CoChat

Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

Open access

The DOI matches its Crossref record; 416 of the 431 references it cites were found in a registry or an index; 13 of the 141 sources its claims cite were checked for support.

Abstract

Smart lighting has become a universal smart product solution, with global revenues of up to US $5.9 billion by 2021. Six main factors drive the technology: light-emitting diode (LED) lighting, sensors, control, analytics, and intelligence.

Overview

CoChat Summary

## TL;DR

This survey reviews smart lighting research from 1993 to 2021 and maps how machine learning is used to solve smart lighting problems, especially for user comfort. It argues that activity recognition is the most promising direction for improving user comfort, but current solutions still face cost, accuracy, and real-time constraints.

## Key findings

  • The authors surveyed 332 papers on smart lighting and report that 59% of the publications were from 2019–2021.
  • From keyword-based classification, they found 4 main issues in smart lighting research (energy efficiency, computer network performance, control performance, and user comfort), 4 implementation targets (street lighting, building/office, home, and city), and 6 leading technologies (IoT, sensors, LED lights, intelligence, renewable energy, and energy harvesting).
  • They identify 8 machine learning application areas in recent smart lighting research: predictive control, intelligent control, hand-gesture recognition, clustering, activity recognition, anomaly detection, optimization, computer vision, and elderly management.
  • The paper reports that energy was the most popular topic with 44 papers, and only 6 papers discussed comfort in smart lighting.
  • For user comfort metrics, the survey lists LUR, UNC, LCR, PRR, CCT, and others, and states that LUR = 1 is optimal while UNC is better when closer to 0.

## Methods

  • The study is a systematic literature review (SLR) with stages of research question formulation, search strategy and selection, data extraction, and synthesis.
  • Search and selection used inclusion criteria based on the strings “smart lighting,” “machine learning,” “user comfort,” and “activity recognition” in the title, with English or Indonesian papers from 1993 to 2021, available in Google Scholar, and in PDF or HTML format.
  • The review analyzes the literature through topic classification, keyword extraction, and quality assessment, then synthesizes the results around smart lighting topics, machine learning methods, and user-comfort-related applications.

## Limitations

  • The paper states that no survey paper had thoroughly discussed all machine learning techniques used in smart lighting research to achieve user comfort before this review.
  • It says there is no existing research on activity recognition smart lighting that measures user comfort; this is explicitly presented as a research gap.
  • Evident from the text: the review’s literature search is limited to papers available in Google Scholar and to English/Indonesian documents from 1993–2021, which may exclude relevant work in other languages or sources.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/access.2022.3169765

Cites

416 of 416 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

FIGURE 1 A line chart comparison that shows the growth and projection of four smart home products from 2019 to 2025 and displays that the smart lighting penetration rate is higher than other products.
FIGURE 1 A line chart comparison that shows the growth and projection of four smart home products from 2019 to 2025 and displays that the smart lighting penetration rate is higher than other products.CC-BY · From the PDF
FIGURE 2 A combination chart consisting a bar chart that displays the smart lighting publications growth per year and a line chart that displays the cumulative growth from 2011 to 2021.
FIGURE 2 A combination chart consisting a bar chart that displays the smart lighting publications growth per year and a line chart that displays the cumulative growth from 2011 to 2021.CC-BY · From the PDF
FIGURE 3 A bar chart that shows the number of publications on three main topics of smart lighting where each topic is divided into subtopics of interest.
FIGURE 3 A bar chart that shows the number of publications on three main topics of smart lighting where each topic is divided into subtopics of interest.CC-BY · From the PDF
FIGURE 4 An illustration that shows an example of the layout of a complete smart lighting system applicable to a corporation where the solution connects to a cloud computing environment, extensive connectivity, and diverse user role management.
FIGURE 4 An illustration that shows an example of the layout of a complete smart lighting system applicable to a corporation where the solution connects to a cloud computing environment, extensive connectivity, and diverse user role management.CC-BY · From the PDF
FIGURE 5 A typical IoT architecture for smart lighting with three main layers: end device layer, platform layer, and application layer, supported by communications to connect all layers.
FIGURE 5 A typical IoT architecture for smart lighting with three main layers: end device layer, platform layer, and application layer, supported by communications to connect all layers.CC-BY · From the PDF
FIGURE 6 A mind map that explains the categories of each machine learning method and reference papers related to each machine learning method.
FIGURE 6 A mind map that explains the categories of each machine learning method and reference papers related to each machine learning method.CC-BY · From the PDF
FIGURE 7 The integration of a smart lighting system and machine learning-based activity recognition that promotes intelligent user behavior control while potentially increasing user comfort.
FIGURE 7 The integration of a smart lighting system and machine learning-based activity recognition that promotes intelligent user behavior control while potentially increasing user comfort.CC-BY · From the PDF
FIGURE 8 Activity recognition taxonomy based on sensors.
FIGURE 8 Activity recognition taxonomy based on sensors.CC-BY · From the PDF
FIGURE 9 An example of a HHMM model in activity recognition for smart lighting.
FIGURE 9 An example of a HHMM model in activity recognition for smart lighting.CC-BY · From the PDF
Image 10
CC-BY · From the PDF
Image 11
CC-BY · From the PDF
Image 12
CC-BY · From the PDF
Image 13
CC-BY · From the PDF

