Journal Home > Volume 16 , Issue 7
Nano Research 2023, 16(7): 10139-10147 https://doi.org/10.1007/s12274-023-5494-4
Research Article | Issue | Published: 09 March 2023

A two-dimensional MoS2 array based on artificial neural network learning for high-quality imaging

Show Author's Information Long Chen1,  Siyuan Chen2,  Jinchao Wu1,  Luhua Chen1,  Shuai Yang1,  Jian Chu1,  Chengming Jiang1,  Sheng Bi1,  Jinhui Song1( )
School of Mechanical Engineering, Dalian University of Technology, Dalian 116024, China
School of Computer Science, Southwest Petroleum University, Chengdu 610500, China
Keywords:
artificial neural network, two-dimensional MoS2, sensing array, individual difference, imaging quality
Topics:
Photoelectric devices
Cite this article:
Chen L, Chen S, Wu J, et al. A two-dimensional MoS2 array based on artificial neural network learning for high-quality imaging. Nano Research, 2023, 16(7): 10139-10147. https://doi.org/10.1007/s12274-023-5494-4
Download citation
EndNote(RIS)
BibTeX

740

Views

96

Downloads

Citations

4

Crossref

4

WoS

4

Scopus

0

CSCD

Abstract Full text Electronic supplementary material About this article

As the basis of machine vision, the biomimetic image sensing devices are the eyes of artificial intelligence. In recent years, with the development of two-dimensional (2D) materials, many new optoelectronic devices are developed for their outstanding performance. However, there are still little sensing arrays based on 2D materials with high imaging quality, due to the poor uniformity of pixels caused by material defects and fabrication technique. Here, we propose a 2D MoS2 sensing array based on artificial neural network (ANN) learning. By equipping the MoS2 sensing array with a “brain” (ANN), the imaging quality can be effectively improved. In the test, the relative standard deviation (RSD) between pixels decreased from about 34.3% to 6.2% and 5.49% after adjustment by the back propagation (BP) and Elman neural networks, respectively. The peak signal to noise ratio (PSNR) and structural similarity (SSIM) of the image are improved by about 2.5 times, which realizes the re-recognition of the distorted image. This provides a feasible approach for the application of 2D sensing array by integrating ANN to achieve high quality imaging.


menu
Abstract
Full text
Outline
Electronic supplementary material
About this article

A two-dimensional MoS2 array based on artificial neural network learning for high-quality imaging

Show Author's information Long Chen1, Siyuan Chen2, Jinchao Wu1, Luhua Chen1, Shuai Yang1, Jian Chu1, Chengming Jiang1, Sheng Bi1, Jinhui Song1( )
School of Mechanical Engineering, Dalian University of Technology, Dalian 116024, China
School of Computer Science, Southwest Petroleum University, Chengdu 610500, China

Abstract

As the basis of machine vision, the biomimetic image sensing devices are the eyes of artificial intelligence. In recent years, with the development of two-dimensional (2D) materials, many new optoelectronic devices are developed for their outstanding performance. However, there are still little sensing arrays based on 2D materials with high imaging quality, due to the poor uniformity of pixels caused by material defects and fabrication technique. Here, we propose a 2D MoS2 sensing array based on artificial neural network (ANN) learning. By equipping the MoS2 sensing array with a “brain” (ANN), the imaging quality can be effectively improved. In the test, the relative standard deviation (RSD) between pixels decreased from about 34.3% to 6.2% and 5.49% after adjustment by the back propagation (BP) and Elman neural networks, respectively. The peak signal to noise ratio (PSNR) and structural similarity (SSIM) of the image are improved by about 2.5 times, which realizes the re-recognition of the distorted image. This provides a feasible approach for the application of 2D sensing array by integrating ANN to achieve high quality imaging.

Keywords: artificial neural network, two-dimensional MoS2, sensing array, individual difference, imaging quality

References(53)

[1]

Meng, J. L.; Wang, T. Y.; Zhu, H.; Ji, L.; Bao, W. Z.; Zhou, P.; Chen, L.; Sun, Q. Q.; Zhang, D. W. Integrated in-sensor computing optoelectronic device for environment-adaptable artificial retina perception application. Nano Lett. 2022, 22, 81–89.
DOI Google Scholar
[2]

Choi, C.; Leem, J.; Kim, M.; Taqieddin, A.; Cho, C.; Cho, K. W.; Lee, G. J.; Seung, H.; Bae, H. J.; Song, Y. M. et al. Curved neuromorphic image sensor array using a MoS2-organic heterostructure inspired by the human visual recognition system. Nat. Commun. 2020, 11, 5934.
DOI Google Scholar
[3]

Wu, P. S.; He, T.; Zhu, H.; Wang, Y.; Li, Q.; Wang, Z.; Fu, X.; Wang, F.; Wang, P.; Shan, C. X. et al. Next-generation machine vision systems incorporating two-dimensional materials: Progress and perspectives. InfoMat 2021, 4, e12275.
DOI Google Scholar
[4]

Yuan, J. T.; Liu, S. E.; Shylendra, A.; Gaviria Rojas, W. A.; Guo, S. L.; Bergeron, H.; Li, S. W.; Lee, H. S.; Nasrin, S.; Sangwan, V. K. et al. Reconfigurable MoS2 memtransistors for continuous learning in spiking neural networks. Nano Lett. 2021, 21, 6432–6440.
DOI Google Scholar
[5]

Li, D.; Wu, B.; Zhu, X. J.; Wang, J. T.; Ryu, B.; Lu, W. D.; Lu, W.; Liang, X. G. MoS2 memristors exhibiting variable switching characteristics toward biorealistic synaptic emulation. ACS Nano 2018, 12, 9240–9252.
DOI Google Scholar
[6]

Liao, F. Y.; Zhou, Z.; Kim, B. J.; Chen, J. W.; Wang, J. L.; Wan, T. Q.; Zhou, Y.; Hoang, A. T.; Wang, C.; Kang, J. F. et al. Bioinspired in-sensor visual adaptation for accurate perception. Nat. Electron. 2022, 5, 84–91.
DOI Google Scholar
[7]

Hong, S.; Choi, S. H.; Park, J.; Yoo, H.; Oh, J. Y.; Hwang, E.; Yoon, D. H.; Kim, S. Sensory adaptation and neuromorphic phototransistors based on CsPb(Br1−xIx)3 perovskite and MoS2 hybrid structure. ACS Nano 2020, 14, 9796–9806.
DOI Google Scholar
[8]

Li, N.; He, C. L.; Wang, Q. Q.; Tang, J. S.; Zhang, Q. T.; Shen, C.; Tang, J.; Huang, H. Y.; Wang, S. P.; Li, J. W. et al. Gate-tunable large-scale flexible monolayer MoS2 devices for photodetectors and optoelectronic synapses. Nano Res. 2022, 15, 5418–5424.
DOI Google Scholar
[9]

Islam, M. M.; Krishnaprasad, A.; Dev, D.; Martinez-Martinez, R.; Okonkwo, V.; Wu, B.; Han, S. S.; Bae, T. S.; Chung, H. S.; Touma, J. et al. Multiwavelength optoelectronic synapse with 2D materials for mixed-color pattern recognition. ACS Nano 2022, 16, 10188–10198.
DOI Google Scholar
[10]

Han, K. H.; Kim, G. S.; Park, J.; Kim, S. G.; Park, J. H.; Yu, H. Y. Reduction of threshold voltage hysteresis of MoS2 transistors with 3-aminopropyltriethoxysilane passivation and its application for improved synaptic behavior. ACS Appl. Mater. Interfaces 2019, 11, 20949–20955.
DOI Google Scholar
[11]

Wang, W. X.; Gao, S.; Li, Y.; Yue, W. J.; Kan, H.; Zhang, C. W.; Lou, Z.; Wang, L. L.; Shen, G. Z. Artificial optoelectronic synapses based on TiNxO2−x/MoS2 heterojunction for neuromorphic computing and visual system. Advanced Functional Materials 2021, 31, 2170247.
DOI Google Scholar
[12]

Dodda, A.; Trainor, N.; Redwing, J. M.; Das, S. All-in-one, bio-inspired, and low-power crypto engines for near-sensor security based on two-dimensional memtransistors. Nat. Commun. 2022, 13, 3587.
DOI Google Scholar
[13]

Sun, Y. L.; Li, M. J.; Ding, Y. T.; Wang, H. P.; Wang, H.; Chen, Z. M.; Xie, D. Programmable van-der-Waals heterostructure-enabled optoelectronic synaptic floating-gate transistors with ultra-low energy consumption. InfoMat 2022, 4, e12317.
DOI Google Scholar
[14]

Jang, H.; Liu, C. Y.; Hinton, H.; Lee, M. H.; Kim, H.; Seol, M.; Shin, H. J.; Park, S.; Ham, D. An atomically thin optoelectronic machine vision processor. Adv. Mater. 2020, 32, 2002431.
DOI Google Scholar
[15]

