A Hybrid 1D CNN-LSTM Model for Anomaly Detection in Agricultural IoT Systems
Smart farming depends on Internet of Things (IoT) sensors that report temperature, humidity, soil moisture and light intensity around the clock. When these sensors fail or their readings are corrupted, automated decisions such as irrigation and climate control can waste resources and reduce yield. Threshold rules and classical machine learning methods struggle with the daily and seasonal cycles found in farm data, and they often raise too many false alarms. This study develops and tests a hybrid 1D Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) model for anomaly detection in agricultural IoT systems.
Authors
- Ridwan Kolapo
- Mustapha Abubakar Ibrahim
- Nurudeen Ibrahim
- Prema Kirubakaran
Institutions
- Nile University of Nigeria (NG)
Publication Details
- Journal
- International Journal of Innovative Science and Research Technology (IJISRT)
- Published
- 2026-11-20
- DOI
- https://doi.org/10.38124/ijisrt/26nov646
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Nile University