Multispectral Classification based on H20 and H20 with NaOH Using Image Segmentation and Ensemble Learning EfficientNetV2, Resnet50, MobileNetV3
Abstract
High Multispectral imaging has become a promising approach in liquid classification, particularly in distinguishing visually similar but subtly spectrally distinct solutions, such as pure water (H₂O) and water mixed with sodium hydroxide (H₂O with NaOH). This study proposed a classification system based on image segmentation and deep learning, utilizing three leading Convolutional Neural Network (CNN) architectures: ResNet 50, EfficientNetV2, and MobileNetV3. Before classification, each multispectral image was processed through color segmentation in HSV space to highlight the dominant spectral, especially in the hue range of 110 170. The model was trained using a data augmentation scheme and optimized with the Adam algorithm, a batch size of 32, and a sigmoid activation function. The dataset consists of 807 images, including 295 H₂O images and 512 H₂O with NaOH images, which were divided into training (64%), validation (16%), and testing (20%) data. Experimental results show that ResNet50 achieves the highest performance, with an accuracy of 93.83% and an F1 score of 93.67%, particularly in identifying alkaline pollution. EfficientNetV2 achieved the lowest loss (0.2001) and exhibited balanced performance across classes, while MobileNetV3, despite being a lightweight model, remained competitive with a recall of 0.97 in the H₂O with NaOH class. Further evaluation with Grad CAM reveals that all models focus on the most critical spectral areas of the segmentation results. These findings support the effectiveness of combining color-based segmentation and CNN in the spectral classification of liquids. This research is expected to serve as a stepping stone in the development of an efficient and accurate automatic liquid classification system for both laboratory and industrial applications.
Downloads
References
Egesa, AO, Davidson, M.T., Pérez, H.E., & Begcy, K. (2024). Biochemical And Physical Screening Using Optical Oxygen Sensing And Multispectral Imaging In Sea Oats Seeds. Agriculture,14(6),875.Https://Doi.Org/10.3390/Agriculture14060875
Yücel, N., Yildirim, M., & Aslan, S. (2023). Performances Of Pre Trained Models In Classification Of Body Cavity Fluid Cytology Images.Http://As Proceeding.Com/:Konya,Turkeyhttps://Www.Icaens.Com/
Cai, W., Li, M., Jin, G., Liu, Q., & Lu, C. (2024). Comparison Of Residual Network And Other Classical Models For Classification Of Interlayer Distresses In Pavement. Applied Sciences (Switzerland), 14(15).Https://Doi.Org/10.3390/App14156568
Kim, R., & Kim, A. (2024). Analysis Of Modern Computer Vision Models For Blood Cell Classification. Https://Doi.Org/10.48550/Arxiv.2407.00759
Riccardi Advisor, M., Marcon Co Advisor, M., & Ugo Leonzio, D. (2022). Multispectral Imaging For Solvent Classification Using NIR & Visible Spectra Laurea Magistrale In Mathematical Engineering Ingegneria Matematica. Https://Www.Politesi.Polimi.It/Retrieve/B07bbaff B44b 425d B21a 78ea9c8c86e9/Executive_Riccardi_Sensor_VIS_IR.Pdf
Melinda, S. T. A., Sudiana, D., Gunawan, D., & Iqbal, M. (2016). Implementation Of Segmentation Scheme Based On Wavelet Transform In Multi Spectral Fluctuation Patterns. Https://Jtec.Utem.Edu.My/Jtec/Article/View/1434
Melinda, M., Tamsir, A. S., Afifah, S., & Gunawan, D. (2018). Impedance Influence Analysis On Multi Spectral Capacitive Sensor. 2018 International Conference On Electrical Engineering And Informatics (Iceltics)(44501), 19 24. Https://Doi.Org/10.1109/ICELTICS.2018.8548794
