Pub Date : 2018-10-01DOI: 10.1109/CONIITI.2018.8587094
José Manjarrés, Vitto Russo, J. Peñaranda, Mauricio Pardo
This paper describes a real-time human activity recognition and heart rate tracking system using ultra-low power wearables in a mobile platform. The mobile application shows both real-time and historical data of activities performed by the user along with the average heart rate for each activity. Random Forest and k-Nearest Neighbors algorithms were used to classify, showing general accuracies of 97.3% and 98.6%, respectively, with only eight features. The presented heart rate monitor is compared with an Apple Watch series 3 and they were demonstrated to display statistically equal values, confirming the reliability of the built monitor. Both wearables have a diameter of 4.5cm and consume currents below 10mA on transmission events and are powered with coin cell batteries, setting feasible characteristics for the need of modern wearable systems.
{"title":"Human Activity and Heart Rate Monitoring System in a Mobile Platform","authors":"José Manjarrés, Vitto Russo, J. Peñaranda, Mauricio Pardo","doi":"10.1109/CONIITI.2018.8587094","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587094","url":null,"abstract":"This paper describes a real-time human activity recognition and heart rate tracking system using ultra-low power wearables in a mobile platform. The mobile application shows both real-time and historical data of activities performed by the user along with the average heart rate for each activity. Random Forest and k-Nearest Neighbors algorithms were used to classify, showing general accuracies of 97.3% and 98.6%, respectively, with only eight features. The presented heart rate monitor is compared with an Apple Watch series 3 and they were demonstrated to display statistically equal values, confirming the reliability of the built monitor. Both wearables have a diameter of 4.5cm and consume currents below 10mA on transmission events and are powered with coin cell batteries, setting feasible characteristics for the need of modern wearable systems.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115686427","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587070
R. García-Vélez, V. Robles-Bykbaev, M. López-Notes, D. Calle-López, M. Barros-Pontón, J. Galán-Mena
The Higher Education Initiative (HEI) promoted by UNESCO and other international institutions, proposes four fundamental postulates related to the sustainable development. From these postulates, one focuses on the cooperation with local and international networks. In the same way, it is important mentioning that in every group, it members are freely interacting individuals who share accepted norms and goals and have a collective identity. For these reasons, during the university training process, it is fundamental that students learn skills to work in groups as well as to address problems in multidisciplinary teams. In the light of the above, in this paper, we present an intelligent system that determines the best alternatives to automatically generate groups of students to address practice activities and problems. Our proposal uses a genetic algorithm to analyze the personality of the students and their academic profiles. The achieved results are encouraging and show a precision of 87% according to an expert team that evaluated the system.
{"title":"An Intelligent System Based on Genetic Algorithms to Generate Study Groups Using Personality Traits and Academic Profiles in Higher Education","authors":"R. García-Vélez, V. Robles-Bykbaev, M. López-Notes, D. Calle-López, M. Barros-Pontón, J. Galán-Mena","doi":"10.1109/CONIITI.2018.8587070","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587070","url":null,"abstract":"The Higher Education Initiative (HEI) promoted by UNESCO and other international institutions, proposes four fundamental postulates related to the sustainable development. From these postulates, one focuses on the cooperation with local and international networks. In the same way, it is important mentioning that in every group, it members are freely interacting individuals who share accepted norms and goals and have a collective identity. For these reasons, during the university training process, it is fundamental that students learn skills to work in groups as well as to address problems in multidisciplinary teams. In the light of the above, in this paper, we present an intelligent system that determines the best alternatives to automatically generate groups of students to address practice activities and problems. Our proposal uses a genetic algorithm to analyze the personality of the students and their academic profiles. The achieved results are encouraging and show a precision of 87% according to an expert team that evaluated the system.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123071209","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587074
Renzo Arimborgo, Edson Espinoza, G. Power, G. Quispe, J. A. Merino
Because of frost in high Peruvian andean areas die alpacas (having reported more of 160 000 deaths in 2015), which can be avoided with suitable sheds. Faced with this reality, it was constructed of a prototype with solar air heating, which has been tested and calculated for use in these sheds with favorable results. During the investigation the heat transfer required by the shed was analyzed, for keep the alpacas in a closed environment at 10°C. It is worth mentioning that there are alpaca communities that supports temperatures of up to -20°C in the Altiplano area. The research was conducted in the district of San Juan de Tarucani in Arequipa and in the district of Ocuviri in Puno. The proposed model permits to keep the alpacas more protected in a warm environment using renewable energy with a system of heat storage for the low temperatures at the nights. As a result of the research, with the development of the proposed solar collector, it is possible to increase the temperature internal of the shed in an ideal range of 5°C.
{"title":"Solar Heating for Alpaca's Sheds in Peruvian Andean Region","authors":"Renzo Arimborgo, Edson Espinoza, G. Power, G. Quispe, J. A. Merino","doi":"10.1109/CONIITI.2018.8587074","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587074","url":null,"abstract":"Because of frost in high Peruvian andean areas die alpacas (having reported more of 160 000 deaths in 2015), which can be avoided with suitable sheds. Faced with this reality, it was constructed of a prototype with solar air heating, which has been tested and calculated for use in these sheds with favorable results. During the investigation the heat transfer required by the shed was analyzed, for keep the alpacas in a closed environment at 10°C. It is worth mentioning that there are alpaca communities that supports temperatures of up to -20°C in the Altiplano area. The research was conducted in the district of San Juan de Tarucani in Arequipa and in the district of Ocuviri in Puno. The proposed model permits to keep the alpacas more protected in a warm environment using renewable energy with a system of heat storage for the low temperatures at the nights. As a result of the research, with the development of the proposed solar collector, it is possible to increase the temperature internal of the shed in an ideal range of 5°C.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128030082","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587077
Samith Tatiana Cruz, Andrés Gómez, Alexandra López Sevillano, C. Lozano-Garzon
Nowadays, large, medium and small companies execute audits to verify the efficiency and effectiveness of processes and products. To manage them, there are guides, methodologies, techniques that are applied in the organization with the aim of avoiding the propagation of threats and vulnerabilities. This work was carried out in the professional services area of a small company, in which the process of Data Quality Management was taken and the audit was conducted to verify the current status of said process and identify recommendations and improvements in its execution, in order to contribute to the improvement of the quality of the developed projects. The audit was conducted based on the NTC-ISO 19011 standard, which was selected with the analyzes and results obtained in the comparison made between different existing frameworks, based on the literature and the evaluation carried out through the Delphi methodology.
{"title":"Audit to the Data Quality Management Process in a Small Organization Based on NTC-ISO 19011","authors":"Samith Tatiana Cruz, Andrés Gómez, Alexandra López Sevillano, C. Lozano-Garzon","doi":"10.1109/CONIITI.2018.8587077","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587077","url":null,"abstract":"Nowadays, large, medium and small companies execute audits to verify the efficiency and effectiveness of processes and products. To manage them, there are guides, methodologies, techniques that are applied in the organization with the aim of avoiding the propagation of threats and vulnerabilities. This work was carried out in the professional services area of a small company, in which the process of Data Quality Management was taken and the audit was conducted to verify the current status of said process and identify recommendations and improvements in its execution, in order to contribute to the improvement of the quality of the developed projects. The audit was conducted based on the NTC-ISO 19011 standard, which was selected with the analyzes and results obtained in the comparison made between different existing frameworks, based on the literature and the evaluation carried out through the Delphi methodology.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"280 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114254965","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587100
Victor Sanchez, Ernesto Iturrizaga, J. León, C. del Carpio
This work proposes an algorithm for the detection of the intestinal parasite Giardia Lamblia from digital images obtained through a digital camera and an optical microscope. Its purpose is to reduce the time of visual inspection analysis of the sample made by the specialist in laboratory. The proposed algorithm converts the acquired RGB images to the HSV colour space. First, the saturation component is filtered using a Gaussian filter, in order to reduce the noise and standardize the areas of interest. The filtered image is thresholdized using a fixed threshold value, in order to segment the objects of interest. Then, using a labelling algorithm, a filtering is performed by object size, in order to eliminate those that do not comply with the dimensions of the parasite. Therefore, the edges are highlighted by a Canny filter, to finally apply the Hough transform and detect the morphology of the object and its physical dimensions. With this information it will be possible to validate if the object satisfies the conditions of a Giardia Lamblia parasite. The proposed method achieved a specificity of 86% and a sensitivity of 67%, processing each image in an average time of less than 2 seconds. The results were obtained from a universe of 30 images.
