Reverse Path Nearby Cluster (Rpnc) Query Optimization using Trajectory Clustering With Ensemble Learning (Tcel) In Spatial Networks
G. Dona Rashmi1, V. Narayani2

1G. Dona Rashmi, Research Scholar, Department of Computer Science, Bharathiar University India.
2Dr.V. Narayani, Assistant Professor, Department of Computer Science, st. Xavier‟s college, Tirunelveli India.
Manuscript received on September 23, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 7562-7572 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1930109119/2019©BEIESP | DOI: 10.35940/ijeat.A1930.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: In spatial network, optimal path planning in real time is an open problem. For complex queries, Query optimization is intensively used. From given locations, most accessible locations can be found by Reverse Path nearby Cluster (R-PNC) query. This facility maximizes the commercial value. Distribution Clustering with Support Vector Machine is used to form a R-PNC clusters in the existing works. Trajectories with low positioning accuracy are used by this method. Trajectory Clustering with Ensemble Learning (TCEL) is proposed to overcome this problem. In this, Reverse Path nearby Cluster (R-PNC) query is used for effective path selection. Spatial datasets are handled using a two step process. Set of micro-clusters are maintained in the first step. Based on the input data, this micro clusters are continuously updated. Infinite data sources are compressed into a finite data set using Micro-clusters. More trajectory information can be stored using this finite dataset. In the second stage, ensemble learning is used to convert this micro-cluster into a macro-clusters of trajectories. Reverse the top k –RPNC. Based on their highest distribution they are stored and they are scanned to minimum from maximum. Improved Weight based Grey Wolf Optimization Algorithm (IWGWOA) is used to compute these values. The proposed system is implemented in MATLAB. The evaluation parameters like Normalized Mutual Information (NMI) and Rand Index (RI) are utilized for performance evaluation of proposed model.
Keywords: Spatial Networks, Trajectory Clustering with Ensemble Learning (TCEL), Prediction of Location, Improved Weight based Grey Wolf Optimization Algorithm (IWGWOA), Reverse Path Nearby Cluster (RPNC)query.