Activity Recognition from Accelerometer Data

By Nishkam Ravi, Nikhil Dandekar, Preetham Mysore, Michael L. Littman. AAAI Conference on Artificial Intelligence, 2005

1,777 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/bbde9ef4a4b4da0620b14a25c5a4a3d6bd4780e5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Creating and benchmarking a new dataset for physical activity monitoring (2012, unknown): “ascending stairs [14].”
Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations (2010, background): “Ravi et al [14] places an accelerometer embedded hoarder board near the pelvic region to detect similar activities, demonstrating the ability of distinguishing daily physical activities with a single accelerometer.”
A Scalable Approach to Activity Recognition based on Object Use (2007, background): “In other approaches, information from accelerometers is used to identify actions such as walking and climbing stairs [1, 20].”
Activity recognition in beach volleyball using a Deep Convolutional Neural Network (2017, methodology): “They have also been employed for the recognition of daily life activities (Bao and Intille 2004; Leutheuser e tal. 2013; Ravi et al. 2005), gesture recognition (Nguyen-Dinh et al.”
Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers (2010, background): “[40] 1 3D acc Standard deviation Energy distribution DC component Correlation coefficients Naive Bayesian k-NN SVM Binary decision 8 NA 46.”
An Activity Recognition System For Mobile Phones (2009, methodology): “Utilizing the same toolkit but only a single triaxial accelerometer worn in the pelvic region, Ravi et al. [ 20 ] studied the performance of base-level classifier algorithms as well as the meta-classifiers, including voting, stacking, and cascading frameworks.”
On-body localization of wearable devices: An investigation of position-aware activity recognition (2016, methodology): “The sampling rate was chosen with consideration of battery life as well as with reference to previous studies [7], [14].”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “Plenty of traditional hand-crafted feature-based approaches [57], [312], [313], [314], [316], [317], [318], [319], [320] have been proposed for HAR using acceleration data.”
Activity identification using body-mounted sensors—a review of classification techniques (2009, methodology): “For example, Maurer et al (2006) and Ravi et al (2005) found this approach to either outperform or match the classification accuracy of other methods, whereas Bao and Intille (2004) found low levels of classification accuracy.”
Simple and Complex Activity Recognition through Smart Phones (2012, methodology): “[5] use a single accelerometer mounted onto the pelvic region of subjects to collect data on eight activities: Standing, walking, running, climbing up stairs, climbing down stairs, situps, vacuuming, and brushing teeth.”
Sensor-Based Activity Recognition (2012, background): “Some authors have attempted to compare discriminative and generative models [48], [153], generally”
Preprocessing techniques for context recognition from accelerometer data (2010, methodology): “The sample correlation coefficient was applied in [43] in order to determine which are the best classifiers (or combination of them) for recognizing activities, and which among several features/attributes are the most important.”
Real-Time Pervasive Monitoring for Postoperative Care (2007, background): “Most early studies for activity recognition are based on empirical feature selection techniques[23-26].”
Physical Human Activity Recognition Using Wearable Sensors (2015, background): “…the number of activities does not exceed ten activities. was used to recognize activities such as sitting, standing, lying, walking, A large number of activities were considered in [27] (sixteen activities) and [7] (twelve activities). running, scrubbing, vacuuming, brushing teeth, falling, etc .”
Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine (2012, methodology): “In particular, we make use of SVMs for classification as it was also used in [7] and [8].”
A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer (2010, methodology): “Block diagram for our proposed recognition technique. several existing studies with varying success rates [10] , [13], [18] .”
Activity recognition with smartphone sensors (2014, methodology): “[19], Ravi et al. conducted a comparative study in terms of classifying eight activities.”