{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:42:54Z","timestamp":1789476174612,"version":"build-2803163510"},"reference-count":44,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2013,9,27]],"date-time":"2013-09-27T00:00:00Z","timestamp":1380240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Smartphone-based activity recognition (SP-AR) recognizes users\u2019 activities using the embedded accelerometer sensor. Only a small number of previous works can be classified as online systems, i.e., the whole process (pre-processing, feature extraction, and classification) is performed on the device. Most of these online systems use either a high sampling rate (SR) or long data-window (DW) to achieve high accuracy, resulting in short battery life or delayed system response, respectively. This paper introduces a real-time\/online SP-AR system that solves this problem. Exploratory data analysis was performed on acceleration signals of 6 activities, collected from 30 subjects, to show that these signals are generated by an autoregressive (AR) process, and an accurate AR-model in this case can be built using a low SR (20 Hz) and a small DW (3 s). The high within class variance resulting from placing the phone at different positions was reduced using kernel discriminant analysis to achieve position-independent recognition. Neural networks were used as classifiers. Unlike previous works, true subject-independent evaluation was performed, where 10 new subjects evaluated the system at their homes for 1 week. The results show that our features outperformed three commonly used features by 40% in terms of accuracy for the given SR and DW.<\/jats:p>","DOI":"10.3390\/s131013099","type":"journal-article","created":{"date-parts":[[2013,9,27]],"date-time":"2013-09-27T12:42:41Z","timestamp":1380285761000},"page":"13099-13122","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":88,"title":["Exploratory Data Analysis of Acceleration Signals to Select Light-Weight  and Accurate Features for Real-Time Activity Recognition on Smartphones"],"prefix":"10.3390","volume":"13","author":[{"given":"Adil","family":"Khan","sequence":"first","affiliation":[{"name":"Division of Information and Computer Engineering, Ajou University, San 5 Woncheon-dong, Suwon 443-749, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Siddiqi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8569-0236","authenticated-orcid":false,"given":"Seok-Won","family":"Lee","sequence":"additional","affiliation":[{"name":"Division of Information and Computer Engineering, Ajou University, San 5 Woncheon-dong, Suwon 443-749, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2013,9,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1007\/s11768-011-0260-7","article-title":"Comparison of fusion methods based on DST and DBN in human activity recognition","volume":"9","author":"Tolstikov","year":"2011","journal-title":"J. Control Theory Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s11390-011-9430-9","article-title":"Activity Recognition based on RFID object usage for smart mobile devices","volume":"26","author":"Yang","year":"2011","journal-title":"J. Comput. Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1007\/s10489-010-0217-4","article-title":"GPARS: A general-purpose activity recognition system","volume":"35","author":"Sarkar","year":"2011","journal-title":"Appl. Intell."},{"key":"ref_4","unstructured":"Ribeiro, P., and Santos-Victor, J. (, January September,). Human Activity Recognition from Video: Modeling, Feature Selection and Classification Architecture. Oxford, UK."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/TITS.2009.2030963","article-title":"Understanding transit scenes: A survey on human behavior-recognition algorithms","volume":"11","author":"Candamo","year":"2010","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"R1","DOI":"10.1088\/0967-3334\/25\/2\/R01","article-title":"Accelerometry: Providing an integrated, practical method for long-term, ambulatory monitoring of human movement","volume":"25","author":"Mathie","year":"2004","journal-title":"Physiol. Meas."