scholarly journals Smartphone-Based Activity Recognition in a Pedestrian Navigation Context

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3243
Author(s):  
Robert Jackermeier ◽  
Bernd Ludwig
Keyword(s):  
Activity Recognition ◽  
Recognition Performance ◽  
Activity Patterns ◽  
Detailed Knowledge ◽  
Navigation Systems ◽  
Pedestrian Navigation ◽  
User Activity ◽  
Device Placement ◽  
Locomotion Behavior ◽  
Current Context

In smartphone-based pedestrian navigation systems, detailed knowledge about user activity and device placement is a key information. Landmarks such as staircases or elevators can help the system in determining the user position when located inside buildings, and navigation instructions can be adapted to the current context in order to provide more meaningful assistance. Typically, most human activity recognition (HAR) approaches distinguish between general activities such as walking, standing or sitting. In this work, we investigate more specific activities that are tailored towards the use-case of pedestrian navigation, including different kinds of stationary and locomotion behavior. We first collect a dataset of 28 combinations of device placements and activities, in total consisting of over 6 h of data from three sensors. We then use LSTM-based machine learning (ML) methods to successfully train hierarchical classifiers that can distinguish between these placements and activities. Test results show that the accuracy of device placement classification (97.2%) is on par with a state-of-the-art benchmark in this dataset while being less resource-intensive on mobile devices. Activity recognition performance highly depends on the classification task and ranges from 62.6% to 98.7%, once again performing close to the benchmark. Finally, we demonstrate in a case study how to apply the hierarchical classifiers to experimental and naturalistic datasets in order to analyze activity patterns during the course of a typical navigation session and to investigate the correlation between user activity and device placement, thereby gaining insights into real-world navigation behavior.

scholarly journals Behavioral and Neural Effects of Familiarization on Object-Background Associations

2020 ◽  
Vol 11 ◽  
Author(s):  
Oliver Baumann ◽  
Jessica McFadyen ◽  
Michael S. Humphreys
Keyword(s):  
Medial Temporal Lobe ◽  
Recognition Performance ◽  
Activity Patterns ◽  
Test Phase ◽  
Context Dependency ◽  
Study Phase ◽  
Activation Patterns ◽  
Hippocampal Activity ◽  
Current Context ◽  
Human Participants

Associative memory is the ability to link together components of stimuli. Previous evidence suggests that prior familiarization with study items affects the nature of the association between stimuli. More specifically, novel stimuli are learned in a more context-dependent fashion than stimuli that have been encountered previously without the current context. In the current study, we first acquired behavioral data from 62 human participants to conceptually replicate this effect. Participants were instructed to memorize multiple object-scene pairs (study phase) and were then tested on their recognition memory for the objects (test phase). Importantly, 1 day prior, participants had been familiarized with half of the object stimuli. During the test phase, the objects were either matched to the same scene as during study (intact pair) or swapped with a different object’s scene (rearranged pair). Our results conceptually replicated the context-dependency effect by showing that breaking up a studied object-context pairing is more detrimental to object recognition performance for non-familiarized objects than for familiarized objects. Second, we used functional magnetic resonance imaging (fMRI) to determine whether medial temporal lobe encoding-related activity patterns are reflective of this familiarity-related context effect. Data acquired from 25 human participants indicated a larger effect of familiarization on encoding-related hippocampal activity for objects presented within a scene context compared to objects presented alone. Our results showed that both retrieval-related accuracy patterns and hippocampal activation patterns were in line with a familiarization-mediated context-dependency effect.

scholarly journals Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1685
Author(s):  
Sakorn Mekruksavanich ◽  
Anuchit Jitpattanakul
Keyword(s):  
Neural Networks ◽  
Activity Recognition ◽  
Human Activities ◽  
Recognition Performance ◽  
Confusion Matrix ◽  
Experimental Studies ◽  
Industrial Applications ◽  
Sensor Data ◽  
Complex Activity ◽  
Activity Data

Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).

scholarly journals A Hybrid Framework for Mitigating Heading Drift for a Wearable Pedestrian Navigation System through Adaptive Fusion of Inertial and Magnetic Measurements

2021 ◽  
Vol 11 (4) ◽  
pp. 1902
Author(s):  
Liqiang Zhang ◽  
Yu Liu ◽  
Jinglin Sun
Keyword(s):  
Magnetic Measurements ◽  
Inertial Sensor ◽  
Angular Rate ◽  
Human Motion ◽  
Navigation Systems ◽  
Pedestrian Navigation ◽  
Hybrid Framework ◽  
Outdoor Environments ◽  
Adaptive Fusion ◽  
Indoor And Outdoor Environments

Pedestrian navigation systems could serve as a good supplement for other navigation methods or for extending navigation into areas where other navigation systems are invalid. Due to the accumulation of inertial sensing errors, foot-mounted inertial-sensor-based pedestrian navigation systems (PNSs) suffer from drift, especially heading drift. To mitigate heading drift, considering the complexity of human motion and the environment, we introduce a novel hybrid framework that integrates a foot-state classifier that triggers the zero-velocity update (ZUPT) algorithm, zero-angular-rate update (ZARU) algorithm, and a state lock, a magnetic disturbance detector, a human-motion-classifier-aided adaptive fusion module (AFM) that outputs an adaptive heading error measurement by fusing heuristic and magnetic algorithms rather than simply switching them, and an error-state Kalman filter (ESKF) that estimates the optimal systematic error. The validation datasets include a Vicon loop dataset that spans 324.3 m in a single room for approximately 300 s and challenging walking datasets that cover large indoor and outdoor environments with a total distance of 12.98 km. A total of five different frameworks with different heading drift correction methods, including the proposed framework, were validated on these datasets, which demonstrated that our proposed ZUPT–ZARU–AFM–ESKF-aided PNS outperforms other frameworks and clearly mitigates heading drift.

