DTCluster: A CFSFDP Improved Algorithm for RFID Trajectory Clustering Under Digital-twin Driven

In the field of indoor monitoring, to analyze the track data collected by RFID readers effectively and intuitively is the critical issue. The indoor environment is usually crowded with a large number of flexible and mobile obstacles. The movements of obstacles always change the road network structure. To analyze the trajectories under the labile road network constrains is the key problem. To solve this problem, we propose a trajectory clustering method based on digital-twin technology called DTCluster. The proposed digital-twin model is a virtual digital model, which can extract and display the changing road network structure through real-time mapping and virtual simulation functions. In our paper, the original CFSFDP algorithm is improved to reduce the influence of the track missing points and to enhance the clustering effect in the face of unequal trajectories in length. We also take two parameters: the speed and the direction of moving targets into account. The trajectory clustering results in our DTCluster follow the changing road network for synchronous display on the proposed digital-twin model. It is convenient and effective for researchers to use DTCluster to find the problems which cannot be observed in the clustering results displayed in original planned road network. These problems can only be observed in the current changed road network environment. In our paper, we demonstrate the validity and intuition of DTCluster byexprimental results

[1]  Wu Muqing,et al.  A Controller Placement Algorithm Based on Density Clustering in SDN , 2018, 2018 IEEE/CIC International Conference on Communications in China (ICCC).

[2]  Fei Tao,et al.  Digital twin-driven product design, manufacturing and service with big data , 2017, The International Journal of Advanced Manufacturing Technology.

[3]  Manuel Paul,et al.  Keeping the digital twin up-to-date — Process monitoring to identify changes in a plant , 2018, 2018 IEEE International Conference on Industrial Technology (ICIT).

[4]  Kai Ming Ting,et al.  Density-ratio based clustering for discovering clusters with varying densities , 2016, Pattern Recognit..

[5]  Stephen Warde,et al.  Overview of Additive Manufacturing Informatics: “A Digital Thread” , 2016, Integrating Materials and Manufacturing Innovation.

[6]  Chongqing Kang,et al.  A Novel Combined Data-Driven Approach for Electricity Theft Detection , 2019, IEEE Transactions on Industrial Informatics.

[7]  Qingwei Liu,et al.  An Energy-Balanced Clustering Protocol Based on an Improved CFSFDP Algorithm for Wireless Sensor Networks , 2018, Sensors.

[8]  Kai Ming Ting,et al.  Local contrast as an effective means to robust clustering against varying densities , 2017, Machine Learning.

[9]  Xin Peng,et al.  A novel method for geographical origin identification of Tetrastigma hemsleyanum (Sanyeqing) by near-infrared spectroscopy , 2018 .

[10]  Wei Gang,et al.  An Improved CFSFDP Algorithm with Cluster Center Automatically Selected Based on Weighted Average Method , 2017, 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER).

[11]  Yiran Chen,et al.  HiSpatialCluster: A novel high‐performance software tool for clustering massive spatial points , 2018, Trans. GIS.

[12]  Edward M. Kraft,et al.  The Air Force Digital Thread/Digital Twin - Life Cycle Integration and Use of Computational and Experimental Knowledge , 2016 .

[13]  Shiqun Yin,et al.  Optimized fuzzy clustering by fast search and find of density peaks , 2018, 2018 IEEE 3rd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA).

[14]  Vijay Sharma,et al.  An Emerging Application Centric RFID Framework Based on New Web Technology , 2018, 2018 IEEE International Conference on RFID Technology & Application (RFID-TA).

[15]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .