Search

Emotion recognition through speech is a technique employed in various scenarios of Human-Computer Interaction (HCI). Existing approaches have achieved significant results; however, limitations persist, with the quantity and diversity of data being more notable when deep learning techniques are used. The lack of a standard in feature selection leads to continuous development and experimentation. Choosing and designing the appropriate network architecture constitutes another challenge. This study addresses the challenge of recognizing emotions in the human voice using deep learning techniques, proposing a comprehensive approach, and developing preprocessing and feature selection stages while constructing a dataset called EmoDSc as a result of combining several available databases. The synergy between spectral features and spectrogram images is investigated. Independently, the weighted accuracy obtained using only spectral features was 89%, while using only spectrogram images, the weighted accuracy reached 90%. These results, although surpassing previous research, highlight the strengths and limitations when operating in isolation. Based on this exploration, a neural network architecture composed of a CNN1D, a CNN2D, and an MLP that fuses spectral features and spectogram images is proposed. The model, supported by the unified dataset EmoDSc, demonstrates a remarkable accuracy of 96%.

Door access control systems are important to protect the security and integrity of physical spaces. Accuracy and speed are important factors that govern their performance. In this paper, we investigate a novel approach to identify users by measuring patterns of their interactions with a doorknob via an embedded accelerometer and gyroscope and by applying deep-learning-based algorithms to these measurements. Our identification results obtained from 47 users show an accuracy of 90.2%. When the sex of the user is used as an input feature, the accuracy is 89.8% in the case of male individuals and 97.0% in the case of female individuals. We study how the accuracy is affected by the sample duration, finding that is its possible to identify users using a sample of 0.5 s with an accuracy of 68.5%. Our results demonstrate the feasibility of using patterns of motor activity to provide access control, thus extending with it the set of alternatives to be considered for behavioral biometrics.

Heart failure is a severe medical condition with an important worldwide incidence that occurs when the heart is unable to efficiently pump the patient's blood throughout the body. The monitoring of edema in the lower limbs is one of the most efficient ways to control the evolution of the condition. Impedance spectroscopy has been proposed as an efficient technique to monitor body volume in patients with heart failure. It is necessary to research new wearable devices for remote patient monitoring, which can be easily worn by patients in a continuous way. In this work, we design and implement new wearable textile electrodes for the monitoring of edema evolution in patients with heart failure. Impedance spectroscopy measurements were carried out in 5 healthy controls and 2 patients with heart failure using our wearable electrodes for 3 days. The results show the appropriateness of impedance spectroscopy and our wearable electrodes to monitor body volume evolution. Impedance spectroscopy is shown to be an efficient marker of the presence of edema in heart failure patients. Initial patient positive feedback was obtained for the use of the wearable device.

In this paper, we introduce LagunAR, a mobile outdoor Augmented Reality (AR) application for providing heritage information and 3D visualization on a city scale. The LagunAR application was developed to provide historical information about the city of La Laguna in the XVI century, when it was the main city in the Canary Islands. The application provides a reconstructed 3D model of the city at that time that is shown on a mobile phone over-imposed on the actual city using geolocation. The geolocated position is used also for providing information of several points of interest in the city. The paper describes the design and implementation of the application and details the optimization techniques that have been used to manage the full information of the city using a mobile phone as a sensor and visualization tool. We explain the application usability study carried out using a heuristic test; in addition it is probed by users in a qualitative user test developed as preliminary research. Results show that it is possible to develop a real-time application that shows the user a city-scale 3D model and also manages the information of the points of interest.

Monkeypox is a smallpox-like disease that was declared a global health emergency in July 2022. Because of this resemblance, it is not easy to distinguish a monkeypox rash from other similar diseases; however, due to the novelty of this disease, there are no widely used databases for this purpose with which to develop image-based classification algorithms. Therefore, three significant contributions are proposed in this work: first, the development of a publicly available dataset of monkeypox images; second, the development of a classification system based on convolutional neural networks in order to automatically distinguish monkeypox marks from those produced by other diseases; and, finally, the use of explainable AI tools for ensemble networks. For point 1, free images of monkeypox cases and other diseases have been searched in government databases and processed until we are left with only a section of the skin of the patients in each case. For point 2, various pre-trained models were used as classifiers and, in the second instance, combinations of these were used to form ensembles. And, for point 3, this is the first documented time that an explainable AI technique (like GradCAM) is applied to the results of ensemble networks. Among all the tests, the accuracy reaches 93% in the case of single pre-trained networks, and up to 98% using an ensemble of three networks (ResNet50, EfficientNetB0, and MobileNetV2). Comparing these results with previous work, a substantial improvement in classification accuracy is observed.

Multimodal emotion recognition implies the use of different resources and techniques for identifying and recognizing human emotions. A variety of data sources such as faces, speeches, voices, texts and others have to be processed simultaneously for this recognition task. However, most of the techniques, which are based mainly on Deep Learning, are trained using datasets designed and built in controlled conditions, making their applicability in real contexts with real conditions more difficult. For this reason, the aim of this work is to assess a set of in-the-wild datasets to show their strengths and weaknesses for multimodal emotion recognition. Four in-the-wild datasets are evaluated: AFEW, SFEW, MELD and AffWild2. A multimodal architecture previously designed is used to perform the evaluation and classical metrics such as accuracy and F1-Score are used to measure performance in training and to validate quantitative results. However, strengths and weaknesses of these datasets for various uses indicate that by themselves they are not appropriate for multimodal recognition due to their original purpose, e.g., face or speech recognition. Therefore, we recommend a combination of multiple datasets in order to obtain better results when new samples are being processed and a good balance in the number of samples by class.

Currently, in many data landscapes, the information is distributed across various sources and presented in diverse formats. This fragmentation can pose a significant challenge to the efficient application of analytical methods. In this sense, distributed data mining is mainly based on clustering or classification techniques, which are easier to implement in distributed environments. However, the solution to some problems is based on the usage of mathematical equations or stochastic models, which are more difficult to implement in distributed environments. Usually, these types of problems need to centralize the required information, and then a modelling technique is applied. In some environments, this centralization may cause an overloading of the communication channels due to massive data transmission and may also cause privacy issues when sending sensitive data. To mitigate this problem, this paper describes a general-purpose distributed analytic platform based on edge computing for distributed networks. Through the distributed analytical engine (DAE), the calculation process of the expressions (that requires data from diverse sources) is decomposed and distributed between the existing nodes, and this allows sending partial results without exchanging the original information. In this way, the master node ultimately obtains the result of the expressions. The proposed solution is examined using three different computational intelligence algorithms, i.e., genetic algorithm, genetic algorithm with evolution control, and particle swarm optimization, to decompose the expression to be calculated and to distribute the calculation tasks between the existing nodes. This engine has been successfully applied in a case study focused on the calculation of key performance indicators of a smart grid, achieving a reduction in the number of communication messages by more than 91% compared to the traditional approach.

Motivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current "smart everything" scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specific mechanisms for enabling a collaborative inference across edge devices towards the in situ execution of highly complex state-of-the-art deep neural networks (DNNs), despite the resource-constrained nature of such infrastructures. In particular, the review discusses the most salient approaches conceived along those lines, elaborating on the specificities of the partitioning schemes and the parallelism paradigms explored, providing an organized and schematic discussion of the underlying workflows and associated communication patterns, as well as the architectural aspects of the DNNs that have driven the design of such techniques, while also highlighting both the primary challenges encountered at the design and operational levels and the specific adjustments or enhancements explored in response to them.

In the last decade, a large amount of data from vehicle location sensors has been generated due to the massification of GPS systems to track them. This is because these sensors usually include multiple variables such as position, speed, angular position of the vehicle, etc., and, furthermore, they are also usually recorded in very short time intervals. On the other hand, routes are often generated so that they do not correspond to reality, due to artifacts such as buildings, bridges, or sensor failures and where, due to the large amount of data, visual analysis of human expert is unable to detect genuinely anomalous routes. The presence of such abnormalities can lead to faulty sensors being detected which may allow sensor replacement to reliably track the vehicle. However, given the reliability of the available sensors, there are very few examples of such anomalies, which can make it difficult to apply supervised learning techniques. In this work we propose the use of unsupervised deep neural network models based on stacked autoencoders to detect anomalous routes in vehicles within Santiago de Chile. The results show that the proposed model is capable of effectively detecting anomalous paths in real data considering validation given by an expert user, reaching a performance of 82.1% on average. As future work, we propose to incorporate the use of Long Short-Term Memory (LSTM) and attention-based networks in order to improve the detection of anomalous trajectories.

Nowadays, the study of the gait by analyzing the distribution of plantar pressure is a well-established technique. The use of intelligent insoles allows real-time monitoring of the user. Thus, collecting and analyzing information is a more accurate process than consultations in so-called gait laboratories. Most of the previous published studies consider the composition and operation of these insoles based on resistive sensors. However, the use of capacitive sensors could provide better results, in terms of linear behavior under the pressure exerted. This behavior depends on the properties of the dielectric used. In this work, the design and implementation of an intelligent plantar insole composed of capacitive sensors is proposed. The dielectric used is a polydimethylsiloxane (PDMS)-based composition. The sensorized plantar insole developed achieves its purpose as a tool for collecting pressure in different areas of the sole of the foot. The fundamentals and details of the composition, manufacture, and implementation of the insole and the system used to collect data, as well as the data samples, are shown. Finally, a comparison of the behavior of both insoles, resistive and capacitive sensor-equipped, is made. The prototype presented lays the foundation for the development of a tool to support the diagnosis of gait abnormalities.

In this work, a novel Window Score Fusion post-processing technique for biometric gait recognition is proposed and successfully tested. We show that the use of this technique allows recognition rates to be greatly improved, independently of the configuration for the previous stages of the system. For this, a strict biometric evaluation protocol has been followed, using a biometric database composed of data acquired from 38 subjects by means of a commercial smartwatch in two different sessions. A cross-session test (where training and testing data were acquired in different days) was performed. Following the state of the art, the proposal was tested with different configurations in the acquisition, pre-processing, feature extraction and classification stages, achieving improvements in all of the scenarios; improvements of 100% (0% error) were even reached in some cases. This shows the advantages of including the proposed technique, whatever the system.

A key factor for successfully implementing gamified learning platforms is making students interact with the system from multiple digital platforms. Learning platforms that try to accomplish all their objectives by concentrating all the interactions from users with them are less effective than initially believed. Conversational bots are ideal solutions for cross-platform user interaction. In this paper, an open student-player model is presented. The model includes the use of machine learning techniques for online adaptation. Then, an architecture for the solution is described, including the open model. Finally, the chatbot design is addressed. The chatbot architecture ensures that its reactive nature fits into our defined architecture. The approach's implementation and validation aim to create a tool to encourage kids to practice multiplication tables playfully.

This paper proposes a novel method for the calibration of a stereo camera system used to reconstruct 3D scenes. An error in the pitch angle of the cameras causes the reconstructed scene to exhibit some distortion with respect to the real scene. To do the calibration procedure, whose purpose is to eliminate or at least minimize said distortion, machine learning techniques have been used, and more specifically, regression algorithms. These algorithms are trained with a large number of vectors of input features with their respective outputs, since, in view of the application of the procedure proposed, it is important that the training set be sufficiently representative of the variety that can occur in a real scene, which includes the different orientations that the pitch angle can take, the error in said angle and the effect that all this has on the reconstruction process. The most efficient regression algorithms for estimating the error in the pitch angle are derived from decision trees and certain neural network configurations. Once estimated, the error can be corrected, thus making the reconstructed scene appear more like the real one. Although the authors base their method on U-V disparity and employ this same technique to completely reconstruct the 3D scene, one of the most interesting features of the method proposed is that it can be applied regardless of the technique used to carry out said reconstruction.

