Dr. Zambrano-Martinez

Abstract

Las técnicas de visión por computador son una subdivisión de la inteligencia artificial, mediante la cual usando una imagen, un grupo de imágenes o una secuencia de imágenes, tenemos la posibilidad de extraer información importante para realizar diversas operaciones como: reconocimiento de objetos, calibración de la cámara, modelado 3D, visión robótica, seguimiento de video, tratamiento de imágenes (contraste, brillo, umbral, etc), entre otros. Existen muchos campos en los que se pueden usar como: rayos x, tomografía, infrarrojos, sensores ópticos, sensores de rangos, meteorología, robótica, entre otros. La aplicación a desarrollar tiene como objetivo ayudar a las personas no videntes, puesto que este grupo de individuos ha sido excluido de la sociedad, ya que todos los elementos que se encuentran en nuestro alrededor no ayudan sino mas bien les hace apartarse de las tareas cotidianas, siendo estas difíciles de realizar; por lo tanto se planteó el desarrollo de un reconocedor de billetes, ya que en este ámbito las personas no videntes son estafadas a menudo cuando realizan el pago o cobro. La aplicación poseerá los siguientes puntos: uso del acelerómetro (una de las grandes ventajas que posee iOS es la presentación del acelerómetro mediante el cual se llamarán los diversos procesos), cámara (se refiere a la captura de las imágenes haciendo uso del dispositivo móvil), sonido( estará basado en diversas ayudas o pasos auditivos, mediante el cual la persona podrá guiarse de cómo será su uso) y vibraciones (alertará sobre diferentes actos que pudiesen desarrollarse).

Thesis

Abstract

The route planning solutions promise improvements in terms of the travel time for a route if they are familiar with the traffic congestion state in real-time. With current solutions, where most are static and based on, the cost of road segments, the first challenge is to obtain reliable estimates of traffic congestion for a city at different times of day, and for different days of the year. Overall, calculating this amount of data will take a long time, and have a high computational cost when evaluating the optimal routes based on dependencies. In this paper, the feasibility of integrating a route recommendation system, a network simulator and a traffic simulator is studied. In parti- cular we study the integration of OMNeT ++ and SUMO, both widely known and used tools, with the ABATIS route server as a solution for route planning, allowing to investigate what are the different effects on vehicle flows densely populated urban areas. To achieve that goal the traffic patterns adopted are adjusted, following driver models ranging from real-time speed changes to changes in route selection. However, the number of vehicles that have to be introduced in the simulation is unknown, and thus we developed a heuristic to adjust the number of vehicles to be injected based on the number of vehicles detected on the different sensors placed along the main streets of Valencia, Spain. Initial results show that the proposed route server offers routes with similar quality compared to the tool integrated in SUMO, and that the use of alternative routes is likely to introduce significant changes on the travel times of vehicles.

Thesis

Abstract

The route planning solutions promise improvements in terms of the travel time for a route if they are familiar with the traffic congestion state in real-time. With current solutions, where most are static and based on, the cost of road segments, the first challenge is to obtain reliable estimates of traffic congestion for a city at different times of day, and for different days of the year. Overall, calculating this amount of data will take a long time, and have a high computational cost when evaluating the optimal routes based on dependencies. In this paper, the feasibility of integrating a route recommendation system, a network simulator and a traffic simulator is studied. In parti- cular we study the integration of OMNeT ++ and SUMO, both widely known and used tools, with the ABATIS route server as a solution for route planning, allowing to investigate what are the different effects on vehicle flows densely populated urban areas. To achieve that goal the traffic patterns adopted are adjusted, following driver models ranging from real-time speed changes to changes in route selection. However, the number of vehicles that have to be introduced in the simulation is unknown, and thus we developed a heuristic to adjust the number of vehicles to be injected based on the number of vehicles detected on the different sensors placed along the main streets of Valencia, Spain. Initial results show that the proposed route server offers routes with similar quality compared to the tool integrated in SUMO, and that the use of alternative routes is likely to introduce significant changes on the travel times of vehicles.

