Adaptive decentralized AI scheme for signal recognition of distributed sensor systems
用于分布式传感器系统信号识别的自适应分散式人工智能方案
分散センサーシステムの信号認識のための適応型分散AIスキーム
분산 센서 시스템의 신호 인식을 위한 적응형 분산형 AI 계획
Esquema de IA descentralizado adaptativo para el reconocimiento de señales de sistemas de sensores distribuidos
Schéma d'IA décentralisé adaptatif pour la reconnaissance des signaux des systèmes de capteurs distribués
Адаптивная децентрализованная схема ИИ для распознавания сигналов распределенных сенсорных систем
Shixiong Zhang ¹, Hao Li ¹, Cunzheng Fan ¹, Zhichao Zeng ¹, Chao Xiong ⁵, Jie Wu ⁶, Zhijun Yan ¹ ³ ⁴, Deming Liu1, Qizhen Sun 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(PGMF)
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 温州质量检测研究院
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.