Verification

Claims the paper makes

13 Valid · 36 Not valid · 136 Not checked · 97 Own results and interpretations

36 more claims

Create a free account to see all 282 claims and to verify the 26 references still open.

See all claims — free account
  • Probably not a substantial claim. 225
  • It may state two separate claims as one. 58

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Items 201–400 of 416

Research works printed but not linked: 23

  1. 2022, Gartner Says Smart Lighting has the Potential to Reduce Energy Costs by 90 Percent
  2. Shaulova, 2022, Smart Home Report 2021—Comfort and Lighting
  3. 10.3390/su13116198 · DOI · Paper page
  4. Smys, 2020, Artificial neural network based power management for smart street lighting systems, J. Artif. Intell., 2, 42
  5. Braw, 2014, Illuminating cities with sustainable smart lighting systems, Guardian, 12, 1
  6. Lakade, 2019, Intelligent lighting system for classrooms and mall using iot, Int. Res. J. Eng. Technol., 6, 3223
  7. Mahandran, 2021, IoT based smart lighting system in an auditorium, Prog. Eng. Appl. Technol., 2, 8
  8. Fanoon, 2030, Smart lighting system for efficient street lighting, J. Technol. Value Addition, 1, 36
  9. Kim, 2019, Design of path prediction smart street lighting system on the Internet of Things, J. Chosun Natural Sci., 12, 14
  10. Khachane, 2018, Intelligent street lighting system, Int. J. Eng. Res. Comput. Sci. Eng, 5, 587
  11. 10.1051/itmconf/20213701024 · DOI · Paper page
  12. Saepurohman, 2019, Analisis principal component analysis (PCA) untuk mereduksi faktor-faktor Yang mempengaruhi kualitas kulit kikil sapi, Prosiding Seminar Konferensi Nasional IDEC, 6, C01
  13. Dharma, 2015, Implementasi principal component analysis pada sistem rekomendasi film dengan pendekatan user based collaborative filtering skripsi, 2, 3464
  14. Manju, 2011, An analysis of q-learning algorithms with strategies of reward function, Int. J. Comput. Sci. Eng., 3, 814
  15. 10.1109/SGCF.2018.8408951 · DOI · Paper page
  16. Divya, 2016, Survey on outlier detection techniques using categorical data, Int. Res. J. Eng. Technol., 3, 899
  17. Gao, 2020, Human action classification using adaptive boosting algorithm, Int. J. Elect., Electron., Comput. Eng. Technol., 1, 6
  18. Almeida, 2015, Computer vision based adaptive lighting solutions for smart and efficient system, J. Impact Factor, 6, 1
  19. Edition, 2010, Energy standard for buildings except low-rise residential buildings
  20. 10.1109/ACCESS.2019.2932055 · DOI
  21. Abdullayev, Mimo ann to daylight harvested hybrid lighting control for an office building, 169
  22. 10.1109/ACCESS.2020.2995461 · DOI · Paper page
  23. Daely, Implementation and analysis of real time scheduling for IoT: A case study of smart led street light, 622

Cited by

See all 101

Metadata

Authors
Putrada, A. G., Abdurohman, M., Perdana, D., & Nuha, H. H.
Affiliations
Telkom University (ID)
Venue
IEEE Access
Published
2022
Volume
10
Pages
45137-45178
ISSN
2169-3536 (ISSN-L)
OpenAlex
W4226062023
Cited by
101
References
431
Citations by year
2026: 15 · 2025: 31 · 2024: 22 · 2023: 24 · 2022: 9
FWCI
9.40
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • Telkom University through the Doctoral Dissertation Research Scheme and the Doctoral Study Program
  • Biofarma Corporation
  • Industri Telekomunikasi Indonesia (INTI) Corporation
  • Lembaga Pengelola Dana Pendidikan (LPDP) of Ministry of Finance of Republic Indonesia through Riset Inovatif Produktif (Rispro) Scheme
Topics
  • Physical Sciences › Engineering › Building and Construction › Building Energy and Comfort Optimization
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT-based Smart Home Systems
Keywords
smart lighting, user comfort, machine learning, activity recognition, Internet of Things, LED lighting, light-emitting diodes, correlated color temperature, flicker perception, energy efficiency, lighting control

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.