Sensors

Research

Jump to: Review

18 pages, 18009 KiB

Open AccessArticle

Position-Aware Indoor Human Activity Recognition Using Multisensors Embedded in Smartphones

by Xiaoqing Wang, Yue Wang and Jiaxuan Wu

Sensors 2024, 24(11), 3367; https://doi.org/10.3390/s24113367 - 24 May 2024

Cited by 1 | Viewed by 854

Abstract

Composite indoor human activity recognition is very important in elderly health monitoring and is more difficult than identifying individual human movements. This article proposes a sensor-based human indoor activity recognition method that integrates indoor positioning. Convolutional neural networks are used to extract spatial [...] Read more.

Composite indoor human activity recognition is very important in elderly health monitoring and is more difficult than identifying individual human movements. This article proposes a sensor-based human indoor activity recognition method that integrates indoor positioning. Convolutional neural networks are used to extract spatial information contained in geomagnetic sensors and ambient light sensors, while transform encoders are used to extract temporal motion features collected by gyroscopes and accelerometers. We established an indoor activity recognition model with a multimodal feature fusion structure. In order to explore the possibility of using only smartphones to complete the above tasks, we collected and established a multisensor indoor activity dataset. Extensive experiments verified the effectiveness of the proposed method. Compared with algorithms that do not consider the location information, our method has a 13.65% improvement in recognition accuracy. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

23 pages, 944 KiB

Open AccessArticle

Unobtrusive Cognitive Assessment in Smart-Homes: Leveraging Visual Encoding and Synthetic Movement Traces Data Mining

by Samaneh Zolfaghari, Annica Kristoffersson, Mia Folke, Maria Lindén and Daniele Riboni

Sensors 2024, 24(5), 1381; https://doi.org/10.3390/s24051381 - 21 Feb 2024

Viewed by 1056

Abstract

The ubiquity of sensors in smart-homes facilitates the support of independent living for older adults and enables cognitive assessment. Notably, there has been a growing interest in utilizing movement traces for identifying signs of cognitive impairment in recent years. In this study, we [...] Read more.

The ubiquity of sensors in smart-homes facilitates the support of independent living for older adults and enables cognitive assessment. Notably, there has been a growing interest in utilizing movement traces for identifying signs of cognitive impairment in recent years. In this study, we introduce an innovative approach to identify abnormal indoor movement patterns that may signal cognitive decline. This is achieved through the non-intrusive integration of smart-home sensors, including passive infrared sensors and sensors embedded in everyday objects. The methodology involves visualizing user locomotion traces and discerning interactions with objects on a floor plan representation of the smart-home, and employing different image descriptor features designed for image analysis tasks and synthetic minority oversampling techniques to enhance the methodology. This approach distinguishes itself by its flexibility in effortlessly incorporating additional features through sensor data. A comprehensive analysis, conducted with a substantial dataset obtained from a real smart-home, involving 99 seniors, including those with cognitive diseases, reveals the effectiveness of the proposed functional prototype of the system architecture. The results validate the system’s efficacy in accurately discerning the cognitive status of seniors, achieving a macro-averaged F₁-score of 72.22% for the two targeted categories: cognitively healthy and people with dementia. Furthermore, through experimental comparison, our system demonstrates superior performance compared with state-of-the-art methods. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

Figure 1
Example of movement patterns based on the Martino-Saltzman model, adopted from [<a href="#B18-sensors-24-01381" class="html-bibr">18</a>]. In (a), all four trajectories seem abnormal without context. Solid lines resemble direct and random walks, the dashed line indicates pacing, and the dotted line suggests a lapping movement. Within the home floor plan context (b), only one trajectory is likely abnormal. Green solid lines represent the shortest paths, the back-and-forth movement in the kitchen (green dashed line) might be a normal table-setting activity, while the repeated looping movement in the living room (red dotted line) could indicate an abnormal lapping pattern, possibly linked to cognitive issues. Full article ">Figure 2
Overview of the functional prototype of the system architecture. Full article ">Figure 3
(a) Illustration of an encoded image showcasing directional changes. Dashed boxes in black and white highlight regions of interest, each zoomed in on the right. (b) Zoomed views reveal details within the boxed areas. White points indicate right-side directional changes, Brown points indicate left-side directional changes, and Vivid violet points indicate movement towards the central position. The shade level of the Blue line depends on the speed of the movement. Full article ">Figure 4
Macro-averaged <math display="inline"><semantics> <msub> <mi>F</mi> <mn>1</mn> </msub> </semantics></math>-scores (a) and weighted-averaged <math display="inline"><semantics> <msub> <mi>F</mi> <mn>1</mn> </msub> </semantics></math>-scores (b) for cognitive assessment by employing traditional models and LOPO cross-validation, taking into account both CRF and SURF. Full article ">Figure 5
Macro-averaged (a) and weighted-averaged measures (b) for long-term cognitive assessment. Full article ">Figure 5 Cont.
Macro-averaged (a) and weighted-averaged measures (b) for long-term cognitive assessment. Full article ">

17 pages, 1554 KiB

Open AccessArticle

A Hybrid Protection Scheme for the Gait Analysis in Early Dementia Recognition

by Francesco Castro, Donato Impedovo and Giuseppe Pirlo

Sensors 2024, 24(1), 24; https://doi.org/10.3390/s24010024 - 19 Dec 2023

Cited by 1 | Viewed by 1602

Abstract

Human activity recognition (HAR) through gait analysis is a very promising research area for early detection of neurodegenerative diseases because gait abnormalities are typical symptoms of some neurodegenerative diseases, such as early dementia. While working with such biometric data, the performance parameters must [...] Read more.

Human activity recognition (HAR) through gait analysis is a very promising research area for early detection of neurodegenerative diseases because gait abnormalities are typical symptoms of some neurodegenerative diseases, such as early dementia. While working with such biometric data, the performance parameters must be considered along with privacy and security issues. In other words, such biometric data should be processed under specific security and privacy requirements. This work proposes an innovative hybrid protection scheme combining a partially homomorphic encryption scheme and a cancelable biometric technique based on random projection to protect gait features, ensuring patient privacy according to ISO/IEC 24745. The proposed hybrid protection scheme has been implemented along a long short-term memory (LSTM) neural network to realize a secure early dementia diagnosis system. The proposed protection scheme is scalable and implementable with any type of neural network because it is independent of the network’s architecture. The conducted experiments demonstrate that the proposed protection scheme enables a high trade-off between safety and performance. The accuracy degradation is at most 1.20% compared with the early dementia recognition system without the protection scheme. Moreover, security and computational analyses of the proposed scheme have been conducted and reported. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

Figure 1
Overall model of an early dementia recognition system with the implementation of the proposed hybrid protection scheme. Full article ">Figure 2
Random projection approach. Full article ">Figure 3
LSTM model architecture. Full article ">Figure 4
Setup of the data collection process. Full article ">Figure 5
Video capture and preprocessing. Full article ">Figure 6
Benchmark of the system accuracy obtained with and without feature protection in the case of walking from left to right. Full article ">Figure 7
Benchmark of the system accuracy obtained with and without feature protection in the case of walking from right to left. Full article ">Figure 8
Benchmark of the system accuracy obtained with and without feature protection in the case of walking in both directions. Full article ">

21 pages, 7596 KiB

Open AccessArticle

Visible Light Communications-Based Assistance System for the Blind and Visually Impaired: Design, Implementation, and Intensive Experimental Evaluation in a Real-Life Situation

by Alin-Mihai Căilean, Sebastian-Andrei Avătămăniței, Cătălin Beguni, Eduard Zadobrischi, Mihai Dimian and Valentin Popa

Sensors 2023, 23(23), 9406; https://doi.org/10.3390/s23239406 - 25 Nov 2023

Cited by 3 | Viewed by 1617

Abstract

Severe visual impairment and blindness significantly affect a person’s quality of life, leading sometimes to social anxiety. Nevertheless, instead of concentrating on a person’s inability, we could focus on their capacities and on their other senses, which in many cases are more developed. [...] Read more.

Severe visual impairment and blindness significantly affect a person’s quality of life, leading sometimes to social anxiety. Nevertheless, instead of concentrating on a person’s inability, we could focus on their capacities and on their other senses, which in many cases are more developed. On the other hand, the technical evolution that we are witnessing is able to provide practical means that can reduce the effects that blindness and severe visual impairment have on a person’s life. In this context, this article proposes a novel wearable solution that has the potential to significantly improve blind person’s quality of life by providing personal assistance with the help of Visible Light Communications (VLC) technology. To prevent the wearable device from drawing attention and to not further emphasize the user’s deficiency, the prototype has been integrated into a smart backpack that has multiple functions, from localization to obstacle detection. To demonstrate the viability of the concept, the prototype has been evaluated in a complex scenario where it is used to receive the location of a certain object and to safely travel towards it. The experimental results have: i. confirmed the prototype’s ability to receive data at a Bit-Error Rate (BER) lower than 10⁻⁷; ii. established the prototype’s ability to provide support for a 3 m radius around a standard 65 × 65 cm luminaire; iii. demonstrated the concept’s compatibility with light dimming in the 1–99% interval while maintaining the low BER; and, most importantly, iv. proved that the use of the concept can enable a person to obtain information and guidance, enabling safer and faster way of traveling to a certain unknown location. As far as we know, this work is the first one to report the implementation and the experimental evaluation of such a concept. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

Figure 1
Schematic representation of the VLC-based smart backpack for blind users’ assistance. Full article ">Figure 2
Schematic of the smart backpack visible light communications component. Full article ">Figure 3
Visible light communications-based smart backpack for blind and severely visually impaired persons’ assistance: (a) Front and lateral side view; (b) Backside view. Full article ">Figure 4
Visible light communication testing scenario: The indoor lighting system uses VLC to provide the user with information concerning a certain point of interest. After leaving the area, the user is no longer in VLC coverage and has to rely on the embedded obstacle localization sensors and on the haptic systems to travel the distance until the point of interest. Full article ">Figure 5
Illustration of signal processing at the VLC receiver level: Channel 1 (yellow) represents the output of the optical receiver; Channel 2 (cyan) represents the signal after filtering and amplification; Channel 4 (green) shows the digital signal that is used by the microcontroller to extract the binary data. The figure also depicts the use of the VPPM modulation in a 30% duty cycle example, the light dimming principles, and provides a comparison with the traditional Manchester coding. Full article ">Figure 6
Example of smart backpack for blind persons’ assistance experimental utility: the prototype’s obstacle sensors are able to identify and inform the user that: (a) an open glass door is obstructing the path; (b) a dispenser is in the path and an open door is found on the user’s right side. Full article ">Figure 7
Experimental results showing the path taken by four blindfolded users, as they navigated from point A to point B while utilizing the VLC-based smart backpack. The results revealed a notable enhancement in the users’ path and a significant reduction in their travel time: (a) With backpack assistance; (b) Without any kind of assistance. Full article ">

20 pages, 5594 KiB

Open AccessArticle

Intelligent ADL Recognition via IoT-Based Multimodal Deep Learning Framework

by Madiha Javeed, Naif Al Mudawi, Abdulwahab Alazeb, Sultan Almakdi, Saud S. Alotaibi, Samia Allaoua Chelloug and Ahmad Jalal

Sensors 2023, 23(18), 7927; https://doi.org/10.3390/s23187927 - 16 Sep 2023

Viewed by 2317

Abstract

Smart home monitoring systems via internet of things (IoT) are required for taking care of elders at home. They provide the flexibility of monitoring elders remotely for their families and caregivers. Activities of daily living are an efficient way to effectively monitor elderly [...] Read more.

Smart home monitoring systems via internet of things (IoT) are required for taking care of elders at home. They provide the flexibility of monitoring elders remotely for their families and caregivers. Activities of daily living are an efficient way to effectively monitor elderly people at home and patients at caregiving facilities. The monitoring of such actions depends largely on IoT-based devices, either wireless or installed at different places. This paper proposes an effective and robust layered architecture using multisensory devices to recognize the activities of daily living from anywhere. Multimodality refers to the sensory devices of multiple types working together to achieve the objective of remote monitoring. Therefore, the proposed multimodal-based approach includes IoT devices, such as wearable inertial sensors and videos recorded during daily routines, fused together. The data from these multi-sensors have to be processed through a pre-processing layer through different stages, such as data filtration, segmentation, landmark detection, and 2D stick model. In next layer called the features processing, we have extracted, fused, and optimized different features from multimodal sensors. The final layer, called classification, has been utilized to recognize the activities of daily living via a deep learning technique known as convolutional neural network. It is observed from the proposed IoT-based multimodal layered system’s results that an acceptable mean accuracy rate of 84.14% has been achieved. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

30 pages, 10215 KiB

Open AccessArticle

Intelligent Localization and Deep Human Activity Recognition through IoT Devices

by Abdulwahab Alazeb, Usman Azmat, Naif Al Mudawi, Abdullah Alshahrani, Saud S. Alotaibi, Nouf Abdullah Almujally and Ahmad Jalal

Sensors 2023, 23(17), 7363; https://doi.org/10.3390/s23177363 - 23 Aug 2023

Cited by 15 | Viewed by 2201

Abstract

Ubiquitous computing has been a green research area that has managed to attract and sustain the attention of researchers for some time now. As ubiquitous computing applications, human activity recognition and localization have also been popularly worked on. These applications are used in [...] Read more.

Ubiquitous computing has been a green research area that has managed to attract and sustain the attention of researchers for some time now. As ubiquitous computing applications, human activity recognition and localization have also been popularly worked on. These applications are used in healthcare monitoring, behavior analysis, personal safety, and entertainment. A robust model has been proposed in this article that works over IoT data extracted from smartphone and smartwatch sensors to recognize the activities performed by the user and, in the meantime, classify the location at which the human performed that particular activity. The system starts by denoising the input signal using a second-order Butterworth filter and then uses a hamming window to divide the signal into small data chunks. Multiple stacked windows are generated using three windows per stack, which, in turn, prove helpful in producing more reliable features. The stacked data are then transferred to two parallel feature extraction blocks, i.e., human activity recognition and human localization. The respective features are extracted for both modules that reinforce the system’s accuracy. A recursive feature elimination is applied to the features of both categories independently to select the most informative ones among them. After the feature selection, a genetic algorithm is used to generate ten different generations of each feature vector for data augmentation purposes, which directly impacts the system’s performance. Finally, a deep neural decision forest is trained for classifying the activity and the subject’s location while working on both of these attributes in parallel. For the evaluation and testing of the proposed system, two openly accessible benchmark datasets, the ExtraSensory dataset and the Sussex-Huawei Locomotion dataset, were used. The system outperformed the available state-of-the-art systems by recognizing human activities with an accuracy of 88.25% and classifying the location with an accuracy of 90.63% over the ExtraSensory dataset, while, for the Sussex-Huawei Locomotion dataset, the respective results were 96.00% and 90.50% accurate. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

16 pages, 3400 KiB

Open AccessArticle

Vision-Based Recognition of Human Motion Intent during Staircase Approaching

by Md Rafi Islam, Md Rejwanul Haque, Masudul H. Imtiaz, Xiangrong Shen and Edward Sazonov

Sensors 2023, 23(11), 5355; https://doi.org/10.3390/s23115355 - 5 Jun 2023

Cited by 3 | Viewed by 2043

Abstract

Walking in real-world environments involves constant decision-making, e.g., when approaching a staircase, an individual decides whether to engage (climbing the stairs) or avoid. For the control of assistive robots (e.g., robotic lower-limb prostheses), recognizing such motion intent is an important but challenging task, [...] Read more.

Walking in real-world environments involves constant decision-making, e.g., when approaching a staircase, an individual decides whether to engage (climbing the stairs) or avoid. For the control of assistive robots (e.g., robotic lower-limb prostheses), recognizing such motion intent is an important but challenging task, primarily due to the lack of available information. This paper presents a novel vision-based method to recognize an individual’s motion intent when approaching a staircase before the potential transition of motion mode (walking to stair climbing) occurs. Leveraging the egocentric images from a head-mounted camera, the authors trained a YOLOv5 object detection model to detect staircases. Subsequently, an AdaBoost and gradient boost (GB) classifier was developed to recognize the individual’s intention of engaging or avoiding the upcoming stairway. This novel method has been demonstrated to provide reliable (97.69%) recognition at least 2 steps before the potential mode transition, which is expected to provide ample time for the controller mode transition in an assistive robot in real-world use. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
The proposed system comprises two parts. (a) Staircase Detection: The system takes egocentric video from a head-mounted camera as input. Then, YOLOv5 model is utilized to detect staircases in the videos and generate and store bounding box (BB) information around them. (b) Intent Prediction: The change of BB properties (e.g., width, area, etc.) with time is treated as signals. Then, features (e.g., mean, variance, etc.) are extracted from these signals. Finally, AdaBoost/Gradient Boost (GB) algorithm is employed to predict the intention (climbing or avoiding the staircase) based on the extracted features. An illustration of the system output is provided using the BB width vs. time signal. Full article ">Figure 2
Camera setup for egocentric video capture: (a) front view, (b) side view, and (c) two-point perspective view. Full article ">Figure 3
Plot of raw and filtered normalized area of the bounding box vs. frame number. The presence of green dots signifies the conclusion of the signals. Full article ">Figure 4
Box plot of features: (a) max–min peak difference of the bounding box area; (b) max–min peak difference of the bounding box width; (c) max–min peak difference of the bounding box X coordinate; (d) max–min peak difference of the bounding box Y coordinate; (e) mean of the bounding box area; (f) mean of the bounding box width; (g) mean of the bounding box X coordinate; (h) mean of the bounding box Y coordinate. Full article ">Figure 5
Illustration of calculating intention classification time before stair climb. (a) Frame at which intention was detected. (b) Frame at which first stepped on the staircase. Full article ">Figure 6
GB classifiers output on a staircase video. Full article ">

