In-sensor reservoir computing for biometric identification based on MoTe₂/BaTiO₃ optical synapses

Abstract

The artificial intelligence era has witnessed a surge of demand in detection and recognition of biometric information, with applications from financial services to information security. However, the physical separation of sensing, memory, and computational units in traditional biometric systems introduces severe decision latency and operational power consumption. Herein, an in-sensor reservoir computing (RC) system based on MoTe₂/BaTiO₃ optical synapses is proposed to detect and recognize the faces and fingerprints information. In optical operation mode, the device exhibits low energy consumption of 41.2 pJ, long retention time of 3 × 10⁴ s, high endurance of 10⁴ switching cycles, and multifunctional sensing-memory-computing visual simulations. The light intensity-dependent optical sensing and multilevel optical storage properties are exploited to achieve sunburned eye simulation and image memory functions. These nonlinear, multi-state, short-term storage, and long-term memory characteristics make MoTe₂/BaTiO₃ optical synapses a suitable reservoir layer and readout layer, with short-term properties to project complicated input features into high-dimensional output features, and long-term properties to be used as a readout layer, thus further building an in-sensor RC system for face and fingerprint recognition. Under the 40% Gaussian noise environment, the system achieves 91.73% recognition accuracy for face and 97.50% for fingerprint images, and experimental verification is carried out, which shows potential in practical applications. These results provide a strategy for constructing a high-performance in-sensor RC system for high-accuracy biometric identification.

Keywords

2D/ferroelectric heterostructure / artificial vision system / in-sensor reservoir computing / optical synapse / sensing-memory-computing

References

[1] An BW, Heo S, Ji S, Bien F, Park J-U. Transparent and flexible fingerprint sensor array with multiplexed detection of tactile pressure and skin temperature. Nat Commun. 2018; 9(1): 2458.

[2] Xia X, O'Gorman L. Innovations in fingerprint capture devices. Pattern Recognit. 2003; 36(2): 361-369.

[3] Jain AK. Biometric recognition. Nature. 2007; 449(7158): 38-40.

[4] Zhou Y, Fu J, Chen Z, et al. Computational event-driven vision sensors for in-sensor spiking neural networks. Nat Electron. 2023; 6(11): 870-878.

[5] Rajasekar V, Predić B, Saracevic M, et al. Enhanced multimodal biometric recognition approach for smart cities based on an optimized fuzzy genetic algorithm. Sci Rep. 2022; 12(1): 622.

[6] Win KN, Li K, Chen J, Viger PF, Li K. Fingerprint classification and identification algorithms for criminal investigation: a survey. Future Gener Comput Syst. 2020; 110: 758-771.

[7] Wang M, Li M, Yu A, Zhu Y, Yang M, Mao C. Fluorescent nanomaterials for the development of latent fingerprints in forensic sciences. Adv Funct Mater. 2017; 27(14): 1606243.

[8] Chen J, Zhou Z, Kim BJ, et al. Optoelectronic graded neurons for bioinspired in-sensor motion perception. Nat Nanotechnol. 2023; 18(8): 882-888.

[9] Minaee S, Abdolrashidi A, Su H, Bennamoun M, Zhang D. Biometrics recognition using deep learning: a survey. Artif Intell Rev. 2023; 56(8): 8647-8695.

[10] Jain AK, Ross A, Prabhakar S. An introduction to biometric recognition. IEEE Trans Circuits Syst Video Technol. 2004; 14(1): 4-20.

[11] Liao F, Zhou Z, Kim BJ, et al. Bioinspired in-sensor visual adaptation for accurate perception. Nat Electron. 2022; 5(2): 84-91.

[12] Wang Y, Gong Y, Yang L, et al. MXene-ZnO memristor for multimodal in-sensor computing. Adv Funct Mater. 2021; 31(21): 2100144.

[13] Meng J, Wang T, Zhu H, et al. Integrated in-sensor computing optoelectronic device for environment-adaptable artificial retina perception application. Nano Lett. 2021; 22(1): 81-89.

[14] Zhu X, Su W, Liu Y, et al. Observation of conductance quantization in oxide-based resistive switching memory. Adv Mater. 2012; 24(29): 3941-3946.

[15] Wang C-Y, Liang S-J, Wang S, et al. Gate-tunable van der Waals heterostructure for reconfigurable neural network vision sensor. Sci Adv. 2020; 6(26): eaba6173.

[16] Ahmed T, Tahir M, Low MX, et al. Fully light-controlled memory and neuromorphic computation in layered black phosphorus. Adv Mater. 2021; 33: 2004207.

