Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 2, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Published on: April 8, 2019

STELLAR-CB: Synthetic Temporal LSTM for Livestock Activity Recognition-Cow Behaviour.

Ghufran Ahmed¹, Rauf Ahmed Shams Malick², Ahmad Sami Al-Shamayleh³

¹Department of Computer Science, School of Computing, National University of Computer and Emerging Sciences, Karachi, Pakistan.

Veterinary Medicine and Science

|June 1, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Green Extraction of <i>Citrus sinensis</i> (L.) Osbeck Peel Essential Oil and Its Impact on Antioxidant and Antimicrobial Activity: Supported by Molecular Docking and DFT Analysis.

Food science & nutrition·2026

Same author

Adaptive confidence ensemble reranking for reliable knowledge-intensive question answering.

Scientific reports·2026

Same author

Tensor language model enables generative scheduling for efficient tensor compilation.

Scientific reports·2026

Same author

Gastroenterological disease detection using transformer-based medical imaging for sustainable healthcare.

Scientific reports·2026

Same author

Sustainable regional corn yield prediction for the United States through interpretable machine learning approach.

Scientific reports·2026

Same author

In-situ cardiac arrest simulations in a tertiary-care hospital in Pakistan: a feasibility study exploring challenges and future directions.

Resuscitation plus·2026

This summary is machine-generated.

Precision livestock farming (PLF) uses activity sensors for animal behavior monitoring. A new framework combines simple SMOTE with LSTM networks to accurately detect rare behaviors, improving animal welfare and farm productivity.

Area of Science:

Agricultural AI
Machine Learning for Animal Behavior
Time-Series Data Analysis

Background:

Precision livestock farming (PLF) relies on activity sensors to monitor animal behaviors.
Class imbalance in sensor data datasets often leads to underrepresentation of critical minority behaviors like 'escaping' or 'being mounted.'

Purpose of the Study:

To develop a novel framework for robust animal behavior recognition using imbalanced time-series data.
To address the challenge of underrepresented minority behaviors in PLF datasets.

Main Methods:

Integration of simple Synthetic Minority Oversampling Technique (SMOTE) with non-overlapping windowed segmentation.
Utilizing Long Short-Term Memory (LSTM) networks to capture temporal dependencies in balanced datasets.

Keywords:

cow behaviour classification data augmentation deep learning livestock activity recognition long‐short‐term memory (LSTM) networks precision livestock farming (PLF)synthetic minority oversampling technique (SMOTE)time series data analysis

Related Experiment Videos

Last Updated: Jun 2, 2026

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Published on: April 8, 2019

Developing a breed-agnostic model by evaluating on a composite accelerometer dataset from three distinct cows.

Main Results:

Achieved state-of-the-art performance with 97.24% accuracy, 97.56% precision, 97.24% recall, and 97.29% F1-score.
Significantly improved detection of rare behaviors without compromising majority class precision.
Demonstrated generalizability across breeds and robustness to behavioral variability.

Conclusions:

The proposed framework offers a resource-efficient and practical solution for handling imbalanced time-series data in agricultural AI.
This approach enhances the reliability of automated behavior monitoring, contributing to improved animal welfare and farm productivity.
The study provides a blueprint for accessible, breed-agnostic AI tools in precision livestock farming.