Power-quality events and operation transients in power systems (PS) with isolated neutral can saturate inductive voltage transformers (IVT), which, when interacting with the overhead and underground cable capacitances, can cause ferroresonance events in the local PS. This abnormal operating mode can partially or totally damage the transformers and switchgears within the affected PS. Distribution system operators (DSO) can minimize these effects by detecting ferroresonance events accurately and fast enough and changing the mode of operation accordingly. Direct detection methods, i.e., based on voltage measurements, are reliable, but the massive deployment of this solution is relatively expensive; i.e., power quality analyzers cost thousands of USD. Alternatively, indirect detection methods are also available, e.g., IVT vibration measurements with accelerometers costing hundreds of USD, but their reliability depends on the installation method used. This manuscript proposes using the acoustic noise caused by magnetostriction forces within the IVT core during ferroresonance events to detect their occurrence. Compared to other indirect methods, electret condenser microphones with preamplifying stage cost less than USD 10 and are less sensitive to the installation procedure. The proposed method is validated experimentally, and its performance compared to IVT vibration measurements one by using the same detection methodology.

The tracking problem (that is, how to follow a previously memorized path) is one of the most important problems in mobile robots. Several methods can be formulated depending on the way the robot state is related to the path. "Trajectory tracking" is the most common method, with the controller aiming to move the robot toward a moving target point, like in a real-time servosystem. In the case of complex systems or systems under perturbations or unmodeled effects, such as UAVs (Unmanned Aerial Vehicles), other tracking methods can offer additional benefits. In this paper, methods that consider the dynamics of the path's descriptor parameter (which can be called "error adaptive tracking") are contrasted with trajectory tracking. A formal description of tracking methods is first presented, showing that two types of error adaptive tracking can be used with the same controller in any system. Then, it is shown that the selection of an appropriate tracking rate improves error convergence and robustness for a UAV system, which is illustrated by simulation experiments. It is concluded that error adaptive tracking methods outperform trajectory tracking ones, producing a faster and more robust convergence tracking, while preserving, if required, the same tracking rate when convergence is achieved.

With the growing need to obtain information about power consumption in buildings, it is necessary to investigate how to collect, store, and visualize such information using low-cost solutions. Currently, the available building management solutions are expensive and challenging to support small and medium-sized buildings. Unfortunately, not all buildings are intelligent, making it difficult to obtain such data from energy measurement devices and appliances or access such information. The internet of things (IoT) opens new opportunities to support real-time monitoring and control to achieve future smart buildings. This work proposes an IoT platform for remote monitoring and control of smart buildings, which consists of four-layer architecture: power layer, data acquisition layer, communication network layer, and application layer. The proposed platform allows data collection for energy consumption, data storage, and visualization. Various sensor nodes and measurement devices are considered to collect information on energy use from different building spaces. The proposed solution has been designed, implemented, and tested on a university campus considering three scenarios: an office, a classroom, and a laboratory. This work provides a guideline for future implementation of intelligent buildings using low-cost open-source solutions to enable building automation, minimize power consumption costs, and guarantee end-user comfort., Competing Interests: The authors declare no conflict of interest.

The population is aging worldwide, creating new challenges to the quality of life of older adults and their families. Falls are an increasing, but not inevitable, threat to older adults. Information technologies provide several solutions to address falls, but smart homes and the most available solutions require expensive and invasive infrastructures. In this study, we propose a novel approach to classify and detect falls of older adults in their homes through low-resolution infrared sensors that are affordable, non-intrusive, do not disturb privacy, and are more acceptable to older adults. Using data collected between 2019 and 2020 with the eHomeseniors platform, we determine activity scores of older adults moving across two rooms in a house and represent an older adult fall through skeletonization. We find that our twofold approach effectively detects activity patterns and precisely identifies falls. Our study provides insights to physicians about the daily activities of their older adults and could potentially help them make decisions in case of abnormal behavior.

Pressure injuries are wounds caused by reduced blood circulation for regular and repetitive periods when pressing the human body against a hard surface. It is a pathology that needs daily preventive care and health promotion to avoid incidences. Thus, this article aims to validate a platform based on the gamified collaborative practices model to prevent pressure injuries. The methodological contribution is Design Science, and the software was evaluated by 16 wheelchair users who aimed at usability (SUS), user experience (UEQ), and ability to promote the system (NPS). In addition to creating a collaborative network using the interactions that occurred during the platform's use. Wheelchair users rated 73.28 for SUS; on the UEQ benchmark scales, they classified: excellent (efficiency, dependability, stimulation, and novelty), good (attractiveness), and above-average (perspicuity) and in NPS obtained 62.5%. Moreover, they provided feedback to improve and legitimize that gamification positively interfered in the execution of collaborative practices. In the end, it is possible to suppose that the prototype contributes to the prevention of pressure injuries. In addition, it is possible to adapt it to apply to other pathologies that require continuous health care such as diabetes, mental illness, heart disease, addictions, multiple sclerosis, cancer, among others, maximizing its purpose.

