Comparative study on the effectiveness of trajectory similarity measurement algorithms

2021 ◽  
Author(s):  
Yanfu Wu
Keyword(s):  
Comparative Study ◽  
Similarity Measurement ◽  
Trajectory Similarity

HERMAS

2021 ◽  
Vol 5 (3) ◽  
pp. 1-21
Author(s):  
Yiwei Song ◽  
Dongzhe Jiang ◽  
Yunhuai Liu ◽  
Zhou Qin ◽  
Chang Tan ◽  
...  
Keyword(s):  
Large Scale ◽  
Human Mobility ◽  
Representation Learning ◽  
User Profiling ◽  
Similarity Measurement ◽  
Learning Framework ◽  
Computation Efficiency ◽  
Trajectory Similarity ◽  
Spatio Temporal ◽  
Embedding Performance

Efficient representations for spatio-temporal cellular Signaling Data (SD) are essential for many human mobility applications. Traditional representation methods are mainly designed for GPS data with high spatio-temporal continuity, and thus will suffer from poor embedding performance due to the unique Ping Pong Effect in SD. To address this issue, we explore the opportunity offered by a large number of human mobility traces and mine the inherent neighboring tower connection patterns. More specifically, we design HERMAS, a novel representation learning framework for large-scale cellular SD with three steps: (1) extract rich context information in each trajectory, adding neighboring tower information as extra knowledge in each mobility observation; (2) design a sequence encoding model to aggregate the embedding of each observation; (3) obtain the embedding for a trajectory. We evaluate the performance of HERMAS based on two human mobility applications, i.e. trajectory similarity measurement and user profiling. We conduct evaluations based on a 30-day SD dataset with 130,612 users and 2,369,267 moving trajectories. Experimental results show that (1) for the trajectory similarity measurement application, HERMAS improves the Hitting Rate (HR@10) from 15.2% to 39.2%; (2) for the user profiling application, HERMAS improves the F1-score for around 9%. More importantly, HERMAS significantly improves the computation efficiency by over 30x.

A comparative Study on Similarity Measurement in Noisy Voice Speaker Identification

2016 ◽  
Vol 1 (3) ◽  
pp. 590
Author(s):  
Inggih Permana
Keyword(s):  
Comparative Study ◽  
Speaker Identification ◽  
Measurement Techniques ◽  
Experimental Result ◽  
Similarity Measurement ◽  
Frequency Of Occurrence ◽  
Mean Square ◽  
Least Mean Square ◽  
Vector Sum ◽  
The Voice

One of important part on speaker identification is the measurement of sound similarity. This study has compared two of the similarity measurement techniques in the noisy voice. First technique is done by using smallest vector sum of pairs and second technique is done by using frequency of occurrence of smallest vector pairs. Noise in the voice can reduce accuracy of speaker identification significantly. To overcome this problem, the two of similarity measurement was combined with Least Mean Square (LMS) for remove noise. Results of the experiments showed that the use of LMS can improve the accuracy of speaker identification at the two of similarity measurement techniques. Second technique produces better accuracy than first technique. Experimental result also showed improvement of LMS learning rate can improve the accuracy of speaker identification.

Sign in / Sign up

Export Citation Format

Share Document