Day 1 28/11/2019
Room #1

Registration 08:30 - 09:00

Aula Magna

Opening Ceremony 09:00 - 09:15

Aula Magna

Plenary. Prof. Julio Madera: Estimation of Distribution Algorithms: from Theory to Applications 09:15 - 10:00

Aula Magna

Plenary. Prof. Nathaniel Osgood: Multiparadigm modeling in Health 10:15 - 11:00

Room R27

Coffee Break 11:00 - 11:30

Heuristic Design and Optimization 11:30 - 13:00

Room R27
11:30 - 12:00
Backbone distribution network design for the Mexican automotive industry

The logistics network of Ford Company in Mexico, was analyzed to propose a better logistics network in the country to improve delivery times to customers. The analysis was conducted with Greenfield Analysis and Network Optimiza-tion. Taking into account the information given by Ford, it was possible to obtain optimal scenarios for the company, which involved the construction of distribu-tion centers in the State of Hidalgo.
Authors: José Antonio Marmolejo-Saucedo (Universidad Panamericana), Brenda Retana-Blanco (Universidad Anahuac Mexico), Roman Rodriguez-Aguilar (Universidad Panamericana), Erika Pedraza-Arroyo (Universidad Anahuac Mexico),
Hide Authors & Abstract

Show Authors & Abstract
12:00 - 12:30
Location of Bases for Pre-Hospital Services

This paper studies the problem of choosing the number of emergency vehicles and the location of their bases in an urban area (Mexico City) in order to have an effective response to traffic accidents. To this end, the use of two types of vehicle will be considered: traditional ambulances and motorcycle ambulances. The potential demands of the service are considered uncertain, so we developed a stochastic programming model for the problem based on scenarios, to address the different categories of uncertainty associated with the aim of minimizing the total cost to install services ensuring a level of coverage. The results of this research allow system designers to consider different tactical and strategic decisions in the design and management of health service networks from cost and coverage perspectives. The model was solved using Benders decomposition.
Authors: Zaida Alarcón Bernal (Universidad Nacional Autónoma de México), Ricardo Aceves-García (Universidad Nacional Autónoma de México), JORGE LUIS ROJAS ARCE (Universidad Nacional Autónoma de México),
Hide Authors & Abstract

Show Authors & Abstract
12:30 - 13:00
A hybrid model for improving the performance of basketball lineups

An optimization model of the NBA team alignments is presented to improve the performance of the teams according to the selected alignment. A set of variables such as inputs and outcome variables are taken into account to optimize the results. Additionally, a technical efficiency analysis was performed on the performance of the alignments selected by the optimization model to validate the results. The results show that the alignments selected through the optimization model were those with greater technical efficiency for the equipment. The application of optimization methods and technical efficiency can be a robust tool for decision making in the sports field.
Authors: Roman Rodriguez-Aguilar (Universidad Panamericana, Escuela de Ciencias Económicas y Empresariales, Augusto Rodin 498, México, Ciudad de México, 03920, México), Rodrigo Infante-Escudero (Universidad Anáhuac), José-Antonio Marmolejo-Saucedo (Universidad Panamericana),
Hide Authors & Abstract

Show Authors & Abstract

Lunch 13:00 - 15:00

Mixed-Integer Programming and Global Optimization 15:00 - 16:30

Room R27
15:00 - 15:30
A New Approach of the Rain-Fall Optimization Algorithm Using Parallelization

This paper introduces a new implementation of the Rain-fall Optimization Algorithm (RFO) proposed by Kaboli, Sevbaraj and Rahim in ”Rain-fall optimization algorithm a population based algorithm for solving constrained optimization problems”[6]. RFO is a natural inspired algorithm which is based on the behavior of the water drops produced by a rainfall going down through a mountain to find the minimum values of the multidimensional functions. The algorithm was tested on four multidimensional benchmark functions: Ackley, Griewank, Rosenbrock and Sphere function. It was also tested in a four-dimensional function, the Kowalik function. The first procedure was to match the results of the rewritten algorithm with the results obtained by the original authors of the algorithm. Then the algorithm had to be modified in order to make some improvements and to find better results with better quality. The main modifications were a new equation to modify the step size for a function called explosion process and a parallel execution of the algorithm with two different restarting techniques: restart to the best and genetic restart to the best.
Authors: Juan Guerrero- Valadez (Universidad Panamericana), Felix Martinez-Rios (Universidad Panamericana),
Hide Authors & Abstract

Show Authors & Abstract
15:30 - 16:00
Using Hadamard transform for cryptanalysis of pseudo-random generators in stream ciphers

This paper discusses the results obtained by an application of the Hadamard transform to cryptanalysis, and in particular, to determine the probability to decipher different pseudo-random number generators used as components of stream ciphers.
Authors: Omar Rojas (Universidad Panamericana. Escuela de Ciencias Económicas y Empresariales. Zapopan, Jalisco, 45010, México), Guillermo Sosa-Gomez (Universidad Panamericana. Escuela de Ciencias Económicas y Empresariales. Zapopan, Jalisco, 45010, México), Octavio Paez-Osuna (Ronin Institute for Independent Scholarship, Montclair, NJ 07042, USA),
Hide Authors & Abstract

Show Authors & Abstract
16:00 - 16:30
A new heuristic based on a parallel implementation of Firefly Algorithm

In this paper a new optimization algorithm is introduced, inspired in the Firefly Algorithm, which is based on the behavior of fireflies, especially on their flashing characteristics. This new algorithm runs C parallel executions of the algorithm that, after a determined number of iterations, are paused and their results are compared so that, using different restarting techniques, new positions for the fireflies in each thread are determined to continue the executions. This parallel implementation allows us to have more diversity in the experiments, allowing Firefly Algorithm to obtain better results. For testing the restarting techniques mentioned before, we used 6 multimodal benchmark functions: Step, Sphere, Sum Square, Trid 10, Zakharov and Rosenbrock functions. For this paper different tests were performed to determine the value of the parameters needed to run the algorithm. These values were used to run the final experiments. The results obtained with the implementation of our algorithm with the different restarting techniques and the parameters established are compared to the results published by other authors, so that we were able to prove the efficiency of this new algorithm. We obtained significantly better results in some of the test functions, proving that our algorithm is a breakthrough in nature-inspired algorithms.
Authors: Alfonso Murillo-Suarez (Universidad Panamericana), Felix Martinez-Rios (Universidad Panamericana),
Hide Authors & Abstract

Show Authors & Abstract

Coffee Break 16:30 - 17:00

Plenary. Prof. Gonzalo Abascal: Blockchain: Core technology to build a trusted personal biometric identity system in Mexico 17:00 - 17:45

Room R27

Gala Dinner 19:00 - 21:00

Buen Bife Insurgentes
Day 2 29/11/2019
Room #1

Mixed-Integer Programming and Global Optimization 09:30 - 11:00

Room R27
09:30 - 10:00
Algorithm to detect and calculate the cerebrospinal fluid (CSF) through Magnetic Resonance Imaging (MRI)

In this work, we introduce a heuristic segmentation algorithm for the detec-tion and subsequent segmentation of the volume of cerebrospinal fluid (CSF) that allows calculating it from MRI, and thus calculating the amount of anesthesia to be used in patients.
Authors: Omar Rojas (Universidad Panamericana. Escuela de Ciencias Económicas y Empresariales. Zapopan, Jalisco, 45010, México.), Guillermo Sosa-Gómez (Universidad Panamericana. Escuela de Ciencias Económicas y Empresariales. Zapopan, Jalisco, 45010, México.), Enrique González-Martín (Universidad Central de Las Villas, Cuba),
Hide Authors & Abstract

Show Authors & Abstract
10:00 - 10:30
SMOTE-Cov: A new over-sampling method based on the Covariance Matrix

Nowadays, many machine learning tasks involve learning from imbalanced datasets, leading to the miss-classification of the minority class. One of the state-of-the-art approaches to "solve" this problem at the data level is Synthetic Minority Over-sampling Technique (SMOTE) which in turn uses KNN to select and generate new instances. However, those approaches do not take into account the attributes’ dependency relationship. This paper presents SMOTE-Cov, a modified SMOTE that use Covariance Matrix instead of KNN to balance datasets, with continuous attributes and binary class. We implemented two variants SMOTECovI, which generates new values within the interval of each attribute and SMOTE-CovO, which allows some values to be outside the interval of the attributes. SMOTE-Cov was validated by means of an experimental study using C4.5 as classifier. The results show that our approach has a similar performance as the state- of-the-art approaches. After applying the statistical tests of Friedman and Holm we did not find any big significance difference.
Authors: Ireimis Leguen-deVarona (University of Camagüey, Cuba), Julio Madera (University of Camagüey, Cuba), Yoan Martínez-López (University of Camagüey, Cuba), José Hernández-Nieto (University of Camagüey, Cuba),
Hide Authors & Abstract

