Search

[EN] A T-shaped slot-array antenna fed through a Groove Gap Waveguide (GGW) is presented in this paper. The array antenna operates at 30 GHz. The way the slots are excited, along with the T-shape on its lid allows a compact single-layer architecture. A uniform linear array of 12 elements is designed to demonstrate the viability of this concept for high-efficient singlelayer slot-array antennas. Preliminary results show a frequency bandwidth of 1 GHz with input reflection coefficient better than ¿12 dB. In addition, being a full-metal antenna, the expected efficiency is high. It is worth stressing the good polarization purity achieved, being below 1.5 dB within the band of interest.

[EN] This contribution presents a low-loss mechanical phase shifter in gap-waveguide technology. The phase shifter is aimed at ground terminals for Ka-band satellite on-the-move applications. The use of the gap-waveguide technology allows to divide the device into two main blocks distributed in two levels: a lower-rotatable block, in charge of the power distribution and the phase shifting; and an upper-fixed block with the output waveguides. In this paper, the lower and upper blocks are designed using Groove-gap waveguides (GGW), and Ridge-gap waveguides, respectively, connected to each other by coupling slots. Results show a good performance within the operating frequency band in terms of the phase shift between consecutive output ports (suitable for array feeding), and the return loss level at the input port.

[EN] In this paper, a new design of a reconfigurable antenna is proposed. The antenna structure is using two PIN diodes for switching between two radiation patterns (directional and bidirectional) and a SPDT switch to achieve good impedance matching. The simulated results show a good impedance matching, with S11 below -10 dB using the SPDT switch configuration. In addition, the far-field directivity for both configurations is around 5 dB.

[EN] A preliminary numerical magnetic field study of a wireless power transfer system composed of two interconnected source loops is addressed in this paper. The key feature of this study is to propose a new configuration capable of maintaining a uniform magnetic field density between the two loops. Furthermore, it has been shown that the Theory of Characteristic Modes is a helpful tool for investigating the near field of the magnetically-coupled loops.

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., [EN] The monitoring of water level in the agriculture irrigation channels is essential to control the opening gates of these channels. In this way, WSNs (Wireless Sensor Networks) have high relevance to obtain this kind of data. In this paper, we propose a sensor to measure the depth changes in irrigation channels to control the gates opening. It is connected to an Adafruit Feather HUZZAH based on ESP8266, which allows us to build a mobile edge computing system. The developed sensor is based on two coils. Sinus-wave powers the first one, and the second is induced. The coils are winding over a polyvinyl chloride (PVC) that has high resistance for corrosion and low price. Besides, we use copper wire as a conductive metal. We test two different configurations of coils. P1 has five spires for the powered coil (PC) and ten spires for the induced coil (IC). On the other hand, P2 has 40 spires for the PC and 80 spires for the IC. The two prototypes were coiled in one layer. Then, both sensors are tested using a glass bottle where the water column increased with the target to obtain the information of the depth. In both prototypes, the difference of voltage between the maximum and minimum studied depths is more or less the same, 4.46V for P1 and 4.44V for P2. Nevertheless, during the stabilization test, the P1 showed better adaptation for the turbulences than the P2. The P1 shows an oscillation of 0.48V, where the P2 has a maximum fluctuation of 3.2V.

[EN] A dual circularly-polarized slot-array antenna fed by a Groove Gap Waveguide (GGW) and operating in the KaBand is presented in this paper. A simple mechanism is proposed to switch the polarization, from RHCP to LHCP, and viceversa. The lid of the antenna has two pieces: one fixed and one sliding. The fixed piece hosts T-shaped slots, and the sliding block is in charge of adjusting the offset of the perpendicular grooves with respect to the longitudinal slots. Preliminary results show an axial ratio below 1.5 dB for both, RHCP and LHCP, within a bandwidth of 1 GHz centered at 30 GHz.

[EN] Independently of any electrical contact, running electronic devices such as smartphones, smart watches, RFID tags etc., is now attainable over small and large distances through Wireless Power Transfer technology. Although, designing systems maintaining appreciable power transfer efficiency still not always achievable. Using two parallel loops, the Theory of Characteristic Modes provides physical insight into the power transfer efficiency. Furthermore, to reach straightforward maximization of the modal power transfer efficiency, the focus of this paper is analyzing the impact of the separation distance and the overlapping between the two antennas on the characteristic modes and their contribution in the total efficiency of the power. The study considers different positions and frequencies of the two parallel antennas.

