Ambient Assisted Working (AAW) is a discipline aiming to provide comfort and safety in the workplace through customization and technology. Workers’ comfort may be compromised in many labor situations, including those depending on environmental conditions, like extremely hot weather conduces to heat stress. Occupational heat stress (OHS) happens when a worker is in an uninterrupted physical activity and in a hot environment. OHS can produce strain on the body, which leads to discomfort and eventually to heat illness and even death. Related ISO standards contain methods to estimate OHS and to ensure the safety and health of workers, but they are subjective, impersonal, performed a posteriori and even invasive. This paper focuses on the design and development of real-time personalized monitoring for a more effective and objective estimation of OHS, taking into account the individual user profile, fusing data from environmental and unobtrusive body sensors. Formulas employed in this work were taken from different domains and joined in the method that we propose. It is based on calculations that enable continuous surveillance of physical activity performance in a comfortable and healthy manner. In this proposal, we found that OHS can be estimated by satisfying the following criteria: objective, personalized, in situ, in real time, just in time and in an unobtrusive way. This enables timely notice for workers to make decisions based on objective information to control OHS.

Artificial Neural Networks (ANNs) were created inspired by the neural networks in the human brain and have been widely applied in speech processing. The application areas of ANN include: Speech recognition, speech emotion recognition, language identification, speech enhancement, and speech separation, amongst others. Likewise, given that speech processing performed by humans involves complex cognitive processes known as auditory attention, there has been a growing amount of papers proposing ANNs supported by deep learning algorithms in conjunction with some mechanism to achieve symmetry with the human attention process. However, while these ANN approaches include attention, there is no categorization of attention integrated into the deep learning algorithms and their relation with human auditory attention. Therefore, we consider it necessary to have a review of the different ANN approaches inspired in attention to show both academic and industry experts the available models for a wide variety of applications. Based on the PRISMA methodology, we present a systematic review of the literature published since 2000, in which deep learning algorithms are applied to diverse problems related to speech processing. In this paper 133 research works are selected and the following aspects are described: (i) Most relevant features, (ii) ways in which attention has been implemented, (iii) their hypothetical relationship with human attention, and (iv) the evaluation metrics used. Additionally, the four publications most related with human attention were analyzed and their strengths and weaknesses were determined.

Machine learning methods have been used to classify neurodegenerative diseases using gait data. Recent works with Huntington’s disease patients have reported results up to 88.2% of correct classification based on a probabilistic modeling approach for gait assessment. The aim of this work was to improve Huntington’s disease patients classification results while reducing the number of sensor devices to capture gait data and identifying the related gait features. The proposed method is based on general Assembles (Meta) Classifier algorithms approach, for the classification of Huntington’s disease affected gait versus Healthy Control subjects normal gait. The proposed methodology was tested on gait data recorded on Huntington’s disease patients and healthy control subjects using raw data from smart-phones movement sensors placed at both ankles. Best partial results of individual classifier algorithms are taken at each iteration of the meta-classifier, to predict the final result by averaging results and majority votes. Several instances of this combined approach were tested and validated. Obtained results confirm an improvement in accuracy, since 13 subjects out of a total of 14 were correctly classified. All 7 Huntington’s disease patients were correctly selected with Logitboost & RandomForest combination.

The most important thing immediately before, during and after a disaster occurs is the dissemination of information, a deployment of devices enabled by IoT (Internet of Things) could bring benefits in terms of giving to people information opportunely for making decisions in face of this disaster. In this paper, we present a sensor to measure water level in rivers, lakes, lagoons and streams. For such purpose and to prove our concept, we designed a pilot project through a micro-model that is constructed with a water level measurement sensor based on a simple open circuit that closes when in contact with water and experimentally tested into a water container under a controlled environment. This micro-model is performed on the basis of a programmable electronic board (Netduino Plus 2), an electronic circuit connected to electrical resistances that are located at a specific height, within a water container, when the water level rises and reaches the resistors, varies the impedance, this shows the actual water level and so on for different heights. The information from water level sensor is transmitted via WiFi to a laptop, then this information is also seen in smartphones, where users can see the water level in rivers. Finally, the micro-model is tested by experimental tests under a controlled environment and satisfactory results are obtained.

Knowing the perceived exertion of workers during their physical activities facilitates the decision-making of supervisors regarding the worker allocation in the appropriate job, actions to prevent accidents, and reassignment of tasks, among others. However, although wearable heart rate sensors represent an effective way to capture perceived exertion, ergonomic methods are generic and they do not consider the diffuse nature of the ranges that classify the efforts. Personalized monitoring is needed to enable a real and efficient classification of perceived individual efforts. In this paper, we propose a heart rate-based personalized method to assess perceived exertion; our method uses fuzzy logic as an option to manage imprecision and uncertainty in involved variables. We applied some experiments to cleaning staff and obtained results that highlight the importance of a custom method to classify perceived exertion of people doing physical work.