Machine Learning Techniques for THz Imaging and Time-Domain Spectroscopy

Terahertz imaging and time-domain spectroscopy have been widely used to characterize the properties of test samples in various biomedical and engineering fields. Many of these tasks require the analysis of acquired terahertz signals to extract embedded information, which can be achieved using machine learning. Recently, machine learning techniques have developed rapidly, and many new learning models and learning algorithms have been investigated. Therefore, combined with state-of-the-art machine learning techniques, terahertz applications can be performed with high performance that cannot be achieved using modeling techniques that precede the machine learning era. In this review, we introduce the concept of machine learning and basic machine learning techniques and examine the methods for performance evaluation. We then summarize representative examples of terahertz imaging and time-domain spectroscopy that are conducted using machine learning.

[1]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[2]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Nathalie Dupuy,et al.  Automated principal component-based orthogonal signal correction applied to fused near infrared-mid-infrared spectra of French olive oils. , 2009, Analytical chemistry.

[4]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[5]  Woo-Jin Jang,et al.  Extraction of acoustic features based on auditory spike code and its application to music genre classification , 2019, IET Signal Process..

[6]  Sergey Levine,et al.  Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders , 2015, ArXiv.

[7]  Stuart E. Dreyfus,et al.  Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure , 1990 .

[8]  Jian Zuo,et al.  Label-free detection and characterization of the binding of hemagglutinin protein and broadly neutralizing monoclonal antibodies using terahertz spectroscopy , 2015, Journal of biomedical optics.

[9]  Jianquan Yao,et al.  Automatic evaluation of traumatic brain injury based on terahertz imaging with machine learning. , 2018, Optics express.

[10]  Joo-Hiuk Son,et al.  Potential clinical applications of terahertz radiation , 2019, Journal of Applied Physics.

[11]  Benyamin Ghojogh,et al.  The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial , 2019, ArXiv.

[12]  Dibo Hou,et al.  Analysis and inspection techniques for mouse liver injury based on terahertz spectroscopy. , 2019, Optics express.

[13]  Weizheng Wang,et al.  Development of convolutional neural network and its application in image classification: a survey , 2019, Optical Engineering.

[14]  Peter de B. Harrington,et al.  Statistical validation of classification and calibration models using bootstrapped latin partitions , 2006 .

[15]  John H. L. Hansen,et al.  Speaker Recognition by Machines and Humans: A tutorial review , 2015, IEEE Signal Processing Magazine.

[16]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[17]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[18]  Daniel M Mittleman,et al.  Twenty years of terahertz imaging [Invited]. , 2018, Optics express.

[19]  Kimin Lee,et al.  Using Pre-Training Can Improve Model Robustness and Uncertainty , 2019, ICML.

[20]  V. A. Anfert’ev,et al.  Diagnosis of Diabetes Based on Analysis of Exhaled Air by Terahertz Spectroscopy and Machine Learning , 2020, Optics and Spectroscopy.

[21]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[22]  Robert L. Ewing,et al.  Terahertz spectroscopic material identification using approximate entropy and deep neural network , 2017, 2017 IEEE National Aerospace and Electronics Conference (NAECON).

[23]  Joo-Hiuk Son,et al.  Terahertz spectroscopic imaging of a rabbit VX2 hepatoma model , 2011 .

[24]  I. Daubechies Orthonormal bases of compactly supported wavelets , 1988 .

[25]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[26]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[27]  Paul A. Viola,et al.  Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade , 2001, NIPS.

[28]  H. Abdi,et al.  Principal component analysis , 2010 .

[29]  Degang Xu,et al.  Terahertz spectroscopic diagnosis of early blast-induced traumatic brain injury in rats. , 2020, Biomedical optics express.

[30]  Joo-Hiuk Son,et al.  Terahertz dynamic imaging of skin drug absorption. , 2012, Optics express.

[31]  Joo-Hiuk Son,et al.  Principle and applications of terahertz molecular imaging , 2013, Nanotechnology.

[32]  Yuhong Xiang,et al.  Terahertz time-domain spectroscopy combined with support vector machines and partial least squares-discriminant analysis applied for the diagnosis of cervical carcinoma , 2015 .

[33]  Joo-Hiuk Son,et al.  Terahertz electromagnetic interactions with biological matter and their applications , 2009 .

[34]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[35]  E. Castro-Camus,et al.  Terahertz meets sculptural and architectural art: Evaluation and conservation of stone objects with T-ray technology , 2015, Scientific reports.

[36]  Mikhail Khodzitsky,et al.  Terahertz time-domain spectroscopy for non-invasive assessment of water content in biological samples. , 2018, Biomedical optics express.

