Pub Date : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281156
M. Greco, Carlos Hernández
Search is a universal problem-solving method in Artificial Intelligence. Specifically, Heuristic Search algorithms, such as A*, use a heuristic function to guide the search process. The heuristic function allows algorithms to explore only a part of the search space, resulting in an efficient search process. This paper presents a new heuristic function to solve the Generalized Covering Traveling Salesman Problem (GCTSP). The heuristic function is precalculated. The method to obtain the function is pre-calculating optimal solutions consecutively to small sub-problems of the GCTSP of increasing difficulty, using an incremental Best First Search algorithm, which reuses heuristics values previously precalculated. The resultating heuristic function can be used with different heuristic search algorithms. To the best of our knowledge, this problem has not been solved with Heuristic Search. This paper is the first to present a solution to the GCTSP using Heuristic Search algorithms, such as A* and Anytime search algorithms. We evaluated different Heuristic Search algorithms. The experimental evaluation shows results of the same quality, obtained orders-of-magnitude faster than the exact methods traditionally used in Operations Research.
{"title":"Heuristic Function to Solve The Generalized Covering TSP with Artificial Intelligence Search","authors":"M. Greco, Carlos Hernández","doi":"10.1109/SCCC51225.2020.9281156","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281156","url":null,"abstract":"Search is a universal problem-solving method in Artificial Intelligence. Specifically, Heuristic Search algorithms, such as A*, use a heuristic function to guide the search process. The heuristic function allows algorithms to explore only a part of the search space, resulting in an efficient search process. This paper presents a new heuristic function to solve the Generalized Covering Traveling Salesman Problem (GCTSP). The heuristic function is precalculated. The method to obtain the function is pre-calculating optimal solutions consecutively to small sub-problems of the GCTSP of increasing difficulty, using an incremental Best First Search algorithm, which reuses heuristics values previously precalculated. The resultating heuristic function can be used with different heuristic search algorithms. To the best of our knowledge, this problem has not been solved with Heuristic Search. This paper is the first to present a solution to the GCTSP using Heuristic Search algorithms, such as A* and Anytime search algorithms. We evaluated different Heuristic Search algorithms. The experimental evaluation shows results of the same quality, obtained orders-of-magnitude faster than the exact methods traditionally used in Operations Research.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115069871","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281147
V. Duarte
In recent decades, one of the most used technique is artificial neural networks (ANN), since their learning is based on a set of connections, it is transparent to the user and the result has managed to solve complex problems in the medical field. The study implemented algorithms of ANN using input data from a battery of psychometric tests. This battery assesses multiple domains of attention and executive functioning, memory and learning, sensorimotor functioning, social perception, language, and visual-spatial processing. We attempt to explore how accuracy is the use of ANN for the prediction of children with Fetal Alcohol Spectrum Disorder (FASD). We implemented the ANN with a configuration of three layers, 20 neurons in the input layer, 25 neurons in the hidden layer, and two neurons in the output layer. We studied the accuracy of the model in training and testing, also the confusion matrix of the model. Using our machine learning approach, we have trained the ANN model to predict children/adolescents with FASD with accuracy ranging from 75.5% in testing data. These results suggest that the ANN approach is a competitive and efficient methodology to detect and differentiate the cognitive neurodevelopmental consequences of prenatal alcohol exposure. However, we could not recommend the use of this technique for diagnosis FASD if the model does not improve accuracy.
{"title":"Artificial Neural Network techniques to distinguish children with Fetal Alcohol Spectrum Disorder from psychometric data","authors":"V. Duarte","doi":"10.1109/SCCC51225.2020.9281147","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281147","url":null,"abstract":"In recent decades, one of the most used technique is artificial neural networks (ANN), since their learning is based on a set of connections, it is transparent to the user and the result has managed to solve complex problems in the medical field. The study implemented algorithms of ANN using input data from a battery of psychometric tests. This battery assesses multiple domains of attention and executive functioning, memory and learning, sensorimotor functioning, social perception, language, and visual-spatial processing. We attempt to explore how accuracy is the use of ANN for the prediction of children with Fetal Alcohol Spectrum Disorder (FASD). We implemented the ANN with a configuration of three layers, 20 neurons in the input layer, 25 neurons in the hidden layer, and two neurons in the output layer. We studied the accuracy of the model in training and testing, also the confusion matrix of the model. Using our machine learning approach, we have trained the ANN model to predict children/adolescents with FASD with accuracy ranging from 75.5% in testing data. These results suggest that the ANN approach is a competitive and efficient methodology to detect and differentiate the cognitive neurodevelopmental consequences of prenatal alcohol exposure. However, we could not recommend the use of this technique for diagnosis FASD if the model does not improve accuracy.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116004509","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281180
Maicholl Gutierrez, Guillermo Cabrera-Guerrero
Intensity-modulated radiation therapy (IMRT) is one of the most widely used techniques in radiation therapy for the treatment of many types of cancers. The main objective is to obtain a treatment plan that allows to eliminate the cancerous cells of the tumour and, at the same time, damage the organs at risk (OAR) around the tumour as little as possible. Beam Angle Optimization resolution techniques, such as reduced Variable Neighborhood Search (rVNS), are expected to be able to combine exploration and exploitation to accelerate the search for the best Beam Angle Configuration (BAC ). We have found an advantage over algorithms from the literature that we try to exploit through the proposed rVNS algorithm, combining different strategies to reduce the number of evaluations.
{"title":"A Reduced Variable Neighbourhood Search Algorithm for the Beam Angle Selection Problem in Radiation Therapy","authors":"Maicholl Gutierrez, Guillermo Cabrera-Guerrero","doi":"10.1109/SCCC51225.2020.9281180","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281180","url":null,"abstract":"Intensity-modulated radiation therapy (IMRT) is one of the most widely used techniques in radiation therapy for the treatment of many types of cancers. The main objective is to obtain a treatment plan that allows to eliminate the cancerous cells of the tumour and, at the same time, damage the organs at risk (OAR) around the tumour as little as possible. Beam Angle Optimization resolution techniques, such as reduced Variable Neighborhood Search (rVNS), are expected to be able to combine exploration and exploitation to accelerate the search for the best Beam Angle Configuration (BAC ). We have found an advantage over algorithms from the literature that we try to exploit through the proposed rVNS algorithm, combining different strategies to reduce the number of evaluations.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"34 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120845612","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281232
David Zabala-Blanco, M. Mora, R. Hernández-García, R. J. Barrientos
Fingerprint recognition is the most employed bio-metric method for identification and verification purposes. Fingerprint images are classified into five categories according to the morphology of their ridges, which decreases the database penetration rate on an identification scheme. The classification procedure mainly starts with the feature extraction from the fingerprint sample, based on minutiae obtained from terminations and bifurcations of ridges. Afterward, the classification process is usually carried out by some artificial neural networks under supervised learning. Recently, convolutional neural networks are utilized as a potential alternative, by showing accuracies close to 100 % with a high cost of learning times even using high-performance computing. On the other hand, the extreme learning machine (ELM) has emerged as a novel algorithm for the single-hidden layer feed-forward neural network, because of its good generalization performance at extremely fast learning speed. In this work, we introduce the ELMs for the fingerprint classification problem. The superior ELMs are given by the mapping activation function and the number of hidden nodes that maximize the accuracy of the classification; a heuristic approach is carried out to find these parameters. The studied databases are the NIST-4 and SFINGE, which are composed by different quantity and quality of fingerprint samples. Results show that ELM classification by using the feature descriptor of Hong08 achieves very high accuracy and low penetration rate, reducing severally the training time in comparison with deep learning approaches.
