scholarly journals Extracting Features from Time Series

2018 ◽  
pp. 85-100 ◽  
Author(s):  
Christian Herff ◽  
Dean J. Krusienski
Keyword(s):  
Time Series ◽  
Feature Extraction ◽  
Clinical Data ◽  
Noise Filtering ◽  
Time Intervals ◽  
Time Points ◽  
Biomedical Systems ◽  
Patient Weight ◽  
Short Time

AbstractClinical data is often collected and processed as time series: a sequence of data indexed by successive time points. Such time series can be from sources that are sampled over short time intervals to represent continuous biophysical wave-(one word waveforms) forms such as the voltage measurements representing the electrocardiogram, to measurements that are sampled daily, weekly, yearly, etc. such as patient weight, blood triglyceride levels, etc. When analyzing clinical data or designing biomedical systems for measurements, interventions, or diagnostic aids, it is important to represent the information contained within such time series in a more compact or meaningful form (e.g., noise filtering), amenable to interpretation by a human or computer. This process is known as feature extraction. This chapter will discuss some fundamental techniques for extracting features from time series representing general forms of clinical data.

Introduction to Analysis Using Time Components

2010 ◽  
pp. 154-192
Author(s):  
Patricia Cerrito ◽  
John Cerrito
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Fixed Time ◽  
Analysis Time ◽  
Time Intervals ◽  
Time Points ◽  
Series Analysis ◽  
Time Component ◽  
Time Stamps ◽  
Insurance Data

The introduction of a time component requires the use of statistical methods that can utilize dependent data. The assumption of independence that is required for regression models is no longer applicable. In this section, we will work with time series analysis. Time series analysis requires that data are collected at discrete, fixed time intervals. Observational and insurance data contain time stamps as to the date of service. These time stamps are transactional in nature and do not occur at fixed time intervals. Therefore, the first step in such an analysis is to convert the transactional time points into fixed time intervals. We need to decide upon the interval: every minute, hour, day, week, month, year. The specific interval will depend upon the analysis to be performed. Once that is completed, the standard time series analysis methods can be used. As an example, we use the MEPS dataset for medications. We use the date of January 1 as time zero.

Alignment of time-resolved data from high throughput experiments

2016 ◽  
Vol 14 (06) ◽  
pp. 1650030
Author(s):  
Nada Abidi ◽  
Raimo Franke ◽  
Peter Findeisen ◽  
Frank Klawonn
Keyword(s):  
Time Series ◽  
High Throughput ◽  
Missing Values ◽  
Stable State ◽  
Series Data ◽  
Time Intervals ◽  
Initial Stimulus ◽  
Time Resolved ◽  
Time Points ◽  
High Throughput Experiments

To better understand the dynamics of the underlying processes in cells, it is necessary to take measurements over a time course. Modern high-throughput technologies are often used for this purpose to measure the behavior of cell products like metabolites, peptides, proteins, [Formula: see text]RNA or mRNA at different points in time. Compared to classical time series, the number of time points is usually very limited and the measurements are taken at irregular time intervals. The main reasons for this are the costs of the experiments and the fact that the dynamic behavior usually shows a strong reaction and fast changes shortly after a stimulus and then slowly converges to a certain stable state. Another reason might simply be missing values. It is common to repeat the experiments and to have replicates in order to carry out a more reliable analysis. The ideal assumptions that the initial stimulus really started exactly at the same time for all replicates and that the replicates are perfectly synchronized are seldom satisfied. Therefore, there is a need to first adjust or align the time-resolved data before further analysis is carried out. Dynamic time warping (DTW) is considered as one of the common alignment techniques for time series data with equidistant time points. In this paper, we modified the DTW algorithm so that it can align sequences with measurements at different, non-equidistant time points with large gaps in between. This type of data is usually known as time-resolved data characterized by irregular time intervals between measurements as well as non-identical time points for different replicates. This new algorithm can be easily used to align time-resolved data from high-throughput experiments and to come across existing problems such as time scarcity and existing noise in the measurements. We propose a modified method of DTW to adapt requirements imposed by time-resolved data by use of monotone cubic interpolation splines. Our presented approach provides a nonlinear alignment of two sequences that neither need to have equi-distant time points nor measurements at identical time points. The proposed method is evaluated with artificial as well as real data. The software is available as an R package tra (Time-Resolved data Alignment) which is freely available at: http://public.ostfalia.de/klawonn/tra.zip .

scholarly journals Construction of Master Recession Curve Using Genetic Algorithms

