scholarly journals An Improved High-Density Sub Trajectory Clustering Algorithm

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 46041-46054
Author(s):  
Xiaoming Liu ◽  
Luxi Dong ◽  
Chunlin Shang ◽  
Xiangda Wei
Keyword(s):  
Clustering Algorithm ◽  
High Density ◽  
Trajectory Clustering

Optimized Video Tracking for Automated Vehicle Turning Movement Counts

2017 ◽  
Vol 2645 (1) ◽  
pp. 104-112
Author(s):  
François Bélisle ◽  
Nicolas Saunier ◽  
Guillaume-Alexandre Bilodeau ◽  
Sebastien le Digabel
Keyword(s):  
Case Studies ◽  
Traffic Engineering ◽  
Clustering Algorithm ◽  
Video Tracking ◽  
Video Data ◽  
Road User ◽  
Generalization Error ◽  
Trajectory Clustering ◽  
Peak Period ◽  
Data Set

This paper proposes a new method for automatically counting vehicle turning movements based on video tracking, expanding on previous work on optimization of parameters for road user trajectory extraction and on automated trajectory clustering. The counting method is composed of three main steps: an automated tracker that extracts vehicle trajectories from video data, an automated trajectory clustering algorithm, and an optimization algorithm. The proposed method was applied to obtain turning movement counts in three typical traffic engineering case studies in Canada representing industry-type conditions. These exhibited varying levels of tracking difficulty, ranging from a single-lane off-ramp to a six-movement intersection with a stop and a right-turn channel. Because of a limitation of the data set, giving flows per movement and not per lane, all sites were chosen with a single lane per movement. The 3-h morning peak period was used in the case studies. The results show an average weighted generalization error of 12% for more than 3,700 vehicles automatically analyzed for more than 8 h of video, ranging from 9.5% to 19.5%. The generalization error is on average 8.6% (and as low as 6.0% per movement) for the 3,084 uninterrupted vehicles that are in plain view of the camera. This paper describes in detail the methodology used and discusses the factors that affect counting performance and how to improve counting accuracy in further research.

scholarly journals Automatic spike sorting for high-density microelectrode arrays

2018 ◽  
Vol 120 (6) ◽  
pp. 3155-3171 ◽  
Author(s):  
Roland Diggelmann ◽  
Michele Fiscella ◽  
Andreas Hierlemann ◽  
Felix Franke
Keyword(s):  
Principal Component Analysis ◽  
Clustering Algorithm ◽  
State Of The Art ◽  
Microelectrode Arrays ◽  
Principal Component ◽  
Component Analysis ◽  
High Density ◽  
Sorting Algorithm ◽  
Spike Sorting ◽  
Recording Electrodes

High-density microelectrode arrays can be used to record extracellular action potentials from hundreds to thousands of neurons simultaneously. Efficient spike sorters must be developed to cope with such large data volumes. Most existing spike sorting methods for single electrodes or small multielectrodes, however, suffer from the “curse of dimensionality” and cannot be directly applied to recordings with hundreds of electrodes. This holds particularly true for the standard reference spike sorting algorithm, principal component analysis-based feature extraction, followed by k-means or expectation maximization clustering, against which most spike sorters are evaluated. We present a spike sorting algorithm that circumvents the dimensionality problem by sorting local groups of electrodes independently with classical spike sorting approaches. It is scalable to any number of recording electrodes and well suited for parallel computing. The combination of data prewhitening before the principal component analysis-based extraction and a parameter-free clustering algorithm obviated the need for parameter adjustments. We evaluated its performance using surrogate data in which we systematically varied spike amplitudes and spike rates and that were generated by inserting template spikes into the voltage traces of real recordings. In a direct comparison, our algorithm could compete with existing state-of-the-art spike sorters in terms of sensitivity and precision, while parameter adjustment or manual cluster curation was not required. NEW & NOTEWORTHY We present an automatic spike sorting algorithm that combines three strategies to scale classical spike sorting techniques for high-density microelectrode arrays: 1) splitting the recording electrodes into small groups and sorting them independently; 2) clustering a subset of spikes and classifying the rest to limit computation time; and 3) prewhitening the spike waveforms to enable the use of parameter-free clustering. Finally, we combined these strategies into an automatic spike sorter that is competitive with state-of-the-art spike sorters.

scholarly journals Extraction of Revolving Channels of Drifters around Mesoscale Eddy Centers Based on Spatiotemporal Trajectory Clustering

2019 ◽  
Vol 36 (9) ◽  
pp. 1903-1916
Author(s):  
Chunyong Ma ◽  
Siqing Li ◽  
Yang Yang ◽  
Jie Yang ◽  
Ge Chen
Keyword(s):  
Clustering Algorithm ◽  
Spatial Clustering ◽  
Mesoscale Eddy ◽  
Mesoscale Eddies ◽  
Trajectory Clustering ◽  
Satellite Altimeter ◽  
Principal Mode ◽  
In Situ Data ◽  
Anticyclonic Eddies

