Journal ArticleDOI
Activity classification and dead reckoning for pedestrian navigation with wearable sensors
Reads0
Chats0
TLDR
This research provides a possible seamless pedestrian navigation solution which can be applied to a wide range of areas where the global navigation satellite system (GNSS) signal remains vulnerable.Abstract:
This paper addresses an approach which integrates activity classification and dead reckoning techniques in step-based pedestrian navigation. In the proposed method, the pedestrian is equipped with a prototype wearable sensor module to record accelerations and determine the headings while walking. To improve the step detection accuracy, different types of activities are classified according to extracted features by means of a probabilistic neural network (PNN). The vertical acceleration data, which indicate the periodic vibration during gait cycle are filtered through a wavelet transform before being used to count the steps and assess the step length from which the distance traveled is estimated. By coupling the distance with the azimuth, navigation through pedestrian dead reckoning is implemented. This research provides a possible seamless pedestrian navigation solution which can be applied to a wide range of areas where the global navigation satellite system (GNSS) signal remains vulnerable. Results of two experiments in this paper reveal that the proposed approach is effective in reducing navigation errors and improving accuracy.read more
Citations
More filters
Book
Indoor Positioning Technologies
TL;DR: This work aims to provide arobust, scalable, scalable and scalable approach to Indoor Positioning that combines 3D Building Modeling, 3D Targeting, and 3D Sensors into a single system.
Proceedings ArticleDOI
Self-contained indoor positioning on off-the-shelf mobile devices
TL;DR: This work introduces a novel self-contained seamless positioning solution for indoor and outdoor environments, well suited for and designed to be operated on off-the-shelf mobile phones.
Journal ArticleDOI
An Incremental Learning Method Based on Probabilistic Neural Networks and Adjustable Fuzzy Clustering for Human Activity Recognition by Using Wearable Sensors
TL;DR: The experimental results showed that the proposed incremental learning method achieved a good tradeoff between incremental learning ability and the recognition accuracy and the experimental results from comparison with other classification methods demonstrated the effectiveness of the proposed method.
Proceedings ArticleDOI
Improved heading estimation for smartphone-based indoor positioning systems
TL;DR: This paper proposes a practical indoor positioning method to handle complicated human movements and noisy inertial sensors in smartphones using recently introduced smartphones equipped with sensors such as accelerometer, magnetometer, and gyroscope and shows 2.42 times accuracy over than traditional methods on the average.
Journal ArticleDOI
Continuous Hidden Markov Model for Pedestrian Activity Classification and Gait Analysis
TL;DR: The achieved relative figure of merits using the collected data validates the reliability of the proposed methods for the desired applications and permits the potential application of the current study in camera-aided inertial navigation for positioning and personal assistance for future research works.
References
More filters
Book ChapterDOI
Activity recognition from user-annotated acceleration data
Ling Bao,Stephen S. Intille +1 more
TL;DR: This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves, and suggests that multiple accelerometers aid in recognition.
Journal ArticleDOI
Active control of lateral balance in human walking
Catherine E. Bauby,Arthur D. Kuo +1 more
TL;DR: The results imply that humans may harness passive dynamic properties of the limbs in the sagittal plane, but must provide significant active control in order to stabilize lateral motion.
Proceedings ArticleDOI
Probabilistic neural networks for classification, mapping, or associative memory
TL;DR: It can be shown that by replacing the sigmoid activation function often used in neural networks with an exponential function, a neural network can be formed which computes nonlinear decision boundaries, which yields decision surfaces which approach the Bayes optimal under certain conditions.
Patent
Dead reckoning navigational system using accelerometer to measure foot impacts
Robert W. Levi,Thomas Judd +1 more
TL;DR: In this paper, a microcomputer assisted position finding system that integrates GPS data, dead reckoning sensors, and digital maps into a low-cost, self-contained navigation instrument is disclosed.
Proceedings ArticleDOI
What shall we teach our pants
K. Van Laerhoven,Ozan Cakmakci +1 more
TL;DR: Using a combination of machine learning techniques such as Kohonen maps and probabilistic models, this work builds a system that is able to learn activities while requiring minimal user attention.