Fusion of smartphone sensor data for classification of daily user activities
Gokhan Sengul,Erol Ozcelik,Sanjay Misra,Sanjay Misra,Robertas Damasevicius,Rytis Maskeliūnas +5 more
Reads0
Chats0
TLDR
A novel hybrid data fusion method to estimate three types of daily user activities using the accelerometer and gyroscope data acquired from a smart watch using a mobile phone and the k-Nearest Neighbor and Support Vector Machine classifiers.Abstract:
New mobile applications need to estimate user activities by using sensor data provided by smart wearable devices and deliver context-aware solutions to users living in smart environments. We propose a novel hybrid data fusion method to estimate three types of daily user activities (being in a meeting, walking, and driving with a motorized vehicle) using the accelerometer and gyroscope data acquired from a smart watch using a mobile phone. The approach is based on the matrix time series method for feature fusion, and the modified Better-than-the-Best Fusion (BB-Fus) method with a stochastic gradient descent algorithm for construction of optimal decision trees for classification. For the estimation of user activities, we adopted a statistical pattern recognition approach and used the k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers. We acquired and used our own dataset of 354 min of data from 20 subjects for this study. We report a classification performance of 98.32 % for SVM and 97.42 % for kNN.read more
Citations
More filters
Journal ArticleDOI
Deep learning based fall detection using smartwatches for healthcare applications
TL;DR: In this paper , a smart watch-based system was used to predict fall detection. But the accuracy of the fall detection was only 99.59% and 97.35% when considering only binary classification (falling vs all other activities), perfect accuracy was achieved when considering all activities.
Journal ArticleDOI
Deep learning based fall detection using smartwatches for healthcare applications
Gokhan Sengul,Rainer Glöckl,Murat Karakaya,Sanjay Misra,Olusola Abayomi-Alli,Robertas Damasevicius +5 more
TL;DR: In this paper, a smart watch-based system was used to predict fall detection. But the accuracy of the fall detection was only 99.59% and 97.35% when considering only binary classification (falling vs all other activities), perfect accuracy was achieved when considering all activities.
Journal ArticleDOI
Human Activity Recognition Based on Embedded Sensor Data Fusion for the Internet of Healthcare Things
Mohamed E. Issa,Ahmed Helmi,Mohammed A. A. Al-qaness,Abdelghani Dahou,Mohamed Abd Elaziz,Robertas Damaševičius +5 more
TL;DR: An efficient human activity recognition (HAR) model is presented based on efficient handcrafted features and Random Forest as a classifier for IoHT applications and results ensure the superiority of the applied model over others introduced in the literature for the same dataset.
Journal ArticleDOI
Improved Human Activity Recognition Using Majority Combining of Reduced-Complexity Sensor Branch Classifiers
TL;DR: This work considers the performance benefits from combining HAR classification estimates from multiple sensors each with lower-complexity processing compared with a higher- complexity single-sensor classifier and shows that while the highest single-Sensor classification accuracy of 91% can be achieved for seven activities, the classification accuracy is reduced to 56% with a reduced- Complexity 50-neuron classifier.
Journal ArticleDOI
Internet-of-Things-Based Suspicious Activity Recognition Using Multimodalities of Computer Vision for Smart City Security
TL;DR: This research applied fine-tuned YOLO-v4 for activity detection, whereas for classification purposes, 3D-CNN has been implemented and the proposed multimodal approach achieves remarkable activity detection and recognition accuracy.
References
More filters
Journal ArticleDOI
Statistical pattern recognition: a review
TL;DR: The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.
Journal ArticleDOI
Understanding and Using Context
TL;DR: An operational definition of context is provided and the different ways in which context can be used by context-aware applications are discussed, including the features and abstractions in the toolkit that make the task of building applications easier.
Journal ArticleDOI
Statistical Pattern Recognition
TL;DR: In this paper, the primary goal of pattern recognition is supervised or unsupervised classification, and the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been used.
Journal ArticleDOI
Using mobile phones to determine transportation modes
TL;DR: This work creates a convenient (no specific position and orientation setting) classification system that uses a mobile phone with a built-in GPS receiver and an accelerometer to identify the transportation mode of an individual when outside.
Journal ArticleDOI
Analysis and Modeling of Inertial Sensors Using Allan Variance
TL;DR: The theoretical basis for the Allan variance for modeling the inertial sensors' error terms and its implementation in modeling different grades of inertial sensor units are covered.