Data Quality and Reliability Assessment of Wearable EMG and IMU Sensor for Construction Activity Recognition

Decoding of unimanual and bimanual reach-and-grasp actions from EMG and IMU signals in persons with cervical spinal cord injury

Objective. Chronic motor impairments of arms and hands as the consequence of a cervical spinal cord injury (SCI) have a tremendous impact on activities of daily life. A considerable number of people however retain minimal voluntary motor control in the paralyzed parts of the upper limbs that are measurable by electromyography (EMG) and inertial measurement units (IMUs). An integration into human-machine interfaces (HMIs) holds promise for reliable grasp intent detection and intuitive assistive device control.Approach. We used a multimodal HMI incorporating EMG and IMU data to decode reach-and-grasp movements of groups of persons with cervical SCI (n = 4) and without (control, n = 13). A post-hoc evaluation of control group data aimed to identify optimal parameters for online, co-adaptive closed-loop HMI sessions with persons with cervical SCI. We compared the performance of real-time, Random Forest-based movement versus rest (2 classes) and grasp type predictors (3 classes) with respect to their co-adaptation and evaluated the underlying feature importance maps.Main results. Our multimodal approach enabled grasp decoding significantly better than EMG or IMU data alone (p<0.05). We found the 0.25 s directly prior to the first touch of an object to hold the most discriminative information. Our HMIs correctly predicted 79.3 ± STD 7.4 (102.7 ± STD 2.3 control group) out of 105 trials with grand average movement vs. rest prediction accuracies above 99.64% (100% sensitivity) and grasp prediction accuracies of 75.39 ± STD 13.77% (97.66 ± STD 5.48% control group). Co-adaption led to higher prediction accuracies with time, and we could identify adaptions in feature importances unique to each participant with cervical SCI.Significance. Our findings foster the development of multimodal and adaptive HMIs to allow persons with cervical SCI the intuitive control of assistive devices to improve personal independence.

Influence of brick laying height on biomechanical load in masons: Cross-sectional field study with technical measurements

BACKGROUND

Work-related musculoskeletal disorders (WMSDs) located in the low back and neck/shoulder regions are major concerns for both workers, workplaces, and society. Masons are prone to WMSD, because their work is characterized by repetitive work and high physical workload. However, the knowledge on the physical workload during bricklaying is primarily based on subjective measurements.

OBJECTIVE

This cross-sectional field study with technical measurements aimed to quantify physical workload in terms of muscular activity and degree of forward bending during bricklaying at different working heights among masons, i.e., knee, hip, shoulder, and above shoulder height.

METHODS

Twelve male (36.1±16.1 years) experienced masons participated in a cross-sectional field study with technical measurements. Surface electromyography from erector spinae longissimus and upper trapezius muscles and an inertial measurement unit-sensor placed on the upper back were used to assess the physical workload (level of muscle activation and degree of forward bending) different bricklaying heights. Manual video analysis was used to determine duration of work tasks, frequency, type, and working height. The working heights were categorized as 'knee', 'hip', 'shoulder', and 'above shoulder'. The 95 percentiles of the normalized Root Mean Square (RMSn) values were extracted assess from erector spinae and trapezius recordings to assess strenuous level muscle of muscle activation.

RESULTS

The RMSn of dominant erector spinae muscle increased from hip- to shoulder height (from 26.6 to 29.6, P <  0.0001), but not from hip to above shoulder height and decreased from hip to knee height (from 26.6 to 18.9, P <  0.0001). For the dominant trapezius muscle, the RMSn increased from hip- to shoulder- and above shoulder height (from 13.9 to 19.7 and 24.0, respectively, P <  0.0001) but decreased from hip- to knee height (from 13.9 to 11.5, P <  0.0001). Compared to hip height (27.9°), an increased forward bending was detected during bricklaying at knee height (34.5°, P <  0.0001) and a decreased degree of forward bending at shoulder- and above shoulder height (17.6° and 12.5°, P <  0.0001, respectively).

CONCLUSION

Based on technical measurements, bricklaying at hip height showed the best compromise between muscular load and degree of forward bending. This study contributes to the development of the work environment for masons and can help guide preventive initiatives to reduce physical workload.

A Light-Weight Artificial Neural Network for Recognition of Activities of Daily Living

Human activity recognition (HAR) is essential for the development of robots to assist humans in daily activities. HAR is required to be accurate, fast and suitable for low-cost wearable devices to ensure portable and safe assistance. Current computational methods can achieve accurate recognition results but tend to be computationally expensive, making them unsuitable for the development of wearable robots in terms of speed and processing power. This paper proposes a light-weight architecture for recognition of activities using five inertial measurement units and four goniometers attached to the lower limb. First, a systematic extraction of time-domain features from wearable sensor data is performed. Second, a small high-speed artificial neural network and line search method for cost function optimization are used for activity recognition. The proposed method is systematically validated using a large dataset composed of wearable sensor data from seven activities (sitting, standing, walking, stair ascent/descent, ramp ascent/descent) associated with eight healthy subjects. The accuracy and speed results are compared against methods commonly used for activity recognition including deep neural networks, convolutional neural networks, long short-term memory and convolutional-long short-term memory hybrid networks. The experiments demonstrate that the light-weight architecture can achieve a high recognition accuracy of 98.60%, 93.10% and 84.77% for seen data from seen subjects, unseen data from seen subjects and unseen data from unseen subjects, respectively, and an inference time of 85 μs. The results show that the proposed approach can perform accurate and fast activity recognition with a reduced computational complexity suitable for the development of portable assistive devices.