[37]  B. Ferguson,et al.  T-ray computed tomography. , 2002, Optics letters.

[38]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[39]  Kodo Kawase,et al.  Terahertz tag identifiable through shielding materials using machine learning. , 2020, Optics express.

[40]  Rui Zhang,et al.  Automatic recognition of breast invasive ductal carcinoma based on terahertz spectroscopy with wavelet packet transform and machine learning. , 2020, Biomedical optics express.

[41]  Iwao Hosako,et al.  State-of-the-Art Database of Terahertz Spectroscopy Based on Modern Web Technology , 2014, IEEE Transactions on Terahertz Science and Technology.

[42]  Joo-Hiuk Son,et al.  Terahertz imaging of excised oral cancer at frozen temperature. , 2013, Biomedical optics express.

[43]  Vili Podgorelec,et al.  Decision trees , 2018, Encyclopedia of Database Systems.

[44]  B. Fischer,et al.  Far-infrared vibrational modes of DNA components studied by terahertz time-domain spectroscopy , 2002, Physics in medicine and biology.

[45]  Leo Breiman,et al.  Pasting Small Votes for Classification in Large Databases and On-Line , 1999, Machine Learning.

[46]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[49]  Quan Wang,et al.  Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models , 2012, ArXiv.

[50]  Seiji Yamamoto,et al.  Brain tumor imaging of rat fresh tissue using terahertz spectroscopy , 2016, Scientific Reports.

[51]  Jon Atli Benediktsson,et al.  Deep Learning for Hyperspectral Image Classification: An Overview , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[52]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[53]  Yan Peng,et al.  Qualitative and Quantitative Identification of Components in Mixture by Terahertz Spectroscopy , 2018, IEEE Transactions on Terahertz Science and Technology.

[54]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[55]  Joo-Hiuk Son,et al.  Detection and manipulation of methylation in blood cancer DNA using terahertz radiation , 2019, Scientific Reports.

[56]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[57]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[58]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[59]  Ronald L. Rivest,et al.  Constructing Optimal Binary Decision Trees is NP-Complete , 1976, Inf. Process. Lett..

[60]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[61]  Joo-Hiuk Son,et al.  Toward Clinical Cancer Imaging Using Terahertz Spectroscopy , 2017, IEEE Journal of Selected Topics in Quantum Electronics.

[62]  Jean Ponce,et al.  A Theoretical Analysis of Feature Pooling in Visual Recognition , 2010, ICML.

[63]  Andrew L. Maas Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[64]  Joo-Hiuk Son,et al.  Terahertz imaging of metastatic lymph nodes using spectroscopic integration technique. , 2017, Biomedical optics express.

[65]  Gavin Brown,et al.  Ensemble Learning , 2010, Encyclopedia of Machine Learning and Data Mining.

[66]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[67]  Michel Menu,et al.  Terahertz time-domain imaging of hidden defects in wooden artworks: application to a Russian icon painting. , 2014, Applied optics.

[68]  Tzu-Tsung Wong,et al.  Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation , 2015, Pattern Recognit..

[69]  Q. Abbasi,et al.  Characterization and Water Content Estimation Method of Living Plant Leaves Using Terahertz Waves , 2019, Applied Sciences.

[70]  Yann LeCun,et al.  Measuring the VC-Dimension of a Learning Machine , 1994, Neural Computation.

[71]  Carlo Luschi,et al.  Revisiting Small Batch Training for Deep Neural Networks , 2018, ArXiv.

[72]  Zhaohui Zhang,et al.  Terahertz spectroscopy and machine learning algorithm for non-destructive evaluation of protein conformation , 2020, Optical and Quantum Electronics.

[73]  Andreas Geiger,et al.  Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art , 2017, Found. Trends Comput. Graph. Vis..

[74]  Fakhri Karray,et al.  Survey on speech emotion recognition: Features, classification schemes, and databases , 2011, Pattern Recognit..

[75]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[76]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[77]  Yande Liu,et al.  Terahertz Spectroscopy Determination of Benzoic Acid Additive in Wheat Flour by Machine Learning , 2019, Journal of Infrared, Millimeter, and Terahertz Waves.

[78]  Henry J. Kelley,et al.  Gradient Theory of Optimal Flight Paths , 1960 .

[79]  Dong-Gyu Lee,et al.  Adaptive Compressed Sensing for the Fast Terahertz Reflection Tomography , 2013, IEEE Transactions on Terahertz Science and Technology.

[80]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[81]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[83]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[84]  Emma Pickwell-MacPherson,et al.  Investigating antibody interactions with a polar liquid using terahertz pulsed spectroscopy. , 2011, Biophysical journal.

