Context-Aware Mouse Behavior Recognition Using Hidden Markov Models

Jiang, Zheheng; Crookes, Danny; Green, Brian D.; Zhao, Yunfeng; Ma, Haiping; Li, Ling; Zhang, Shengping; Tao, Dacheng; Zhou, Huiyu

doi:10.1109/tip.2018.2875335

Cited by 40 publications

(37 citation statements)

References 46 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particularly, our dataset is more challenging than the existing DeepLabCut Mouse Pose dataset. For example, our PDMB dataset contains a wide range of behaviours [4] (e.g., rear, groom and eat), and abnormal poses. Fig.…”

Section: A Datasets and Evaluation Metricsmentioning

confidence: 99%

“…Historically, studying mouse behaviour can be a time-consuming and difficult task because the collected data requires experts to physically engage. Recent advances in computer vision and machine learning have facilitated automated analysis for complex behaviours [4]- [6]. This makes it possible to conduct a wide range of behavioural experiments without human intervention, which has yielded new insights into the pathologies and treatment of specific diseases [7]- [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structured Context Enhancement Network for Mouse Pose Estimation

Zhou

Jiang

Liu

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Automated analysis of mouse behaviours is crucial for many applications in neuroscience. However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours. Although deep learning based methods have made promising advances in human pose estimation, they cannot be directly applied to pose estimation of mice due to different physiological natures. Particularly, since mouse body is highly deformable, it is a challenge to accurately locate different keypoints on the mouse body. In this paper, we propose a novel Hourglass network based model, namely Graphical Model based Structured Context Enhancement Network (GM-SCENet) where two effective modules, i.e., Structured Context Mixer (SCM) and Cascaded Multi-level Supervision (CMLS) are subsequently implemented. SCM can adaptively learn and enhance the proposed structured context information of each mouse part by a novel graphical model that takes into account the motion difference between body parts. Then, the CMLS module is designed to jointly train the proposed SCM and the Hourglass network by generating multi-level information, increasing the robustness of the whole network. Using the multi-level prediction information from SCM and CMLS, we develop an inference method to ensure the accuracy of the localisation results. Finally, we evaluate our proposed approach against several baselines on our Parkinson's Disease Mouse Behaviour (PDMB) and the standard DeepLabCut Mouse Pose datasets. The experimental results show that our method achieves better or competitive performance against the other state-of-the-art approaches.

show abstract

Section: A Datasets and Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Structured Context Enhancement Network for Mouse Pose Estimation

Zhou

Jiang

Liu

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, the approach requires data access platforms that share data and compare models. Initial attempts to make progress in this direction include the OpenBehavior project (Jiang et al, 2019a;White et al, 2019) but more efforts in this direction are needed (von Ziegler et al, 2020). Finally, a limitation is the advanced computer science knowledge required to implement and adapt the latest algorithms to neuroscientific and clinical settings .…”

Section: Advantages and Limitationsmentioning

confidence: 99%

Challenges of a small world analysis for the continuous monitoring of behavior in mice

Bermudez-Contreras¹,

Whishaw²,

sutherland³

et al. 2021

Preprint

View full text Add to dashboard Cite

The automation of monitoring and analysis of mouse behaviour in a homecage can be obtained from continuous video records with machine learning and computer vision. The approach of recreating a mouse’s “real world” behavior and laboratory test behavior in the “small world” of a laboratory cage can provide insights into phenotypical expression of mouse genotypes, development and aging, and neurological disease. Algorithms identify behavioral acts (walk, rear), actions (sleep duration, distance travelled), organized patterns of movement (home base activity and excursions) over extended periods of time. In addition, performance on specific tests can be incorporated within a mouse’s living arrangement. Here we review approaches to engineering a small world and state of the art machine learning analyses for automated study of mouse homecage behavior. We highlight advantages and limitations of these approaches as a supplement to acute behavioral testing methodology.

show abstract

“…In recent years, ML algorithms have become a popular problem-solving approach in various disciplines of science, from computer, vision and behaviour analysis [7] to cybersecurity, e.g. anomaly detection [8].…”

Section: A Machine Learningmentioning

confidence: 99%

Evaluation of Machine Learning Algorithms for Anomaly Detection

Elmrabit

Zhou

et al. 2020

2020 International Conference on Cyber Security and Protection of Digital Services (Cyber Security)

Self Cite

105

View full text Add to dashboard Cite

Malicious attack detection is one of the critical cyber-security challenges in the peer-to-peer smart grid platforms due to the fact that attackers' behaviours change continuously over time. In this paper, we evaluate twelve Machine Learning (ML) algorithms in terms of their ability to detect anomalous behaviours over the networking practice. The evaluation is performed on three publicly available datasets: CICIDS-2017, UNSW-NB15 and the Industrial Control System (ICS) cyberattack datasets. The experimental work is performed through the ALICE high-performance computing facility at the University of Leicester. Based on these experiments, a comprehensive analysis of the ML algorithms is presented. The evaluation results verify that the Random Forest (RF) algorithm achieves the best performance in terms of accuracy, precision, Recall, F1-Score and Receiver Operating Characteristic (ROC) curves on all these datasets. It is worth pointing out that other algorithms perform closely to RF and that the decision regarding which ML algorithm to select depends on the data produced by the application system.

show abstract

Context-Aware Mouse Behavior Recognition Using Hidden Markov Models

Cited by 40 publications

References 46 publications

Structured Context Enhancement Network for Mouse Pose Estimation

Structured Context Enhancement Network for Mouse Pose Estimation

Challenges of a small world analysis for the continuous monitoring of behavior in mice

Evaluation of Machine Learning Algorithms for Anomaly Detection

Contact Info

Product

Resources

About