Pub Date : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955002
S. Subchan, Rachmat Wahyudi Ismail, T. Asfihani, D. Adzkiya
Ship maneuvering is the ability of ships to turn and spin while operating on seas. The ship's hydrodynamic coefficients are a set of parameters that influence the mathematical model of ship motion. In other words, if the hydrodynamic coefficients are more accurate, the ship motion produced by the model is closer to the actual motion. This study uses unscented Kalman filter and recursive least square to estimate the hydrodynamic coefficients in the 4-DOF ship motion models based on the data from free running model test.
{"title":"Estimation of Hydrodynamic Coefficients using Unscented Kalman Filter and Recursive Least Square","authors":"S. Subchan, Rachmat Wahyudi Ismail, T. Asfihani, D. Adzkiya","doi":"10.1109/IWCIA47330.2019.8955002","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955002","url":null,"abstract":"Ship maneuvering is the ability of ships to turn and spin while operating on seas. The ship's hydrodynamic coefficients are a set of parameters that influence the mathematical model of ship motion. In other words, if the hydrodynamic coefficients are more accurate, the ship motion produced by the model is closer to the actual motion. This study uses unscented Kalman filter and recursive least square to estimate the hydrodynamic coefficients in the 4-DOF ship motion models based on the data from free running model test.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128693116","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955042
Tomohiro Hayashida, I. Nishizaki, Shinya Sekizaki, Yuki Takamori
Particle Swarm Optimization (PSO) is useful as a method for solving optimization problems with continuous value variables because the convergence speed of solution search is fast. PSO is a evolutionary computation method in which individuals (particles) with position and velocity information are placed in the search space and acts for the purpose of finding an optimal solution with sharing information with other particles. This study constructs a particle swarm optimization method introducing the immune algorithms to improve the search capability of each particle and perform solution search more efficiently. To verify the usefulness of the proposed method, some numerical experiments are performed in this study.
{"title":"Improvement of Two-swarm Cooperative Particle Swarm Optimization Using Immune Algorithms and Swarm Clustering","authors":"Tomohiro Hayashida, I. Nishizaki, Shinya Sekizaki, Yuki Takamori","doi":"10.1109/IWCIA47330.2019.8955042","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955042","url":null,"abstract":"Particle Swarm Optimization (PSO) is useful as a method for solving optimization problems with continuous value variables because the convergence speed of solution search is fast. PSO is a evolutionary computation method in which individuals (particles) with position and velocity information are placed in the search space and acts for the purpose of finding an optimal solution with sharing information with other particles. This study constructs a particle swarm optimization method introducing the immune algorithms to improve the search capability of each particle and perform solution search more efficiently. To verify the usefulness of the proposed method, some numerical experiments are performed in this study.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129735750","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955065
Taketo Kamikawa, T. Hasuike
This research focuses on the two purposes of maximizing the amount of heat generated by incineration and minimizing the collection distance of waste, in determining allocations and locations of general waste incineration facilities as a case study of Chiba northwest bay area. For these purposes, we propose the multi-objective optimization with Voronoi diagram and genetic algorithm (MOVGA). As for the maximization of the amount of generated heat, we predict the amount by using regression equation of multiple linear regression analysis and formulate it as the set partitioning problem (SPP) to maximize the prediction value. As for the minimization of waste collection distances, we formulate it as the multi-Weber problem. To solve these two problems, we use MOVGA, which has the seeds of the Voronoi diagram as a gene. As a result of the survey using data of 2015 year of Chiba northwest bay area, in the case of 3 facilities it was found that the calorific value increased enough to cover the power of 4,205 households (converted to housing complex) per year despite the increase of 3% t-km per year.
