Research map / Architectures and efficiency / CNN design
MSDC: Exploiting Multi-State Power Consumption in Non-intrusive Load Monitoring Based on a Dual-CNN Model
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use multi-state power representation with dual CNNs rather than a single-state CNN | NILM · REDD, dishwasher, unseen-house test | MAE: 8.40 -> 4.64 | Helped |
| Use multi-state power representation with dual CNNs rather than a single-state CNN | NILM · UK-DALE, dishwasher, unseen-house test | MAE: 8.75 -> 3.38 | Helped |
| Replace state cross-entropy loss with CRF regularization to model state transitions (ablation) | MSDC · REDD, unseen-house average | MAE: 19.70 -> 19.32 | Helped |
| Replace state cross-entropy loss with CRF regularization to model state transitions (ablation) | MSDC · REDD, unseen-house average | SAE: 14.33 -> 13.28 | Helped |
| Replace state cross-entropy loss with CRF regularization to model state transitions (ablation) | MSDC · REDD, unseen-house average | SAE_delta | Hurt |
Closest papers by meaning
- Sequence-to-Point Learning With Neural Networks for Non-Intrusive Load Monitoring (AAAI 2018 · similarity 0.90)
- Subtask Gated Networks for Non-Intrusive Load Monitoring (AAAI 2019 · similarity 0.89)
- PowerPM: Foundation Model for Power Systems (NeurIPS 2024 · similarity 0.82)
- NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling (NeurIPS 2026 · similarity 0.80)
- The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference (ICML 2025 · similarity 0.79)
- NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes (NeurIPS 2024 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.