Search

[EN] The detection of hypertension (HT) is of great importance for the early diagnosis of cardiovascular diseases (CVDs), as subjects with high blood pressure (BP) are asymptomatic until advanced stages of the disease. The present study proposes a classification model to discriminate between normotensive (NTS) and hypertensive (HTS) subjects employing electrocardiographic (ECG) and photoplethysmographic (PPG) recordings as an alternative to traditional cuff-based methods. A total of 913 ECG, PPG and BP recordings from 69 subjects were analyzed. Then, signal preprocessing, fiducial points extraction and feature selection were performed, providing 17 discriminatory features, such as pulse arrival and transit times, that fed machine-learning-based classifiers. The main innovation proposed in this research uncovers the relevance of previous calibration to obtain accurate HT risk assessment. This aspect has been assessed using both close and distant time test measurements with respect to calibration. The k-nearest neighbors-classifier provided the best outcomes with an accuracy for new subjects before calibration of 51.48%. The inclusion of just one calibration measurement into the model improved classification accuracy by 30%, reaching gradually more than 96% with more than six calibration measurements. Accuracy decreased with distance to calibration, but remained outstanding even days after calibration. Thus, the use of PPG and ECG recordings combined with previous subject calibration can significantly improve discrimination between NTS and HTS individuals. This strategy could be implemented in wearable devices for HT risk assessment as well as to prevent CVDs., This research received financial support from grants PID2021-00X128525-IV0, PID2021123804OB-I00 and TED2021-129996B-I00 of the Spanish Government 10.13039/501100011033 jointly with the European Regional Development Fund (EU), SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2021/286 from Generalitat Valenciana.

Contribution: An improved inverted lecturing (IIL) framework based on blending flipped lectures and hands-on experiments provides instructional benefits, compared to traditional teaching (TT) and inverted lecturing (IL), in an introductory course in digital systems. Background: IL has proven more effective than TT in improving student learning in engineering courses, but has mostly been used for theory sessions. The impact of combining inverted lectures and hands-on experiments on student learning has not still been thoroughly assessed in engineering courses. Intended Outcomes: Attendance, marks, and satisfaction should improve for students in IL-based theory lectures, compared with those receiving TT, and should improve still further for students receiving the IIL-based method. Workload both for student and instructor should not increase significantly. Application Design: The three methods were compared in six consecutive offerings of the course. In the first two, TT was used for both theory and laboratory classes; in the next two, IL was used for theory lectures; and in the final two offerings the IIL-based scheme was used. The instructor, intended learning outcomes (ILOs), course syllabus, and student grading scheme were constant over the six semesters. A total of 184 students with similar backgrounds participated. Findings: Students under the IL- and IIL-based frameworks were more engaged than those receiving TT, and were more satisfied with their learning process. The IIL-based learners achieved the deepest conceptual understanding. Finally, the IL- and IIL-based methods did not significantly increase workload for either the students or the instructor.

The fast aging of the population around the world makes ambient intelligence-based assistive technologies essential for sustainable and efficient health-care systems. Aging adults who decide to live alone at home need constant monitoring to control their health status and quality of life. This work introduces a new wearable device that continuously monitors the emotional state of the elderly. Electro-dermal activity (EDA) is used to classify the aging adults into two groups: sleepiness and stressed. The results report a performance of more than 83% of accuracy by using exclusively time and magnitude features from EDA events.

This paper introduces an architecture as a proof-of-concept for emotion detection and regulation in smart health environments. The aim of the proposal is to detect the patient's emotional state by analysing his/her physiological signals, facial expression and behaviour. Then, the system provides the best-tailored actions in the environment to regulate these emotions towards a positive mood when possible. The current state-of-the-art in emotion regulation through music and colour/light is implemented with the final goal of enhancing the quality of life and care of the subject. The paper describes the three main parts of the architecture, namely "Emotion Detection", "Emotion Regulation" and "Emotion Feedback Control". "Emotion Detection" works with the data captured from the patient, whereas "Emotion Regulation" offers him/her different musical pieces and colour/light settings. "Emotion Feedback Control" performs as a feedback control loop to assess the effect of emotion regulation over emotion detection. We are currently testing the overall architecture and the intervention in real environments to achieve our final goal.

