Computational intelligence algorithm for indoor lighting control systems
Various studies indicate that adequate lighting a has a major role in influencing productivity indoors. Through integration with sensors, IoT and machine learning algorithm, intelligent lighting systems can be engineered. The benefits of intelligent lighting include – faster return on investment, en...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143086 |
| _version_ | 1811679356743843840 |
|---|---|
| author | Sneha Shrikumar |
| author2 | Arokiaswami Alphones |
| author_facet | Arokiaswami Alphones Sneha Shrikumar |
| author_sort | Sneha Shrikumar |
| collection | NTU |
| description | Various studies indicate that adequate lighting a has a major role in influencing productivity indoors. Through integration with sensors, IoT and machine learning algorithm, intelligent lighting systems can be engineered. The benefits of intelligent lighting include – faster return on investment, energy savings, increased security, and enablement of remote access, among others.
In this thesis, the development of one such intelligent lighting system has been detailed. Devices like Ultra-wide band sensors and Lux sensors were collected and utilized in this system to retrieve information about the user’s location and existing brightness in the room, respectively. This data was preprocessed, scaled, and then transmitted to various machine learning algorithms to predict suitable lighting conditions. The outputs of these algorithms were then stored and compared to find the best fit for this set up. Analysis of the results revealed that Decision Tree algorithm has the best performance with an F1 score of 0.9072.
Therefore, using the proposed lighting system, the brightness at desk level within the office space will always be within the recommended brightness range of 200-400 Lux, irrespective of the changing brightness conditions in the area. As adequate lighting is always provided, it ensures user comfort, well-being, and increased security.
The proposed lighting system can be easily scaled to a wide number of applications that include lighting in homes, offices, workspaces, and buildings. As these lights can be accessed from any part of the world, it provides remote monitoring facility and enhances user experiences. Lastly, as the system comprises of low-cost components that are also easily replaceable and only provide lighting when needed, it can provide huge cost and power savings. |
| first_indexed | 2024-10-01T03:07:52Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/143086 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:07:52Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1430862023-07-04T16:53:44Z Computational intelligence algorithm for indoor lighting control systems Sneha Shrikumar Arokiaswami Alphones School of Electrical and Electronic Engineering Energy Research Institute @NTU Krishnamoorthy Baskaran EAlphones@ntu.edu.sg Engineering::Electrical and electronic engineering Various studies indicate that adequate lighting a has a major role in influencing productivity indoors. Through integration with sensors, IoT and machine learning algorithm, intelligent lighting systems can be engineered. The benefits of intelligent lighting include – faster return on investment, energy savings, increased security, and enablement of remote access, among others. In this thesis, the development of one such intelligent lighting system has been detailed. Devices like Ultra-wide band sensors and Lux sensors were collected and utilized in this system to retrieve information about the user’s location and existing brightness in the room, respectively. This data was preprocessed, scaled, and then transmitted to various machine learning algorithms to predict suitable lighting conditions. The outputs of these algorithms were then stored and compared to find the best fit for this set up. Analysis of the results revealed that Decision Tree algorithm has the best performance with an F1 score of 0.9072. Therefore, using the proposed lighting system, the brightness at desk level within the office space will always be within the recommended brightness range of 200-400 Lux, irrespective of the changing brightness conditions in the area. As adequate lighting is always provided, it ensures user comfort, well-being, and increased security. The proposed lighting system can be easily scaled to a wide number of applications that include lighting in homes, offices, workspaces, and buildings. As these lights can be accessed from any part of the world, it provides remote monitoring facility and enhances user experiences. Lastly, as the system comprises of low-cost components that are also easily replaceable and only provide lighting when needed, it can provide huge cost and power savings. Master of Science (Communications Engineering) 2020-07-30T01:32:56Z 2020-07-30T01:32:56Z 2020 Thesis-Master by Coursework https://hdl.handle.net/10356/143086 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Sneha Shrikumar Computational intelligence algorithm for indoor lighting control systems |
| title | Computational intelligence algorithm for indoor lighting control systems |
| title_full | Computational intelligence algorithm for indoor lighting control systems |
| title_fullStr | Computational intelligence algorithm for indoor lighting control systems |
| title_full_unstemmed | Computational intelligence algorithm for indoor lighting control systems |
| title_short | Computational intelligence algorithm for indoor lighting control systems |
| title_sort | computational intelligence algorithm for indoor lighting control systems |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/143086 |
| work_keys_str_mv | AT snehashrikumar computationalintelligencealgorithmforindoorlightingcontrolsystems |