36 pages, 8924 KiB

Open AccessArticle

Automated Implementation of the Edinburgh Visual Gait Score (EVGS) Using OpenPose and Handheld Smartphone Video

by Shri Harini Ramesh, Edward D. Lemaire, Albert Tu, Kevin Cheung and Natalie Baddour

Sensors 2023, 23(10), 4839; https://doi.org/10.3390/s23104839 - 17 May 2023

Cited by 5 | Viewed by 3369

Abstract

Recent advancements in computing and artificial intelligence (AI) make it possible to quantitatively evaluate human movement using digital video, thereby opening the possibility of more accessible gait analysis. The Edinburgh Visual Gait Score (EVGS) is an effective tool for observational gait analysis, but [...] Read more.

Recent advancements in computing and artificial intelligence (AI) make it possible to quantitatively evaluate human movement using digital video, thereby opening the possibility of more accessible gait analysis. The Edinburgh Visual Gait Score (EVGS) is an effective tool for observational gait analysis, but human scoring of videos can take over 20 min and requires experienced observers. This research developed an algorithmic implementation of the EVGS from handheld smartphone video to enable automatic scoring. Participant walking was video recorded at 60 Hz using a smartphone, and body keypoints were identified using the OpenPose BODY25 pose estimation model. An algorithm was developed to identify foot events and strides, and EVGS parameters were determined at relevant gait events. Stride detection was accurate within two to five frames. The level of agreement between the algorithmic and human reviewer EVGS results was strong for 14 of 17 parameters, and the algorithmic EVGS results were highly correlated (r > 0.80, “r” represents the Pearson correlation coefficient) to the ground truth values for 8 of the 17 parameters. This approach could make gait analysis more accessible and cost-effective, particularly in areas without gait assessment expertise. These findings pave the way for future studies to explore the use of smartphone video and AI algorithms in remote gait analysis. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

22 pages, 11919 KiB

Open AccessArticle

Flight Controller as a Low-Cost IMU Sensor for Human Motion Measurement

by Artur Iluk

Sensors 2023, 23(4), 2342; https://doi.org/10.3390/s23042342 - 20 Feb 2023

Cited by 1 | Viewed by 3084

Abstract

Human motion analysis requires information about the position and orientation of different parts of the human body over time. Widely used are optical methods such as the VICON system and sets of wired and wireless IMU sensors to estimate absolute orientation angles of [...] Read more.

Human motion analysis requires information about the position and orientation of different parts of the human body over time. Widely used are optical methods such as the VICON system and sets of wired and wireless IMU sensors to estimate absolute orientation angles of extremities (Xsens). Both methods require expensive measurement devices and have disadvantages such as the limited rate of position and angle acquisition. In the paper, the adaptation of the drone flight controller was proposed as a low-cost and relatively high-performance device for the human body pose estimation and acceleration measurements. The test setup with the use of flight controllers was described and the efficiency of the flight controller sensor was compared with commercial sensors. The practical usability of sensors in human motion measurement was presented. The issues related to the dynamic response of IMU-based sensors during acceleration measurement were discussed. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

13 pages, 525 KiB

Open AccessArticle

Incremental Learning of Human Activities in Smart Homes

by Sook-Ling Chua, Lee Kien Foo, Hans W. Guesgen and Stephen Marsland

Sensors 2022, 22(21), 8458; https://doi.org/10.3390/s22218458 - 3 Nov 2022

Cited by 4 | Viewed by 2139

Abstract

Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to [...] Read more.

Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

22 pages, 4385 KiB

Open AccessArticle

Group Decision Making-Based Fusion for Human Activity Recognition in Body Sensor Networks

by Yiming Tian, Jie Zhang, Qi Chen, Shuping Hou and Li Xiao

Sensors 2022, 22(21), 8225; https://doi.org/10.3390/s22218225 - 27 Oct 2022

Cited by 2 | Viewed by 1488

Abstract

Ensemble learning systems (ELS) have been widely utilized for human activity recognition (HAR) with multiple homogeneous or heterogeneous sensors. However, traditional ensemble approaches for HAR cannot always work well due to insufficient accuracy and diversity of base classifiers, the absence of ensemble pruning, [...] Read more.

Ensemble learning systems (ELS) have been widely utilized for human activity recognition (HAR) with multiple homogeneous or heterogeneous sensors. However, traditional ensemble approaches for HAR cannot always work well due to insufficient accuracy and diversity of base classifiers, the absence of ensemble pruning, as well as the inefficiency of the fusion strategy. To overcome these problems, this paper proposes a novel selective ensemble approach with group decision-making (GDM) for decision-level fusion in HAR. As a result, the fusion process in the ELS is transformed into an abstract process that includes individual experts (base classifiers) making decisions with the GDM fusion strategy. Firstly, a set of diverse local base classifiers are constructed through the corresponding mechanism of the base classifier and the sensor. Secondly, the pruning methods and the number of selected base classifiers for the fusion phase are determined by considering the diversity among base classifiers and the accuracy of candidate classifiers. Two ensemble pruning methods are utilized: mixed diversity measure and complementarity measure. Thirdly, component decision information from the selected base classifiers is combined by using the GDM fusion strategy and the recognition results of the HAR approach can be obtained. Experimental results on two public activity recognition datasets (The OPPORTUNITY dataset; Daily and Sports Activity Dataset (DSAD)) suggest that the proposed GDM-based approach outperforms the well-known fusion techniques and other state-of-the-art approaches in the literature. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

22 pages, 3314 KiB

Open AccessArticle

A Novel Segmentation Scheme with Multi-Probability Threshold for Human Activity Recognition Using Wearable Sensors

by Bangwen Zhou, Cheng Wang, Zhan Huan, Zhixin Li, Ying Chen, Ge Gao, Huahao Li, Chenhui Dong and Jiuzhen Liang

Sensors 2022, 22(19), 7446; https://doi.org/10.3390/s22197446 - 30 Sep 2022

Cited by 7 | Viewed by 1692

Abstract

In recent years, much research has been conducted on time series based human activity recognition (HAR) using wearable sensors. Most existing work for HAR is based on the manual labeling. However, the complete time serial signals not only contain different types of activities, [...] Read more.

In recent years, much research has been conducted on time series based human activity recognition (HAR) using wearable sensors. Most existing work for HAR is based on the manual labeling. However, the complete time serial signals not only contain different types of activities, but also include many transition and atypical ones. Thus, effectively filtering out these activities has become a significant problem. In this paper, a novel machine learning based segmentation scheme with a multi-probability threshold is proposed for HAR. Threshold segmentation (TS) and slope-area (SA) approaches are employed according to the characteristics of small fluctuation of static activity signals and typical peaks and troughs of periodic-like ones. In addition, a multi-label weighted probability (MLWP) model is proposed to estimate the probability of each activity. The HAR error can be significantly decreased, as the proposed model can solve the problem that the fixed window usually contains multiple kinds of activities, while the unknown activities can be accurately rejected to reduce their impacts. Compared with other existing schemes, computer simulation reveals that the proposed model maintains high performance using the UCI and PAMAP2 datasets. The average HAR accuracies are able to reach 97.71% and 95.93%, respectively. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

13 pages, 9972 KiB

Open AccessArticle

Cadence Detection in Road Cycling Using Saddle Tube Motion and Machine Learning

by Bernhard Hollaus, Jasper C. Volmer and Thomas Fleischmann

Sensors 2022, 22(16), 6140; https://doi.org/10.3390/s22166140 - 17 Aug 2022

Cited by 4 | Viewed by 2958

Abstract

Most commercial cadence-measurement systems in road cycling are strictly limited in their function to the measurement of cadence. Other relevant signals, such as roll angle, inclination or a round kick evaluation, cannot be measured with them. This work proposes an alternative cadence-measurement system [...] Read more.

