Filters








1,787,404 Hits in 6.0 sec

An Online Transfer Learning Framework With Extreme Learning Machine for Automated Credit Scoring

Rana Alasbahi, Xiaolin Zheng
2022 IEEE Access  
The results show the superiority of the proposed algorithm over the benchmarks in terms of the majority of classification metrics concerning both time series and overall results.  ...  statistical distributions of the records between classes, and concept drift due to changing statistical characteristics concerning certain classes and features with time.  ...  G-Mean time series comparison for PPDai dataset. Algorithm 1 1 Pseudocode of the General Framework of Transfer Learning With Lag Input: boostingChunk, featureSizem Lag.  ... 
doi:10.1109/access.2022.3171569 fatcat:6bavbx7c7fcrdf75qwrrg73xgm

A Computational Method to Assist the Diagnosis of Breast Disease Using Dynamic Thermography

Thiago Alves Elias da Silva, Lincoln Faria da Silva, Débora Christina Muchaluat-Saade, Aura Conci
2020 Sensors  
Time series that are broken down into subsets of different cardinalities are generated from such features.  ...  Features are extracted from the arrays, such as the ones based on statistical, clustering, histogram comparison, fractal geometry, diversity indices and spatial statistics.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20143866 pmid:32664410 fatcat:forf4ri6xrd5dbhex5pcz26yia

Flood Monitoring in Vegetated Areas Using Multitemporal Sentinel-1 Data: Impact of Time Series Features

Viktoriya Tsyganskaya, Sandro Martinis, Philip Marzahn
2019 Water  
The analysis of the transferability for the time series approach showed that the time series feature based on VV (vertical/vertical) polarization is particularly suitable for deriving TFV types for different  ...  classification depending on the time series feature used.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/w11091938 fatcat:f3kfiktyvbbovakkcpdjuzbwxy

Approaches and Challenges in the Visual-interactive Comparison of Human Motion Data

Jürgen Bernard, Anna Vögele, Reinhard Klein, Dieter Fellner
2017 Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
This work reflects the design space for visual-interactive systems facilitating the visual comparison of human MoCap data, and presents a taxonomy comprising three primary factors, following the general  ...  Based on a literature review, relevant visual comparison approaches are discussed. We outline remaining challenges and inspiring works on MoCap data, information visualization, and visual analytics.  ...  User interaction allows the temporal synchronization and visual comparison of feature progressions. ate time series can be seen as an instance of comparing individual features.  ... 
doi:10.5220/0006127502170224 dblp:conf/grapp/BernardVKF17 fatcat:wluvr2p2snfgfksgddjdv7pwu4

QMNET Talk: The need for interdisciplinary comparison when analyzing time series [article]

Ben Fulcher
2020 figshare.com  
Jones (2017) Van der Pol Oscillator Generate a dataset by sampling c and k Feature-based dimensionality reduction Can reconstruct parametric variation underlying a time-series dataset This could  ...  A Self-Organizing, Living Library of Time-Series Data. Scientific Data 7: 213 (2020). Fulcher (2018). Feature-based time-series analysis, Feature Engineering, CRC Press. what feature should I use?  ... 
doi:10.6084/m9.figshare.12775748.v1 fatcat:3ozo64z3mvbutmi4eurj2uk3ea

A Singular Spectrum Analysis-based Synthetic Dataset Generation Method for Remaining Useful Life Estimation of Turbo Fan Engines

Peerapol Yuvapoositanon, Mahanakorn University of Technology, Prakit Intachai, Phetchaburi Rajabhat University
2021 International Journal of Intelligent Engineering and Systems  
The validity of proposed method is confirmed by testing with 200 actual datasets from turbofan engine datasets and 200 synthetic datasets generated by the proposed method in comparison to those generated  ...  It was revealed that the synthetic datasets generated by the proposed SSA-based method performed the best with the MAE of 25.123 and RMSE of 36.825 confirming the applicability of the proposed SSA-based  ...  We choose to explain this concept via the reconstruction of a pair of uncorrelated time series , ( ) ( ), and time series , ( ) ( ).  ... 
doi:10.22266/ijies2021.0831.32 fatcat:2cxgtbcfobcr3ez35k2fmfmawm

Time series features for supporting hydrometeorological explorations and predictions in ungauged locations using large datasets [article]

Georgia Papacharalampous, Hristos Tyralis
2022 arXiv   pre-print
time series features for data science and, more precisely, from a large variety of such features.  ...  time series) were found to be useful predictors of many streamflow features.  ...  of the time series features.  ... 
arXiv:2204.06540v1 fatcat:4xqdtabpefgrnfb7ircpqb33z4

Detection of Temporary Flooded Vegetation Using Sentinel-1 Time Series Data

Viktoriya Tsyganskaya, Sandro Martinis, Philip Marzahn, Ralf Ludwig
2018 Remote Sensing  
Multi-temporal characteristics and patterns are applied to generate novel times series features, which represent a basis for the developed approach.  ...  Sentinel-1 times series were used for the period between September 2016 and July 2017.  ...  Acknowledgments: The authors would like to thank the anonymous reviewers for their helpful comments and constructive suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs10081286 fatcat:egiikaqw7fds3ltuxmt5ozit2e

