What question did this study set out to answer?

Develop and evaluate regularized recurrent neural network architectures capable of effective, real-time non-intrusive appliance load monitoring across unseen buildings.

August 1, 2018

Regularized LSTM Based Deep Learning Model: First Step towards Real-Time Non-Intrusive Load Monitoring

View Full Paper

Ask AI

Bookmark

Develop and evaluate regularized recurrent neural network architectures capable of effective, real-time non-intrusive appliance load monitoring across unseen buildings.
Designed and implemented two deep recurrent neural network architectures: Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU).
Applied regularization techniques to mitigate overfitting and evaluated generalization performance on buildings not included in the training dataset.
Assessed model performance across energy disaggregation tasks using accuracy, F1 score, and mean absolute error metrics.
The regularized LSTM model demonstrated superior performance in accuracy, F1 score, and mean absolute error when evaluated on unseen buildings.
Regularization improved network generalization, establishing the model as a viable approach for real-time end-use appliance energy disaggregation.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Computational modeling demonstrates accurate energy disaggregation using regularized LSTM networks across unseen buildings, indicating feasibility for real-time appliance load monitoring.

Cite This Study

Rafiq et al. (2018) studied this question.

synapsesocial.com/papers/6a0f85a82badbc352afe4951 https://doi.org/10.1109/sege.2018.8499519

View Full Paper

Ask AI

Bookmark

Implication

Computational modeling demonstrates accurate energy disaggregation using regularized LSTM networks across unseen buildings, indicating feasibility for real-time appliance load monitoring.

Regularized LSTM Based Deep Learning Model: First Step towards Real-Time Non-Intrusive Load Monitoring

Key Points

Discussion

Implication

Cite This Study

Regularized LSTM Based Deep Learning Model: First Step towards Real-Time Non-Intrusive Load Monitoring

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider