@InProceedings{Kim2008_emg,
  Title                    = {EMG-based Hand Gesture Recognition for Realtime Biosignal Interfacing},
  Author                   = {Kim, J. and Mastnik, S. and Andr{\'e}, E.},
  Booktitle                = {Proceedings of the International Conference on Intelligent User Interfaces},
  Year                     = {2008},
  Pages                    = {30--39},

  Abstract                 = {In this paper the development of an electromyogram (EMG) based interface for hand gesture recognition is presented. To recognize control signs in the gestures, we used a single channel EMG sensor positioned on the inside of the forearm. In addition to common statistical features such as variance, mean value, and standard deviation, we also calculated features from the time and frequency domain including Fourier variance, region length, zerocrosses, occurrences, etc. For realizing real-time classification assuring acceptable recognition accuracy, we combined two simple linear classifiers (k-NN and Bayes) in decision level fusion. Overall, a recognition accuracy of 94% was achieved by using the combined classifier with a selected feature set. The performance of the interfacing system was evaluated through 40 test sessions with 30 subjects using an RC Car. Instead of using a remote control unit, the car was controlled by four different gestures performed with one hand. In addition, we conducted a study to investigate the controllability and ease of use of the interface and the employed gestures.},
  Acmid                    = {1378778},
  Doi                      = {10.1145/1378773.1378778},
  ISBN                     = {978-1-59593-987-6},
  Keywords                 = {biosignal analysis, electromyogram, gesture recognition, human-computer interaction, neural interfacing},
  Location                 = {Gran Canaria, Spain},
  Numpages                 = {10},
  Owner                    = {jf2lin},
  Review                   = {Uses a single channel EMG to recognize 4 hand gestures to control an RC car. Motion is fist, fist with wrist left, fist with wrist right, and fist with wrist down. 

- threshold on rms to determine the start and end fo a signal (segmentation)
- for actual signal, used max, min, mean value, variance, signal length, rms. for freq signals, used fundamental freq, fourier varience, region length (partial length of the spectrum containing greater magnitude than mean value of total fourier coeff), percentage to max value, zero crossing

- used knn and bayes classifier, and has voting schemes btwn them
- calibrate with 10-20 samples of each gesture for subject. above 90% acc in classification rate. 

