Study on the Ion Mobility Spectrometry Data Classification and Application of Port Container Narcotics Using Machine Learning Algorithm
Source abstract
Abstract
Narcotics should be strictly controlled as they can cause great disruption to society. Narcotics mostly flow into ports from major narcotic makers via transit points and through cargo containers. To prevent narcotic entry through smuggling, airports use animals or detect narcotics through X-rays. However, the use of animals in ports is not practical, and the method using X-rays sometimes does not detect substance narcotics with low atomic numbers. In this paper, we aimed to detect and classify narcotics using ion mobility spectrometry (IMS) data generated by inhaling air inside the container. To classify narcotic IMS data consisting of time-series data, the performance was improved using a time-series classification machine learning algorithm instead of the threshold method previously used. To this end, K-nearest neighbor, time-series forest, and random convolutional kernel algorithms were applied to the proposed algorithm considering the features of narcotic IMS data. The results demonstrate that the proposed algorithm outperforms the existing algorithm, and it reduces the classification performance processing time up to 5 s with more than 0.9 accuracy level.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Chemical Sensor Technologies · Metabolomics and Mass Spectrometry Studies · Isotope Analysis in Ecology
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information and Communication Engineering, Hoseo University, Asan 31499, Republic of Korea
Korea Electronics Technology Institute, Seongnam 12767, Republic of Korea
Funding
Ministry of Oceans and Fisheries · Ministry of Science and ICT
References (36)
Show source-provided references
1. Korea Prosecution Service (2022). White Paper on Narcotic Crimes Chapter 3, Korea Prosecution Service.
2. Moser, A.Y., Bizo, L., and Brown, W.Y. (2019). Olfactory generalization in detector dogs. Animals, 9.10.3390/ani9090702 ↗
3. Li, W., Chen, J., Wu, X., and Wang, W. (2017, January 8–11). The automatic detection of hiding narcotics in human bodies based on fractal dimension and SVM classification. Proceedings of the 2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA), Beijing, China.
4. Using spatial diversity to detect narcotics and explosives using NQR signals10.1109/TSP.2007.896287 ↗
5. Goubran, R.A., and Lawrence, A.H. (1997, January 19–21). DSP techniques for narcotic detection using ion mobility spectrometry. Proceedings of the IEEE Instrumentation and Measurement Technology Conference Sensing, Processing, Networking, IMTC Proceedings, Ottawa, ON, Canada.
6. A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data10.1016/j.envsoft.2019.104502 ↗
7. Braei, M., and Wagner, S. (2020). Anomaly detection in univariate time-series: A survey on the state-of-the-art. arXiv.
8. Yao, H., Xue, T., Wang, D., Qi, Y., and Su, M. (2021, January 26–28). Development direction of automated terminal and systematic planning of smart port. Proceedings of the 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang, China.10.1109/ICBAIE52039.2021.9389884 ↗
9. Towards smart port infrastructures: Enhancing port activities using information and communications technology10.1109/ACCESS.2020.2990961 ↗
10. Heikkilä, M., Saarni, J., and Saurama, A. (2022). Innovation in smart ports: Future directions of digitalization in container ports. J. Mar. Sci. Eng., 10.10.3390/jmse10121925 ↗
11. Darban, Z.Z., Webb, G.I., Pan, S., Aggarwal, C.C., and Salehi, M. (2022). Deep learning for time series anomaly detection: A survey. arXiv.