{"title":"Multi-objective optimization of allocations and locations of incineration facilities with Voronoi diagram and genetic algorithm: Case study of northwest bay area in Chiba prefecture","authors":"Taketo Kamikawa, T. Hasuike","doi":"10.1109/IWCIA47330.2019.8955065","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955065","url":null,"abstract":"This research focuses on the two purposes of maximizing the amount of heat generated by incineration and minimizing the collection distance of waste, in determining allocations and locations of general waste incineration facilities as a case study of Chiba northwest bay area. For these purposes, we propose the multi-objective optimization with Voronoi diagram and genetic algorithm (MOVGA). As for the maximization of the amount of generated heat, we predict the amount by using regression equation of multiple linear regression analysis and formulate it as the set partitioning problem (SPP) to maximize the prediction value. As for the minimization of waste collection distances, we formulate it as the multi-Weber problem. To solve these two problems, we use MOVGA, which has the seeds of the Voronoi diagram as a gene. As a result of the survey using data of 2015 year of Chiba northwest bay area, in the case of 3 facilities it was found that the calorific value increased enough to cover the power of 4,205 households (converted to housing complex) per year despite the increase of 3% t-km per year.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129776979","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955041
Asuka Terai, Taiki Sugyo
Metaphor generation is influenced by emotional or sensuous knowledge structure. Hence, there is a possibility that it might be difficult to select an adequate vehicle in metaphor generation. The purpose of this research is to construct a metaphor database based on a literature corpus and use the database to build a metaphor generation support system. At first, sentences including metaphors were extracted from a literature corpus. The extracted sentences were analyzed using dependency parsing in order to construct a metaphor database for the metaphor generation system. The system outputs candidate vehicles from a given topic and its expressed features by searching the sentences including the topic or the features in the database. Furthermore, an experiment was conducted to evaluate the usability of the system. In the experiment, participants were asked to generate a sentence including a metaphor from a shown image with or without the system. Third-party evaluation was conducted to evaluate the metaphors generated in the experiment. The results seem to suggest the efficiency of the system.
{"title":"Construction of a Corpus-Based Metaphor Generation Support System Built on Japanese Literature","authors":"Asuka Terai, Taiki Sugyo","doi":"10.1109/IWCIA47330.2019.8955041","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955041","url":null,"abstract":"Metaphor generation is influenced by emotional or sensuous knowledge structure. Hence, there is a possibility that it might be difficult to select an adequate vehicle in metaphor generation. The purpose of this research is to construct a metaphor database based on a literature corpus and use the database to build a metaphor generation support system. At first, sentences including metaphors were extracted from a literature corpus. The extracted sentences were analyzed using dependency parsing in order to construct a metaphor database for the metaphor generation system. The system outputs candidate vehicles from a given topic and its expressed features by searching the sentences including the topic or the features in the database. Furthermore, an experiment was conducted to evaluate the usability of the system. In the experiment, participants were asked to generate a sentence including a metaphor from a shown image with or without the system. Third-party evaluation was conducted to evaluate the metaphors generated in the experiment. The results seem to suggest the efficiency of the system.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"2008 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125624884","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 : 2019-11-01DOI: 10.1109/iwcia47330.2019.8955095
{"title":"[Front matter]","authors":"","doi":"10.1109/iwcia47330.2019.8955095","DOIUrl":"https://doi.org/10.1109/iwcia47330.2019.8955095","url":null,"abstract":"","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114626963","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955062
Keiichi Tamura, Akitada Omagari, Shuichi Hashida
With the developments in deep learning, the security of neural networks against vulnerabilities has become one of the most urgent research topics in deep learning. There are many types of security countermeasures. Adversarial examples and their defense methods, in particular, have been well-studied in recent years. An adversarial example is designed to make neural networks misclassify or produce inaccurate output. Audio adversarial examples are a type of adversarial example where the main target of attack is a speech-to-text transcription neural network. In this study, we propose a new defense method against audio adversarial examples for the speech-to-text transcription neural networks. It is difficult to determine whether an input waveform data representing the sound of voice is an audio adversarial example. Therefore, the main framework of the proposed defense method is based on a sandbox approach. To evaluate the proposed defense method, we used actual audio adversarial examples that were created on Deep Speech, which is a speech-to-text transcription neural network. We confirmed that our defense method can identify audio adversarial examples to protect speech-to-text systems.
