Real-time Posture Research Articles

Smart-Cover: A real time sitting posture monitoring system

Prolonged asymmetrical sitting is common and can exacerbate musculoskeletal back pain and spinal deformities. Monitoring sitting posture can help maintain correct posture and prevent health problems. Currently posture is assessed by expert clinicians using subjective visual observation. More objective methods involve the use of a gold-standard motion capture system in Laboratories, which is expensive and not widely available. We develop a Smart-Cover, an automatic system to provide real time visualization and information about sitting posture. A Sitting Pressure Sensor (SPS) is built using Velostat, conductive fabric and foam to collect pressure distribution information within the seat surface. The data are collected from 10 healthy young subjects where each subject sits for 30 min and are transferred to a cloud server using Internet-of-Things (IoT). A rule-based classifier is used to provide timely notification to users about sitting duration and level of asymmetry. A new end-point device application is developed to show sitting balance. Dial based displays show level of asymmetry, active and static sitting, and daily summary score. Our system is user friendly, inexpensive, automatic and quantitative method for evaluating posture in real time, which has the capability of providing quantitative information about sitting behaviour. The results show that our system can be used for objective monitoring of sitting posture which has medical and social benefits. Smart-Cover can support the management of patients during their rehabilitation by monitoring pressure areas and balance when seated. In addition, it offers users at home, schools and offices the means to improve their sitting posture.

Developing and Evaluating a Mixed Sensor Smart Chair System for Real-Time Posture Classification: Combining Pressure and Distance Sensors.

A novel sensor-embedded smart chair system was developed to monitor and classify a worker's sitting postures in real time. The smart chair system was a mixed sensor system utilizing six pressure sensors and six infrared reflective distance sensors in combination. The pressure sensors were embedded in the seat cushion to gather seat cushion pressure distribution data. The distance sensors were placed in the seatback to measure seatback-trunk distances at different locations in the frontal plane. The use of the seatback distance sensors represented a unique design feature, which distinguished the mixed sensor system from the previous posture monitoring systems. Employing a k-Nearest Neighbor algorithm, the mixed sensor system classified an instantaneous posture as one of posture categories determined based on an analysis of the ergonomics literature on sitting postures and sitting-related musculoskeletal problems. The mixed sensor system was evaluated in posture classification performance in comparison with two benchmark systems that utilized only a single type of sensors. The purpose of the comparisons was to determine the utility of the design combining seat cushion pressure sensors and seatback distance sensors. The mixed sensor system yielded significantly superior classification performance than the two benchmark systems. The mixed sensor system is low-cost utilizing only a small number of sensors; yet, it accomplishes accurate classification of postures relevant to the ergonomic analyses of seated work tasks. The mixed sensor system could be utilized for various applications including the development of a real-time posture feedback system for preventing sitting-related musculoskeletal disorders.

Research on the CNC incremental forming based on multidirectional real-time adjustment of the sheet posture

There are some problems in the CNC incremental forming with the sheet metal part containing vertical wall, such as excessive thinning and easy fracture. A new CNC incremental forming method was proposed based on the feature recognition for the multidirectional adjustment of the sheet metal posture. According to the feature recognition, the multi-feature of the sheet metal part was decomposed into a number of the forming feature units according to the size and distribution of the forming angles, so that the forming angles of the surface are less than the forming limit angle. The feature recognition and forming feature unit generation algorithm, sheet posture control method, and sheet posture surface generation algorithm were studied, and the finite element analysis and the forming experiments based on the proposed algorithms were also presented. The research results show that the proposed method can change the sheet metal posture in real time during the CNC incremental forming process and realize the non-rupture forming with the large forming angle parts such as vertical wall parts.

Real-time human posture recognition using an adaptive hybrid classifier

A reliable adaptive hybrid classifier (hAHC), which combines a posture-based adaptive signal segmentation algorithm with a multi-layer perceptron (MLP) classifier, together with a plurality voting approach, was proposed and evaluated in this study. The hAHC model was evaluated using a real-time posture recognition framework that sought to identify five behaviours (sitting, walking, standing, running, and lying) based on simulated crowd security scenarios. It was compared to a single MLP classifier (sMLP) and a static hybrid classifier (hSHC) from three perspectives (classification precision, recall and F1-score) that used the real-time dataset collected from unfamiliar subjects. Experimental results showed that the hAHC model improved the classification accuracy and robustness slightly more than the hSHC, and significantly more compared to the sMLP (hAHC 82%; hSHC 79%; sMLP 71%). Additionally, the hAHC approach displayed the real-time results as animated figures in an adaptive window, in contrast to the hSHC which used a fixed size-sliding temporal window that as our results demonstrated, was less suitable for presenting real-time results. The main research contribution from this study has been the development of an efficient software-only-based sensor calibration algorithm that can improve accelerometer precision, together with the design of a posture-based adaptive signal segmentation algorithm that cooperated with an adaptive hybrid classifier to improve the performance of real-time posture recognition.

Methods of Ergonomic Evaluation in Upper Limb: A Review in Agricultural Manual Work

Background: Into literary collections exists a great availability of kinematic models for upper limbs; e.g. for shoulder modeling, were found that the number of published articles, since 1990 to 2009, can reach 100. Aims: To describe the main ergonomic methods adopted to evaluate the upper limb in manual agricultural work and the quality of available evidence in electronic databases. Methods: A search in scientific literature made through Web of Science, Scopus, ScienceDirect, ESBCO - PubMed and IEEE databases. At the same time, in systematically classified and published articles during the period 2013 to 2018, based on Delphi consensus criteria and evidences analyzed under PRISMA declaration criteria and catalogued in accordance with the approaches of physical ergonomics. Papers selection had basis on the key words: farmers, musculoskeletal, farmers' upper limb, agricultural risk factor, and occupational risk factor. Along this retrospective study, initially were found 1508 articles, where 37 of them were analyzed. All selected papers met rigor of inclusion criteria (specific farmer population without mechanical aid), and exclusion (duplicity or triplicate in databases, and intervention with clinical or medical examinations). Conclusion: Results showed that the most of evaluation techniques used are indirect: realized by self-administered questionnaires (SAQ) or self-reporting, this is an evidence of little ergonomic analysis in farmers doing manual work; most of the studies selected were catalogued as good or reasonable quality. This systematic review highlights the needing of adjusting tools in order to identify and evaluate potentially dangerous tasks by their movements and/or postures in real time.

Wearable bioimpedance for continuous and context-aware clinical monitoring.

Bioimpedance monitoring provides a non-invasive, safe and affordable opportunity to monitor total body water for a wide range of clinical applications. However, the measurement is susceptible to variations in posture and movement. Existing devices do not account for these variations and are therefore unsuitable to perform continuous measurements to depict trend changes. We developed a wearable bioimpedance monitoring system with embedded real-time posture detection using a distributed accelerometer network. We tested the device on 14 healthy volunteers following a standardized protocol of posture change and evaluated the agreement with a commercial device. The impedance showed a high correlation (r>0.98), a bias of -4.5 Ω, and limits of agreement of -30 and 21 Ω. Context-awareness was achieved with an accuracy of 94.6% by classifying data from two accelerometers placed at the upper and lower leg. The calculated current consumption of the system was as low as 10 mA during continuous measurement operation, suggesting that the system can be used for continuous measurements over multiple days without charging. The proposed motion-aware design will enable the measurement of relevant bioimpedance parameters over long periods and support informed clinical decision making.

Adaptive Image-Based Visual Servoing Using Reinforcement Learning With Fuzzy State Coding

Image-based visual servoing (IBVS) allows precise control of positioning and motion for relatively stationary targets using visual feedback. For IBVS, a mixture parameter $\beta$ allows better approximation of the image Jacobian matrix, which has a significant effect on the performance of IBVS. However, the setting for the mixture parameter depends on the camera's real-time posture; there is no clear way to define the change rules for most IBVS applications. Using simple model-free reinforcement learning, Q-learning, this article proposes a method to adaptively adjust the image Jacobian matrix for IBVS. If the state-space is discretized, traditional Q-learning encounters problems with the resolution that can cause sudden changes in the action, so the visual servoing system performs poorly. Besides, a robot in a real-world environment also cannot learn on as large a scale as virtual agents, so the efficiency with which agents learn must be increased. This article proposes a method that uses fuzzy state coding to accelerate learning during the training phase and to produce a smooth output in the application phase of the learning experience. A method that compensates for delay also allows more accurate extraction of features in a real environment. The results for simulation and experiment demonstrate that the proposed method performs better than other methods, in terms of learning speed, movement trajectory, and convergence time.

