BACKGROUND: KNOWME Networks is a wireless body area network with 2 triaxial accelerometers, a heart rate monitor, and mobile phone that acts as the data collection hub. One function of KNOWME Networks is to detect physical activity (PA) in overweight Hispanic youth. The purpose of this study was to evaluate the in-laboratory recognition accuracy of KNOWME. METHODS: Twenty overweight Hispanic participants (10 males; age 14.6 ± 1.8 years), underwent 4 data collection sessions consisting of 9 activities/session: lying down, sitting, sitting fidgeting, standing, standing fidgeting, standing playing an active video game, slow walking, brisk walking, and running. Data were used to train activity recognition models. The accuracy of personalized and generalized models is reported. RESULTS: Overall accuracy for personalized models was 84%. The most accurately detected activity was running (96%). The models had difficulty distinguishing between the static and fidgeting categories of sitting and standing. When static and fidgeting activity categories were collapsed, the overall accuracy improved to 94%. Personalized models demonstrated higher accuracy than generalized models. CONCLUSIONS: KNOWME Networks can accurately detect a range of activities. KNOWME has the ability to collect and process data in real-time, building the foundation for tailored, real-time interventions to increase PA or decrease sedentary time.
BACKGROUND: KNOWME Networks is a wireless body area network with 2 triaxial accelerometers, a heart rate monitor, and mobile phone that acts as the data collection hub. One function of KNOWME Networks is to detect physical activity (PA) in overweight Hispanic youth. The purpose of this study was to evaluate the in-laboratory recognition accuracy of KNOWME. METHODS: Twenty overweight Hispanic participants (10 males; age 14.6 ± 1.8 years), underwent 4 data collection sessions consisting of 9 activities/session: lying down, sitting, sitting fidgeting, standing, standing fidgeting, standing playing an active video game, slow walking, brisk walking, and running. Data were used to train activity recognition models. The accuracy of personalized and generalized models is reported. RESULTS: Overall accuracy for personalized models was 84%. The most accurately detected activity was running (96%). The models had difficulty distinguishing between the static and fidgeting categories of sitting and standing. When static and fidgeting activity categories were collapsed, the overall accuracy improved to 94%. Personalized models demonstrated higher accuracy than generalized models. CONCLUSIONS: KNOWME Networks can accurately detect a range of activities. KNOWME has the ability to collect and process data in real-time, building the foundation for tailored, real-time interventions to increase PA or decrease sedentary time.
Authors: Gautam Thatte; Ming Li; Adar Emken; Urbashi Mitra; Shri Narayanan; Murali Annavaram; Donna Spruijt-Metz Journal: Conf Proc IEEE Eng Med Biol Soc Date: 2009
Authors: Danice K Eaton; Laura Kann; Steve Kinchen; Shari Shanklin; James Ross; Joseph Hawkins; William A Harris; Richard Lowry; Tim McManus; David Chyen; Connie Lim; Nancy D Brener; Howell Wechsler Journal: MMWR Surveill Summ Date: 2008-06-06
Authors: Daniel Santiago Madrigal; Alicia Salvatore; Gardenia Casillas; Crystal Casillas; Irene Vera; Brenda Eskenazi; Meredith Minkler Journal: Prog Community Health Partnersh Date: 2014
Authors: D Spruijt-Metz; C K F Wen; G O'Reilly; M Li; S Lee; B A Emken; U Mitra; M Annavaram; G Ragusa; S Narayanan Journal: Curr Obes Rep Date: 2015-12
Authors: P T Katzmarzyk; S Barlow; C Bouchard; P M Catalano; D S Hsia; T H Inge; C Lovelady; H Raynor; L M Redman; A E Staiano; D Spruijt-Metz; M E Symonds; M Vickers; D Wilfley; J A Yanovski Journal: Int J Obes (Lond) Date: 2014-03-25 Impact factor: 5.095