Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction
With the development of e-commerce, noninvasive mail inspection is becoming particularly prominent. Terahertz waves have fingerprint spectrum characteristics and can penetrate nonpolar materials. Terahertz waves are ideal for the nondestructive identification of harmful substances hidden in the mail...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | International Journal of Optics |
| Online Access: | http://dx.doi.org/10.1155/ijo/5636677 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850280572258091008 |
|---|---|
| author | Tao Li Yungao Gu Chao Wang Yiyang Yao Ying Zhang Yajie Guo Dayong Gu |
| author_facet | Tao Li Yungao Gu Chao Wang Yiyang Yao Ying Zhang Yajie Guo Dayong Gu |
| author_sort | Tao Li |
| collection | DOAJ |
| description | With the development of e-commerce, noninvasive mail inspection is becoming particularly prominent. Terahertz waves have fingerprint spectrum characteristics and can penetrate nonpolar materials. Terahertz waves are ideal for the nondestructive identification of harmful substances hidden in the mail. However, the gaps between mail packages and samples affect the accuracy of the inspection. In this study, the influence of irregular gaps was analyzed using a model sample under envelope occlusion. A spectral reconstruction method based on Voigt and asymmetric least squares (AsLS) fitting is proposed. Principal component analysis (PCA) results showed that the reconstructed spectral data were easier to identify and the root mean square error (RMSE) of quantitative analysis was the smallest. PCA–support vector machine (SVM) and convolutional neural network (CNN) classification models were used to verify the effectiveness of this method. |
| format | Article |
| id | doaj-art-b26a62a5ea9a4366b3ae6d94caf56fc3 |
| institution | OA Journals |
| issn | 1687-9392 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Optics |
| spelling | doaj-art-b26a62a5ea9a4366b3ae6d94caf56fc32025-08-20T01:48:41ZengWileyInternational Journal of Optics1687-93922025-01-01202510.1155/ijo/5636677Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral ReconstructionTao Li0Yungao Gu1Chao Wang2Yiyang Yao3Ying Zhang4Yajie Guo5Dayong Gu6School of SoftwareMechanical and Electrical CollegeSchool of SoftwareSchool of SoftwareSchool of SoftwareSchool of SoftwareDepartment of Laboratory MedicineWith the development of e-commerce, noninvasive mail inspection is becoming particularly prominent. Terahertz waves have fingerprint spectrum characteristics and can penetrate nonpolar materials. Terahertz waves are ideal for the nondestructive identification of harmful substances hidden in the mail. However, the gaps between mail packages and samples affect the accuracy of the inspection. In this study, the influence of irregular gaps was analyzed using a model sample under envelope occlusion. A spectral reconstruction method based on Voigt and asymmetric least squares (AsLS) fitting is proposed. Principal component analysis (PCA) results showed that the reconstructed spectral data were easier to identify and the root mean square error (RMSE) of quantitative analysis was the smallest. PCA–support vector machine (SVM) and convolutional neural network (CNN) classification models were used to verify the effectiveness of this method.http://dx.doi.org/10.1155/ijo/5636677 |
| spellingShingle | Tao Li Yungao Gu Chao Wang Yiyang Yao Ying Zhang Yajie Guo Dayong Gu Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction International Journal of Optics |
| title | Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction |
| title_full | Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction |
| title_fullStr | Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction |
| title_full_unstemmed | Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction |
| title_short | Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction |
| title_sort | identification of hazardous substances in mail by terahertz radiation based on voigt and asls fitting spectral reconstruction |
| url | http://dx.doi.org/10.1155/ijo/5636677 |
| work_keys_str_mv | AT taoli identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction AT yungaogu identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction AT chaowang identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction AT yiyangyao identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction AT yingzhang identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction AT yajieguo identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction AT dayonggu identificationofhazardoussubstancesinmailbyterahertzradiationbasedonvoigtandaslsfittingspectralreconstruction |