methods: The approach for detecting the behavior of individual cows was designed in terms of their eating, drinking, active, and inactive behaviors captured from video sequences and based on the investigation of the attributes and practicality of the state-of-the-art deep learning methods. Result: Among the four models employed, Mask R-CNN achieved average recognition accuracies of 93.34%, 88.03%, 93.51% and 93.38% for eating, drinking, active and inactive behaviors. This implied that Mask R-CNN achieved higher cow detection accuracy and speed than the remaining models with 20 fps, making the proposed approach competes favorably well with other approaches and suitable for behavior recognition of group-ranched cattle in real-time.

scholarly journals Hybrid CNN-LSTM Model for Answer Identification

2019 ◽  
Vol 8 (3) ◽  
pp. 1163-1166
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Comparative Analysis ◽  
Hybrid Model ◽  
Deep Neural Network ◽  
Extraction Methods ◽  
Learning Methods ◽  
Automatic Feature Extraction

User quest for information has led to development of Question Answer (QA) system to provide relevant answers to user questions. The QA task are different than normal NLP tasks as they heavily depend to semantics and context of given data. Retrieving and predicting answers to verity of questions require understanding of question, relevance with context and identifying and retrieving of suitable answers. Deep learning helps to produce impressive performance as it employs deep neural network with automatic feature extraction methods. The paper proposes a hybrid model to identify suitable answer for posed question. The proposes power exploits the power of CNN for extracting features and ability of LSTM for considering long term dependencies and semantic of context and question. Paper provides a comparative analysis on deep learning methods useful for predicting answer with the proposed method .The model is implemented on twenty tasks of babI dataset of Facebook .

scholarly journals Controllably Deep Supervision and Multi-Scale Feature Fusion Network for Cloud and Snow Detection Based on Medium- and High-Resolution Imagery Dataset

2021 ◽  
Vol 13 (23) ◽  
pp. 4805
Author(s):  
Guangbin Zhang ◽  
Xianjun Gao ◽  
Yuanwei Yang ◽  
Mingwei Wang ◽  
Shuhao Ran
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Feature Fusion ◽  
Detection Accuracy ◽  
Learning Methods ◽  
Training Requirements ◽  
Scale Feature ◽  
Multi Scale ◽  
Hinge Loss

Clouds and snow in remote sensing imageries cover underlying surface information, reducing image availability. Moreover, they interact with each other, decreasing the cloud and snow detection accuracy. In this study, we propose a convolutional neural network for cloud and snow detection, named the cloud and snow detection network (CSD-Net). It incorporates the multi-scale feature fusion module (MFF) and the controllably deep supervision and feature fusion structure (CDSFF). MFF can capture and aggregate features at various scales, ensuring that the extracted high-level semantic features of clouds and snow are more distinctive. CDSFF can provide a deeply supervised mechanism with hinge loss and combine information from adjacent layers to gain more representative features. It ensures the gradient flow is more oriented and error-less, while retaining more effective information. Additionally, a high-resolution cloud and snow dataset based on WorldView2 (CSWV) was created and released. This dataset meets the training requirements of deep learning methods for clouds and snow in high-resolution remote sensing images. Based on the datasets with varied resolutions, CSD-Net is compared to eight state-of-the-art deep learning methods. The experiment results indicate that CSD-Net has an excellent detection accuracy and efficiency. Specifically, the mean intersection over the union (MIoU) of CSD-Net is the highest in the corresponding experiment. Furthermore, the number of parameters in our proposed network is just 7.61 million, which is the lowest of the tested methods. It only has 88.06 GFLOPs of floating point operations, which is less than the U-Net, DeepLabV3+, PSPNet, SegNet-Modified, MSCFF, and GeoInfoNet. Meanwhile, CSWV has a higher annotation quality since the same method can obtain a greater accuracy on it.

scholarly journals A Video-Based Fire Detection Using Deep Learning Models

2019 ◽  
Vol 9 (14) ◽  
pp. 2862 ◽  
Author(s):  
Byoungjun Kim ◽  
Joonwhoan Lee
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Fire Behavior ◽  
Fire Detection ◽  
Majority Voting ◽  
Detection Accuracy ◽  
Final Decision ◽  
Short Term ◽  
Bounding Boxes