{"title":"The Extreme Learning Machine Algorithm for Classifying Fingerprints","authors":"David Zabala-Blanco, M. Mora, R. Hernández-García, R. J. Barrientos","doi":"10.1109/SCCC51225.2020.9281232","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281232","url":null,"abstract":"Fingerprint recognition is the most employed bio-metric method for identification and verification purposes. Fingerprint images are classified into five categories according to the morphology of their ridges, which decreases the database penetration rate on an identification scheme. The classification procedure mainly starts with the feature extraction from the fingerprint sample, based on minutiae obtained from terminations and bifurcations of ridges. Afterward, the classification process is usually carried out by some artificial neural networks under supervised learning. Recently, convolutional neural networks are utilized as a potential alternative, by showing accuracies close to 100 % with a high cost of learning times even using high-performance computing. On the other hand, the extreme learning machine (ELM) has emerged as a novel algorithm for the single-hidden layer feed-forward neural network, because of its good generalization performance at extremely fast learning speed. In this work, we introduce the ELMs for the fingerprint classification problem. The superior ELMs are given by the mapping activation function and the number of hidden nodes that maximize the accuracy of the classification; a heuristic approach is carried out to find these parameters. The studied databases are the NIST-4 and SFINGE, which are composed by different quantity and quality of fingerprint samples. Results show that ELM classification by using the feature descriptor of Hong08 achieves very high accuracy and low penetration rate, reducing severally the training time in comparison with deep learning approaches.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128230650","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281186
Samuel Sepúlveda Cuevas, M. Diéguez
Student-centered learning and active methodologies have generated changes in the teaching-learning process, in teachers and the classroom. However, it is not enough to incorporate student-centered methodological strategies into the classroom, but they must be aligned to achieve the development of specific skills in the student. Then, it is considered necessary to develop support for teachers and curriculum, which allow them to better manage both the review and the planning of a subject, the definition of learning outcomes, assessment methods and associated methodological strategies, ensuring the contribution of each subject to the achievement of the competencies declared in the curriculum of a career. This article presents the discussion and ongoing work regarding learning outcomes and their relationship with teaching-learning methodologies and Bloom’s Taxonomy.
{"title":"EM-(RA)2: a tool support proposal for Learning Outcomes and the Teaching-Learning Process","authors":"Samuel Sepúlveda Cuevas, M. Diéguez","doi":"10.1109/SCCC51225.2020.9281186","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281186","url":null,"abstract":"Student-centered learning and active methodologies have generated changes in the teaching-learning process, in teachers and the classroom. However, it is not enough to incorporate student-centered methodological strategies into the classroom, but they must be aligned to achieve the development of specific skills in the student. Then, it is considered necessary to develop support for teachers and curriculum, which allow them to better manage both the review and the planning of a subject, the definition of learning outcomes, assessment methods and associated methodological strategies, ensuring the contribution of each subject to the achievement of the competencies declared in the curriculum of a career. This article presents the discussion and ongoing work regarding learning outcomes and their relationship with teaching-learning methodologies and Bloom’s Taxonomy.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114081729","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281221
Liliana Huallcca, G. Muñoz, José Mellado, Daniel Vega-Araya, Manuel Villalobos-Cid
Given its importance with regards to the health and performance of the students, the evaluation and control of the academic load have come to form part of a critical component of the educational process. Several universities around the world have performed studies evaluating their programs by contrasting the planned and effective academic load using a credit system. Most of them have used strategies based on interviews, surveys, questionnaires and logbooks to quantify the effective load. In addition, it has become necessary to define academic programs with activities and load planned according to a uniform criterion. To evaluate the programs of our department, we propose a strategy based on three stages: (1) the designing of an informatic tool which allows academics to plan the class-to-class activities of each course by considering load, (2) holding a set of meetings with academics and students to discuss the planned and effective load of the courses, and (3) a study of the balance of the load between the different weeks of the semesters. In this manuscript, we describe the first stage of the strategy associated with the informatics tool.
