A Resource-Aware Framework for Intelligent JPEG Compression on Solar-Powered Edge Cameras for Environmental Monitoring IOT
DOI:
https://doi.org/10.31838/NJAP/08.01.18Keywords:
Adaptive Image Compression, WSN, IOT, Machine learning, Feature Extraction.Abstract
In wireless sensor networks, image data transmission is constrained by power, processing, and bandwidth limitations. Traditional compression methods, such as JPEG, do not adapt to varying network capacities or image complexity. The Intelligent Adaptive Compression Framework (IACF) utilizes machine learning at the edges of solar-powered cameras to optimize image transmission bitrates. This is achieved by relying on a feature vector composed of 19 descriptors and contextual parameters such as power level and network hop count. This approach demonstrates a predictive accuracy of 0.9845, indicating the effectiveness of contextually based compression. A simplified model with five features achieved an R² value of 0.9693, indicating reduced complexity without significant loss of resolution. The Intelligent Adaptive Compression Framework (IACF) offers an effective solution for improving visual data performance in resource-constrained environments.
References
1. K. M. Delphin Raj et al., Comput. Mater. Continua, doi: 10.32604/cmc.2022.021873 (2022).
2. H. Qiu et al., IEEE Trans. Ind. Inf. 17, 2124–2133 (2021).
3. D.-U. Lee et al., IEEE Trans. Image Process. 18, 2100–2113 (2009).
4. X. Zhang et al., Multimedia Tools Appl. 77, 13679–13699 (2018).
5. P. Morozkin, M. Swynghedauw, and M. Trocan, J. Inf. Telecommun. 3, 342–360 (2019).
6. P. Chakraborty, J. Cruz, and S. Bhunia, IEEE Internet Things J. 8, 7303–7315 (2020).
7. M. Nasri et al., Int. J. Speech Technol. 18, 205–216 (2015).
8. M. Nasri et al., Comput. Electr. Eng. 37, 798–810 (2011).
9. Z. Chen, Y. Hu, and Y. Zhang, IEEE Trans. Geosci. Remote Sens. 57, 4577–4590 (2019).
10. Z. Cheng et al., IEEE Trans. Multimedia 22, 860–873 (2019).
11. S. J. Mousavirad and L. A. Alexandre, Appl. Soft Comput. 141, 110278 (2023).
12. Merllin Ann George et al. "A Study on Various Image Feature Extraction Techniques." International Journal of Scientific Research in Computer Science, Engineering and Information Technology (2019). https://doi.org/10.32628/cseit1195528.
13. M. A. George et al., Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., doi: 10.32628/cseit1195528 (2019).
14. A. M. Khidhir and N. Y. Abdullah, Int. J. Res. Dev. Eng. 2, 22–32 (2013).
15. J. Yang, G. Zhu, and Y.-Q. Shi, IEEE Trans. Image Process. 25, 2647–2656 (2016).
16. F. Wang, W. Chen, and L. Qiu, Fractals 27, 1950060 (2019).
17. M. Li et al., IEEE Trans. Image Process. 29, 5900–5911 (2020).
18. C. Christierson and A. Green, “Applications of AI-based Methods in Live Stream Video Compression,” Master’s thesis, Lund University, 2025.
19. G. Ciocca, S. Corchs, and F. Gasparini, “Complexity perception of texture images,” in New Trends in Image Analysis and Processing--ICIAP 2015 Workshops (Springer International Publishing, Genoa, Italy, 2015), Proceedings 18.
20. B. Kumar et al., Int. J. Remote Sens. 41, 6248–6287 (2020).
21. H. Zhong and R. Wang, J. Neurosci. Methods 369, 109423 (2022).
22. J. Mohsin, F. H. Saleh, and A. M. A. Al-muqarm, “Real-time Surveillance System to detect and analyzers the Suspects of COVID-19 patients by using IoT under edge computing techniques,” in 2020 2nd Al-Noor International Conference for Science and Technology (NICST) (IEEE, 2020).
23. J. Mohsin and S. Albermany, “Proposing an IOT Secure Framework for Monitoring COVID-19 Patients,” in 2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT) (IEEE, 2023).
24. J. Mohsin, “Analyzing Wireless Network Implementation Using Cooja Simulation in Contiki Operating System,” in 6th International Scientific Conference for Creativity and Innovation, Alkut University College Journal (2025), pp. 1012–1025.
25. J. Mohsin and Z. H. Al-Shably, “Implementations of the Lenstra–Lenstra–Lovász algorithm in MATLAB,” in AIP Conference Proceedings 3219 (AIP Publishing LLC, 2024).
26. M.-C. Popescu et al., WSEAS Trans. Circuits Syst. 8, 579–588 (2009).
27. G. M. I. Alam et al., “Deep learning model based prediction of vehicle CO,” (Reference incomplete in original text).
28. A. Karuppasamy et al., Intell.-Based Med. 9, 100126 (2024).
29. A. Jadon, A. Patil, and S. Jadon, “A comprehensive survey of regression-based loss functions for time series forecasting,” in International Conference on Data Management, Analytics & Innovation (Springer Nature Singapore, Singapore, 2024).
30. J. Terven et al., Artif. Intell. Rev. 58, 195 (2025).
31. I. K. M. Jais, A. R. Ismail, and S. Q. Nisa, Knowl. Eng. Data Sci. 2, 41–46 (2019).
32. X. Li et al., “AIDER: Aerial Imagery Dataset for Emergency Response Applications,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2020).
33. Images.CV, “Weather Image Classification Dataset,” available at https://images.cv/dataset/weather-image-classification-dataset.
34. L. Perez and J. Wang, “The effectiveness of data augmentation in image classification using deep learning,” arXiv:1712.04621 (2017).
35. G. Chogovadze, R. Pautrat, and M. Pollefeys, “Controllable data augmentation through deep relighting,” arXiv:2110.13996 (2021).
