scholarly journals Low-Rank and Sparse Recovery of Human Gait Data

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4525
Author(s):  
Kaveh Kamali ◽  
Ali Akbar Akbari ◽  
Christian Desrosiers ◽  
Alireza Akbarzadeh ◽  
Martin J.-D. Otis ◽  
...  
Keyword(s):  
Matrix Completion ◽  
Principal Component ◽  
Reconstruction Error ◽  
Human Motion ◽  
Optical Tracking ◽  
Training Data ◽  
Low Rank ◽  
Human Gait ◽  
Group Sparsity ◽  
Model Combining

Due to occlusion or detached markers, information can often be lost while capturing human motion with optical tracking systems. Based on three natural properties of human gait movement, this study presents two different approaches to recover corrupted motion data. These properties are used to define a reconstruction model combining low-rank matrix completion of the measured data with a group-sparsity prior on the marker trajectories mapped in the frequency domain. Unlike most existing approaches, the proposed methodology is fully unsupervised and does not need training data or kinematic information of the user. We evaluated our methods on four different gait datasets with various gap lengths and compared their performance with a state-of-the-art approach using principal component analysis (PCA). Our results showed recovering missing data more precisely, with a reduction of at least 2 mm in mean reconstruction error compared to the literature method. When a small number of marker trajectories is available, our findings showed a reduction of more than 14 mm for the mean reconstruction error compared to the literature approach.

scholarly journals Comparison Analysis of Gait Classification For Human Motion Identification Using Embedded Computer

2018 ◽  
Vol 8 (6) ◽  
pp. 5014
Author(s):  
Agung Nugroho Jati ◽  
Astri Novianty ◽  
Nanda Septiana ◽  
Leni Widia Nasution
Keyword(s):  
Support Vector Machine ◽  
Principal Component ◽  
Human Motion ◽  
Human Gait ◽  
Support Vector ◽  
Nearest Neighbour ◽  
Classification Methods ◽  
Comparison Analysis ◽  
Gait Classification ◽  
Embedded Computer

In this paper, it will be discussed about comparison between two kinds of classification methods in order to improve security system based of human gait. Gait is one of biometric methods which can be used to identify person. K-Nearest Neighbour has parallelly implemented with Support Vector Machine for classifying human gait in same basic system. Generally, system has been built using Histogram and Principal Component Analysis for gait detection and its feature extraction. Then, the result of the simulation showed that K-Nearest Neighbour is slower in processing and less accurate than Support Vector Machine in gait classification.

scholarly journals Predicting the effects of drug combinations using probabilistic matrix factorization

2021 ◽  
Author(s):  
Ron Nafshi ◽  
Timothy R Lezon
Keyword(s):  
Matrix Factorization ◽  
Partial Information ◽  
Matrix Completion ◽  
Drug Combinations ◽  
Training Data ◽  
Low Rank ◽  
Probabilistic Matrix Factorization ◽  
Low Rank Matrix Completion ◽  
The Individual ◽  
Synergistic Combinations

Drug development is costly and time-consuming, and developing novel practical strategies for creating more effective treatments is imperative. One possible solution is to prescribe drugs in combination. Synergistic drug combinations could allow lower doses of each constituent drug, reducing adverse reactions and drug resistance. However, it is not feasible to sufficiently test every combination of drugs for a given illness to determine promising synergistic combinations. Since there is a finite amount of time and resources available for finding synergistic combinations, a model that can identify synergistic combinations from a limited subset of all available combinations could accelerate development of therapeutics. By applying recommender algorithms, such as the low-rank matrix completion algorithm Probabilistic Matrix Factorization (PMF), it may be possible to identify synergistic combinations from partial information of the drug interactions. Here, we use PMF to predict the efficacy of two-drug combinations using the NCI ALMANAC, a robust collection of pairwise drug combinations of 104 FDA-approved anticancer drugs against 60 common cancer cell lines. We find that PMF is able predict drug combination efficacy with high accuracy from a limited set of combinations and is robust to changes in the individual training data. Moreover, we propose a new PMF-guided experimental design to detect all synergistic combinations without testing every combination.

scholarly journals Low-Rank Approximations of Nonseparable Panel Models

2021 ◽  
Author(s):  
Iván Fernández-Val ◽  
Hugo Freeman ◽  
Martin Weidner
Keyword(s):  
Voter Turnout ◽  
Matrix Completion ◽  
Principal Component ◽  
Low Rank ◽  
Estimation Methods ◽  
Difference In Differences ◽  
Panel Models ◽  
Large Panels ◽  
Low Rank Approximations ◽  
The U.S

Abstract We provide estimation methods for nonseparable panel models based on low-rank factor structure approximations. The factor structures are estimated by matrix-completion methods to deal with the computational challenges of principal component analysis in the presence of missing data. We show that the resulting estimators are consistent in large panels, but suffer from approximation and shrinkage biases. We correct these biases using matching and difference-in-differences approaches. Numerical examples and an empirical application to the effect of election day registration on voter turnout in the U.S. illustrate the properties and usefulness of our methods.

