Freezing of gait (FOG) is one of the most incapacitating motor symptoms in Parkinson’s disease (PD). The occurrence of FOG reduces the patients’ quality of live and leads to falls. FOG assessment has usually been made through questionnaires, however, this method can be subjective and could not provide an accurate representation of the severity of this symptom. The use of sensor-based systems can provide accurate and objective information to track the symptoms’ evolution to optimize PD management and treatments. Several authors have proposed specific methods based on wearables and the analysis of inertial signals to detect FOG in laboratory conditions, however, its performance is usually lower when being used at patients’ homes. This study presents a new approach based on a recurrent neural network (RNN) and a single waist-worn triaxial accelerometer to enhance the FOG detection performance to be used in real home-environments. Also, several machine and deep learning approaches for FOG detection are evaluated using a leave-one-subject-out (LOSO) cross-validation. Results show that modeling spectral information of adjacent windows through an RNN can bring a significant improvement in the performance of FOG detection without increasing the length of the analysis window (required to using it as a cue-system).

The aim of this study was to estimate occupational exposure to inhalable wood dust by country, industry, the level of exposure and type of wood dust in 25 member states of the European Union (EU-25) for the purposes of hazard control, exposure surveillance and assessment of health risks. National labour force statistics, a country questionnaire (in 15 member states, EU-15), a company survey (in Finland, France, Germany and Spain), exposure measurements (from Denmark, Finland, France, Germany, The Netherlands and the United Kingdom) and expert judgements were used to generate preliminary estimates of exposure to different types of wood dust. The estimates were generated according to industrial class (six wood industries, four other sectors) and level of exposure (five classes). These estimates were reviewed and finalized by national experts from 15 member states. Crude estimates were generated also for 10 new member states (EU-10). The basic data and final estimates were included in the WOODEX database. In 2000–2003, about 3.6 million workers (2.0% of the employed EU-25 population) were occupationally exposed to inhalable wood dust. Of those, construction employed 1.2 million exposed workers (33%), mostly construction carpenters. The numbers of exposed workers were 700 000 (20%) in the furniture industry, 300 000 (9%) in the manufacture of builders' carpentry, 200 000 (5%) in sawmilling, 150 000 (4%) in forestry and <100 000 in other wood industries. In addition, there were 700 000 exposed workers (20%) in miscellaneous industries employing carpenters, joiners and other woodworkers. The numbers of exposed workers varied by country ranging from <3000 in Luxembourg and Malta to 700 000 in Germany. The highest exposure levels were estimated to occur in the construction sector and furniture industry. Due to limited exposure data there was considerable uncertainty in the estimates concerning construction woodworkers. About 560 000 workers (16% of the exposed) may be exposed to a level exceeding 5 mg m⁻³. Mixed exposure to more than one species of wood and dust from wooden boards was very common, but reliable data on exposure to different species of wood could not be retrieved. This kind of assessment procedure integrating measurement data, company data, country-specific data and expert judgement could also serve as one model for the assessment of other occupational exposures.