In this research, a compact electronic nose (e-nose) based on a shear horizontal surface acoustic wave (SH-SAW) sensor array is proposed for the NO 2 detection, classification and discrimination among some of the most relevant surrounding toxic chemicals, such as carbon monoxide (CO), ammonia (NH 3 ), benzene (C 6 H 6 ) and acetone (C 3 H 6 O). Carbon-based nanostructured materials (CBNm), such as mesoporous carbon (MC), reduced graphene oxide (rGO), graphene oxide (GO) and polydopamine/reduced graphene oxide (PDA/rGO) are deposited as a sensitive layer with controlled spray and Langmuir-Blodgett techniques. We show the potential of the mass loading and elastic effects of the CBNm to enhance the detection, the classification and the discrimination of NO 2 among different gases by using Machine Learning (ML) techniques (e.g., PCA, LDA and KNN). The small dimensions and low cost make this analytical system a promising candidate for the on-site discrimination of sub-ppm NO 2 .

U-V disparity is a technique that is commonly used to detect obstacles in 3D scenes, modeling them as a set of vertical planes. In this paper, the authors describe the general lines of a method based on this technique for fully reconstructing 3D scenes, and conduct an analytical study of its performance and sensitivity to errors in the pitch angle of the stereoscopic vision system. The equations of the planes calculated for a given error in this angle yield the deviation with respect to the ideal planes (with a zero error in the angle) for a large test set consisting of planes with different orientations, which is represented graphically to analyze the method's qualitative and quantitative performance. The relationship between the deviation of the planes and the error in the pitch angle is observed to be linear. Two major conclusions are drawn from this study: first, that the deviation between the calculated and ideal planes is always less than or equal to the error considered in the pitch angle; and second, that even though in some cases the deviation of the plane is zero or very small, the probability that a plane of the scene deviates from the ideal by the greatest amount possible, which matches the error in the pitch angle, is very high.

This work studies the propagation characteristics of a rectangular waveguide with aligned/misaligned double-sided dielectric-filled metallic corrugations. Two modes are found to propagate in the proposed double-sided configuration below the hollow-waveguide cutoff frequency: a quasi-resonant mode and a backward mode. This is in contrast to the single-sided configuration, which only allows for backward propagation. Moreover, the double-sided configuration can be of interest for waveguide miniaturization on account of the broader band of its backward mode. The width of the stopband between the quasi-resonant and backward modes can be controlled by the misalignment of the top and bottom corrugations, being null for the glide-symmetric case. The previous study is complemented with numerical results showing the impact of the height of the corrugations, as well as the filling dielectric permittivity, on the bandwidth and location of the appearing negative-effective-permeability band. The multi-modal transmission-matrix method has also been employed to estimate the rejection level and material losses in the structure and to determine which port modes are associated with the quasi-resonant and backward modes. Finally, it is shown that glide symmetry can advantageously be used to reduce the dispersion and broadens the operating band of the modes.

Agile development processes are increasing their consideration of usability by integrating various user-centered design techniques throughout development. One such technique is Personas, which proposes the creation of fictitious users with real preferences to drive application design. Since applying this technique conflicts with the time constraints of agile development, Personas has been adapted over the years. Our objective is to determine the adoption level and type of integration, as well as to propose improvements to the Personas technique for agile development. A systematic mapping study was performed, retrieving 28 articles grouped by agile methodology type. We found some common integration strategies regardless of the specific agile approach, along with some frequent problems, mainly related to Persona modelling and context representation. Based on these limitations, we propose an adaptation to the technique in order to reduce the creation time for a preliminary persona. The number of publications dealing with Personas and agile development is increasing, which reveals a growing interest in the application of this technique to develop usable agile software.

The change from face-to-face work to teleworking caused by the pandemic has induced multiple workers to spend more time than usual in front of a computer; in addition, the sudden installation of workstations in homes means that not all of them meet the necessary characteristics for the worker to be able to position himself/herself comfortably with the correct posture in front of their computer. Furthermore, from the point of view of the medical personnel in charge of occupational risk prevention, an automated tool able to quantify the degree of incorrectness of a postural habit in a worker is needed. For this purpose, in this work, a system based on the postural detection of the worker is designed, implemented and tested, using a specialized hardware system that processes video in real time through convolutional neural networks. This system is capable of detecting the posture of the neck, shoulders and arms, providing recommendations to the worker in order to prevent possible health problems, due to poor posture. The results of the proposed system show that this video processing can be carried out in real time (up to 25 processed frames/sec) with a low power consumption (less than 10 watts) using specialized hardware, obtaining an accuracy of over 80% in terms of the pattern detected.

To achieve optimal mobility, visually impaired people have to deal with obstacle detection and avoidance challenges. Aside from the broadly adopted white cane, electronic aids have been developed. However, available electronic devices are not extensively used due to their complexity and price. As an effort to improve the existing ones, this work presents the design of a low-cost aid for blind people. A standard low-cost HC-SRF04 ultrasonic range is modified by adding phase modulation in the ultrasonic pulses, allowing it to detect the origin of emission, thus discriminating if the echo pulses come from the same device and avoiding false echoes due to interference from other sources. This improves accuracy and security in areas where different ultrasonic sensors are working simultaneously. The final device, based on users and trainers feedback for the design, works with the user's own mobile phone, easing utilization and lowering manufacturing costs. The device was tested with a set of twenty blind persons carrying out a travel experiment and satisfaction survey. The main results showed a change in total involuntary contacts with unknown obstacles and high user satisfaction. Hence, we conclude that the device can fill a gap in the mobility aids and reduce feelings of insecurity amongst the blind.

State-of-the-art scenarios, such as Internet of Things (IoT) and Smart Cities, have recently arisen. They involve the processing of huge data sets under strict time requirements, rendering the use of cloud resources unfeasible. For this reason, Fog computing has been proposed as a solution; however, there remains a need for intelligent allocation decisions, in order to make it a fully usable solution in such contexts. In this paper, a network-aware scheduling algorithm is presented, which aims to select the fog node most suitable for the execution of an application within a given deadline. This decision is made taking the status of the network into account. This scheduling algorithm was implemented as an extension to the Kubernetes default scheduler, and compared with existing proposals in the literature. The comparison shows that our proposal is the only one that can execute all the submitted jobs within their deadlines (i.e., no job is rejected or executed exceeding its deadline) with certain configurations in some of the scenarios tested, thus obtaining an optimal solution in such scenarios.

