Time-Series Data Analysis Using Sliding Window Based SVD for Motion Evaluation

2017 ◽  
Vol 21 (7) ◽  
pp. 1240-1250
Author(s):  
Yinlai Jiang ◽  
Isao Hayashi ◽  
Shuoyu Wang ◽  
Kenji Ishida ◽  
◽  
...  
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Sliding Window ◽  
Singular Values ◽  
Singular Value ◽  
Series Data ◽  
Singular Vectors ◽  
Walking Difficulty ◽  
The Right ◽  
Value Decomposition

A method based on singular value decomposition (SVD) is proposed for extracting features from motion time-series data observed with various sensing systems. Matrices consisting of the sliding window (SW) subsets of time-series data are decomposed, yielding singular vectors as the patterns of the motion, and the singular values as a scalar, by which the corresponding singular vectors describe the matrices.The sliding window based singular value decomposition was applied to analyze acceleration during walking. Three levels of walking difficulty were simulated by restricting the right knee joint in the measurement. The accelerations of the middles of the shanks and the back of the waist were measured and normalized before the SW-SVD was performed.The results showed that the first singular values inferred from the acceleration data of the restricted side (the right shank) significantly related to the increase of the restriction among all the subjects while there were no common trends in the singular values of the left shank and the waist. The SW-SVD was suggested to be a reliable method to evaluate walking disability. Furthermore, a 2D visualization tool is proposed to provide intuitive information about walking difficulty which can be used in walking rehabilitation to monitor recovery.

Acquisition of Embodied Knowledge on Gesture Motion by Singular Value Decomposition

2011 ◽  
Vol 15 (8) ◽  
pp. 1011-1018 ◽  
Author(s):  
Isao Hayashi ◽  
◽  
Yinlai Jiang ◽  
Shuoyu Wang ◽  
Keyword(s):  
Time Series ◽  
Singular Value Decomposition ◽  
Time Series Data ◽  
Singular Spectrum Analysis ◽  
Singular Value ◽  
Series Data ◽  
Embodied Knowledge ◽  
Interval Time Series ◽  
Nonverbal Information ◽  
Value Decomposition

Communication is classified in terms of verbal and nonverbal information. We discuss an acquisition method of knowledge from nonverbal information. In particular, a gesture is an efficient form of nonverbal communication as well as in verbal ways, and we formulate here a method that measures similarity and estimation between gestures. A gesture includes human embodied knowledge, and therefore the visible bodily actions can communicate particular messages. However, we have infinite patterns for gesture, determined by personality. Recently, the singular spectrum analysis method is utilized as an attractive method. In this paper, we propose a new method for acquiring embodied knowledge from time-series data on gestures using singular value decomposition. The motion behavior is categorized into several clusters with similarity and estimation between interval time-series data. We discuss the usefulness of the proposed method using an example of gesture motion.

Development of A Pharmaceutical Early Warning Scoring Model for Cardiac Arrest Using Deep Learning: Retrospective Cohort Study (Preprint)

2020 ◽  
Author(s):  
Hsiao-Ko Chang ◽  
Hui-Chih Wang ◽  
Chih-Fen Huang ◽  
Feipei Lai
Keyword(s):  
Time Series ◽  
Cardiac Arrest ◽  
Early Warning ◽  
Time Series Data ◽  
Predictive Accuracy ◽  
Vital Signs ◽  
Sliding Window ◽  
Early Warning Score ◽  
Series Data ◽  
Dynamic Time