Fire is an abnormal event which can cause significant damage to lives and property. In this paper, we propose a deep learning-based fire detection method using a video sequence, which imitates the human fire detection process. The proposed method uses Faster Region-based Convolutional Neural Network (R-CNN) to detect the suspected regions of fire (SRoFs) and of non-fire based on their spatial features. Then, the summarized features within the bounding boxes in successive frames are accumulated by Long Short-Term Memory (LSTM) to classify whether there is a fire or not in a short-term period. The decisions for successive short-term periods are then combined in the majority voting for the final decision in a long-term period. In addition, the areas of both flame and smoke are calculated and their temporal changes are reported to interpret the dynamic fire behavior with the final fire decision. Experiments show that the proposed long-term video-based method can successfully improve the fire detection accuracy compared with the still image-based or short-term video-based method by reducing both the false detections and the misdetections.

A Deep Learning Method to Analyze and Classify Happy Moments: A Comparative Analytic Study (Preprint)

2019 ◽  
Author(s):  
Qiudan Li ◽  
Ruoran Liu ◽  
Riheng Yao ◽  
Daniel Dajun Zeng
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Deep Learning ◽  
Short Term Memory ◽  
Detailed Comparison ◽  
Public Attention ◽  
Learning Methods ◽  
Policy Makers ◽  
Important Indicator ◽  
Machine Learning Methods

BACKGROUND Happiness is considered as an important indicator of users’ mental and physical health. Fostering happiness has gained increasing public attention as one of the ways to decrease health costs in the long run. Understanding what makes users feel happy may help policy makers develop policies and methods that steer users towards behaviors identified to promote happiness. OBJECTIVE This paper aimed to investigate the use of deep learning methods to analyze happy moments and compare them with the traditional machine learning methods, which may provide a mechanism to accurately classify happy moments and help understand why users feel happy. METHODS A crowdsourced corpus of happy moments, HappyDB, was used. The dataset contained 14,125 posts with category labels that described sources and reasons for happy feelings: Achievement, Affection, Bonding, Enjoy the moment, Leisure, Nature and Exercise. We compared the performance of deep learning methods such as the convolutional neural network (CNN), bidirectional long-short term memory (Bi-LSTM), and attention Bi-LSTM with that of the traditional machine learning methods including logistic regression, SVM, and naïve Bayes. Standard measures including precision, recall, and F1 were adopted for each category. Macro-precision, macro-recall, and macro-F1 were used to evaluate the overall performance of the models. RESULTS We found that CNN achieved the best performance on macro-precision, macro-recall, and macro-F1, with values of 80.8, 79.3, and 80.0, respectively. Among the traditional machine learning methods, logistic regression performed the best, with macro-precision of 80.6, macro-recall of 71.1, and macro-F1 of 75.5. A detailed comparison of CNN and logistic regression on each category showed that CNN was able to improve F1 score for all categories. Specifically, F1 improved by at least 1.8% on the Bonding category and up to 11.3% on Nature. Performance improvements mainly depended on significant improvements on recall, especially for minor categories. For example, the recall of CNN was 80.9 and 70.9 for Nature and Exercise, which was an improvement of 28.5% and 11.6% compared with logistic regression. The reason was that CNN explicitly modeled the relationship between word features and the categories of happy moments by extracting important word features through convolution and pooling operations. CONCLUSIONS This is the first study to analyze happy moments based on deep learning methods. Compared with the traditional machine learning methods, deep learning methods, especially CNN, showed superiority on classifying the happy moments, which would facilitate understanding of the reasons why users feel happy and thus help policy makers formulate targeted policies to promote happiness.

scholarly journals Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey

2019 ◽  
Vol 9 (20) ◽  
pp. 4396 ◽  
Author(s):  
Hongyu Liu ◽  
Bo Lang
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Intrusion Detection ◽  
Cyber Security ◽  
Detection System ◽  
Research Area ◽  
Machine Learning Algorithms ◽  
Detection Accuracy ◽  
Learning Methods ◽  
Machine Learning Methods

