Search Results (58)

Unsafe events such as slips and trips occur regularly on construction sites. Efficient identification of these events can help protect workers from accidents and improve site safety. However, current detection methods rely on subjective reporting, which has several limitations. To address these limitations, this study presents a sound-based slip and trip classification method using wearable sound sensors and machine learning. Audio signals were recorded using a smartwatch during simulated slip and trip events. Various 1D and 2D features were extracted from the processed audio signals and used to train several classifiers. Three key findings are as follows: (1) The hybrid CNN-LSTM network achieved the highest classification accuracy of 0.966 with 2D MFCC features, while GMM-HMM achieved the highest accuracy of 0.918 with 1D sound features. (2) 1D MFCC features achieved an accuracy of 0.867, outperforming time- and frequency-domain 1D features. (3) MFCC images were the best 2D features for slip and trip classification. This study presents an objective method for detecting slip and trip events, thereby providing a complementary approach to manual assessments. Practically, the findings serve as a foundation for developing automated near-miss detection systems, identification of workers constantly vulnerable to unsafe events, and detection of unsafe and hazardous areas on construction sites. Full article

Background: Current methods of postural control assessments and interventions to improve postural stability and thereby prevent falls often fail to incorporate the hazardous perturbation situations that frequently accompany falls. Virtual environments can safely incorporate these hazards. The purpose of the study was to identify if virtual slip and trip perturbations can be used as an exposure paradigm in place of real slip and trip perturbations to improve postural control. Methods: Fifteen healthy young adults were included in this study. Two paradigms, real gait exposure (real) and virtual environment gait exposure (virtual), consisting of real and virtual slip and trip trials, were performed by each participant in a counterbalanced order to avoid order effects. At baseline and following real and virtual paradigms, the modified clinical test for sensory integration and balance (mCTSIB), limits of stability (LOS), and single-leg stance (SLS) using BTracks balance plate were administered. Separate one-way (baseline vs. Real vs. Virtual) repeated measures analysis of variance were conducted on response variables. Results: In the posterior left quadrant of the LOS, significant differences were found after the real paradigm compared to baseline (p = 0.04). For the anterior left quadrant and total LOS, significant differences post real paradigm (p = 0.002 and p < 0.001) and virtual paradigm (p = 0.007 and p < 0.001) compared to baseline were observed. For the SLS, the left-leg significant differences were observed post real paradigm (p = 0.019) and virtual paradigm (p = 0.009) compared to BL in path length, while significant main effects were found for mean sway velocity for the left leg only (p = 0.004). For the right leg, significant differences were only observed after the virtual paradigm (p = 0.01) compared to BL. Conclusions: Both virtual and real paradigms were identified to improve postural control. The virtual paradigm led to increased postural control in the right-leg SLS condition, while the real paradigm did not, without any adverse effects. Findings suggest virtual reality perturbation exposure acutely improves postural control ability compared to baseline among healthy young adults. Full article

Older adults make up about 12% of the public sector, primary care, and hospital use and represent a large proportion of the users of healthcare services. Older people are also more vulnerable to serious injury from unexpected falls due to tripping, slipping, or illness. This underscores the immediate necessity of stable and cost-effective e-health technologies in maintaining independent living. Artificial intelligence (AI) and machine learning (ML) offer promising solutions for early fall prediction and continuous health monitoring. This paper introduces a novel cooperative AI model that forecasts the risk of future falls in the elderly based on behavioral and health abnormalities. Two AI models’ predictions are combined to produce accurate predictions: The ${AI}_1$ model is based on vital signs using Fuzzy Logic, and the ${AI}_2$ model is based on Activities of Daily Living (ADLs) using a Deep Belief Network (DBN). A meta-model then combines the outputs to generate a total fall risk prediction. The results show 85.71% sensitivity, 100% specificity, and 90.00% prediction accuracy when compared to the Morse Falls Scale (MFS). This emphasizes how deep learning-based cooperative systems can improve well-being for older adults living alone, facilitate more precise fall risk assessment, and improve preventive care. Full article