The global oceanic transports of energy, plankton, and other tracers by mesoscale eddies can be estimated by combining satellite altimetry and in situ data. However, the revolving channels of particles entrained by mesoscale eddies, which could help explain the dynamic process of eddies entraining materials, are still unknown. In this study, satellite altimeter and drifter data from 1993 to 2016 are adopted, and the normalized trajectory clustering algorithm (N-TRACLUS) is proposed to extract the revolving channels of drifters. First, the trajectories of drifters are normalized and clustered by using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. Next, the revolving channels of drifters around the eddy center are extracted. The ring or arc pattern in the middle of a normalized eddy appears when drifters are uninterruptedly entrained by eddies for more than 30 days. Moreover, the revolving channels of drifters in cyclonic eddies are relatively closer to the eddy center than those in anticyclonic eddies. These revolving channels suggest the principal mode of materials’ continuous motion processes that are inside eddies.

An efficient trajectory-clustering algorithm based on an index tree

2011 ◽  
Vol 34 (7) ◽  
pp. 850-861 ◽  
Author(s):  
Guan Yuan ◽  
Shixiong Xia ◽  
Lei Zhang ◽  
Yong Zhou ◽  
Cheng Ji
Keyword(s):  
Radio Frequency Identification ◽  
Clustering Algorithm ◽  
Real Data ◽  
Structural Similarity ◽  
Location Based Services ◽  
Similarity Function ◽  
Data Sets ◽  
Trajectory Clustering ◽  
Trajectory Data ◽  
Index Tree

With the development of location-based services, such as the Global Positioning System and Radio Frequency Identification, a great deal of trajectory data can be collected. Therefore, how to mine knowledge from these data has become an attractive topic. In this paper, we propose an efficient trajectory-clustering algorithm based on an index tree. Firstly, an index tree is proposed to store trajectories and their similarity matrix, with which trajectories can be retrieved efficiently; secondly, a new conception of trajectory structure is introduced to analyse both the internal and external features of trajectories; then, trajectories are partitioned into trajectory segments according to their corners; furthermore, the similarity between every trajectory segment pairs is compared by presenting the structural similarity function; finally, trajectory segments are grouped into different clusters according to their location in the different levels of the index tree. Experimental results on real data sets demonstrate not only the efficiency and effectiveness of our algorithm, but also the great flexibility that feature sensitivity can be adjusted by different parameters, and the cluster results are more practically significant.

A spatial-temporal trajectory clustering algorithm for eye fixations identification

2016 ◽  
Vol 20 (2) ◽  
pp. 377-393
Author(s):  
Mingxin Yu ◽  
Yingzi Lin ◽  
Jeffrey Breugelmans ◽  
Xiangzhou Wang ◽  
Yu Wang ◽  
...  
Keyword(s):  
Clustering Algorithm ◽  
Trajectory Clustering ◽  
Eye Fixations ◽  
Temporal Trajectory

Trajectory Clustering by Sampling and Density

2014 ◽  
Vol 48 (6) ◽  
pp. 74-85 ◽  
Author(s):  
Jiacai Pan ◽  
Qingshan Jiang ◽  
Zheping Shao
Keyword(s):  
Traffic Flow ◽  
Clustering Algorithm ◽  
Moving Objects ◽  
Distance Measure ◽  
Classical Method ◽  
Trajectory Clustering ◽  
Trajectory Data ◽  
Density Based Clustering ◽  
Clustering Quality ◽  
Parameter Values

AbstractThe trajectory data of moving objects contain huge amounts of information pertaining to traffic flow. It is incredibly important to extract valuable knowledge from this particular kind of data. Trajectory clustering is one of the most widely used approaches to complete this extraction. However, the current practice of trajectory clustering always groups similar subtrajectories that are partitioned from the trajectories; these methods would thus lose important information of the trajectory as a whole. To deal with this problem, this paper introduces a new trajectory-clustering algorithm based on sampling and density, which groups similar traffic movement tracks (car, ship, airplane, etc.) for further analysis of the characteristics of traffic flow. In particular, this paper proposes a novel technique of measuring distances between trajectories using point sampling. This distance measure does not divide the trajectory and thus conserves the integrated knowledge of these trajectories. This trajectory clustering approach is a new adaptation of a density-based clustering algorithm to the trajectories of moving objects. This paper then adopts the entropy theory as the heuristic for selecting the parameter values of this algorithm and the sum of the squared error method for measuring the clustering quality. Experiments on real ship trajectory data have shown that this algorithm is superior to the classical method TRACLUSS in the run time and that this method works well in discovering traffic flow patterns.

Sign in / Sign up

Export Citation Format

Share Document