Pub Date : 2018-05-16DOI: 10.1007/978-3-030-03023-0_7
Dorfell Parra, Carlos Camargo
{"title":"A Systematic Literature Review of Hardware Neural Networks","authors":"Dorfell Parra, Carlos Camargo","doi":"10.1007/978-3-030-03023-0_7","DOIUrl":"https://doi.org/10.1007/978-3-030-03023-0_7","url":null,"abstract":"","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133393819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1007/978-3-030-03023-0_11
G. A. Ramos, Jesús A. López
{"title":"Comparison of Evolutionary Algorithms for Estimation of Parameters of the Equivalent Circuit of an AC Motor","authors":"G. A. Ramos, Jesús A. López","doi":"10.1007/978-3-030-03023-0_11","DOIUrl":"https://doi.org/10.1007/978-3-030-03023-0_11","url":null,"abstract":"","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124747414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1109/COLCACI.2018.8484849
H. Nieto-Chaupis
This paper presents a study about the impact of the so-called teleconsults applied in those patients belonging to peripheral areas of Lima city with a diagnosis of diabetes and manifesting depressive episodes. We focus in essence in the capability and efficiency of the teleconsults to tackle the progress of diabetes accompanied of depress in adult population. Firstly we have applied a survey whose resulting statistics enters a mathematical formalism based on probabilities of success and by which we have evaluated for several scenarios with different efficiencies that have been constructed with the parameters of Telemedicine. We have found for a concrete human group that when the patient adds teleconsults in their treatment of diabetes and depression, their recovery in terms of stabilizing their glucose and a by stopping depression in a very early stage could take 15 3 days after the 5th day of teleconsults. Our study have concluded that psychological disturbs on the behavior of patients might have effect on their diabetes’s treatment particularly in those living in peripheral areas of Lima city. However we have identified that the eHealth system might be limited seriously.
{"title":"Are Teleconsults Enough Efficient to Tackle the Progress of Type-2 Diabetes and Depress in Adult Patients?","authors":"H. Nieto-Chaupis","doi":"10.1109/COLCACI.2018.8484849","DOIUrl":"https://doi.org/10.1109/COLCACI.2018.8484849","url":null,"abstract":"This paper presents a study about the impact of the so-called teleconsults applied in those patients belonging to peripheral areas of Lima city with a diagnosis of diabetes and manifesting depressive episodes. We focus in essence in the capability and efficiency of the teleconsults to tackle the progress of diabetes accompanied of depress in adult population. Firstly we have applied a survey whose resulting statistics enters a mathematical formalism based on probabilities of success and by which we have evaluated for several scenarios with different efficiencies that have been constructed with the parameters of Telemedicine. We have found for a concrete human group that when the patient adds teleconsults in their treatment of diabetes and depression, their recovery in terms of stabilizing their glucose and a by stopping depression in a very early stage could take 15 3 days after the 5th day of teleconsults. Our study have concluded that psychological disturbs on the behavior of patients might have effect on their diabetes’s treatment particularly in those living in peripheral areas of Lima city. However we have identified that the eHealth system might be limited seriously.","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132317657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1007/978-3-030-03023-0_2
N. Salazar, Jesus Alfonso Lopez Sotelo, Gustavo Andres Salazar Gomez
{"title":"Application of Transfer Learning for Object Recognition Using Convolutional Neural Networks","authors":"N. Salazar, Jesus Alfonso Lopez Sotelo, Gustavo Andres Salazar Gomez","doi":"10.1007/978-3-030-03023-0_2","DOIUrl":"https://doi.org/10.1007/978-3-030-03023-0_2","url":null,"abstract":"","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122584591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1007/978-3-030-03023-0_4
Diego F. Sendoya-Losada, Diana C. Vargas-Duque, Ingrid J. Ávila-Plazas
{"title":"Implementation of a neural control system based on PI control for a non-linear process","authors":"Diego F. Sendoya-Losada, Diana C. Vargas-Duque, Ingrid J. Ávila-Plazas","doi":"10.1007/978-3-030-03023-0_4","DOIUrl":"https://doi.org/10.1007/978-3-030-03023-0_4","url":null,"abstract":"","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116320275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1109/COLCACI.2018.8484847
B. Pérez, C. Castellanos, D. Correal
The prevention of students dropping out is considered very important in many educational institutions. In this paper we describe the results of an educational data analytics case study focused on detection of dropout of System Engineering (SE) undergraduate students after 7 years of enrollment in a Colombian university. Original data is extended and enriched using a feature engineering process. Our experimental results showed that simple algorithms achieve reliable levels of accuracy to identify predictors of dropout. Decision Trees, Logistic Regression and Na¨ıve Bayes results were compared in order to propose the best option. Also, Watson Analytics is evaluated to establish the usability of the service for a non expert user. Main results are presented in order to decrease the dropout rate by identifying potential causes. In addition, we present some findings related to data quality to improve the students data collection process.