This article introduces a new and unobtrusive wearable monitoring device based on electrodermal activity (EDA) to be used in health-related computing systems. This paper introduces the description of the wearable device capable of acquiring the EDA of a subject in order to detect his/her calm/distress condition from the acquired physiological signals. The lightweight wearable device is placed in the wrist of the subject to allow continuous physiological measurements. With the aim of validating the correct operation of the wearable EDA device, pictures from the International Affective Picture System are used in a control experiment involving fifty participants. The collected signals are processed, features are extracted and a statistical analysis is performed on the calm/distress condition classification. The results show that the wearable device solely based on EDA signal processing reports around 89% accuracy when distinguishing calm condition from distress condition.

Automatic recognition of emotions is an emerging field, because it plays a key role to improve current affective human-computer interactions. Although for that purpose a variety of linear methods have been applied to the electroencephalographic (EEG) recording, nonlinear analysis has recently revealed novel and more useful insights about the brain behavior under different emotional states. This work briefly reviews the main progresses in this context, also highlighting the main challenges that will have to be mandatory tackled in future.

The electroencephalogram (EEG) is the most common tool used to study mental disorders. In the last years, the use of this recording for recognition of negative stress has been receiving growing attention. However, precise identification of this emotional state is still an interesting unsolved challenge. Nowadays, stress presents a high prevalence in developed countries and, moreover, its chronic condition often leads to concomitant physical and mental health problems. Recently, a measure of time series irregularity, such as quadratic sample entropy (QSEn), has been suggested as a promising single index for discerning between emotions of calm and stress. Unfortunately, this index only considers repetitiveness of similar patterns and, hence, it is unable to quantify successfully dynamics associated with the data temporal structure. With the aim of extending QSEn ability for identification of stress from the EEG signal, permutation entropy (PEn) and its modification to be amplitude-aware (AAPEn) have been analyzed in the present work. These metrics assess repetitiveness of ordinal patterns, thus considering causal information within each one of them and obtaining improved estimates of predictability. Results have shown that PEn and AAPEn present a discriminant power between emotional states of calm and stress similar to QSEn, i.e., around 65%. Additionally, they have also revealed complementary dynamics to those quantified by QSEn, thus suggesting a synchronized behavior between frontal and parietal counterparts from both hemispheres of the brain. More precisely, increased stress levels have resulted in activation of the left frontal and right parietal regions and, simultaneously, in relaxing of the right frontal and left parietal areas. Taking advantage of this brain behavior, a discriminant model only based on AAPEn and QSEn computed from the EEG channels P3 and P4 has reached a diagnostic accuracy greater than 80%, which improves slightly the current state of the art. Moreover, because this classification system is notably easier than others previously proposed, it could be used for continuous monitoring of negative stress, as well as for its regulation towards more positive moods in controlled environments.

Recognition of emotions is still an unresolved challenge, which could be helpful to improve current human-machine interfaces. Recently, nonlinear analysis of some physiological signals has shown to play a more relevant role in this context than their traditional linear exploration. Thus, the present work introduces for the first time the application of three recent entropy-based metrics: sample entropy (SE), quadratic SE (QSE) and distribution entropy (DE) to discern between emotional states of calm and negative stress (also called distress). In the last few years, distress has received growing attention because it is a common negative factor in the modern lifestyle of people from developed countries and, moreover, it may lead to serious mental and physical health problems. Precisely, 279 segments of 32-channel electroencephalographic (EEG) recordings from 32 subjects elicited to be calm or negatively stressed have been analyzed. Results provide that QSE is the first single metric presented to date with the ability to identify negative stress. Indeed, this metric has reported a discriminant ability of around 70%, which is only slightly lower than the one obtained by some previous works. Nonetheless, discriminant models from dozens or even hundreds of features have been previously obtained by using advanced classifiers to yield diagnostic accuracies about 80%. Moreover, in agreement with previous neuroanatomy findings, QSE has also revealed notable differences for all the brain regions in the neural activation triggered by the two considered emotions. Consequently, given these results, as well as easy interpretation of QSE, this work opens a new standpoint in the detection of emotional distress, which may gain new insights about the brain’s behavior under this negative emotion.

This paper introduces a software framework denominated ARISTARKO. ARISTARKO has been designed and developed to integrate the data acquisition from a wearable physiological data acquisition device with any necessary processing layers in order to classify the acquired signals into a predefined set of emotional states. In this particular article, we use ARISTARKO for the sake of designing an experiment capable of showing a series of images from the well-known IAPS database. The IAPS pictures are labelled with arousal, valence and dominance values. Arousal is classified from the information contained in the database and the physiological signals acquired by the wearable, namely electro-dermal, electrocardiogram and superficial electromyogram activity, and skin temperature.

