Security-aware selective quantization and optimization framework (SASQOF) for resource-constrained ML-based IoT irrigation systems
This study evaluates selective dynamic 8-bit integer (INT8) quantization of long short-term memory (LSTM) recurrent weights while retaining a 32-bit floating-point (FP32) linear output layer, together with authenticated sensor processing, using 10,257 observations from the Secured and Optimized IoT-Based Irrigation System (SOIBIS) experimental farm at Federal University Lokoja, Nigeria. Five seeded runs compare eight models under chronological and feature-group evaluations. The chronological test contains only label pattern 101, for which a majority baseline also achieves 100% exact-match accuracy. On the class-diverse feature-group test, selective quantization achieves 98.40% mean exact-match accuracy, compared with 100% for a decision tree and 84.68% for a majority baseline. Selective quantization reduces serialized model size by 64.9% and single-record host model-only latency by 50.7%, but increases 12-record model-only latency by approximately 41.1%. Mean authenticated single-record inference-path time is 0.441 ms on the host. All 1,200 specified functional packet checks met their expected outcomes. These are host-software findings, not evidence of ESP32 deployment, independently verified pump actuation, water savings, or agronomic superiority.
Authors
- Dauda Olorunkemi Isiaka
- Joshua Babatunde Agbogun
- Victoria Yemi-peters (ORCID: https://orcid.org/0000-0003-3364-4593)
- Afolayan Ayodele Obiniyi
Institutions
- Federal University Lokoja (NG)
Publication Details
- Journal
- African Scientific Reports
- Published
- 2026-11-16
- DOI
- https://doi.org/10.46481/asr.2026.5.3.646
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00