[17] Choi C, Leem J, Kim M, et al. Curved neuromorphic image sensor array using a MoS₂-organic heterostructure inspired by the human visual recognition system. Nat Commun. 2020; 11(1): 5934.

[18] Shang J, Liu G, Yang H, et al. Thermally stable transparent resistive random access memory based on all-oxide heterostructures. Adv Funct Mater. 2014; 24(15): 2171-2179.

[19] Ren Q, Zhu C, Ma S, et al. Optoelectronic devices for in-sensor computing. Adv Mater. 2024;2407476.

[20] Moon J, Ma W, Shin JH, et al. Temporal data classification and forecasting using a memristor-based reservoir computing system. Nat Electron. 2019; 2(10): 480-487.

[21] Sun L, Wang Z, Jiang J, et al. In-sensor reservoir computing for language learning via two-dimensional memristors. Sci Adv. 2021; 7(20): eabg1455.

[22] Chen Z, Li W, Fan Z, et al. All-ferroelectric implementation of reservoir computing. Nat Commun. 2023; 14: 3585.

[23] Tan H, Liu G, Zhu X, et al. An optoelectronic resistive switching memory with integrated demodulating and arithmetic functions. Adv Mater. 2015; 27(17): 2797-2803.

[24] Du C, Cai F, Zidan MA, Ma W, Lee SH, Lu WD. Reservoir computing using dynamic memristors for temporal information processing. Nat Commun. 2017; 8(1): 2204.

[25] Tanaka G, Yamane T, Héroux JB, et al. Recent advances in physical reservoir computing: a review. Neural Netw. 2019; 115: 100-123.

[26] Du W, Li C, Huang Y, et al. An optoelectronic reservoir computing for temporal information processing. IEEE Electron Device Lett. 2022; 43(3): 406-409.

[27] Wang P, Li J, Xue W, et al. Integrated in-memory sensor and computing of artificial vision based on full-vdW optoelectronic ferroelectric field-effect transistor. Adv Sci. 2024; 11: 2305679.

[28] Chen S, Mahmoodi MR, Shi Y, et al. Wafer-scale integration of two-dimensional materials in high-density memristive crossbar arrays for artificial neural networks. Nat Electron. 2020; 3(10): 638-645.

[29] Zhou F, Zhou Z, Chen J, et al. Optoelectronic resistive random access memory for neuromorphic vision sensors. Nat Nanotechnol. 2019; 14: 776-782.

[30] Long X, Tan H, Sánchez F, Fina I, Fontcuberta J. Non-volatile optical switch of resistance in photoferroelectric tunnel junctions. Nat Commun. 2021; 12(1): 382.

[31] Chai X, Jiang J, Zhang Q, et al. Nonvolatile ferroelectric field-effect transistors. Nat Commun. 2020; 11(1): 2811.

[32] Guo R, You L, Lin W, et al. Continuously controllable photoconductance in freestanding BiFeO₃ by the macroscopic flexoelectric effect. Nat Commun. 2020; 11(1): 2571.

[33] Carroli M, Dixon AG, Herder M, et al. Multiresponsive nonvolatile memories based on optically switchable ferroelectric organic field-effect transistors. Adv Mater. 2021; 33: 2007965.

[34] Qiao H, Wang C, Choi WS, Park MH, Kim Y. Ultra-thin ferroelectrics. Mater Sci Eng R Rep. 2021; 145: 100622.

[35] Lanza M, Sebastian A, Lu WD, et al. Memristive technologies for data storage, computation, encryption, and radio-frequency communication. Science. 2022; 376(6597): eabj9979.

[36] Ko C, Lee Y, Chen Y, et al. Ferroelectrically gated atomically thin transition-metal dichalcogenides as nonvolatile memory. Adv Mater. 2016; 28(15): 2923-2930.

[37] Lv L, Zhuge F, Xie F, et al. Reconfigurable two-dimensional optoelectronic devices enabled by local ferroelectric polarization. Nat Commun. 2019; 10(1): 3331.

[38] Wu G, Tian B, Liu L, et al. Programmable transition metal dichalcogenide homojunctions controlled by nonvolatile ferroelectric domains. Nat Electron. 2020; 3(1): 43-50.

[39] Wang X, Yu P, Lei Z, et al. Van der Waals negative capacitance transistors. Nat Commun. 2019; 10: 3037.