Wang, S. Y.; Chen, C. S.; Yu, Z. H.; He, Y. L.; Chen, X. Y.; Wan, Q.; Shi, Y.; Zhang, D. W.; Zhou, H.; Wang, X. R. et al. A MoS2/PTCDA hybrid heterojunction synapse with efficient photoelectric dual modulation and versatility. Adv. Mater. 2019, 31, 1806227.
DOI Google Scholar
[16]

Jeong, Y.; Lee, H. J.; Park, J.; Lee, S.; Jin, H. J.; Park, S.; Cho, H.; Hong, S.; Kim, T.; Kim, K. et al. Engineering MoSe2/MoS2 heterojunction traps in 2D transistors for multilevel memory, multiscale display, and synaptic functions. npj 2D Mater. Appl. 2022, 6, 23.
DOI Google Scholar
[17]

Zang, L. Y.; Chen, L.; Tan, D. C.; Cao, X. G.; Sun, N.; Jiang, C. M. Research on multi-morphology evolution of MoS2 in chemical vapor deposition. ChemistrySelect 2021, 6, 8107–8113.
DOI Google Scholar
[18]

Nur, R.; Tsuchiya, T.; Toprasertpong, K.; Terabe, K.; Takagi, S.; Takenaka, M. A floating gate negative capacitance MoS2 phototransistor with high photosensitivity. Nanoscale 2022, 14, 2013–2022.
DOI Google Scholar
[19]

Zhu, X. J.; Li, D.; Liang, X. G.; Lu, W. D. Ionic modulation and ionic coupling effects in MoS2 devices for neuromorphic computing. Nat. Mater. 2019, 18, 141–148.
DOI Google Scholar
[20]

Ma, S. L.; Wu, T. X.; Chen, X. Y.; Wang, Y.; Tang, H. W.; Yao, Y. T.; Wang, Y.; Zhu, Z. Y.; Deng, J. N.; Wan, J. et al. An artificial neural network chip based on two-dimensional semiconductor. Sci. Bull. 2022, 67, 270–277.
DOI Google Scholar
[21]

Kim, K. S.; Ji, Y. J.; Kim, K. H.; Choi, S.; Kang, D. H.; Heo, K.; Cho, S.; Yim, S.; Lee, S.; Park, J. H. et al. Ultrasensitive MoS2 photodetector by serial nano-bridge multi-heterojunction. Nat. Commun. 2019, 10, 4701.
DOI Google Scholar
[22]

Chen, L.; Zang, L. Y.; Chen, L. H.; Wu, J. C.; Jiang, C. M.; Song, J. H. Study on the catalyst effect of NaCl on MoS2 growth in a chemical vapor deposition process. CrystEngComm 2021, 23, 5337–5344.
DOI Google Scholar
[23]

Yin, S. Q.; Luo, Z. C.; Li, Q.; Xiong, C. Y.; Liu, Y. L.; Singh, R.; Zeng, F.; Zhong, Y.; Zhang, X. Z. Emulation of learning and memory behaviors by memristor based on Ag migration on 2D MoS2 surface. Phys. Stat. Solidi (A) 2019, 216, 1900104.
DOI Google Scholar
[24]

Fung, V.; Zhang, J. X.; Hu, G. X.; Ganesh, P.; Sumpter, B. G. Inverse design of two-dimensional materials with invertible neural networks. npj Computat. Mater. 2021, 7, 212.
DOI Google Scholar
[25]

Krishnaprasad, A.; Dev, D.; Han, S. S.; Shen, Y. Q.; Chung, H. S.; Bae, T. S.; Yoo, C.; Jung, Y.; Lanza, M.; Roy, T. MoS2 synapses with ultra-low variability and their implementation in boolean logic. ACS Nano 2022, 16, 2866–2876.
DOI Google Scholar
[26]

Naqi, M.; Kang, M. S.; Liu, N.; Kim, T.; Baek, S.; Bala, A.; Moon, C.; Park, J.; Kim, S. Multilevel artificial electronic synaptic device of direct grown robust MoS2 based memristor array for in-memory deep neural network. npj 2D Mater. Appl. 2022, 6, 53.
DOI Google Scholar
[27]

Radhakrishnan, S. S.; Sebastian, A.; Oberoi, A.; Das, S.; Das, S. A biomimetic neural encoder for spiking neural network. Nat. Commun. 2021, 12, 2143.
DOI Google Scholar
[28]

