(Peer-Reviewed) Adaptive decentralized AI scheme for signal recognition of distributed sensor systems
Shixiong Zhang 张世雄 ¹, Hao Li 李豪 ¹, Cunzheng Fan 范存政 ¹, Zhichao Zeng 曾志超 ¹, Chao Xiong 熊超 ⁵, Jie Wu 吴杰 ⁶, Zhijun Yan 闫志君 ¹ ³ ⁴, Deming Liu 刘德明 ¹, Qizhen Sun 孙琪真 ¹ ² ³ ⁴
¹ School of Optical and Electronic Information, National Engineering Research Center of Next Generation Internet Access-system, Huazhong University of Science and Technology, Wuhan 430074, China
中国 武汉 华中科技大学光学与电子信息学院 下一代互联网接入系统国家工程研究中心
² PGMF and School of Physics, Huazhong University of Science and Technology, Wuhan 430074, China
中国 武汉 华中科技大学物理学院 精密重力测量研究设施
³ Jinyinhu Laboratory, Wuhan 430048, China
中国 武汉 金银湖实验室
⁴ Optics Valley Laboratory, Wuhan 430074, China
中国 武汉 光谷实验室
⁵ Nanjing Research Institute of Electronic Equipment, Nanjing 210007, China
中国 南京 南京电子设备研究所
⁶ Wenzhou Quality and Technology Testing Research Institute, Wenzhou 325000, China
中国 温州 温州市质量技术检测科学研究院
Opto-Electronic Advances
, 2024-09-29
Abstract
Artificial intelligence (AI) plays a critical role in signal recognition of distributed sensor systems (DSS), boosting its applications in multiple monitoring fields. Due to the domain differences between massive sensors in signal acquisition conditions, such as manufacturing process, deployment, and environments, current AI schemes for signal recognition of DSS frequently encounter poor generalization performance.
In this paper, an adaptive decentralized artificial intelligence (ADAI) method for signal recognition of DSS is proposed, to improve the entire generalization performance. By fine-tuning pre-trained model with the unlabeled data in each domain, the ADAI scheme can train a series of adaptive AI models for all target domains, significantly reducing the false alarm rate (FAR) and missing alarm rate (MAR) induced by domain differences.
The field tests about intrusion signal recognition with distributed optical fiber sensors system demonstrate the efficacy of the ADAI scheme, showcasing a FAR of merely 4.3% and 0%, along with a MAR of only 1.4% and 2.7% within two specific target domains. The ADAI scheme is expected to offer a practical paradigm for signal recognition of DSS in multiple application fields.
Ultrafast all-optical modulation of wide-bandwidth pulses enabled by silicon-metasurfaces
Kaloyan Georgiev, Khosro Zangeneh Kamali, Anton A. Trifonov, Giulia Crotti, Lyuben Petrov, Stefan Georgiev, Hristo Iliev, Lei Xu, Unai Arregui Leon, Mohsen Rahmani, Giuseppe Della Valle, Ivan Buchvarov, Dragomir Neshev
Opto-Electronic Advances
2026-09-15
Physics-informed neural fields enable blind aberration correction for partially coherent quantitative phase imaging
Shun Zhou, Xingyu Huang, Linpeng Lu, Habib Ullah, Kaiyu Du, Maciej Trusiak, Malgorzata Kujawinska, Yuzhen Zhang, Yao Fan, Qian Chen, Qinrong Zhang, Chao Zuo
Opto-Electronic Science
2026-08-26
Heterogeneously integrated micro-ring with SnS₂ for dual-functional optical modulation and photodetection
Jinyi Du, Lidan Lu, Xu Zhang, Bofei Zhu, Wenbo Bo, Yingjie Xu, Guang Chen, Yanlin He, Guanghui Ren, Xiaoping Lou, Zheng You, Lianqing Zhu
Opto-Electronic Advances
2026-08-25
Hardware-aware lightweight photonic spiking neural network for pattern classification
Shuiying Xiang, Yahui Zhang, Shangxuan Shi, Haowen Zhao, Dianzhuang Zheng, Xingxing Guo, Yanan Han, Ye Tian, Liyue Zhang, Yuechun Shi, Yue Hao
Opto-Electronic Advances
2026-08-25
PhyspeNet: An empirical physics-aware network for adaptive speckle reconstructive spectrometry
Junrui Liang, Min Jiang, Jun Li, Zhongming Huang, Junhong He, Yanting Guo, Yanzhao Ke, Jun Ye, Jiangming Xu, Jinyong Leng, Pu Zhou
Opto-Electronic Advances
2026-08-25
A 36 × 240 Gbps hybrid mode/wavelength division multiplexing transmitter using lithium niobate on insulator
Mingyu Zhu, Weihan Wang, Ruitao Ma, Aoyun Gao, Chun Gao, Zexu Wang, Fei Huang, Zhenyuan Bao, Dajian Liu, Jiaxuan Gan, Zejie Yu, Huan Li, Weike Zhao, Daoxin Dai
Opto-Electronic Advances
2026-08-25