2012 ◽  
Vol 60 (1) ◽  
pp. 3-15 ◽  
Author(s):  
Miloš Gregor ◽  
Peter Malík
Keyword(s):  
Time Series ◽  
Genetic Algorithms ◽  
Measured Data ◽  
Time Intervals ◽  
Short Time Series ◽  
Recession Curve ◽  
Natural Time ◽  
Master Recession Curve ◽  
Different Types ◽  
Short Time

Construction of Master Recession Curve Using Genetic Algorithms The article describes a new methodology of using genetic algorithms to assemble a natural time series of discharge recession, from which a master recession curve can be interpreted both for streams and for springs. Presented approach can avoid obstacles such as limited time-series datasets, incomplete recessions or too many recessionary segments in many recession series, different time intervals of observations (daily or weekly frequencies). Short time-series intervals, imprecise or mistaken measurements and different types of datasets (averaged or directly measured data) are taken into account as well. Even rough measurements of discharges with inaccurate sensing range can be analysed, if sufficiently long observation is available. Complicated hydrograph shapes in the case of e.g. karstic springs (often caused by combination of laminar and turbulent discharge sub-regimes due to karst network settings) can be processed as well. Subsequent construction of master recession curve is much easier an offers better conditions for its interpretation. Presented algorithm was already implemented to a programme solution, completed on the user form.

Proposal of PV Output Estimate Method in Short Time Intervals

2016 ◽  
Vol 136 (12) ◽  
pp. 891-897 ◽  
Author(s):  
Katsuhiro Matsuda ◽  
Kazuhiro Misawa ◽  
Hirotaka Takahashi ◽  
Kenta Furukawa ◽  
Satoshi Uemura
Keyword(s):  
Time Intervals ◽  
Estimate Method ◽  
Short Time

EVALUATION OF SHORT TIME INTERVALS IN NORMAL AGING AND LATE-LIFE DEPRESSIONS

2020 ◽  
pp. 54-69
Author(s):  
Elena Yu. Balashova ◽  
◽  
Lika I. Mikeladze ◽  
Elena K. Kozlova ◽  
◽  
...  
Keyword(s):  
Late Life ◽  
Normal Aging ◽  
Time Intervals ◽  
Short Time

scholarly journals Neural Network Approach for Global Solar Irradiance Prediction at Extremely Short-Time-Intervals Using Particle Swarm Optimization Algorithm

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1213
Author(s):  
Ahmed Aljanad ◽  
Nadia M. L. Tan ◽  
Vassilios G. Agelidis ◽  
Hussain Shareef
Keyword(s):  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Solar Irradiance ◽  
Particle Swarm ◽  
Time Interval ◽  
Time Intervals ◽  
Swarm Optimization ◽  
Backpropagation Neural Networks ◽  
Proposed Model ◽  
Short Time

Hourly global solar irradiance (GSR) data are required for sizing, planning, and modeling of solar photovoltaic farms. However, operating and controlling such farms exposed to varying environmental conditions, such as fast passing clouds, necessitates GSR data to be available for very short time intervals. Classical backpropagation neural networks do not perform satisfactorily when predicting parameters within short intervals. This paper proposes a hybrid backpropagation neural networks based on particle swarm optimization. The particle swarm algorithm is used as an optimization algorithm within the backpropagation neural networks to optimize the number of hidden layers and neurons used and its learning rate. The proposed model can be used as a reliable model in predicting changes in the solar irradiance during short time interval in tropical regions such as Malaysia and other regions. Actual global solar irradiance data of 5-s and 1-min intervals, recorded by weather stations, are applied to train and test the proposed algorithm. Moreover, to ensure the adaptability and robustness of the proposed technique, two different cases are evaluated using 1-day and 3-days profiles, for two different time intervals of 1-min and 5-s each. A set of statistical error indices have been introduced to evaluate the performance of the proposed algorithm. From the results obtained, the 3-days profile’s performance evaluation of the BPNN-PSO are 1.7078 of RMSE, 0.7537 of MAE, 0.0292 of MSE, and 31.4348 of MAPE (%), at 5-s time interval, where the obtained results of 1-min interval are 0.6566 of RMSE, 0.2754 of MAE, 0.0043 of MSE, and 1.4732 of MAPE (%). The results revealed that proposed model outperformed the standalone backpropagation neural networks method in predicting global solar irradiance values for extremely short-time intervals. In addition to that, the proposed model exhibited high level of predictability compared to other existing models.

scholarly journals Identifying bidirectional total and non-linear information flow in functional corticomuscular coupling during a dorsiflexion task: a pilot study