Most commercial cadence-measurement systems in road cycling are strictly limited in their function to the measurement of cadence. Other relevant signals, such as roll angle, inclination or a round kick evaluation, cannot be measured with them. This work proposes an alternative cadence-measurement system with less of the mentioned restrictions, without the need for distinct cadence-measurement apparatus attached to the pedal and shaft of the road bicycle. The proposed design applies an inertial measurement unit (IMU) to the seating pole of the bike. In an experiment, the motion data were gathered. A total of four different road cyclists participated in this study to collect different datasets for neural network training and evaluation. In total, over 10 h of road cycling data were recorded and used to train the neural network. The network’s aim was to detect each revolution of the crank within the data. The evaluation of the data has shown that using pure accelerometer data from all three axes led to the best result in combination with the proposed network architecture. A working proof of concept was achieved with an accuracy of approximately 95% on test data. As the proof of concept can also be seen as a new method for measuring cadence, the method was compared with the ground truth. Comparing the ground truth and the predicted cadence, it can be stated that for the relevant range of 50 rpm and above, the prediction over-predicts the cadence with approximately 0.9 rpm with a standard deviation of 2.05 rpm. The results indicate that the proposed design is fully functioning and can be seen as an alternative method to detect the cadence of a road cyclist. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

Figure 1
The hardware block diagram with the SensorTile module (A) which contains the IMU, the SensorTile Cradle board in top (B) and bottom view (C) [<a href="#B28-sensors-22-06140" class="html-bibr">28</a>] and the Hall-effect sensor (D) [<a href="#B29-sensors-22-06140" class="html-bibr">29</a>]. The connecting cable between Hall-effect sensor and SensorTile module has the supply voltage in red, the ground in black, the analogous Hall-effect sensor output in violet, and a spare wire in green. Full article ">Figure 2
The experimental setup for the measurement of the motion data and the cadence signal. The IMU is fixed to the saddle tube with the given orientation. The Hall-effect sensor is fixed on the frame opposite the permanent magnet on the crank arm. Full article ">Figure 3
Structure of the neural network model, with layer types and sizes as indicated. <math display="inline"><semantics> <msub> <mi>N</mi> <mrow> <mi>b</mi> <mi>a</mi> <mi>t</mi> <mi>c</mi> <mi>h</mi> </mrow> </msub> </semantics></math> symbolises the variable dimension based on the number of batches. Full article ">Figure 4
Pedal stroke signal from the Hall-effect sensor after pre-processing versus the output signal predicted by the network. The binary threshold indicates the threshold used to decide if the network output is mapped to 0 or 1. Full article ">Figure 5
Neural network evaluation: true cadence as measured with the Hall-effect sensor versus predicted cadence from the network. (a) Comparison for a large section from the test dataset. (b) Comparison for a zoomed section from the test dataset. Full article ">Figure 6
Bland–Altmann diagrams for the comparison of the IMU-ML method with the Hall-effect sensor used as ground truth. (a) Comparison for the entire cadence range in the dataset. (b) Comparison for 50 rpm and above. Full article ">

21 pages, 7753 KiB

Open AccessArticle

Predicting Activity Duration in Smart Sensing Environments Using Synthetic Data and Partial Least Squares Regression: The Case of Dementia Patients

by Miguel Ortiz-Barrios, Eric Järpe, Matías García-Constantino, Ian Cleland, Chris Nugent, Sebastián Arias-Fonseca and Natalia Jaramillo-Rueda

Sensors 2022, 22(14), 5410; https://doi.org/10.3390/s22145410 - 20 Jul 2022

Cited by 2 | Viewed by 2348

Abstract

The accurate recognition of activities is fundamental for following up on the health progress of people with dementia (PwD), thereby supporting subsequent diagnosis and treatments. When monitoring the activities of daily living (ADLs), it is feasible to detect behaviour patterns, parse out the [...] Read more.

The accurate recognition of activities is fundamental for following up on the health progress of people with dementia (PwD), thereby supporting subsequent diagnosis and treatments. When monitoring the activities of daily living (ADLs), it is feasible to detect behaviour patterns, parse out the disease evolution, and consequently provide effective and timely assistance. However, this task is affected by uncertainties derived from the differences in smart home configurations and the way in which each person undertakes the ADLs. One adjacent pathway is to train a supervised classification algorithm using large-sized datasets; nonetheless, obtaining real-world data is costly and characterized by a challenging recruiting research process. The resulting activity data is then small and may not capture each person’s intrinsic properties. Simulation approaches have risen as an alternative efficient choice, but synthetic data can be significantly dissimilar compared to real data. Hence, this paper proposes the application of Partial Least Squares Regression (PLSR) to approximate the real activity duration of various ADLs based on synthetic observations. First, the real activity duration of each ADL is initially contrasted with the one derived from an intelligent environment simulator. Following this, different PLSR models were evaluated for estimating real activity duration based on synthetic variables. A case study including eight ADLs was considered to validate the proposed approach. The results revealed that simulated and real observations are significantly different in some ADLs (p-value < 0.05), nevertheless synthetic variables can be further modified to predict the real activity duration with high accuracy (

R^{2} (p r e d) > 90 %

). Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

Review

Jump to: Research

35 pages, 5160 KiB

Open AccessReview

A Comprehensive Survey on Emerging Assistive Technologies for Visually Impaired Persons: Lighting the Path with Visible Light Communications and Artificial Intelligence Innovations

by Alexandru Lavric, Cătălin Beguni, Eduard Zadobrischi, Alin-Mihai Căilean and Sebastian-Andrei Avătămăniței

Sensors 2024, 24(15), 4834; https://doi.org/10.3390/s24154834 - 25 Jul 2024

Cited by 2 | Viewed by 3566

Abstract

In the context in which severe visual impairment significantly affects human life, this article emphasizes the potential of Artificial Intelligence (AI) and Visible Light Communications (VLC) in developing future assistive technologies. Toward this path, the article summarizes the features of some commercial assistance [...] Read more.

In the context in which severe visual impairment significantly affects human life, this article emphasizes the potential of Artificial Intelligence (AI) and Visible Light Communications (VLC) in developing future assistive technologies. Toward this path, the article summarizes the features of some commercial assistance solutions, and debates the characteristics of VLC and AI, emphasizing their compatibility with blind individuals’ needs. Additionally, this work highlights the AI potential in the efficient early detection of eye diseases. This article also reviews the existing work oriented toward VLC integration in blind persons’ assistive applications, showing the existing progress and emphasizing the high potential associated with VLC use. In the end, this work provides a roadmap toward the development of an integrated AI-based VLC assistance solution for visually impaired people, pointing out the high potential and some of the steps to follow. As far as we know, this is the first comprehensive work which focuses on the integration of AI and VLC technologies in visually impaired persons’ assistance domain. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

18 pages, 3463 KiB

Open AccessReview

Sonification for Personalised Gait Intervention

by Conor Wall, Peter McMeekin, Richard Walker, Victoria Hetherington, Lisa Graham and Alan Godfrey

Sensors 2024, 24(1), 65; https://doi.org/10.3390/s24010065 - 22 Dec 2023

Cited by 5 | Viewed by 1821

Abstract

Mobility challenges threaten physical independence and good quality of life. Often, mobility can be improved through gait rehabilitation and specifically the use of cueing through prescribed auditory, visual, and/or tactile cues. Each has shown use to rectify abnormal gait patterns, improving mobility. Yet, [...] Read more.

Mobility challenges threaten physical independence and good quality of life. Often, mobility can be improved through gait rehabilitation and specifically the use of cueing through prescribed auditory, visual, and/or tactile cues. Each has shown use to rectify abnormal gait patterns, improving mobility. Yet, a limitation remains, i.e., long-term engagement with cueing modalities. A paradigm shift towards personalised cueing approaches, considering an individual’s unique physiological condition, may bring a contemporary approach to ensure longitudinal and continuous engagement. Sonification could be a useful auditory cueing technique when integrated within personalised approaches to gait rehabilitation systems. Previously, sonification demonstrated encouraging results, notably in reducing freezing-of-gait, mitigating spatial variability, and bolstering gait consistency in people with Parkinson’s disease (PD). Specifically, sonification through the manipulation of acoustic features paired with the application of advanced audio processing techniques (e.g., time-stretching) enable auditory cueing interventions to be tailored and enhanced. These methods used in conjunction optimize gait characteristics and subsequently improve mobility, enhancing the effectiveness of the intervention. The aim of this narrative review is to further understand and unlock the potential of sonification as a pivotal tool in auditory cueing for gait rehabilitation, while highlighting that continued clinical research is needed to ensure comfort and desirability of use. Full article

(This article belongs to the Special Issue Human Activity Recognition in Smart Sensing Environment)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Human Activity Recognition in Smart Sensing Environment

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (16 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI