Diagnosing fatigue in gait patterns by support vector machines and self-organizing maps

The aim of the study was to train and test support vector machines (SVM) and self-organizing maps (SOM) to correctly classify gait patterns before, during and after complete leg exhaustion by isokinetic leg exercises. Ground reaction forces were derived for 18 gait cycles on 9 adult participants. Immediately before the trials 7–12, participants were required to completely exhaust their calves with the aid of additional weights (44.4 ± 8.8 kg). Data were analyzed using: (a) the time courses directly and (b) only the deviations from each individual’s calculated average gait pattern. On an inter-individual level the person recognition of the gait patterns was 100% realizable. Fatigue recognition was also highly probable at 98.1%. Additionally, applied SOMs allowed an alternative visualization of the development of fatigue in the gait patterns over the progressive fatiguing exercise regimen.     

How professional pilots perceive interactions of working conditions,rosters, stress,sleep problems,fatigue and mental health. A qualitative content analysis

IntroductionSo far, no qualitative content analysis (QCA) has analysed pilots’ experiences and perceptions regarding weaknesses of fatigue risk management (FRM), flight time limitations (FTL), rosters, fatigue-severity, sleep problems, and how they relate to pilots’ mental health and well-being.ObjectiveThis research analyses pilots’ described perceptions of stress, fatigue, aviation safety and how regulations like FTL can affect their health and well-being.MethodIn total, 119 international pilots described their perceptions of FTL, rosters, aviation safety, and how they relate to fatigue and health. The QCA was conducted to analyse interactions of working conditions, stressors, fatigue, sleep problems and mental health of EASA-based and Australian pilots.ResultsAlthough pilots were rostered for only 60.8% to 62.5% of the legally allowed duty and flight hours/month, 78.6% reported severe or very high fatigue, 22.8% significant depression, 12.3% significant anxiety symptoms, 10.5% reported significant depression and anxiety symptoms. Pilots uttered severe concerns about FTL, sleep restrictions associated with early starts, minimum rest, etc. Pilots also expressed distinct fears regarding more fatigue-related crashes, and how adverse working conditions, work-related and psychosocial stress could impair their health.ConclusionsThis QCA provided valuable insights into interactions of working conditions, fatigue, sleep restrictions, physical and mental health. Progressive health impairment due to lack of sleep and accumulated fatigue promote burnout, mental and physical health problems, which not only threaten flight safety, but also sustainability of aviation.     

Transition patterns of driving style from a traditional driving environment to a connected vehicle environment: A case of an extra-long tunnel road

To provide a better understanding of individual driver’s driving style classification in a traditional and a CV environment, spatiotemporal characteristics of vehicle trajectories on a road tunnel were extracted through a driving simulator-based experiment. Speed, acceleration, and rate of acceleration changes are selected as clustering indexes. The dynamic time warping and k-means clustering were adopted to classify participants into different risk level groups. To assess the driver behavior benefits in a CV environment, an indicator BI (behavior indicator, BI) was defined based on the standard deviation of speed, the standard deviation of acceleration, and the standard deviation of the rate of acceleration change. Then, the index BI of each driver was calculated. Furthermore, this paper explored driving style classification, not in terms of traditional driving environment, but rather the transition patterns from a traditional driving environment to a CV environment. The results revealed that inside a long tunnel, 80 % of drivers benefited from a CV environment. Moreover, drivers might need training before using a CV system, especially female drivers who have low driving mileage. In addition, the results showed that the driving style of 69 % of the drivers’ transferred from a high risk-level to a low risk-level when driving in a CV environment. The study results can be expected to improve driving training education programs and also to provide a valuable reference for developing individual in-vehicle human-machine interface projects and other proactive safety countermeasures.     

计算机化分类测验终止规则的类别、特点及应用

计算机化分类测验(Computerized Classification Testing, CCT)能够高效地对被试进行分类, 已广泛应用于合格性测验及临床心理学中。作为CCT的重要组成部分, 终止规则决定测验何时停止以及将被试最终划分到何种类别, 因此直接影响测验效率及分类准确率。已有的三大类终止规则(似然比规则、贝叶斯决策理论规则及置信区间规则)的核心思想分别为构造假设检验、设计损失函数和比较置信区间相对位置。同时, 在不同测验情境下, CCT的终止规则发展出不同的具体形式。未来研究可以继续开发贝叶斯规则、考虑多维多类别情境以及结合作答时间和机器学习算法。针对测验实际需求, 三类终止规则在合格性测验上均有应用潜力, 而临床问卷则倾向应用贝叶斯规则。     

Imminent Danger? Probabilistic Classification Learning of Threat-Related Information in Obsessive-Compulsive Disorder

A tendency to overestimate threat has been shown in individuals with OCD. We tested the hypothesis that this bias in judgment is related to difficulties in learning probabilistic associations between events. Thirty participants with OCD and 30 matched healthy controls completed a learning experiment involving 2 variants of a probabilistic classification learning task. In the neutral weather-prediction task, rainy and sunny weather had to be predicted. In the emotional task danger of an epidemic from virus infection had to be predicted (epidemic-prediction task). Participants with OCD were as able as controls to improve their prediction of neutral events across learning trials but scored significantly below healthy controls on the epidemic-prediction task. Lower performance on the emotional task variant was significantly related to a heightened tendency to overestimate threat. Biased information processing in OCD might thus hamper corrective experiences regarding the probability of threatening events.     

Stress perçu et santé physique des doctorants dans les universités françaises

Few studies have focused on PhD students in France despite the fact that this population appears to be particularly vulnerable to stress and often faces precariousness. This research investigated associations between socio-demographic factors, health behaviours, perceived stress and physical health in a wide sample of PhD students (n = 1923) in order to have a better understanding of this population's specificities. Our results indicated that stress is a critical issue among PhD candidates. Predictors of perceived stress were: gender, age, satisfaction with supervision, sleep quality and sports practice. Findings from this study confirm the relevance of the transactional model to investigate students’ health issues and suggest that physical activity and stress management should be encouraged through health promotion programs.