Monitoring animals' behavior living in wild or semi-wild environments is a very interesting subject for biologists who work with them. The difficulty and cost of implanting electronic devices in this kind of animals suggest that these devices must be robust and have low power consumption to increase their battery life as much as possible. Designing a custom smart device that can detect multiple animal behaviors and that meets the mentioned restrictions presents a major challenge that is addressed in this work. We propose an edge-computing solution, which embeds an ANN in a microcontroller that collects data from an IMU sensor to detect three different horse gaits. All the computation is performed in the microcontroller to reduce the amount of data transmitted via wireless radio, since sending information is one of the most power-consuming tasks in this type of devices. Multiples ANNs were implemented and deployed in different microcontroller architectures in order to find the best balance between energy consumption and computing performance. The results show that the embedded networks obtain up to 97.96% ± 1.42% accuracy, achieving an energy efficiency of 450 Mops/s/watt.

This study aims to produce accurate predictions of the NO 2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO 2 from the station or employing NO 2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model's performance, especially for t + 4 ( ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 ( ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases.

Communicating in social and public environments are considered professional skills that can strongly influence career development. Therefore, it is important to proper train and evaluate students in this kind of abilities so that they can better interact in their professional relationships, during the resolution of problems, negotiations and conflict management. This is a complex problem as it involves corporal analysis and the assessment of aspects that until recently were almost impossible to quantitatively measure. Nowadays, a number of new technologies and sensors have being developed for the capture of different kinds of contextual and personal information, but these technologies were not yet fully integrated inside learning settings. In this context, this paper presents a framework to facilitate the analysis and detection of patterns of students in oral presentations. Four steps are proposed for the given framework: Data collection , Statistical Analysis , Clustering , and Sequential Pattern Mining . Data Collection step is responsible for the collection of students interactions during presentations and the arrangement of data for further analysis. Statistical Analysis provides a general understanding of the data collected by showing the differences and similarities of the presentations along the semester. The Clustering stage segments students into groups according to well-defined attributes helping to observe different corporal patterns of the students. Finally, Sequential Pattern Mining step complements the previous stages allowing the identification of sequential patterns of postures in the different groups. The framework was tested in a case study with data collected from 222 freshman students of Computer Engineering (CE) course at three different times during two different years. The analysis made it possible to segment the presenters into three distinct groups according to their corporal postures. The statistical analysis helped to assess how the postures of the students evolved throughout each year. The sequential pattern mining provided a complementary perspective for data evaluation and helped to observe the most frequent postural sequences of the students. Results show the framework could be used as a guidance to provide students automated feedback throughout their presentations and can serve as background information for future comparisons of students presentations from different undergraduate courses.

Prostate cancer (PCa) is the second most frequently diagnosed cancer among men worldwide, with almost 1.3 million new cases and 360,000 deaths in 2018. As it has been estimated, its mortality will double by 2040, mostly in countries with limited resources. These numbers suggest that recent trends in deep learning-based computer-aided diagnosis could play an important role, serving as screening methods for PCa detection. These algorithms have already been used with histopathological images in many works, in which authors tend to focus on achieving high accuracy results for classifying between malignant and normal cases. These results are commonly obtained by training very deep and complex convolutional neural networks, which require high computing power and resources not only in this process, but also in the inference step. As the number of cases rises in regions with limited resources, reducing prediction time becomes more important. In this work, we measured the performance of current state-of-the-art models for PCa detection with a novel benchmark and compared the results with PROMETEO, a custom architecture that we proposed. The results of the comprehensive comparison show that using dedicated models for specific applications could be of great importance in the future.

At present, sexual robots have become a new paradigm of social robots. In this paper, we developed a systematic literature review about sexual robots (sexbots). To do this, we used the Scopus and WoS databases to answer different research questions regarding the design, interaction, and gender and ethical approaches from 1980 until 2020. In our review, we found a male bias in this discipline, and in recent years, articles have shown that user opinion has become more relevant. Some insights and recommendations on gender and ethics in designing sexual robots were also made.

While technology has helped improve process efficiency in several domains, it still has an outstanding debt to education. In this article, we introduce NAIRA, a Multimodal Learning Analytics platform that provides Real-Time Feedback to foster collaborative learning activities' efficiency. NAIRA provides real-time visualizations for students' verbal interactions when working in groups, allowing teachers to perform precise interventions to ensure learning activities' correct execution. We present a case study with 24 undergraduate subjects performing a remote collaborative learning activity based on the Jigsaw learning technique within the COVID-19 pandemic context. The main goals of the study are (1) to qualitatively describe how the teacher used NAIRA's visualizations to perform interventions and (2) to identify quantitative differences in the number and time between students' spoken interactions among two different stages of the activity, one of them supported by NAIRA's visualizations. The case study showed that NAIRA allowed the teacher to monitor and facilitate the learning activity's supervised stage execution, even in a remote learning context, with students working in separate virtual classrooms with their video cameras off. The quantitative comparison of spoken interactions suggests the existence of differences in the distribution between the monitored and unmonitored stages of the activity, with a more homogeneous speaking time distribution in the NAIRA supported stage.