A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time Series [article]

Wenqian Jiang, Cheng Cheng, Beitong Zhou, Guijun Ma, Ye Yuan
2019 arXiv   pre-print
This paper proposes a novel fault diagnosis approach based on generative adversarial networks (GAN) for imbalanced industrial time series where normal samples are much larger than failure cases.  ...  Aimed at obtaining data distribution and hidden pattern in both original distinguishing features and latent space, the encoder-decoder-encoder three-sub-network is employed in GAN, based on Deep Convolution  ...  Comparison between BiGANs and our method based on different sizes of subsample VI.  ... 
arXiv:1904.00575v1 fatcat:2wd7vlpvrfc4hkrye6xbswbjay

SAX-EFG

Uday Kamath, Jessica Lin, Kenneth De Jong
2014 Proceedings of the 2014 conference on Genetic and evolutionary computation - GECCO '14  
In this paper we explore a feature construction algorithm based on genetic programming that uses SAX-generated motifs as the building blocks for the construction of more complex features.  ...  Recently, the field of time series classification has seen success by using preprocessing steps that discretize the time series using a Symbolic Aggregate ApproXimation technique (SAX) and using recurring  ...  A comparison of EFG with feature-based, statistical and kernel methods on some subset of datasets with the same preprocessing from time series to symbolic discrete set using SAX will be the next research  ... 
doi:10.1145/2576768.2598321 dblp:conf/gecco/KamathLJ14 fatcat:veyowqqhszg4ldqntzxweqympy

A Bag-of-Features Framework to Classify Time Series

M. G. Baydogan, G. Runger, E. Tuv
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Nearest-neighbor classifiers with Dynamic Time Warping (DTW) distance is a strong solution in this context, but its performance degrades with long time series, relatively short features of interest, and  ...  On the other hand, feature-based ap-* Corresponding author.  ...  The number of subsequences generated for the time series is 100 10 − 5 = 5 Algorithm 2 2 TSBF (Time Series Classification Based on a Bag-of-Features Representation) for all time series x n do Standardize  ... 
doi:10.1109/tpami.2013.72 pmid:24051736 fatcat:pxwoupvonnb2rno545kbwizm34

catch22: CAnonical Time-series CHaracteristics

Carl H. Lubba, Sarab S. Sethi, Philip Knaute, Simon R. Schultz, Ben D. Fulcher, Nick S. Jones
2019 Data mining and knowledge discovery  
Selecting an appropriate feature-based representation of time series for a given application can be achieved through systematic comparison across a comprehensive time-series feature library, such as those  ...  However, this approach is computationally expensive and involves evaluating many similar features, limiting the widespread adoption of feature-based representations of time series for real-world applications  ...  We further thank the authors behind the UEA/UCR time series classification repository for the valuable data that made this project possible.  ... 
doi:10.1007/s10618-019-00647-x fatcat:bx7r24txxbfq3kanmnucikeugy

TSrepr R package: Time Series Representations

Peter Laurinec
2018 Journal of Open Source Software  
The comparison of model-based time series representations on electricity consumption time series.  ...  Time series representations are, in other words, methods for dimensionality reduction, feature extraction or for the preprocessing of time series.  ...  However, these packages are mainly focused on motif discovery in time series. Figure 1 . 1 The comparison of model-based time series representations on electricity consumption time series.  ... 
doi:10.21105/joss.00577 fatcat:rkdnylc5qbfnlbk4uawr4qwufi

Structural Generative Descriptions for Time Series Classification

Edgar S. Garcia-Trevino, Javier A. Barria
2014 IEEE Transactions on Cybernetics  
The impact of the proposed data representation stage in the solution to the generic underlying problem of time series classification is investigated.  ...  In this paper, we formulate a novel time series representation framework that captures the inherent data dependency of time series and that can be easily incorporated into existing statistical classification  ...  The first group are descriptive techniques which are based on the direct comparison of observations (raw data-based approaches) or the conversion of time series data into a fixed-length feature vector  ... 
doi:10.1109/tcyb.2014.2322310 pmid:24860046 fatcat:w6ef4ygcxra27fwmsrklr4szbq

Dynamic Multi-scale Convolutional Neural Network for Time Series Classification

Bin Qian, Yong Xiao, Zhenjing Zheng, Mi Zhou, Wanqing Zhuang, Sen Li, Qianli Ma
2020 IEEE Access  
The filters of the convolutional neural networks are fixed length and shared by each sample. However, each time series usually has different time scale features.  ...  Specifically, we design a variable-length filters generator to produce a set of variable-length filters conditioned on the input time series.  ...  time series forest (TSF) [11] and time series bag of features (TSBF) [12] .  ... 
doi:10.1109/access.2020.3002095 fatcat:wc3s66qke5fwjo6n7rrw4ql5h4
« Previous Showing results 1 — 15 out of 1,787,404 results