Show Authors & Abstract
10:30 - 11:00
DEVELOPMENT OF RENEWABLE ELNERGY RESOURCES IN GLOBAL ENERGY INTERCONNECTION

Today electricity demands are increasing day by day and cause unbalance in the present conventional grid system. So people try to change from conventional grid to smart grid. The smart grid can help us to reach the goal of clean air and energy independence by integrating renewable energy sources (RES) into the grid system. Power plants based on RES depend on the various geographical and environmental factors of the locations of RES power stations. By knowing these factors of locations, it can be easier to make right decision to install the power plant. To integrate RES into the grid system, the first thing to do is to determine where RES power plants should be placed, and to determine the location of new prospective power plants based on RES.
Authors: Thu Min (National Research University “Moscow Power Engineering Institute”), He Yang (National Research University “Moscow Power Engineering Institute”), Michael Tyagunov (National Research University “Moscow Power Engineering Institute”), Shestopalova Alexandrovna (National Research University “Moscow Power Engineering Institute”), Aung Ko (National Research University “Moscow Power Engineering Institute”),
Hide Authors & Abstract

Show Authors & Abstract

Coffee Break 11:00 - 11:30

Simulation and Distributed Systems 11:30 - 13:30

Room R27
11:30 - 12:00
Didactic Tool for Teaching Election Algorithms in Distributed Systems

Currently there are several platforms that offer teaching services and new knowledge to people who require it. However, there is a need to provide tools that support the appropriation of knowledge in a simpler way and with a higher margin of success. In the teaching of distributed systems, the correct understanding of distributed algorithms is an important challenge, since they allow defining and organizing the processes that compete for system resources, or working together to solve a task. Being able to understand an algorithm with a certain degree of difficulty and make this degree of difficulty decrease with tools that can facilitate student learning is one of the main objectives of this tool.
Authors: Francisco de Asis Lopez-Fuentes (Universidad Autónoma Metropolitana), Araceli López-Reyes (Universidad Autónoma Metropolitana),
Hide Authors & Abstract

Show Authors & Abstract
12:00 - 12:30
Vulnerability of Network Coding under Pollution Attacks

The growing data demand in the communication networks has encouraged the scientific community to investigate techniques which contributes with new models to improve communications and connectivity. Network coding is an important contribution for transmission of information in the communication networks. This technique allows optimizing the data transmission times in a network. However, the absence of security mechanisms in the network coding schemes expose to data to different types of attacks. In this paper, we analyze how pollution attack affects the network coding performance. We analyze the behavior our network coding scheme under the presence of a pollution attack in different points of the network to detect the weakest points in our scheme.
Authors: Francisco de Asis Lopez-Fuentes (Universidad Autónoma Metropolitana), Raul Ortega-Vallejo (Universidad Autónoma Metropolitana),
Hide Authors & Abstract

Show Authors & Abstract
12:30 - 13:00
Secure Key Distribution Prototype based on Kerberos

The Internet isn't a secure place and many of the protocols used on the Internet don't provide security features. Therefore, many of the applications sent with passwords, but aren't encrypted by in the network are extremely vulnerable to possible attacks. An example is the Kerberos Protocol, which is a protocol integrated by three servers (SA, TGS and SS), but these communication servers never securely authenticate each other and validate that they are really them. Therefore, these servers need a prototype that allows the secure distribution of keys between them in order to provide a greater security to the Kerberos authentication protocol, due to the fact that the Kerberos Protocol doesn't provide authentication between its servers. To deal with this problem our solution implement a referee as responsible for creating and distributing encrypted keys using encryption algorithms. This referee is responsible for providing each of the distributed session server keys (KDC), once the session keys are received to the corresponding servers, with them it will be possible to encrypt or decrypt the information provided by the referee. Our goal is to provide greater security during a communication between servers, by validating that the communication between these servers is secure and authentic. Thus, servers reduce the risk of possible attacks.
Authors: Francisco de Asis Lopez-Fuentes (Universidad Autónoma Metropolitana), Abigail Veronica Chantes-Barrios (Universidad Autónoma Metropolitana),
Hide Authors & Abstract

Show Authors & Abstract

Lunch 13:30 - 15:00

Information Technologies 15:00 - 16:50

Room R27
15:00 - 15:30
A Sentiment Analysis Method for Analyzing Users Opinions about Drugs for Chronic Diseases

Nowadays, more and more people use the Web as the primary medium for answering their queries and making decisions in multiple domains, not being the exception the healthcare domain. In this sense, blogs, forums, wikis, social networks, and review websites about chronic diseases management must be exploited to derive actionable knowledge that support and improve the health self-management of this kind of diseases, which are among the most prevalent medical conditions in low and middle. This work proposes a sentiment analysis method that combines machine learning with psycholinguistic features to determine the polarity of the user’s opinions about drugs for chronic diseases such as diabetes and hypertension. The effectiveness of this method was measured by using a corpus of opinions written in Spanish. These opinions were provided by people with diabetes and/or hypertension that have lived with such diseases for many years. The proposed method obtained encouraging results based on the F-measure metric, ranging from 0.725 to 0.793 for the SMO, and BayesNet classification techniques.
Authors: María del Pilar Salas-Zárate (Tecnológico Nacional de México/I. T. Orizaba, Av. Oriente 9 No. 852, Col. E. Zapata, 94320, Orizaba, Veracruz, México.), Giner Alor-Hernández (Tecnológico Nacional de México/I. T. Orizaba, Av. Oriente 9 No. 852, Col. E. Zapata, 94320, Orizaba, Veracruz, México.), Jorge Luis García-Alcaraz (Universidad Autónoma de Ciudad Juárez), Luis Omar Colombo-Mendoza (Tecnológico Nacional de México/I. T. Orizaba, Av. Oriente 9 No. 852, Col. E. Zapata, 94320, Orizaba, Veracruz, México.), Mario Andrés Paredes-Valverde (Tecnológico Nacional de México/I. T. Orizaba, Av. Oriente 9 No. 852, Col. E. Zapata, 94320, Orizaba, Veracruz, México.), José Luis Sánchez-Cervantes (CONACYT-Tecnológico Nacional de México/I. T. Orizaba, Av. Oriente 9, No. 852, Col. E. Zapata, 94320, Orizaba, Veracruz, México),
Hide Authors & Abstract

Show Authors & Abstract
15:30 - 16:00
A Comparison of Speech-to-Speech Neural Network Methodologies for Digit Pronunciation

In this work, the classical problem of digit recognition and pronunciation from an audio source in Spanish is revisited and compared with that of directly teaching a deep neural network to pronounce the corresponding digit. While the first approach roughly corresponds to that of most current speech processing methodologies that intend to identify and reconstruct phonetic units, before performing any task from reproducing to translation, the second approach is rarely found in the literature despite the fact that it is clearly more biologically inspired than the first one. Advantages and disadvantages of both methodologies are discussed based on the obtained results.
Authors: Miguel Bernal (Sonora Institute of Technology), Manuel Quintana (Sonora Institute of Technology),
Hide Authors & Abstract

Show Authors & Abstract
16:00 - 16:30
Main Metric Components in the generation of mixed indicators: an application of SGVD methodology

The analysis of mixed principal components is presented by applying the generalized singular decomposition methodology (GSVD). This multivariate analysis allows quantitative and qualitative analysis, combining principal component analysis with multiple correspondence analysis. The GSVD methodology is developed and applied to the data of the national survey of household income and expenditure in Mexico for the period 2016. The objective is to build an indicator of consumption patterns of Mexican households through a set of variables that consider sociodemographic aspects of households (qualitative) as well as variables that interest consumption items of households (quantitative). The results show that the indicator generated by mixed main components allows characterizing sets of households according to their sociodemographic characteristics and consumption patterns. This indicator allows comprehensive evaluation of household profiles according to interest consumption items and defined sociodemographic variables. The results are presented by applying the Varimax rotation, which allows a better interpretation of the mixed main components generated.
Authors: Roman Rodriguez-Aguilar (Universidad Panamericana, Escuela de Ciencias Económicas y Empresariales),
Hide Authors & Abstract

Show Authors & Abstract
16:30 - 16:50
Proofs of the Undecidability of Stegananalysis Techniques

Steganalysis comprises a set of techniques that aim to find hidden information inside different types of digital media. In contrary, Steganography, comprises a group of techniques that, by manipulation of a cover object, intends to hide information in it to make the information imperceptible. Current steganalysis techniques suffer from a certain degree of failure in detection of a payload and, frequently, the impossibility to discover if a media hides any information in it. In this work, we prove that the detection of hidden material within a media, or a Steganalysis procedure, is an undecidable problem. Our proof comprises two tests: first, we demonstrate the undecidability by using the principle of Diagonalization of Cantor and second, we apply a reduction technique based on the undecidability of malware detection, based on the hypothesis that there exists a similitude between Steganography techniques and the generation of an innocuous computer virus. Both demonstrations proved that, indeed, the steganalysis procedures are undecidable problems.
Authors: Juan Gutierrez-Cardenas (Universidad de Lima),
Hide Authors & Abstract

Show Authors & Abstract

Coffee Break 16:50 - 17:00

Best paper award 17:00 - 17:15

Closing Ceremony 17:15 - 17:30

Room R27