Conference Paper

Abstract

Los altos niveles de tráfico urbano son una de las principales preocupaciones en nuestras sociedades, generando problemas como consumo de combustible y emisiones de CO2 excesivos. Recientemente, los Sistemas de Transporte Inteligente (ITS) han emergido como una tecnología capaz de mitigar estos problemas. Sin embargo, el análisis de tráfico y las correspondientes propuestas de mejora típicamente se basan en simulaciones, las cuales deberían ser lo más realistas posible. No obstante, lograr un elevado grado de realismo puede ser complejo, especialmente cuando los patrones de tráfico real, definidos a través de una matriz origen-destino (O-D) para los vehículos en una ciudad, son desconocidos. En este trabajo proponemos una nueva técnica para importar datos de tráfico a la herramienta de simulación de movilidad SUMO. Concretamente, nuestra propuesta parte de las mediciones de los anillos de inducción, típicamente disponibles por parte de las autoridades de tráfico. A continuación usando la herramienta DFROUTER conjuntamente con una heurística basada en un ajuste globla del tráfico, permite generar una matriz O-D para el tráfico que se asemeje lo más posible a la distribución del tráfico real. Aplicando la técnica propuesta a la ciudad de Valencia, verificamos mediante simulación que los resultados obtenidos son muy similares a otros datos de tráfico de movilidad existentes para las ciudades de Cologne (Alemania) y Bologna (Italia), demostrando la validez de la estrategia propuesta.

Conference Paper

Abstract

Nowadays, one of the main challenges faced in large metropolitan areas is traffic congestion. To address this problem, an adequate traffic control could produce many benefits, including reduced pollutant emissions and reduced travel times. If it were possible to characterize the state of traffic by predicting traffic conditions, measures could be taken to preventively mitigate the effects of congestion and related problems. This paper performs an experimental study of the traffic distribution in the city of Valencia, characterizing the different streets of the city in terms of vehicle load with respect to the travel time during rush hour traffic conditions. Experimental results based on realistic vehicular traffic traces show that most of the street segments under analysis present a good fit under quadratic regression, although a large number of street segments fall under other categories mainly due to lack of traffic. Based on this study, a clustering analysis study associated to the different streets shows how these streets can be classified into four independent categories, evidencing an uneven traffic distribution throughout the city.

Conference Paper

Abstract

Uno de los principal problemas al que se enfrentan los Sistemas Inteligente de Transporte (ITS) es la congestión del tráfico, que requiere modelos para predecir el impacto de diferentes soluciones en el flujo de tráfico urbano. Para lograrlo es imprescindible el uso de simuladores, los cuales deberían ser tan realistas como sea posible. Sin embargo, lograr ese alto grado de realismo pueden ser difícil de conseguir cuando no se dispone de los patrones de tráfico real, típicamente definidos a través de una matriz origen-destino (O-D) para los vehículos de una ciudad. En este sentido, la principal contribución de este trabajo es la propuesta de una heurística para mejorar el modelo de la congestión del tráfico. Proponemos un procedimiento que, partiendo de las mediciones de los anillos de inducción reales, permite refinar iterativamente la salida del DFROUTER, herramienta para estimar la distribución real del tráfico y que se integra en SUMO (Simulador de Movilidad Urbana). De esta forma, DFROUTER permite generar una matriz O-D para el tráfico, acercándose a una distribución realista del mismo, y que además puede ser importada directamente por SUMO para la realización de diferentes estudios. Aplicamos nuestra técnica a la ciudad de Valencia para así poder determinar el grado de congestión esperable si ciertas condiciones causan tráfico adicional en la circulación de la ciudad, adoptando dos tipos de patrones para la inyección de tráfico: uniforme y basado en zonas calientes. Finalmente estudiamos sobre el impacto de diferentes niveles de congestión del tráfico en escenarios urbanos.

Conference Paper

Abstract

Traffic congestion is an important problem faced by Intelligent Transportation Systems (ITS), requiring models that allow predicting the impact of different solutions on urban traffic flow. Such an approach typically requires the use of simulations, which should be as realistic as possible. However, achieving high degrees of realism can be complex when the actual traffic patterns, defined through an Origin/Destination (O-D) matrix for the vehicles in a city, remain unknown. Thus, the main contribution of this paper is a heuristic for improving traffic congestion modeling. In particular, we propose a procedure that, starting from real induction loop measurements made available by traffic authorities, iteratively refines the output of DFROUTER, which is a module provided by the SUMO (Simulation of Urban MObility) tool. This way, it is able to generate an O-D matrix for traffic that resembles the real traffic distribution and that can be directly imported by SUMO. We apply our technique to the city of Valencia, and we then compare the obtained results against other existing traffic mobility data for the cities of Cologne (Germany) and Bologna (Italy), thereby validating our approach. We also use our technique to determine what degree of congestion is expectable if certain conditions cause additional traffic to circulate in the city, adopting both a uniform pattern and a hotspot-based pattern for traffic injection to demonstrate how to regulate the overall number of vehicles in the city. This study allows evaluating the impact of vehicle flow changes on the overall traffic congestion levels.

