Jose Medina

Bio: Jose Medina is an academic researcher from University of Cuenca. The author has contributed to research in topics: Clinker (cement) & Kiln. The author has an hindex of 3, co-authored 8 publications receiving 16 citations.

A robust video identification framework using perceptual image hashing

Abstract: This paper proposes a general framework that allows to identify a video in real time using perceptual image hashing algorithms. In order to evaluate the versatility and performance of the framework, it was coupled for a use case about ads tv monitoring. Four Perceptual Image Hashing (PIH) algorithms were subject to a benchmarking process in order to identify the best one for the use case. This process was focused on analyze differences in terms of discriminability (D), robustness (R), time processing (Tp) and efficiency (E). A truth table was used to obtain information about discriminability and robustness, while processing time was directly measured. An efficiency metric based on time processing and identification capacity was proposed. In general terms, DHASH and PHASH algorithms have higher identification capacities than AHASH and WHASH in order to identify a video using only one frame. Moreover, a progressive decrease in robustness with the increment of the Hamming distance is observed in all cases. However, in a specific case of tv monitoring where speed is critical, the processing time becomes the most discriminatory parameter for the selection of the algorithm. So, for this case, a particular type of PIH (Average Hash) is highlighted as the most efficient one among other techniques, reaching an accuracy of 100% and frame rates on processing average of 108 fps with a Hamming Distance of 1. At the end, the proposed framework has remarkable identification skills, and presents an efficient search. Furthermore, presents the steps to select the best algorithm and its more adequate parameters, according to the requirements of each particular case.

Audio fingerprint parameterization for multimedia advertising identification

Abstract: This article follows step by step a general framework for fingerprint extraction in order to develop a system for advertisements' monitoring. The parameterization process uses some spatial and spectral characteristics measured over 600 advertisements that contain various types of sounds. Key factors such as accuracy, process time, and granularity are analyzed together in order to enhance the system performance. At the end, the algorithm shows an accuracy of 99% using three seconds of granularity samples, and also the best compromise between processing time and performance is achieved. This study suggests a set of parameterization steps which could be successfully implemented in other related audio applications.

Towards a multi-screen interactive ad delivery platform

Abstract: Interactive advertising based on multiple devices opens new possibilities for mobile applications, where users can search, select, or expand the information provided in advertising commercials by incorporating interactivity-friendly companion devices such as smart phones and tablets. In this paper, we derive the basic requirements for a flexible infrastructure that can support interactive ad applications. The infrastructure comprises a set of components and their externally visible properties, and the relationships between them. The main contributions of this work are first, establishing a desirable set of requirements for a suitable working scenario on which the different interactivity supporting systems people use in a regular basis can be easily integrated, and second, the definition of a platform which considers the different stages and requirements identified from different works in related areas.

On the implementation of a Laboratory of Digital Television according to the ISDB-Tb standard

Abstract: This paper summarizes the implementation process of the Digital Television (DTV) Laboratory of the University of Cuenca according to the open television broadcasting ISDB-Tb standard, adopted by Ecuador in 2010. The Laboratory arises as a research and testing environment for Digital Television DTV signal transmission and interactive applications. The goal of this article is to document the aspects that have been considered to simulate a real DTV scenario where: a Transport Stream (TS) is first generated, then transmitted through the communication channel and finally, received in televisions using an ISDB-Tb receiver. The TS is formed by combining DTV audiovisual content and interactive applications. Therefore, it facilitates the development and testing of new services and allows taking full advantage of the characteristics of the new DTV adopted format. Keywords: Terrestrial digital television, digital television laboratory, Ginga-NCL, interactive applications, user behavior registering, ISDB-Tb, applications server, Electronic Program Guides. RESUMEN Este articulo resume el proceso de implementacion del Laboratorio de Television Digital (DTV) de la Universidad de Cuenca, que surge como un entorno confiable de experimentacion e investigacion que hace uso de las caracteristicas asociadas al estandar ISDB-Tb adoptado por Ecuador en el ano 2010 para la transmision de senales de television abierta. El objetivo de este articulo es documentar los aspectos que se han considerado para simular un escenario real en el que un Transport Stream (TS) formado por contenido audiovisual y aplicaciones interactivas, primero se genera, para luego transmitirse a traves del canal de comunicaciones, y finalmente ser recibido en una television con receptor ISDB-Tb. Asi, se facilita el desarrollo y la experimentacion de nuevos servicios aprovechando el nuevo formato de DTV. Palabras clave: Television digital terrestre, laboratorio de television digital, Ginga-NCL, aplicaciones interactivas, registro de actividad del usuario, ISDB-Tb, servidor de aplicaciones, guia de programacion electronica.