Forestry is recognized as one of the most physically demanding professions. Walking in presents unique biomechanical challenges due to complex, irregular terrain, with several possible risks. This study investigated how human gait adapts across solid surfaces, forest trails, and natural forest environments. Fifteen healthy adult participants (average age 38.3; ten males and five females) completed 150 walking trials, with full-body motion captured via a 17 Inertial Measurement Unit (IMU) sensors (Xsens MVN Awinda system). The analysis focused on spatial and temporal gait parameters, including cadence, step length, foot strike pattern, and center of mass variability. Statistical methods (ANOVA and Kruskal–Wallis) revealed that surface type significantly influenced gait mechanics. On forest terrain, participants exhibited wider steps, reduced cadence, increased step and stride variability, and a substantial shift from heel-to-toe strikes. Gait adaptations reflect compensatory neuromuscular strategies to maintain body balance. The findings confirm that forestry terrain complexity compromises human gait stability and increases physical demands, supporting step variability and slip, trip, and fall risk. By identifying key biomechanical markers of instability, this study contributes to understanding human locomotion principles. Understanding these changes can help design safety measures for outdoor professions, particularly forestry. Full article

In this experiment, a novel designed Mn-N-bearing, nearly Ni-free, TRIP-aided economical 19Cr (Fe-18.9Cr-10.1Mn-0.3Ni-0.26N-0.03C) duplex stainless steel (DSS) was prepared, and it exhibited a good combination of strength and toughness after suitable solution treatment, showing good application potential. The deformation mechanisms of ferrite and austenite are different during tensile deformation at room temperature: the ferrite phase was deformed by a dislocation slip mechanism and formed a cell structure due to its higher stacking fault energy; the lower stacking fault energy of austenite resulted in a strain-induced martensite phase transformation mechanism. With an increase in aging time from 1 h to 7 h at 750 °C in air, the σ phase precipitates in the ferrite triple grain boundary junction, which leads to an increase in ultimate tensile strength, acts as an obstacle to the dislocation motion and decreases the ductility, deteriorating the pitting corrosion resistance in 3.5 wt.% NaCl solution at the same time. The σ phase precipitation behavior does not alter the deformation mechanism of the phases of the solution-treated TRIP-aided economical DSS. Full article

Background/Objectives: Traditional fusion leads to a loss of spine mobility across the fused vertebrae. Vertebral body tethering (VBT) was developed with the goal of increasing flexibility and maintaining some spinal mobility. However, it is not known if the additional mobility leads to significant functional improvement. This prospective motion analysis study evaluates functional outcomes, specifically gait stability, in pre-operative, post-fusion, and post-VBT patients by using postural perturbations on a treadmill. Methods: Overall, 79 subjects underwent a computer-controlled treadmill study with postural perturbations, which simulated trips and slips. The subjects were harnessed for safety. Overall, 21 subjects were healthy controls, 18 patients were at least one-year post-VBT, 15 patients were at least one-year post-fusion, and 25 were pre-operative scoliosis patients. Subject weight, height, and treadmill acceleration were recorded and used to determine anteroposterior single (ASSTs, PSSTs) and multiple (AMSTs, PMSTs) stepping thresholds to describe the maximum torque a patient could withstand before failing to recover from the simulated trip. Independent t-tests were run to compare groups under the advice of a master statistician with expertise in orthopedic surgery. Results: Pre-operative scoliosis patients had lower PSSTs than healthy controls (uncorrected p = 0.036). No significant differences were observed between pre-operative and post-operative groups for both fusion and VBT. There was no significant difference in ASST, AMST, or PMST between any of the groups. Conclusions: The lower PSST in pre-operative scoliosis patients compared to healthy controls may reflect impaired reactive balance and potentially increased fall risk. Interestingly, there was no significant difference in reactive balance measures between pre-operative and post-operative scoliosis patients or between post-fusion and post-VBT patients. Full article

Slips, trips, and falls (STFs) are a major occupational hazard that contributes significantly to workplace injuries and the associated financial costs. The application of traditional fall detection techniques in the real world is limited because they are usually based on simulated falls. By using kinematic data from real near-fall incidents that occurred in physically demanding work environments, this study overcomes this limitation and improves the ecological validity of fall detection algorithms. This study systematically tests several machine-learning architectures for near-fall detection using the Prev-Fall dataset, which consists of high-resolution inertial measurement unit (IMU) data from 110 workers. Convolutional neural networks (CNNs), residual networks (ResNets), convolutional long short-term memory networks (convLSTMs), and InceptionTime models were trained and evaluated over a range of temporal window lengths using a neural architecture search. High-validation F1 scores were achieved by the best-performing models, particularly CNNs and InceptionTime, indicating their effectiveness in near-fall classification. The need for more contextual variables to increase robustness was highlighted by recurrent false positives found in subsequent tests on previously unobserved occupational data, especially during biomechanically demanding activities such as bending and squatting. Nevertheless, our findings suggest the applicability of machine-learning-based STF prevention systems for workplace safety monitoring and, more generally, applications in fall mitigation. To further improve the accuracy and generalizability of the system, future research should investigate multimodal data integration and improved classification techniques. Full article

This study assessed the effect of filter parameters on gait characteristics and the performance of machine-learning models. Overground walking trials (n = 99) with and without perturbations (slips, trips) were collected for 33 healthy older adults. Kinematics were collected by a motion capture system. Different Butterworth low-pass parameters were applied to the raw data, including three orders (2–6) and nine cutoffs (4–20 Hz). Spatiotemporal gait outcomes were then calculated to develop classification models to automatically identify the trial type (gait, gait–slip, or gait–trip) using Logistic Regression, Support Vector Classification, and Random Forest Classification. A 3 × 9 ANOVA showed main effects of order and cutoff (p < 0.01 for all) on gait characteristics during both perturbed and regular walking trials. However, the gait characteristics were different between them. The filter parameters significantly affected the performance of classification models using different classifiers, with significant main effects of the filter order (p < 0.05) and cutoff (p < 0.01) on AUC and overall accuracy for all of the models. Our results suggest that the standard Butterworth filter (fourth-order, cutoff: 6 Hz) is suitable for the development of classification models with low–medium complexity, while for models with high complexity (i.e., ensemble models), a filter with a higher order and cutoff (sixth-order, cutoff 10–12 Hz) might yield better performance. Full article

The deep shale gas resources of the Sichuan Basin are abundant and constitute an important component of China’s natural gas production. Complicated by fault zones and other geostructures, the in situ stress state of the deep shale gas reservoirs in the Luzhou block remains poorly understood. This study integrated multiple datasets, including acoustic logging, diagnostic fracture injection testing (DFIT), imaging logging, and laboratory stress measurements, for calibration and constraint. A high-precision geomechanical model of the Luzhou block was constructed using the finite element method. This model characterizes the geomechanical properties of the reservoir and explores its applications in optimizing shale gas horizontal well placement, drilling processes, and fracture design. The study findings indicate that the Longmaxi Formation reservoir demonstrates abnormally high pore pressure, with gradients ranging from 16.7 to 21.7 kPa/m. The predominant stress regime is strike-slip, with an overburden stress gradient of 25.5 kPa/m and a minimum horizontal principal stress gradient ranging from 18.8 to 24.5 kPa/m. Based on a three-dimensional geomechanical model, a quantitative delineation of areas conducive to density reduction and pressure control drilling was conducted, and field experiments were implemented in well Y65-X. Utilizing an optimized drilling fluid density of 1.85 g/cm³, the deviated horizontal section was completed in a single trip, resulting in a 67% reduction in the drilling cycle compared to adjacent wells. Similarly, the Y2-X well demonstrated a test daily output of 506,900 cubic meters following an optimization of segmentation clustering and fracturing parameters. Studies indicate that 3D geomechanical modeling, informed by multi-source data constraints, can markedly enhance model precision, and such geomechanical models and their results can effectively augment drilling operational efficiency, elevate single-well production, and are advantageous for development. Full article

