scholarly journals Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 588 ◽  
Author(s):  
Hoda Allahbakhshi ◽  
Lindsey Conrow ◽  
Babak Naimi ◽  
Robert Weibel
Keyword(s):  
Physical Activity ◽  
Real Life ◽  
Classification Performance ◽  
Training Data ◽  
Sensor Data ◽  
Gps Data ◽  
Accelerometer Data ◽  
Life Data ◽  
Sensor Position ◽  
Real Life Data

This paper aims to examine the role of global positioning system (GPS) sensor data in real-life physical activity (PA) type detection. Thirty-three young participants wore devices including GPS and accelerometer sensors on five body positions and performed daily PAs in two protocols, namely semi-structured and real-life. One general random forest (RF) model integrating data from all sensors and five individual RF models using data from each sensor position were trained using semi-structured (Scenario 1) and combined (semi-structured + real-life) data (Scenario 2). The results showed that in general, adding GPS features (speed and elevation difference) to accelerometer data improves classification performance particularly for detecting non-level and level walking. Assessing the transferability of the models on real-life data showed that models from Scenario 2 are strongly transferable, particularly when adding GPS data to the training data. Comparing individual models indicated that knee-models provide comparable classification performance (above 80%) to general models in both scenarios. In conclusion, adding GPS data improves real-life PA type classification performance if combined data are used for training the model. Moreover, the knee-model provides the minimal device configuration with reliable accuracy for detecting real-life PA types.

scholarly journals Real-Time Physical Activity Recognition on Smart Mobile Devices Using Convolutional Neural Networks

2020 ◽  
Vol 10 (23) ◽  
pp. 8482
Author(s):  
Konstantinos Peppas ◽  
Apostolos C. Tsolakis ◽  
Stelios Krinidis ◽  
Dimitrios Tzovaras
Keyword(s):  
Neural Network ◽  
Physical Activity ◽  
Real Time ◽  
Mobile Devices ◽  
Mobile Device ◽  
Classification Performance ◽  
Sensor Data ◽  
Accelerometer Data ◽  
Smart Mobile ◽  
Fully Connected

Given the ubiquity of mobile devices, understanding the context of human activity with non-intrusive solutions is of great value. A novel deep neural network model is proposed, which combines feature extraction and convolutional layers, able to recognize human physical activity in real-time from tri-axial accelerometer data when run on a mobile device. It uses a two-layer convolutional neural network to extract local features, which are combined with 40 statistical features and are fed to a fully-connected layer. It improves the classification performance, while it takes up 5–8 times less storage space and outputs more than double the throughput of the current state-of-the-art user-independent implementation on the Wireless Sensor Data Mining (WISDM) dataset. It achieves 94.18% classification accuracy on a 10-fold user-independent cross-validation of the WISDM dataset. The model is further tested on the Actitracker dataset, achieving 79.12% accuracy, while the size and throughput of the model are evaluated on a mobile device.

Evolutionary Induction of Mixed Decision Trees

2008 ◽  
pp. 3509-3523
Author(s):  
Marek Kretowski ◽  
Marek Grzes
Keyword(s):  
Decision Trees ◽  
System Performance ◽  
Real Life ◽  
Training Data ◽  
Genetic Operators ◽  
Life Data ◽  
Real Life Data ◽  
Hyper Plane ◽  
Optimal Tree ◽  
Node Type

This article presents a new evolutionary algorithm (EA) for induction of mixed decision trees. In nonterminal nodes of a mixed tree, different types of tests can be placed, ranging from a typical inequality test up to an oblique test based on a splitting hyper-plane. In contrast to classical top-down methods, the proposed system searches for an optimal tree in a global manner, that is it learns a tree structure and finds tests in one run of the EA. Specialized genetic operators are developed, which allow the system to exchange parts of trees, generating new sub-trees, pruning existing ones as well as changing the node type and the tests. An informed mutation application scheme is introduced and the number of unprofitable modifications is reduced. The proposed approach is experimentally verified on both artificial and real-life data and the results are promising. Scaling of system performance with increasing training data size was also investigated.

Automated Iterative Gap Filling Method for Drilling Logs and Other Data Series

2021 ◽  
Author(s):  
Andrzej T. Tunkiel ◽  
Dan Sui ◽  
Tomasz Wiktorski
Keyword(s):  
Missing Values ◽  
Real Life ◽  
Single Step ◽  
Training Data ◽  
Data Series ◽  
Iterative Approach ◽  
Gap Filling ◽  
Life Data ◽  
Real Life Data ◽  
Multiple Issues

Abstract Data scientists are facing multiple issues when working with real-life data. Logs are rarely devoid of incorrect values and one of the common categories of data problems is missing values. Gaps in logs are of various shapes, sizes, and quantities, with a plethora of techniques to infill, or restore missing values. No single algorithm will perform best for all scenarios, hence in pursuit of best results exploration of various options is necessary. Furthermore, gap filling in single step may be impossible for certain methods, where gaps exist for multiple attributes. This paper explores an automated iterative approach, where a selection of common algorithms and different input combinations are evaluated on existing data to select the best method based on R2 score. With the ability to perform iterative infilling, where previously imputed data is re-used as training data to patch other gaps, this represents the most automated and universal approach for gap filling in real-life data-series. This paper presents the methodologies and issues behind automated iterative approach to gap filling, and discusses what is necessary to achieve the final goal of high quality, one-click and optimal data infilling.

Neuropsychology in the Real World

2014 ◽  
Vol 25 (4) ◽  
pp. 233-238 ◽  
Author(s):  
Martin Peper ◽  
Simone N. Loeffler
Keyword(s):  
Neuropsychological Assessment ◽  
Real World ◽  
Ecological Validity ◽  
Real Life ◽  
Emotional States ◽  
Context Sensitive ◽  
Traditional Assessment ◽  
Life Data ◽  
Real Life Data ◽  
Assessment And Treatment

Current ambulatory technologies are highly relevant for neuropsychological assessment and treatment as they provide a gateway to real life data. Ambulatory assessment of cognitive complaints, skills and emotional states in natural contexts provides information that has a greater ecological validity than traditional assessment approaches. This issue presents an overview of current technological and methodological innovations, opportunities, problems and limitations of these methods designed for the context-sensitive measurement of cognitive, emotional and behavioral function. The usefulness of selected ambulatory approaches is demonstrated and their relevance for an ecologically valid neuropsychology is highlighted.

Sign in / Sign up

Export Citation Format

Share Document