[EN] In this paper we present a new method to compute singular integrals and nearly singular integrals in the context of boundary integral equations for electromagnetism. In particular the method is well suited for integral equations of the second kind. The method consist of splitting the integral in two parts, one regular, which is computed via adaptive integration, and another singular and local (with very small support of the integrand) which is computed using asymptotic expansion. This method can be applied to any second kind integral equation arising in CEM, like MFIE, Charge-Current integral equation, Non Resonant Charge Current Integral Equation (NRCCIE),...

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., [EN] The monitoring of water level in the agriculture irrigation channels is essential to control the opening gates of these channels. In this way, WSNs (Wireless Sensor Networks) have high relevance to obtain this kind of data. In this paper, we propose a sensor to measure the depth changes in irrigation channels to control the gates opening. It is connected to an Adafruit Feather HUZZAH based on ESP8266, which allows us to build a mobile edge computing system. The developed sensor is based on two coils. Sinus-wave powers the first one, and the second is induced. The coils are winding over a polyvinyl chloride (PVC) that has high resistance for corrosion and low price. Besides, we use copper wire as a conductive metal. We test two different configurations of coils. P1 has five spires for the powered coil (PC) and ten spires for the induced coil (IC). On the other hand, P2 has 40 spires for the PC and 80 spires for the IC. The two prototypes were coiled in one layer. Then, both sensors are tested using a glass bottle where the water column increased with the target to obtain the information of the depth. In both prototypes, the difference of voltage between the maximum and minimum studied depths is more or less the same, 4.46V for P1 and 4.44V for P2. Nevertheless, during the stabilization test, the P1 showed better adaptation for the turbulences than the P2. The P1 shows an oscillation of 0.48V, where the P2 has a maximum fluctuation of 3.2V.

In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate.

In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate.

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, This paper describes experiences that combine digital peer production with digital ink affordances. Rather than preparing papers to obtain a summative final mark, students work over the course of the term producing different small learning resources such as short engineering problems, reasoning or synthesis where the lecturer acts as manager and supervisor. Teacher intervention is carried out using digital ink over each individual student production being possible to share the results throughout a public or group repository and in class offering a pro-active argument about preventing common mistakes. In order to enhance students programming skills important efforts are oriented to produce learning objects in the form of Java applets. It has the additional advantage of fostering collaborative knowledge construction because any object serves to the whole group as learning material as soon as it is already produced and validated. Qualitative and quantitative results show both an overall satisfaction from students participating in the experiences, and better results in the common written exams, when compared to the other groups following the traditional method.

The increasing interest of online learning is unquestionable nowadays, with MOOCs being taken by thousands of students. However, for online learning to go mainstream it is necessary that professors perceive that the effort required to prepare and manage an online course is manageable. Today, a myriad of inexpensive tools and services can be used to produce and manage online courses with unprecedented ease and without distressing the professor. For that, this paper proposes an architecture based on Cloud services that simplifies the process of managing an online course, from delivering on-demand fully customized remote laboratories to communication automation for student engagement and feedback gathering. This approach has been applied to produce, distribute and manage an Online Course on Cloud Computing with Amazon Web Services. The paper describes the methodology, tools and results of this experience to point out that it is possible to deliver online courses with automatically provisioned labs, with minimal management overhead, while still providing a high quality learning experience to a worldwide audience.

In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate.

The increasing interest of online learning is unquestionable nowadays, with MOOCs being taken by thousands of students. However, for online learning to go mainstream it is necessary that professors perceive that the effort required to prepare and manage an online course is manageable. Today, a myriad of inexpensive tools and services can be used to produce and manage online courses with unprecedented ease and without distressing the professor. For that, this paper proposes an architecture based on Cloud services that simplifies the process of managing an online course, from delivering on-demand fully customized remote laboratories to communication automation for student engagement and feedback gathering. This approach has been applied to produce, distribute and manage an Online Course on Cloud Computing with Amazon Web Services. The paper describes the methodology, tools and results of this experience to point out that it is possible to deliver online courses with automatically provisioned labs, with minimal management overhead, while still providing a high quality learning experience to a worldwide audience.