{"title":"An informatics tool for class-to-class planning and academic-load evaluation","authors":"Liliana Huallcca, G. Muñoz, José Mellado, Daniel Vega-Araya, Manuel Villalobos-Cid","doi":"10.1109/SCCC51225.2020.9281221","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281221","url":null,"abstract":"Given its importance with regards to the health and performance of the students, the evaluation and control of the academic load have come to form part of a critical component of the educational process. Several universities around the world have performed studies evaluating their programs by contrasting the planned and effective academic load using a credit system. Most of them have used strategies based on interviews, surveys, questionnaires and logbooks to quantify the effective load. In addition, it has become necessary to define academic programs with activities and load planned according to a uniform criterion. To evaluate the programs of our department, we propose a strategy based on three stages: (1) the designing of an informatic tool which allows academics to plan the class-to-class activities of each course by considering load, (2) holding a set of meetings with academics and students to discuss the planned and effective load of the courses, and (3) a study of the balance of the load between the different weeks of the semesters. In this manuscript, we describe the first stage of the strategy associated with the informatics tool.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125092877","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281205
Nelson Troncoso, Luis Rojo-González, Óscar C. Vásquez, R. Acuña, H. Chávez, Manuel Villalobos-Cid
Distribution customers are exposed to various tariff mechanisms from which they must select one that minimizes the electricity bill. Also, distributed generation (mainly Solar Photovoltaic) and distributed storage (mainly electro-chemical batteries) have arisen as an alternative to reduce electric bills. In general, the problem of selecting a specific photovoltaic and energy storage system size is NP-hard, as the trade-off between tariff mechanisms and photovoltaic and energy storage energy relationships is difficult; also, distribution customers may not have specific knowledge of the underlying optimization problem nor how to formulate an analysis in particular. This work considers the particular case of the Chilean distribution tariff mechanism to propose an easy-to-implement algorithm to obtain an near-optimal solution to the photovoltaic and energy storage sizing system, maximizing the economic return. A numerical example is presented to illustrate the usefulness of the proposed algorithm.
{"title":"Photovoltaic and Energy Storage Sizing Algorithm for the Chilean Distribution Tariff","authors":"Nelson Troncoso, Luis Rojo-González, Óscar C. Vásquez, R. Acuña, H. Chávez, Manuel Villalobos-Cid","doi":"10.1109/SCCC51225.2020.9281205","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281205","url":null,"abstract":"Distribution customers are exposed to various tariff mechanisms from which they must select one that minimizes the electricity bill. Also, distributed generation (mainly Solar Photovoltaic) and distributed storage (mainly electro-chemical batteries) have arisen as an alternative to reduce electric bills. In general, the problem of selecting a specific photovoltaic and energy storage system size is NP-hard, as the trade-off between tariff mechanisms and photovoltaic and energy storage energy relationships is difficult; also, distribution customers may not have specific knowledge of the underlying optimization problem nor how to formulate an analysis in particular. This work considers the particular case of the Chilean distribution tariff mechanism to propose an easy-to-implement algorithm to obtain an near-optimal solution to the photovoltaic and energy storage sizing system, maximizing the economic return. A numerical example is presented to illustrate the usefulness of the proposed algorithm.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132703475","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281231
J. A. Riquelme, R. J. Barrientos, R. Hernández-García, C. Navarro
The Nearest Neighbors search is a widely used technique with applications on several classification problems. Particularly, the k-nearest neighbor (kNN) algorithm is a well-known method used in modern information retrieval systems aiming to obtain relevant objects based on their similarity to a given query object. Although algorithms based on an exhaustive search have proven to be effective for the kNN classification, their main drawback is their high computational complexity, especially with high-dimensional data. In this work, we present a novel and parallel algorithm to solve kNN queries on a multi-GPU platform. The proposed method is comprised of two stages, which first is based on pivots using the value of K to reduce the search space, and the second one uses a set of heaps to return the final results. Experimental results showed that using between 1-4 GPUs, the proposed algorithm achieves speed-ups of 117x, 224x, 330x, and 389x, respectively. Besides, the obtained results were compared with previous approaches of the state-of-the-art (cp-select and CUB Library), evidencing the superiority of our proposal.
{"title":"An exhaustive algorithm based on GPU to process a kNN query","authors":"J. A. Riquelme, R. J. Barrientos, R. Hernández-García, C. Navarro","doi":"10.1109/SCCC51225.2020.9281231","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281231","url":null,"abstract":"The Nearest Neighbors search is a widely used technique with applications on several classification problems. Particularly, the k-nearest neighbor (kNN) algorithm is a well-known method used in modern information retrieval systems aiming to obtain relevant objects based on their similarity to a given query object. Although algorithms based on an exhaustive search have proven to be effective for the kNN classification, their main drawback is their high computational complexity, especially with high-dimensional data. In this work, we present a novel and parallel algorithm to solve kNN queries on a multi-GPU platform. The proposed method is comprised of two stages, which first is based on pivots using the value of K to reduce the search space, and the second one uses a set of heaps to return the final results. Experimental results showed that using between 1-4 GPUs, the proposed algorithm achieves speed-ups of 117x, 224x, 330x, and 389x, respectively. Besides, the obtained results were compared with previous approaches of the state-of-the-art (cp-select and CUB Library), evidencing the superiority of our proposal.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133981964","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281157
Norka Bedregal-Alpaca, Víctor Manuel Cornejo Aparicio, Olha Sharhorodska
Active methodologies have led to changes in ways of teaching and learning, including Game-Based Learning as a tool for dynamization and learning supportIn the subject Discrete Structures II identified the low academic performance of students and their difficulty in appropriation of concepts and properties of group and semi-group theory. As a solution alternative it was proposed to implement the Hangman GameAn exploratory-descriptive quasi-experimental design was developed by implementing a structured survey to capture students' perception of playful activity. The experience was carried out with the 35 students enrolled in the subjectIt was concluded that applying Game-Based Learning, through a virtual medium and in support of the face-to-face model, contributed to the appropriation of concepts and properties of the subject worked by improving the qualifications and motivation of the student. In addition, it led to the development of other skills and competencies, in particular the lifelong learning competence.
{"title":"Game-based learning for the appropriation of Discrete Mathematics concepts: \"Hanged on the Moodle Platform\"","authors":"Norka Bedregal-Alpaca, Víctor Manuel Cornejo Aparicio, Olha Sharhorodska","doi":"10.1109/SCCC51225.2020.9281157","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281157","url":null,"abstract":"Active methodologies have led to changes in ways of teaching and learning, including Game-Based Learning as a tool for dynamization and learning supportIn the subject Discrete Structures II identified the low academic performance of students and their difficulty in appropriation of concepts and properties of group and semi-group theory. As a solution alternative it was proposed to implement the Hangman GameAn exploratory-descriptive quasi-experimental design was developed by implementing a structured survey to capture students' perception of playful activity. The experience was carried out with the 35 students enrolled in the subjectIt was concluded that applying Game-Based Learning, through a virtual medium and in support of the face-to-face model, contributed to the appropriation of concepts and properties of the subject worked by improving the qualifications and motivation of the student. In addition, it led to the development of other skills and competencies, in particular the lifelong learning competence.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115218872","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281195
L. Dombrovskaia, José P. del Rio, Patricio Rodríguez
Attrition is a concern of most engineering schools around the world. The engineering students drop out mainly in the first two years of their program. Predicting the student’s possibility to drop out from the program would allow the university to design remedial programs and therefore prevent their drop-out in some cases. Our goal was to explore the possibility to predict the student permanence in the third semester based on her/his performance during the first semester at the engineering school additionally to her/his performance at secondary education, family income and standard admission test.We explored four different algorithms for classification of student’s permanence in the program past the first semester: support vector machine, random forest, k-nearest neighbors and gradient booting. The best results were achieved with the random forest algorithm for classification of the permanence beyond the first year with a F1 score of 92,4%. The most influential factor in predicting the permanence was the number of failed courses during the first semester followed by the results in individual courses, while the PSU Mathematics score was the most influential among admission tests.
{"title":"Prediction of student’s retention in first year of engineering program at a technological chilean university","authors":"L. Dombrovskaia, José P. del Rio, Patricio Rodríguez","doi":"10.1109/SCCC51225.2020.9281195","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281195","url":null,"abstract":"Attrition is a concern of most engineering schools around the world. The engineering students drop out mainly in the first two years of their program. Predicting the student’s possibility to drop out from the program would allow the university to design remedial programs and therefore prevent their drop-out in some cases. Our goal was to explore the possibility to predict the student permanence in the third semester based on her/his performance during the first semester at the engineering school additionally to her/his performance at secondary education, family income and standard admission test.We explored four different algorithms for classification of student’s permanence in the program past the first semester: support vector machine, random forest, k-nearest neighbors and gradient booting. The best results were achieved with the random forest algorithm for classification of the permanence beyond the first year with a F1 score of 92,4%. The most influential factor in predicting the permanence was the number of failed courses during the first semester followed by the results in individual courses, while the PSU Mathematics score was the most influential among admission tests.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114200794","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：