Physical rehabilitation therapies for children present a challenge, and its success-the improvement of the patient's condition-depends on many factors, such as the patient's attitude and motivation, the correct execution of the exercises prescribed by the specialist or his progressive recovery during the therapy. With the aim to increase the benefits of these therapies, social humanoid robots with a friendly aspect represent a promising tool not only to boost the interaction with the pediatric patient, but also to assist physicians in their work. To achieve both goals, it is essential to monitor in detail the patient's condition, trying to generate user profile models which enhance the feedback with both the system and the specialist. This paper describes how the project NAOTherapist-a robotic architecture for rehabilitation with social robots-has been upgraded in order to include a monitoring system able to generate user profile models through the interaction with the patient, performing user-adapted therapies. Furthermore, the system has been improved by integrating a machine learning algorithm which recognizes the pose adopted by the patient and by adding a clinical reports generation system based on the QUEST metric.

Porous titanium is a metallic biomaterial with good properties for the clinical repair of cortical bone tissue, although the presence of pores can compromise its mechanical behavior and clinical use. It is therefore necessary to characterize the implant pore size and distribution in a suitable way. In this work, we explore the new use of electrical impedance spectroscopy for the characterization and monitoring of titanium bone implants. Electrical impedance spectroscopy has been used as a non-invasive route to characterize the volumetric porosity percentage (30%, 40%, 50% and 60%) and the range of pore size (100-200 and 355-500 mm) of porous titanium samples obtained with the space-holder technique. Impedance spectroscopy is proved to be an appropriate technique to characterize the level of porosity of the titanium samples and pore size, in an affordable and non-invasive way. The technique could also be used in smart implants to detect changes in the service life of the material, such as the appearance of fractures, the adhesion of osteoblasts and bacteria, or the formation of bone tissue.

In tissue engineering, of utmost importance is the control of tissue formation, in order to form tissue constructs of clinical relevance. In this work, we present the use of an impedance spectroscopy technique for the real-time measurement of the dielectric properties of skeletal myoblast cell cultures. The processes involved in the growth and differentiation of these cell cultures in skeletal muscle are studied. A circuit based on the oscillation-based test technique was used, avoiding the use of high-performance circuitry or external input signals. The effect of electrical pulse stimulation applied to cell cultures was also studied. The technique proved useful for monitoring in real-time the processes of cell growth and estimating the fill factor of muscular stem cells. Impedance spectroscopy was also useful to study the real-time monitoring of cell differentiation, obtaining different oscillation amplitude levels for differentiated and undifferentiated cell cultures. Finally, an electrical model was implemented to better understand the physical properties of the cell culture and control the tissue formation process.

In physical Human-Robot Interaction (pHRI), forces exerted by humans need to be estimated to accommodate robot commands to human constraints, preferences, and needs. This paper presents a method for the estimation of the interaction forces between a human and a robot using a gripper with proprioceptive sensing. Specifically, we measure forces exerted by a human limb grabbed by an underactuated gripper in a frontal plane using only the gripper's own sensors. This is achieved via a regression method, trained with experimental data from the values of the phalanx angles and actuator signals. The proposed method is intended for adaptive shared control in limb manipulation. Although adding force sensors provides better performance, the results obtained are accurate enough for this application. This approach requires no additional hardware: it relies uniquely on the gripper motor feedback-current, position and torque-and joint angles. Also, it is computationally cheap, so processing times are low enough to allow continuous human-adapted pHRI for shared control.

Falls have become a relevant public health issue due to their high prevalence and negative effects in elderly people. Wearable fall detector devices allow the implementation of continuous and ubiquitous monitoring systems. The effectiveness for analyzing temporal signals with low energy consumption is one of the most relevant characteristics of these devices. Recurrent neural networks (RNNs) have demonstrated a great accuracy in some problems that require analyzing sequential inputs. However, getting appropriate response times in low power microcontrollers remains a difficult task due to their limited hardware resources. This work shows a feasibility study about using RNN-based deep learning models to detect both falls and falls' risks in real time using accelerometer signals. The effectiveness of four different architectures was analyzed using the SisFall dataset at different frequencies. The resulting models were integrated into two different embedded systems to analyze the execution times and changes in the model effectiveness. Finally, a study of power consumption was carried out. A sensitivity of 88.2% and a specificity of 96.4% was obtained. The simplest models reached inference times lower than 34 ms, which implies the capability to detect fall events in real-time with high energy efficiency. This suggests that RNN models provide an effective method that can be implemented in low power microcontrollers for the creation of autonomous wearable fall detection systems in real-time.

High-throughput data analysis challenges in laboratory automation and lab-on-a-chip devices' applications are continuously increasing. In cell culture monitoring, specifically, the electrical cell-substrate impedance sensing technique (ECIS), has been extensively used for a wide variety of applications. One of the main drawbacks of ECIS is the need for implementing complex electrical models to decode the electrical performance of the full system composed by the electrodes, medium, and cells. In this work we present a new approach for the analysis of data and the prediction of a specific biological parameter, the fill-factor of a cell culture, based on a polynomial regression, data-analytic model. The method was successfully applied to a specific ECIS circuit and two different cell cultures, N2A (a mouse neuroblastoma cell line) and myoblasts. The data-analytic modeling approach can be used in the decoding of electrical impedance measurements of different cell lines, provided a representative volume of data from the cell culture growth is available, sorting out the difficulties traditionally found in the implementation of electrical models. This can be of particular importance for the design of control algorithms for cell cultures in tissue engineering protocols, and labs-on-a-chip and wearable devices applications.

