2026 Vol.9 Aug.N04

• Title: Design of multi-source sensor data acquisition and fusion processing for smart helmet
• Name: HaoLinZhao， ShiTing Lv ，XiaoFeng Ren， Lei Liu*
• Company: School of Mechanical and Electrical Engineering, Zhengzhou Business University, GongYi 451200,China
• Abstract:

  Most of the multi-source sensor fusion methods of smart helmet rely on fixed weight weighting mechanism to merge information. Because of ignoring the dynamic difference of real-time signal quality of different sensing channels, it is difficult to adaptively adjust the contribution ratio of each channel information, resulting in poor fusion accuracy. In this paper, a method of multi-source sensor data acquisition and fusion processing for smart helmet is proposed. Based on the helmet multi-channel heterogeneous sensing acquisition time sequence, the multi-channel sensing time sequence correlation and state vector construction are carried out, and the head motion parameters, environmental perception parameters and human body sign parameters are brought into a unified state description framework, and the state time sequence evolution relationship and observation mapping relationship are established. Based on the difference between the observation difference quantification theory and the field sensing information, the gain matrix is calculated dynamically, and the information weight is assigned independently according to the real-time signal stability of each sensing channel, thus weakening the influence of disturbed channels on the fusion results. Combined with the gain parameter and observation difference, the prior state is corrected, and the uncertainty description matrix is updated synchronously, forming a closed-loop operation link that can continuously iterate with time-series samples, and continuously tracking the state change of helmet system. In the experiment, the fusion accuracy of the proposed method is tested. Through the test and comparison results, it is clear that when the proposed method is used for multi-source data fusion of smart helmets, the time series fit can be stably maintained above 0.85, which has an ideal fusion effect.

  
  

• Keyword: smart helmet; Multi-source sensing; Time series correlation; Dynamic gain; Data fusion; Kalman filter;
• DOI: 10.12250/jpciams2026090810
• Citation form: HaoLinZhao,ShiTing Lv,XiaoFeng Ren,Lei Liu.Design of multi-source sensor data acquisition and fusion processing for smart helmet[J]. Computer Informatization and Mechanical System,2026,Vol.9,pp.

[1] Raj M P .Design a Smart Helmet with Multi-Fusion Sensor for Accident Detection[J].INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 2025, 09(05):1-9.

[2] Prof. B N B , Shaikh S A , Lahane V V ,et al.A Review of Smart Helmet and Accident Alert System[J].INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 2025, 09(11):1-9.

[3] Prema C .IOT Based - Smart Helmet for Air Quality and Hazardous Event Detection for the Mining Industry[J].INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 2025, 09(02):1-9.

[4] Pinnelli M , Albanil I D P M , Ledda A ,et al.Design and Performance Evaluation of a Smart Helmet System for Human Activity Recognition in Worker Safety Applications[J].IEEE Sensors Journal, 2026, 26(2):3206-3215.

[5] He Z , Geng X .Aeroderivative gas turbines fault diagnosis via IKOA-optimized CNN-BiLSTM with multi-source sensor data[J].Measurement, 2025, 257:118978-118978.

[6] Correia B M ,Pieter H.H. Aparício,Rogério M.G. Martins,et al.Towards automated traffic accident reconstruction using ITS and multi-sensor data fusion[J].Transportation Engineering, 2026, 23:100425-100425.

[7] Zhang M .Multi-source field sensor data fusion based on cross modal attention mechanism and reinforcement learning driven pesticide application optimization model: towards sustainable crop protection[J].Future Technology, 2026, 5(1):26-37.

[8] Belgacem H , Aggoune-Mtalaa W , Stolfi D H ,et al.Multi-Sensor Data Fusion: An Overview of Concepts, Methods, and Classifications[J].IEEE Access, 2026, 14:41202-41229.

[9] Masciulli C , Berardo G , Gaeta M ,et al.Multisensor Data Fusion for Enhanced Persistent Scatterer Analysis: Improving Ground Deformation Monitoring[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18(18):26812-26830.

[10] Shuming Y , Changlin X , Yuqiang C ,et al.Data-Driven Fault Diagnosis for Rolling Bearings Based on Machine Learning and Multisensor Information Fusion[J].Sensors Journal, IEEE, 2025, 25(2):3452-3464.

[11] Zhang B , Liu R W , Liu J ,et al.Multi-Sensor Data Fusion Meets Edge Computing for Intelligent Surface Vehicles[J].IEEE Internet of Things Magazine, 2025, 8(5):127-135.

[12] Dong Q , Wei Q .Construction of multi-source sensor data fusion and construction state recognition model for intelligent construction[J].IET conference proceedings.  2026, 2025(34):448-452.

[13] Wang J , Nie L , Gu Z ,et al.Real-Time GPS Spoofing Detection in Consumer Drones Through Multi-Sensor Data Fusion and TimesNet[J].Consumer Electronics, IEEE Transactions on, 2025, 71(2):5569-5583.

[14] Liu B , Cheng J , Cao J .Evaluation of Tourism Development Efficiency Using Multisource Sensor Data: A Case Study in China[J].Sensors and Materials, 2026, 38(1):419-419.

[15] Yadav A , Doshi H , Jayaprakash B ,et al.A Novel Hybrid Framework for Forecasting Appliance-Level Electrical Energy Consumption Using Multi-Sensor Data in Smart Systems[J].Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 2026, 50(2):1081-1105.