Background: Advances in prosthetic technology, especially microprocessor-controlled knees (MPKs), have helped enhance gait symmetry and reduce fall risks for individuals who have undergone transfemoral amputation. However, challenges remain in walking in constrained situations due to the limitations of passive prosthetic feet, lacking ankle mobility. This study investigates the benefits of SYNSYS^®, a new microprocessor-controlled knee–ankle–foot system (MPKA_NEW), designed to synergize knee and ankle movements. Methods: A randomized crossover trial was conducted on 12 male participants who had undergone transfemoral amputation who tested both the MPKA_NEW and their usual MPK prosthesis. Biomechanical parameters were evaluated using quantitative gait analysis in various walking conditions. Participants also completed self-reported questionnaires on their quality of life, locomotor abilities, and prosthesis satisfaction. Results: The MPKA_NEW showed a significant reduction in the risk of slipping and tripping compared to standard MPK prostheses, as evidenced by increased flat-foot time and minimum toe clearance during gait analysis. The MPKA_NEW also improved physical component scores in quality-of-life assessments (Short-Form 36 General Health Questionnaire), suggesting enhanced stability and reduced cognitive load during walking. Conclusions: The MPKA_NEW offers significant improvements in gait safety and quality of life for people who have undergone TFA, particularly in challenging conditions. Further studies are needed to assess the long-term benefits and adaptability across diverse amputee populations. Full article

Background/Objectives: Custody officers (CO) are often exposed to workplace hazards when monitoring prisoners, managing prisoners’ recreational time, or searching for contraband, yet research into their injuries is limited. This review aimed to identify, appraise, and synthesise research investigating injuries in CO. Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol and registration with the Open Science Framework, a systematic search of five databases (PubMed, ProQuest, Embase, CINAHL and SportDiscus) using key search terms was conducted. The identified studies were considered against eligibility criteria, with the remaining studies critically appraised using the appropriate Joanna Briggs Institute checklist. Results: From the 975 identified studies, eight studies (mean critical appraisal score = 69 ± 25%) remained to inform the review. The incidence of fatal injuries ranged from 0.027 to 0.03 per 1000 full-time employees (FTE), whereas that of non-fatal injuries ranged from 15.9 to 44.0 per 1000 FTE. CO aged 31+ years were the most likely to experience injuries (22–44%). Male CO were more commonly injured than female CO in both fatal injuries (male = 89%, female = 11%) and non-fatal injuries (male = 73–74%, female = 26–27%). Assaults (11.5–38%) and slips/trips/falls (23.2–25%) were found to be the most common causes of injuries. The upper extremity was the most commonly injured body part (26–30%), with musculoskeletal sprains and strains (30–60.2%) the most common types of injury. Conclusions: CO injury profiles are similar to those reported in general-duty police officers. As such, musculoskeletal conditioning, reconditioning, and fall prevention practices employed in law enforcement may serve as an initial approach to risk mitigation in this population. Full article

Background: Humans encounter disturbances like slips, pushes, and trips while walking, mainly from external forces. Technological advances have improved methods to study these impacts on gait, with split-belt treadmills being particularly effective. This scoping review aims to examine the types of perturbations used during split-belt treadmill gait, explore the methods used to induce them, and consolidate current knowledge on the effects of split-belt treadmill-induced gait perturbations. Methods: The review included publications from January 2015 to May 2024, as searched via PubMed, EBSCO, and ScienceDirect. Results: The review examined 33 studies on split-belt treadmills, focusing on perturbations like slip-like, trip-like, lateral displacements, and tilts, with speed changes being the most common. Perturbations were mainly applied during initial contact. The results show that young, healthy adults adapt quickly to anticipatory and reactive adjustments, while older adults and those with neurological impairments use less efficient strategies like increased muscular co-contraction. Asymmetrical gait adaptations persist after perturbations, highlighting motor learning and the role of the central nervous system and sensory feedback. Conclusions: Despite their precision, split-belt and tilting treadmills may not fully replicate real-world walking complexities. The review highlights the strengths and limitations of split-belt treadmills, emphasizing the need to integrate diverse methods to enhance rehabilitation and improve gait stability. Full article