12. Noise reduction in chaotic time-series data: A survey of common methods10.1103/PhysRevE.48.1752 ↗
13. Nikos, M., and Stavros, D.N. (2001). Information Processing and Technology, Nova Science Publishers, Inc.
14. Liu, U., Zhang, Y., Cao, Y., Zhu, Y., Zaidi, N., Ranaweera, C., Li, G., and Zhu, Q. (2023, January 16–18). Kernel-based feature extraction for time series clustering. Knowledge science, engineering and management. Proceedings of the 16th International Conference, KSEM 2023, Guangzhou, China.10.1007/978-3-031-40283-8_24 ↗
15. Nearest neighbor pattern classification10.1109/TIT.1967.1053964 ↗
16. Grochowalski, J.M., and Chady, T. (2023). Rapid identification of material defects based on pulsed multifrequency eddy current testing and the k-nearest neighbor method. Materials, 16.10.3390/ma16206650 ↗
17. Chiappa, V., Bogani, G., Interlenghi, M., Vittori Antisari, G., Salvatore, C., Zanchi, L., Ludovisi, M., Leone Roberti Maggiore, U., Calareso, G., and Haeusler, E. (2023). Using radiomics and machine learning applied to MRI to predict response to neoadjuvant chemotherapy in locally advanced cervical cancer. Diagnostics, 13.10.3390/diagnostics13193139 ↗
18. Random forests10.1023/A:1010933404324 ↗
19. A time series forest for classification and feature extraction10.1016/j.ins.2013.02.030 ↗
20. ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels10.1007/s10618-020-00701-z ↗
21. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
22. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4–9). Attention is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, Red Hook, NY, USA.
23. Liang, Z., Powell, A., Ersoy, I., Poostchi, M., Silamut, K., Palaniappan, K., Guo, P., Hossain, M.A., Sameer, A., and Maude, R.J. (2016, January 15–18). Cnn-based image analysis for malaria diagnosis. Proceedings of the 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Shenzhen, China.10.1109/BIBM.2016.7822567 ↗
24. Wang, Z., and Oates, T. (2015, January 25–30). Encoding time series as images for visual inspection and classification using tiled convolutional neural networks. Proceedings of the Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, USA.
25. Recurrence plots of dynamical systems10.1209/0295-5075/4/9/004 ↗
26. Chen, T., Sampath, V., May, M.C., Shan, S., Jorg, O.J., Aguilar Martín, J.J., Stamer, F., Fantoni, G., Tosello, G., and Calaon, M. (2023). Machine learning in manufacturing towards industry 4.0: From ‘for now’ to ‘four-know’. Appl. Sci., 13.10.3390/app13031903 ↗
27. A Data-model Interactive Remaining Useful Life Prediction Approach of Lithium-ion Batteries Based on PF-BiGRU-TSAM
28. Jafari, S., and Byun, Y.-C. (2023). A CNN-GRU Approach to the Accurate Prediction of Batteries’ Remaining Useful Life from Charging Profiles. Computers, 12.10.3390/computers12110219 ↗
29. Adaptive window-based detection of narcotics and explosives using IMS signals in cargo containers
30. Time series data cleaning: A survey10.1109/ACCESS.2019.2962152 ↗
31. Song, S., Zhang, A., Wang, J., and Yu, P.S. (June, January 31). SCREEN: Stream data cleaning under speed constraints. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Australia.10.1145/2723372.2723730 ↗
32. Berndt, D.J., and Clifford, J. (2019, January 4–8). Using dynamic time warping to find patterns in time series. Proceedings of the KDD Workshop, Anchorage, AK, USA.
33. Batista, G., and Silva, D.F. (2009, January 24–28). How k-nearest neighbor parameters affect its performance. Proceedings of the Argentine Symposium on Artificial Intelligence (ASAI), Mar del Plata, Argentina.
34. pyts: A python package for time series classification
35. Löning, M., Bagnall, A., Ganesh, S., Kazakov, V., Lines, J., and Király, F.J. (2019). sktime: A unified interface for machine learning with timeseries. arXiv.
36. Tai, C.-Y., Wang, W.-J., and Huang, Y.-M. (2023). Using Time-Series Generative Adversarial Networks to Synthesize Sensing Data for Pest Incidence Forecasting on Sustainable Agriculture. Sustainability, 15.10.3390/su15107834 ↗