{"title":"Applying Data Mining Techniques to Predict Student Dropout: A Case Study","authors":"B. Pérez, C. Castellanos, D. Correal","doi":"10.1109/COLCACI.2018.8484847","DOIUrl":"https://doi.org/10.1109/COLCACI.2018.8484847","url":null,"abstract":"The prevention of students dropping out is considered very important in many educational institutions. In this paper we describe the results of an educational data analytics case study focused on detection of dropout of System Engineering (SE) undergraduate students after 7 years of enrollment in a Colombian university. Original data is extended and enriched using a feature engineering process. Our experimental results showed that simple algorithms achieve reliable levels of accuracy to identify predictors of dropout. Decision Trees, Logistic Regression and Na¨ıve Bayes results were compared in order to propose the best option. Also, Watson Analytics is evaluated to establish the usability of the service for a non expert user. Main results are presented in order to decrease the dropout rate by identifying potential causes. In addition, we present some findings related to data quality to improve the students data collection process.","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115026190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1109/COLCACI.2018.8484850
H. Nieto-Chaupis
Often system identification is used to attack problems corresponding in those system which exists a perception of type input-output. We brought this methodology to apply it to the concrete case of analyze the risks that are continuously expected due to the climatic variations as consequence of the arrival of phenomena such as "El Niño". In this paper we have associated the Volterra’a master equation to a one interpretation in the territory of probabilities. The resulting Volterra output is therefore seen as a kind of risk probability. For this end we used Google images by which we have focused our attention to the populations located near to rivers that are in permanent risk in summer times. This methodology can be finally seen as a scheme for disaster anticipation. We paid attention to the zones which have been affected by river overflow along the coast of Peru.
{"title":"About the Usage of System Identification Methodologies For Climate Risks Analysis Along the Peruvian Coast","authors":"H. Nieto-Chaupis","doi":"10.1109/COLCACI.2018.8484850","DOIUrl":"https://doi.org/10.1109/COLCACI.2018.8484850","url":null,"abstract":"Often system identification is used to attack problems corresponding in those system which exists a perception of type input-output. We brought this methodology to apply it to the concrete case of analyze the risks that are continuously expected due to the climatic variations as consequence of the arrival of phenomena such as \"El Niño\". In this paper we have associated the Volterra’a master equation to a one interpretation in the territory of probabilities. The resulting Volterra output is therefore seen as a kind of risk probability. For this end we used Google images by which we have focused our attention to the populations located near to rivers that are in permanent risk in summer times. This methodology can be finally seen as a scheme for disaster anticipation. We paid attention to the zones which have been affected by river overflow along the coast of Peru.","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126039367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1109/COLCACI.2018.8484853
H. Nieto-Chaupis
We present a computer-based eHealth system expected to provide tele-consults aimed to reduce complications due to the diabetes disease in adult population mainly between 30 and 60 years old. The software of the tele-consultations system which is essentially based in probabilities and entirely based in the Monte Carlo technology whose main philosophy: accept or reject, This stochastic computing method is supported with a mathematical model which is build through acquired data and experience that allows us to model and carry out predictions on the glucose’s values in time within a certain statistical error. The idea behind of this eHealth system is the rapid identification of those people with a potential risk to acquire complications derived from the high values of glucose in time. The conclusion derived from this computer-based study is that of the opportune intervention derived from the tele-consultations might alleviate and to improve the diabetes treatment by employing simple mobile phones and minimal software applications. We illustrated the prospective implementation of this tele-care system with simulations for people with an old diagnosis of diabetes and demonstrating the prospective role o these eHealth systems aimed to improve the quality of life in the middle and long term. From a combined sample 3 from 4 diabetes patients might be keeping under control their glucose’s values with a continuous assistance of the proposed eHealth system.