Article

Abstract

The goal of this paper is to know which is the best Big Data architecture that is substantially adapted to make a large amount of data processed in real-time provided by the Spanish Notaries. Taking as a starting point the Hadoop ecosystem, where there is a stack of Big Data technologies, which they can solve a daily problem. Those technologies can be extrapolated in many data areas that require real-time processing with proper storage in a cluster. The results obtained in this project are, on the one hand, the creation of large amounts of synthetic data with characteristics similar to the data of the servers of the Notary, in order to test the chosen architecture, and on the other hand, the creation of a fully functional, small-scale virtualized architecture within a virtual cluster, for real-time data capture, with their respective processing and storage in the virtual cluster.

Thesis

Abstract

Hoy en día, uno de los principales retos a que se enfrentan las grandes áreas metropolitanas es la congestión del tráfico. Para tratar adecuadamente este problema, aplicar un control centralizado del tráfico podría producir muchos beneficios, incluyendo tanto reducción de emisiones de CO2 como del tiempo de viaje. Si fuese posible caracterizar el estado del tráfico para predecir las condiciones del tráfico futuras, se podrían tomar medidas para mitigar de forma preventiva los efectos de la congestión, y los problemas a ella asociados. Este trabajo realiza un estudio experimental de la distribución del tráfico en la ciudad de Valencia, caracterizando las diferentes calles de la ciudad en términos de cantidad de vehículos con respecto al tiempo del viaje en hora punta. Los resultados experimentales basados en trazas reales del tráfico de la ciudad muestran que la mayoría de los segmentos de calle analizados presentan una buena correlación con una regresión cuadrática, aunque otros segmentos de calle pertenecen a otras categorías principalmente debido a la falta de tráfico por dichas vías. El estudio muestra cómo estas calles se pueden clasificar en cuatro categorías claramente independientes, lo que evidencia una distribución de tráfico desigual en la ciudad.

Conference paper

Abstract

Currently, one of the main challenges faced in large metropolitan areas is traffic congestion. To address this problem, adequate traffic control could produce many benefits, including reduced pollutant emissions and reduced travel times. If it were possible to characterize the state of traffic by predicting future traffic conditions for optimizing the route of automated vehicles, and if these measures could be taken to preventively mitigate the effects of congestion with its related problems, the overall traffic flow could be improved. This paper performs an experimental study of the traffic distribution in the city of Valencia, Spain, characterizing the different streets of the city in terms of vehicle load with respect to the travel time during rush hour traffic conditions. Experimental results based on realistic vehicular traffic traces from the city of Valencia show that only some street segments fall under the general theory of vehicular flow, offering a good fit using quadratic regression, while a great number of street segments fall under other categories. Although in some cases such discrepancies are related to lack of traffic, injecting additional vehicles shows that significant mismatches still persist. Thus, in this paper we propose an equation to characterize travel times over a segment belonging to the sigmoid family; specifically, we apply logistic regression, being able to significantly improve the curve fitting results for most of the street segments under analysis. Based on our regression results, we performed a clustering analysis of the different street segments, showing that they can be classified into three well-defined categories, which evidences a predictable traffic distribution using the logistic regression throughout the city during rush hours, and allows optimizing the traffic for automated vehicles.

