Posture Identification Research Articles

IoMT-Enabled Fusion-Based Model to Predict Posture for Smart Healthcare Systems

Smart healthcare applications depend on data from wearable sensors (WSs) mounted on a patient’s body for frequent monitoring information. Healthcare systems depend on multi-level data for detecting illnesses and consequently delivering correct diagnostic measures. The collection of WS data and integration of that data for diagnostic purposes is a difficult task. This paper proposes an Errorless Data Fusion (EDF) approach to increase posture recognition accuracy. The research is based on a case study in a health organization. With the rise in smart healthcare systems, WS data fusion necessitates careful attention to provide sensitive analysis of the recognized illness. As a result, it is dependent on WS inputs and performs group analysis at a similar rate to improve diagnostic efficiency. Sensor breakdowns, the constant time factor, aggregation, and analysis results all cause errors, resulting in rejected or incorrect suggestions. This paper resolves this problem by using EDF, which is related to patient situational discovery through healthcare surveillance systems. Features of WS data are examined extensively using active and iterative learning to identify errors in specific postures. This technology improves position detection accuracy, analysis duration, and error rate, regardless of user movements. Wearable devices play a critical role in the management and treatment of patients. They can ensure that patients are provided with a unique treatment for their medical needs. This paper discusses the EDF technique for optimizing posture identification accuracy through multi-feature analysis. At first, the patients’ walking patterns are tracked at various time intervals. The characteristics are then evaluated in relation to the stored data using a random forest classifier.

AN EXPERIMENTAL APPROACH TO IMPROVING THE JOINT STIFFNESS OF INDUSTRIAL ROBOTS THROUGH DEXTEROUS POSTURE IDENTIFICATION

Improving a robot’s posture enables it to perform with greater accuracy and repeatability. A stiffer posture also protects the robot from unnecessary vibrations and deflections that may be induced by an applied load. This paper presents a method for choosing high stiffness robot postures. The method is demonstrated on a six-degree-of-freedom Fanuc M10-iA serial manipulator. The posture identification and stiffness modelling were achieved by a reliable and cost-effective alternative to deflection measurement using IEPE accelerometers.

Sensor based posture detection system

Posture identification system has been extensively useful in areas such as physical activities, ecological awareness events, man machine interfacing applications, control room panel monitoring systems and in autonomous old people caring systems. This paper describes a sensor based posture detection and guidance system while doing yoga exercise. In our day-to-day life, doing yoga exercise has become a well-known discipline, which helps people to be physically fit and have good mental health. Practicing yoga exercise is a recognized system for the human beings to improve their physical and mental activities. This practice helps in regulatory activities in an individual’s mind, body and soul. As a result of this, flexibility, muscle power and body image will increase. The existing method has shown the recognition of posture analysis through virtual reality and exergame. We proposed a suit that is designed and implemented through a virtual master. The suit is integrated with various types of accelerometer sensors which are fixed on the flexible bands, that are light in weight and are used indirectly to measure the orientation of the limbs. Also the sensor integrated suit is very helpful to measure the direction of the tilt moment. Predefined calibrated values are loaded on to the microcontroller, which are compared with the measured values and when there is a match the information is sent to a mobile application. The mobile app identifies whether the user is doing the posture correctly or not based on the information given to practice the yoga exercise.

Identification of Movements and Postures Using Wearable Sensors for Implementation in a Bi-Hormonal Artificial Pancreas System.

Background: Closed loop bi-hormonal artificial pancreas systems, such as the artificial pancreas (AP™) developed by Inreda Diabetic B.V., control blood glucose levels of type 1 diabetes mellitus patients via closed loop regulation. As the AP™ currently does not classify postures and movements to estimate metabolic energy consumption to correct hormone administration levels, considerable improvements to the system can be made. Therefore, this research aimed to investigate the possibility to use the current system to identify several postures and movements. Methods: seven healthy participants took part in an experiment where sequences of postures and movements were performed to train and assess a computationally sparing algorithm. Results: Using accelerometers, one on the hip and two on the abdomen, user-specific models achieved classification accuracies of 86.5% using only the hip sensor and 87.3% when including the abdomen sensors. With additional accelerometers on the sternum and upper leg for identification, 90.0% of the classified postures and movements were correct. Conclusions: The current hardware configuration of the AP™ poses no limitation to the identification of postures and movements. If future research shows that identification can still be done accurately in a daily life setting, this algorithm may be an improvement for the AP™ to sense physical activity.