This paper introduces a software program to recognise discrete emotions on an ageing adult from his/her physiological and psychological responses. This research considers the capacity from an audiovisual method to evoke different emotions and uses it to interpret and modulate basic emotion states. Different body sensors, in the case of physiological response, and a set of questionnaires, in the case of psychological responses, are selected to measure the power in causing fear, anger, disgust, sadness, amusement, affection and the neutral state, through a set of films used as an emotional induction method. The initial results suggest that it is possible to extract discrete values about positive and negative emotional states with films and to use these responses as keys to get emotion regulation.

Nowadays, assistive technologies together with ubiquitous and pervasive computing are emerging as main alternative to help ageing population. In this respect, an important number of works have been carried out to improve the quality of life in elderly from a physical point of view. However, less efforts have been made in monitoring the mental and emotional states of the elderly. This work presents a non-linear model for discriminating different arousal levels through quadratic entropy and a decision tree-based algorithm. Two hundred and seventy eight EEG recordings lasting one minute each were used to train the proposed model. The recordings belong to the Dataset for Emotion Analysis using Physiological signals (DEAP). In agreement with the complexity and variability observed in other works, our results report a low quadratic entropy when subjects face high arousal stimuli. Finally, the model achieves a global performance around 70 % when discriminating between calm and excitement events.

Ambient intelligence is a suitable paradigm for developing daily life solutions including the health care domain. Many ageing adults who decide to live alone at home need constant monitoring to control their health status and quality of life. This paper introduces the description of a wearable device capable of acquiring the electrodermal activity (EDA) in order to obtain information on the arousal level of the elderly. The lightweight wearable device is placed in the wrist of the ageing adult to allow continuous monitoring of EDA signals. With the aim of triggering changes in the emotional state of the ageing adult, fifty pictures from the International Affective Picture System are used to assess the electronic device through a series of experiments. The initial results show that the overall system classifies people into two classes: calmed and stressed patients. The results show that through measuring the EDA events’ magnitudes, the ageing adults’ arousal level is classified with a global accuracy higher than 80 %.

The increasing life expectancy is causing a fast ageing population around the globe, which is raising the demand on assistive systems based on ambient intelligence. While numerous papers have focused on the physical aspects in elderly, only a few works have attempted to regulate their emotional state. In this work, a new approach for monitoring and detecting the emotional state in elderly is presented. First, different physiological signals are acquired by means of wearable sensors, and data are transmitted to the embedded system. Next, noise and artifacts are removed by applying different signal processing techniques, depending on the signal behavior. Finally, several temporal and statistical markers are extracted and used to feed the classification model. In this very first version, a logistic regression model is used to detect two possible emotional states. In order to calibrate the model and adjust the boundary decision, twenty volunteers have agreed to be monitored and recorded to train the model. Finally, a decision maker regulates the environment, acting directly upon the elderly’s emotional state.

This paper introduces a distributed multiagent system architecture for multimodal emotion identification, which is based on simultaneous analysis of physiological parameters from wearable devices, human behaviors and activities, and facial micro-expressions. Wearable devices are equipped with electrodermal activity, electrocardiogram, heart rate, and skin temperature sensor agents. Facial expressions are monitored by a vision agent installed at the height of the human’s head. Also, the activity of the user is monitored by a second vision agent mounted overhead. The emotion is refined as a cooperative decision taken at a central agent node denominated “Central Emotion Detection Node” from the local decision offered by the three agent nodes called “Face Expression Analysis Node”, “Behavior Analysis Node” and “Physiological Data Analysis Node”. This way, the emotion identification results are outperformed through an intelligent fuzzy-based decision making technique.

In this chapter, we describe our work on the design of an auto-managed system for the tracking and location of products in transportation routes, called Transportation Monitoring System (TMSystem). Manufacturers, retailers and customers require tracking of goods in production and distribution lines. Automatic Vehicle Location (AVL) Systems are being introduced in many cities around the world. These systems are aimed for cost reduction purposes, and also provide optimization of time and resources. Companies usually control the quality of their production during the manufacturing phase, but products can also be controlled along the distribution and transportation phases, before they are delivered to customers. When controlling all the phases, including also the location of the transport, a large amount of data (Big Data) will be generated, and should be processed in order to get useful information, and so all the resources in the company are optimized. A four-layer system is proposed in order to provide an efficient solution for the Real-Time Monitoring (RTM) of goods. Two Web Services are proposed, Location Web Service and Check Order Web Service, so that customers can easily access information about the shipment of their orders. Finally, a Web Application is developed to access those Web Services.

In this paper we summarize our work on the design of an auto-managed system for the tracking and location of products in transportation routes. Manufacturers, retailers and customers require tracking of goods in production and distribution lines. Companies usually control the quality of their production during the manufacturing phase, but products can also be controlled along the distribution and transportation phases, before they are delivered to customers. A service-oriented four-layer system is proposed in order to provide an efficient solution for the Real-Time Monitoring (RTM) of goods. Several Web Services are defined, so that customers can easily access information about the shipment of their orders. Finally, a sample Web Application is developed to access those Web Services.

This paper summarizes our work on the design and implementation of a RFID-based system for the tracking and location of objects, and urban transport routes as a particular case. The data retrieved from the RFID readers can be associated with the data stored in a database, so we propose the development of a Web environment to gather information through any web browser. The architectural model is based on Fosstrak EPCISRepository, as it is an open source RFID software platform that implements the EPC Network specifications and it has been certified by EPCGlobal. We have developed a WebServiceapplication for location of the bus stops and lines on the route map, as a particular case of the tracking system, and the time left for the bus to arrive to a specific stop is also indicated on the graphical interface.

The development of prefabricated facades, using architectural concrete panels or GRC panels, starts by cutting facade maps included in the architectural project. The aim of the architectural department is creating a design of the panels, taking care about the viability in terms of dimensions, weight, location, etc, and also looking at the cost of the execution. With this aim we develop an ad-hoc tool to automate the process. The software, based in AutoCAD, allows the architect to obtain the maps for the final panels and its locations using a graphical interface. The interface prompts the user for all the geometry of the facade selecting it from the drawing or creating it at the moment, including: frameworks, pillars, structural lines, design lines, expansion joints and no paneled areas (windows, doors, etc.). These will be the input data for the cutting algorithm that defines the geometry of each panel. To run the cutting process, the architect must input some parameters about the panels, such as maximum size, type, etc. The algorithm divides the surface of the facade into the smallest units that can be considered and generates the micro-panels layer. By using these micro-panels, the algorithm decides which ones should be together to conform the final panel planning, attending some criteria: viability to fix the panel to the structure, weight, dimensions, total number of panels, number of similar panels, etc. When this process is finished the interface shows a detailed resume of the costs, as well as the panel’s drawings.

Blind Source Separation (BSS) has been probed as one of the most effective techniques for atrial activity (AA) extraction in supraventricular tachyarrhythmia episodes like atrial fibrillation (AF). In these situations, a wavelet transform denoising stage can improve the extraction quality with low computational cost. Each ECG lead is processed to obtain its representation in the wavelet domain where the BSS systems improve their performance. The comparison of spectral parameters (main peak and power spectral density concentration) and statistics values (kurtosis) proves that the sparse decomposition in the wavelet domain of the observed mixtures reduces Gaussian contamination of these signals, speeds up the convergence and increase the quality of the extracted signal. The easy and fast implementation, robustness and efficiency are some of the main advantages of this technique making possible the application in real time systems as a support tool to clinical diagnostics.

Tracking of goods in production and distribution lines is required by manufacturers, retailers, and customers, as well. Companies usually control the quality of their production in the manufacturing phase, but products can also be controlled along the distribution and transportation steps, before they are delivered to customers. The main objective of the project described on this paper is to develop a tracking system for architectural concrete panels. The system should enable the traceability, both downstream, allowing to know the origin of the panels and which processes were followed for any panel installed in a building, and upstream, so it is possible to further analyze the processes followed by the panel to be installed, including distribution and transportation. Therefore, the planning can be performed for optimizing processes and resources, and achieving an appropriate distribution of the timing, costs, etc. An auto managed three-level based RFID system is proposed in this paper in order to provide an efficient solution for the real-time monitoring (RTMS) of special loads, such as architectural concrete. The solution has been implemented by means of RFID passive and active tags and wirelessly communicated readers, corresponding to three levels of the supply chain. In the highest level, a wireless network connecting all the readers based on ZigBee technology has been implemented. This network is also connected to a GPRS system. Thereby, the main advantage of the proposed system is its ability to provide real-time localization of products (RTLS) all over the world.