{"title":"An Algorithm for Giardia Lamblia Detection in Digital Images Acquired Through an Optical Microscope","authors":"Victor Sanchez, Ernesto Iturrizaga, J. León, C. del Carpio","doi":"10.1109/CONIITI.2018.8587100","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587100","url":null,"abstract":"This work proposes an algorithm for the detection of the intestinal parasite Giardia Lamblia from digital images obtained through a digital camera and an optical microscope. Its purpose is to reduce the time of visual inspection analysis of the sample made by the specialist in laboratory. The proposed algorithm converts the acquired RGB images to the HSV colour space. First, the saturation component is filtered using a Gaussian filter, in order to reduce the noise and standardize the areas of interest. The filtered image is thresholdized using a fixed threshold value, in order to segment the objects of interest. Then, using a labelling algorithm, a filtering is performed by object size, in order to eliminate those that do not comply with the dimensions of the parasite. Therefore, the edges are highlighted by a Canny filter, to finally apply the Hough transform and detect the morphology of the object and its physical dimensions. With this information it will be possible to validate if the object satisfies the conditions of a Giardia Lamblia parasite. The proposed method achieved a specificity of 86% and a sensitivity of 67%, processing each image in an average time of less than 2 seconds. The results were obtained from a universe of 30 images.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133166488","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587057
Andrés Baquero-Larriva, Gustavo Alvarez-Coello
Fuel consumption in transport vehicles is one of the main sources of CO2 emissions worldwide. These kind of vehicles in the most of developing countries, do not have On Board Diagnostics (OBD) systems or similar interfaces, so is essential to develop low cost, easy to build and reliable fuel consumption measurement systems. The present research focused on the development of a data acquisition system, which integrated different devices and technologies. This system uses an electronic printed circuit board (PCB) with a microcontroller that registers instant and real time measurements of diesel consumption and monitors the geographical position of the vehicle using GPS technology.
{"title":"Low Cost Data Adquisition System to Register Fuel Consumption in Diesel Engine Vehicles","authors":"Andrés Baquero-Larriva, Gustavo Alvarez-Coello","doi":"10.1109/CONIITI.2018.8587057","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587057","url":null,"abstract":"Fuel consumption in transport vehicles is one of the main sources of CO2 emissions worldwide. These kind of vehicles in the most of developing countries, do not have On Board Diagnostics (OBD) systems or similar interfaces, so is essential to develop low cost, easy to build and reliable fuel consumption measurement systems. The present research focused on the development of a data acquisition system, which integrated different devices and technologies. This system uses an electronic printed circuit board (PCB) with a microcontroller that registers instant and real time measurements of diesel consumption and monitors the geographical position of the vehicle using GPS technology.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131773042","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587091
Lina J. Alfonso, J. P. Ospina, Jorge E. Ortiz
Ad hoc networks are decentralized systems that work without a fixed infrastructure and exhibit dynamic and stochastic behaviors. These conditions allow us to analyze them through properties like self-organization, adaptation and the use of the agent paradigm for managing and controlling the network. In this article, socially inspired computing is used to implement a register module for software agents through the concepts of institution and robustness; our goal is to build a software application that keeps working under the unexpected operating conditions of the ad hoc networks. IEEE FIPA protocols were used to design the agents and the communication channels. Three scenarios were developed, and failures in the systems were simulated. The results show the robustness of the module; it can recover itself from failures and allow the services to keep operating in acceptable conditions.
{"title":"A Register Module for Agents Communities Through Robustness Property in Ad Hoc Networks","authors":"Lina J. Alfonso, J. P. Ospina, Jorge E. Ortiz","doi":"10.1109/CONIITI.2018.8587091","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587091","url":null,"abstract":"Ad hoc networks are decentralized systems that work without a fixed infrastructure and exhibit dynamic and stochastic behaviors. These conditions allow us to analyze them through properties like self-organization, adaptation and the use of the agent paradigm for managing and controlling the network. In this article, socially inspired computing is used to implement a register module for software agents through the concepts of institution and robustness; our goal is to build a software application that keeps working under the unexpected operating conditions of the ad hoc networks. IEEE FIPA protocols were used to design the agents and the communication channels. Three scenarios were developed, and failures in the systems were simulated. The results show the robustness of the module; it can recover itself from failures and allow the services to keep operating in acceptable conditions.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128793675","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587101
H. Bermudez, R. Sanchez-Iborra, W. Campo, J. Arciniegas, M. Cano
The use of adaptive transmission techniques through HTTP for the reproduction of video services is becoming more and more popular. Currently, there are problems of interoperability due to the large number of devices with different characteristics, which also used different techniques of adaptive transmission. Therefore, telecommunications service providers are looking for alternatives that allow them to support all this diversity of devices and technologies, in order to offer their users higher quality services. In this paper, we present a comparative performance evaluation of the main adaptive streaming techniques for Live Video Streaming services using QoE (Quality of Experience) as the key performance indicator. The study is carried out in an emulated LTE (Long Term Evolution) network composed by real devices (video server and client) interacting with an NS-3 simulated LTE network. We show for the constructed emulation scenario, the technology that presents the best performance in terms of delays and user mobility.