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, This paper describes experiences that combine digital peer production with digital ink affordances. Rather than preparing papers to obtain a summative final mark, students work over the course of the term producing different small learning resources such as short engineering problems, reasoning or synthesis where the lecturer acts as manager and supervisor. Teacher intervention is carried out using digital ink over each individual student production being possible to share the results throughout a public or group repository and in class offering a pro-active argument about preventing common mistakes. In order to enhance students programming skills important efforts are oriented to produce learning objects in the form of Java applets. It has the additional advantage of fostering collaborative knowledge construction because any object serves to the whole group as learning material as soon as it is already produced and validated. Qualitative and quantitative results show both an overall satisfaction from students participating in the experiences, and better results in the common written exams, when compared to the other groups following the traditional method.

[EN] Personal audio systems aim to create listening (or bright) and quiet (or dark) zones in a room using an array of loudspeakers. For this purpose, many algorithms have been presented in the literature, being Weighted Pressure Matching (wPM) one of the most versatile. The main strength of wPM is that it can render a target soundfield in the listening zone while having control over the mean acoustic potential energy in the quiet zone. In this paper, we propose a variation of wPM such that it can provide control not only over the mean energy, but also over the spatial energy differences, obtaining a more uniform soundfield in the dark zone. The new algorithm is called wPM with Total Variation (wPM-TV), where TV is a tool used in the field of Graph Signal Processing (GSP). Firstly, we propose a graph representation of the control microphones of the dark zone and secondly, we use the wPM-TV algorithm to provide spatial control over that zone. Simulations show the good performance of the proposed algorithm and its versatility to obtain a more uniform distribution of the acoustic potential energy in the dark zone at the cost of slightly increasing the mean square reproduction error in the bright zone.

[EN] Personal audio systems aim to create listening (or bright) and quiet (or dark) zones in a room using an array of loudspeakers. For this purpose, many algorithms have been presented in the literature, being Weighted Pressure Matching (wPM) one of the most versatile. The main strength of wPM is that it can render a target soundfield in the listening zone while having control over the mean acoustic potential energy in the quiet zone. In this paper, we propose a variation of wPM such that it can provide control not only over the mean energy, but also over the spatial energy differences, obtaining a more uniform soundfield in the dark zone. The new algorithm is called wPM with Total Variation (wPM-TV), where TV is a tool used in the field of Graph Signal Processing (GSP). Firstly, we propose a graph representation of the control microphones of the dark zone and secondly, we use the wPM-TV algorithm to provide spatial control over that zone. Simulations show the good performance of the proposed algorithm and its versatility to obtain a more uniform distribution of the acoustic potential energy in the dark zone at the cost of slightly increasing the mean square reproduction error in the bright zone.

[EN] Control flow monitoring using a watchdog processor is a well-known technique to increase the dependability of a microprocessor system. Most approaches embed reference signatures for the watchdog processor into the processor instruction stream. These signatures contain the information required to detect control flow errors during program execution by the main processor. This paper proposes an architecture that offers both fault-tolerance and dynamic cache locking combined. This combination is achieved taking advantage of the fact that watchdog processor signatures are inserted along the program code. Then cache locking information is incorporated into these signatures. And also the required circuitry to inform the cache controller whether to lock or not the instructions fetched by the main processor is added into the watchdog processor. With this approach both fault-tolerant and real-time features are supported by the same hardware, therefore saving room on the silicon die or FPGA size. Results from experiments show that in most cases this approach reaches the same performance than previous, hardware-costly proposals.

[EN] Monitoring the execution of real-time systems has many advantages, it is not only useful to understand the behaviour of an application but also to find unfulfilled timing constraints in an implementation. However, real-time operating systems usually do not include the tracing tools to observe the behaviour during the execution. This paper presents the art2kitekt runtime monitoring tool, used to measure and to visualise the temporal characteristics of a real-time application. To demonstrate the functionality of the tool, the behaviour of an RTEMS-based application running over a Xilinx Zynq UltraScale+ is observed.

[EN] Cardiac function deterioration of heart failure patients is frequently manifested by the occurrence of decompensation events. One relevant step to adequately prevent cardiovascular status degradation is to predict decompensation episodes in order to allow preventive medical interventions.In this paper we introduce a methodology with the goal of finding onsets of worsening progressions from multiple physiological parameters which may have predictive value in decompensation events. The best performance was obtained for the model composed by only two features using a telemonitoring dataset (myHeart) with 41 patients. Results were achieved by applying leave-one-subject-out validation and correspond to a geometric mean of 83.67%. The obtained performance suggests that the methodology has the potential to be used in decision support solutions and assist in the prevention of this public health burden.

[EN] The use of precision agriculture and the Internet of Things has improved the efficiency of many cultures. Nevertheless, there are a few low-cost options to monitor soil moisture. Moreover, those options depend on the specific characteristics of the soil. In this paper, we attempt to find a sensor, based on mutual inductance, that could be used for more than one sort of soil. We study three prototypes, one of them with casing. The sensors are powered with a voltage of 10 peak to peak volts. One of the soils has a high content of organic matter and sand while the other is rich in sand and silt. The best prototype for the soil with high levels of organic matter has 10 turns on the powered coil and 5 on the induced coil. The best frequency for this sensor is 1340 kHz. For the soil with a significant quantity of silt, the best prototype has 80 turns on the powered coil and 40 on the induced coil. The frequency at which this sensor works best is 229 kHz, which happens to be its peak frequency. With those characteristics regressions lines with R2 values higher than 0.75 can be modeled

[EN] This paper presents a new method for fraud detection in credit cards based on exploiting the dynamics of the card transactions. We hypothesize different behavior models in the use of the card between legitimate clients and fraudsters that are registered in the sequential pattern that follows the transactions. The method considers analyses in subspaces defined by two or three variables recorded in the transactions. From these subspaces, several dynamic features, such as transaction velocity and acceleration, are estimated as input vectors for a classification process. Linear and quadratic discriminant analysis and random forest are implemented as single classifiers. All the single classification results obtained for each of the subspaces are late fused to obtain an overall result using alpha integration algorithm. The proposed method was evaluated using a subset of real data with a very low fraud to legitimate transaction ratio. We demonstrated that the temporal dependence of card transactions exploited in different subspaces and fused to give an overall result improves the detection accuracy of fraud detection in credit cards.

[EN] The sewerage is a critical infrastructure in cities because of the drainage of the urban runoff and the evacuation of the wastewater. Two types of sewerage, separated sewerage and combined sewerage, can be differentiated. In this paper, we show the application of a level sensor and a rain sensor for monitoring the separated sewerage. The level sensor is used for knowing if there is a critical level of water in the sewerage. The rain sensor is used to know if it is raining. The combination of this information allows the identification of three scenarios. These scenarios are normal situation, low drainage and illicit discharge/blockages in the pipeline. In addition, we study the use of sensors and mathematical models for monitoring the velocity of the wastewater. We concluded that the use of mathematical models is a good option for monitoring the velocity. Because with exception of the thermal sensors the other types of sensors show important gaps. The velocity is used to estimate the flow that is dumping in the water bodies. We use an ESP32 board program with Arduino IDE for data collection and sending the data to a server on the same network via Wi-Fi. The server is a computer that processes the data. We present the programming code and the ports that should be used for transmitting the data from Arduino to computer server.

[EN] With the aging of the car park in big cities, together with the fact that the number of users of private vehicles is increasing, the quality of air (QoA) in large cities has been worryingly reduced. Therefore, it is becoming increasingly necessary to implement new monitoring infrastructures to improve our smart cities. Therefore, in this paper, we present a collaborative Long Range (LoRa)-based sensor network for pollution monitoring in smart cities. The system is based on geo-located nodes capable of measuring the temperature, relative humidity and concentration of CO2 in urban environments. The system also takes into account the subjective opinions of citizens. By using the collected data and considering the restrictions policies of the city, the system in able to send the required orders to panels and traffic signs to control de traffic circulation. Finally, the citizens can be advised to avoid going to too polluted areas. The system has been testes in a real environment with very interesting results.

[EN] The illegal dumpings in sewerage can cause problems in the Wastewater treatment plants. In this paper, we propose a system for detecting these illegal dumpings. We use conductivity sensor for detecting the change in the conductivity of water. Because this change may be due to a dump. The system is based on two coils, a coil is powered by a sinus-wave and induced the other coil. To prevent damaged for water in the copper we encapsulate the coils in a PVC tube. These coils are connected to flyport to send the values and generate alarms. We test with different configurations of coils with encapsulation of 3 and 1 mm. In the different prototypes tested have been seen that with the 3 mm encapsulation no significant differences are observed. The better prototypes are based on 40 spires of the powered coil and 80 spires in the induced coil. The best difference between samples of 0 and 40 g/l of table salt are in the prototype when the spires are distributed in 1 layer (6.06 V). Another prototype test with the same number of turns but distributed in 4 layers has a difference of 4.10 V. But during the verification phase we verified that this last prototype presents a relative error of 2.54% compared to 6.55% of the prototype distributed in a layer

[EN] The monitoring of industry processes can optimize the use of resources and improve its efficiency. In dairy farms, several parameters from the processes must be monitored. This paper proposes the design of a monitoring system for a farm that produces dairy products and jams. Several similar studies are analysed. Based on this, and on the farm characteristics, a novel design is developed. The principal benefits of the system are also exposed.

[EN] This paper aims to build a fuzzy system by means of genetic programming, which is used to extract the relevant function for each rule consequent through symbolic regression. The employed TSK fuzzy system is complemented with a variational Bayesian Gaussian mixture clustering method, which identifies the domain partition, simultaneously specifying the number of rules as well as the parameters in the fuzzy sets. The genetic programming approach is accompanied with an orthogonal least square algorithm, to extract robust rule consequent functions for the fuzzy system. The proposed model is validated with a synthetic surface, and then with real data from a gas turbine compressor map case, which is compared with an adaptive neuro-fuzzy inference system model. The results have demonstrated the efficacy of the proposed approach for modelling system with small data or bifurcating dynamics, where the analytical equations are not available, such as those in a typical industrial setting.

[EN] An optimization procedure for the design of miniaturized substrate integrated quasi-lumped filters based on aggressive space mapping techniques is presented in this paper. A gradient-descent approach based on a lossy coarse model is employed. Thus, a 3-pole bandpass filter response centered at 10 GHz is designed, manufactured and measured, showing the validity of the technique even if strong dependencies between the different electrical and physical parameters are present.

[EN] Electric Vehicles (EVs) are growing attention fortheir higher efficiency and less-polluting specifications. However,a massive introduction of EVs could lead to several issues inpower systems. Several authors have proposed various smartcharging approaches. But, these approaches could not be ap-propriately implemented without knowing the charging behaviorof the EV customers. Thus, this paper proposes an EV chargingload prediction for the particular case of Quito, Ecuador. Thisforecasting is performed based on data obtained from a GPSsystem and on statistical methods.

This paper analyzes the feasibility of using a simple diffraction model to compute the blocking of the human body to millimeter wave radio frequencies in indoor environments. The model makes a set of approximations that are evaluated to determine the applicability limits of such simplified approach, in particular for the human body blockage case. The work presented here: (1) describes briefly the mathematical support that is used to model the concealment using the Knife-Edge model, (2) identifies the potential simplifications applicable to the mathematical model implementation that allow a 3D geometric human body to be modelled with simple 2D shapes, (3) characterizes the polarization influence on the mm-wave blocking for such simplified human body models.

Aerial base stations have been recently considered in the deployment of wireless networks. Finding the optimal position for one or multiple aerial base stations is a complex problem tackled by several works. However, just a few works consider the mobility of the users which makes necessary an online optimization to follow the changes in the scenario where the optimization is performed. This paper deals with the online optimization of an aerial base station placement considering different types of users mobility and three algorithms: a Q-learning technique, a Gradient-based solution and a Greedy-search solution. Our objective is to minimize in an urban environment the path loss of the user at street level with the highest path loss. Simulation results show that the performance of the three methods is similar when a high number of users move randomly and uniformly around the scenario under test. Nevertheless, in some situations when the number of users is reduced or when the users move together in a similar direction, both Gradient and Greedy algorithms present a significantly better performance than the Q-learning method.

Wireless Body Area Networks (WBANs) have increased the attention of the research community for the next generation wireless medical devices. Among others, Wireless Capsule Endoscopy (WCE) aims to transmit better quality images. For this, the Ultra Wideband (UWB) frequency band is becoming a good alternative to currently allocated frequencies for in-body networks, allowing higher data rate and having a low power transmission. Common channel characterization in WBANs are performed in frequency domain, i.e., analyzing the received power as a function of frequency. Nevertheless, indepth studies in delay domain analyzing the impulse response of the channel are barely considered in current literature. In this paper, an initial study in delay domain, i.e., the Power Delay Profile (PDP) characteristics, is performed. Moreover, a comparison between the channel response in frequency and delay domain is performed. This work gives an insightful view of the impulse response of the channel for in-body to on-body communications. For that, an extensive campaign of phantom measurements and software simulations are conducted.

