Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home
Automated indoor environmental control is a research topic that is beginning to receive much attention in smart home automation. All machine learning models proposed to date for this purpose have relied on reinforcement learning using simple metrics of comfort as reward signals. Unfortunately, such...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/13/5091 |
| _version_ | 1797591766501687296 |
|---|---|
| author | Omar al-Ani Sanjoy Das Hongyu Wu |
| author_facet | Omar al-Ani Sanjoy Das Hongyu Wu |
| author_sort | Omar al-Ani |
| collection | DOAJ |
| description | Automated indoor environmental control is a research topic that is beginning to receive much attention in smart home automation. All machine learning models proposed to date for this purpose have relied on reinforcement learning using simple metrics of comfort as reward signals. Unfortunately, such indicators do not take into account individual preferences and other elements of human perception. This research explores an alternative (albeit closely related) paradigm called imitation learning. In the proposed architecture, machine learning models are trained with tabular data pertaining to environmental control activities of the real occupants of a residential unit. This eliminates the need for metrics that explicitly quantify human perception of comfort. Moreover, this article introduces the recently proposed deep attentive tabular neural network (TabNet) into smart home research by incorporating TabNet-based components within its overall framework. TabNet has consistently outperformed all other popular machine learning models in a variety of other application domains, including gradient boosting, which was previously considered ideal for learning from tabular data. The results obtained herein strongly suggest that TabNet is the best choice for smart home applications. Simulations conducted using the proposed architecture demonstrate its effectiveness in reproducing the activity patterns of the home unit’s actual occupants. |
| first_indexed | 2024-03-11T01:42:02Z |
| format | Article |
| id | doaj.art-6c6b7f69ed46479184bde6ed62d5f57e |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T01:42:02Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-6c6b7f69ed46479184bde6ed62d5f57e2023-11-18T16:30:16ZengMDPI AGEnergies1996-10732023-06-011613509110.3390/en16135091Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart HomeOmar al-Ani0Sanjoy Das1Hongyu Wu2Electrical & Computer Engineering Department, Kansas State University, Manhattan, KS 66506, USAElectrical & Computer Engineering Department, Kansas State University, Manhattan, KS 66506, USAElectrical & Computer Engineering Department, Kansas State University, Manhattan, KS 66506, USAAutomated indoor environmental control is a research topic that is beginning to receive much attention in smart home automation. All machine learning models proposed to date for this purpose have relied on reinforcement learning using simple metrics of comfort as reward signals. Unfortunately, such indicators do not take into account individual preferences and other elements of human perception. This research explores an alternative (albeit closely related) paradigm called imitation learning. In the proposed architecture, machine learning models are trained with tabular data pertaining to environmental control activities of the real occupants of a residential unit. This eliminates the need for metrics that explicitly quantify human perception of comfort. Moreover, this article introduces the recently proposed deep attentive tabular neural network (TabNet) into smart home research by incorporating TabNet-based components within its overall framework. TabNet has consistently outperformed all other popular machine learning models in a variety of other application domains, including gradient boosting, which was previously considered ideal for learning from tabular data. The results obtained herein strongly suggest that TabNet is the best choice for smart home applications. Simulations conducted using the proposed architecture demonstrate its effectiveness in reproducing the activity patterns of the home unit’s actual occupants.https://www.mdpi.com/1996-1073/16/13/5091comfort indexdeep tabular learningenvironmental controlimitation learningreinforcement learningPPV |
| spellingShingle | Omar al-Ani Sanjoy Das Hongyu Wu Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home Energies comfort index deep tabular learning environmental control imitation learning reinforcement learning PPV |
| title | Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home |
| title_full | Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home |
| title_fullStr | Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home |
| title_full_unstemmed | Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home |
| title_short | Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home |
| title_sort | imitation learning with deep attentive tabular neural networks for environmental prediction and control in smart home |
| topic | comfort index deep tabular learning environmental control imitation learning reinforcement learning PPV |
| url | https://www.mdpi.com/1996-1073/16/13/5091 |
| work_keys_str_mv | AT omaralani imitationlearningwithdeepattentivetabularneuralnetworksforenvironmentalpredictionandcontrolinsmarthome AT sanjoydas imitationlearningwithdeepattentivetabularneuralnetworksforenvironmentalpredictionandcontrolinsmarthome AT hongyuwu imitationlearningwithdeepattentivetabularneuralnetworksforenvironmentalpredictionandcontrolinsmarthome |