Article

Abstract

Currently, one of the main challenges that large metropolitan areas must face is traffic congestion. To address this problem, it becomes necessary to implement an efficient solution to control traffic that generates benefits for citizens, such as reducing vehicle journey times and, consequently, environmental pollution. By properly analyzing traffic demand, it is possible to predict future traffic conditions, using this information for the optimization of the routes taken by vehicles. Such an approach becomes especially effective if applied in the context of autonomous vehicles, which have a more predictable behavior, thus enabling city management entities to mitigate the effects of traffic congestion and pollution, thereby improving the traffic flow in a city in a fully centralized manner. This paper represents a step forward towards this novel traffic management paradigm by proposing a route server capable of handling all the traffic in a city, and balancing traffic flows by accounting for present and future traffic congestion conditions. We perform a simulation study using real data of traffic congestion in the city of Valencia, Spain, to demonstrate how the traffic flow in a typical day can be improved using our proposed solution. Experimental results show that our proposed traffic prediction equation, combined with frequent updating of traffic conditions on the route server, can achieve substantial improvements in terms of average travel speeds and travel times, both indicators of lower degrees of congestion and improved traffic fluidity.

Article

Abstract

Currently, one of the main challenges that large metropolitan areas have to face is traffic congestion, which has become an important problem faced by city authorities. To address this problem, it becomes necessary to implement an efficient solution to control traffic that generates benefits for citizens, such as reducing vehicle journey times and, consequently, use of fuel, noise and environmental pollution. In fact, by properly analyzing traffic demand, it becomes possible to predict future traffic conditions, and to use that information for the optimization of the routes taken by vehicles. Such an approach becomes especially effective if applied in the context of autonomous vehicles, which have a more predictable behavior, thus enabling city management entities to mitigate the effects of traffic congestion and pollution by improving the traffic flow in a city in a fully centralized manner. Validating this approach typically requires the use of simulations, which should be as realistic as possible. However, achieving high degrees of realism can be complex when the actual traffic patterns, defined through an Origin/Destination (O-D) matrix for the vehicles in a city, are unknown, as occurs most of the times. Thus, the first contribution of this thesis is to develop an iterative heuristic for improving traffic congestion modeling; starting from real induction loop measurements made available by the City Hall of Valencia, Spain, we were able to generate an O-D matrix for traffic simulation that resembles the real traffic distribution. If it were possible to characterize the state of traffic by predicting future traffic conditions for optimizing the route of automated vehicles, and if these measures could be taken to preventively mitigate the effects of congestion with its related problems, the overall traffic flow could be improved. Thereby, the second contribution of this thesis was to develop a Traffic Prediction Equation to characterize the different streets of a city in terms of travel time with respect to the vehicle load, and applying logistic regression to those data to predict future traffic conditions. The third and last contribution of this thesis towards our envisioned traffic management paradigm was a route server capable of handling all the traffic in a city, and balancing traffic flows by accounting for present and future traffic congestion conditions. Thus, we perform a simulation study using real data of traffic congestion in the city of Valencia, Spain, to demonstrate how the traffic flow in a typical day can be improved using our proposed solution. Experimental results show that our proposed solution, combined with frequent updating of traffic conditions on the route server, is able to achieve substantial improvements in terms of average travel speeds and travel times, both indicators of lower degrees of congestion and improved traffic fluidity.

Doctoral Thesis

Abstract

Currently, one of the main challenges that large metropolitan areas have to face is traffic congestion. To address this problem it is necessary to implement an efficient solution to control traffic that generates benefits for citizens such as reducing vehicle journey times and, consequently, environmental pollution as well. By properly analyzing traffic demand it becomes possible to predict future traffic conditions, and use this information for the optimization of routes. Such an approach becomes especially effective if applied in the context of automated vehicles, which have a more predictable behavior, thus being capable of mitigating the effects of traffic congestion by improving the traffic flow of the city in a centralized manner. This paper performs an experimental study of traffic congestion in an area characterized by intense traffic in the city of Valencia, Spain. By comparing the traffic flow in a typical day with our proposed improved solution, we show that significant benefits are achieved. In particular, we have created an interface to connect an existing urban traffic simulator (SUMO), and a network simulator (OMNeT++), with a modified route server. The latter continually updates present and future traffic conditions to properly balance traffic throughout the city. Experimental results show that our proposed Traffic Prediction Equation, combined with frequent updating of traffic conditions on the route server, is able to achieve substantial improvements in terms of average travel speeds and travel times, both indicators of lower degrees of congestion and improved traffic fluidity.

