dtw   234

« earlier    

RT : The snow is causing delays and cancellations at . Remember to check with your airline before heading to the air…
DTW  from twitter_favs
2 days ago by vielmetti
At where cancelled my to flight, conveniently just a few minutes after I checked my bag.

EWR  DTW  from twitter
2 days ago by vielmetti
Hey - what are the current plans for to ? You are showing it 10 minutes delayed, which se…
DTW  EWR  UA3530  from twitter
2 days ago by vielmetti
Working to see what happened with flight from to . Passenger on-board said a tow truck som…
DTW  dl2421  RDU  from twitter_favs
4 days ago by vielmetti
Oakland international airport waiting for flight to
dtw  from twitter
11 weeks ago by vielmetti
[1705.05681] Optimal Warping Paths are unique for almost every pair of Time Series
"An optimal warping path between two time series is generally not unique. The size and form of the set of pairs of time series with non-unique optimal warping path is unknown. This article shows that optimal warping paths are unique for almost every pair of time series in a measure-theoretic sense. All pairs of time series with non-unique optimal warping path form a negligible set and are geometrically the union of zero sets of quadratic forms. The result is useful for analyzing and understanding adaptive learning methods in dynamic time warping spaces."
papers  time-series  alignment  dtw 
may 2017 by arsyed
[1703.01141] Dynamic State Warping
"The ubiquity of sequences in many domains enhances significant recent interest in sequence learning, for which a basic problem is how to measure the distance between sequences. Dynamic time warping (DTW) aligns two sequences by nonlinear local warping and returns a distance value. DTW shows superior ability in many applications, e.g. video, image, etc. However, in DTW, two points are paired essentially based on point-to-point Euclidean distance (ED) without considering the autocorrelation of sequences. Thus, points with different semantic meanings, e.g. peaks and valleys, may be matched providing their coordinate values are similar. As a result, DTW is sensitive to noise and poorly interpretable. This paper proposes an efficient and flexible sequence alignment algorithm, dynamic state warping (DSW). DSW converts each time point into a latent state, which endows point-wise autocorrelation information. Alignment is performed by using the state sequences. Thus DSW is able to yield alignment that is semantically more interpretable than that of DTW. Using one nearest neighbor classifier, DSW shows significant improvement on classification accuracy in comparison to ED (70/85 wins) and DTW (74/85 wins). We also empirically demonstrate that DSW is more robust and scales better to long sequences than ED and DTW."
papers  time-series  sequence  alignment  dtw 
may 2017 by arsyed
Dinner is a capricciosa pizza and a glass of Montepulciano at . Headed to Miami Beach w/…
DTW  from twitter
march 2017 by peterhoneyman
[1703.01541] Soft-DTW: a Differentiable Loss Function for Time-Series
"We propose in this paper a differentiable learning loss between time series. Our proposal builds upon the celebrated Dynamic Time Warping (DTW) discrepancy. Unlike the Euclidean distance, DTW is able to compare asynchronous time series of varying size and is robust to elastic transformations in time. To be robust to such invariances, DTW computes a minimal cost alignment between time series using dynamic programming. Our work takes advantage of a smoothed formulation of DTW, called soft-DTW, that computes the soft-minimum of all alignment costs. We show in this paper that soft-DTW is a differentiable loss function, and that both its value and its gradient can be computed with quadratic time/space complexity (DTW has quadratic time and linear space complexity). We show that our regularization is particularly well suited to average and cluster time series under the DTW geometry, a task for which our proposal significantly outperforms existing baselines (Petitjean et al., 2011). Next, we propose to tune the parameters of a machine that outputs time series by minimizing its fit with ground-truth labels in a soft-DTW sense."
papers  time-series  dtw 
march 2017 by arsyed

« earlier    

related tags

155  747  activity-recognition  airport  alex-park  algorithm  algorithms  alignment  analysis  annarbor  approximate  asr  asrt  audio  avgeek  aviation  boeing  books  bounds  c  car  cdtw  classification  clustering  code  complexity  computer-vision  computerscience  constraint-learning  constraint  continuous-profile-model  continuous  correlation  courses  cpm  cuda  cython  data  dataanalysis  datamining  dataset  detroit  digital  dimensionality-reduction  discretization  distance  dl2421  dsp  dynamic  eamon-keough  edit-distance  embedding  entropy  erp  ewr  example  f0  feature-extraction  filter  flightdelay  frechet  gbl  gpu  hac  hashing  hmm  homepage  indexing  interpolation  intro  ipynbs  ipython  ir  java  kernel-methods  knn  kws  lcss  libarary  library  libs  likelihood  low-resource  lower-bound  lower-bounding  lsh  machinelearning  margin-methods  matching  mathematics  matlab  metric  mfcc  mtg  music  neural-net  non-metric  normalization  notes  paper  papers  parallel  parking  pattern  people  performance  photos  pitch  pocket-read  posteriorgram  prediction  pronunciation  python  qbe  quantization  r  random-walk  rdu  realtime  recognition  representation  research  retrieval  rpy  sax  sci  scoring  search  searching  segmental-dtw  semisupervised  sequence-alignment  sequence  series  shuttle  signal-processing  similarity-measures  similarity  slides  softmax  software  speaker-segmentation  spectogram  speech  speechrecog  spoken-term-detection  spoken-term-discovery  streaming  strings  synthesis  theano  thesis  time-series  time-warping  time  timeseries  timewarping  tracking  trajectory  ts  ua3530  ucr-dtw  unsupervised  urbanism  vad  video  visualization  vtln  warp  warping  距离 

Copy this bookmark: