Research On The Method Of Personnel Trajectory In Coal Mine

With the wide application of positioning technologies such as RFID,WiFi and ZigBee in coal mines,it can accurately track miners' trajectories and generate a large number of positioning data.But at present,these data are only used for attendance and historical location inquiry in miner management system.Therefore,how to effectively use the hidden trajectory information of location data,expand the function of miner management system,and analyze the abnormal behavior of miners through positioning data has gradually become an important research direction of data mining technology in the field of coal mine application.On this basis,combined with the actual situation of coal mine,using data mining technology,the hot spot distribution and abnormal trajectory of coal mine are studied.Firstly,aiming at the research content of this paper,the mining model of miner is put forward by using big data related technology combined with the location data of underground personnel in coal mines.The model is divided into three parts: data acquisition,data processing and visualization.Secondly,aiming at the problem those existing hotspot area detection algorithms can not recognize multi-density,KL_TM framework for identifying hotspots based on miners' activities is proposed.The framework consists of two parts: candidate key position selection algorithm and hotspot area filtering algorithm.KL_TM reduces the data redundancy and computational complexity,and effectively solve the hotspot area discovery problem of multi-density spatio-temporal trajectory data.Then,in view of the fact that the existing abnormal trajectory studies do not take time into account,and that the location data in coal mines have macro-and micro-sparse attributes,an outlier-based abnormal trajectory screening IMTRAOD algorithm is proposed.The algorithm not only takes into account the spatial characteristics of the trajectory,but also takes the time characteristics as an index,and has higher accuracy,lower miss detection rate and false detection rate.Finally,theory and practice are used to verify the feasibility of the method proposed in the text,and large data technology is used to design and implement the data mining platform for miners' trajectory.The main contents of the system include the display of trajectory of miners,the identification of key areas and the screening of abnormal trajectories.In the process of system development,modularization is adopted to facilitate the expansion of functions.At the same time,through thevisualization of daily trajectory and abnormal trajectory,managers can not only more intuitively understand the progress and working status of miners,but also can stop the miners' irregularities in time and avoid the irregularities becoming the miners' habitual actions.