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1109\/TBME.2003.812189","article-title":"Ambulatory system for human motion analysis using a kinematic sensor: Monitoring of daily physical activity in the elderly","volume":"50","author":"Najafi","year":"2003","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bao, L., and Intille, S. (2004). Activity Recognition from User-Annotated Acceleration Data, Springer.","DOI":"10.1007\/978-3-540-24646-6_1"},{"key":"ref_9","unstructured":"Ravi, N., Dandekar, N., Mysore, P., and Littman, M. (2005, January 9\u201313). Activity Recognition from Accelerometer Data. Menlo Park, CA, USA."},{"key":"ref_10","unstructured":"Wang, S., Yang, J., Chen, N., Chen, X., and Zhang, Q. (2005, January 13\u201315). Human Activity Recognition with User-Free Accelerometers in the Sensor Networks. Beijing, China."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1258\/135763304323070788","article-title":"A pilot study of long-term monitoring of human movements in the home using accelerometry","volume":"10","author":"Mathie","year":"2004","journal-title":"J. Telemed. Telecare"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Khan, A., Lee, Y., and Kim, T. (2008, January 20\u201325). Accelerometer Signal-Based Human Activity Recognition Using Augmented Autoregressive Model Coefficients and Artificial Neural Nets. Vancouver, BC, Canada.","DOI":"10.1109\/IEMBS.2008.4650379"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Huynh, T., and Schiele, B. (2005, January 12\u201314). Analyzing Features for Activity Recognition. Grenoble, France.","DOI":"10.1145\/1107548.1107591"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kao, T.P., Lin, C.W., and Wang, J.S. (2009, January 5\u20138). Development of a Portable Activity Detector for Daily Activity Recognition. Seoul, Korea.","DOI":"10.1109\/ISIE.2009.5222001"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Jatob\u00e1, L.C., Grossmann, U., Kunze, C., Ottenbacher, J., and Stork, W. (2008, January 20\u201325). Context-Aware Mobile Health Monitoring: Evaluation of Different Pattern Recognition Methods for Classification of Physical Activity. Vancouver, BC, Canada.","DOI":"10.1109\/IEMBS.2008.4650398"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Helmi, M., and AlModarresi, S. (2009, January 20\u201324). Human Activity Recognition Using a Fuzzy Inference System. Jeju Island, Korea.","DOI":"10.1109\/FUZZY.2009.5277329"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, M., and Sawchuk, A.A. (2011, January 17\u201321). A Bag-of-Features-Based Framework for Human Activity Representation and Recognition. Beijing, China.","DOI":"10.1145\/2030045.2030058"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Casale, P., Pujol, O., and Radeva, P. (2011). Human activity recognition from accelerometer data using a wearable device. Pattern Recognit. Image Anal.","DOI":"10.1007\/978-3-642-21257-4_36"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1007\/s10489-013-0427-7","article-title":"EFM: Evolutionary fuzzy model for dynamic activities recognition using a smartphone accelerometer","volume":"39","author":"Fahim","year":"2013","journal-title":"Appl. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lara, O.D., and Labrador, M.A. (2012, January 14\u201317). A Mobile Platform for Real-Time Human Activity Recognition. Las Vegas, NV, USA.","DOI":"10.1109\/CCNC.2012.6181018"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Berchtold, M., Budde, M., Gordon, D., Schmidtke, H., and Beigl, M. (2010, January 10\u201313). Actiserv: Activity Recognition Service for Mobile Phones. Seoul, Korea.","DOI":"10.1109\/ISWC.2010.5665868"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1145\/1964897.1964918","article-title":"Activity recognition using cell phone accelerometers","volume":"12","author":"Kwapisz","year":"2011","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1007\/s11036-008-0112-y","article-title":"An activity recognition system for mobile phones","volume":"14","year":"2009","journal-title":"Mob. Netw. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lu, H., Yang, J., Liu, Z., Lane, N.D., Choudhury, T., and Campbell, A.T. (2010, January 3\u20135). The Jigsaw Continuous Sensing Engine for Mobile Phone Applications. Zurich, Switzerland.","DOI":"10.1145\/1869983.1869992"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sun, L., Zhang, D., Li, B., Guo, B., and Li, S. (2010, January 26\u201329). Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations. Xi'an, China.","DOI":"10.1007\/978-3-642-16355-5_42"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, S., Chen, C., and Ma, J. (2010, January 17\u201318). Accelerometer Based Transportation Mode Recognition on Mobile Phones. Shenzhen, China.","DOI":"10.1109\/APWCS.2010.18"},{"key":"ref_27","first-page":"38","article-title":"Recognizing human activities user-independently on smartphones based on accelerometer data","volume":"1","author":"Siirtola","year":"2012","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"key":"ref_28","first-page":"630","article-title":"Activity recognition with mobile phones","volume":"6913","author":"Frank","year":"2011","journal-title":"Mach. Learn. Knowl. Dis. Databases"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gomes, J.B., Krishnaswamy, S., Gaber, M.M., Sousa, P.A.C., and Menasalvas, E. (2012, January 23\u201326). MARS: A Personalised Mobile Activity Recognition System. Bangalore, India.","DOI":"10.1109\/MDM.2012.33"},{"key":"ref_30","first-page":"849","article-title":"Online classifier construction algorithm for human activity detection using a tri-axial accelerometer","volume":"205","author":"Chen","year":"2008","journal-title":"Appl. Math. Comput."},{"key":"ref_31","unstructured":"Mantyjarvi, J., Lindholm, M., Vildjiounaite, E., Makela, S.M., and Ailisto, H. (2005, January 18\u201323). Identifying Users of Portable Devices from Gait Pattern with Accelerometers. Philadelphia, PA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"He, Z., and Jin, L. (2009, January 11\u201314). Activity Recognition from Acceleration Data Based on Discrete Consine Transform and SVM. San Antonio, TX, USA.","DOI":"10.1109\/ICSMC.2009.5346042"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/TITB.2010.2051955","article-title":"A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer","volume":"14","author":"Khan","year":"2010","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ryder, J., Longstaff, B., Reddy, S., and Estrin, D. (2009, January 29\u201331). Ambulation: A Tool for Monitoring Mobility Patterns over Time Using Mobile Phones. Vancouver, BC, Canada.","DOI":"10.1109\/CSE.2009.312"},{"key":"ref_35","unstructured":"Zhang, S. (2012). Smartphone Based Activity Recognition System. [Ph.D. Thesis, Computer Science and Engineering, The Ohio State University]."},{"key":"ref_36","unstructured":"Croarkin, C. (2010). NIST\/SEMATECH e-Handbook of Statistical Methods, United States Department of Commerce."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1007\/s10877-005-7089-x","article-title":"Tutorial on univariate autoregressive spectral analysis","volume":"19","author":"Takalo","year":"2005","journal-title":"J. Clin. Monit. Comput."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","article-title":"A new look at the statistical model identification","volume":"19","author":"Akaike","year":"1974","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1162\/089976600300014980","article-title":"Generalized discriminant analysis using a kernel approach","volume":"12","author":"Baudat","year":"2000","journal-title":"Neural Comput."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/TITB.2007.899496","article-title":"Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions","volume":"12","author":"Ermes","year":"2008","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/MEMB.2003.1213624","article-title":"Mobile monitoring with wearable photoplethysmographic biosensors","volume":"22","author":"Asada","year":"2003","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1016\/S0747-5632(99)00037-0","article-title":"Detection of posture and motion by accelerometry: A validation study in ambulatory monitoring","volume":"15","author":"Foerster","year":"1999","journal-title":"Comput. Hum. Behav."},{"key":"ref_43","unstructured":"Burg, J.P. (1967, January 31). Maximum Entropy Spectral Analysis. Oklahoma City, OK, USA."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/JPROC.2004.840301","article-title":"The design and implementation of FFTW3","volume":"93","author":"Frigo","year":"2005","journal-title":"IEEE Proc."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/13\/10\/13099\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:49:35Z","timestamp":1760219375000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/13\/10\/13099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,27]]},"references-count":44,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2013,10]]}},"alternative-id":["s131013099"],"URL":"https:\/\/doi.org\/10.3390\/s131013099","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,27]]}}}