Posture Detection Research Articles

Automatic detection of sow posture and estrus based on convolutional neural network

Estrus detection is an essential operation in the breeding of sows, and accurate estrus detection is immensely important to maintain the productivity and reproductive performance of sow. However, traditional sow estrus detection relies on the manually back-pressure test, which is time-consuming and labor-intensive. This study aimed to develop an automatic method to detect estrus. In this study, a model based on the optimized yolov5s algorithm was constructed to detect the four sow postures of standing, sitting, sternum, lateral, and calculated the frequency of posture change in sows. Based on this, we studied the behavior of sows before and after estrus. The method embedded a convolutional block attention module into the backbone network to improve the feature extraction capability of the model. In addition, the object box judgment module was used to avoid interference from other sows in the detection region. Accelerate the optimized model on the TensorRT platform, ensuring that the embedded graphics card can run the model with lower latency. The result shows that the precision of estrus detection is 97.1%, and the accuracy of estrus detection is 94.1%. The processing time of a single image on the embedded graphics card is 74.4 ms, and this method could better meet the estrus detection demand in sow production.

Human Posture Detection Using Image Augmentation and Hyperparameter-Optimized Transfer Learning Algorithms

With the advancement in pose estimation techniques, human posture detection recently received considerable attention in many applications, including ergonomics and healthcare. When using neural network models, overfitting and poor performance are prevalent issues. Recently, convolutional neural networks (CNNs) were successfully used for human posture recognition from human images due to their superior multiscale high-level visual representations over hand-engineering low-level characteristics. However, calculating millions of parameters in a deep CNN requires a significant number of annotated examples, which prohibits many deep CNNs such as AlexNet and VGG16 from being used on issues with minimal training data. We propose a new three-phase model for decision support that integrates CNN transfer learning, image data augmentation, and hyperparameter optimization (HPO) to address this problem. The model is used as part of a new decision support framework for the optimization of hyperparameters for AlexNet, VGG16, CNN, and multilayer perceptron (MLP) models for accomplishing optimal classification results. The AlexNet and VGG16 transfer learning algorithms with HPO are used for human posture detection, while CNN and Multilayer Perceptron (MLP) were used as standard classifiers for contrast. The HPO methods are essential for machine learning and deep learning algorithms because they directly influence the behaviors of training algorithms and have a major impact on the performance of machine learning and deep learning models. We used an image data augmentation technique to increase the number of images to be used for model training to reduce model overfitting and improve classification performance using the AlexNet, VGG16, CNN, and MLP models. The optimal combination of hyperparameters was found for the four models using a random-based search strategy. The MPII human posture datasets were used to test the proposed approach. The proposed models achieved an accuracy of 91.2% using AlexNet, 90.2% using VGG16, 87.5% using CNN, and 89.9% using MLP. The study is the first HPO study executed on the MPII human pose dataset.

Visual detection on posture transformation characteristics of sows in late gestation based on Libra R-CNN

Posture transformation characteristics of sows in late gestation can be used as intuitive indicators to predict sow delivery time. To reduce the imbalance in posture distribution and insignificant differences between coherent sow postures in late gestation, a model based on Libra R-CNN was proposed to recognise the sow postures. Libra R-CNN is a simple but effective framework that incorporates intersection over union (IoU)-balanced sampling, a balanced feature pyramid, and balanced L1 loss, aiming to balance learning for object detection. The model used here realised the recognition of sow postures: lateral, sternum , sitting, and standing. Experimental results revealed close relationships between the two basic characteristics (‘ratio of express nesting behaviour’ and ‘frequency of postural transformation’) and delivery time. The mean average precision values for IoU = 0.5 (mAP 0.5 ) of Libra R-CNN on the validation and test sets from the sow posture sample library were 0.97 and 0.96, whilst the AP value of various postures was balanced. From 16 to 4 h before sow farrowing, the values of the two basic characteristics were significantly increased and lasted for a long time, and started to decrease rapidly 4 h before farrowing. Heat stress caused sow agitation but decreased nesting behaviour before parturition . The Pearson correlation coefficients of 15 features constructed based on the two characteristics and delivery time were all above 0.6. Therefore, Libra R-CNN realised the detection of sow posture and the two basic characteristics can be used as effective indicators for the automated prediction of sow delivery time. • Nesting behaviour and the frequency of postural transformation investigated. • Values of both characteristics significantly increased before sows farrowing. • Characteristics used as effective indicators for sow delivery prediction. • The mAP 0.5 of Libra R-CNN for the validation sets was 0.97. • Heat stress shown to cause sow agitation, but decreased nesting behaviour.

Research on the Efficiency of Working Status Based on Wearable Devices in Different Light Environments.

According to the working scenes, a proper light environment can enable people to maintain greater attention and meditation. A posture detection system in different working scenes is proposed in this paper, and different lighting conditions are provided for changes in body posture. This aims to stimulate the nervous system and improve work efficiency. A brainwave acquisition system was used to capture the participants’ optimal attention and meditation. The posture data are collected by ten miniature inertial measurement units (IMUs). The gradient descent method is used for information fusion and updating the participant’s attitude after sensor calibration. Compared with the optical capture system, the reliability of the system is verified, and the correlation coefficient of both joint angles is as high as 0.9983. A human rigid body model is designed for reconstructing the human posture. Five classical machine learning algorithms, including logistic regression, support vector machine (SVM), decision tree, random forest, and k-nearest neighbor (KNN), are used as classification algorithms to recognize different postures based on joint angles series. The results show that SVM and random forest achieve satisfactory classification effects. The effectiveness of the proposed method is demonstrated in the designed systematic experiment.

An Intelligent Cost-Efficient System to Prevent the Improper Posture Hazards in Offices Using Machine Learning Algorithms.

In this research, an intelligent and cost-efficient system has been proposed to detect the improper sitting posture of a person working at a desk, mostly in offices, using machine learning classification techniques. The current era demands to avoid the harms of an improper posture as it, when prolonged, is very painful and can be fatal sometimes. This study also includes a comparison of two arrangements. Arrangement 01 includes six force-sensitive resistor (FSR) sensors alone, and it is less expensive. Arrangement 02 consists of two FSR sensors and one ultrasonic sensor embedded in the back seat of a chair. The K-nearest neighbor (KNN), Naive Bayes, logistic regression, and random forest algorithms are used to augment the gain and enhanced accuracy for posture detection. The improper postures recognized in this study are backward-leaning, forward-leaning, left-leaning, and right-leaning. The presented results validate the proposed system as the accuracy of 99.8% is achieved using a smaller number of sensors that make the proposed prototype cost-efficient with improved accuracy and lower execution time. The proposed model is of a dire need for employees working in offices or even at the residential level to make it convenient to work for hours without having severe effects of improper posture and prolonged sitting.

Automatic Detection of Unbalanced Sitting Postures in Wheelchairs Using Unlabeled Sensor Data

This letter presents an effective data-driven anomaly detection scheme for automatically recognizing unbalanced sitting posture in a wheelchair using data from pressure sensors embedded in the wheelchair. Essentially, the designed approach merges the desirable features of the kernel principal component analysis (KPCA) as a feature extractor with the Kantorovich distance (KD)-driven monitoring chart to detect abnormal sitting posture in a wheelchair. It is worth noting that this approach does not require labeled data but only employs normal event data to train the detection model, which makes it more appealing in practice. Specifically, we used the KPCA model to exploit its capacity to reduce the dimensionality of nonlinear data to obtain good detection. At the same time, the KD monitoring scheme is an efficient distribution-driven anomaly detection approach in multivariate data. Furthermore, a nonparametric decision threshold using kernel density estimation is adopted to extend the flexibility of the proposed approach. Publicly available data have been used to verify the detection capacity of the proposed approach. The overall detection system proved promising, outperforming some commonly used monitoring methods.

Automated Detection of Improper Sitting Postures in Computer Users Based on Motion Capture Sensors

Prolonged computer-related work can be linked to musculoskeletal disorders (MSD) in the upper limbs and improper posture. In this regard, we report on developing resources supporting improper posture studies based on motion capture sensors. These resources were used to create a baseline detector for the automated detection of improper sitting postures, which was next used to evaluate the applicability of Hjorth’s parameters—Activity, Mobility and Complexity—on the specific classification task. Specifically, based on accelerometer data, we computed Hjorth’s time-domain parameters, which we stacked as feature vectors and fed to a binary classifier (kNN, decision tree, linear SVM and Gaussian SVM). The experimental evaluation in a setup involving two different keyboard types (standard and ergonomic) validated the practical worth of the proposed sitting posture detection method, and we reported an average classification accuracy of up to 98.4%. We deem that this research contributes toward creating an automated system for improper posture monitoring for people working on a computer for prolonged periods.