LONG Jianing, Z. Z. L. X. L. Y. R. Z. Y. J. Z. M. F. P. H. Z. H. C. W. X. (2023). Wheat Lodging Types Detection Based On UAV Image Using Improved Efficientnetv2. Https://Doi.Org/10.12133/J.Smartag.SA202308010
Saeed, A., Shaukat, S., Shehzad, K., Ahmad, I., Eshmawi, A.A., Amin, A.H., & Tag Eldin, E. (2022). A Deep Learning Based Approach For The Diagnosis Of Acute Lymphoblastic Leukemia. Electronics (Switzerland), 11(19).Https://Doi.Org/10.3390/Electronics11193168
Bukhari, MT (2024). Efficacy Of Lightweight Vision Transformers In The Diagnosis Of Pneumonia.Https://Doi.Org/10.1101/2024.10.24.24316057
Badruzzaman, A., & Arymurthy, A. M. (2024). Sharealike 4.0 International License (CC BY SA 4.0). How To Cite: Ahmad Badruzzaman And Aniati Murni Arymurthy, A Comparative Study Of Convolutional Neural Network In Detecting Blast Cells For Diagnose A Comparative Study Of Convolutional Neural Network In Detecting Blast Cells For Diagnose Acute Myeloid Leukemia. Journal Of Electronics, Electromedical Engineering, And Medical Informatics, 6(1), 84 91.Https://Doi.Org/10.35882/Jeemi.V6i1.354
Chirikhina, E., Chirikhin, A., Dewsbury Ennis, S., Bianconi, F., & Xiao, P. (2021). Skin Characterization By Using Contact Capacitive Imaging And High Resolution Ultrasound Imaging With Machine Learning Algorithms. Applied Sciences (Switzerland), 11(18).Https://Doi.Org/10.3390/App11188714
Arefi, F., Mansourian, A. M., & Kasaei, S. (2024). Deep Spectral Improvement For Unsupervised Image Instance Segmentation. PLOS ONE, 19(10), E0307432. Https://Doi.Org/10.1371/Journal.Pone.0307432
Yarahmadi, P., Ahmadpour, E., Moradi, P., & Samadzadehaghdam, N. (2025). Automatic Classification Of Giardia Infection From Stool Microscopic Images Using Deep Neural Networks. Bioimpacts, 15.Https://Doi.Org/10.34172/Bi.30272
Rashki, M., & Faes, M. G. R. (2023). No Free Lunch Theorems For Reliability Analysis. ASCE ASME Journal Of Risk And Uncertainty In Engineering Systems, Part A: Civil Engineering, 9(3). Https://Doi.Org/10.1061/AJRUA6.RUENG 1015
Liang, X., Liang, J., Yin, T., & Tang, X. (2023). A Lightweight Method For Facial Expression Recognition Based On Improved Mobilenetv3. IET Image Processing, 17(8), 2375 2384.Https://Doi.Org/10.1049/Ipr2.12798
Lu, L., Qi, W., Bing, W., Shichao, F., Li, L., & Qingjie, L. (2021). Water Body Extraction From High Resolution Remote Sensing Images Based On Scaling Efficientnets. Journal Of Physics: Conference Series, 1894(1).Https://Doi.Org/10.1088/1742 6596/1894/1/012100
Vali, A., Comai, S., & Matteucci, M. (2020). Deep Learning For Land Use And Land Cover Classification Based On Hyperspectral And Multispectral Earth Observation Data: A Review. In Remote Sensing (Vol. 12, Issue 15). MDPI AG.Https://Doi.Org/10.3390/RS12152495
Wang, M., Liu, W., Gu, X., Cui, F., Ding, J., Zhu, Y., Bian, J., Chen, Y., & Zhou, J. (2024). Few Shot Learning To Identify Atypical Endometrial Hyperplasia And Endometrial Cancer Based On Transvaginal Ultrasonic Images. Heliyon, 10(16).Https://Doi.Org/10.1016/J.Heliyon.2024.E36426
Junidar, J., Melinda, M., Diannuari, DD, Acula, DD, & Zainal, Z. (2025). FACE AUTISTIC CLASSIFICATION BASED ON THERMAL USING IMAGE ENSEMBLE LEARNING OF VGG 19, RESNET50V2, AND EFFICIENTNET. Radioelectronics And Computer Systems, 2025(1(113)), 153 164.Https://Doi.Org/10.32620/Reks.2025.1.11
Melinda, M., Tanjung, A., Tamsir, A. S., Basari, B., & Gunawan, D. (2017). Grouped Data Analysis Of H₂O And H₂O Mixed With Naoh On Multi Spectral High Fluctuation Pattern. 2017 International Conference On Electrical Engineering And Informatics (Iceltics), 184 188. Https://Doi.Org/10.1109/ICELTICS.2017.8253266
Melinda, Tamsir, A. S., Basari, & Gunawan, D. (2016). Analysis Of Consistence Level Using New Method Of Statistical Transformation Approach In Multi Spectral Fluctuation Pattern. 2016 6th IEEE International Conference On Control System, Computing And Engineering (ICCSCE), 251 255. Https://Doi.Org/10.1109/ICCSCE.2016.7893580
Melinda, M., Yunidar, Y., Noufal, Z., Prasetyo, AB, & Irhamsyah, M. (2022). A Novel Subtraction Method For Signal Fluctuation. 2022 5th International Seminar On Research Of Information Technology And Intelligent Systems, ISRITI 2022, 700 705.Https://Doi.Org/10.1109/ISRITI56927.2022.10052936
Melinda, M., Tamsir, A. S., Basari, B., & Gunawan, D. (2017). Performance Of Consistency Parameters Analysis Using Fourier And Wavelet Transform On Multi Spectral Fluctuation Signal. 2017 International Conference On Electrical Engineering And Informatics (Iceltics), 7 11. Https://Doi.Org/10.1109/ICELTICS.2017.8253248
Zhang, S., Yuan, Y., Wang, Z., Wei, S., Zhang, X., Zhang, T., Song, X., Zou, Y., Wang, J., Chen, F., & Li, J. (2025). A Novel Deep Learning Model For Spectral Analysis: Lightweight Resnet CNN With Adaptive Feature Compression For Oil Spill Type Identification. Spectrochimica Acta Part A: Molecular And Biomolecular Spectroscopy, 329, 125626. Https://Doi.Org/10.1016/J.Saa.2024.125626
Jackson, A. (2021). Smart Buildings: Water Leakage Detection Using Tinyml Edificios Inteligentes: Detección De Fugas De Agua Utilizando Tinyml (Vol. 2, Issue 1). Https://Orcid.Org/0009 0000 3207 7238www.Infotechjournal.Org
Dong, S., Feng, W., Quan, Y., Dauphin, G., Gao, L., & Xing, M. (2022). Deep Ensemble CNN Method Based On Sample Expansion For Hyperspectral Image Classification. IEEE Transactions On Geoscience And Remote Sensing, 60. Https://Doi.Org/10.1109/TGRS.2022.3183189Analysis. Complexity, 2020.Https://Doi.Org/10.1155/2020/8361989
Li, J., He, Z., Li, D., & Zheng, A. (2022). Research On Water Seepage Detection Technology For Tunnel Asphalt Pavement Based On Deep Learning And Digital Image Processing. Scientific Reports, 12(1).Https://Doi.Org/10.1038/S41598 022 15828 W
Gupta, S., D., U., & Hebbar, R. (2022). Analysis and application of multispectral data for water segmentation using machine learning. http://arxiv.org/abs/2212.08749
Kirby, K., Ferguson, S., Rennie, C. D., Cousineau, J., & Nistor, I. (2024). Identification of the best method for detecting surface water in Sentinel-2 multispectral satellite imagery. Remote Sensing Applications: Society and Environment, 36. https://doi.org/10.1016/j.rsase.2024.101367
Alhichri, H. (2023). RS-DeepSuperLearner: fusion of CNN ensemble for remote sensing scene classification. Annals of GIS, 29(1), 121–142. https://doi.org/10.1080/19475683.2023.2165544
Anand, V., Oinam, B., & Wieprecht, S. (2024). Machine learning approach for water quality predictions based on multispectral satellite imageries. Ecological Informatics, 84. https://doi.org/10.1016/j.ecoinf.2024.102868
Yao, W., Lian, C., & Bruzzone, L. (2022). A CNN Ensemble Based on a Spectral Feature Refining Module for Hyperspectral Image Classification. Remote Sensing, 14(19). https://doi.org/10.3390/rs14194982
Müller, D., Soto-Rey, I., & Kramer, F. (n.d.). An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networks. https://doi.org/10.48550/arXiv.2201.11440
Souza, F. E. S. de, & Rodrigues, J. I. de J. (2023). Evaluation of Machine Learning Algorithms in the Classification of Multispectral Images from the Sentinel-2A/2B Orbital Sensor for Mapping the Environmental Dynamics of Ria Formosa (Algarve, Portugal). ISPRS International Journal of Geo-Information, 12(9). https://doi.org/10.3390/ijgi12090361
Copyright (c) 2025 Melinda Melinda, Yunidar Yunidar, Zulhelmi Zulhelmi, Arya Suyanda, Lailatul Qadri Zakaria, W.K Wong
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