Zhou, Y.; Wang, Y. S.; Zhuge, F. W.; Guo, J. M.; Ma, S. J.; Wang, J. L.; Tang, Z. J.; Li, Y.; Miao, X. S.; He, Y. H. et al. A reconfigurable two-WSe2-transistor synaptic cell for reinforcement learning. Adv. Mater. 2022, 34, 2107754.
DOI Google Scholar
[29]

Yang, X. X.; Yu, J. R.; Zhao, J.; Chen, Y. H.; Gao, G. Y.; Wang, Y. F.; Sun, Q. J.; Wang, Z. L. Mechanoplastic tribotronic floating-gate neuromorphic transistor. Adv. Funct. Mater. 2020, 30, 2002506.
DOI Google Scholar
[30]

Zhang, M.; Fan, Z. H.; Jiang, X. X.; Zhu, H.; Chen, L.; Xia, Y. D.; Yin, J.; Liu, X. K.; Sun, Q. Q.; Zhang, D. W. MoS2-based charge-trapping synaptic device with electrical and optical modulated conductance. Nanophotonics 2020, 9, 2475–2486.
DOI Google Scholar
[31]

Lee, E.; Kim, J.; Bhoyate, S.; Cho, K.; Choi, W. Realizing scalable two-dimensional MoS2 synaptic devices for neuromorphic computing. Chem. Mater. 2020, 32, 10447–10455.
DOI Google Scholar
[32]

Wang, B. L.; Wang, X. W.; Wang, E. Z.; Li, C. Y.; Peng, R. X.; Wu, Y. H.; Xin, Z. Q.; Sun, Y. F.; Guo, J.; Fan, S. S. et al. Monolayer MoS2 synaptic transistors for high-temperature neuromorphic applications. Nano Lett. 2021, 21, 10400–10408.
DOI Google Scholar
[33]

Xu, R. J.; Jang, H.; Lee, M. H.; Amanov, D.; Cho, Y.; Kim, H.; Park, S.; Shin, H. J.; Ham, D. Vertical MoS2 double-layer memristor with electrochemical metallization as an atomic-scale synapse with switching thresholds approaching 100 mV. Nano Lett. 2019, 19, 2411–2417.
DOI Google Scholar
[34]

Migliato Marega, G.; Wang, Z. Y.; Paliy, M.; Giusi, G.; Strangio, S.; Castiglione, F.; Callegari, C.; Tripathi, M.; Radenovic, A.; Iannaccone, G. et al. Low-power artificial neural network perceptron based on monolayer MoS2. ACS Nano 2022, 16, 3684–3694.
DOI Google Scholar
[35]

Yan, X. D.; Ma, J. H.; Wu, T.; Zhang, A. Y.; Wu, J. B.; Chin, M.; Zhang, Z. H.; Dubey, M.; Wu, W.; Chen, M. S. W. et al. Reconfigurable stochastic neurons based on tin oxide/MoS2 hetero-memristors for simulated annealing and the Boltzmann machine. Nat. Commun. 2021, 12, 5710.
DOI Google Scholar
[36]

Nam, J. H.; Oh, S.; Jang, H. Y.; Kwon, O.; Park, H.; Park, W.; Kwon, J. D.; Kim, Y.; Cho, B. Low power MoS2/Nb2O5 memtransistor device with highly reliable heterosynaptic plasticity. Adv. Funct. Mater. 2021, 31, 2104174.
DOI Google Scholar
[37]

Ke, Y. Z.; Mao, L. N.; Jie, W. J.; Gong, T. X.; Huang, W.; Zhang, X. S. An artificial electrical-chemical mixed synapse based on ion-gated MoS2 nanosheets for real-time facilitation index tuning. ACS Appl. Mater. Interfaces 2021, 13, 15755–15760.
DOI Google Scholar
[38]

Xie, D. D.; Jiang, J.; Hu, W. N.; He, Y. L.; Yang, J. L.; He, J.; Gao, Y. L.; Wan, Q. Coplanar multigate MoS2 electric-double-layer transistors for neuromorphic visual recognition. ACS Appl. Mater. Interfaces 2018, 10, 25943–25948.
DOI Google Scholar
[39]

Dodda, A.; Das, S. Demonstration of stochastic resonance, population coding, and population voting using artificial MoS2 based synapses. ACS Nano 2021, 15, 16172–16182.
DOI Google Scholar
[40]

Arnold, A. J.; Razavieh, A.; Nasr, J. R.; Schulman, D. S.; Eichfeld, C. M.; Das, S. Mimicking neurotransmitter release in chemical synapses via hysteresis engineering in MoS2 transistors. ACS Nano 2017, 11, 3110–3118.
DOI Google Scholar
[41]

