SOCIAL SECURITY AND SAVING: NEW TIME SERIES EVIDENCE

1996 ◽  
Vol 49 (2) ◽  
pp. 151-164
Author(s):  
MARTIN FELDSTEIN
Keyword(s):  
Time Series ◽  
Social Security ◽  
New Time

Social Security and Private Saving: New Time-Series Evidence

1982 ◽  
Vol 90 (3) ◽  
pp. 606-629 ◽  
Author(s):  
Dean R. Leimer ◽  
Selig D. Lesnoy
Keyword(s):  
Time Series ◽  
Social Security ◽  
Private Saving ◽  
New Time

Explaining Economic Growth in China: New Time Series and Econometric Tests of Various Models

2020 ◽  
Vol Prépublication (0) ◽  
pp. I79-XXXIV
Author(s):  
Zhiming Long ◽  
Rémy Herrera ◽  
Weinan Ding
Keyword(s):  
Economic Growth ◽  
Time Series ◽  
Econometric Tests ◽  
New Time

A New Time Series Prediction Method Based on LS-SVR and AGO

2013 ◽  
Vol 5 (6) ◽  
pp. 542-551
Author(s):  
Guo Yangming ◽  
Zhang Lu ◽  
Li Xiaolei ◽  
Ran Congbao ◽  
Ma Jiezhong
Keyword(s):  
Time Series ◽  
Time Series Prediction ◽  
Prediction Method ◽  
New Time

scholarly journals Edge4TSC: Binary Distribution Tree-Enabled Time Series Classification in Edge Environment

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1908
Author(s):  
Chao Ma ◽  
Xiaochuan Shi ◽  
Wei Li ◽  
Weiping Zhu
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Time Series Data ◽  
Series Representation ◽  
Series Data ◽  
Feature Engineering ◽  
Time Series Classification ◽  
Binary Distribution ◽  
New Time

In the past decade, time series data have been generated from various fields at a rapid speed, which offers a huge opportunity for mining valuable knowledge. As a typical task of time series mining, Time Series Classification (TSC) has attracted lots of attention from both researchers and domain experts due to its broad applications ranging from human activity recognition to smart city governance. Specifically, there is an increasing requirement for performing classification tasks on diverse types of time series data in a timely manner without costly hand-crafting feature engineering. Therefore, in this paper, we propose a framework named Edge4TSC that allows time series to be processed in the edge environment, so that the classification results can be instantly returned to the end-users. Meanwhile, to get rid of the costly hand-crafting feature engineering process, deep learning techniques are applied for automatic feature extraction, which shows competitive or even superior performance compared to state-of-the-art TSC solutions. However, because time series presents complex patterns, even deep learning models are not capable of achieving satisfactory classification accuracy, which motivated us to explore new time series representation methods to help classifiers further improve the classification accuracy. In the proposed framework Edge4TSC, by building the binary distribution tree, a new time series representation method was designed for addressing the classification accuracy concern in TSC tasks. By conducting comprehensive experiments on six challenging time series datasets in the edge environment, the potential of the proposed framework for its generalization ability and classification accuracy improvement is firmly validated with a number of helpful insights.

scholarly journals Investigation of GPS draconitic year effect on GPS time series of eliminated eclipsing GPS satellite data

2016 ◽  
Vol 6 (1) ◽  
Author(s):  
A. Allahverdi-zadeh ◽  
J. Asgari ◽  
A.R. Amiri-Simkooei
Keyword(s):  
Time Series ◽  
Original Position ◽  
Year Effect ◽  
The Earth ◽  
Gps Satellites ◽  
Position Time Series ◽  
The Difference ◽  
Original Time ◽  
Almost All ◽  
New Time

AbstractGPS draconitic signal (351.6 ± 0.2 days) and its higher harmonics are observed at almost all IGS products such as position time series of IGS permanent stations. Orbital error and multipath are known as two possible sources of these signals. The effect of Earth shadow crossing of GPS satellites is another suspect for this signal. Up to now there is no serious attempt to investigate this dependence. AMATLAB toolbox is developed and used to determine the satellites located at the earth shadow. RINEX observation files and precise ephemeris are imported to the toolbox and a cylindrical model is used to detect the shadow regions. Data of these satellites were removed from the RINEX observation files of three IGS permanent stations (GRAZ,ONSAandWSRT) and new RINEX observation fileswere created. The time span of these data is about 11 years. The new and original fileswere then processed using precise point positioning (PPP) method to determine position time series, for further analysis. Both the original and new time series were analyzed using the least squares harmonic estimation (LS-HE) in the following steps. The 1st step is the validation of the draconitic harmonics signature in the original position time series of the three stations. The 2nd step does the same for the new time series. It confirms that the power spectrum at the draconitic signals decreases to some extent for the new time series. The difference between the original and new time series (difference between all three position quantity (X, Y and Z)) is then analyzed in the 3rd step. Signature of the draconitic harmonics is also observed to the differences. The results represent that all eight harmonics of GPS draconitic period do exist at the residuals and mainly they decrease. All of the three stations were then processed together using the multivariate LS-HE method. At the 4th step, the difference of the spectral values between the original time series and new times serieswere analyzed. Decreasing of the spectral values at most harmonics (e.g. 1st, 2nd, 4th, 6th, 7th and 8th) represents the effect of removing satellite observations at shadow of the earth on draconitic harmonics. At least, five harmonics among seven shows the amelioration of results (draconitic error reduction) after removing the earth shadowed data from RINEX raw data. The results show that the draconitic year’s component of data is in part due to eclipsing satellites.

Sign in / Sign up

Export Citation Format

Share Document