Automated and Continuous Fatigue Monitoring in Construction Workers Using Forearm EMG and IMU Wearable Sensors and Recurrent Neural Network

About 40% of the US construction workforce experiences high-level fatigue, which leads to poor judgment, increased risk of injuries, a decrease in productivity, and a lower quality of work. Therefore, it is essential to monitor fatigue to reduce its adverse effects and prevent long-term health problems. However, since fatigue demonstrates itself in several complex processes, there is no single standard measurement method for fatigue detection. This study aims to develop a system for continuous workers' fatigue monitoring by predicting the aerobic fatigue threshold (AFT) using forearm muscle activity and motion data. The proposed system consists of five modules: Data acquisition, activity recognition, oxygen uptake prediction, maximum aerobic capacity (MAC) estimation, and continuous AFT monitoring. The proposed system was evaluated on the participants performing fourteen scaffold-building activities. The results show that the AFT features have achieved a higher accuracy of 92.31% in assessing the workers' fatigue level compared to heart rate (51.28%) and percentage heart rate reserve (50.43%) features. Moreover, the overall performance of the proposed system on unseen data using average two-min AFT features was 76.74%. The study validates the feasibility of using forearm muscle activity and motion data to workers' fatigue levels continuously.

Data quality evaluation in wearable monitoring

Wearable recordings of neurophysiological signals captured from the wrist offer enormous potential for seizure monitoring. Yet, data quality remains one of the most challenging factors that impact data reliability. We suggest a combined data quality assessment tool for the evaluation of multimodal wearable data. We analyzed data from patients with epilepsy from four epilepsy centers. Patients wore wristbands recording accelerometry, electrodermal activity, blood volume pulse, and skin temperature. We calculated data completeness and assessed the time the device was worn (on-body), and modality-specific signal quality scores. We included 37,166 h from 632 patients in the inpatient and 90,776 h from 39 patients in the outpatient setting. All modalities were affected by artifacts. Data loss was higher when using data streaming (up to 49% among inpatient cohorts, averaged across respective recordings) as compared to onboard device recording and storage (up to 9%). On-body scores, estimating the percentage of time a device was worn on the body, were consistently high across cohorts (more than 80%). Signal quality of some modalities, based on established indices, was higher at night than during the day. A uniformly reported data quality and multimodal signal quality index is feasible, makes study results more comparable, and contributes to the development of devices and evaluation routines necessary for seizure monitoring.

Toward Soft Wearable Strain Sensors for Muscle Activity Monitoring

The force-generating capacity of skeletal muscle is an important metric in the evaluation and diagnosis of musculoskeletal health. Measuring changes in muscle force exertion is essential for tracking the progress of athletes during training, for evaluating patients’ recovery after muscle injury, and also for assisting the diagnosis of conditions such as muscular dystrophy, multiple sclerosis, or Parkinson’s disease. Traditional hardware for strength evaluation requires technical training for operation, generates discrete time points for muscle assessment, and is implemented in controlled settings. The ability to continuously monitor muscle force without restricting the range of motion or adapting the exercise protocol to suit specific hardware would allow for a richer dataset that can help unlock critical features of muscle health and strength evaluation. In this paper, we employ wearable, ultra-sensitive soft strain sensors for tracking changes in muscle deformation during contractions. We demonstrate the sensors’ sensitivity to isometric contractions, as well as the sensors’ capacity to track changes in peak torque over the course of an isokinetic fatiguing protocol for the knee extensors. The wearable soft system was able to efficiently estimate peak joint torque reduction caused by muscle fatigue (mean NRMSE = 0.15±0.03).

Exploring human activity recognition using feature level fusion of inertial and electromyography data

Wearables are objective tools for human activity recognition (HAR). Advances in wearables enable synchronized multi-sensing within a single device. This has resulted in studies investigating the use of single or multiple wearable sensor modalities for HAR. Some studies use inertial data, others use surface electromyography (sEMG) from multiple muscles and different post-processing approaches. Yet, questions remain about accuracies relating to e.g., multi-modal approaches, and sEMG post-processing. Here, we explored how inertial and sEMG could be efficiently combined with machine learning and used with post-processing methods for better HAR. This study aims recognition of four basic daily life activities; walking, standing, stair ascent and descent. Firstly, we created a new feature vector based on the domain knowledge gained from previous mobility studies. Then, a feature level data fusion approach was used to combine inertial and sEMG data. Finally, two supervised learning classifiers (Support Vector Machine, SVM, and the k-Nearest Neighbors, kNN) were tested with 5-fold cross-validation. Results show the use of inertial data with sEMG increased overall accuracy by 3.5% (SVM) and 6.3% (kNN). Extracting features from linear envelopes instead of bandpass filtered sEMG improves overall HAR accuracy in both classifiers. Clinical Relevance- Post-processing on sEMG signals can improve the performance of multimodal HAR.

Review of the Application of Wearable Devices in Construction Safety: A Bibliometric Analysis from 2005 to 2021

Wearable devices as an emerging technology to collect safety data on construction site is gaining increasing attention from researchers and practitioners. Given the rapid development of wearable devices research and the high application prospects of wearable devices in construction safety, a state-of-the-art review of research and implementations in this field is needed. The aim of this study is to provide an objective and extensive bibliometric analysis of the published articles on wearable applications in construction safety for the period of 2005–2021. CiteSpace software was used to conduct co-citation analysis, co-occurrence analysis, and cluster identification on 169 identified articles. The results show that 10 research clusters (e.g., attentional failure, brain-computer interface) were extremely important in the development of wearable devices for construction safety. The results highlight the evolution of wearable devices in construction-safety-related research, revealing the underlying structure of this cross-cutting research area. The analysis also summarizes the status quo of wearable devices in the construction safety field and provides a dynamic platform for integrating future applications.

Automated Workers’ Ergonomic Risk Assessment in Manual Material Handling Using sEMG Wearable Sensors and Machine Learning

Manual material handling tasks have the potential to be highly unsafe from an ergonomic viewpoint. Safety inspections to monitor body postures can help mitigate ergonomic risks of material handling. However, the real effect of awkward muscle movements, strains, and excessive forces that may result in an injury may not be identified by external cues. This paper evaluates the ability of surface electromyogram (EMG)-based systems together with machine learning algorithms to automatically detect body movements that may harm muscles in material handling. The analysis utilized a lifting equation developed by the U.S. National Institute for Occupational Safety and Health (NIOSH). This equation determines a Recommended Weight Limit, which suggests the maximum acceptable weight that a healthy worker can lift and carry, as well as a Lifting Index value to assess the risk extent. Four different machine learning models, namely Decision Tree, Support Vector Machine, K-Nearest Neighbor, and Random Forest are developed to classify the risk assessments calculated based on the NIOSH lifting equation. The sensitivity of the models to various parameters is also evaluated to find the best performance using each algorithm. Results indicate that Decision Tree models have the potential to predict the risk level with close to 99.35% accuracy.

Creating a Scoring System with an Armband Wearable Device for Table Tennis Forehand Loop Training: Combined Use of the Principal Component Analysis and Artificial Neural Network

BACKGROUND

This study presents an intelligent table tennis e-training system based on a neural network (NN) model that recognizes data from sensors built into an armband device, with the component values (performances scores) estimated through principal component analysis (PCA).

METHODS

Six expert male table tennis players on the National Youth Team (mean age 17.8 ± 1.2 years) and seven novice male players (mean age 20.5 ± 1.5 years) with less than 1 year of experience were recruited into the study. Three-axis peak forearm angular velocity, acceleration, and eight-channel integrated electromyographic data were used to classify both player level and stroke phase. Data were preprocessed through PCA extraction from forehand loop signals. The model was trained using 160 datasets from five experts and five novices and validated using 48 new datasets from one expert and two novices.

RESULTS

The overall model's recognition accuracy was 89.84%, and its prediction accuracies for testing and new data were 93.75% and 85.42%, respectively. Principal components corresponding to the skills "explosive force of the forearm" and "wrist muscle control" were extracted, and their factor scores were standardized (0-100) to score the skills of the players. Assessment results indicated that expert scores generally fell between 60 and 100, whereas novice scores were less than 70.

CONCLUSION

The developed system can provide useful information to quantify expert-novice differences in fore-hand loop skills.

Automatic Scaffolding Workface Assessment for Activity Analysis through Machine Learning

Scaffolding serves as one construction trade with high importance. However, scaffolding suffers from low productivity and high cost in Australia. Activity Analysis is a continuous procedure of assessing and improving the amount of time that craft workers spend on one single construction trade, which is a functional method for monitoring onsite operation and analyzing conditions causing delays or productivity decline. Workface assessment is an initial step for activity analysis to manually record the time that workers spend on each activity category. This paper proposes a method of automatic scaffolding workface assessment using a 2D video camera to capture scaffolding activities and the model of key joints and skeleton extraction, as well as machine learning classifiers, were used for activity classification. Additionally, a case study was conducted and showed that the proposed method is a feasible and practical way for automatic scaffolding workface assessment.