@InProceedings{7362803,
  author = {P. M. Baggenstoss},
  booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},
  title = {Class-specific model mixtures for the classification of time-series},
  year = {2015},
  pages = {2341-2345},
  abstract = {We present a new classifier for acoustic time-series that involves a mixture of generative models. Each model operates on a feature stream extracted from the time-series using overlapped Hanning-weighted segments and has a probability density function (PDF) modeled with a hidden Markov model (HMM). The models use a variety of segmentation sizes and feature extraction methods, yet can be combined at a higher level using a mixture PDF thanks to the PDF projection theorem (PPT) that converts the feature PDF to raw time-series PDFs. The effectiveness of the method is shown using an open data set of short-duration acoustic signals.},
  keywords = {acoustic signal processing;feature extraction;hidden Markov models;signal classification;time series;time-series classification;short-duration acoustic signals;PPT;PDF projection theorem;mixture PDF;feature extraction methods;segmentation sizes;HMM;hidden Markov model;probability density function;overlapped Hanning-weighted segments;feature stream;generative models;acoustic time-series;Hidden Markov models;Feature extraction;Computational modeling;Mel frequency cepstral coefficient;Cepstrum;Support vector machines;Probability density function;Classification;PDF projection;generative models;kernel methods},
  doi = {10.1109/EUSIPCO.2015.7362803},
  issn = {2076-1465},
  month = {Aug},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096431.pdf},
}

{"_id":"WeDHH89gYNi2mXKjH","bibbaseid":"baggenstoss-classspecificmodelmixturesfortheclassificationoftimeseries-2015","downloads":0,"creationDate":"2016-01-08T22:33:13.860Z","title":"Class-specific model mixtures for the classification of time-series","author_short":["Baggenstoss, P. M."],"year":2015,"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["P.","M."],"propositions":[],"lastnames":["Baggenstoss"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"Class-specific model mixtures for the classification of time-series","year":"2015","pages":"2341-2345","abstract":"We present a new classifier for acoustic time-series that involves a mixture of generative models. Each model operates on a feature stream extracted from the time-series using overlapped Hanning-weighted segments and has a probability density function (PDF) modeled with a hidden Markov model (HMM). The models use a variety of segmentation sizes and feature extraction methods, yet can be combined at a higher level using a mixture PDF thanks to the PDF projection theorem (PPT) that converts the feature PDF to raw time-series PDFs. The effectiveness of the method is shown using an open data set of short-duration acoustic signals.","keywords":"acoustic signal processing;feature extraction;hidden Markov models;signal classification;time series;time-series classification;short-duration acoustic signals;PPT;PDF projection theorem;mixture PDF;feature extraction methods;segmentation sizes;HMM;hidden Markov model;probability density function;overlapped Hanning-weighted segments;feature stream;generative models;acoustic time-series;Hidden Markov models;Feature extraction;Computational modeling;Mel frequency cepstral coefficient;Cepstrum;Support vector machines;Probability density function;Classification;PDF projection;generative models;kernel methods","doi":"10.1109/EUSIPCO.2015.7362803","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096431.pdf","bibtex":"@InProceedings{7362803,\n author = {P. M. Baggenstoss},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {Class-specific model mixtures for the classification of time-series},\n year = {2015},\n pages = {2341-2345},\n abstract = {We present a new classifier for acoustic time-series that involves a mixture of generative models. Each model operates on a feature stream extracted from the time-series using overlapped Hanning-weighted segments and has a probability density function (PDF) modeled with a hidden Markov model (HMM). The models use a variety of segmentation sizes and feature extraction methods, yet can be combined at a higher level using a mixture PDF thanks to the PDF projection theorem (PPT) that converts the feature PDF to raw time-series PDFs. The effectiveness of the method is shown using an open data set of short-duration acoustic signals.},\n keywords = {acoustic signal processing;feature extraction;hidden Markov models;signal classification;time series;time-series classification;short-duration acoustic signals;PPT;PDF projection theorem;mixture PDF;feature extraction methods;segmentation sizes;HMM;hidden Markov model;probability density function;overlapped Hanning-weighted segments;feature stream;generative models;acoustic time-series;Hidden Markov models;Feature extraction;Computational modeling;Mel frequency cepstral coefficient;Cepstrum;Support vector machines;Probability density function;Classification;PDF projection;generative models;kernel methods},\n doi = {10.1109/EUSIPCO.2015.7362803},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096431.pdf},\n}\n\n","author_short":["Baggenstoss, P. M."],"key":"7362803","id":"7362803","bibbaseid":"baggenstoss-classspecificmodelmixturesfortheclassificationoftimeseries-2015","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096431.pdf"},"keyword":["acoustic signal processing;feature extraction;hidden Markov models;signal classification;time series;time-series classification;short-duration acoustic signals;PPT;PDF projection theorem;mixture PDF;feature extraction methods;segmentation sizes;HMM;hidden Markov model;probability density function;overlapped Hanning-weighted segments;feature stream;generative models;acoustic time-series;Hidden Markov models;Feature extraction;Computational modeling;Mel frequency cepstral coefficient;Cepstrum;Support vector machines;Probability density function;Classification;PDF projection;generative models;kernel methods"],"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["class","specific","model","mixtures","classification","time","series","baggenstoss"],"keywords":["acoustic signal processing;feature extraction;hidden markov models;signal classification;time series;time-series classification;short-duration acoustic signals;ppt;pdf projection theorem;mixture pdf;feature extraction methods;segmentation sizes;hmm;hidden markov model;probability density function;overlapped hanning-weighted segments;feature stream;generative models;acoustic time-series;hidden markov models;feature extraction;computational modeling;mel frequency cepstral coefficient;cepstrum;support vector machines;probability density function;classification;pdf projection;generative models;kernel methods"],"authorIDs":[],"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}