Continuous Trend-Based Classification of Streaming Time Series

2005 ◽  
pp. 294-308 ◽  
Author(s):  
Maria Kontaki ◽  
Apostolos N. Papadopoulos ◽  
Yannis Manolopoulos
Keyword(s):  
Time Series

scholarly journals Time–frequency time–space LSTM for robust classification of physiological signals

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuan D. Pham
Keyword(s):  
Time Series ◽  
Network Architecture ◽  
Time Series Data ◽  
Short Term Memory ◽  
Physiological Signals ◽  
Series Data ◽  
Time Frequency ◽  
Time Space ◽  
Deep Recurrent Neural Network

AbstractAutomated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

scholarly journals High-pass filtering artifacts in multivariate classification of neural time series data

2021 ◽  
Vol 352 ◽  
pp. 109080
Author(s):  
Joram van Driel ◽  
Christian N.L. Olivers ◽  
Johannes J. Fahrenfort
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Series Data ◽  
Multivariate Classification ◽  
High Pass

scholarly journals ECG Prediction Based on Classification via Neural Networks and Linguistic Fuzzy Logic Forecaster

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Eva Volna ◽  
Martin Kotyrba ◽  
Hashim Habiballa
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Ecg Signals ◽  
Detection Systems ◽  
Language Interpretation ◽  
Different Types ◽  
Time Courses ◽  
Natural Language Interpretation ◽  
Unique Capability

The paper deals with ECG prediction based on neural networks classification of different types of time courses of ECG signals. The main objective is to recognise normal cycles and arrhythmias and perform further diagnosis. We proposed two detection systems that have been created with usage of neural networks. The experimental part makes it possible to load ECG signals, preprocess them, and classify them into given classes. Outputs from the classifiers carry a predictive character. All experimental results from both of the proposed classifiers are mutually compared in the conclusion. We also experimented with the new method of time series transparent prediction based on fuzzy transform with linguistic IF-THEN rules. Preliminary results show interesting results based on the unique capability of this approach bringing natural language interpretation of particular prediction, that is, the properties of time series.

Image Classification of Time Series Based on Deep Convolutional Neural Network

2021 ◽  
Author(s):  
Wenjie Cao ◽  
Cheng Zhang ◽  
Zhenzhen Xiong ◽  
Ting Wang ◽  
Junchao Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Deep Convolutional Neural Network

Classification of Technological Development Trends Based on the Analysis of US Patent Time Series. An Empirical Approach

2021 ◽  
pp. 251-278
Author(s):  
Vladimir I. Karnyshev ◽  
◽  
Vladimir I. Avdzeyko ◽  
Evgenia S. Paskal ◽  
◽  
...  
Keyword(s):  
Time Series ◽  
New Technologies ◽  
Practical Interest ◽  
The United States ◽  
Direct Access ◽  
Investment Planning ◽  
Short Term ◽  
Development Trends ◽  
Technical Problems

The forecasting of development trends and the timely revealing of new technical (technological) fields are the key prerequisite for an effective development of modern economy. Only reliable results of technological analysis (forecast) allow identifying new technologies, understanding the evolution of entire industries, carrying out strategic investment planning at the state level, and also planning R&D correctly. The aim of this work is to justify one of the possible approaches to the classification of technical (technological) fields in terms of assessing their relevance, novelty and short-term prospects. This approach is based on patent analysis, in particular, on the study of the time series features of US invention patents (1976-2018) for more than seventy-three thousand main groups (subgroups) of the 17th edition of the International Patent Classification (IPC17). The United States Patent and Trademark Office (USPTO) has been selected as the primary source of information because it is one of the world’s largest and constantly updated patent resources, providing direct access to full-text descriptions. In the authors’ opinion, a feature analysis of the US patent issue dynamics at time intervals (1976-2015, 2009-2018 and 2016-2018) allows dividing the IPC groups (subgroups) into the following three main clusters: “unpromising”, “promising” and “breakthrough”. In terms of the timely revealing of new, previously unknown, technologies or solutions in the technical field, or of the steadily growing technological trends, the “breakthrough” and “promising” subgroups are of the greatest practical interest. The article presents the results of an empirical classification of 71,266 subgroups (with a non-zero number of the issued patents since 1976 to 2018) in eight sections of the IPC17. These data may be useful for developers, researchers and R&D planners in solving complex scientific and technical problems, as well as for making short-term forecast estimates of a specific technical (technological) field development.

Classification of landslide activity based on spaceborne interferometric SAR at the Moselle Valley, Germany

2021 ◽  
Author(s):  
Andre C. Kalia
Keyword(s):  
Time Series ◽  
Clustering Algorithm ◽  
Statistical Tests ◽  
Spatial Density ◽  
Deformation Pattern ◽  
Visual Interpretation ◽  
Landslide Activity ◽  
Spatial Coverage ◽  
Interferometric Sar

<p>Landslide activity is an important information for landslide hazard assessment. However, an information gap regarding up to date landslide activity is often present. Advanced differential interferometric SAR processing techniques (A-DInSAR), e.g. Persistent Scatterer Interferometry (PSI) and Small Baseline Subset (SBAS) are able to measure surface displacements with high precision, large spatial coverage and high spatial sampling density. Although the huge amount of measurement points is clearly an improvement, the practical usage is mainly based on visual interpretation. This is time-consuming, subjective and error prone due to e.g. outliers. The motivation of this work is to increase the automatization with respect to the information extraction regarding landslide activity.</p><p>This study focuses on the spatial density of multiple PSI/SBAS results and a post-processing workflow to semi-automatically detect active landslides. The proposed detection of active landslides is based on the detection of Active Deformation Areas (ADA) and a subsequent classification of the time series. The detection of ADA consists of a filtering of the A-DInSAR data, a velocity threshold and a spatial clustering algorithm (Barra et al., 2017). The classification of the A-DInSAR time series uses a conditional sequence of statistical tests to classify the time series into a-priori defined deformation patterns (Berti et al., 2013). Field investigations and thematic data verify the plausibility of the results. Subsequently the classification results are combined to provide a layer consisting of ADA including information regarding the deformation pattern through time.</p>

Sign in / Sign up

Export Citation Format

Share Document