scholarly journals Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 692
Author(s):  
Jingcheng Chen ◽  
Yining Sun ◽  
Shaoming Sun
Keyword(s):  
Feature Selection ◽  
Activity Recognition ◽  
Human Activity ◽  
Joint Angle ◽  
Recognition Performance ◽  
Wearable Sensors ◽  
Estimation Algorithm ◽  
Recognition System ◽  
Human Activity Recognition ◽  
Time Frequency

Human activity recognition (HAR) is essential in many health-related fields. A variety of technologies based on different sensors have been developed for HAR. Among them, fusion from heterogeneous wearable sensors has been developed as it is portable, non-interventional and accurate for HAR. To be applied in real-time use with limited resources, the activity recognition system must be compact and reliable. This requirement can be achieved by feature selection (FS). By eliminating irrelevant and redundant features, the system burden is reduced with good classification performance (CP). This manuscript proposes a two-stage genetic algorithm-based feature selection algorithm with a fixed activation number (GFSFAN), which is implemented on the datasets with a variety of time, frequency and time-frequency domain features extracted from the collected raw time series of nine activities of daily living (ADL). Six classifiers are used to evaluate the effects of selected feature subsets from different FS algorithms on HAR performance. The results indicate that GFSFAN can achieve good CP with a small size. A sensor-to-segment coordinate calibration algorithm and lower-limb joint angle estimation algorithm are introduced. Experiments on the effect of the calibration and the introduction of joint angle on HAR shows that both of them can improve the CP.

scholarly journals Context-Aware Human Activity Recognition in Industrial Processes

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 134
Author(s):  
Friedrich Niemann ◽  
Stefan Lüdtke ◽  
Christian Bartelt ◽  
Michael ten Hompel
Keyword(s):  
Activity Recognition ◽  
Time Management ◽  
Recognition Performance ◽  
Context Information ◽  
Context Aware ◽  
Recognition Model ◽  
Movement Data ◽  
Information Activity ◽  
The Subject ◽  
Motion Capturing

The automatic, sensor-based assessment of human activities is highly relevant for production and logistics, to optimise the economics and ergonomics of these processes. One challenge for accurate activity recognition in these domains is the context-dependence of activities: Similar movements can correspond to different activities, depending on, e.g., the object handled or the location of the subject. In this paper, we propose to explicitly make use of such context information in an activity recognition model. Our first contribution is a publicly available, semantically annotated motion capturing dataset of subjects performing order picking and packaging activities, where context information is recorded explicitly. The second contribution is an activity recognition model that integrates movement data and context information. We empirically show that by using context information, activity recognition performance increases substantially. Additionally, we analyse which of the pieces of context information is most relevant for activity recognition. The insights provided by this paper can help others to design appropriate sensor set-ups in real warehouses for time management.

scholarly journals User Activity Recognition through Software Sensors

2017 ◽  
pp. 243-265 ◽  
Author(s):  
Stephan Reiff-Marganiec ◽  
Kamran Taj Pathan ◽  
Yi Hong
Keyword(s):  
Activity Recognition ◽  
Software Sensors ◽  
User Activity

scholarly journals Human-centred Mobile Pedestrian Navigation Systems

2011 ◽  
Vol 153 ◽  
pp. 237-250 ◽  
Author(s):  
Georg Garnter ◽  
Haosheng Huang ◽  
Alexandra Millonig ◽  
Manuela Schmidt ◽  
Felix Ortag
Keyword(s):  
Navigation Systems ◽  
Pedestrian Navigation

scholarly journals TWO NEW PEDESTRIAN NAVIGATION PATH OPTIONS BASED ON SEMI-INDOOR SPACE

2020 ◽  
Vol VI-4/W1-2020 ◽  
pp. 175-182
Author(s):  
J. Yan ◽  
S. Zlatanova ◽  
A. A. Diakite
Keyword(s):  
Path Selection ◽  
Selection Strategy ◽  
Navigation Systems ◽  
Indoor Space ◽  
Pedestrian Navigation ◽  
Navigation Path ◽  
Shortest Distance ◽  
Making Choices ◽  
Navigation Experience ◽  
Indoor Spaces

Abstract. Navigation is very critical for our daily life, especially when we have to go through the unfamiliar areas where the spaces are very complex, such as completely bounded (indoor), partially bounded (semi-indoor and/or semi-outdoor), entirely open (outdoor), or combined. Current navigation systems commonly offer the shortest distance/time path, but it is not always appropriate for some situations. For instance, on a rainy day, a path with as many places that are covered by roofs/shelters is more attractive. However, current navigation systems cannot provide such kinds of navigation paths, which can be explained by that they lack information about such roofed/sheltered-covered spaces. This paper proposes two roofed/sheltered navigation path options by employing semi-indoor spaces in the navigation map: (i) the Most-Top-Covered path (MTC-path) and (ii) path to the Nearest sI-space from departure (NSI-path). A path selection strategy is introduced to help pedestrians in making choices between the two new path options and the traditional shortest path. We demonstrate and validate the research with path planning on two navigation cases. The results show the two path options and the path selection strategy bring in new navigation experience for humans.

Sign in / Sign up

Export Citation Format

Share Document