BACKGROUND In most of Taiwan’s medical institutions, congestion is a serious problem for emergency departments. Due to a lack of beds, patients spend more time in emergency retention zones, which make it difficult to detect cardiac arrest (CA). OBJECTIVE We seek to develop a pharmaceutical early warning model to predict cardiac arrest in emergency departments via drug classification and medical expert suggestion. METHODS We propose a new early warning score model for detecting cardiac arrest via pharmaceutical classification and by using a sliding window; we apply learning-based algorithms to time-series data for a Pharmaceutical Early Warning Scoring Model (PEWSM). By treating pharmaceutical features as a dynamic time-series factor for cardiopulmonary resuscitation (CPR) patients, we increase sensitivity, reduce false alarm rates and mortality, and increase the model’s accuracy. To evaluate the proposed model we use the area under the receiver operating characteristic curve (AUROC). RESULTS Four important findings are as follows: (1) We identify the most important drug predictors: bits, and replenishers and regulators of water and electrolytes. The best AUROC of bits is 85%; that of replenishers and regulators of water and electrolytes is 86%. These two features are the most influential of the drug features in the task. (2) We verify feature selection, in which accounting for drugs improve the accuracy: In Task 1, the best AUROC of vital signs is 77%, and that of all features is 86%. In Task 2, the best AUROC of all features is 85%, which demonstrates that thus accounting for the drugs significantly affects prediction. (3) We use a better model: For traditional machine learning, this study adds a new AI technology: the long short-term memory (LSTM) model with the best time-series accuracy, comparable to the traditional random forest (RF) model; the two AUROC measures are 85%. (4) We determine whether the event can be predicted beforehand: The best classifier is still an RF model, in which the observational starting time is 4 hours before the CPR event. Although the accuracy is impaired, the predictive accuracy still reaches 70%. Therefore, we believe that CPR events can be predicted four hours before the event. CONCLUSIONS This paper uses a sliding window to account for dynamic time-series data consisting of the patient’s vital signs and drug injections. In a comparison with NEWS, we improve predictive accuracy via feature selection, which includes drugs as features. In addition, LSTM yields better performance with time-series data. The proposed PEWSM, which offers 4-hour predictions, is better than the National Early Warning Score (NEWS) in the literature. This also confirms that the doctor’s heuristic rules are consistent with the results found by machine learning algorithms.

scholarly journals Differentially Private Autocorrelation Time-Series Data Publishing Based on Sliding Window

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jing Zhao ◽  
Shubo Liu ◽  
Xingxing Xiong ◽  
Zhaohui Cai
Keyword(s):  
Time Series ◽  
Privacy Protection ◽  
Large Scale ◽  
Differential Privacy ◽  
Time Series Data ◽  
Sliding Window ◽  
Data Publishing ◽  
Series Data ◽  
Data Publication ◽  
Autocorrelation Time

Privacy protection is one of the major obstacles for data sharing. Time-series data have the characteristics of autocorrelation, continuity, and large scale. Current research on time-series data publication mainly ignores the correlation of time-series data and the lack of privacy protection. In this paper, we study the problem of correlated time-series data publication and propose a sliding window-based autocorrelation time-series data publication algorithm, called SW-ATS. Instead of using global sensitivity in the traditional differential privacy mechanisms, we proposed periodic sensitivity to provide a stronger degree of privacy guarantee. SW-ATS introduces a sliding window mechanism, with the correlation between the noise-adding sequence and the original time-series data guaranteed by sequence indistinguishability, to protect the privacy of the latest data. We prove that SW-ATS satisfies ε-differential privacy. Compared with the state-of-the-art algorithm, SW-ATS is superior in reducing the error rate of MAE which is about 25%, improving the utility of data, and providing stronger privacy protection.

scholarly journals A Predictive Meta Model for Forecasting Stock Price using Time Series Data

2021 ◽  
Vol 10 (1) ◽  
pp. 345-356
Keyword(s):  
Time Series ◽  
Stock Market ◽  
Stock Price ◽  
Time Series Data ◽  
Stock Exchange ◽  
Series Data ◽  
Meta Model ◽  
Price Range ◽  
Stock Traders ◽  
The Right

Stock market prediction through time series is a challenging as well as an interesting research areafor the finance domain, through which stock traders and investors can find the right time to buy/sell stocks. However, various algorithms have been developed based on the statistical approach to forecast the time series for stock data, but due to the volatile nature and different price ranges of the stock price one particular algorithm is not enough to visualize the prediction. This study aims to propose a model that will choose the preeminent algorithm for that particular company’s stock that can forecastthe time series with minimal error. This model can assist a trader/investor with or without expertise in the stock market to achieve profitable investments. We have used the Stock data from Stock Exchange Bangladesh, which covers 300+ companies to train and test our system. We have classified those companies based on the stock price range and then applied our model to identify which algorithm suites most for a particular range of stock price. Comparative forecasting results of all algorithms in diverse price ranges have been presented to show the usefulness of this Predictive Meta Model

scholarly journals Efficient time series data classification using sliding window technique based improved association rule mining with enhanced support vector machine