30 subjects.},
  Timestamp                = {2015.04.03}
}

{"_id":"dKvXmeKTsBTEiGdXj","bibbaseid":"kim-mastnik-andr-emgbasedhandgesturerecognitionforrealtimebiosignalinterfacing-2008","downloads":0,"creationDate":"2017-09-14T16:34:36.642Z","title":"EMG-based Hand Gesture Recognition for Realtime Biosignal Interfacing","author_short":["Kim, J.","Mastnik, S.","André, E."],"year":2008,"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/jfslin/jfslin.github.io/master/jf2lin.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"EMG-based Hand Gesture Recognition for Realtime Biosignal Interfacing","author":[{"propositions":[],"lastnames":["Kim"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Mastnik"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["André"],"firstnames":["E."],"suffixes":[]}],"booktitle":"Proceedings of the International Conference on Intelligent User Interfaces","year":"2008","pages":"30--39","abstract":"In this paper the development of an electromyogram (EMG) based interface for hand gesture recognition is presented. To recognize control signs in the gestures, we used a single channel EMG sensor positioned on the inside of the forearm. In addition to common statistical features such as variance, mean value, and standard deviation, we also calculated features from the time and frequency domain including Fourier variance, region length, zerocrosses, occurrences, etc. For realizing real-time classification assuring acceptable recognition accuracy, we combined two simple linear classifiers (k-NN and Bayes) in decision level fusion. Overall, a recognition accuracy of 94% was achieved by using the combined classifier with a selected feature set. The performance of the interfacing system was evaluated through 40 test sessions with 30 subjects using an RC Car. Instead of using a remote control unit, the car was controlled by four different gestures performed with one hand. In addition, we conducted a study to investigate the controllability and ease of use of the interface and the employed gestures.","acmid":"1378778","doi":"10.1145/1378773.1378778","isbn":"978-1-59593-987-6","keywords":"biosignal analysis, electromyogram, gesture recognition, human-computer interaction, neural interfacing","location":"Gran Canaria, Spain","numpages":"10","owner":"jf2lin","review":"Uses a single channel EMG to recognize 4 hand gestures to control an RC car. Motion is fist, fist with wrist left, fist with wrist right, and fist with wrist down. - threshold on rms to determine the start and end fo a signal (segmentation) - for actual signal, used max, min, mean value, variance, signal length, rms. for freq signals, used fundamental freq, fourier varience, region length (partial length of the spectrum containing greater magnitude than mean value of total fourier coeff), percentage to max value, zero crossing - used knn and bayes classifier, and has voting schemes btwn them - calibrate with 10-20 samples of each gesture for subject. above 90% acc in classification rate. 30 subjects.","timestamp":"2015.04.03","bibtex":"@InProceedings{Kim2008_emg,\n Title = {EMG-based Hand Gesture Recognition for Realtime Biosignal Interfacing},\n Author = {Kim, J. and Mastnik, S. and Andr{\\'e}, E.},\n Booktitle = {Proceedings of the International Conference on Intelligent User Interfaces},\n Year = {2008},\n Pages = {30--39},\n\n Abstract = {In this paper the development of an electromyogram (EMG) based interface for hand gesture recognition is presented. To recognize control signs in the gestures, we used a single channel EMG sensor positioned on the inside of the forearm. In addition to common statistical features such as variance, mean value, and standard deviation, we also calculated features from the time and frequency domain including Fourier variance, region length, zerocrosses, occurrences, etc. For realizing real-time classification assuring acceptable recognition accuracy, we combined two simple linear classifiers (k-NN and Bayes) in decision level fusion. Overall, a recognition accuracy of 94% was achieved by using the combined classifier with a selected feature set. The performance of the interfacing system was evaluated through 40 test sessions with 30 subjects using an RC Car. Instead of using a remote control unit, the car was controlled by four different gestures performed with one hand. In addition, we conducted a study to investigate the controllability and ease of use of the interface and the employed gestures.},\n Acmid = {1378778},\n Doi = {10.1145/1378773.1378778},\n ISBN = {978-1-59593-987-6},\n Keywords = {biosignal analysis, electromyogram, gesture recognition, human-computer interaction, neural interfacing},\n Location = {Gran Canaria, Spain},\n Numpages = {10},\n Owner = {jf2lin},\n Review = {Uses a single channel EMG to recognize 4 hand gestures to control an RC car. Motion is fist, fist with wrist left, fist with wrist right, and fist with wrist down. \n\n- threshold on rms to determine the start and end fo a signal (segmentation)\n- for actual signal, used max, min, mean value, variance, signal length, rms. for freq signals, used fundamental freq, fourier varience, region length (partial length of the spectrum containing greater magnitude than mean value of total fourier coeff), percentage to max value, zero crossing\n\n- used knn and bayes classifier, and has voting schemes btwn them\n- calibrate with 10-20 samples of each gesture for subject. above 90% acc in classification rate. \n\n30 subjects.},\n Timestamp = {2015.04.03}\n}\n\n","author_short":["Kim, J.","Mastnik, S.","André, E."],"key":"Kim2008_emg","id":"Kim2008_emg","bibbaseid":"kim-mastnik-andr-emgbasedhandgesturerecognitionforrealtimebiosignalinterfacing-2008","role":"author","urls":{},"keyword":["biosignal analysis","electromyogram","gesture recognition","human-computer interaction","neural interfacing"],"downloads":0},"search_terms":["emg","based","hand","gesture","recognition","realtime","biosignal","interfacing","kim","mastnik","andré"],"keywords":["biosignal analysis","electromyogram","gesture recognition","human-computer interaction","neural interfacing"],"authorIDs":[],"dataSources":["iCsmKnycRmHPxmhBd"]}