Activity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection

By Piero Zappi, Clemens Lombriser, Thomas Stiefmeier, Elisabetta Farella, Daniel Roggen, Luca Benini, Gerhard Tröster. European Conference/Workshop on Wireless Sensor Networks, 2008

364 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fb9f2602d92808461d4c5bf18b00092b053218c8

How researchers see this paper

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

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Advanced internet of things for personalised healthcare systems: A survey (2017, methodology): “In healthcare, it studied gesture determination, including open/close hood, doors and trunk, checking steering wheel, etc. to assist doctors’ diagnosis [123].”
Recent trends in machine learning for human activity recognition—A survey (2018, methodology): “The authors optimized the hyperparameters of their network and fused the various sensor modalities such as accelerometer, gyroscope, and magnetometer in different combinations and compared the results by evaluating them on OPPORTUNITY (Roggen et al., 2009) and Skoda (Zappi et al., 2008) datasets.”
Machine Learning in Wireless Sensor Networks: Algorithms, Strategies, and Applications (2014, methodology): “[92] presented a real-time approach for activity recognition using WSNs that accurately detects body gesture and motion.”
Convolutional Neural Networks for human activity recognition using mobile sensors (2014, background): “• Skoda [33] The Skoda Mini Checkpoint dataset describes the activities of assembly-line workers in a car maintenance senario.”
Comparison of Data Preprocessing Approaches for Applying Deep Learning to Human Activity Recognition in the Context of Industry 4.0 (2018, background): “0 (daily activity data collected by a smartphone in an uncontrolled environment, with a sampling rate of 20 Hz) [34,35], and Skoda (manipulative gestures performed in a car maintenance scenario, with sampling rate of 98 Hz) [36].”
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, methodology): “Extensive experiments are performed on Opportunity [59], Skoda [316], and Hand-Gesture [49] datasets.”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, background): “[32] propose sensor selection algorithms to develop energy-aware systems that deal with the power vs.”
Privacy and Utility Preserving Sensor-Data Transformations (2019, methodology): “Skoda [40] is collected by an assembly-line worker in a car production company wearing 19 accelerometer sensors on his right and left arm and performing a set of pre-speciﬁed experiments.”
Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application (2008, methodology): “modeling using customized sensors worn by people [35][7] [36][6][37].”
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition (2016, methodology): “Performance changes are not significant in the case of the Skoda dataset, showing a plateau.”
Deep Learning for Sensor-based Human Activity Recognition (2020, background): “s (д). The sampling frequency is usually in the range of tens to hundreds of Hz. For recognizing human activities, accelerometers can be mounted on various parts of a body, such as the waist [7], arm [173], ankle [10], wrist [61], et al. There are three axes in an often-used accelerometer. Therefore”
Deep Recurrent Neural Networks for Human Activity Recognition (2017, methodology): “The proposed method results in an overall accuracy of 92.6%, outperforming other methods such as HMMs [23], DBNs [6], and CNNs [11], as shown in Figure 12b.”
Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey (2010, neutral): “Lester et al.[82] and Ward et al.[83] suggest personal activity recognition systems by using HMMs. Similarly, Zappi et al.[63] propose a dynamic sensor selection system used for HMM based recognition of manipulative activities of assembly line workers.”