Localization for Wireless Capsule Endoscopy (WCE) in the Ultra-Wideband frequency band is a very active field of investigation due to its potential advantages in future endoscopy applications. Received Signal Strength (RSS) based localization is commonly preferred due to its simplicity. Previous studies on Ultra-Wideband (UWB) RSS-based localization showed that the localization accuracy depends on the average ranging error related to the selected combination of receivers, which not always is the one experiencing the highest level of received power. In this paper the tendency of the localization error is further investigated through supplementary software simulations and previously conducted laboratory measurements. Two-dimensional (2D) and three-dimensional (3D) positioning are performed and the trend of the localization error compared in both cases. Results shows that the distribution of the selected path loss values, corresponding to the receivers used for localization, around the in-body position to estimate also affects the localization accuracy.

[EN] Optical coherence tomography (OCT) is an important imaging modality that is used frequently to monitor the state of retinal layers both in humans and animals. Automated OCT analysis in rodents is an important method to study the possible toxic effect of treatments before the test in humans. In this paper, an automatic method to detect the most significant retinal layers in rat OCT images is presented. This algorithm is based on an encoder-decoder fully convolutional network (FCN) architecture combined with a robust method of post-processing. After the validation, it was demonstrated that the proposed method outperforms the commercial Insight image segmentation software. We obtained results (averaged absolute distance error) in the test set for the training database of 2.52±0.80 µm. In the predictions done by the method, in a different database (only used for testing), we also achieve the promising results of 4.45 ± 3.02 µm.

[EN] The sewerage is a critical infrastructure in cities because of the drainage of the urban runoff and the evacuation of the wastewater. Two types of sewerage, separated sewerage and combined sewerage, can be differentiated. In this paper, we show the application of a level sensor and a rain sensor for monitoring the separated sewerage. The level sensor is used for knowing if there is a critical level of water in the sewerage. The rain sensor is used to know if it is raining. The combination of this information allows the identification of three scenarios. These scenarios are normal situation, low drainage and illicit discharge/blockages in the pipeline. In addition, we study the use of sensors and mathematical models for monitoring the velocity of the wastewater. We concluded that the use of mathematical models is a good option for monitoring the velocity. Because with exception of the thermal sensors the other types of sensors show important gaps. The velocity is used to estimate the flow that is dumping in the water bodies. We use an ESP32 board program with Arduino IDE for data collection and sending the data to a server on the same network via Wi-Fi. The server is a computer that processes the data. We present the programming code and the ports that should be used for transmitting the data from Arduino to computer server.

[EN] Forest fires are one of the main environmental problems in the entire Mediterranean basin. In a context where low power and long-range networks (LPWAN) are increasingly common to the rise of Internet of Things (IoT) architecture, the interest in providing solutions to monitor scenarios and fire prevention based on these technologies is huge. This paper presents a low cost Long Range (LoRa) based network able to evaluate level of fire risk and the presence of a forest fire. The system is composed by a LoRa node and a set of sensors to measure the temperature, relative humidity, wind speed and CO2. The evaluation algorithm is based on the 30- 30-30 rule. Through website the users can see the parameters measured by nodes in real time. The system has been tested in a real environment and the results show that it is possible to cover a circular area of 1.1km or radius.

[EN] Cardiac function deterioration of heart failure patients is frequently manifested by the occurrence of decompensation events. One relevant step to adequately prevent cardiovascular status degradation is to predict decompensation episodes in order to allow preventive medical interventions.In this paper we introduce a methodology with the goal of finding onsets of worsening progressions from multiple physiological parameters which may have predictive value in decompensation events. The best performance was obtained for the model composed by only two features using a telemonitoring dataset (myHeart) with 41 patients. Results were achieved by applying leave-one-subject-out validation and correspond to a geometric mean of 83.67%. The obtained performance suggests that the methodology has the potential to be used in decision support solutions and assist in the prevention of this public health burden.

[EN] Monitoring the execution of real-time systems has many advantages, it is not only useful to understand the behaviour of an application but also to find unfulfilled timing constraints in an implementation. However, real-time operating systems usually do not include the tracing tools to observe the behaviour during the execution. This paper presents the art2kitekt runtime monitoring tool, used to measure and to visualise the temporal characteristics of a real-time application. To demonstrate the functionality of the tool, the behaviour of an RTEMS-based application running over a Xilinx Zynq UltraScale+ is observed.

[EN] Control flow monitoring using a watchdog processor is a well-known technique to increase the dependability of a microprocessor system. Most approaches embed reference signatures for the watchdog processor into the processor instruction stream. These signatures contain the information required to detect control flow errors during program execution by the main processor. This paper proposes an architecture that offers both fault-tolerance and dynamic cache locking combined. This combination is achieved taking advantage of the fact that watchdog processor signatures are inserted along the program code. Then cache locking information is incorporated into these signatures. And also the required circuitry to inform the cache controller whether to lock or not the instructions fetched by the main processor is added into the watchdog processor. With this approach both fault-tolerant and real-time features are supported by the same hardware, therefore saving room on the silicon die or FPGA size. Results from experiments show that in most cases this approach reaches the same performance than previous, hardware-costly proposals.

[EN] The use of precision agriculture and the Internet of Things has improved the efficiency of many cultures. Nevertheless, there are a few low-cost options to monitor soil moisture. Moreover, those options depend on the specific characteristics of the soil. In this paper, we attempt to find a sensor, based on mutual inductance, that could be used for more than one sort of soil. We study three prototypes, one of them with casing. The sensors are powered with a voltage of 10 peak to peak volts. One of the soils has a high content of organic matter and sand while the other is rich in sand and silt. The best prototype for the soil with high levels of organic matter has 10 turns on the powered coil and 5 on the induced coil. The best frequency for this sensor is 1340 kHz. For the soil with a significant quantity of silt, the best prototype has 80 turns on the powered coil and 40 on the induced coil. The frequency at which this sensor works best is 229 kHz, which happens to be its peak frequency. With those characteristics regressions lines with R2 values higher than 0.75 can be modeled

[EN] With the aging of the car park in big cities, together with the fact that the number of users of private vehicles is increasing, the quality of air (QoA) in large cities has been worryingly reduced. Therefore, it is becoming increasingly necessary to implement new monitoring infrastructures to improve our smart cities. Therefore, in this paper, we present a collaborative Long Range (LoRa)-based sensor network for pollution monitoring in smart cities. The system is based on geo-located nodes capable of measuring the temperature, relative humidity and concentration of CO2 in urban environments. The system also takes into account the subjective opinions of citizens. By using the collected data and considering the restrictions policies of the city, the system in able to send the required orders to panels and traffic signs to control de traffic circulation. Finally, the citizens can be advised to avoid going to too polluted areas. The system has been testes in a real environment with very interesting results.

[EN] This paper presents a new method for fraud detection in credit cards based on exploiting the dynamics of the card transactions. We hypothesize different behavior models in the use of the card between legitimate clients and fraudsters that are registered in the sequential pattern that follows the transactions. The method considers analyses in subspaces defined by two or three variables recorded in the transactions. From these subspaces, several dynamic features, such as transaction velocity and acceleration, are estimated as input vectors for a classification process. Linear and quadratic discriminant analysis and random forest are implemented as single classifiers. All the single classification results obtained for each of the subspaces are late fused to obtain an overall result using alpha integration algorithm. The proposed method was evaluated using a subset of real data with a very low fraud to legitimate transaction ratio. We demonstrated that the temporal dependence of card transactions exploited in different subspaces and fused to give an overall result improves the detection accuracy of fraud detection in credit cards.