Human Factors Evaluation of an Ambient Display for Real-Time Posture Feedback to Sedentary Workers

While multiple previous studies have proposed utilizing an ambient display for providing real-time posture feedback to seated computer workers, it is not well understood how effective ambient feedback is in supporting the users’ dual task of computer work and posture monitoring/rectification. The objective of the current study was to evaluate an ambient display for real-time posture feedback in comparison with typical conditions, an on-screen display and no display condition, in terms of the dual task performance. The ambient and the on-screen display were also compared in terms of perceived detection efficiency and user acceptance measures. A total of 24 participants performed the dual task in each of the three display conditions (the ambient, on-screen and no display conditions). The dependent measures for the dual task performance were the number of typed answers and the occurrence rate of high-risk postures; and, for the subjective evaluation, two detection efficiency measures (visibility and understandability) and four user acceptance measures (performance expectancy, effort expectancy, attitude toward using technology and social influence) were employed. The study demonstrated that both the ambient and the on-screen displays enhanced the dual task performance with respect to the no-display condition and the ambient display was superior to the on-screen display in the subjective experience measures.

Wearable Strain Sensors Using Light Transmittance Change of Carbon Nanotube-Embedded Elastomers with Microcracks.

A number of flexible and stretchable strain sensors based on piezoresistive and capacitive principles have been recently developed. However, piezoresistive sensors suffer from poor long-term stability and considerable hysteresis of signals. On the other hand, capacitive sensors exhibit limited sensitivity and strong electromagnetic interference from the neighboring environment. In order to resolve these problems, a novel stretchable strain sensor based on the modulation of optical transmittance of carbon nanotube (CNT)-embedded Ecoflex is introduced in this paper. Within the film of multiwalled CNTs embedded in the Ecoflex substrate, the microcracks are propagated under tensile strain, changing the optical transmittance of the film. The proposed sensor exhibits good stretchability (ε ≈ 400%), high linearity (R2 > 0.98) in the strain range of ε = 0-100%, excellent stability, high sensitivity (gauge factor ≈ 30), and small hysteresis (∼1.8%). The sensor was utilized to detect the bending of the finger and wrist for the control of a robot arm. Furthermore, the applications of this sensor to the real-time posture monitoring of the neck and to the detection of subtle human motions were demonstrated.

Posture measurement of soft pneumatic bending actuator using optical fibre-based sensing membrane

PurposeSoft robotics is a burgeoning field owing to its high adaptability and safety in human–machine interaction and unstructured environments. However, the feedback control of soft actuators with flexible sensors is still a challenge.Design/methodology/approachTo address this issue, this study proposes an optical fibre-based sensing membrane for the posture measurement of soft pneumatic bending actuators. The major contribution is the development of a flexible sensing membrane with a high sensitivity and repeatability for the feedback control of soft actuators. The characteristics of sensing membrane were analysed. The relationship between wavelength shift and bending curvature was derived. The curvatures of soft actuator were measured at four bending status, and the postures were reconstructed.FindingsThe results indicate that the measurement error is less than 2.1% of the actual bending curvature. The sensitivity is up to 212.8 pm/m−1, and the signal fluctuation in repeated measurements is negligible. This approach has broad application prospects in soft robotics, because it makes the optical fibre achieve more strength and compatible with soft actuators, thus improving the sensing accuracy, sensitivity and reliability of fibre sensors.Originality/valueDifferent from previous approaches, an optical fibre with FBGs is embedded into a multilayered polyimide film to form a flexible sensing membrane, and the membrane is embedded into a soft pneumatic bending actuator as the smart strain limited layer which is able to measure the posture in real time. This approach makes the optical fibre stronger and compatible with the soft pneumatic bending actuator, and the sensing accuracy, sensitivity and reliability are improved. The proposed sensing configuration is effective for the feedback control of the soft pneumatic bending actuators.

A Wearable System That Detects Posture and Heart Rate: Designing an Integrated Device With Multiparameter Measurements for Better Health Care

We present an integrated wearable system that combines real-time posture detection, heart rate (HR) monitoring, and quantitative activity monitoring into a robust wearable device. The system includes a wearable device, a smartphone application, and a server. MSP430, an ultralow-power microprocessor, is used in the wearable device to calculate HR, count walking and running steps, tabulate push-ups and sit-ups, and detect posture. Data transmissions are conducted from the wearable device to a smartphone to display the information to the user, record all received data, and upload data to a server. A total of 10 healthy subjects volunteered for our experiments, with an age range of 22 to 29 years. The results are 100% accurate in various postures.

Real time vision-based hand gesture recognition using depth sensor and a stochastic context free grammar

This paper presents a new algorithm in computer vision for the recognition of hand gestures. In the proposed system, Kinect sensor is used to track and segment hand in the clutter background and feature extracted by finger and an angle between them. Classify the hand posture using multi-class support vector machine. The hand gesture is recognised by stochastic context free grammar (SCFG). Stochastic context free grammar uses syntactic structure analysis and by this method, recognises hand gestures by set of production rules which consists of a combination of hand postures. The proposed algorithm is able to recognise various hand postures in real time with more than 97% accuracy.