Confernce paper

Abstract

La contaminación relacionada con los vehículos es uno de los principales problemas de muchas grandes áreas metropolitanas, y la administración y ayuntamientos buscan métodos eficaces para mejorar la calidad de vida de los ciudadanos, especialmente en las zonas céntricas y cerca de lugares como hospitales o escuelas. Uno de los métodos adoptados recientemente es el cierre de estas zonas al tráfico. Sin embargo, no se ha estudiado a fondo el impacto de estos métodos. En este trabajo evaluamos si la limitación del tráfico por motivos medioambientales es factible y eficiente. Concretamente, analizamos el impacto de cortar una calle o carretera para evitar la contaminación en determinada zona, mostrando cómo nuestro algoritmo de asignación de rutas propuesto es capaz de desviar el tráfico para minimizar la circulación en esos lugares. Además, determinamos cómo varían las emisiones totales de los vehículos en esa zona debido a las restricciones de tráfico aplicadas. Los resultados de simulación muestran que, incluso al cerrar una sola calle, los índices de contaminación aumentan entre un 3 y un 4 % en áreas circundantes, lo cual hace dudar de la aplicabilidad y eficacia de tales métodos.

Confernce paper

Abstract

Vehicle-related pollution is a main issue for many large metropolitan areas, and city administrations seek effective methods to improve the life quality of citizens, especially in downtown areas, and near places like hospitals or schools. One of the methods recently adopted is closing down these areas to traffic. However, the impact of such approaches has not been thoroughly studied. In this paper we assess whether limiting traffic for environmental reasons is feasible and efficient. In particular, we analyze the impact of blocking a street/road to avoid pollution in that zone, showing how our proposed route assignment algorithm is able to deviate traffic to minimize circulation in those places, In addition, we determine how the overall vehicle emissions in that area vary due to the traffic restrictions enforced. Experimental results show that, even when closing a single street, pollution indexes increase by 3-4 %, which raises doubts regarding the applicability and effectiveness of such methods.

Confernce paper

Abstract

Currently, online banking is a fundamental tool for natural or legal persons, leading to the fact that banking services that were performed in a traditional way (physical form) are transferred to the Internet due to its ease of use and comfort for the client, having these services at your disposal at any time. For this reason, these online banking services become attractive to criminals, which is why they devise various strategies to generate attacks on the data centres of banking agencies to obtain as much information as possible from users and thus steal information and money from banking entities illegally. This investigative work aims to perform a bibliographic review, using the methodology of a systematic review of the literature, SLR, selecting the information exhaustively and adequately through research of studies related to the computer security algorithms necessary to counterattacks of computer security that online banking platforms are objectives to know the preparation and proposal for security problems that online banking has, using a variety of research in publications, magazines and other research elements that will allow the development of this review article. The results allow us to conclude that the security algorithms based on DHCP Snooping can be the beginning of various points and proposals to counteract attacks on online banking servers of financial platforms. Through DHCP Snooping, it is possible to counteract DHCP Spoofing, which is the principle of most online attacks on different cybersecurity systems and applications. As for the work implemented, we found other alternatives to counter attacks using DHCP Snooping through its multiple solutions for protecting online banking servers.

Article

Abstract

The objective of the article was to generate an Automatic Speech Recognition (ASR) model based on the translation from human voice to text, being considered as one of the branches of artificial intelligence. Voice analysis allows identifying information about the acoustics, phonetics, syntax, semantics of words, among other elements where ambiguity in terms, pronunciation errors, similar syntax but different semantics can be identified, which represent characteristics of the language. The model focused on the acoustic analysis of words proposing the generation of a methodology for acoustic recognition from speech transcripts from audios containing human voice and the error rate per word was considered to identify the accuracy of the model. The audios were taken from the Integrated Security Service ECU911 that represent emergency calls registered by the entity. The model was trained with the CMUSphinx tool for the Spanish language without internet connection. The results showed that the word error rate varies in relation to the number of audios; that is, the greater the number of audios, the smaller number of erroneous words and the greater the accuracy of the model. The investigation concluded by emphasizing the duration of each audio as a variable that affects the accuracy of the model.

Article

Abstract

En la actualidad estamos presenciando un auge del Internet de las Cosas, verificándose que un número cada vez mayor de dispositivos está conectado a Internet para ofrecer una visión completa de determinado sistema a monitorizar, incluyendo infraestructuras públicas de agua, luz y gas, así como sistemas industriales, aplicaciones de logística, etc. En este contexto, también el usuario común desea beneficiarse de estas ventajas en proyectos propios en el entorno de su hogar, sin que eso requiera necesariamente una instalación domótica completa debido a los elevados costes asociados. Siendo así, en este trabajo se presenta una solución de muy bajo coste y bajo consumo para el control remoto de un invernadero de pequeña dimensión adecuado para el interior de un hogar. Además, para evitar que el usuario necesite desarrollar una aplicación propia, se ofrece una interfaz mediante Telegram, lo cual permite gestionar el sistema de manera segura desde cualquier terminal compatible con la aplicación.

Conference paper

Abstract

Industrialization and the rapid growth of urban areas are alarmingly increasing the presence of air pollutants. These pollutants affect the quality of life of people and present an opportunity for study is created to determine the atmospheric behavior and relationship between meteorological variables present in the environment. Prior to this, rolling windows of time were applied to remove anomalous data. Next, variables were identified, and the data was segmented through the X-means algorithm. Also, two clusters that represent the relationships between pairs of variables and the temporality of the time windows. As a result, an inverse correlation of -0.78 was found between the ozone and dew point variables within the hours of the working day.

Article

Abstract

In recent years, Automatic Speech Recognition (ASR) services have performed notable progress in the research efforts of big companies such as Google and Amazon. However, the ASRs are still sensitive to the audio processing quality in other languages. To solve this issue, various speech enhancement algorithms that are the most prominent in improving speech intelligibility were proposed, such as Singular Value Decomposition (SVD), log Minimum Mean Square Error (log-MMSE) and Wiener. By preprocessing the audio files with these algorithms, we seek to reduce the Word Error Rate (WER), which compares the transcription performed by the ASR against a manual transcription. Thus, we can determine the percentage of error that the ASR service has acquired. Results demonstrated that Google is more efficient than Amazon and Vosk counterparts. Also, we decided that applying a Low-pass filter combined with a log-MMSE algorithm to the audio files can substantially reduce the WER percentage of transcription depending on the noise characteristics contained in the audio.

Conference Paper

Abstract

Nowadays, the world faces a high level of environmental pollution. This phenomenon has become a constant challenge for our society due to its negative impact on health and the increased risk of disease. Considering this problem, applications, techniques and methodologies are generated that seek to relate atmospheric pollutants to each other to predict the state of the air. On the other hand, recommendation systems are present in numerous decision-making methods to find trends in various fields. Consequently, this work presents a methodology for a recommender system that provides people with the best hours to perform outdoor activities according to the pollutants found in the environment. The results obtained were verified through an evaluation and thus be able to contribute to the creation of new recommenders based on the previous topics.

Conference Paper

Abstract

In recent years, the exponential growth of interconnections between digital devices has caused a significant rise in cyberattack incidents. This produces severe and disastrous consequences for an organisation by exploiting existing vulnerabilities in emerging technologies. One of the most innovative and effective defence mechanisms today is cryptography, considered an essential requirement in the cybersecurity community for data protection. In this work, we implement encryption methods that are executed independently on each machine in a distributed manner through the web service called Simple Object Access Protocol (SOAP) to protect the data. To perform it, an experimental scenario was created using a distributed system with virtual machines that host standard encryption methods such as AES-256, Cesar, and Blowfish to send encrypted data from a source machine to a destination machine, in turn, decrypt the encrypted data. The results show that our proposal increases the security of the data sent from a source to its destination, making it difficult for the attacker to obtain the data quickly. In addition, the consumption of computational resources for executing the algorithms in the distributed system is minimal, which is adequate to guarantee its use in any computer with very few resources.

Article

Abstract

Currently, in metropolitan areas, the amounts of polluting gases are increasing, which causes the growth of global warming. One of the leading gases causing the greenhouse effect is carbon dioxide (CO2). For this reason, its monitoring and control is a highly studied topic worldwide due to the various problems in the ecosystem. One of the ways to monitor CO2 levels in the environment is through devices with specialised sensors and wireless communication through a sensor network. This research paper presents a bibliographic review of studies on sensor networks for CO2 monitoring. The objective of this article is to identify which are the sensors and the most used communication technology for the monitoring of this polluting gas. The methodology used in this article is a bibliographic review, which effectively allows the investigation of information to perform a critical analysis. Scientific articles, doctoral thesis, and other research on this subject have been considered for analysis. The results concluded that the most widely used wireless protocol is Zigbee due to its reduced energy consumption in implementation. The MQ-135 sensor is the most used, which is indicated to detect harmful gases in a maximum range of 10-1000 ppm (parts per million).

