**4. Conclusions**

This paper has presented a simple alternative for estimating the PM2.5 concentration in which a series of image processing schemes and simple linear regression are employed. The proposed method uses images with a high and low PM2.5 concentration to obtain the difference between these images. The difference is used to find the RoI. Two main stages are involved in this approach. The first stage includes a series of image processing schemes, which are used to automatically select the final RoI, from which only a single feature is extracted and used in a simple linear regression model. The second stage is employed to find a simple linear regression model with the single feature, by applying the final RoI identified in the first stage. Then, PM2.5 concentration estimation is performed. Using an image data set and an open PM2.5 concentration data set, experiments were conducted to verify the proposed approach. The results indicated that the proposed approach with the automatically selected RoI achieved the best performance, with *R*<sup>2</sup> = 0.73. Although the proposed method is not as direct as chemical schemes used to analyze the composition of air, the aim of this paper has been fulfilled,

i.e., to provide a simple alternative approach for PM2.5 concentration estimation with an acceptable performance. The proposed approach is not expected to replace component analysis using physical or chemical techniques. However, we hope that the proposed method can provide a cheaper and easier way to conduct PM2.5 estimation with an acceptable performance more efficiently. To achieve this, further work will be conducted and can be summarized as follows:


**Author Contributions:** Conceptualization, J.-J.L. and C.-H.H.; Formal analysis, J.-J.L. and C.-H.H.; Investigation, J.-J.L.; Methodology, J.-J.L.; Resources, Y.-F.H. and C.-H.L.; Software, D.-C.L.; Supervision, J.-J.L.; Visualization, D.-C.L.; Writing—original draft, J.-J.L. and D.-C.L.; Writing—review and editing, Y.-F.H. and C.-H.H. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research is partially sponsored by Chaoyang University of Technology (CYUT) and Higher Education Sprout Project, Ministry of Education (MOE), Taiwan, under the project titled "The R&D and the cultivation of talent for health-enhancement products."

**Conflicts of Interest:** The authors declare no conflict of interest.