Real time vision-based hand gesture recognition using depth sensor and a stochastic context free grammar

This paper presents a new algorithm in computer vision for the recognition of hand gestures. In the proposed system, Kinect sensor is used to track and segment hand in the clutter background and feature extracted by finger and an angle between them. Classify the hand posture using multi-class support vector machine. The hand gesture is recognised by stochastic context free grammar (SCFG). Stochastic context free grammar uses syntactic structure analysis and by this method, recognises hand gestures by set of production rules which consists of a combination of hand postures. The proposed algorithm is able to recognise various hand postures in real time with more than 97% accuracy.

Development of a 4-DOF Robotic Arm: Prototype Design

This paper discusses the development of a prototype industrial robotic arm. This work is related to the previous project where a seven-degree-of-freedom (DOFs) three fingered robotic hand has been developed for grasping work. However, the working range for the task was just limited to within working range of the robot hand, thus a robot arm is required. The objective of this work was to determine the design of the robot arm’s link and joint, components and actuators. The 4-DOF robot arm has four joints to imitate a human upper arm namely joint 1, 2, 3 and 4 that rotate around x, y, and z axes, respectively. The joints move four arm links to get the required posture of the wrist that will be assembled with the hand in future application. The investigation of the components and mechanism was implemented to make sure that they matched in terms of the dimensions and capability to lift the load. DC geared motor with the calculated torque has been selected as the actuators of the four joints. Spur gear was chosen to increase the motor torque by 4:1 ratio due to the unavailability of higher torque low cost motors to lift 2.635 kg of the required payload. 3D mechanical design and simulation using SolidWorks software application were repeated several times to confirm the link-joint motion before the final design proceeds to the fabrication step. Fabricated arm was tested for movement using the control system from a separate study to observe the feasibility of the design. It can be observed that the joints and links were able to move according to their desired positions except joint 1 that is due to the heavy steel material of the spur gears that has caused misalignment of the gears during rotation. Replacing these gears with nylon or ABS material is expected to solve the problem in the next study. Overall, the constructed robot arm proved that the proposed design is able to achieve the design requirements and practically moved in several postures in real time. With minor modification, it will be a good reference for the development of the actual sized arm for the existing hand in the next study.Â

Behavior Monitoring Based on Intensity Matrix Distribution in Output Plane of Single-Mode Fiber Bundle

A smart structure using intensity-based optical fiber sensors has the potential to be a simple and low-cost system. In this paper, a novel fiber-optic smart structure system using a complementary metal–oxide–semiconductor (CMOS) is demonstrated that simultaneously monitors a number of hetero-core optical fiber bending sensors. The proposed system can integrate a number of optical fiber transmission lines. Therefore, the system does not require a number of photodetectors, which is different from conventional techniques. To simultaneously measure optical intensity, we coupled a number of hetero-core optical fiber sensors to a CMOS camera. The optical fiber sensor can detect macrobending to the optical light intensity. The output images comprise luminance spots distribution directly representing the sensor arrangements in the smart structure. A template matching technique based on the sum of absolute differences was introduced to distinguish between the overall behaviors of structures. A recognition experiment for object shapes was performed with a smart pressure sheet in which hetero-core optical fiber sensors are embedded as a simple case. In addition, a real-time human body posture recognition application was implemented using a fiber-optic smart clothing to apply the proposed system. Recognition results show that all images comprising luminance spots distribution were matched with the correct template images, with an error rate of 0% for 15 trials.

Towards Wearable Everyday Body-Frame Tracking using Passive RFIDs

We introduce RF-Wear, an accurate and wearable solution to track movements of a user's body using passive RFIDs embedded in their clothing. RF-Wear processes wireless signals reflected off these tags to a compact single-antenna RFID reader in the user's pocket. In doing so, RF-Wear enables a first-of-its-kind body-frame tracking mechanism that is lightweight and convenient for day-to-day use, without relying on external infrastructure. At the heart of RF-Wear is a novel primitive that computes angles between different parts of the user's body using the RFID tags attached to them. RF-Wear achieves this by treating groups of RFID tags as an array of antennas whose orientation can be computed accurately relative to the handheld reader. By computing the orientation of individual body parts, we demonstrate how RF-Wear reconstructs the real-time posture of the user's entire body frame. Our solution overcomes multiple challenges owing to the interactions of wireless signals with the body, the 3-D nature of human joints and the flexibility of fabric on which RFIDs are placed. We implement and evaluate a prototype of RF-Wear on commercial RFID readers and tags and demonstrate its performance in body-frame tracking. Our results reveal a mean error of 8--12° in tracking angles at joints that rotate along one degree-of-freedom, and 21°- azimuth, 8°- elevation for joints supporting two degrees-of-freedom.