Networks play important roles in modern life, and cyber security has become a vital research area. An intrusion detection system (IDS) which is an important cyber security technique, monitors the state of software and hardware running in the network. Despite decades of development, existing IDSs still face challenges in improving the detection accuracy, reducing the false alarm rate and detecting unknown attacks. To solve the above problems, many researchers have focused on developing IDSs that capitalize on machine learning methods. Machine learning methods can automatically discover the essential differences between normal data and abnormal data with high accuracy. In addition, machine learning methods have strong generalizability, so they are also able to detect unknown attacks. Deep learning is a branch of machine learning, whose performance is remarkable and has become a research hotspot. This survey proposes a taxonomy of IDS that takes data objects as the main dimension to classify and summarize machine learning-based and deep learning-based IDS literature. We believe that this type of taxonomy framework is fit for cyber security researchers. The survey first clarifies the concept and taxonomy of IDSs. Then, the machine learning algorithms frequently used in IDSs, metrics, and benchmark datasets are introduced. Next, combined with the representative literature, we take the proposed taxonomic system as a baseline and explain how to solve key IDS issues with machine learning and deep learning techniques. Finally, challenges and future developments are discussed by reviewing recent representative studies.

scholarly journals FCNN: An Efficient Intrusion Detection Method Based on Raw Network Traffic

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Yue Wang ◽  
Yiming Jiang ◽  
Julong Lan
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Intrusion Detection ◽  
Superior Performance ◽  
Detection Accuracy ◽  
Input Unit ◽  
Learning Methods ◽  
Training Time ◽  
Machine Learning Methods ◽  
Network Intrusion

When traditional machine learning methods are applied to network intrusion detection, they need to rely on expert knowledge to extract feature vectors in advance, which incurs lack of flexibility and versatility. Recently, deep learning methods have shown superior performance compared with traditional machine learning methods. Deep learning methods can learn the raw data directly, but they are faced with expensive computing cost. To solve this problem, a preprocessing method based on multipacket input unit and compression is proposed, which takes m data packets as the input unit to maximize the retention of information and greatly compresses the raw traffic to shorten the data learning and training time. In our proposed method, the CNN network structure is optimized and the weights of some convolution layers are assigned directly by using the Gabor filter. Experimental results on the benchmark data set show that compared with the existing models, the proposed method improves the detection accuracy by 2.49% and reduces the training time by 62.1%. In addition, the experiments show that the proposed compression method has obvious advantages in detection accuracy and computational efficiency compared with the existing compression methods.

Fault diagnosis systems for rotating machines operating with fluid-film bearings

2022 ◽  
pp. 135065012110732
Author(s):  
Ivan Stebakov ◽  
Alexey Kornaev ◽  
Sergey Popov ◽  
Leonid Savin
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Anomaly Detection ◽  
Multilayer Perceptron ◽  
Multiclass Classification ◽  
Detection Accuracy ◽  
Network Architectures ◽  
Rotating Machines ◽  
Learning Methods ◽  
Deep Network

The paper deals with the application of deep learning methods to rotating machines fault diagnosis. The main challenge is to design a fault diagnosis system connected with multisensory measurement system that will be sensitive and accurate enough in detecting weak changes in rotating machines. The experimental part of the research presents the test rig and results of high-speed multisensory measurements. Six states of a rotating machine, including a normal one and five states with loosened mounting bolts and small unbalancing of the shaft, are under study. The application of deep network architectures including multilayer perceptron, convolutional neural networks, residual networks, autoencoders and their combination was estimated. The deep learning methods allowed to identify the most informative sensors, then solve the anomaly detection and the multiclass classification problems. An autoencoder based on ResNet architecture demonstrated the best result in anomaly detection. The accuracy of the proposed network is up to 100% while the accuracy of an expert is up to 65%. A one-dimensional convolutional neural network combined with a multilayer perceptron that contains a pretrained encoder demonstrated the best result in multiclass classification. The detailed fault detection accuracy with the determination of the specific fault is 83.3%. The combinations of known deep network architectures and application of the proposed approach of pretraining of the encoders together with using a block of inputs for one prediction demonstrated high efficiency.

Sign in / Sign up

Export Citation Format

Share Document