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Tie Liang ◽  
Qingyu Zhang ◽  
Xiaoguang Liu ◽  
Bin Dong ◽  
Xiuling Liu ◽  
...  
Keyword(s):  
Time Series ◽  
Information Flow ◽  
Gamma Band ◽  
Motor Dysfunction ◽  
Beta Band ◽  
Short Time Series ◽  
Information Interaction ◽  
Stroke Group ◽  
Short Time ◽  
Maximal Information Coefficient

Abstract Background The key challenge to constructing functional corticomuscular coupling (FCMC) is to accurately identify the direction and strength of the information flow between scalp electroencephalography (EEG) and surface electromyography (SEMG). Traditional TE and TDMI methods have difficulty in identifying the information interaction for short time series as they tend to rely on long and stable data, so we propose a time-delayed maximal information coefficient (TDMIC) method. With this method, we aim to investigate the directional specificity of bidirectional total and nonlinear information flow on FCMC, and to explore the neural mechanisms underlying motor dysfunction in stroke patients. Methods We introduced a time-delayed parameter in the maximal information coefficient to capture the direction of information interaction between two time series. We employed the linear and non-linear system model based on short data to verify the validity of our algorithm. We then used the TDMIC method to study the characteristics of total and nonlinear information flow in FCMC during a dorsiflexion task for healthy controls and stroke patients. Results The simulation results showed that the TDMIC method can better detect the direction of information interaction compared with TE and TDMI methods. For healthy controls, the beta band (14–30 Hz) had higher information flow in FCMC than the gamma band (31–45 Hz). Furthermore, the beta-band total and nonlinear information flow in the descending direction (EEG to EMG) was significantly higher than that in the ascending direction (EMG to EEG), whereas in the gamma band the ascending direction had significantly higher information flow than the descending direction. Additionally, we found that the strong bidirectional information flow mainly acted on Cz, C3, CP3, P3 and CPz. Compared to controls, both the beta-and gamma-band bidirectional total and nonlinear information flows of the stroke group were significantly weaker. There is no significant difference in the direction of beta- and gamma-band information flow in stroke group. Conclusions The proposed method could effectively identify the information interaction between short time series. According to our experiment, the beta band mainly passes downward motor control information while the gamma band features upward sensory feedback information delivery. Our observation demonstrate that the center and contralateral sensorimotor cortex play a major role in lower limb motor control. The study further demonstrates that brain damage caused by stroke disrupts the bidirectional information interaction between cortex and effector muscles in the sensorimotor system, leading to motor dysfunction.

scholarly journals Optimal Perturbations of an Oceanic Vortex Lens

Fluids ◽  
2018 ◽  
Vol 3 (3) ◽  
pp. 63 ◽  
Author(s):  
Thomas Meunier ◽  
Claire Ménesguen ◽  
Xavier Carton ◽  
Sylvie Le Gentil ◽  
Richard Schopp
Keyword(s):  
Normal Mode ◽  
Growth Rates ◽  
Time Interval ◽  
Time Intervals ◽  
Horizontal Structure ◽  
Azimuthal Wave ◽  
Wave Numbers ◽  
Non Linear ◽  
Long Time ◽  
Short Time

The stability properties of a vortex lens are studied in the quasi geostrophic (QG) framework using the generalized stability theory. Optimal perturbations are obtained using a tangent linear QG model and its adjoint. Their fine-scale spatial structures are studied in details. Growth rates of optimal perturbations are shown to be extremely sensitive to the time interval of optimization: The most unstable perturbations are found for time intervals of about 3 days, while the growth rates continuously decrease towards the most unstable normal mode, which is reached after about 170 days. The horizontal structure of the optimal perturbations consists of an intense counter-shear spiralling. It is also extremely sensitive to time interval: for short time intervals, the optimal perturbations are made of a broad spectrum of high azimuthal wave numbers. As the time interval increases, only low azimuthal wave numbers are found. The vertical structures of optimal perturbations exhibit strong layering associated with high vertical wave numbers whatever the time interval. However, the latter parameter plays an important role in the width of the vertical spectrum of the perturbation: short time interval perturbations have a narrow vertical spectrum while long time interval perturbations show a broad range of vertical scales. Optimal perturbations were set as initial perturbations of the vortex lens in a fully non linear QG model. It appears that for short time intervals, the perturbations decay after an initial transient growth, while for longer time intervals, the optimal perturbation keeps on growing, quickly leading to a non-linear regime or exciting lower azimuthal modes, consistent with normal mode instability. Very long time intervals simply behave like the most unstable normal mode. The possible impact of optimal perturbations on layering is also discussed.

Sign in / Sign up

Export Citation Format

Share Document