[85]  Joo-Hiuk Son,et al.  Convergence of Terahertz Sciences in Biomedical Systems , 2012 .

[86]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[87]  J. Son,et al.  Determining terahertz resonant peaks of biomolecules in aqueous environment. , 2020, Optics express.

[88]  Zexuan Zhu,et al.  Quantitative characterization of bovine serum albumin thin-films using terahertz spectroscopy and machine learning methods. , 2018, Biomedical optics express.

[89]  Joo-Hiuk Son,et al.  Terahertz Tomographic Imaging of Transdermal Drug Delivery , 2012, IEEE Transactions on Terahertz Science and Technology.

[90]  G. Freymann,et al.  Highly accurate thickness measurement of multi-layered automotive paints using terahertz technology , 2016 .

[91]  M. Narasimha Murty,et al.  Genetic K-means algorithm , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[92]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[93]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[94]  Samy Bengio,et al.  A Parallel Mixture of SVMs for Very Large Scale Problems , 2001, Neural Computation.

[95]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[96]  Christopher M. Bishop,et al.  Regularization and complexity control in feed-forward networks , 1995 .

[97]  Ke Yang,et al.  Biomedical Applications of Terahertz Spectroscopy and Imaging. , 2016, Trends in biotechnology.

[98]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[99]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[100]  Joo-Hiuk Son,et al.  Nanoparticle-enabled terahertz imaging for cancer diagnosis. , 2009, Optics express.

[101]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[102]  C. Ahn,et al.  Stiffness measurement using terahertz and acoustic waves for biological samples. , 2015, Optics express.

[103]  Joo-Hiuk Son,et al.  Terahertz molecular resonance of cancer DNA , 2016, Scientific Reports.

[104]  Joo-Hiuk Son,et al.  Terahertz Biomedical Science and Technology , 2014 .

[105]  Stefano Squartini,et al.  Polyphonic Sound Event Detection by Using Capsule Neural Networks , 2018, IEEE Journal of Selected Topics in Signal Processing.

[106]  Joo-Hiuk Son,et al.  Transformation of terahertz vibrational modes of cytosine under hydration , 2020, Scientific Reports.

[107]  Qi Wu,et al.  Medical image classification using synergic deep learning , 2019, Medical Image Anal..

[108]  Kun She,et al.  Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication , 2018, Entropy.

[109]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[110]  Joo-Hiuk Son,et al.  A Fast Spatial-domain Terahertz Imaging Using Block-based Compressed Sensing , 2011 .

[111]  Geoffrey E. Hinton,et al.  Unsupervised learning : foundations of neural computation , 1999 .

[112]  Yang-Hui He,et al.  Machine-Learning the Landscape , 2021, The Calabi–Yau Landscape.

[113]  Gerhard Nahler,et al.  Pearson Correlation Coefficient , 2020, Definitions.

[114]  Joo-Hiuk Son,et al.  Effective demethylation of melanoma cells using terahertz radiation. , 2019, Biomedical optics express.

[115]  Synho Do,et al.  How much data is needed to train a medical image deep learning system to achieve necessary high accuracy , 2015, 1511.06348.

[116]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[117]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[118]  S M Pincus,et al.  Approximate entropy as a measure of system complexity. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[119]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[120]  Chan-Sik Park,et al.  Temperature-Dependent Terahertz Imaging of Excised Oral Malignant Melanoma , 2013, IEEE Journal of Biomedical and Health Informatics.

[121]  Joo-Hiuk Son,et al.  Molecular imaging with terahertz waves , 2010, 35th International Conference on Infrared, Millimeter, and Terahertz Waves.

[122]  G. Zhang,et al.  Qualitative and quantitative detection of liver injury with terahertz time-domain spectroscopy. , 2020, Biomedical optics express.

[123]  Gabriel Kreiman,et al.  Unsupervised Learning of Visual Structure using Predictive Generative Networks , 2015, ArXiv.

[124]  Khaled Shaalan,et al.  Speech Recognition Using Deep Neural Networks: A Systematic Review , 2019, IEEE Access.

[125]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[126]  Wei Liu,et al.  Rapid determination of aflatoxin B1 concentration in soybean oil using terahertz spectroscopy with chemometric methods. , 2019, Food chemistry.

[127]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[128]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[129]  Michael Mitzenmacher,et al.  Detecting Novel Associations in Large Data Sets , 2011, Science.

[130]  Joo-Hiuk Son,et al.  Fast terahertz reflection tomography using block-based compressed sensing. , 2011, Optics express.