Article

Abstract

In recent years, bullying and cyberbullying have increased, affecting schools, colleges, and universities. Due to advances in information technology, any person is exposed to being attacked. Therefore, it is necessary to create solutions through appropriate techniques that help prevent bullying and cyberbullying. Consequently, this article proposes to create a textual synthesis from survey data that allows the development of models to classify or predict both victims and aggressors of bullying and cyberbullying. Data mining techniques, decision trees, and grouping techniques were used, resulting in a textual synthesis. This allowed the creation and evaluation of a supervised learning model and another model with clustering techniques applied to the data from the surveys performed on university students. The results demonstrated the importance of textual synthesis for generating models for the classification or prediction of victims and aggressors of bullying and cyberbullying, with an accuracy greater than 75% for the grouping model with the best performance.

Article

Abstract

Foreign trade is fundamental to the economy as it involves many transactions and data from a country. This study analyses exports from Ecuador to generate knowledge for experts in this field. A data visualization model covering 2008 and 2018 was developed to achieve this. The study was based on the CRISP-DM methodology, widely used in data mining projects. This methodology is adapted through five iterative phases to develop the mining and visualization model. Through the implementation of this methodology, it was possible to generate a visual model that provides an effective tool to manipulate the main variables related to foreign trade. The result was the creation of a graphical model adapted into a tool to explore and analyse Ecuador's exports. This model provides an intuitive interface to manipulate and examine the main variables, which can facilitate informed decision-making in foreign trade.

Article

Abstract

Currently, bullying among children is a serious social problem and even acts as one of the primary mental health problems. Therefore, various types of bullying have been detected, including physical, verbal, social, and cyberbullying, which uses technology within reach of the aggressor to broadcast the damage and make the victim constantly harassed. Artificial intelligence and bullying are widely studied and researched, but they are not regularly used together to mitigate the bullying problem. Nevertheless, this research aims to identify the keywords extracted from different audiovisual media whose central theme is bullying and cyberbullying to create semantic fields corresponding to the text extracted from the video and generate a guide for automated bullying detection as support for professionals.

Article

Abstract

To achieve a more accurate assessment of air quality, it is necessary to know the relationship between meteorological variables and the different air pollutants; this will also be aimed at avoiding the risks present both in the ecosystem and in human health in the future. The problem begins with finding an association between air pollutants and meteorological variables in the models and categorization methods that can be used. Due to this reason, the objective of this article is to analyze the quality of the associations between pollutants and meteorological variables by seasonality using decision trees to find knowledge that allows locating patterns that will be important for environmental analysis. Therefore, it was possible to achieve a periodic control of the quality of the associations of pollutants and meteorological variables, whose validation of the confidence level of the association rules is greater than 70% in the months studied.

Article

About this book

This book constitutes the proceedings of the 11th Ecuadorian Conference on Information and Communication Technologies, TICEC 2023, held in Cuenca, Ecuador, during October 18–20, 2023. The 31 full papers presented were carefully reviewed and selected from 120 submissions. The papers cover a great variety of topics, such as internet of things, cyber-physical systems, human-machine interface, artificial Intelligence, e-Learning, smart healthcare, smart healthcare and others. The papers are organized in the following topical sections: data science and machine learning; ICTs and their applications; and software development.

Article

Abstract

The present study applies fuzzy logic techniques to find an integrated ultraviolet radiation index for Cuenca-Ecuador. This index integrates information on meteorological variables and ultraviolet rays, whose data were provided by the Research Department of the Institute for Sectional Regime Studies of Ecuador (IERSE), corresponding to 2018. Analysis techniques in data mining were used to process and segment this information. Subsequently, a fuzzy logic model with the Mamdani approach was generated to obtain an integrated ultraviolet radiation index. This model combines the values of the Ultraviolet radiation A and Ultraviolet radiation B components through 49 fuzzy inference rules. The results obtained were compared with the ultraviolet radiation indices of the tropospheric model. As a result, a slightly higher fuzzy index was obtained in terms of the index score concerning the tropospheric model.

Article

Abstract

Health problems in older adults lead to situations where communication with peers, family and caregivers becomes challenging for seniors; therefore, it is necessary to use alternative methods to facilitate communication. In this context, Augmentative and Alternative Communication (AAC) methods are widely used to support this population segment. Moreover, with Artificial Intelligence (AI), and specifically, machine learning algorithms, AAC can be improved. Although there have been several studies in this field, it is interesting to analyze common phrases used by seniors, depending on their context (i.e., slang and everyday expressions typical of their age). This paper proposes a semantic analysis of the common phrases of older adults and their corresponding meanings through Natural Language Processing (NLP) techniques and a pre-trained language model using semantic textual similarity to represent the older adults’ phrases with their corresponding graphic images (pictograms). The results show good scores achieved in the semantic similarity between the phrases of the older adults and the definitions, so the relationship between the phrase and the pictogram has a high degree of probability.

Article

Hello,

I'm Jorge Luis Zambrano-Martinez, Ph.D.

About

Let me introduce myself.

Profile

Skills

Education

Universitat Politècnica de València

Universitat Oberta de Catalunya, Universitat Autònoma de Barcelona, Universitat Rovira i Virgili

Universitat Politècnica de València

Universidad Politécnica Salesiana

Colegio Hermano Miguel De La Salle

Work Experience

Researcher

Universidad del Azuay

IT Security Administration Professor

Universidad Laica Eloy Alfaro de Manabí

Networking Security Professor

Universidad Técnica de Manabí

Software Developer

Empresa Municipal de Aseo de Cuenca (EMAC) - EP

Networking Security Professor

Universidad Técnica de Manabi

Course Instructor

ESPE-Innovativa

Researcher

Laboratorie d’ Analyse et d’ Architecture des Systèmes (LAAS- CNRS)

Researcher

Universitat Politècnica de València

Head of Systems Department

Comisariato del Constructor S.A.

Asistant Professor

Universidad Politécnica Salesiana

Publications

Semantic Similarity of Common Verbal Expressions in Older Adults through a Pre-Trained Model

Finding an Integrated Ultraviolet Radiation Index Using Fuzzy Logic Techniques

Information and Communication Technologies

Analysis of the Quality of the Associations of Pollutants and Meteorological Variables by Seasonality

Text Generation Guide for Automated Detection of Bullying and Cyberbullying

Visual Model of Foreign Trade in Ecuadorian Export

Textual Synthesis of Test for Bullying and Cyberbullying

Review of studies on sensor networks for CO2 monitoring

Text Encryption through Distributed Systems

A Methodology to Develop an Outdoor Activities Recommender Based on Air Pollution Variables

Improving audio of emergency calls in Spanish performed to the ECU 911 through filters for ASR technology

Knowledge extraction through time windows on atmospheric variables

Cactus Pi: gestión remota de un mini-invernadero usando Telegram

Speech recognition based on Spanish accent acoustic model

Revisión de la literatura de las metodologías de ciberseguridad en plataformas bancarias

Assessing the impact of road traffic constraints on pollution

Evaluación del impacto de las restricciones de tráfico en los niveles de contaminación

Towards a Centralized Route Management Solution for Autonomous Vehicles

Efficient Traffic Management in Urban Environments

A centralized route-management solution for autonomous vehicles in urban areas

Modeling and Characterization of Traffic Flows in Urban Environments

Distribución del tráfico vehicular en áreas urbanas: clasificación y análisis

Big Data y Seguridad

Towards Realistic Urban Traffic Experiments Using DFROUTER: Heuristic, Validation and Extensions

Modelado realista del tráfico urbano usando DFROUTER

Analysis and Classification of the Vehicular Traffic Distribution in an Urban Area

Simulación de Tráfico Vehicular en base a Trazas Reales

Using Real Traffic Data for ITS Simulation: Procedure and Validation

Sistema centralizado para la optimización del tráfico mediante un servidor de rutas

Estudio y selección de las técnicas SIFT, SURF y ASIFT de reconocimiento de imágenes para el diseño de un prototipo en dispositivos móviles

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract