Scholarly Works, Industrial and Systems Engineering
Permanent URI for this collection
Research articles, presentations, and other scholarship
Browse
Recent Submissions
- Mapping the complex causal mechanisms of drinking and driving behaviors among adolescents and young adultsHosseinichimeh, Niyousha; MacDonald, Rod; Li, Kaigang; Fell, James C.; Haynie, Denise L.; Simons-Morton, Bruce; Banz, Barbara C.; Camenga, Deepa R.; Iannotti, Ronald J.; Curry, Leslie A.; Dziura, James; Mayes, Linda C.; Andersen, David F.; Vaca, Federico E. (Pergamon-Elsevier, 2022-03)Background: The proportion of motor vehicle crash fatalities involving alcohol-impaired drivers declined substantially between 1982 and 1997, but progress stopped after 1997. The systemic complexity of alcohol-impaired driving contributes to the persistence of this problem. This study aims to identify and map key feedback mechanisms that affect alcohol-impaired driving among adolescents and young adults in the U.S. Methods: We apply the system dynamics approach to the problem of alcohol-impaired driving and bring a feedback perspective for understanding drivers and inhibitors of the problem. The causal loop diagram (i.e., map of dynamic hypotheses about the structure of the system producing observed behaviors over time) developed in this study is based on the output of two group model building sessions conducted with multidisciplinary subject-matter experts bolstered with extensive literature review. Results: The causal loop diagram depicts diverse influences on youth impaired driving including parents, peers, policies, law enforcement, and the alcohol industry. Embedded in these feedback loops are the physical flow of youth between the categories of abstainers, drinkers who do not drive after drinking, and drinkers who drive after drinking. We identify key inertial factors, discuss how delay and feedback processes affect observed behaviors over time, and suggest strategies to reduce youth impaired driving. Conclusion: This review presents the first causal loop diagram of alcohol-impaired driving among adolescents and it is a vital first step toward quantitative simulation modeling of the problem. Through continued research, this model could provide a powerful tool for understanding the systemic complexity of impaired driving among adolescents, and identifying effective prevention practices and policies to reduce youth impaired driving.
- Trajectories and outcomes of adolescents that ride with an impaired driver/drive while impairedVaca, Federico E.; Li, Kaigang; Haynie, Denise L.; Gao, Xiang; Camenga, Deepa R.; Dziura, James; Banz, Barbara C.; Curry, Leslie A.; Mayes, Linda; Hosseinichimeh, Niyousha; MacDonald, Rod; Iannotti, Ronald J.; Simons-Morton, Bruce (Elsevier, 2022-03)Introduction: For young drivers, independent transportation has been noted to offer them opportunities that can be beneficial as they enter early adulthood. However, those that choose to engage in riding with an impaired driver (RWI) and drive while impaired (DWI) over time can face negative consequences reducing such opportunities. This study examined the prospective association of identified longitudinal trajectory classes among adolescents that RWI and DWI with their later health, education, and employment in emerging adulthood. Methods: We analyzed all seven annual assessments (Waves, W1–W7) of the NEXT Generation Health Study, a nationally representative longitudinal study starting with 10th grade (2009–2010 school year). Using all seven waves, trajectory classes were identified by latent class analysis with RWI (last 12 months) and DWI (last 30 days) dichotomized as ≥ once = 1 vs. none = 0. Results: Four RWI trajectories and four DWI trajectories were identified: abstainer, escalator, decliner, and persister. For RWI and DWI trajectories respectively, 45.0% (N = 647) and 76.2% (N = 1657) were abstainers, 15.6% (N = 226) and 14.2% (N = 337) were escalators, 25.0% (N = 352) and 5.4% (N = 99) were decliners, and 14.4% (N = 197) and 3.8% (N = 83) persisters. RWI trajectories were associated with W7 health status (χ2 = 13.20, p <.01) and education attainment (χ2 = 18.37, p <.01). Adolescent RWI abstainers reported better later health status than RWI escalators, decliners, and persisters; and decliners reported less favorable later education attainment than abstainers, escalators, and persisters. DWI trajectories showed no association with health status, education attainment, or employment. Conclusions: Our findings suggest the importance of later health outcomes of adolescent RWI. The mixed findings point to the need for more detailed understanding of contextual and time-dependent trajectory outcomes among adolescents engaging in RWI and DWI.
- What determines the success of states in reducing alcohol related crash fatalities? A longitudinal analysis of alcohol related crashes in the US from 1985 to 2019Hosseinichimeh, Niyousha; Williams, Ross; MacDonald, Rod; Li, Kaigang; Vaca, Federico E. (Pergamon-Elsevier, 2022-09)In the United States, nearly 28 people die in alcohol–related motor vehicle crashes every day (1 fatality every 52 min). Over decades, states have enacted multiple laws to reduce such fatalities. From 1982 to 2019, the proportion of drivers in fatal crashes with a blood alcohol concentration (BAC) above 0.01 g/dl declined from 41% to 22%. States vary in terms of their success in reducing alcohol–related crash fatalities. The purpose of this study was to examine factors associated with changes in fatalities related to alcohol–impaired driving at the state level. We created a panel dataset of 50 states from 1985 to 2019 by merging different data sources and used fixed–effect linear regression models to analyze the data. Our two outcome variables were the ratio of drivers in fatal crashes with BAC ≥ 0.01 g/dl to those with BAC = 0.00, and the ratio of those with BAC ≥ 0.08 g/dl to those with BAC < 0.08 g/dl. Our independent variables included four laws (0.08 g/dl BAC per se law, administrative license revocation law, minimum legal drinking age law, and zero tolerance law), number of arrests due to impaired driving, alcohol consumption per capita, unemployment rate, and vehicle miles traveled. We found that the 0.08 g/dl per se law was significantly associated with lower alcohol–related crash fatalities while alcohol consumption per capita was significantly and positively associated with crash–related fatalities. Arrests due to driving under the influence (DUI) and crash fatalities were nonlinearly correlated. In addition, interaction of DUI arrests and two laws (0.08 g/dl BAC per se law, and zero tolerance) were significantly associated with lower crash–related fatalities. Our findings suggest that states which have more restrictive laws and enforce them are more likely to significantly reduce alcohol–related crash fatalities.
- From text to map: a system dynamics bot for constructing causal loop diagramsHosseinichimeh, Niyousha; Majumdar, Aritra; Williams, Ross; Ghaffarzadegan, Navid (Wiley, 2024-07)We introduce and test the System Dynamics Bot, a computer program leveraging a large language model to automate the creation of causal loop diagrams from textual data. To evaluate its performance, we ensembled two distinct databases. The first dataset includes 20 causal loop diagrams and associated texts sourced from the system dynamics literature. The second dataset comprises responses from 30 participants to a vignette, along with causal loop diagrams coded by three system dynamics modelers. The bot uses textual data and successfully identifies approximately 60% of the links between variables and feedback loops in both datasets. This article outlines our approach, provides examples, and presents evaluation results. We discuss encountered challenges and implemented solutions in developing the System Dynamics Bot. The bot can facilitate extracting mental models from textual data and improve model-building processes. Moreover, the two datasets can serve as a test-bed for similar programs.
- Best-Response Dynamics for Large-Scale Integer Programming Games with Applications to Aquatic Invasive Species PreventionLee, Hyunwoo; Hildebrand, Robert; Cai, Wenbo; Büyüktahtakın, İ. Esra (2025-06)This paper presents a scalable algorithm for computing the best pure Nash equilibrium (PNE) in large-scale integer programming games (IPGs). While recent advances in IPG algorithms are extensive, existing methods are limited to a small number of players, typically 𝑛 = 2, 3. Motivated by a county-level aquatic invasive species (AIS) prevention problem involving 84 players, we develop efficient and scalable algorithms that significantly extend the applicability of IPGs. Specifically, we propose the best-response dynamics incorporated zero-regret (BZR) algorithm, which leverages best-response dynamics (BRD) for rapid PNE identification and integrates BRD as a primal heuristic within the zero-regret (ZR) framework. This approach dramatically improves the scalability of IPG algorithms, allowing us to solve IPGs with up to 30 players in random datasets and the 84-player AIS prevention problem with Minnesota data. To model the AIS prevention problem, we introduce the edge-weighted budgeted maximum coverage (EBMC) game, a newclass of IPG that has not been previously studied. We establish theoretical conditions for the existence of a PNE under both selfish and locally altruistic utility functions. Experimental results in EBMC games and knapsack problem games demonstrate that BZR significantly enhances ZR in both finding a PNE and identifying the best PNE, particularly in games with many players.
- Using musculoskeletal models to estimate the effects of exoskeletons on spine loads during dynamic lifting tasks: differences between OpenSim and the AnyBody modelling systemBehjati Ashtiani, Mohamad; Akhavanfar, Mohammadhossein; Li, Lingyu; Kim, Sunwook; Nussbaum, Maury A. (Elsevier, 2025-05-23)Occupational back-support exoskeletons (BSEs) can reduce physical demands during lifting by providing assistive torques, but their effects on spine loading are poorly understood. In this study, we used two common musculoskeletal models developed in OpenSim and the AnyBody Modeling System to estimate intervertebral joint forces (IJF) during asymmetric and symmetric lifting tasks with and without BSEs. Data from an earlier study were used, involving 18 participants who performed repetitive lowering/lifting in three task conditions and with three different BSEs (along with a control condition using no BSE). We simulated the tasks with both models and estimated axial compression and anteroposterior shear forces at the L4/L5 joint and derived peak values (95th percentile) as outcome measures. OpenSim estimated significantly larger axial compression and anteroposterior shear forces than AMS. Both models estimated reductions in spine loading when using either of the BSEs, though OpenSim estimated greater reductions than AMS. Strong positive, linear relationships (r > 0.95) between the two model estimates were found for axial compression, while much weaker and even negative relationships were observed for shear forces, especially under asymmetric conditions. The differences in model estimates were likely due to variations in model assumptions and passive tissue representations. Future research should explore more detailed human-exoskeleton interaction models, evaluate the impact of modelling assumptions on IJF estimates, and assess the agreement of these findings with in vivo measurements such as electromyography.
- Effectiveness and usability of a trunk posture feedback system: An exploratory, longitudinal study for up to 10 days among vehicle assembly operatorsChoi, Jiwon; Kim, Sunwook; Lim, Sol; Porto, Ryan; Nussbaum, Maury A. (Elsevier, 2025-10)Postural feedback systems are a potential ergonomic intervention to reduce postural exposures, and thus musculoskeletal disorder risk, but field-based evidence of their longer-term effectiveness remains limited. We conducted an exploratory investigation of a commercial postural feedback system, which provided auditory and vibrotactile feedback following excessive trunk motion, in vehicle manufacturing. Eight workers used the system during regular shifts for up to 10 workdays. We observed a reduction in “poor” postures on the first day of feedback. However, these benefits diminished over time, possibly due to a novelty effect—with improvements diminishing as participants adapted to the system—and effects varied greatly across participants. Participant responses were mixed; some reported improved postural awareness while others found the feedback irritating and often ignored it. Findings from this exploratory study suggest the importance of enhancing postural feedback system design to sustain behavioral change over time and better support individual needs.
- Two Novel Slip Training Methods Improve the Likelihood of Recovering Balance After a Laboratory-Induced SlipAllin, Leigh J.; Nussbaum, Maury A.; Madigan, Michael L. (Human Kinetics, 2018-08-06)Task-specific balance training is an approach to fall prevention that has the potential to reduce the number of slip-induced falls. However, a limitation of current task-specific training methods is that they require nontrivial financial and/or equipment resources. This pilot study evaluated the efficacy of 2 low-cost, low-tech methods for slip-recovery training in improving balance recovery ability. The 2 methods were as follows: (1) repeated unexpected slip training (UST), which involved repeated unexpected slips while walking (similar to current methods of task-specific slip-recovery training) and (2) volitional sliprecovery training (VST), which involved practicing a slip recovery response after volitionally stepping to induce a slip-like perturbation. A total of 36 young adults completed 1 training session (UST, VST, or control), followed by 1 unexpected, laboratory-induced slip while walking on the following day. Compared with controls, UST and VST resulted in a higher proportion of successful balance recoveries from the laboratory-induced slips. UST improved both proactive control and the reactive stepping response after slipping, whereas VST improved the ability to arrest the motion of the slipping foot. Based on these preliminary results, UST and VST may provide practical, cost-effective methods for slip-recovery training.
