A hierarchical method for human concurrent activity recognition using miniature inertial sensors

Sensor Review ◽  
2017 ◽  
Vol 37 (1) ◽  
pp. 101-109 ◽  
Author(s):  
Ye Chen ◽  
Zhelong Wang
Keyword(s):  
Activity Recognition ◽  
Inertial Sensors ◽  
The Body ◽  
Lower Limbs ◽  
Sensor Nodes ◽  
Upper Body ◽  
Accurate Information ◽  
Postoperative Rehabilitation ◽  
Content Type ◽  
Hierarchical Method

Purpose Existing studies on human activity recognition using inertial sensors mainly discuss single activities. However, human activities are rather concurrent. A person could be walking while brushing their teeth or lying while making a call. The purpose of this paper is to explore an effective way to recognize concurrent activities. Design/methodology/approach Concurrent activities usually involve behaviors from different parts of the body, which are mainly dominated by the lower limbs and upper body. For this reason, a hierarchical method based on artificial neural networks (ANNs) is proposed to classify them. At the lower level, the state of the lower limbs to which a concurrent activity belongs is firstly recognized by means of one ANN using simple features. Then, the upper-level systems further distinguish between the upper limb movements and infer specific concurrent activity using features processed by the principle component analysis. Findings An experiment is conducted to collect realistic data from five sensor nodes placed on subjects’ wrist, arm, thigh, ankle and chest. Experimental results indicate that the proposed hierarchical method can distinguish between 14 concurrent activities with a high classification rate of 92.6 per cent, which significantly outperforms the single-level recognition method. Practical implications In the future, the research may play an important role in many ways such as daily behavior monitoring, smart assisted living, postoperative rehabilitation and eldercare support. Originality/value To provide more accurate information on people’s behaviors, human concurrent activities are discussed and effectively recognized by using a hierarchical method.

Quantitative body symmetry assessment during neurological examination

2020 ◽  
Vol 28 (5) ◽  
pp. 573-584
Author(s):  
Kristina Daunoraviciene ◽  
Jurgita Ziziene ◽  
Agne Ovcinikova ◽  
Rasa Kizlaitiene ◽  
Julius Griskevicius
Keyword(s):  
Inertial Sensors ◽  
The Body ◽  
Lower Limbs ◽  
Upper Body ◽  
Lower Body ◽  
Temporal Parameters ◽  
Body Asymmetry ◽  
Upper And Lower Extremities ◽  
Spatiotemporal Parameters ◽  
Measurement Units

BACKGROUND: A lack of movement coordination characterized by the undershoot or overshoot of the intended location with the hand, arm, or leg is often found in individuals with multiple sclerosis (MS). Standardized as Finger-to-Nose (FNT) and The Heel-to-Shin (HST) tests are the most frequently used tests for qualitative examination of upper and lower body coordination. Inertial sensors facilitate in performing quantitative motion analysis and by estimating body symmetry more accurately assess coordination lesion and imbalance. OBJECTIVES: To assess the body symmetry of upper and lower limbs quantitatively, and to find the best body symmetry indices to discriminate MS from healthy individuals (CO). METHODS: 28 MS patients and 23 CO participated in the study. Spatiotemporal parameters obtained from six Inertial Measurement Units (IMUs) were placed on the upper and lower extremities during FNT and HST tests. All data were analyzed using statistical methods in MATLAB. RESULTS: Asymmetry indices of temporal parameters showed a significant increase in upper body and lower body asymmetry of MS compared to CO. However, CO have a greater kinematic asymmetry compared to MS. CONCLUSION: Temporal parameters are the most sensitive to body asymmetry evaluation. However, range of motion is completely inappropriate if it is calculated for one movement cycle.

scholarly journals A Feasibility Study of Kinematic Characteristics on the Upper Body According to the Shooting of Elite Disabled Archery Athletes

2021 ◽  
Vol 18 (6) ◽  
pp. 2962
Author(s):  
Tae-Whan Kim ◽  
Jae-Won Lee ◽  
Seoung-Ki Kang ◽  
Kyu-Yeon Chae ◽  
Sang-Hyup Choi ◽  
...  
Keyword(s):  
The Body ◽  
Lower Limbs ◽  
Upper Body ◽  
Movement Trajectory ◽  
Phase 2 ◽  
Kinematic Characteristics ◽  
Significant Difference ◽  
Athletes With Disabilities ◽  
Body Center ◽  
Time Required

The purpose of this study is to compare and analyze the kinematic characteristics of the upper limb segments during the archery shooting of Paralympic Wheelchair Class archers (ARW2—second wheelchair class—paraplegia or comparable disability) and Paralympic Standing Class archers (ARST—standing archery class—loss of 25 points in the upper limbs or lower limbs), where archers are classified according to their disability grade among elite disabled archers. The participants of this study were selected as seven elite athletes with disabilities by the ARW2 (n = 4) and ARST (n = 3). The analysis variables were (1) the time required for each phase, (2) the angle of inclination of the body center, (3) the change of trajectory of body center, and (4) the change of the movement trajectory of the bow center by phase when performing six shots in total. The ARW2 group (drawing phase; M = 2.228 s, p < 0.05, holding phase; M = 4.414 s, p < 0.05) showed a longer time than the ARST group (drawing phase; M = 0.985 s, holding phase; M = 3.042 s), and the angle of the body did not show a significant difference between the two groups. Additionally, in the direction of the anteroposterior axis in the drawing phase, the change in the movement trajectory of the body center showed a more significant amount of change in the ARW2 group than in the ARST group, and the change in the movement trajectory of the bow center did not show a significant difference between the two groups.

scholarly journals Constellations of pain: a qualitative study of the complexity of women’s endometriosis-related pain

2020 ◽  
pp. 204946372096141
Author(s):  
Sarah J Drabble ◽  
Jaqui Long ◽  
Blessing Alele ◽  
Alicia O’Cathain
Keyword(s):  
Clinical Encounter ◽  
The Body ◽  
Lower Limbs ◽  
Upper Body ◽  
Pain Experience ◽  
Face To Face ◽  
The United Kingdom ◽  
Type Pattern ◽  
Emotional Aspects ◽  
Pain Experiences

Introduction: Prior research into endometriosis-related pain has focused on specific aspects of the pain experience such as cyclical pain, emotional aspects of pain and certain types of pain such as dysmenorrhea and dyspareunia. However, research has paid less attention to the diversity and complexity of women’s pain experiences, which can lead to failure to recognise some symptoms as part of endometriosis and poor symptom management. Methods: We conducted qualitative semi-structured face-to-face interviews with 20 women in the United Kingdom recruited from an endometriosis self-help group with a diagnosis of endometriosis via laparoscopy. A topic guide framed questions around experiences of pain. Interviews were audio-recorded and transcribed verbatim. Transcripts were analysed using inductive thematic analysis. Results: Women experienced multiple types of pain that they felt were caused by endometriosis and affected many different parts of the body including bowel, bladder, lungs, kidneys, nerves, upper body, lower limbs and head. These pains consisted of different conceptual categories: type, pattern and intensity. These categories came together to create a complex, interrelated experience for each individual that we termed ‘constellations of pain’ because each woman had a complex set of pain categories and no two individuals appeared to have the same pain experience. Conclusion: The complexity and diversity of endometriosis-related pain found in this study has implications for improving diagnosis, medical and non-medical pain management and improving the clinical encounter between women and healthcare professionals.

scholarly journals Human Activity Recognition of Exoskeleton Robot with Supervised Learning Techniques

2021 ◽  
Author(s):  
Jiacheng Mai ◽  
zhiyuan chen ◽  
Chunzhi Yi ◽  
Zhen Ding
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
The Body ◽  
Lower Limbs ◽  
Data Sets ◽  
Learning Approaches ◽  
Learning Method

Abstract Lower limbs exoskeleton robots improve the motor ability of humans and can facilitate superior rehabilitative training. By training large datasets, many of the currently available mobile and signal devices that may be worn on the body can employ machine learning approaches to forecast and classify people's movement characteristics. This approach could help exoskeleton robots improve their ability to predict human activities. Two popular data sets are PAMAP2, which was obtained by measuring people's movement through inertial sensors, and WISDM, which was collected people's activity information through mobile phones. With the focus on human activity recognition, this paper applied the traditional machine learning method and deep learning method to train and test these datasets, whereby it was found that the prediction performance of a decision tree model was highest on these two data sets, which is 99% and 72% separately, and the time consumption of decision tree is the least. In addition, a comparison of the signals collected from different parts of the human body showed that the signals deriving from the hands presented the best performance in terms of recognizing human movement types.

scholarly journals Exercises using the upper limbs hyperinflate COPD patients more than exercises using the lower limbs at the same metabolic demand

2016 ◽  
Vol 71 (1) ◽  
Author(s):  
E.F. Porto ◽  
A.A.M. Castro ◽  
M. Velloso ◽  
O. Nascimento ◽  
F. Dal Maso ◽  
...  
Keyword(s):  
Pulmonary Ventilation ◽  
The Body ◽  
Lower Limbs ◽  
Upper Body ◽  
Dynamic Hyperinflation ◽  
Upper Limbs ◽  
Lower Body ◽  
Metabolic Demand ◽  
Inspiratory Capacity ◽  
Upper Body Exercise

mandatory constituents of a rehabilitation programme for patients with COPD. However, it is not known how much these exercises may induce pulmonary dynamic hyperinflation (DH). Objective. To evaluate the DH in patients with COPD exercising the upper and lower parts of the body at the same metabolic demand. Methods. Sixteen patients aged 63 ± 13 years and with a FEV1 of 1.5 ± 0.7 L (41 ± 11% pred) were studied. Patients initially performed a maximal exercise test with the arms using the diagonal movement technique. The lower limbs were exercised on a treadmill at the same metabolic demand. Results. Inspiratory capacity decreased 222 ± 158 ml (9.8%) after the upper body exercise (p &lt; 0.0001) and 148 ± 161 ml (7%) after exercise with the lower body (p = 0.0028) and a difference between the two groups was found (p &lt; 0.05). There was no difference between resting IC before upper and lower limbs exercises (p = 0.8); increase in minute ventilation and in pulmonary ventilation in percentage of maximum voluntary ventilation and reduction of expiratory time were larger in the upper limbs exercise (p &lt; 0.05). Dyspnea as measured by the Borg Scale was higher in the upper body (3.9 ± 2.2) than in the lower body (2.3 ± 1.3) at the end of the exercise (p = 0.033). Pulmonary ventilation and inspiratory capacity were correlated (p = 0.0001; r = 0.82). Conclusion. Exercise with the upper part of the body causes more DH and dyspnea than exercise with the lower part of the body at the same metabolic demand.

Body shape classification and block optimization based on space vector length

2019 ◽  
Vol 31 (1) ◽  
pp. 115-129
Author(s):  
Jie Sun ◽  
Qianyun Cai ◽  
Tao Li ◽  
Lei Du ◽  
Fengyuan Zou
Keyword(s):  
Cross Section ◽  
Human Body ◽  
Body Shape ◽  
The Body ◽  
Upper Body ◽  
Shape Classification ◽  
Content Type ◽  
Vector Length ◽  
Space Vectors ◽  
Three Body

