MétaCan
Menu
Back to cohort
Record W4408689889 · doi:10.2478/cait-2025-0002

Federated Learning and Blockchain-Based Collaborative Framework for Real-Time Wild Life Monitoring

2025· article· en· W4408689889 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.

Bibliographic record

VenueCybernetics and Information Technologies · 2025
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsHorizon College and Seminary
Fundersnot available
KeywordsBlockchainComputer scienceCollaborative learningData scienceProcess managementKnowledge managementComputer securityBusiness

Abstract

fetched live from OpenAlex

Abstract Effective wildlife monitoring in hilly and rural areas can protect communities and diminish human-wildlife conflicts. A collaborative framework may overcome challenges like inadequate data integrity and security, declining detection accuracy over time, and delays in critical decision-making. The proposed study aims to develop a real-time wildlife monitoring framework using Federated Learning and blockchain to improve conservation strategies. Min-max normalization enhances training data and Elastic Weight Consolidation (EWC) for real-time adaptation. The improvised YOLOv8+EWC enables real-time classification and continual learning and prevents catastrophic forgetting. It also automates actions based on detection results using smart contracts and ensures secure, transparent data management with blockchain. Compared to existing classifiers such as Deep Neural Network, Dense-YOLO4, and WilDect: YOLO, YOLOv8+EWC performs exceptionally well across several metrics, accomplishing an accuracy of 98.91%. Thus, the proposed model enables reliable decision-making by providing accurate, real-time information about wildlife.

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)0.000
metaresearch head score (Gemma)0.023
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Open science
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.772
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.023
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0020.008
Research integrity0.0000.000
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 head0.010
GPT teacher head0.260
Teacher spread0.250 · 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