Speaking and presenting in public are critical skills for academic and professional development. These skills are demanded across society, and their development and evaluation are a challenge faced by higher education institutions. There are some challenges to evaluate objectively, as well as to generate valuable information to professors and appropriate feedback to students. In this paper, in order to understand and detect patterns in oral student presentations, we collected data from 222 Computer Engineering (CE) fresh students at three different times, over two different years (2017 and 2018). For each presentation, using a developed system and Microsoft Kinect, we have detected 12 features related to corporal postures and oral speaking. These features were used as input for the clustering and statistical analysis that allowed for identifying three different clusters in the presentations of both years, with stronger patterns in the presentations of the year 2017. A Wilcoxon rank-sum test allowed us to evaluate the evolution of the presentations attributes over each year and pointed out a convergence in terms of the reduction of the number of features statistically different between presentations given at the same course time. The results can further help to give students automatic feedback in terms of their postures and speech throughout the presentations and may serve as baseline information for future comparisons with presentations from students coming from different undergraduate courses.

Currently, the improvement of core skills appears as one of the most significant educational challenges of this century. However, assessing the development of such skills is still a challenge in real classroom environments. In this context, Multimodal Learning Analysis techniques appear as an attractive alternative to complement the development and evaluation of core skills. This article presents an exploratory study that analyzes the collaboration and communication of students in a Software Engineering course, who perform a learning activity simulating Scrum with Lego ® bricks. Data from the Scrum process was captured, and multidirectional microphones were used in the retrospective ceremonies. Social network analysis techniques were applied, and a correlational analysis was carried out with all the registered information. The results obtained allowed the detection of important relationships and characteristics of the collaborative and Non-Collaborative groups, with productivity, effort, and predominant personality styles in the groups. From all the above, we can conclude that the Multimodal Learning Analysis techniques offer considerable feasibilities to support the process of skills development in students., Competing Interests: The authors declare no conflict of interest.

The 2D point location problem has applications in several areas, such as geographic information systems, navigation systems, motion planning, mapping, military strategy, location and tracking moves. We aim to present a new approach that expands upon current techniques and methods to locate the 2D position of a signal source sent by an emitter device. This new approach is based only on the geometric relationship between an emitter device and a system composed of m≥2 signal receiving devices. Current approaches applied to locate an emitter can be deterministic, statistical or machine-learning methods. We propose to perform this triangulation by geometric models that exploit elements of pole-polar geometry. For this purpose, we are presenting five geometric models to solve the point location problem: (1) based on centroid of points of pole-polar geometry, PPC; (2) based on convex hull region among pole-points, CHC; (3) based on centroid of points obtained by polar-lines intersections, PLI; (4) based on centroid of points obtained by tangent lines intersections, TLI; (5) based on centroid of points obtained by tangent lines intersections with minimal angles, MAI. The first one has computational cost On and whereas has the computational cost Onlognwhere n is the number of points of interest., Competing Interests: The authors declare no conflict of interest. The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.

During the last decade, Wireless sensor networks (WSNs) have attracted interest due to the excellent monitoring capabilities offered. However, WSNs present shortcomings, such as energy cost and reliability, which hinder real-world applications. As a solution, Relay Node (RN) deployment strategies could help to improve WSNs. This fact is known as the Relay Node Placement Problem (RNPP), which is an NP-hard optimization problem. This paper proposes to address two Multi-Objective (MO) formulations of the RNPP. The first one optimizes average energy cost and average sensitivity area. The second one optimizes the two previous objectives and network reliability. The authors propose to solve the two problems through a wide range of MO metaheuristics from the three main groups in the field: evolutionary algorithms, swarm intelligence algorithms, and trajectory algorithms. These algorithms are the Non-dominated Sorting Genetic Algorithm II (NSGA-II), Strength Pareto Evolutionary Algorithm 2 (SPEA2), Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), Multi-Objective Artificial Bee Colony (MO-ABC), Multi-Objective Firefly Algorithm (MO-FA), Multi-Objective Gravitational Search Algorithm (MO-GSA), and Multi-Objective Variable Neighbourhood Search Algorithm (MO-VNS). The results obtained are statistically analysed to determine if there is a robust metaheuristic to be recommended for solving the RNPP independently of the number of objectives.

A smart sensor system for cell culture real-time supervision is proposed, allowing for a significant reduction in human effort applied to this type of assay. The approach converts the cell culture under test into a suitable "biological" oscillator. The system enables the remote acquisition and management of the "biological" oscillation signals through a secure web interface. The indirectly observed biological properties are cell growth and cell number, which are straightforwardly related to the measured bio-oscillation signal parameters, i.e., frequency and amplitude. The sensor extracts the information without complex circuitry for acquisition and measurement, taking advantage of the microcontroller features. A discrete prototype for sensing and remote monitoring is presented along with the experimental results obtained from the performed measurements, achieving the expected performance and outcomes.

The reduction in size, power consumption and price of many sensor devices has enabled the deployment of many sensor networks that can be used to monitor and control several aspects of various habitats. More specifically, the analysis of sounds has attracted a huge interest in urban and wildlife environments where the classification of the different signals has become a major issue. Various algorithms have been described for this purpose, a number of which frame the sound and classify these frames, while others take advantage of the sequential information embedded in a sound signal. In the paper, a new algorithm is proposed that, while maintaining the frame-classification advantages, adds a new phase that considers and classifies the score series derived after frame labelling. These score series are represented using cepstral coefficients and classified using standard machine-learning classifiers. The proposed algorithm has been applied to a dataset of anuran calls and its results compared to the performance obtained in previous experiments on sensor networks. The main outcome of our research is that the consideration of score series strongly outperforms other algorithms and attains outstanding performance despite the noisy background commonly encountered in this kind of application.