PurposeConsidering two-dimensional features in the body shape classification system cannot fully reflect the three-dimensional (3D) morphological characteristics of human body. The purpose of this paper is to propose a 3D feature based method to characterize and classify the upper body shape of women, and then obtained the corresponding garment block and improved the fitness of clothing.Design/methodology/approachIn this study, the [TC]23D scanner was used to obtain human data, and 15 layers of cross-sections of young females’ upper body were extracted. In total, 240 space vectors were obtained with the center of the bust cross-section as the original point. By using the principal component analysis and K-means clustering analysis, the body shape classification based on the space vectors length was realized. The garment block corresponding to three body types was obtained using the 3D scanning data and the cross-section convex hull, and compared with existing garment block and evaluated fitness of the blocks.FindingsIn total, 11 main components used to characterize the 3D morphological features of young women were obtained, which could explain 95.28 percent features of young women’s upper body. By cluster analysis, the body shape of women was divided into three categories. The block of three body types was obtained by the construction of the convex hull model.Originality/valueThis paper investigates a classification method of the body shape based on space vector length, which can effectively reflect the difference of surface shape of human body and further improve the matching degree of human body and clothing.

Effects of clothing ease and body postures on the air gap and clothing coverage

2019 ◽  
Vol 31 (4) ◽  
pp. 578-594
Author(s):  
Shitan Wang ◽  
Xiuhua Wang ◽  
Yunyi Wang
Keyword(s):  
Air Gap ◽  
The Body ◽  
Upper Body ◽  
Gap Size ◽  
Lower Body ◽  
Content Type ◽  
Body Postures ◽  
Body Regions ◽  
Gap Models ◽  
The Right

Purpose The purpose of this paper is to determine the effects of clothing ease and body postures on the size and distribution of the air gap as well as the body coverage with the clothing. Design/methodology/approach Visual and quantitative analyses were conducted using a 3D body scanner and Geomagic Software. The air gap size and clothing area factor (fcl) in three test coverall and seven selected postures were calculated and compared. Findings The results indicated that both the clothing ease and body postures had a strong effect on the air gap and clothing coverage, especially the more complex the postures, the wider the range of influence. Nevertheless, these effects varied over body regions, being stronger at the lower body than the upper body. The air gap size at the left side of the body was generally larger than the right side. It was also found that the clothing coverage was linearly correlated with the air gap size and could be employed as an indicator to evaluate clothing protective capabilities. Practical implications The findings suggested that greater attention should be paid to the protection and flexibility at the lower body and asymmetrical distribution of the air gap should be considered in the future air gap modeling. Originality/value The outcomes provided useful information to improve the protective clothing and develop more realistic air gap models to simulate the heat and mass transfer.

Classifying male upper lateral somatotypes using space vectors

2016 ◽  
Vol 28 (1) ◽  
pp. 115-129 ◽  
Author(s):  
Mi Kyung Yoon ◽  
Yun Ja Nam ◽  
Woong Kim
Keyword(s):  
Extreme Values ◽  
Three Dimensional ◽  
Upper Body ◽  
Accurate Information ◽  
Space Vector ◽  
Content Type ◽  
3D Data ◽  
Body Shell ◽  
Space Vectors ◽  
The Right

Purpose – The purpose of this paper is to develop a method for defining and categorizing upper lateral somatotypes for clothing size systems used for clothing pattern creation based on directional angles of 3D space vectors. Design/methodology/approach – 3D data for 317 men in their twenties obtained from the fifth Size Korea survey were used in this study. Standard landmarks and surfaces were set on the 3D shapes, and six space vector angles of the lateral form were defined and measured. Relationships among the measurement results were clarified, and the results were compared with those obtained using existing classifying methods. Findings – The measurement of the defined directional angles indicated that the swayback type and bend-forward type had the two extreme values, and the straight type was between the two values. The analysis of the correlation between six directional angles indicated that some points in the lower area of the upper body had a high correlation with other points in the lower area. Researchlimitations/implications – The subjects of this study were limited to lateral somatotypes, and there is a need for future studies that focus on frontal somatotypes. This research is confined to the upper lateral somatotypes of men in their twenties. Further study is needed to extend the results of this study to other body types such as those of elderly and overweight persons. Practical implications – Major angle measurements quantified by the somatotypes can be specifically reflect in developing and revised to the right patterns which is spread body shell replica or individual pattern for MTM. Social implications – This objective somatotype analysis method can be involved in determining individual body somatotype of ordermade clothes or can provided the accurate information interactively to MTM automatic customized pattern making system. Originality/value – Accurate measurements of size, shape, and posture were applied and characterized to realize the process. Accuracy was improved compared to existing 2D analysis methods through three-dimensional analysis using directional space vector angles based on 3D forms.

