Human Activity Classification for Electricity Infrastructure Protection in Rwanda

Author (s)

Ntambara Etienne, Rukundo Simeon, Nkurunziza Egide, & Ingabire Daria

Abstract

The theft and vandalism of REG electricity infrastructure can disrupt essential services, raise maintenance costs, and pose safety hazards. However, no prior work has established a leakage-controlled, balanced image classification benchmark for activity cues relevant to this operational context. This study developed and tested an AI-based human activity recognition system as an early-warning tool to protect Rwanda Energy Group (REG) electricity infrastructure. We assembled two public Kaggle image datasets, Wall Climbing ALEE and Climbing V2, into six classes: climbing, cutting, normal, opening, suspicious, and vendors. The final dataset included 23,647 images: 19,554 for training, 1,814 for validation, and 2,279 for testing. Oversampling during training reduced the imbalance ratio from 13.751 to 1.000, while maintaining validation and test distributions. We fine-tuned a pretrained YOLO11m model with 224×224 pixel inputs, applying augmentation, AdamW optimization, dropout, cosine learning-rate scheduling, and early stopping. On the untouched test set, the model achieved 99.74% top-1 accuracy, 99.12% balanced accuracy, 99.40% macro F1-score, 0.9998 macro ROC-AUC, and 0.9971 macro average precision; it misclassified only six images out of 2,279. Suspicious activity detection remains a primary challenge, with 95.95% recall and 97.93% F1-score. GPU benchmarking on an NVIDIA Tesla T4 showed a mean latency of 6.64 ms and throughput of about 150.50 images/sec. These results support deploying the model as a high-performance visual perception layer, though operational use will require temporal modeling, sensor fusion, field validation, human oversight, and privacy safeguards.

Key words: Human activity recognition, CCTV, YOLO11, Electricity infrastructure security, Early warning, Rwanda Energy Group, REG.

Download PDF

Cite This Article:

Ntambara, E., Rukundo, S., Nkurunziza, E., & Ingabire, D. (2026). Human Activity Classification for Electricity Infrastructure Protection in Rwanda, Journal of Scientific Reports, 15(1), 103-127.  DOI: https://doi.org/10.58970/JSR.1242

About Author (s)

Ntambara Etienne (Corresponding author), ICT Department, Rwanda Polytechnic Huye College, Huye, Rwanda. ORCID: https://orcid.org/0009-0002-4071-8300

Rukundo Simeon, Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore. ORCID: https://orcid.org/0009-0000-9904-2304

Nkurunziza Egide, ICT Department, Rwanda Polytechnic Huye College, Huye, Rwanda. ORCID: https://orcid.org/0009-0007-0977-3156

Ingabire Daria, ICT Department, Rwanda Polytechnic Huye College, Huye, Rwanda. ORCID: https://orcid.org/0009-0000-6333-4030

Download PDF

DOI: https://doi.org/10.58970/JSR.1242

Summarize this article with: