Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion

Jiang, Haiyang; Pan, Yaozong; Zhang, Jian; Yang, Haitao

doi:10.3390/sym11060761

Cited by 7 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the murine behavior recognition task, 3DCNN [33,34], LSTM, and Bi-LSTM [35,36] were compared with ConvLSTM. The 3DCNN network also used the keypoint feature map sequence as an input.…”

Section: Methodsmentioning

confidence: 99%

Murine Motion Behavior Recognition Based on DeepLabCut and Convolutional Long Short-Term Memory Network

Liu¹,

Zhu

Rao

2022

Symmetry

View full text Add to dashboard Cite

Murine behavior recognition is widely used in biology, neuroscience, pharmacology, and other aspects of research, and provides a basis for judging the psychological and physiological state of mice. To solve the problem whereby traditional behavior recognition methods only model behavioral changes in mice over time or space, we propose a symmetrical algorithm that can capture spatiotemporal information based on behavioral changes. The algorithm first uses the improved DeepLabCut keypoint detection algorithm to locate the nose, left ear, right ear, and tail root of the mouse, and then uses the ConvLSTM network to extract spatiotemporal information from the keypoint feature map sequence to classify five behaviors of mice: walking straight, resting, grooming, standing upright, and turning. We developed a murine keypoint detection and behavior recognition dataset, and experiments showed that the method achieved a percentage of correct keypoints (PCK) of 87±1% at three scales and against four backgrounds, while the classification accuracy for the five kinds of behaviors reached 93±1%. The proposed method is thus accurate for keypoint detection and behavior recognition, and is a useful tool for murine motion behavior recognition.

show abstract

“…In the murine behavior recognition task, 3DCNN [33,34], LSTM, and Bi-LSTM [35,36] were compared with ConvLSTM. The 3DCNN network also used the keypoint feature map sequence as an input.…”

Section: Methodsmentioning

confidence: 99%

Murine Motion Behavior Recognition Based on DeepLabCut and Convolutional Long Short-Term Memory Network

Liu¹,

Zhu

Rao

2022

Symmetry

View full text Add to dashboard Cite

show abstract

“…Symmetry-Adapted Machine Learning for Information Security delivers successfully accepted submissions [1][2][3][4][5][6][7][8][9][10][11][12] in this Special Issue of Symmetry. Proposals for several innovative paradigms, novel architectural designs, and frameworks with symmetry-adapted machine learning are covered in this particular issue.…”

Section: Symmetry-adapted Machine Learning For Information Securitymentioning

confidence: 99%

“…Jiang et al [7] introduces a novel 3D-CNN model to improve the identification accuracy of battlefield target aggregation operation while maintaining the low computational cost of spatio-temporal depth neural networks. A 3D convolution two-stream model based on multi-scale feature fusion further improved the multi-fiber system reducing the computational complexity of the network.…”

Section: Symmetry-adapted Machine Learning For Information Securitymentioning

confidence: 99%

Symmetry-Adapted Machine Learning for Information Security

Park

2020

Symmetry

View full text Add to dashboard Cite

Nowadays, data security is becoming an emerging and challenging issue due to the growth in web-connected devices and significant data generation from information and communication technology (ICT) platforms. Many existing types of research from industries and academic fields have presented their methodologies for supporting defense against security threats. However, these existing approaches have failed to deal with security challenges in next-generation ICT systems due to the changing behaviors of security threats and zero-day attacks, including advanced persistent threat (APT), ransomware, and supply chain attacks. The symmetry-adapted machine-learning approach can support an effective way to deal with the dynamic nature of security attacks by the extraction and analysis of data to identify hidden patterns of data. It offers the identification of unknown and new attack patterns by extracting hidden data patterns in next-generation ICT systems. Therefore, we accepted twelve articles for this Special Issue that explore the deployment of symmetry-adapted machine learning for information security in various application areas. These areas include malware classification, intrusion detection systems, image watermarking, color image watermarking, battlefield target aggregation behavior recognition models, Internet Protocol (IP) cameras, Internet of Things (IoT) security, service function chains, indoor positioning systems, and cryptoanalysis.

show abstract

“…In recent years, researchers have been trying to use artificial intelligence for planning in order to reduce the burden of commanders and improve speed and efficiency. But artificial intelligence is mainly used for tactical decision making, such as target classification [1][2][3], behavior recognition [4], threat assessment and target assignment [5,6], fire support of the maneuver operation [7], and so on. For combat-level mission planning, there is little research on the application of machine learning because it is difficult to obtain training datasets.…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Mission Planning Model for the Air Strike Operations against Islands Based on Neural Network and Simulation

Song

Zhang

Zhao

et al. 2022

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

Mission planning of air strike operations is hard because it has to give instructions to a large number of units during a relatively long period of time in an uncertain environment. If some instruction parameters can be calculated by an intelligent agent, better strategies can be found more quickly. In a specific combat scenario of air strike operations against islands, an intelligent model is proposed to improve the performance and flexibility of mission planning. The proposed intelligent mission planning model is based on rule-based decision and uses a fully connected recurrent neural network to calculate some of the decision parameters. The proposed intelligent mission planning model shows better results as compared to rule-based decision making with randomized parameters, and it performs as good as experts in the test set of the specific combat scenario.

show abstract

Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion

Cited by 7 publications

References 17 publications

Murine Motion Behavior Recognition Based on DeepLabCut and Convolutional Long Short-Term Memory Network

Murine Motion Behavior Recognition Based on DeepLabCut and Convolutional Long Short-Term Memory Network

Symmetry-Adapted Machine Learning for Information Security

An Intelligent Mission Planning Model for the Air Strike Operations against Islands Based on Neural Network and Simulation

Contact Info

Product

Resources

About