This paper proposes a new yet efficient method allowing a significant improvement in the on-line analysis of biological cell growing and evolution. The procedure is based on an empirical-mathematical approach for calibration and fitting of any cell-electrode electrical model. It is valid and can be extrapolated for any type of cellular line used in electrical cell-substrate impedance spectroscopy (ECIS) tests. Parameters of the bioimpedance model, acquired from ECIS experiments, vary for each cell line, which makes obtaining results difficult and-to some extent-renders them inaccurate. We propose a fitting method based on the cell line initial characterization, and carry out subsequent experiments with the same line to approach the percentage of well filling and the cell density (or cell number in the well). To perform our calibration technique, the so-called oscillation-based test (OBT) approach is employed for each cell density. Calibration results are validated by performing other experiments with different concentrations on the same cell line with the same measurement technique. Accordingly, a bioimpedance electrical model of each cell line is determined, which is valid for any further experiment and leading to a more precise electrical model of the electrode-cell system. Furthermore, the model parameters calculated can be also used by any other measurement techniques. Promising experimental outcomes for three different cell-lines have been achieved, supporting the usefulness of this technique.

The analysis and classification of the sounds produced by certain animal species, notably anurans, have revealed these amphibians to be a potentially strong indicator of temperature fluctuations and therefore of the existence of climate change. Environmental monitoring systems using Wireless Sensor Networks are therefore of interest to obtain indicators of global warming. For the automatic classification of the sounds recorded on such systems, the proper representation of the sound spectrum is essential since it contains the information required for cataloguing anuran calls. The present paper focuses on this process of feature extraction by exploring three alternatives: the standardized MPEG-7, the Filter Bank Energy (FBE), and the Mel Frequency Cepstral Coefficients (MFCC). Moreover, various values for every option in the extraction of spectrum features have been considered. Throughout the paper, it is shown that representing the frame spectrum with pure FBE offers slightly worse results than using the MPEG-7 features. This performance can easily be increased, however, by rescaling the FBE in a double dimension: vertically, by taking the logarithm of the energies; and, horizontally, by applying mel scaling in the filter banks. On the other hand, representing the spectrum in the cepstral domain, as in MFCC, has shown additional marginal improvements in classification performance., Competing Interests: The authors declare there to be no conflict of interest. The founding sponsors played no role: in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; and in the decision to publish the results.

A novel ecosystem to promote the physical, emotional and psychic health and well-being of the elderly is presented. Our proposal was designed to add several services developed to meet the needs of the senior population, namely services to improve social inclusion and increase contribution to society. Moreover, the solution monitors the vital signs of elderly individuals, as well as environmental parameters and behavior patterns, in order to seek eminent danger situations and predict potential hazardous issues, acting in accordance with the various alert levels specified for each individual. The platform was tested by seniors in a real scenario. The experimental results demonstrated that the proposed ecosystem was well accepted and is easy to use by seniors.

Applications involving data acquisition from sensors need samples at a preset frequency rate, the filtering out of noise and/or analysis of certain frequency components. We propose a novel software architecture based on open-software hardware platforms which allows programmers to create data streams from input channels and easily implement filters and frequency analysis objects. The performances of the different classes given in the size of memory allocated and execution time (number of clock cycles) were analyzed in the low-cost platform Arduino Genuino. In addition, 11 people took part in an experiment in which they had to implement several exercises and complete a usability test. Sampling rates under 250 Hz (typical for many biomedical applications) makes it feasible to implement filters, sliding windows and Fourier analysis, operating in real time. Participants rated software usability at 70.2 out of 100 and the ease of use when implementing several signal processing applications was rated at just over 4.4 out of 5. Participants showed their intention of using this software because it was percieved as useful and very easy to use. The performances of the library showed that it may be appropriate for implementing small biomedical real-time applications or for human movement monitoring, even in a simple open-source hardware device like Arduino Genuino. The general perception about this library is that it is easy to use and intuitive.

Crop monitoring is an essential practice within the field of precision agriculture since it is based on observing, measuring and properly responding to inter- and intra-field variability. In particular, "on ground crop inspection" potentially allows early detection of certain crop problems or precision treatment to be carried out simultaneously with pest detection. "On ground monitoring" is also of great interest for woody crops. This paper explores the development of a low-cost crop monitoring system that can automatically create accurate 3D models (clouds of coloured points) of woody crop rows. The system consists of a mobile platform that allows the easy acquisition of information in the field at an average speed of 3 km/h. The platform, among others, integrates an RGB-D sensor that provides RGB information as well as an array with the distances to the objects closest to the sensor. The RGB-D information plus the geographical positions of relevant points, such as the starting and the ending points of the row, allow the generation of a 3D reconstruction of a woody crop row in which all the points of the cloud have a geographical location as well as the RGB colour values. The proposed approach for the automatic 3D reconstruction is not limited by the size of the sampled space and includes a method for the removal of the drift that appears in the reconstruction of large crop rows., Competing Interests: The authors declare no conflict of interest.

This work studies the feasibility of using mental attention to access a computer. Brain activity was measured with an electrode placed at the Fp1 position and the reference on the left ear; seven normally developed people and three subjects with cerebral palsy (CP) took part in the experimentation. They were asked to keep their attention high and low for as long as possible during several trials. We recorded attention levels and power bands conveyed by the sensor, but only the first was used for feedback purposes. All of the information was statistically analyzed to find the most significant parameters and a classifier based on linear discriminant analysis (LDA) was also set up. In addition, 60% of the participants were potential users of this technology with an accuracy of over 70%. Including power bands in the classifier did not improve the accuracy in discriminating between the two attentional states. For most people, the best results were obtained by using only the attention indicator in classification. Tiredness was higher in the group with disabilities (2.7 in a scale of 3) than in the other (1.5 in the same scale); and modulating the attention to access a communication board requires that it does not contain many pictograms (between 4 and 7) on screen and has a scanning period of a relatively high t s c a n ≈ 10 s. The information transfer rate (ITR) is similar to the one obtained by other brain computer interfaces (BCI), like those based on sensorimotor rhythms (SMR) or slow cortical potentials (SCP), and makes it suitable as an eye-gaze independent BCI., Competing Interests: The authors declare no conflict of interest.