Automatic sleep stage classification based on easy to register signals as a validation tool for ergonomic steering in smart bedding systems

Ergonomic sleep studies benefit from long-term monitoring in the home environment to cope with daily variations and habituation effects. Polysomnography allows to asses sleep accurately, but is costly, time-consuming and possibly disturbing for the sleeper. Actigraphy is cheap and user friendly, but for many studies lacks accuracy and detailed information. This proof-of-concept study investigates Least-Squares Support Vector Machines as a tool for automatic sleep stage classification (Wake-N1-Rem to N2-N3 separation), using automatic trainingset-specific filtered features as derived from three easy to register signals, namely heart rate, breathing rate and movement. The algorithms are trained and validated using 20 nights out of a 600 night database from over 100 different healthy persons. Different training and test set strategies were analyzed leading to different results. The more person-specific the training nights to the test nights, the better the classification accuracy as validated against the hypnograms scored by experts from the full polysomnograms. In the limit of complete person-specific training, the accuracy of the algorithm on the test set reached 94%. This means that this algorithm could serve its use in long-term monitoring sleep studies in the home environment, especially when prior person-specific polysomnographic training is performed.     

Using environmental affordances to direct people natural movement indoors

Understanding and predicting people's displacement movement is particularly important for professionals involved in planning complex buildings (e.g., hospitals, convention centers, subway stations and university campus). Some decisions taken by the visitors while choosing what route to follow can be influenced by some environmental cues which can act as a factor of attraction, influencing the wayfinding process. Therefore, the main objective of this study was to evaluate the hypotheses that, in the context of a simulated emergency egress, people prefer to move along either a wider and with more lighting corridor or to bear right. To collect the users' responses, a constant stimulus method was used, combined with a two forced choices method, involving the projection of stereoscopic images in a wall-screen. Results suggest that, in a "T-type" intersection, users randomly chose which direction to follow. However, if there is an increment in the width of the side corridor, users tend to follow the wider corridor. When light is inserted, users also prefer to choose the corridors with more lighting. In situations where the variables corridor width and existence of lighting are concurrent, the corridors with light are the most chosen by the users.     

DHM simulation in virtual environments: a case-study on control room design

This paper will present the workflow developed for the application of serious games in the design of complex cooperative work settings. The project was based on ergonomic studies and development of a control room among participative design process. Our main concerns were the 3D human virtual representation acquired from 3D scanning, human interaction, workspace layout and equipment designed considering ergonomics standards. Using Unity3D platform to design the virtual environment, the virtual human model can be controlled by users on dynamic scenario in order to evaluate the new work settings and simulate work activities. The results obtained showed that this virtual technology can drastically change the design process by improving the level of interaction between final users and, managers and human factors team.     

Anthropometric aspects of body seated in school

This study aimed to assess the student-furniture interface from anthropometric parameters of the sitting posture. The sample was composed of 887 students from two public schools in the State of Parana-Brazil, which attended children from 7 to 17 years of age. The data collection used anthropometric measures of the sitting position, a questionnaire containing a human body diagram for indication of discomfort areas and photographic records to verify postural and ergonomic inadequacies in classroom. The following anthropometric variables were measured: popliteal height, sacro-popliteal length, hip width, lumbar support height, and elbow and thigh height. Percentiles 5 and 95 of anthropometric variables showed differences statistically significant, with variation coefficient greater than 30%. In relation to body discomfort, the highest occurrences were recorded for ankle, knees and shoulder joints as well as for spine and buttocks. It was concluded that children use school furniture that does not meet their anthropometric standards, which favored the adoption of incorrect postures and contributed to the emergence of musculoskeletal problems that can interfere with their educational process.     

Computer decision support tools in primary care

Computer Decision Support Tools (CDSTs) can support clinicians at various stages of the care process and improve healthcare, but implementation of these tools has been difficult. In this study we examine the need for, the use of, and barriers and facilitators to the use of a CDST from a human factor perspective. Results show that there is a need for CDSTs, and that physicians do use well-developed CDSTs. However, there are also barriers against the use, such usability issues and problems fitting them into the clinical workflow.     

The entry of women in predominantly male professions: when training supports the search of alternative ways of organizing work time

Following a research carried out on the integration of women in professional areas predominantly for men, this paper intends to present and debate the project of a training course which aims the transformation of the organization of work schedules in order to improve the well-being of the workers involved. The conception of training courses with this type of objective involves the confrontation and debate between the "invested skills" of the trainers and the "constituted skills" of the trainees. But will this paradigm remain intact when applied to training courses permeated by the gender dimension? That is what one will try to realize with the effective implementation of a training course, whose reflection will allow, ultimately, to enrich our understanding on gender, work, health and training.     

Active participation in preventionist professional practices: a specific ergonomics training course

Currently, the different forms of corporate management methods (quality circles, lean manufacturing, etc.) are usually based on employee mobilisation. Very often, the goal of this type of approach is at best, to ensure that employees embrace corporate projects, or otherwise to impose changes on them without taking into account the real work and difficulties that they face daily. However, do these employee solicitation methods converge with participatory approaches as envisaged by ergonomists and more generally, preventionists? Based on the observation that the activity of institutional preventionists evolves with regulatory constraints and work related to the monitoring of indicators, the implementation and steering of the participatory approach within companies may be a major lever for prevention. After describing the foundations of a participatory approach, this paper will present a training experiment aimed at implementing and promoting employee participation in prevention efforts. The content of this training is then analysed with regard to the balance between methodology and the use of trainees' narratives. The results of the training session are presented from the point of view of the development prospects for pedagogical tools and the organisation of the training.     

Bivariate pointing movements on large touch screens: investigating the validity of a refined Fitts' Law

On the basis of three empirical studies Fitts' Law was refined for bivariate pointing tasks on large touch screens. In the first study different target width parameters were investigated. The second study considered the effect of the motion angle. Based on the results of the two studies a refined model for movement time in human-computer interaction was formulated. A third study, which is described here in detail, concerns the validation of the refined model. For the validation study 20 subjects had to execute a bivariate pointing task on a large touch screen. In the experimental task 250 rectangular target objects were displayed at a randomly chosen position on the screen covering a broad range of ID values (ID= [1.01; 4.88]). Compared to existing refinements of Fitts' Law, the new model shows highest predictive validity. A promising field of application of the model is the ergonomic design and evaluation of project management software. By using the refined model, software designers can calculate a priori the appropriate angular position and the size of buttons, menus or icons.     

Selection of a voice for a speech signal for personalized warnings: the effect of speaker's gender and voice pitch

There is an increasing interest in multimodal technology-based warnings, namely those conveying speech-warning statements. This type of warning may be tailored to the situation as well as to the target user's characteristics. However, more information is needed on how to design these warnings in a way that ensures intelligibility, promotes compliance and reduces the potential for annoyance. In this context, this paper reports an exploratory study whose main purpose was to assist the selection of a synthesized voice for a subsequent compliance study with personalized (i.e., using the person's name) technology-based warnings using Virtual Reality. Participants were requested to listen to speech signals, gathered from a speech synthesizer and post-processed in order to change the pitch perception, and then these were evaluated by fulfilling the MOS-X questionnaire. After that, the participants ranked the voices according to their preference. The effects of the speaker's gender and voice pitch, on both ratings and ranking were assessed. The preference of the male and female listeners for a talker's voice gender was also investigated. The results show that participants mostly prefer as first choice the high-pitched female voice, which also gathered the highest overall score in the MOS-X questionnaire. No significant influence of the participants' gender was found on the assessed measures.     

Personality of social robots perceived through the appearance

Past research showed that people are able to perceive the personality of others at zero acquaintances. There are two main ways, verbal and non-verbal methods, which play an important role for one in perceiving personality of others. Extensive research was conducted in relating personality with verbal, paralinguistic and gestures cues. However, there are not much research, to our knowledge, that relates the appearance and perceived personality of robots. The main objective of this research is to relate individual design features with big five perceived personality of the robots. We used the results of rated perceptions across 100 pictorial images of robots and relate the results with the 40 individual design features using General Linear Model (GLM). The initial results of the GLM analysis showed that participants' rating of personality of robot fell along the dimension of perceived friendliness which is a common rotation of extroversion and agreeableness. Some relationships were found between humanlike design features and perceived friendliness of robots. Since participants are more familiar with humans, participants perceived robots with humanlike features friendlier than the others. Some other findings such as color and surface material were found related with participants' perceived friendliness as well. In the future, we will work on the analysis of the main and interaction effects of individual features on user's perceived friendliness.