Radhakrishnan, S. S.; Chakrabarti, S.; Sen, D.; Das, M.; Schranghamer, T. F.; Sebastian, A.; Das, S. A sparse and spike-timing-based adaptive photoencoder for augmenting machine vision for spiking neural networks. Adv. Mater. 2022, 34, 2202535.
DOI Google Scholar
[42]

Mennel, L.; Symonowicz, J.; Wachter, S.; Polyushkin, D. K.; Molina-Mendoza, A. J.; Mueller, T. Ultrafast machine vision with 2D material neural network image sensors. Nature 2020, 579, 62–66.
DOI Google Scholar
[43]

Mouri, S.; Miyauchi, Y.; Matsuda, K. Tunable photoluminescence of monolayer MoS2 via chemical doping. Nano Lett. 2013, 13, 5944–5948.
DOI Google Scholar
[44]

Neri, I.; López-Suárez, M.; Caponi, S.; Mattarelli, M. Fast MoS2 thickness identification by transmission imaging. Appl. Nanosci. 2021, 11, 605–610.
DOI Google Scholar
[45]

Jeon, J.; Jang, S. K.; Jeon, S. M.; Yoo, G.; Jang, Y. H.; Park, J. H.; Lee, S. Layer-controlled CVD growth of large-area two-dimensional MoS2 films. Nanoscale 2015, 7, 1688–1695.
DOI Google Scholar
[46]

Khan, H.; Medina, H.; Tan, L. K.; Tjiu, W.; Boden, S. A.; Teng, J. H.; Nandhakumar, I. A single-step route to single-crystal molybdenum disulphide (MoS2) monolayer domains. Sci. Rep. 2019, 9, 4142.
DOI Google Scholar
[47]

Lee, S. Y.; Kim, U. J.; Chung, J.; Nam, H.; Jeong, H. Y.; Han, G. H.; Kim, H.; Oh, H. M.; Lee, H.; Kim, H. et al. Large work function modulation of monolayer MoS2 by ambient gases. ACS Nano 2016, 10, 6100–6107.
DOI Google Scholar
[48]

Lee, Y. T.; Kang, J. H.; Kwak, K.; Ahn, J.; Choi, H. T.; Ju, B. K.; Shokouh, S. H.; Im, S.; Park, M. C.; Hwang, D. K. High-performance 2D MoS2 phototransistor for photo logic gate and image sensor. ACS Photon. 2018, 5, 4745–4750.
DOI Google Scholar
[49]

Liu, H.; Gao, F.; Hu, Y. X.; Zhang, J.; Wang, L. F.; Feng, W.; Hou, J.; Hu, P. G. Enhanced photoresponse of monolayer MoS2 through hybridization with carbon quantum dots as efficient photosensitizer. 2D Mater. 2019, 6, 035025.
DOI Google Scholar
[50]

Dong, W. S.; Wang, P. Y.; Yin, W. T.; Shi, G. M.; Wu, F. F.; Lu, X. T. Denoising prior driven deep neural network for image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 41, 2305–2318.
DOI Google Scholar
[51]

Wen, S. P.; Xiao, S. X.; Yang, Y.; Yan, Z.; Zeng, Z. G.; Huang, T. W. Adjusting learning rate of memristor-based multilayer neural networks via fuzzy method. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 2019, 38, 1084–1094.
DOI Google Scholar
[52]

Li, X. Y.; Zhang, L.; Wang, Z. P.; Dong, P. Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks. J. Energy Storage 2019, 21, 510–518.
DOI Google Scholar
[53]

Chen, L.; Zang, L. Y.; Wu, J. C.; Tan, D. C.; Li, Z. X.; Song, J. H.; Jiang, C. M. High-output photodetector by microlithographic mono-layer MoS2 for image sensor. Adv. Mater. Techhnol. 2022, 8, 2200707.
DOI Google Scholar
File
12274_2023_5494_MOESM1_ESM.pdf (981.4 KB)
Publication history
Copyright
Acknowledgements

Publication history

Received: 21 November 2022
Revised: 05 January 2023
Accepted: 08 January 2023
Published: 09 March 2023
Issue date: July 2023

Copyright

© Tsinghua University Press 2023

Acknowledgements

Acknowledgements

This project was financially supported by the Dalian Science and Technology Innovation Fund of China (No. 2019J11CY011) and the Science Fund for Creative Research Groups of NSFC (No. 51621064).

Return