Design of a Supervisory Control System for a Clinker Kiln Operation

Abstract: The Clinker kiln is the core of the cement production process, which is a heavy infrastructure, where a mixture of limestone and clay undergoes physical and chemical transformations at high temperatures The process has a very complex non-linear behavior, which hinders its control automatically This article presents the design of a fuzzy logic-based supervisory system for control tasks upon the Clinker kiln operation [1] The proposed supervisory system, which has been tested offline in an industrial kiln, uses process variables as the temperature in the burning area, the percentage of oxygen and the back-end temperature, to take appropriate control actions to face operating kiln conditions The considered control variables in the design are the fuel flow to the burner, the air fan speed and the kiln rotational speed As a result, the supervisory control system tests showed an improvement in kiln stability and clinker production

A robust video identification framework using perceptual image hashing

Abstract: This paper proposes a general framework that allows to identify a video in real time using perceptual image hashing algorithms. In order to evaluate the versatility and performance of the framework, it was coupled for a use case about ads tv monitoring. Four Perceptual Image Hashing (PIH) algorithms were subject to a benchmarking process in order to identify the best one for the use case. This process was focused on analyze differences in terms of discriminability (D), robustness (R), time processing (Tp) and efficiency (E). A truth table was used to obtain information about discriminability and robustness, while processing time was directly measured. An efficiency metric based on time processing and identification capacity was proposed. In general terms, DHASH and PHASH algorithms have higher identification capacities than AHASH and WHASH in order to identify a video using only one frame. Moreover, a progressive decrease in robustness with the increment of the Hamming distance is observed in all cases. However, in a specific case of tv monitoring where speed is critical, the processing time becomes the most discriminatory parameter for the selection of the algorithm. So, for this case, a particular type of PIH (Average Hash) is highlighted as the most efficient one among other techniques, reaching an accuracy of 100% and frame rates on processing average of 108 fps with a Hamming Distance of 1. At the end, the proposed framework has remarkable identification skills, and presents an efficient search. Furthermore, presents the steps to select the best algorithm and its more adequate parameters, according to the requirements of each particular case.

Semantic Recommender Systems for Digital TV: From Demographic Stereotyping to Personalized Recommendations

Abstract: Compared to analog transmissions, Digital Television (DTV) standards allows a higher number of available TV stations and consequently, a larger entertainment offer In this context, Recommender Systems (RS) support users in choosing entertainment content by narrowing their options to a reduced set based on their preferences an interests However, new users or those having incomplete profiles prevent the system to produce accurate recommendations, which is more noticeable in early stages of the RS This paper proposes the use of a demographic stereotyping approach based on minimal user attributes acquired during user registration Furthermore, we propose an experimental procedure that can be used to compare the system accuracy for the created stereotypes and for users making extensive use of the system

Towards a multi-screen interactive ad delivery platform

Abstract: Interactive advertising based on multiple devices opens new possibilities for mobile applications, where users can search, select, or expand the information provided in advertising commercials by incorporating interactivity-friendly companion devices such as smart phones and tablets. In this paper, we derive the basic requirements for a flexible infrastructure that can support interactive ad applications. The infrastructure comprises a set of components and their externally visible properties, and the relationships between them. The main contributions of this work are first, establishing a desirable set of requirements for a suitable working scenario on which the different interactivity supporting systems people use in a regular basis can be easily integrated, and second, the definition of a platform which considers the different stages and requirements identified from different works in related areas.

Ley Orgánica de Comunicación en la programación de la radio comercial. Análisis de la Ley del 1x1 en el Ecuador

Abstract: This article presents an analysis of public policy regarding the obligatory diffusion of Ecuadorian music on Ecuadorian commercial radio stations in accordance with communications laws passed in 2013. The research focuses on mass diffusion of the music, as well as commercial radio in Ecuador. In this article, the researcher aims to define “Ecuadorian music” according to national law, the role of commercial radio in Ecuadorian-created music, the difficulties experienced by local musicians in diffusing their product on local radio, and how the new laws have increased professional satisfaction among Ecuadorian musicians.