TrajPy: empowering feature engineering for trajectory analysis across domains
Trajectories, sequentially measured quantities that form a path, are an important presence in many different fields, from hadronic beams in physics to electrocardiograms in medicine. Trajectory anal-ysis requires the quantification and classification of curves either using statistical descriptors or physics-based features. To date, there is no extensive and user-friendly package for trajectory anal-ysis available, despite its importance and potential application across domains. We developed a free open-source python package named TrajPy as a complementary tool to empower trajectory analysis. The package showcases a friendly graphic user interface and provides a set of physical descriptors that help characterizing these intricate structures. In combina-tion with image analysis, it was already successfully applied to the study of mitochondrial motility in neuroblastoma cell lines and to the analysis of in silico models for cell migration. The TrajPy package was developed in Python 3 and released under the GNU GPL-3 license. Easy installation is available through PyPi and the development source code can be found in the repository https://github.com/ocbe-uio/TrajPy/. The package release is automatically archived under the DOI 10.5281/zenodo.3656044.
Code (1)
Tasks
Feature EngineeringSimilar Papers 제목 키워드 기반
Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models
Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cogn…
Autonomous DrivingDecoderMambaPrompt Engineering+1Empowering Machines to Think Like Chemists: Unveiling Molecular Structure-Polarity Relationships with Hierarchical Symbolic Regression
Thin-layer chromatography (TLC) is a crucial technique in molecular polarity analysis. Despite its importance, the interpretability of predictive models for TLC, especially those driven by artificial intelligence, remain…
Feature EngineeringregressionSymbolic RegressionEmpowering the trustworthiness of ML-based critical systems through engineering activities
This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions. We start from the fundamental principle…
Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking
Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to ext…
Contrastive LearningMulti-Object TrackingObject TrackingOnline Multi-Object TrackingAccelerating scientific discovery with the common task framework
Machine learning (ML) and artificial intelligence (AI) algorithms are transforming and empowering the characterization and control of dynamic systems in the engineering, physical, and biological sciences. These emerging …
Speech Recognition