[40] Luo ZD, Yang MM, Liu Y, Alexe M. Emerging opportunities for 2D semiconductor/ferroelectric transistor-structure devices. Adv Mater. 2021; 33: 2005620.

[41] Li T, Lipatov A, Lu H, et al. Optical control of polarization in ferroelectric heterostructures. Nat Commun. 2018; 9: 1-8.

[42] Du J, Xie D, Zhang Q, et al. A robust neuromorphic vision sensor with optical control of ferroelectric switching. Nano Energy. 2021; 89: 106439.

[43] Luo Z-D, Xia X, Yang M-M, Wilson NR, Gruverman A, Alexe M. Artificial optoelectronic synapses based on ferroelectric field-effect enabled 2D transition metal dichalcogenide memristive transistors. ACS Nano. 2019; 14(1): 746-754.

[44] Milano G, Pedretti G, Montano K, et al. In materia reservoir computing with a fully memristive architecture based on self-organizing nanowire networks. Nat Mater. 2022; 21(2): 195-202.

[45] Appeltant L, Soriano MC, Van der Sande G, et al. Information processing using a single dynamical node as complex system. Nat Commun. 2011; 2(1): 468.

[46] Ruppert C, Aslan B, Heinz TF. Optical properties and band gap of single-and few-layer MoTe₂ crystals. Nano Lett. 2014; 14(11): 6231-6236.

[47] Shafi AM, Uddin MG, Cui X, et al. Strain engineering for enhancing carrier mobility in MoTe₂ field-effect transistors. Adv Sci. 2023; 10: 2303437.

[48] Hu G, An H, Xi J, Lu J, Hua Q, Peng Z. A ZnO micro/nanowire-based photonic synapse with piezo-phototronic modulation. Nano Energy. 2021; 89: 106282.

[49] Wang D, Zhao S, Li L, et al. All-flexible artificial reflex arc based on threshold-switching memristor. Adv Funct Mater. 2022; 32(21): 2200241.

[50] Gao S, Liu G, Yang H, et al. An oxide Schottky junction artificial optoelectronic synapse. ACS Nano. 2019; 13(2): 2634-2642.

[51] Panda MR, Gangwar R, Muthuraj D, et al. High performance lithium-ion batteries using layered 2H-MoTe₂ as anode. Small. 2020; 16: 2002669.

[52] Panda MR, Ghosh A, Kumar A, et al. Blocks of molybdenum ditelluride: a high rate anode for sodium-ion battery and full cell prototype study. Nano Energy. 2019; 64: 103951.

[53] Zhou L, Xu K, Zubair A, et al. Large-area synthesis of high-quality uniform few-layer MoTe₂. J Am Chem Soc. 2015; 137(37): 11892-11895.

[54] Zhou Y, Yang C, Fu X, et al. Optical modulation of MoTe₂/ferroelectric Heterostructure via Interface doping. ACS Appl Mater Interfaces. 2024; 16(10): 13247-13257.

[55] Sung SH, Kim TJ, Shin H, Im TH, Lee KJ. Simultaneous emulation of synaptic and intrinsic plasticity using a memristive synapse. Nat Commun. 2022; 13(1): 2811.

[56] Ma N, Yang Y. Boosted photocurrent in ferroelectric BaTiO₃ materials via two dimensional planar-structured contact configurations. Nano Energy. 2018; 50: 417-424.

[57] Lao J, Yan M, Tian B, et al. Ultralow-power machine vision with self-powered sensor reservoir. Adv Sci. 2022; 9: 2106092.

[58] Zhang Z, Zhao X, Zhang X, et al. In-sensor reservoir computing system for latent fingerprint recognition with deep ultraviolet photo-synapses and memristor array. Nat Commun. 2022; 13(1): 6590.

[59] Wang H, Yang J, Yang Z, et al. Optical-electrical coordinately modulated memristor based on 2D ferroelectric RP perovskite for artificial vision applications. Adv Sci. 2024; 11(33): 2403150.

[60] Zhong Y, Tang J, Li X, Gao B, Qian H, Wu H. Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing. Nat Commun. 2021; 12(1): 408.

[61] Blanter YM, Büttiker M. Shot noise in mesoscopic conductors. Phys Rep. 2000; 336(1-2): 1-166.

[62] Wang T-Y, Meng J-L, Li Q-X, et al. Reconfigurable optoelectronic memristor for in-sensor computing applications. Nano Energy. 2021; 89: 106291.

RIGHTS & PERMISSIONS

2025 The Author(s). InfoMat published by UESTC and John Wiley & Sons Australia, Ltd.