Pressure Sensor Array With Low-Power Near-Sensor CMOS Chip for Human Gait Monitoring

Recent years have witnessed the emerging development of flexible electronic devices in applications, such as human gait monitoring. The automatic posture identification could be achieved by sensing the feet pressure. However, the sensor data processing chip usually consumes high power. In this letter, a wearable gait recognition system integrated with an ultrahigh-energy efficiency chip is proposed. A low-power human gait pressure monitoring and recognition solution that uses artificial intelligence near-sensor chips is reported. A large-scale flexible pressure sensor array (64 × 64 pixels) was fabricated. The gait posture was recognized dynamically with a CMOS chip embedded near the sensors. The system owns a recognition rate for three different gaits of 92% with the chip power consumption of 1.45 mW. This letter paves the way for future low-power human gait monitoring.

RETRACTED ARTICLE: Error-less data fusion for posture detection using smart healthcare systems and wearable sensors for patient monitoring

Smart healthcare applications rely on frequent monitoring information from the patient’s body using wearable sensors (WSs). Healthcare systems rely on multi-level information for identifying the diseases and hence providing a proper diagnosis. The challenging task is the acquisition of WS information and assimilation of the same for diagnosis purposes. This proposal introduces an error-less data fusion (EDF) technique for improving the accuracy of posture identification. In a smart healthcare system, WS data fusion requires intense care for providing sensitive analysis of the diagnosed disease. Therefore, it depends on the WS data and collectively analyzes the same frequency for improving diagnosis efficiency. Errors due to the sensors’ failure, invariant time factor, aggregation, and analysis result in failed or inappropriate recommendations. This proposal addresses this issue using EDF relevant for posture detection of patients through healthcare monitoring systems. The WS data features are intensively analyzed using active and repeated learning for identifying the errors in different fusion processes. This technique is keen on improving the precision of posture detection, time of analysis, and error rate, irrespective of the users’ movement actions.

Monitoring Indoor Activity of Daily Living using Thermal Imaging: A Case Study

Monitoring indoor activities of daily living (ADLs) of a person is subjected to dependency on sensor type, power supply stability, and connectivity stability without mentioning artifacts introduced by the person himself. Multiple challenges have to be overcome in this field, such as; detecting the precise spatial location of the person, and estimating vital signs like an individual’s average temperature. Privacy is another domain of the problem to be thought of with care. Identifying the person’s posture without a camera is another challenge. Posture identification is a key in assisting detection of a person’s fall. Thermal imaging could be a proper solution for most of the mentioned challenges. It provides monitoring both the person’s average temperature and spatial location while maintaining privacy. In this research, an IoT system for monitoring an indoor ADL using thermal sensor array (TSA) is proposed. Three classes of ADLs are introduced, which are daily activity, sleeping activity and no-activity respectively. Estimating person average temperature using TSAs is introduced as well in this paper. Results have shown that the three activity classes can be identified as well as the person’s average temperature during day and night. The person’s spatial location can be determined while his/her privacy is maintained as well.

Design of an ergonomic App for entire rapid body assessment based on Mask RCNN

The rapid entire body assessment (REBA) is a rapid and semi-quantitative ergonomic assessment method for those who engaged in manual handling and/or standing work for a long time. In order to provide a self-assessment tool for operators, an App software based on Mask RCNN is proposed in this paper. The software is developed by adopting the architecture of a mobile terminal App combined with an imaging processing server. The main functions of the App are video capturing of work process, the operation of the process of REBA, human-machine interaction, etc., while the server is work for processing the video imaging transmitted from the App, key-points extraction of worker’s body from the images for work posture identification. One thousand working scene photos marked by VIA are used for training and testing based on the Microsoft COCO dataset to obtain a reliable target detection model. Experiment of container handling scene shows that the App evaluation software has achieved higher evaluation efficiency and accuracy. The validation of this method has been proved compared with manual evaluation based on REBA. And other work posture evaluation methods will be developed in the future to form an ergonomic evaluation software system.

Smart Sleep Monitoring System via Passively Sensing Human Vibration Signals

In this paper, a bed-mounted vibration sensor-based system is proposed to monitor vital parameters during sleep, including heartbeat rate (HR) and respiratory rate (RR), body movements and sleep postures. Our system enables smart healthcare that monitors daily sleep in a ubiquitous and non-invasive manner. Besides, the system is contact-free, as no external wearable devices and physical contacts are required. Furthermore, the vibration-based approach also avoids the privacy violation caused by the usage of surveillance cameras. To effectively monitor sleep status, a robust stable signal mode decomposition based HR and RR estimation method is developed for the complicated and noisy vibration signals. Besides, algorithms for body movement and sleep posture identification are also proposed based on vibration signal features. A prototype system is demonstrated with system details, showing great potentials in monitoring sleep status in a real-time user-friendly manner. Experimental results of short term and long term experiments with different participants and beds show that our system achieves satisfying accuracy compared with dedicated commercial devices.

Deep learning-based classification of work-related physical load levels in construction

Work-related musculoskeletal disorders (WMSDs) are the leading cause of the nonfatal injuries for construction workers, and a worker’s overexertion is a major source of such WMSDs. Pushing, pulling, and carrying movements—which are all activities largely associated with physical loads—account for 35% of WMSDs. However, most previous studies have focused on the identification of non-ergonomic postures, and there has been limited effort expended on measuring a worker’s exposures to the physical loads caused by materials or tools during construction tasks. With the advantage of using a wearable inertial measurement sensor to monitor a worker’s bodily movements, this study investigates the feasibility of identifying various physical loading conditions by analyzing a worker’s lower body movements. In the experiment with laboratory settings, workers performed a load carrying task by moving concrete bricks. A bidirectional long short-term memory algorithm is employed to classify physical load levels; this approach achieved 74.6 to 98.6% accuracy and 0.59 to 0.99 F-score in classification. The results demonstrate the feasibility of the proposed approach in identifying the states of physical loads. The findings of this study contribute to the literature on classifying ergonomically at-risk workers and on preventing WMSDs in high physical demand occupations, thereby helping enhance the health and safety of the construction workplace.

Posture, movement, and aircraft passengers: An investigation into factors influencing in-flight discomfort.

Aircraft passengers' physical activity levels are often limited during flight for extended periods of time, which can have serious impact on health, comfort, and passenger experience. However, several factors, such as limited personal space and social factors, can make movement difficult. The study aimed to identify participant behaviour and postures during medium to long-haul flights and their effect on location and severity of physical discomfort. This work investigated how aircraft passengers' comfort ratings changed over time and explored the association between postures and comfort ratings during flight. The study also explored the association between performing in-flight exercises and factors limiting participants' abilities to complete these exercises. Twenty-nine participants sat in an aircraft simulated cabin for 180 minutes and periodically performed in-seat exercises. They also completed a questionnaire providing data on demographic information, self-reported discomfort scores for multiple areas of the body, which types of exercises participants performed, and qualitative comments about discomfort. Self-reported comfort ratings were measured at 20 min intervals and posture identification was conducted by analysing the video recordings. Six postures were identified, and it was observed that individual participants changed posture at least once and up to nine times during the three-hour period. Body part areas with the highest reported scores of discomfort ratings were: back of the neck, back-left shoulder, back-right shoulder, back-left buttock, and lower back. Participants reported that they had difficulty in performing recommended in-flight exercises due to limited space. Limited space in aircraft seating restricts passenger movement. Some body areas are more prone to discomfort.

Kinematic modeling of a motorcycle rider for design of functional clothing

Purpose Whilst motorcycling is an activity of pleasure in most parts of the world, in India, it is a regular mode of commuting. The number of registered motorized two wheelers increased at the rate of 14.7 percent during the year 2016-2017 to reach the figure of 20.19m in 2018. But, with this increase, the number of motorcycle road accidents is also increasing. Uncomfortable riding clothing is one of the major factors for motorcycle rider’s muscular fatigue, which might at times lead to serious accidents. No kinematic human models have been, so far, used for the design of protective, functional and aesthetic looking products, and the result is, hence, a compromised fit that is not protective or comfortable. The purpose of this paper is to develop virtual 3D human body models for specific postures of a motorcycle rider. Design/methodology/approach Kinematic analysis of a motorcycle rider was conducted to identify typical body postures obtained by the motorcycle rider while mounting and riding a motorcycle. The identified body postures were mapped on a virtual parametric human model to obtain digital model of a motorcycle rider. 3D garment patterns for jacket and trouser were developed on all the four body postures. 3D patterns were flattened out to get 2D flat patterns that were compared and analyzed, and appropriate pattern shapes from each of the four postures were selected. Virtual fit analysis was conducted for the finally garment. Findings It is well established that a static 2D anthropometry fails to accurately capture the dimensions of complex 3D human form, yielding poor garment fit. Therefore, in this study, virtual, 3D human body models were developed in selected dynamic poses. Garment patterns developed in 3D have the typical movement inbuilt in them; hence, they offer more comfort and ease of motion to the wearer. Originality/value The identification of typical body postures of motorcycle rider has not been done before. The CAD models developed in the study can be used for the generation of ergonomic garment patterns for the motorcycle riders.

Joint-angle-based yoga posture recognition for prevention of falls among older people

PurposeUnited Nations’ World Population Ageing Report states that falls are one of the most common problems in the elderly around the world. Falls are a leading cause of morbidity and mortality among mature adults, and the second leading cause of accidental or unintentional injury/death after road traffic injuries. The rates are higher in hospitalized patients and nursing home residents. Major contributing reasons for falling are loss of footing or traction, balance problem in carpets and rugs, reduced muscle strength, poor vision, mobility/gait, cognitive impairment: in other words lack of balance. Balance can be improved by the practice of yoga which helps to balance both body and mind through a series of physical postures called asanas, breathing control and meditation. Elders, especially women, are often unable to practice yoga regularly, largely brought on by a feeling of discomfort at having to do so in full public view, preferring instead to have private sessions at home, and at leisure. A computer-assisted self-learning system can be developed to help such elders, though improper training and the postures associated with it may harm the body’s muscles and ligaments. To have a flawless system it is essential to classify asanas, and identify the one the practitioner is currently practicing, following which the system can offer the guidance necessary. The purpose of this paper is to propose a posture recognition system, especially of sitting and standing postures. Asanas are chiefly classified into two: sitting and standing postures. This study helps to decide the values of the parameters for classification, which involve the hip and joint angles.Design/methodology/approachTo model human bodies, skeleton parts such as head, neck (which are responsible for head movements), arms, hands (to decide on hand postures), and legs and feet (for standing posture identification) have been modeled and stored as a vector. Each feature is defined as a set of movable joints. Every interaction among the skeleton joints defines an action. Human skeletal information may be represented as a hierarchy of joints, in a parent–child relationship. So that whenever there is a change in joint its corresponding parent joint may also be altered.FindingsThe findings have to do with analyzing the reasons for falls in the elderly and their need for yoga as a precautionary measure. As yoga is ideally suited to self-assisted learning, it is feasible to design a system that assists people who do not wish to practice yoga in public. However, asanas are to be classified prior to doing so. In this paper, the authors have designed a posture identification framework comprising the sitting and standing postures that are fundamental to all yoga asanas, using joint angle measurements. Having fixed joint angle values is not possible, given the variations in angle values among the participants. Consequently, such parameters as the hip joint and knee angles are to be specified in range for a classification of asanas.Research limitations/implicationsThis work identifies the angle limits of standing and sitting postures so as to design a self-assisting system for yoga. Yoga asanas are classified and tested to enable their accurate identification. Extensive testing with older people is needed to assess the system.Practical implicationsThe increase in the population of the elderly, coupled with their need for medical care, is a major concern worldwide. As older people are reluctant to practice yoga in public, it is anticipated that the proposed system will motivate them to do so at their convenience, and in the seclusion of their homes.Social implicationsAs older people are reluctant to adapt as well as practice yoga in public view, the proposal motivates and helps them to carry out yoga practices at their convenience.Originality/valueThis paper fulfills the initial study on the need and feasibility of creating a self-assisted yoga learning system. To identify postures and classify them joint angles are used; their range of motion has been calculated in order to set them as parameters of classification.

Screening by changes in stereotypical behavior during cell motility

Stereotyped behaviors are series of postures that show very little variability between repeats. They have been used to classify the dynamics of individuals, groups and species without reference to the lower-level mechanisms that drive them. Stereotypes are easily identified in animals due to strong constraints on the number, shape, and relative positions of anatomical features, such as limbs, that may be used as landmarks for posture identification. In contrast, the identification of stereotypes in single cells poses a significant challenge as the cell lacks these landmark features, and finding constraints on cell shape is a non-trivial task. Here, we use the maximum caliber variational method to build a minimal model of cell behavior during migration. Without reference to biochemical details, we are able to make behavioral predictions over timescales of minutes using only changes in cell shape over timescales of seconds. We use drug treatment and genetics to demonstrate that maximum caliber descriptors can discriminate between healthy and aberrant migration, thereby showing potential applications for maximum caliber methods in automated disease screening, for example in the identification of behaviors associated with cancer metastasis.

Real-time analysis of the behaviour of groups of mice via a depth-sensing camera and machine learning.

Preclinical studies of psychiatric disorders use animal models to investigate the impact of environmental factors or genetic mutations on complex traits such as decision-making and social interactions. Here, we introduce a method for the real-time analysis of the behaviour of mice housed in groups of up to four over several days and in enriched environments. The method combines computer vision through a depth-sensing infrared camera, machine learning for animal and posture identification, and radio-frequency identification to monitor the quality of mouse tracking. It tracks multiple mice accurately, extracts a list of behavioural traits of both individuals and the groups of mice, and provides a phenotypic profile for each animal. We used the method to study the impact of Shank2 and Shank3 gene mutations-mutations that are associated with autism-on mouse behaviour. Characterization and integration of data from the behavioural profiles of Shank2 and Shank3 mutant female mice revealed their distinctive activity levels and involvement in complex social interactions.

Activity Recognition for Ergonomics Assessment of Industrial Tasks With Automatic Feature Selection

In industry, ergonomic assessment is currently performed manually based on the identification of postures and actions by experts. We aim at proposing a system for automatic ergonomic assessment based on activity recognition. In this letter, we define a taxonomy of activities, composed of four levels, compatible with items evaluated in standard ergonomic worksheets. The proposed taxonomy is applied to learn activity recognition models based on Hidden Markov Models. We also identify dedicated sets of features to be used as input of the recognition models so as to maximize the recognition performance for each level of our taxonomy. We compare three feature selection methods to obtain these subsets. Data from 13 participants performing a series of tasks mimicking industrial tasks are collected to train and test the recognition module. Results show that the selected subsets allow us to successfully infer ergonomically relevant postures and actions.

Body Posture Visualizer to Support Multimodal Learning Analytics

Learning analytics consists of gathering and analyzing data from students in order to understand complex aspects of the learning process and promote its improvement. Currently, to the best of our knowledge, there is a lack of tools aimed at displaying multimodal data in an integrated way for general purpose analysis. In this paper, we present a free software tool based on the Microsoft Kinect sensor for automatic capture, identification, and visualization of ten body postures for posterior analysis. It is also possible to incorporate the identification of new postures if necessary. Learning and recognition is based on the AdaBoost algorithm. Posture recognition reached accuracy rates as high as 80% for 8 of the 10 identified postures. Concerning the software usability, a heuristic evaluation with three specialists was performed, as well as a usability test with five volunteer students. Results indicated that the software interface, based on the metaphor of a video editor, may allow its effective use by end users, though some adjustments are still necessary, such as the terminology used in some commands and the help system.

Threshold-based fall detection using a hybrid of tri-axial accelerometer and gyroscope

Objective: Falling is an important health maintenance issue for the elderly and people with movement disorders, strokes and multiple sclerosis. With the development of light, low-cost wearable technology, inertia-based fall detection has gained much attention. However, some large movements, such as jumping and postural changes, are frequently confounded with falls. For example, commonly used fall detection methods based on acceleration amplitude produce a large number of false alerts unless they are combined with post-fall posture identification. In this paper, we propose two new inertial parameters to improve the selectivity of threshold-based fall detection methods, and evaluate strategies to distinguish falls from other activities of daily life (ADLs). Approach: We define two new inertial parameters, acceleration cubic-product-root magnitude (ACM) and angular velocity cubic-product-root magnitude (AVCM). Along with acceleration magnitude (AM), we test threshold-based fall detection methods based on single parameters and combinations. We collected inertial data on four types of simulated falls and eight types of ADLs from a study with 15 participants wearing a chest-mounted sensor with accelerometer and gyroscope. Two public datasets, UMAFall and Cognent Labs, were also included to evaluate fall detection methods. Main results: We chose the detection threshold with 99% sensitivity and the best possible specificity. The hybrid of AM, ACM and AVCM method had a lower rate of misclassification than single-parameter methods. Leave-one-out cross-validation shows that the hybrid fall detection method can achieve both high specificity and high sensitivity. Significance: Using multiple inertial parameters improves the specificity of fall detection.

Data fusion and multiple classifier systems for human activity detection and health monitoring: Review and open research directions

Activity detection and classification using different sensor modalities have emerged as revolutionary technology for real-time and autonomous monitoring in behaviour analysis, ambient assisted living, activity of daily living (ADL), elderly care, rehabilitations, entertainments and surveillance in smart home environments. Wearable devices, smart-phones and ambient environments devices are equipped with variety of sensors such as accelerometers, gyroscopes, magnetometer, heart rate, pressure and wearable camera for activity detection and monitoring. These sensors are pre-processed and different feature sets such as time domain, frequency domain, wavelet transform are extracted and transform using machine learning algorithm for human activity classification and monitoring. Recently, deep learning algorithms for automatic feature representation have also been proposed to lessen the burden of reliance on handcrafted features and to increase performance accuracy. Initially, one set of sensor data, features or classifiers were used for activity recognition applications. However, there are new trends on the implementation of fusion strategies to combine sensors data, features and classifiers to provide diversity, offer higher generalization, and tackle challenging issues. For instances, combination of inertial sensors provide mechanism to differentiate activity of similar patterns and accurate posture identification while other multimodal sensor data are used for energy expenditure estimations, object localizations in smart homes and health status monitoring. Hence, the focus of this review is to provide in-depth and comprehensive analysis of data fusion and multiple classifier systems techniques for human activity recognition with emphasis on mobile and wearable devices. First, data fusion methods and modalities were presented and also feature fusion, including deep learning fusion for human activity recognition were critically analysed, and their applications, strengths and issues were identified. Furthermore, the review presents different multiple classifier system design and fusion methods that were recently proposed in literature. Finally, open research problems that require further research and improvements are identified and discussed.

Inverse Piezoresistive Nanocomposite Sensors for Identifying Human Sitting Posture.

Sitting posture is the position in which one holds his/her body upright against gravity while sitting. Poor sitting posture is regarded as an aggravating factor for various diseases. In this paper, we present an inverse piezoresistive nanocomposite sensor, and related deciphering neural network, as a new tool to identify human sitting postures accurately. As a low power consumption device, the proposed tool has simple structure, and is easy to use. The strain gauge is attached to the back of the user to acquire sitting data. A three-layer BP neural network is employed to distinguish normal sitting posture, slight hunchback and severe hunchback according to the acquired data. Experimental results show that our method is both realizable and effective, achieving 98.75% posture identification accuracy. This successful application of inverse piezoresistive nanocomposite sensors reveals that the method could potentially be used for monitoring of diverse physiological parameters in the future.