2018 ◽  
Vol 7 (3.3) ◽  
pp. 218 ◽  
Author(s):  
D Senthil ◽  
G Suseendran
Keyword(s):  
Time Series ◽  
Support Vector Machine ◽  
Association Rule ◽  
Association Rule Mining ◽  
Time Series Data ◽  
Sliding Window ◽  
Series Data ◽  
Support Vector ◽  
Rule Mining ◽  
Window Technique

Time series analysis is an important and complex problem in machine learning and statistics. In the existing system, Support Vector Machine (SVM) and Association Rule Mining (ARM) is introduced to implement the time series data. However it has issues with lower accuracy and higher time complexity. Also it has issue with optimal rules discovery and segmentation on time series data. To avoid the above mentioned issues, in the proposed research Sliding Window Technique based Improved ARM with Enhanced SVM (SWT-IARM with ESVM) is proposed. In the proposed system, the preprocessing is performed using Modified K-Means Clustering (MKMC). The indexing process is done by using R-tree which is used to provide faster results. Segmentation is performed by using SWT and it reduces the cost complexity by optimal segments. Then IARM is applied on efficient rule discovery process by generating the most frequent rules. By using ESVM classification approach, the rules are classified more accurately.  

INTERPRETATION OF SINGULAR SPECTRUM ANALYSIS AS COMPLETE EIGENFILTER DECOMPOSITION

2012 ◽  
Vol 04 (04) ◽  
pp. 1250023 ◽  
Author(s):  
KENJI KUME
Keyword(s):  
Time Series ◽  
Spectrum Analysis ◽  
Singular Spectrum Analysis ◽  
Singular Value ◽  
Original Time Series ◽  
Singular Vectors ◽  
Singular Spectrum ◽  
Original Time ◽  
Value Decomposition ◽  
Insight Into

Singular spectrum analysis is a nonparametric and adaptive spectral decomposition of a time series. This method consists of the singular value decomposition for the trajectory matrix constructed from the original time series, followed with the subsequent reconstruction of the decomposed series. In the present paper, we show that these procedures can be viewed simply as complete eigenfilter decomposition of the time series. The eigenfilters are constructed from the singular vectors of the trajectory matrix and the completeness of the singular vectors ensure the completeness of the eigenfilters. The present interpretation gives new insight into the singular spectrum analysis.

scholarly journals Modified singular spectrum analysis in identifying rainfall trend over peninsular Malaysia

2019 ◽  
Vol 15 (1) ◽  
pp. 283
Author(s):  
S.M. Shaharudin ◽  
N. Ahmad ◽  
N.H. Zainuddin
Keyword(s):  
Time Series ◽  
Spectrum Analysis ◽  
Time Series Data ◽  
Singular Spectrum Analysis ◽  
Singular Values ◽  
Peninsular Malaysia ◽  
Series Data ◽  
Rainfall Time Series ◽  
Singular Spectrum ◽  
Torrential Rainfall

<p>Identifying the local time scale of the torrential rainfall pattern through Singular Spectrum Analysis (SSA) is useful to separate the trend and noise components. However, SSA poses two main issues which are torrential rainfall time series data have coinciding singular values and the leading components from eigenvector obtained from the decomposing time series matrix are usually assesed by graphical inference lacking in a specific statistical measure. In consequences to both issues, the extracted trend from SSA tended to flatten out and did not show any distinct pattern.  This problem was approached in two ways. First, an Iterative Oblique SSA (Iterative O-SSA) was presented to make adjustment to the singular values data. Second, a measure was introduced to group the decomposed eigenvector based on Robust Sparse K-means (RSK-Means). As the results, the extracted trend using modification of SSA appeared to fit the original time series and looked more flexible compared to SSA.</p>

Sign in / Sign up

Export Citation Format

Share Document