MétaCan
Menu
Back to cohort
Record W4223586001 · doi:10.1016/j.jafr.2022.100308

Weed detection in soybean crops using custom lightweight deep learning models

2022· article· en· W4223586001 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueJournal of Agriculture and Food Research · 2022
Typearticle
Languageen
FieldAgricultural and Biological Sciences
TopicSmart Agriculture and AI
Canadian institutionsToronto Metropolitan University
FundersRyerson University
KeywordsWeedDeep learningConvolutional neural networkComputer scienceArtificial intelligencePrecision agricultureRaspberry piAgricultureAgricultural engineeringMachine learningPattern recognition (psychology)Embedded systemAgronomyEngineeringInternet of Things

Abstract

fetched live from OpenAlex

Weed detection has become an integral part of precision farming that leverages the IoT framework. Weeds have become responsible for 45% of the agriculture industry's crop losses due mainly to the competition with crops. An efficient weed detection method can reduce this percentage. This paper proposes a vision-based weed detection system using deep learning models that effectively detect weed within a soybean plantation. Five deep learning models are used, including MobileNetV2, ResNet50, and three custom Convolutional Neural Network (CNN) Models. The MobileNetV2 and ResNet50 were deployed on a Raspberry PI controller for comparison purposes. Based on a dataset with 400 images and 1536 total segments, the custom 5-layer CNN architecture shows high detection accuracy of 97.7% and the lowest latency & memory usage with 1.78 GB and 22.245 ms respectively. Utilizing the proposed custom deep learning CNN model with high accuracy can positively impact efficiency, time, and overall production within the soybean industry.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.888
Threshold uncertainty score0.740

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.066
GPT teacher head0.272
Teacher spread0.207 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it