Nonlinear Low-Rank Matrix Completion for Human Motion Recovery

2018 ◽  
Vol 27 (6) ◽  
pp. 3011-3024 ◽  
Author(s):  
Guiyu Xia ◽  
Huaijiang Sun ◽  
Beijia Chen ◽  
Qingshan Liu ◽  
Lei Feng ◽  
...  
Keyword(s):  
Matrix Completion ◽  
Human Motion ◽  
Low Rank ◽  
Motion Recovery ◽  
Rank Matrix ◽  
Low Rank Matrix Completion ◽  
Low Rank Matrix

scholarly journals Predicting the Effects of Drug Combinations Using Probabilistic Matrix Factorization

2021 ◽  
Vol 1 ◽  
Author(s):  
Ron Nafshi ◽  
Timothy R. Lezon
Keyword(s):  
Matrix Factorization ◽  
Partial Information ◽  
Matrix Completion ◽  
Drug Combinations ◽  
Training Data ◽  
Low Rank ◽  
Probabilistic Matrix Factorization ◽  
Low Rank Matrix Completion ◽  
The Individual ◽  
Synergistic Combinations

Drug development is costly and time-consuming, and developing novel practical strategies for creating more effective treatments is imperative. One possible solution is to prescribe drugs in combination. Synergistic drug combinations could allow lower doses of each constituent drug, reducing adverse reactions and drug resistance. However, it is not feasible to sufficiently test every combination of drugs for a given illness to determine promising synergistic combinations. Since there is a finite amount of time and resources available for finding synergistic combinations, a model that can identify synergistic combinations from a limited subset of all available combinations could accelerate development of therapeutics. By applying recommender algorithms, such as the low-rank matrix completion algorithm Probabilistic Matrix Factorization (PMF), it may be possible to identify synergistic combinations from partial information of the drug interactions. Here, we use PMF to predict the efficacy of two-drug combinations using the NCI ALMANAC, a robust collection of pairwise drug combinations of 104 FDA-approved anticancer drugs against 60 common cancer cell lines. We find that PMF is able predict drug combination efficacy with high accuracy from a limited set of combinations and is robust to changes in the individual training data. Moreover, we propose a new PMF-guided experimental design to detect all synergistic combinations without testing every combination.

scholarly journals Robust Principal Component Analysis-Based Infrared Small Target Detection

2019 ◽  
Vol 33 ◽  
pp. 9925-9926
Author(s):  
Qiwei Chen ◽  
Cheng Wu ◽  
Yiming Wang
Keyword(s):  
Iteration Process ◽  
Principal Component ◽  
Component Analysis ◽  
Low Rank ◽  
Small Target ◽  
Frame Sequence ◽  
Augmented Lagrange Multiplier ◽  
Small Targets ◽  
Infrared Small Target ◽  
Augmented Lagrange Multiplier Method

A method based on Robust Principle Component Analysis (RPCA) technique is proposed to detect small targets in infrared images. Using the low rank characteristic of background and the sparse characteristic of target, the observed image is regarded as the sum of a low-rank background matrix and a sparse outlier matrix, and then the decomposition is solved by the RPCA. The infrared small target is extracted from the single-frame image or multi-frame sequence. In order to get more efficient algorithm, the iteration process in the augmented Lagrange multiplier method is improved. The simulation results show that the method can detect out the small target precisely and efficiently.

scholarly journals Clipped Matrix Completion: A Remedy for Ceiling Effects

2019 ◽  
Vol 33 ◽  
pp. 5151-5158
Author(s):  
Takeshi Teshima ◽  
Miao Xu ◽  
Issei Sato ◽  
Masashi Sugiyama
Keyword(s):  
Matrix Completion ◽  
Low Rank ◽  
Trace Norm ◽  
Minimization Algorithm ◽  
Benchmark Data ◽  
Hinge Loss ◽  
Norm Minimization ◽  
Rank Matrix ◽  
Recovery Error ◽  
Low Rank Matrix

We consider the problem of recovering a low-rank matrix from its clipped observations. Clipping is conceivable in many scientific areas that obstructs statistical analyses. On the other hand, matrix completion (MC) methods can recover a low-rank matrix from various information deficits by using the principle of low-rank completion. However, the current theoretical guarantees for low-rank MC do not apply to clipped matrices, as the deficit depends on the underlying values. Therefore, the feasibility of clipped matrix completion (CMC) is not trivial. In this paper, we first provide a theoretical guarantee for the exact recovery of CMC by using a trace-norm minimization algorithm. Furthermore, we propose practical CMC algorithms by extending ordinary MC methods. Our extension is to use the squared hinge loss in place of the squared loss for reducing the penalty of overestimation on clipped entries. We also propose a novel regularization term tailored for CMC. It is a combination of two trace-norm terms, and we theoretically bound the recovery error under the regularization. We demonstrate the effectiveness of the proposed methods through experiments using both synthetic and benchmark data for recommendation systems.

Sign in / Sign up

Export Citation Format

Share Document