Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies
  1. Home
  3. Temporal And Autoregressive Features For Cattle Behavior Classification Using Low-power Lorawan Accelerometer Data.
  1. Home
  3. Temporal And Autoregressive Features For Cattle Behavior Classification Using Low-power Lorawan Accelerometer Data.

Related Concept Videos

Classification of Signals01:30

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

You might also read

Related Articles

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

Sort by
Same author

A discrete enzyme action optimizer for traveling salesman problems with a smart tourism routing application: a case study in Bitlis, Türkiye.

Scientific reports·2026
Same author

Robust Position-Only Null Steering in Linear Antenna Arrays via a Nature-Inspired Optimizer for Wireless Communication.

Biomimetics (Basel, Switzerland)·2026
Same author

Intelligent Control of Magnetic Ball Suspension Systems via a Novel Hyperbolic Tangent PID Controller Tuned by the Artificial Lemming Algorithm.

Biomimetics (Basel, Switzerland)·2026
Same author

Temperature Control of Nonlinear Continuous Stirred Tank Reactors Using an Enhanced Nature-Inspired Optimizer and Fractional-Order Controller.

Biomimetics (Basel, Switzerland)·2026
Same author

Global-best-guided electric eel foraging optimizer for robust parameter identification of Lorenz and memristive chaotic systems.

Scientific reports·2026
Same author

Training Rarámuri Criollo Cattle to Virtual Fencing in a Chaparral Rangeland.

Animals : an open access journal from MDPI·2025
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
Same journal

Three-Dimensional Modeling and Performance Analysis of Dynamic mmWave V2I Networks Based on Stochastic Geometry.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet
07:05

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet

Published on: January 3, 2017

Temporal and Autoregressive Features for Cattle Behavior Classification Using Low-Power LoRaWAN Accelerometer Data.

Onur Uysal1, Mehmet Emin Bakir2, Andres R Perea2

  • 1Department of Computer Engineering, Izmir Katip Celebi University, 35620 Izmir, Turkey.

Sensors (Basel, Switzerland)
|June 26, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

This study enhances cow behavior monitoring using AI and sensor data compressed into a Motion Index (MI). New time-series features significantly improve the accuracy of distinguishing between resting and ruminating behaviors.

Keywords:
LoRaWANaccelerometercattle behavior classificationmachine learningprecision agricultureprecision livestock managementsmart farmingtime-series analysis

Related Experiment Videos

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet
07:05

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet

Published on: January 3, 2017

Area of Science:

  • Precision Livestock Management
  • Animal Behavior
  • Machine Learning

Background:

  • Automated behavior monitoring in livestock is crucial for precision management.
  • Existing methods using accelerometer sensors and AI face energy and bandwidth limitations on rangelands.
  • Low-Power Long-Range Wide-Area Network (LoRaWAN) collars use a compressed Motion Index (MI) but struggle with fine-grained behavior classification.

Purpose of the Study:

  • To improve the accuracy of automated cow behavior classification using compressed sensor data.
  • To overcome the limitations of the Motion Index (MI) in distinguishing between stationary behaviors like resting and ruminating.
  • To develop a robust system for autonomous deployment in precision livestock management.

Main Methods:

  • Utilized a dataset of 9222 labeled observations from 24 cows across four breeds.
  • Applied time-series analysis to the Motion Index (MI) data, incorporating session-aware lag features, rolling statistics, and autoregressive previous-behavior features.
  • Implemented a Viterbi sequence-decoding step with a learned behavior-transition model for autonomous deployment.

Main Results:

  • The enhanced time-series approach significantly improved four-class accuracy from 0.647 to 0.94 macro-F1.
  • Per-class F1 scores reached 0.95 for ruminating and 0.92 for resting, a substantial improvement over MI-only models.
  • The Viterbi decoding step recovered significant ruminating signals in autonomous settings while maintaining accuracy for walking and grazing.

Conclusions:

  • Treating compressed sensor data (MI) as a time series effectively recovers information lost during onboard compression.
  • The developed feature engineering and sequence decoding methods provide a robust solution for accurate, low-energy behavior monitoring in livestock.
  • The improvements are consistent across different classifiers and cattle breeds, highlighting the generalizability of the approach.