{"title":"Comparative Study of Adaptive Streaming Techniques in LTE Networks Using QoE Metrics","authors":"H. Bermudez, R. Sanchez-Iborra, W. Campo, J. Arciniegas, M. Cano","doi":"10.1109/CONIITI.2018.8587101","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587101","url":null,"abstract":"The use of adaptive transmission techniques through HTTP for the reproduction of video services is becoming more and more popular. Currently, there are problems of interoperability due to the large number of devices with different characteristics, which also used different techniques of adaptive transmission. Therefore, telecommunications service providers are looking for alternatives that allow them to support all this diversity of devices and technologies, in order to offer their users higher quality services. In this paper, we present a comparative performance evaluation of the main adaptive streaming techniques for Live Video Streaming services using QoE (Quality of Experience) as the key performance indicator. The study is carried out in an emulated LTE (Long Term Evolution) network composed by real devices (video server and client) interacting with an NS-3 simulated LTE network. We show for the constructed emulation scenario, the technology that presents the best performance in terms of delays and user mobility.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132336155","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587090
Rafael Enrique Rodriguez-Rodriguez, Andrés Felipe Quevedo Vega, A. F. Sánchez, Alexandra López, Jaime Fernando Pérez
Nowadays IT audit is a priority for large, medium and small companies, for this reason techniques and methodologies have been developed to manage IT audits, in order to avoid the spread of threats and risks within organizations. For the project development, methodologies and good practices were investigated in order to manage IT audits, looking for the most aligned to the collection of evidences as well as the execution of the tests that are done to the controls in the systems of information, the foregoing aims to make a diagnostic selection of the available methodologies for IT audit evidence collecting, as well as identify the characteristics of the applications used in the management of IT audits also called CAAT tools with their functional aspects to categorize their effectiveness against applied methodologies, for the analysis of the results of the methodologies and thus propose a model to automate the collection of documentary evidence in compliance tests in IT audit, based on a methodology.
{"title":"Design of an Automation Model for Taking Documentary Evidence of Compliance Tests of the IT Audit","authors":"Rafael Enrique Rodriguez-Rodriguez, Andrés Felipe Quevedo Vega, A. F. Sánchez, Alexandra López, Jaime Fernando Pérez","doi":"10.1109/CONIITI.2018.8587090","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587090","url":null,"abstract":"Nowadays IT audit is a priority for large, medium and small companies, for this reason techniques and methodologies have been developed to manage IT audits, in order to avoid the spread of threats and risks within organizations. For the project development, methodologies and good practices were investigated in order to manage IT audits, looking for the most aligned to the collection of evidences as well as the execution of the tests that are done to the controls in the systems of information, the foregoing aims to make a diagnostic selection of the available methodologies for IT audit evidence collecting, as well as identify the characteristics of the applications used in the management of IT audits also called CAAT tools with their functional aspects to categorize their effectiveness against applied methodologies, for the analysis of the results of the methodologies and thus propose a model to automate the collection of documentary evidence in compliance tests in IT audit, based on a methodology.","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130476491","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 : 2018-10-01DOI: 10.1109/CONIITI.2018.8587096
Álvaro Ramiro Hernández Millán, M. Mendoza-Moreno, Larry Mauricio Portocarrero López, Alexander Castro-Romero
The growing use of machine learning algorithms for image classification process using open source libraries promotes the identification of data sets to be applied on different contexts. In this way, the most outstanding algorithms for image classification with machine learning supervised techniques were implemented and their accuracy level was compared in an uncommon context, such as identification documents (combining text and images) of a university institution as a study case. The used dataset has a high complexity level in terms of design, diversity and population density. The study has provided outstanding results such as: 1) the implementation of the Transfer Learning / Image Retraining technique for which the expected performance was obtained in shorter times compared to the other techniques or algorithms studied, and 2) the need to implement a previous classifier whose objective is to refine the dataset to promote higher precision levels for new instances (new documents to classify).
{"title":"Comparative Study of Machine Learning Supervised Techniques for Image Classification Using an Institutional Identification Documents Dataset","authors":"Álvaro Ramiro Hernández Millán, M. Mendoza-Moreno, Larry Mauricio Portocarrero López, Alexander Castro-Romero","doi":"10.1109/CONIITI.2018.8587096","DOIUrl":"https://doi.org/10.1109/CONIITI.2018.8587096","url":null,"abstract":"The growing use of machine learning algorithms for image classification process using open source libraries promotes the identification of data sets to be applied on different contexts. In this way, the most outstanding algorithms for image classification with machine learning supervised techniques were implemented and their accuracy level was compared in an uncommon context, such as identification documents (combining text and images) of a university institution as a study case. The used dataset has a high complexity level in terms of design, diversity and population density. The study has provided outstanding results such as: 1) the implementation of the Transfer Learning / Image Retraining technique for which the expected performance was obtained in shorter times compared to the other techniques or algorithms studied, and 2) the need to implement a previous classifier whose objective is to refine the dataset to promote higher precision levels for new instances (new documents to classify).","PeriodicalId":292178,"journal":{"name":"2018 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121896919","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}