Abstract
Maddelerin cinsinin tayin edilmesi, mevcut maddeye karışan kimyasalların ve partiküllerin tespiti insan sağlığı açısından önemlidir. Tespitler hastalanan insanların şikâyeti sonrasında ya da periyodik aralıklarla yapılan denetimler ile anlaşılabilmektedir. Bunun nedeni bu tür sistemlerin teknik kişilerce değerlendirilmesinin gerekmesinden ve günlük değerlendirilebilecek numunelerin kısıtlı sayıda olmasından kaynaklanmaktadır. Makine öğrenmesi ile eğitilmiş olan sistemler bu değerlendirmeleri gerçek zamanlı sistemlere yakın sürelerde, yüksek doğrulukla gerçekleştirebilmektedir. Makine öğrenmesi kullanan sistemlerde kabul edilebilir ve kabul edilemez olan numuneler ile ağ yapısı eğitilerek oluşabilecek numunedeki farklılıklar otonom olarak sınıflandırılarak değerlendirilebilmektedir. Böylece uzman kişilerin ufak değişimleri gözden kaçırma ihtimali azalırken, daha fazla sayıda numune değerlendirilebilmektedir. Optik sistemler ile yapılan tespitler hem partikül incelemesi açısından hem de çözünmüş madde açısından incelemeye olanak sağlamaktadır. Ayrıca tahribatsız inceleme yapısı ile şeffaf tüp, şeffaf boru, spektrofotometre küveti gibi alternatif ortamlarda ölçümler alınabilmekte, bu da esnek kullanım imkânı sunmaktadır. Yaptığımız çalışmalarda sütün kompleks yapısındaki farklılıklar ve su içerisindeki mikroplastiklerin optik sistemler kullanarak sınıflandırması yapılmıştır. Yapılan deneylerin sınıflandırılmasında yapay sinir ağlarından ve derin öğrenme algoritmalarından faydalanılmıştır. Bu algoritmaların madde tayini açısından yüksek doğruluk gösterdiği görülmüştür.
Supporting Institution
Erciyes Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi
Project Number
FDK-2020-9708
Thanks
Çalışmalarımıza sağladığı fon desteği için Erciyes Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi'ne teşekkür ederiz (Proje No: FDK-2020-9708).
References
- Asheri Arnon, T., Ezra, S., & Fishbain, B. (2019). Water characterization and early contamination detection in highly varying stochastic background water, based on Machine Learning methodology for processing real-time UV-Spectrophotometry. Water Research, 155, 333–342. https://doi.org/10.1016/j.watres.2019.02.027
- Bajaj, N. S., Patange, A. D., Jegadeeshwaran, R., Pardeshi, S. S., Kulkarni, K. A., & Ghatpande, R. S. (2023). Application of metaheuristic optimization based support vector machine for milling cutter health monitoring. Intelligent Systems with Applications, 18(February), 200196. https://doi.org/10.1016/j.iswa.2023.200196
- Bridgeman, J., Baker, A., Brown, D., & Boxall, J. B. (2015). Portable LED fluorescence instrumentation for the rapid assessment of potable water quality. Science of the Total Environment. https://doi.org/10.1016/j.scitotenv.2015.04.050
- Dubreuil, M., Delrot, P., Leonard, I., Alfalou, A., Brosseau, C., & Dogariu, A. (2013). Exploring underwater target detection by imaging polarimetry and correlation techniques. Applied Optics. https://doi.org/10.1364/AO.52.000997
- Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., & Chouvarda, I. (2017). Machine Learning and Data Mining Methods in Diabetes Research. Computational and Structural Biotechnology Journal, 15, 104–116. https://doi.org/10.1016/j.csbj.2016.12.005
- Lyu, Y., Chen, J., & Song, Z. (2019). Image-based process monitoring using deep learning framework. In Chemometrics and Intelligent Laboratory Systems (Vol. 189). Elsevier B.V. https://doi.org/10.1016/j.chemolab.2019.03.008
- Mhaskar, H. N., Pereverzyev, S. V., & van der Walt, M. D. (2017). A Deep Learning Approach to Diabetic Blood Glucose Prediction. Frontiers in Applied Mathematics and Statistics, 3(July), 1–11. https://doi.org/10.3389/fams.2017.00014
- Piederrière, Y., Boulvert, F., Cariou, J., Le Jeune, B., Guern, Y., & Le Brun, G. (2005). Backscattered speckle size as a function of polarization: influence of particle-size and- concentration. Optics Express, 13(13), 5030. https://doi.org/10.1364/opex.13.005030
- Potansiyeli Görmek - Google. (n.d.). Retrieved July 24, 2023, from https://about.google/intl/tr_zz/stories/seeingpotential/
- Sayato, Y. (1989). WHO Guidelines for Drinking-Water Quality. Eisei Kagaku, 35(5), 307–312. https://doi.org/10.1248/jhs1956.35.307
- Skadsen, J., Janke, R., Grayman, W., Samuels, W., Tenbroek, M., Steglitz, B., & Bahl, S. (2008). Distribution system on-line monitoring for detecting contamination and water quality changes. Journal / American Water Works Association, 100(7), 81–94. https://doi.org/10.1002/j.1551-8833.2008.tb09678.x
- Wang, H., Hu, H., Jiang, J., Li, J., Li, X., Zhang, W., Cheng, Z., & Liu, T. (2021). Polarization differential imaging in turbid water via Mueller matrix and illumination modulation. Optics Communications, 499(June), 127274. https://doi.org/10.1016/j.optcom.2021.127274
- Yacouby, R., & Axman, D. (2020). Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models. https://doi.org/10.18653/v1/2020.eval4nlp-1.9
- Zulkifli, S. N., Rahim, H. A., & Lau, W. J. (2018). Detection of contaminants in water supply: A review on state-of-the-art monitoring technologies and their applications. Sensors and Actuators, B: Chemical, 255, 2657–2689. https://doi.org/10.1016/j.snb.2017.09.078
Abstract
Detection of the types of substances, chemicals, and particles present in a given substance is crucial for human health. The detections can only be made after the complaints of affected individuals or through periodic inspections. The reason for this is the need for evaluation by technical experts and the limited number of samples that can be assessed daily. Systems trained with machine learning can perform these evaluations with high accuracy and in near real-time, similar to real-time systems. By training the network with acceptable and unacceptable samples, machine learning-based systems can autonomously classify and evaluate differences in potential samples. As a result, the possibility of experts overlooking minor changes decreases, and a greater number of samples can be evaluated. Detection using optical systems allows examination of both particles and dissolved substances. Furthermore, its non-destructive nature enables measurements in alternative environments such as transparent tubes, transparent pipes, and spectrophotometer cuvettes, offering flexible usability options. In our research, we classified the differences in the complex structure of milk and microparticles in water using optical systems. Artificial neural networks and deep learning algorithms were utilized for the classification of these experiments. It was observed that these algorithms demonstrated high accuracy in substance recognition.
Project Number
FDK-2020-9708
References
- Asheri Arnon, T., Ezra, S., & Fishbain, B. (2019). Water characterization and early contamination detection in highly varying stochastic background water, based on Machine Learning methodology for processing real-time UV-Spectrophotometry. Water Research, 155, 333–342. https://doi.org/10.1016/j.watres.2019.02.027
- Bajaj, N. S., Patange, A. D., Jegadeeshwaran, R., Pardeshi, S. S., Kulkarni, K. A., & Ghatpande, R. S. (2023). Application of metaheuristic optimization based support vector machine for milling cutter health monitoring. Intelligent Systems with Applications, 18(February), 200196. https://doi.org/10.1016/j.iswa.2023.200196
- Bridgeman, J., Baker, A., Brown, D., & Boxall, J. B. (2015). Portable LED fluorescence instrumentation for the rapid assessment of potable water quality. Science of the Total Environment. https://doi.org/10.1016/j.scitotenv.2015.04.050
- Dubreuil, M., Delrot, P., Leonard, I., Alfalou, A., Brosseau, C., & Dogariu, A. (2013). Exploring underwater target detection by imaging polarimetry and correlation techniques. Applied Optics. https://doi.org/10.1364/AO.52.000997
- Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., & Chouvarda, I. (2017). Machine Learning and Data Mining Methods in Diabetes Research. Computational and Structural Biotechnology Journal, 15, 104–116. https://doi.org/10.1016/j.csbj.2016.12.005
- Lyu, Y., Chen, J., & Song, Z. (2019). Image-based process monitoring using deep learning framework. In Chemometrics and Intelligent Laboratory Systems (Vol. 189). Elsevier B.V. https://doi.org/10.1016/j.chemolab.2019.03.008
- Mhaskar, H. N., Pereverzyev, S. V., & van der Walt, M. D. (2017). A Deep Learning Approach to Diabetic Blood Glucose Prediction. Frontiers in Applied Mathematics and Statistics, 3(July), 1–11. https://doi.org/10.3389/fams.2017.00014
- Piederrière, Y., Boulvert, F., Cariou, J., Le Jeune, B., Guern, Y., & Le Brun, G. (2005). Backscattered speckle size as a function of polarization: influence of particle-size and- concentration. Optics Express, 13(13), 5030. https://doi.org/10.1364/opex.13.005030
- Potansiyeli Görmek - Google. (n.d.). Retrieved July 24, 2023, from https://about.google/intl/tr_zz/stories/seeingpotential/
- Sayato, Y. (1989). WHO Guidelines for Drinking-Water Quality. Eisei Kagaku, 35(5), 307–312. https://doi.org/10.1248/jhs1956.35.307
- Skadsen, J., Janke, R., Grayman, W., Samuels, W., Tenbroek, M., Steglitz, B., & Bahl, S. (2008). Distribution system on-line monitoring for detecting contamination and water quality changes. Journal / American Water Works Association, 100(7), 81–94. https://doi.org/10.1002/j.1551-8833.2008.tb09678.x
- Wang, H., Hu, H., Jiang, J., Li, J., Li, X., Zhang, W., Cheng, Z., & Liu, T. (2021). Polarization differential imaging in turbid water via Mueller matrix and illumination modulation. Optics Communications, 499(June), 127274. https://doi.org/10.1016/j.optcom.2021.127274
- Yacouby, R., & Axman, D. (2020). Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models. https://doi.org/10.18653/v1/2020.eval4nlp-1.9
- Zulkifli, S. N., Rahim, H. A., & Lau, W. J. (2018). Detection of contaminants in water supply: A review on state-of-the-art monitoring technologies and their applications. Sensors and Actuators, B: Chemical, 255, 2657–2689. https://doi.org/10.1016/j.snb.2017.09.078
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Deep Learning, Neural Networks, Stream and Sensor Data |
| Journal Section | PAPERS |
| Authors | |
| Project Number | FDK-2020-9708 |
| Publication Date | October 18, 2023 |
| Submission Date | August 21, 2023 |
| Acceptance Date | August 26, 2023 |
| Published in Issue | Year 2023 Volume: IDAP-2023 : International Artificial Intelligence and Data Processing Symposium Issue: IDAP-2023 |
The Creative Commons Attribution 4.0 International License
is applied to all research papers published by JCS and
A Digital Object Identifier (DOI) 
is assigned for each published paper.