Robust and Accurate Capture of Human Joint Pose Using an Inertial Sensor.

Wearable inertial measurement units (IMU) measuring acceleration, earth magnetic field, and gyroscopic measurements can be considered for capturing human skeletal postures in real time. Number of movement disorders require accurate and robust estimation of the human joint pose. Though these movements are inherently slow, the accuracy of estimation is vital as many subtle moment patterns, such as tremor are useful to capture under many assessments scenarios. Also, as the end user is a patient with movement disabilities, the practical wearability aspects impose stringent requirements such as the use of minimal number of sensors as well as positioning them in conformable areas of the human body; particularly for longer term monitoring. Estimating skeletal and limb orientations to describe human posture dynamically via model-based approaches poses numerous challenges. In this paper, we convey that the use of measurement conversion ideas-a representation signifying a linear characterization of an inherently non linear estimation problem, pragmatically improves the overall estimation of the limb orientation. A quaternion, as opposed to the Euler angle-based approach is adopted to avoid Gimbal lock scenarios. We also lay a systematic basis for quaternion normalization, typically performed in the pre-filtering stage, by introducing an optimization-based mathematical justification. A robust version of the extended Kalman filter is configured to amalgamate the underlying ideas in enhancing the overall system performance while providing a structured and a comprehensive approach to IMU-based real time human pose estimation problem, particularly in a movement disability capture context.

Investigation of PID Control Model Performance in Off-road Working Vehicle Motion Stability Control System

This paper focuses on tip-over problem of orchard vehicle, establishes vehicle dynamic model with 7 degrees of freedom (DOF), and proposes a vehicle motion stability control method based on real-time adjustment of vehicle posture parameters, relies on ADAMS and MATLAB to set up co-simulation control model, and conducts vehicle scale model motion stability control simulation and test. Analysis of simulation result shows that vehicle motion stability control model mentioned above can effectively prevent orchard vehicle tip-over accidents. To verify simulation result, vehicle state parameter collection system is established to acquire information on vehicle velocity and posture in real time. It is found in the same environment, including road conditions and parameter adjustment, vehicle scale model test and co-simulation result have a basically consistent variation tendency. When vehicle encounters tip-over accident, angles such as pitching angle vary rapidly. In anti-tip-over control process, pitching and rolling angle have greater influence on vehicle motion stability. If Kp and Kd are adjusted properly, good vehicle motion stability control effect is acquired.DOI: http://dx.doi.org/10.5755/j01.eie.23.2.17256

Real time RULA assessment using Kinect v2 sensor

The evaluation of the exposure to risk factors in workplaces and their subsequent redesign represent one of the practices to lessen the frequency of work-related musculoskeletal disorders. In this paper we present K2RULA, a semi-automatic RULA evaluation software based on the Microsoft Kinect v2 depth camera, aimed at detecting awkward postures in real time, but also in off-line analysis. We validated our tool with two experiments. In the first one, we compared the K2RULA grand-scores with those obtained with a reference optical motion capture system and we found a statistical perfect match according to the Landis and Koch scale (proportion agreement index = 0.97, k = 0.87). In the second experiment, we evaluated the agreement of the grand-scores returned by the proposed application with those obtained by a RULA expert rater, finding again a statistical perfect match (proportion agreement index = 0.96, k = 0.84), whereas a commercial software based on Kinect v1 sensor showed a lower agreement (proportion agreement index = 0.82, k = 0.34).

A real-time posture monitoring method for rail vehicle bodies based on machine vision

ABSTRACTMonitoring vehicle operation conditions has become significantly important in modern high-speed railway systems. However, the operational impact of monitoring the roll angle of vehicle bodies has principally been limited to tilting trains, while few studies have focused on monitoring the running posture of vehicle bodies during operation. We propose a real-time posture monitoring method to fulfil real-time monitoring requirements, by taking rail surfaces and centrelines as detection references. In realising the proposed method, we built a mathematical computational model based on space coordinate transformations to calculate attitude angles of vehicles in operation and vertical and lateral vibration displacements of single measuring points. Moreover, comparison and verification of reliability between system and field results were conducted. Results show that monitoring of the roll angles of car bodies obtained through the system exhibit variation trends similar to those converted from the dynamic deflection of bogie secondary air springs. The monitoring results of two identical conditions were basically the same, highlighting repeatability and good monitoring accuracy. Therefore, our monitoring results were reliable in reflecting posture changes in running railway vehicles.