@Article{Parkka2006,
  Title                    = {Activity classification using realistic data from wearable sensors},
  Author                   = {P\"{a}rkk\"{a}, J. and Ermes, M. and Korpip\"{a}\"{a}, P. and M\"{a}ntyj\"{a}rvi, J. and Peltola, J. and Korhonen, I.},
  Journal                  = {Information Technology in Biomedicine, IEEE Transactions on},
  Year                     = {2006},

  Month                    = {Jan},
  Number                   = {1},
  Pages                    = {119-128},
  Volume                   = {10},

  Abstract                 = {Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network},
  Doi                      = {10.1109/TITB.2005.856863},
  ISSN                     = {1089-7771},
  Keywords                 = {biomedical equipment;biomedical measurement;data analysis;decision trees;gait analysis;medical computing;neural nets;pattern classification;risk analysis;2 h;artificial neural network;automatic classification;automatically generated decision tree;custom decision tree;cycling;everyday activity classification;health risk;health-enhancing physical activity;healthier lifestyle;leave-one-subject-out cross validation;realistic data library;running;walking;wearable sensors;Artificial neural networks;Biomedical measurements;Cancer;Cardiovascular diseases;Classification tree analysis;Decision trees;Energy measurement;Legged locomotion;Testing;Wearable sensors;Activity classification;context awareness;physical activity;wearable sensors},
  Timestamp                = {2014.12.21}
}

{"_id":"rovSRwdrbSHGXsnLp","bibbaseid":"prkk-ermes-korpip-mntyjrvi-peltola-korhonen-activityclassificationusingrealisticdatafromwearablesensors-2006","downloads":0,"creationDate":"2017-09-14T16:34:36.905Z","title":"Activity classification using realistic data from wearable sensors","author_short":["Pärkkä, J.","Ermes, M.","Korpipää, P.","Mäntyjärvi, J.","Peltola, J.","Korhonen, I."],"year":2006,"bibtype":"article","biburl":"https://raw.githubusercontent.com/jfslin/jfslin.github.io/master/jf2lin.bib","bibdata":{"bibtype":"article","type":"article","title":"Activity classification using realistic data from wearable sensors","author":[{"propositions":[],"lastnames":["Pärkkä"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Ermes"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Korpipää"],"firstnames":["P."],"suffixes":[]},{"propositions":[],"lastnames":["Mäntyjärvi"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Peltola"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Korhonen"],"firstnames":["I."],"suffixes":[]}],"journal":"Information Technology in Biomedicine, IEEE Transactions on","year":"2006","month":"Jan","number":"1","pages":"119-128","volume":"10","abstract":"Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network","doi":"10.1109/TITB.2005.856863","issn":"1089-7771","keywords":"biomedical equipment;biomedical measurement;data analysis;decision trees;gait analysis;medical computing;neural nets;pattern classification;risk analysis;2 h;artificial neural network;automatic classification;automatically generated decision tree;custom decision tree;cycling;everyday activity classification;health risk;health-enhancing physical activity;healthier lifestyle;leave-one-subject-out cross validation;realistic data library;running;walking;wearable sensors;Artificial neural networks;Biomedical measurements;Cancer;Cardiovascular diseases;Classification tree analysis;Decision trees;Energy measurement;Legged locomotion;Testing;Wearable sensors;Activity classification;context awareness;physical activity;wearable sensors","timestamp":"2014.12.21","bibtex":"@Article{Parkka2006,\n Title = {Activity classification using realistic data from wearable sensors},\n Author = {P\\\"{a}rkk\\\"{a}, J. and Ermes, M. and Korpip\\\"{a}\\\"{a}, P. and M\\\"{a}ntyj\\\"{a}rvi, J. and Peltola, J. and Korhonen, I.},\n Journal = {Information Technology in Biomedicine, IEEE Transactions on},\n Year = {2006},\n\n Month = {Jan},\n Number = {1},\n Pages = {119-128},\n Volume = {10},\n\n Abstract = {Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network},\n Doi = {10.1109/TITB.2005.856863},\n ISSN = {1089-7771},\n Keywords = {biomedical equipment;biomedical measurement;data analysis;decision trees;gait analysis;medical computing;neural nets;pattern classification;risk analysis;2 h;artificial neural network;automatic classification;automatically generated decision tree;custom decision tree;cycling;everyday activity classification;health risk;health-enhancing physical activity;healthier lifestyle;leave-one-subject-out cross validation;realistic data library;running;walking;wearable sensors;Artificial neural networks;Biomedical measurements;Cancer;Cardiovascular diseases;Classification tree analysis;Decision trees;Energy measurement;Legged locomotion;Testing;Wearable sensors;Activity classification;context awareness;physical activity;wearable sensors},\n Timestamp = {2014.12.21}\n}\n\n","author_short":["Pärkkä, J.","Ermes, M.","Korpipää, P.","Mäntyjärvi, J.","Peltola, J.","Korhonen, I."],"key":"Parkka2006","id":"Parkka2006","bibbaseid":"prkk-ermes-korpip-mntyjrvi-peltola-korhonen-activityclassificationusingrealisticdatafromwearablesensors-2006","role":"author","urls":{},"keyword":["biomedical equipment;biomedical measurement;data analysis;decision trees;gait analysis;medical computing;neural nets;pattern classification;risk analysis;2 h;artificial neural network;automatic classification;automatically generated decision tree;custom decision tree;cycling;everyday activity classification;health risk;health-enhancing physical activity;healthier lifestyle;leave-one-subject-out cross validation;realistic data library;running;walking;wearable sensors;Artificial neural networks;Biomedical measurements;Cancer;Cardiovascular diseases;Classification tree analysis;Decision trees;Energy measurement;Legged locomotion;Testing;Wearable sensors;Activity classification;context awareness;physical activity;wearable sensors"],"downloads":0},"search_terms":["activity","classification","using","realistic","data","wearable","sensors","pärkkä","ermes","korpipää","mäntyjärvi","peltola","korhonen"],"keywords":["biomedical equipment;biomedical measurement;data analysis;decision trees;gait analysis;medical computing;neural nets;pattern classification;risk analysis;2 h;artificial neural network;automatic classification;automatically generated decision tree;custom decision tree;cycling;everyday activity classification;health risk;health-enhancing physical activity;healthier lifestyle;leave-one-subject-out cross validation;realistic data library;running;walking;wearable sensors;artificial neural networks;biomedical measurements;cancer;cardiovascular diseases;classification tree analysis;decision trees;energy measurement;legged locomotion;testing;wearable sensors;activity classification;context awareness;physical activity;wearable sensors"],"authorIDs":[],"dataSources":["iCsmKnycRmHPxmhBd"]}