- Required friction during overground walking is lower among obese compared to non-obese older men, but does not differ with obesity among womenArena, Sara L.; Garman, Christina R.; Nussbaum, Maury A.; Madigan, Michael L. (Elsevier, 2017-02-27)Obesity and aging have been independently associated with altered required friction during walking, but it is unclear how these factors interact to influence the likelihood of slipping. Therefore, the purpose of this study was to determine whether there are differences related to obesity and aging on required friction during overground walking. Fourteen older non-obese, 11 older obese, 20 younger non-obese, and 20 younger obese adults completed walking trials at both a self-selected and hurried speed. When walking at a hurried speed, older obese men walked at a slower gait speed and exhibited lower frictional demands compared both to older non-obese men and to younger obese men. No differences in required friction were found between non-obese and obese younger adults. These results suggest that the increased rate of falls among obese or older adults is not likely due to a higher risk of slip initiation.
- Relative Effort while Walking Is Higher among Women Who Are Obese, and Older WomenKoushyar, Hoda; Anderson, Dennis E.; Nussbaum, Maury A.; Madigan, Michael L. (Lippincott Williams & Wilkins, 2019-07-23)Purpose: Individuals who are obese, and older individuals, exhibit gait alterations that may result, in part, from walking with greater effort relative to their maximum strength capacity. The goal of this study was to investigate obesity-related and age-related differences in relative effort during gait. Methods: Four groups of women completed the study, including 10 younger healthy-weight, 10 younger obese, 10 older healthy-weight, and 9 older obese women. The protocol included strength measurements at the hip, knee, and ankle in both flexion and extension, and gait trials under self-selected and constrained (1.5 m·s-1 gait speed and 0.65-m step length) conditions. Relative effort was calculated as the ratio of joint torques during gait, and strength from a subject-specific model that predicted strength as a function of joint angle. Results: Relative effort during self-selected gait was higher among women who were obese in knee extension (P = 0.028) and ankle plantar flexion (P = 0.013). Although both joint torques and strength were higher among women who were obese, these increases in relative effort were attributed to greater obesity-related increases in joint torques than strength. Relative effort was also higher among older women in hip flexion (P < 0.001) and knee extension (P = 0.008), and attributed to age-related strength loss. Results were generally similar between self-selected and constrained gait, indicating the greater relative effort among women who were obese and older women was not attributed to differences in gait spatiotemporal characteristics. Conclusions: Women who were obese, as well as older women, walk with greater relative effort. These results may help explain the compromised walking ability among these individuals.
- Obesity as a Factor Contributing to Falls by Older AdultsMadigan, Michael L.; Rosenblatt, Noah J.; Grabiner, Mark D. (Springer, 2014-05-24)The growth of the worldwide population of older adults presents significant challenges, many inter-related, that range from the health of individuals to the health of national economies. In the US, more than one-third of older adults may be obese, a condition that may independently increase the risk for mobility impairment, fall-related injury and, possibly, costs of post-injury treatment and care. The effectiveness of conventional exercise-based fall prevention programs is significant but smaller than both the annual rate of falling of older adults and rate of growth of this population, who are at greatest risk for injurious falls. The anthropometric and functional consequences of obesity may impose limitations on the ability to perform compensatory stepping responses following large postural disturbances. The focus of this paper is the potential of task-specific training to improve compensatory stepping responses and reduce falls by obese people given the individual-specific anthropometric and functional consequences of obesity.
- Impaired plantar sensitivity among the obese is associated with increased postural swayWu, Xuefang; Madigan, Michael L. (Elsevier, 2014-09-19)Impaired foot plantar sensitivity has been hypothesized among individuals who are obese, and may contribute to their impaired balanced during quiet standing. The objective of this study was to investigate the effects of obesity on plantar sensitivity, and explore the relationship between plantar sensitivity and balance during quiet standing. Thirty-nine young adults from the university population participated in the study including 19 obese and 20 non-obese adults. Plantar sensitivity was measured as the force threshold at which an increasing force applied to the plantar surface of the foot was first perceived, and the force threshold at which a decreasing force was last perceived. Measurements were obtained while standing, and at two locations on the plantar surface of the dominant foot. Postural sway during quiet standing was then measured under three different sensory conditions. Results indicated less sensitive plantar sensitivity and increased postural sway among the obese, and statistically significant correlations between plantar sensitivity and postural sway that were characterized as weak to moderate in strength. As such, impaired plantar sensitivity among individuals who are obese may be a mechanism by which obesity degrades standing balance among these individuals.
- Feet kinematics upon slipping discriminate between recoveries and three types of slip-induced fallsAllin, Leigh J.; Nussbaum, Maury A.; Madigan, Michael L. (Taylor & Francis, 2018-01-03)This study investigated the relationship between feet kinematics upon slipping while walking and the outcome of the slip. Seventy-one slips (induced by walking over an unexpectedly slippery surface) were analysed, which included 37 recoveries, 16 feet-split falls, 11 feet-forward falls and seven lateral falls. Feet kinematics differed between recoveries and three types of slip-induced falls, and a discriminant model including six measures of feet kinematics correctly predicted 87% of slip outcomes. Two potentially modifiable characteristics of the feet kinematics upon slipping that can improve the likelihood of successfully averting a fall were identified: (1) quickly arresting the motion of the slipping foot and (2) a recovery step that places the trailing toe approximately 0–10% body height anterior to the sacrum. These results may inform the development of task-specific balance training interventions that promote favourable recovery responses to slipping. Practitioner Summary: This study investigated the relationship between feet movements upon slipping and outcomes of the slip. Potentially modifiable characteristics that can reduce the likelihood of falling were: (1) quickly arresting slipping foot motion and (2) a recovery step that places the trailing toe approximately 0–10% body height anterior to the sacrum.
- Falls resulting from a laboratory-induced slip occur at a higher rate among individuals who are obeseAllin, Leigh J.; Wu, Xuefang; Nussbaum, Maury A.; Madigan, Michael L. (Elsevier, 2016-02-06)Falls due to slipping are a serious concern, with slipping estimated to cause 40-50% of all fall-related injuries. Epidemiological data indicates that older and obese adults experience more falls than young, non-obese individuals. An increasingly heavier and older U.S. population and workforce may be exacerbating the problem of slip-induced falls. The purpose of this study was to investigate the effects of obesity and age on slip severity and rate of falling resulting from laboratory-induced slips. Four groups of participants (young obese, young non-obese, older obese, older non-obese) were slipped while walking at a self-selected, slightly hurried pace. Slip severity (slip distance, slip duration, mean slip speed and peak slip speed) and slip outcome (fall or recovery) were compared between groups. Obese individuals experienced 22% faster slips than non-obese individuals in terms of mean slip speed (p=0.022). Obesity did not affect slip distance, slip duration or peak slip speed. Obese individuals also exhibited a higher rate of falls; 32% of obese individuals fell compared to 10% of non-obese (p=0.005). Obese individuals were more than eight times more likely to experience a fall than non-obese individuals when adjusting for age, gender and gait speed. No age effects were found for slip severity or slip outcome. These results, along with epidemiological data reporting higher fall rates among the obese, indicate that obesity may be a significant risk factor for experiencing slip-induced falls. Slip severity thresholds were also reported that may have value in developing controls for fall prevention.
- Alternative measures of toe trajectory more accurately predict the probability of tripping than minimum toe clearanceByju, Achu G.; Nussbaum, Maury A.; Madigan, Michael L. (Elsevier, 2016-12-08)Tripping is responsible for a large percentage of falls. Minimum toe clearance (MTC) during the swing phase of gait is commonly used to infer the probability of tripping (POT). However, there is limited empirical evidence to support the relationship between these two variables, and other measures of toe trajectory may better predict POT than MTC. The goals of this study were to: 1) quantify the relationship between MTC and POT; and 2) explore alternative measures of toe trajectory that may predict POT more accurately than MTC. POT was estimated by comparing the distribution of tripping obstacles measured along heavily-used, paved sidewalks on a university campus, to the toe trajectory of 40 young adults obtained while walking over an obstacle-free walkway in a research laboratory. POT exhibited a curvilinear relationship with MTC, and regression equations were established to predict POT from MTC. POT was more accurately predicted when using virtual points on the bottom of the anterior edge of the shoe to determine MTC, compared to using a physical marker located on top of the toes to determine MTC. POT was also more accurately predicted when using a new measure of toe trajectory (the area below 40 mm and above the toe trajectory, normalized by the swing length), compared to just MTC. These are the first empirical results supporting a direct, quantitative relationship between MTC and POT. These results may improve the ability to identify risk factors that influence POT, and aid in developing interventions to reduce POT.
- Age-related differences in muscle power during single-step balance recoveryMadigan, Michael L. (Human Kinetics, 2006-08-01)The purpose of this study was to investigate age-related differences in muscle power during a surrogate task of trip recovery. Participants included 10 healthy young men (19-23 years old) and 10 healthy older men (65-83). The task involved releasing participants from a forward-leaning posture. After release, participants attempted to recover their balance using a single step of the right foot. Muscle power at the hip, knee, and ankle of the stepping limb were determined from the product of joint angular velocity and joint torque. Muscle powers during balance recovery followed a relatively consistent pattern in both young and older men, and showed effects of both lean and age. Interestingly, the effects of age did not always involve smaller peak power values in the older men as expected from the well-documented loss of muscle power with aging. Older men exhibited smaller peak muscle power at the knee and larger peak muscle power at the ankle and hip compared to young men. The increases in muscle power at the ankle and hip may result from a neuromuscular adaptation aimed at improving balance recovery ability by compensating for the age-related loss of muscle function. © 2006 Human Kinetics, Inc.
- A Pilot Study Exploring Obesity-Related Differences in Fall Rate and Kinematic Response Resulting From a Laboratory-Induced TripGarman, Christina R.; Nussbaum, Maury A.; Franck, Christopher T.; Madigan, Michael L. (Taylor & Francis, 2016-08-15)Background: Obese adults are reported to fall at a higher rate than non-obese adults. Purpose: To help determine the reason for this higher fall rate, we quantified fall rates, kinematics at trip onset, and kinematics during the response to a laboratory-induced trip among two groups of young adults with higher and lower body mass indexes (BMI) that approximated obese and healthy-weight ranges. Our focus was on young adults given that they comprise a substantial portion of the workforce. Methods: Twenty-one young adult subjects, including 10 with a lower BMI (19.4–25.7 kg/m2) and 11 with a higher BMI (29.8–42.9 kg/m2), walked along a 10 m walkway at a purposeful speed. During a randomly selected walking trial, an obstacle was raised to elicit a trip. Results: Among the 19 subjects who unambiguously fell or recovered, 30% of subjects with higher BMI fell and 0% of lower BMI subjects fell, but this difference did not reach statistical significance. Among the 15 subjects who used an elevating strategy, all recovered balance, and the only kinematic response variable that differed between BMI groups was that recovery step time was longer among the higher BMI group. Among the four subjects who used a lowering strategy, no statistical analysis was possible due to a small number of subjects, but several measures were consistent with a less favorable kinematic response among the three higher BMI fallers compared to the one lower BMI subject who recovered. Conclusions: This study provides preliminary evidence that obesity may adversely influence fall rate and recovery kinematics after tripping among young adults. Additional larger scale studies are needed to better understand contributing and modifiable factors that can be targeted via intervention.
- A bootstrapping method to assess the influence of age, obesity, gender, and gait speed on probability of tripping as a function of obstacle heightGarman, Christina R.; Franck, Christopher T.; Nussbaum, Maury A.; Madigan, Michael L. (Elsevier, 2015-02-03)Tripping is a common mechanism for inducing falls. The purpose of this study was to present a method that determines the probability of tripping over an unseen obstacle while avoiding the ambiguous situation wherein median minimum foot clearance (MFC) and MFC interquartile range concurrently increase or decrease, and determines how the probability of tripping varies with potential obstacle height. The method was used to investigate the effects of age, obesity, gender, and gait speed on the probability of tripping. MFC was measured while 80 participants walked along a 10-m walkway at self-selected and hurried gait speeds. The method was able to characterize the probability of tripping as a function of obstacle height, and identify effects of age, obesity, gender, and gait speed. More specifically, the probability of tripping was lower among older adults, higher among obese adults, higher among females, and higher at the slower self-selected speed. Many of these results were not found, or clear, from the more common approach on characterizing likelihood of tripping based on MFC measures of central tendency and variability.
- A data-driven approach to classifying manual material handling tasks using markerless motion capture and recurrent neural networksOjelade, Aanuoluwapo; Rajabi, Mohammad Sadra; Kim, Sunwook; Nussbaum, Maury A. (Elsevier, 2025-05)Work-related musculoskeletal disorders (WMSDs) are prevalent problems that encompass a range of conditions affecting muscles, tendons, and nerves due to repetitive strain, non-neutral postures, and forceful exertions. These disorders lead to pain, reduced productivity and substantial healthcare costs. Effective physical exposure assessment tools are needed in the workplace to quantify WMSD risks and the association between exposure and risks. While several tools are available, they are often limited in scope and lack the ability to assess physical risks continuously. In this study, we evaluated a data-driven approach to continuously classify manual material handling tasks and specific task conditions using different feature sets and machine learning algorithms. Specifically, kinematic data from markerless motion capture (MMC) system was used as input for various recurrent neural networks to classify among eight distinct manual material handling tasks: box lifting, asymmetric box lifting, box carriage, box pushing, box pulling, cart pushing, overhead lifting, and box lowering. The models we tested include bidirectional long-short term memory, gated recurrent units, and bidirectional gated recurrent units. We also classified specific task conditions, such as hand configurations and initial lifting height. Overall, using the MMC's kinematic data led to satisfactory results (e.g., accuracy of 80–94 %) in classifying the tasks and the task conditions. Our results, though, also emphasize that classification performance varied across different feature sets, tasks, and between males and females. Nonetheless, use of MMC demonstrates clear potential for physical exposure assessment.
- Employing Eye Trackers to Reduce Nuisance AlarmsHerdt, Katherine; Hildebrandt, Michael; LeBlanc, Katya; Lau, Nathan (MDPI, 2025-04-22)When process operators anticipate an alarm prior to its annunciation, that alarm loses information value and becomes a nuisance. This study investigated using eye trackers to measure and adjust the salience of alarms with three methods of gaze-based acknowledgement (GBA) of alarms that estimate operator anticipation. When these methods detected possible alarm anticipation, the alarm’s audio and visual salience was reduced. A total of 24 engineering students (male = 14, female = 10) aged between 18 and 45 were recruited to predict alarms and control a process parameter in three scenario types (parameter near threshold, trending, or fluctuating). The study evaluated whether behaviors of the monitored parameter affected how frequently the three GBA methods were utilized and whether reducing alarm salience improved control task performance. The results did not show significant task improvement with any GBA methods (F(3,69) = 1.357, p = 0.263, partial η2 = 0.056). However, the scenario type affected which GBA method was more utilized (X2 (2, N = 432) = 30.147, p < 0.001). Alarm prediction hits with gaze-based acknowledgements coincided more frequently than alarm prediction hits without gaze-based acknowledgements (X2 (1, N = 432) = 23.802, p < 0.001, OR = 3.877, 95% CI 2.25–6.68, p < 0.05). Participant ratings indicated an overall preference for the three GBA methods over a standard alarm design (F(3,63) = 3.745, p = 0.015, partial η2 = 0.151). This study provides empirical evidence for the potential of eye tracking in alarm management but highlights the need for additional research to increase validity for inferring alarm anticipation.