[EN] The illegal dumpings in sewerage can cause problems in the Wastewater treatment plants. In this paper, we propose a system for detecting these illegal dumpings. We use conductivity sensor for detecting the change in the conductivity of water. Because this change may be due to a dump. The system is based on two coils, a coil is powered by a sinus-wave and induced the other coil. To prevent damaged for water in the copper we encapsulate the coils in a PVC tube. These coils are connected to flyport to send the values and generate alarms. We test with different configurations of coils with encapsulation of 3 and 1 mm. In the different prototypes tested have been seen that with the 3 mm encapsulation no significant differences are observed. The better prototypes are based on 40 spires of the powered coil and 80 spires in the induced coil. The best difference between samples of 0 and 40 g/l of table salt are in the prototype when the spires are distributed in 1 layer (6.06 V). Another prototype test with the same number of turns but distributed in 4 layers has a difference of 4.10 V. But during the verification phase we verified that this last prototype presents a relative error of 2.54% compared to 6.55% of the prototype distributed in a layer

[EN] The monitoring of industry processes can optimize the use of resources and improve its efficiency. In dairy farms, several parameters from the processes must be monitored. This paper proposes the design of a monitoring system for a farm that produces dairy products and jams. Several similar studies are analysed. Based on this, and on the farm characteristics, a novel design is developed. The principal benefits of the system are also exposed.

[EN] An optimization procedure for the design of miniaturized substrate integrated quasi-lumped filters based on aggressive space mapping techniques is presented in this paper. A gradient-descent approach based on a lossy coarse model is employed. Thus, a 3-pole bandpass filter response centered at 10 GHz is designed, manufactured and measured, showing the validity of the technique even if strong dependencies between the different electrical and physical parameters are present.

[EN] This paper aims to build a fuzzy system by means of genetic programming, which is used to extract the relevant function for each rule consequent through symbolic regression. The employed TSK fuzzy system is complemented with a variational Bayesian Gaussian mixture clustering method, which identifies the domain partition, simultaneously specifying the number of rules as well as the parameters in the fuzzy sets. The genetic programming approach is accompanied with an orthogonal least square algorithm, to extract robust rule consequent functions for the fuzzy system. The proposed model is validated with a synthetic surface, and then with real data from a gas turbine compressor map case, which is compared with an adaptive neuro-fuzzy inference system model. The results have demonstrated the efficacy of the proposed approach for modelling system with small data or bifurcating dynamics, where the analytical equations are not available, such as those in a typical industrial setting.

[EN] Control flow monitoring using a watchdog processor is a well-known technique to increase the dependability of a microprocessor system. Most approaches embed reference signatures for the watchdog processor into the processor instruction stream. These signatures contain the information required to detect control flow errors during program execution by the main processor. This paper proposes an architecture that offers both fault-tolerance and dynamic cache locking combined. This combination is achieved taking advantage of the fact that watchdog processor signatures are inserted along the program code. Then cache locking information is incorporated into these signatures. And also the required circuitry to inform the cache controller whether to lock or not the instructions fetched by the main processor is added into the watchdog processor. With this approach both fault-tolerant and real-time features are supported by the same hardware, therefore saving room on the silicon die or FPGA size. Results from experiments show that in most cases this approach reaches the same performance than previous, hardware-costly proposals.

[EN] The sewerage is a critical infrastructure in cities because of the drainage of the urban runoff and the evacuation of the wastewater. Two types of sewerage, separated sewerage and combined sewerage, can be differentiated. In this paper, we show the application of a level sensor and a rain sensor for monitoring the separated sewerage. The level sensor is used for knowing if there is a critical level of water in the sewerage. The rain sensor is used to know if it is raining. The combination of this information allows the identification of three scenarios. These scenarios are normal situation, low drainage and illicit discharge/blockages in the pipeline. In addition, we study the use of sensors and mathematical models for monitoring the velocity of the wastewater. We concluded that the use of mathematical models is a good option for monitoring the velocity. Because with exception of the thermal sensors the other types of sensors show important gaps. The velocity is used to estimate the flow that is dumping in the water bodies. We use an ESP32 board program with Arduino IDE for data collection and sending the data to a server on the same network via Wi-Fi. The server is a computer that processes the data. We present the programming code and the ports that should be used for transmitting the data from Arduino to computer server.

[EN] Cardiac function deterioration of heart failure patients is frequently manifested by the occurrence of decompensation events. One relevant step to adequately prevent cardiovascular status degradation is to predict decompensation episodes in order to allow preventive medical interventions.In this paper we introduce a methodology with the goal of finding onsets of worsening progressions from multiple physiological parameters which may have predictive value in decompensation events. The best performance was obtained for the model composed by only two features using a telemonitoring dataset (myHeart) with 41 patients. Results were achieved by applying leave-one-subject-out validation and correspond to a geometric mean of 83.67%. The obtained performance suggests that the methodology has the potential to be used in decision support solutions and assist in the prevention of this public health burden.