Falls are the most common type of accident in the construction industry, and falls to a lower level are among the leading causes of fatalities. Work-related fatalities due to falls, slips, and trips have been increasing, with Hispanic workers among the highest fatalities. This study investigated the association between fall accidents and attributes such as age, musculoskeletal pain (MSPs), sleep hours, safety knowledge, use of personal protective equipment (PPE), and working hours among Hispanic construction workers involved in building construction. This study collected 220 valid responses and used nonparametric chi-square tests and binary logistic regression to analyze the data. This study found that the location of the fall, MSPs, and use of personal protective equipment have a significant effect on the likelihood of having fall accidents. The strongest predictor of fall accidents was “fall from a ladder”, followed by having two or three MSPs. The use of PPE had the highest decreasing ratio in odds of fall accidents, indicating the importance of wearing PPE properly. The results show the importance of integrating safety management strategies within construction projects’ broader life cycle management. The insights list how project engineers can incorporate these findings into Building Information Modeling (BIM) systems to enhance project planning and safety measures in reducing fall-related accidents and their severe consequences. This study highlights the importance of addressing MSPs, properly using PPE, and reducing falls from ladders in the construction industry to prevent fall accidents among Hispanic workers and minimize their severe consequences. Full article

Slip, trip, and fall (STF) accidents cause high rates of absence from work in many companies. During the 2022 reporting period, the German Social Accident Insurance recorded 165,420 STF accidents, of which 12 were fatal and 2485 led to disability pensions. Particularly in the traffic, transport and logistics sector, STF accidents are the most frequently reported occupational accidents. Therefore, an accurate detection of near-falls is critical to improve worker safety. Efficient detection algorithms are essential for this, but their performance heavily depends on large, well-curated datasets. However, there are drawbacks to current datasets, including small sample sizes, an emphasis on older demographics, and a reliance on simulated rather than real data. In this paper we report the collection of a standardised kinematic STF dataset from real-world STF events affecting parcel delivery workers and steelworkers. We further discuss the use of the data to evaluate dynamic stability control during locomotion for machine learning and build a standardised database. We present the data collection, discuss the classification of the data, present the totality of the data statistically, and compare it with existing databases. A significant research gap is the limited number of participants and focus on older populations in previous studies, as well as the reliance on simulated rather than real-world data. Our study addresses these gaps by providing a larger dataset of real-world STF events from a working population with physically demanding jobs. The population studied included 110 participants, consisting of 55 parcel delivery drivers and 55 steelworkers, both male and female, aged between 19 and 63 years. This diverse participant base allows for a more comprehensive understanding of STF incidents in different working environments. Full article

Motorcycles are efficient and flexible tools for short-trip transportation, but they feature static instability and lean while cornering. This characteristic increases the danger of overturning. This study proposes a system to brake a motorcycle safely in a turn. The optimal slip ratio decision model is used to generate the optimal value according to roll angle and vertical force. Given that the roll angle cannot be measured directly, a Kalman filter is used to estimate the roll angle via kinematic parameters, measured by inertial measurement unit. The PID controller adjusts the current slip ratio to follow the optimal slip ratio. Using the motorcycle dynamics model from BikeSim, a co-simulation platform is constructed in MATLAB/Simulink to verify the reliability of the designed brake system. The results show that, compared with a traditional brake controller, the proposed brake system can control the motorcycle braking process by autoregulating the optimal slip ratio in time, according to the kinematic parameters. Both brake performance and stability are well considered, which contributes to improving the safety of the motorcycle. This research work has certain reference value for the development of motorcycle active safety systems. Full article