{"title":"Continuous Surveillance By Tele-consults Based on Monte Carlo Algorithms to Anticipate and Lessen Risk Levels Due to Type-2 Diabetes Complications","authors":"H. Nieto-Chaupis","doi":"10.1109/COLCACI.2018.8484853","DOIUrl":"https://doi.org/10.1109/COLCACI.2018.8484853","url":null,"abstract":"We present a computer-based eHealth system expected to provide tele-consults aimed to reduce complications due to the diabetes disease in adult population mainly between 30 and 60 years old. The software of the tele-consultations system which is essentially based in probabilities and entirely based in the Monte Carlo technology whose main philosophy: accept or reject, This stochastic computing method is supported with a mathematical model which is build through acquired data and experience that allows us to model and carry out predictions on the glucose’s values in time within a certain statistical error. The idea behind of this eHealth system is the rapid identification of those people with a potential risk to acquire complications derived from the high values of glucose in time. The conclusion derived from this computer-based study is that of the opportune intervention derived from the tele-consultations might alleviate and to improve the diabetes treatment by employing simple mobile phones and minimal software applications. We illustrated the prospective implementation of this tele-care system with simulations for people with an old diagnosis of diabetes and demonstrating the prospective role o these eHealth systems aimed to improve the quality of life in the middle and long term. From a combined sample 3 from 4 diabetes patients might be keeping under control their glucose’s values with a continuous assistance of the proposed eHealth system.","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114371332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-16DOI: 10.1109/COLCACI.2018.8484845
F. Trujillano, Andres Flores, Carlos Saito, Mario Balcazar, Daniel Racoceanu
Climate change is affecting the agricultural production in Ancash - Peru and corn is one of the most important crops of the region. It is essential to constantly monitor grain yields and generate statistic models in order to evaluate how climate change will affect food security. The present study proposes as a proof of concept to use Deep learning techniques for the classification of near infrared images, acquired by an Unmanned Aerial Vehicle (UAV), in order to estimate areas of corn, for food security purpose. The results show that using a well balanced (altitudes, seasons, regions) database during the acquisition process improves the performance of a trained system, therefore facing crop classification from a variable and difficult-to-access geography.
{"title":"Corn classification using Deep Learning with UAV imagery. An operational proof of concept","authors":"F. Trujillano, Andres Flores, Carlos Saito, Mario Balcazar, Daniel Racoceanu","doi":"10.1109/COLCACI.2018.8484845","DOIUrl":"https://doi.org/10.1109/COLCACI.2018.8484845","url":null,"abstract":"Climate change is affecting the agricultural production in Ancash - Peru and corn is one of the most important crops of the region. It is essential to constantly monitor grain yields and generate statistic models in order to evaluate how climate change will affect food security. The present study proposes as a proof of concept to use Deep learning techniques for the classification of near infrared images, acquired by an Unmanned Aerial Vehicle (UAV), in order to estimate areas of corn, for food security purpose. The results show that using a well balanced (altitudes, seasons, regions) database during the acquisition process improves the performance of a trained system, therefore facing crop classification from a variable and difficult-to-access geography.","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134156860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/COLCACI.2018.8484855
Mario A. Giraldo, J. Duitama, J. D. Arias-Londoño
Support Vector Machine (SVM) is a classifier widely used in machine learning because of its high generalization capacity. The sequential minimal optimization (SMO) its most popular implementation, scales somewhere between linear and quadratic in the training set size for various test problems. This fact makes using SVM to train large data sets have a high computational cost. SVM implementations on distributed systems such as MapReduce and Spark have shown efficiency to improve computational cost; this paper analyzes how data subset size and number of mapping tasks affects SVM performance on MapReduce and Spark. Also, a cost model as a useful tool for setting data subset size according to available hardware and data to be processed is proposed.
{"title":"MapReduce and Spark-based architecture for bi-class classification using SVM","authors":"Mario A. Giraldo, J. Duitama, J. D. Arias-Londoño","doi":"10.1109/COLCACI.2018.8484855","DOIUrl":"https://doi.org/10.1109/COLCACI.2018.8484855","url":null,"abstract":"Support Vector Machine (SVM) is a classifier widely used in machine learning because of its high generalization capacity. The sequential minimal optimization (SMO) its most popular implementation, scales somewhere between linear and quadratic in the training set size for various test problems. This fact makes using SVM to train large data sets have a high computational cost. SVM implementations on distributed systems such as MapReduce and Spark have shown efficiency to improve computational cost; this paper analyzes how data subset size and number of mapping tasks affects SVM performance on MapReduce and Spark. Also, a cost model as a useful tool for setting data subset size according to available hardware and data to be processed is proposed.","PeriodicalId":138992,"journal":{"name":"2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121800090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：