Accurate Detection of Intelligent Running Posture Based on Artificial Intelligence Sensor

In order to solve the problem of low accuracy of human posture recognition during motion, the author proposes a human posture recognition and detection method based on multiple sensors. The method uses acceleration sensor, angular velocity sensor, and single-chip microcomputer to collect data; uses time domain and frequency domain analysis methods to analyze the collected data; and then uses Bayesian classifier to classify and identify the current motion posture of the human body. The obtained results are as follows: in the traditional method, with the increase of subjects, the accuracy of the classification method continues to decline; when the number of subjects reaches 50, the accuracy rate is only 60%; in the experiment, the zero crossing times of the acceleration signal axis are selected, and the axis area of the angular velocity signal is used as the characteristic item to distinguish the two different attitudes of going upstairs and going downstairs; the discrimination can reach about 90%. The authors combine the data collected by the acceleration sensor and the angular velocity sensor to perform feature extraction and classification, and the classification accuracy can reach more than 95%. It is proved that the method proposed by the authors can perform human gesture recognition very quickly and has a high accuracy rate.

Intelligent Skiing Posture Detection and Recognition Through Internet of Bodies

The training of special ability of skiing should start from the control of body posture ability to highlight the characteristics of the sports. Thus, the athletes can have the sports ability in the process of high-speed skiing. This paper establishes a system to automatically recognize the skiing posture which can help athletes grasp the skiing postures. First, the skiing images are collected by distributed camera. Second, the skeleton features are extracted to learn a classification model which is used to recognize and adjust skiing postures. Lastly, the analytical results of posture recognition is returned to athletes through Internet of bodies. The framework can effectively recognize the skiing postures and provide athletes with training advices.

Yoga Posture Detection and Correction System

Humans, by nature, are sensitive to a wide range of health problems. Yoga can help you improve your body for the better. Although there are many benefits of exercising, doing so incorrectly can lead to a dangerous lifestyle. As a result, proper instruction is required for people who are completing activities on their own. With the right direction, a person can reach several benefits from activities while also improving his or her health. Activities such as meditation and breathing techniques are very important to increase the mental as well as physical well-being of a person by doing asana. These days, Yoga is very popular around the globe. Many people are using self-learning platforms like TV or Videos. Some people also practice it by teaching to one another. However, it is not easy for beginners for finding the inaccurate parts of their Yoga poses by themselves. Hence, a Yoga posture detection and correction system is designed by us. In our paper, first, a Yoga pose assessment method using improved Machine Learning algorithms for pose detection is proposed by us for helping the self-learning of Yoga[19][23]. Using the system, the user is under real time supervision. User’s pose is compared with the pose in the pre-trained dataset and the difference is calculated between angles of body joints. As a result, the yoga pose is correctly detected. Second, according to the difference in angles the feedback will be provided to the user for improving the pose and doing it correctly. This application designed by us is evaluated on various Yoga postured under varying conditions. As a result, there is a guaranteed robustness.

Sleep Posture Detection Using an Accelerometer Placed on the Neck.

Sleep position monitoring is key when attempting to address posture triggered sleep disorders. Many studies have explored sleep posture detection from a dedicated physical sensing channel exploiting optimum body locations, such as the torso; or alternatively non-contact approaches. But, little work has been done to try to detect sleep position from a body location which, whilst being suboptimal for that purpose, does however allow for better extraction of more critical biomarkers from other sensing modalities, making possible multi-modal monitoring in certain clinical applications. This work presents two different approaches, at varying levels of complexity, for detecting 4 main sleep positions (supine, prone, lateral right and lateral left) from accelerometry data obtained by a single wearable device placed on the neck. An ultra light-weight threshold-based model is presented in this work, in addition to an Extra-Trees classifier. The threshold-based model was able to achieve 95% average accuracy and 0.89 F1-score on out-of-sample data, showing that it is possible to obtain a moderately high classification performance using a simple rule-based model. The ExtraTrees classifier, on the other hand, was able to achieve 99 % average accuracy and 0.99 average F1-score using only 25 base estimators with maximum depth of 20. Both models show promise in detecting sleep posture with high accuracy when collecting the signals from a neck-worn accelerometer sensor.

Technology-Based Compensation Assessment and Detection of Upper Extremity Activities of Stroke Survivors: Systematic Review.

BackgroundUpper extremity (UE) impairment affects up to 80% of stroke survivors and accounts for most of the rehabilitation after discharge from the hospital release. Compensation, commonly used by stroke survivors during UE rehabilitation, is applied to adapt to the loss of motor function and may impede the rehabilitation process in the long term and lead to new orthopedic problems. Intensive monitoring of compensatory movements is critical for improving the functional outcomes during rehabilitation.ObjectiveThis review analyzes how technology-based methods have been applied to assess and detect compensation during stroke UE rehabilitation.MethodsWe conducted a wide database search. All studies were independently screened by 2 reviewers (XW and YF), with a third reviewer (BY) involved in resolving discrepancies. The final included studies were rated according to their level of clinical evidence based on their correlation with clinical scales (with the same tasks or the same evaluation criteria). One reviewer (XW) extracted data on publication, demographic information, compensation types, sensors used for compensation assessment, compensation measurements, and statistical or artificial intelligence methods. Accuracy was checked by another reviewer (YF). Four research questions were presented. For each question, the data were synthesized and tabulated, and a descriptive summary of the findings was provided. The data were synthesized and tabulated based on each research question.ResultsA total of 72 studies were included in this review. In all, 2 types of compensation were identified: disuse of the affected upper limb and awkward use of the affected upper limb to adjust for limited strength, mobility, and motor control. Various models and quantitative measurements have been proposed to characterize compensation. Body-worn technology (25/72, 35% studies) was the most used sensor technology to assess compensation, followed by marker-based motion capture system (24/72, 33% studies) and marker-free vision sensor technology (16/72, 22% studies). Most studies (56/72, 78% studies) used statistical methods for compensation assessment, whereas heterogeneous machine learning algorithms (15/72, 21% studies) were also applied for automatic detection of compensatory movements and postures.ConclusionsThis systematic review provides insights for future research on technology-based compensation assessment and detection in stroke UE rehabilitation. Technology-based compensation assessment and detection have the capacity to augment rehabilitation independent of the constant care of therapists. The drawbacks of each sensor in compensation assessment and detection are discussed, and future research could focus on methods to overcome these disadvantages. It is advised that open data together with multilabel classification algorithms or deep learning algorithms could benefit from automatic real time compensation detection. It is also recommended that technology-based compensation predictions be explored.

Intelligent Running Posture Detection Based on Artificial Intelligence Combined with Sensor

In order to avoid injuries caused by incorrect running posture to a greater extent and reduce the impact on athletes’ performance and physical health, on the basis of artificial intelligence sensors, the author studies the accurate detection of intelligent running motion posture. Using artificial intelligence sensors, an adaptive error quaternion unscented Kalman filter (DAUKF) algorithm is designed. The attitude analysis and recognition system based on the inertial measurement unit can not only measure the motion information of human body but also obtain the motion characteristic data and movement state of the human body through the analysis of posture data. Use the error quaternion and gyroscope drift error to establish the equation of state, the measurement values of the accelerometer and magnetometer are used to establish the observation equation, and the fading memory method is introduced to adaptively adjust the observation noise covariance, so as to reduce the interference of the system itself and the environment on attitude detection. Experimental results show that the proposed method improves the attitude detection accuracy, effectively suppresses the influence of drift error and dynamic observation noise, and provides a foot attitude detection scheme suitable for long-distance running.

FSR-Based Smart System for Detection of Wheelchair Sitting Postures Using Machine Learning Algorithms and Techniques

This paper presents an intelligent system containing FSR-based posture detection using machine learning algorithms. This paper is aimed at detecting the sitting posture of a wheelchair user. Individuals using wheelchairs are at increased risk of pressure ulcers when they hold an incorrect position for too long because the blood supply desists at some points of their skin due to increased pressure. The main objective of this research is to find a better configuration combined with the best machine learning algorithm for the detection of posture to prevent pressure ulcers. In the proposed monitoring system, two configurations consisting of a 3 × 3 matrix configuration (9 sensors) and a crossconfiguration (5 sensors) of FSR sensors are embedded on a wheelchair seat to get pressure data generated and collected in a real-time processing unit and then compared. The posture recognition is performed for five sitting positions: ideal, backward-leaning, forward-leaning, right-leaning, and left-leaning based on five machine learning algorithms: K -nearest neighbors ( K -NN), logistic regression (LR), decision tree (DT), support vector machines (SVM), and LightGBM. The research study provides a system to detect a real-time pressure sitting posture on a processing unit (laptop) wirelessly using the ESP32 module. Consequently, a posture classification accuracy of up to 95.41% is accomplished using a 3 × 3 matrix configuration. The proposed system helps prevent pressure ulcers and is valuable in risk assessment related to pressure ulcers. This system describes the relationship between accuracy, different sensor configurations, and performance of the multiple machine learning algorithms.

Augmented Reality Based Fitness Website: ProFIT-AR

The novel coronavirus (COVID-19) outbreak was declared as a global pandemic by the World Health Organization on 11th March 2020. COVID-19 spread has its origin from the wet markets of Wuhan city of China. With corona virus spreading in the world, everything has changed its track and went online, whether it is work or fun. So in this race, how can the fitness industry be left alone in the market? Workout from home started trending on every social media platform and people started performing exercises at home. Often, it happens that when someone starts something new without any proper guidance, then there are high chances of getting backfalls. Hence, so is the case with working out from home. Workout from home can lead to many dangerous injuries if not done under the proper guidance and safety measures. But this is just not one problem of concern. Another point to be noted is that users tend to leave workout at their home due to lack-lustered interaction with the website. We have fulfilled this gap by introducing the technology of Augmented reality in the picture Key Words: Posture detection, Rep counts, Augmented reality, Workout from Home

A Wearable Sensor Network With Embedded Machine Learning for Real-Time Motion Analysis and Complex Posture Detection

This work presents an embedded system driven by a wearable sensor network and machine learning to perform complex posture detection and high-precision <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">human activity recognition</i> (HAR) in real time. The presented prototype performs real-time HAR using raw data collected from three wireless wearable motion sensor nodes in parallel. The sensors communicate the measured inertial data to a Raspberry Pi 3 running a pre-trained classifier, which performs motion detection and classification in real-time. Our approach based on raw data and machine learning provides more efficiency and simplicity by decreasing the computation cost and the latency. Our detection and classification algorithm utilizes a new custom preconditioning method called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-Mapping Spherical Normalization (MMSN)</i> , in combination with a Support Vector Machine with Radial Basis Function Kernel (RBF-SVM). This new preconditioning algorithm allows to sparse the raw inertial data to increase successful classification results without adding any computational burden. The presented approach achieves a motion classification accuracy of 98.28% for 12 body motions, while allowing for real-time prediction with low latency output (< 20 ms which is 50% less than some studies) for preconditioning and processing thanks to the new MMSN preconditioning method and the use of raw data. We tested our approach with 10 able-bodied subjects.

Construction of Swimmer's Underwater Posture Training Model Based on Multimodal Neural Network Model.

Swimming monitoring based on acceleration sensor is an emerging research direction in the field of human motion recognition. As a public sport, swimming has a wide audience. The swimming monitoring system can facilitate people to monitor and record their own swimming data, so as to formulate a reasonable training plan. Aiming at the defects of single modal information representation ability, high contingency, and easy to be influenced by the outside world, this paper adopts the underwater posture training model of swimmers to perform multimodal information fusion. In this paper, a multimodal information fusion method based on evolutionary neural network is proposed, and an intelligent perception information processing model of the intelligent subject system is constructed. Aiming at the defect that the accuracy and speed of the underwater posture monitoring of swimmers cannot be guaranteed in a complex environment, an evolutionary neural network optimized by a multimodal adaptive genetic algorithm is constructed to perform multimodal information fusion to ensure the effectiveness of the system in the face of complex information. Regarding attitude detection, it mainly uses the three dimensions of the angle of movement, the influence of gravity, and the strength and speed of the movement to measure. The MPU6050 module processor has a wide range of applications and is a mold processing tool with high performance and level. It completes the data processing, data calculation, and data storage of the inspection system in this paper. This paper further studies the working principle, structure, and operation process of this module and adjusts the time error in the detection of carrier motion and attitude so that the processing function of this module can play an optimal state. Four kinds of swimming posture measurement experiments were carried out on the swimmers, and the experimental data were analyzed. The whole system is controlled by the host computer man-machine interaction software remotely and in real time through commands. The experimental results show that the system realizes the detection of the basic posture, meets the basic requirements of the system design, and provides a certain foundation for the follow-up research.

An Adaptive Human Posture Detection Algorithm Based on Generative Adversarial Network.

Human posture equipment technology has advanced significantly thanks to advances in deep learning and machine vision. Even the most advanced models may not be able to predict all body joints accurately. This paper proposes an adaptive generative adversarial network to improve the human posture detection algorithm in order to address this issue. GAN is used in the algorithm to detect human posture improvement. The algorithm uses OpenPose to detect and connect keypoints and then generates heat maps in the GAN system model. During the training process, the confidence evaluation mechanism is added to the system model. The generator predicts posture, while the resolver refines human joints over time. And, by using normalization technologies in the confidence evaluation mechanism, the generator can pay more attention to the prominent body joints, improving the algorithm's body detection accuracy of nodes. In MPII, LSP, and FLIC datasets, the proposed algorithm has shown to have a good detection effect. Its positioning accuracy is about 95.37 percent, and it can accurately locate the joints of the entire body. Several other algorithms are outperformed by this one. The algorithm described in this article has the best simultaneous runtime in the LSP dataset.

Target Recognition and Grabbing Positioning Method Based on Convolutional Neural Network

With the continuous reform of intelligent manufacturing, industrial production has gradually developed from automation to intelligence. The fusion of vision technology and industrial machines has become a hot research direction in current intelligent transformation. However, machines are not as flexible as humans when grabbing, and still have great limitations. Affected by various characteristics of target objects, such as shape, material, weight and other factors, as well as complex and changeable environmental factors, the research of machine grabbing still faces severe challenges. For the actual complex working conditions, the poor target detection effect leads to the inability to complete accurate grabbing, which affects the production efficiency. This paper proposes a grabbing system with convolutional neural network, which can achieve target detection, classification, positioning and grabbing tasks. First, by comparing the current mainstream target recognition and detection algorithms, select SSD that have both real-time performance and accuracy. Then make specific network structure improvements according to the detection requirements, and insert the Inception structure. At the same time optimize its loss function and nonmaximum suppression. The improved recognition rate is higher, and the target detection frame is closer to the real part, which greatly reduces the recognition error. Second, this research proposes an algorithm model for regional posture detection and grabbing positioning, which uses the output of the previous stage as input to perform posture detection and grabbing positioning of the grabbed target. In the network, the posture angle of the grabbing target is output in a classified manner, and the position coordinates of the grabbing point are output using a regression method. Experiments have proved that our method can perform efficient target recognition and grabbing positioning.

Development of an educational protocol for ergonomic risk assessment of working postures to enhance the competence of occupational health nurses.

To develop a protocol and provide a valid, evidence-based procedure for identifying the ergonomic risk of working postures by occupational health nurses. Although ergonomic risk assessment tools have been used for the early detection of risky working postures, their operational procedures and validations do not target the competence of occupational nursing personnel. This study developed and validated an educational protocol, comprised of 13 procedures in five stages. First, the number of work tasks in the workplace is determined. Second, the working postures are confirmed. Third, the raters are trained to use the assessment tools. Fourth, high-risk postures are identified and categorized. Fifth, the inter-rater reliability of the tool is reported. The content of the protocol is validated by experts, with a validity value of 0.87. The protocol was created through review of literature published from 1991 to 2021, protocol development (between 2018 to 2020) and expert validation (2020). The protocol can be applied to educate occupational health nurses and increase their competence in detecting workers' ergonomic risks. It can be used as a reference in occupational health nursing education to evaluate work tasks and detect risky postures.