Automated recognition of robotic manipulation failures in high-throughput biodosimetry tool

Authors:
Youhua Chen;Hongliang Wang;Jian Zhang;Guy Garty;Nabil Simaan;Y. Lawrence Yao;David J. Brenner
Affiliations:
Department of Mechanical Engineering, Columbia University, New York, NY, USA;Department of Mechanical Engineering, Columbia University, New York, NY, USA;Department of Mechanical Engineering, Columbia University, New York, NY, USA;Center for Radiological Research, Columbia University, New York, NY, USA;Department of Mechanical Engineering, Columbia University, New York, NY, USA;Department of Mechanical Engineering, Columbia University, New York, NY, USA;Center for Radiological Research, Columbia University, New York, NY, USA
Venue:
Expert Systems with Applications: An International Journal
Year:
2012

Citing 8
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multicategory Classification by Support Vector Machines

Computational Optimization and Applications - Special issue on computational optimization—a tribute to Olvi Mangasarian, part I
PCA versus LDA

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Choosing Multiple Parameters for Support Vector Machines

Machine Learning
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Identification of contributing variables using kernel-based discriminant modeling and reconstruction

Expert Systems with Applications: An International Journal
Adding diagnostics to intelligent robot systems

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems

Quantified Score

Hi-index	12.05

Visualization

Abstract

A completely automated, high-throughput biodosimetry workstation has been developed by the Center for Minimally Invasive Radiation Biodosimetry at Columbia University over the past few years. To process patients' blood samples safely and reliably presents a significant challenge in the development of this biodosimetry tool. In this paper, automated failure recognition methods of robotic manipulation of capillary tubes based on a torque/force sensor are described. The characteristic features of sampled raw signals are extracted through data preprocessing. The 12-dimensional (12D) feature space is projected onto a two-dimensional (2D) feature plane by the optimized Principal Component Analysis (PCA) and Fisher Discrimination Analysis (FDA) feature extraction functions. For the three-class manipulation failure problem in the cell harvesting module, FDA yields better separability index than that of PCA and produces well separated classes. Three classification methods, Support Vector Machine (SVM), Fisher Linear Discrimination (FLD) and Quadratic Discrimination Analysis (QDA), are employed for real-time recognition. Considering the trade-off between error rate and computation cost, SVM achieves the best overall performance.