Fabrication and stress analysis of ankle foot orthosis with additive manufacturing

2018 ◽  
Vol 24 (2) ◽  
pp. 301-312 ◽  
Author(s):  
Harish Kumar Banga ◽  
Rajendra M. Belokar ◽  
Parveen Kalra ◽  
Rajesh Kumar
Keyword(s):  
Additive Manufacturing ◽  
3D Printing ◽  
Stress Analysis ◽  
Low Cost ◽  
The Body ◽  
Lower Limbs ◽  
Content Type ◽  
Body Of Knowledge ◽  
New Applications ◽  
Foot Orthosis

Purpose Ankle–foot orthoses (AFOs) are assistive devices prescribed for a number of physical and neurological disorders affecting the mobility of the lower limbs. Additive manufacturing has been explored as an alternative process; however, it has proved to be inefficient cost-wise. This work aims to explore the possibilities of generating modular AFO elements, namely, calf, shank and footplate, with the localized composite reinforcement that aids in the optimization of the device in terms of functionality, aesthetics, rigidity and cost. Design/methodology/approach The conventional lower leg–foot orthosis configuration depends on thermoforming a polymer sheet around a mortar cast with a trademark firmness relying upon the trim-line with the inalienable plan restrictions. In manufacturing of AFO the expert, i.e. orthotist's, guidance is used. Polypropylene and polyethylene material is used in fabrication of AFO to complete all-round reported points of interest over the ordinary outlines, yet their mechanical conduct under administration conditions cannot be effectively anticipated. Findings AFOs made of polypropylene and polyethylene material are available in the market, which are used by children of age 3-5 years. With the existing AFO design, patients are facing excessive heating and sweating problems during long-term usage. After feedback from patients and orthotists (who prescribed AFO to patients), an attempt has been made to solve the problem with a new and improved AFO design of AFO by using finite element modelling and stress analysis. Also, the results indicate that the new design is similar to the actual product design. Originality/value This work introduces the low-cost 3D printing with reinforcement approach as an alternative route for the designing and manufacturing of orthotic devices with complex shapes. It is expected that new applications add-up to increase the body of knowledge about the behaviour of such products which will mix both areas, composite theory and additive manufacturing. This study investigated the fields related to 3D scanning, 3D printing and computer-aided designing for the manufacturing of a customized AFO.

A Body Model Server for Human Motion Capture and Representation

1996 ◽  
Vol 5 (4) ◽  
pp. 381-392 ◽  
Author(s):  
Joshua Bers
Keyword(s):  
Real Time ◽  
Data Streams ◽  
Geometric Model ◽  
Human Motion ◽  
The Body ◽  
Geometric Constraints ◽  
Upper Body ◽  
Accurate Information ◽  
Joint Angles ◽  
Body Model

This paper presents a body model server (BMS) that provides real-time access to the position and posture of a person's torso, arms, hands, head, and eyes. It can be accessed by clients over a network. The BMS is designed to function as a device-independent data-layer between the sensing devices and client applications that require real-time human motion data, such as animation control. It can provide clients with accurate information at up to 40 Hz. For data collection, the model uses four magnetic position/ orientation sensors, two data-gloves, and an eye-tracker. The BMS combines the data-streams from the sensors and transforms them into snapshots of the user's upper-body pose. A geometric model made up of joints and segments structures the input. Posture of the body is represented by joint angles. Two unique characteristics of our approach are the use of the implicit, geometric constraints of the sensed body to simplify the computation of the unmeasured joint angles, and the use of time-stamped data that allow synchronization with other data streams, e.g., speech input. This paper describes the architecture of the BMS, including the management of multiple input devices, the representation and computation of the position and joint angle data, and the client-server interface.

Sign in / Sign up

Export Citation Format

Share Document