2022
DOI: 10.1109/jiot.2021.3090583
|View full text |Cite
|
Sign up to set email alerts
|

Wireless AI-Powered IoT Sensors for Laboratory Mice Behavior Recognition

Abstract: According to the U.S. Department of Agriculture in 2018, there are more than 100 million animals used in research, education, and testing per year. Of the laboratory animals used for research, 95 percent are mice and rats as reported by the Foundation for Biomedical Research (FBR). We present here our work in developing wireless Artificial Intelligent (AI)-powered IoT Sensors (AIIS) for laboratory mice motion recognition utilizing embedded micro-inertial measurement units (uIMUs). Based on the AIIS, we have de… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
1
1

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 52 publications
0
2
0
Order By: Relevance
“…[48][49][50] Due to the sample size imbalance between different behaviors, training an effective classification model that can recognize both large-sample-size mouse behavior (i.e., Resting, Eating) and small-sample-size behavior (i.e., Drinking, Scratching) is difficult. In our previous work, [29] Chen et al proposed and proved the effectiveness of an imbalanced learning method to improve classification accuracy. This paper also applied the imbalanced learning method during the classification process.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…[48][49][50] Due to the sample size imbalance between different behaviors, training an effective classification model that can recognize both large-sample-size mouse behavior (i.e., Resting, Eating) and small-sample-size behavior (i.e., Drinking, Scratching) is difficult. In our previous work, [29] Chen et al proposed and proved the effectiveness of an imbalanced learning method to improve classification accuracy. This paper also applied the imbalanced learning method during the classification process.…”
Section: Methodsmentioning
confidence: 99%
“…Our group has recently developed a wireless IoT sensor‐based system for laboratory mice motion data collection. [ 29 ] By rudimentary data analyses, we were able to classify five behaviors, including resting, walking, rearing, digging, and shaking, of mice using a support vector machine (SVM) with an average recall of 76.23%. In this work, we discuss the extremely important work of selecting the proper AI algorithms in order to enable small motion sensor data to be applicable for real‐time tracking and recognition of small animal motions.…”
Section: Introductionmentioning
confidence: 99%
“…Smart libraries and labs can also be used to improve accessibility, security, and energy efficiency [38]. Therefore, AI and the IoT at the application and infrastructure levels in the education systems of smart cities can help to automate and optimize various systems and processes, resulting in an intelligent campus where IoT devices are employed to track students' and teachers' movements on campus, to improve security, and to optimize the usage of the infrastructure as well as improved efficiency, productivity, and cost savings, and an enhanced quality of education for students [39].…”
Section: Parent-teacher Communicationmentioning
confidence: 99%