{"title":"Novel Defense Method against Audio Adversarial Example for Speech-to-Text Transcription Neural Networks","authors":"Keiichi Tamura, Akitada Omagari, Shuichi Hashida","doi":"10.1109/IWCIA47330.2019.8955062","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955062","url":null,"abstract":"With the developments in deep learning, the security of neural networks against vulnerabilities has become one of the most urgent research topics in deep learning. There are many types of security countermeasures. Adversarial examples and their defense methods, in particular, have been well-studied in recent years. An adversarial example is designed to make neural networks misclassify or produce inaccurate output. Audio adversarial examples are a type of adversarial example where the main target of attack is a speech-to-text transcription neural network. In this study, we propose a new defense method against audio adversarial examples for the speech-to-text transcription neural networks. It is difficult to determine whether an input waveform data representing the sound of voice is an audio adversarial example. Therefore, the main framework of the proposed defense method is based on a sandbox approach. To evaluate the proposed defense method, we used actual audio adversarial examples that were created on Deep Speech, which is a speech-to-text transcription neural network. We confirmed that our defense method can identify audio adversarial examples to protect speech-to-text systems.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134291212","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955092
R. F. Rachmadi, I. Purnama, S. M. S. Nugroho, Y. Suprapto
In this paper, we investigate the performance of fusion convolutional neural network (CNN) classifier for image-based kinship verification problem. Two fusion configurations were used for the experiments, early fusion CNN classifier and late fusion CNN classifier. The early fusion configuration of the CNN classifier takes combined two face images as input for verification. The advantages of early fusion configuration are no heavy changes in the classifier architecture and only the first layer that have a different filter size. The late fusion configuration of the CNN classifier formed by creating dual CNN network for extracting the deep features of each face image and classify the kinship relationship using two fully-connected layers. The softmax and angular softmax (a-softmax) loss are used for evaluating the network in the training process with fine-tuning strategy. The classifier then evaluated using large-scale FIW (Family in the Wild) kinship verification dataset consists of 1,000 family and 11 different kinship relationship. Experiments using the 5-fold configuration on FIW dataset show that the ensemble of fusion CNN classifier produces comparable performance with several different state-of-the-art methods.
本文研究了融合卷积神经网络(CNN)分类器在基于图像的亲属关系验证问题中的性能。实验采用了两种融合配置，早期融合CNN分类器和后期融合CNN分类器。CNN分类器的早期融合配置是将合并后的两张人脸图像作为输入进行验证。早期融合配置的优点是对分类器架构没有很大的改变，只有第一层具有不同的过滤器大小。通过创建双CNN网络，提取每张人脸图像的深层特征，并使用两个全连接层对亲属关系进行分类，形成CNN分类器的后期融合配置。在训练过程中使用softmax和角softmax (a-softmax)损失来评估网络，并采用微调策略。然后使用大型FIW (Family in Wild)亲属关系验证数据集对分类器进行评估，该数据集由1000个家庭和11种不同的亲属关系组成。在FIW数据集上使用5倍配置的实验表明，融合CNN分类器的集成与几种不同的最先进的方法产生相当的性能。
{"title":"Image-based Kinship Verification using Fusion Convolutional Neural Network","authors":"R. F. Rachmadi, I. Purnama, S. M. S. Nugroho, Y. Suprapto","doi":"10.1109/IWCIA47330.2019.8955092","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955092","url":null,"abstract":"In this paper, we investigate the performance of fusion convolutional neural network (CNN) classifier for image-based kinship verification problem. Two fusion configurations were used for the experiments, early fusion CNN classifier and late fusion CNN classifier. The early fusion configuration of the CNN classifier takes combined two face images as input for verification. The advantages of early fusion configuration are no heavy changes in the classifier architecture and only the first layer that have a different filter size. The late fusion configuration of the CNN classifier formed by creating dual CNN network for extracting the deep features of each face image and classify the kinship relationship using two fully-connected layers. The softmax and angular softmax (a-softmax) loss are used for evaluating the network in the training process with fine-tuning strategy. The classifier then evaluated using large-scale FIW (Family in the Wild) kinship verification dataset consists of 1,000 family and 11 different kinship relationship. Experiments using the 5-fold configuration on FIW dataset show that the ensemble of fusion CNN classifier produces comparable performance with several different state-of-the-art methods.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"46 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124666937","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955045
H. Seki, Shuhei Toriyama
We study term expansion (or document expansion), which is used for classifying documents, especially for short documents such as twitter and blogs on the Web. Term expansion enables us to augment the sparse information in those short documents. Carpineto et al. have proposed a term expansion method based on FCA (Formal Concept Analysis), while Rogers et al. have proposed another term expansion method based on LDA (Latent Dirichlet Allocation). In this paper, we take the notion of weighted term similarity measures in FCA, and examine its effectiveness used for term expansion. We also study the effectiveness of some correlation measures in the field of association rule mining. We perform some experimental study on the effects of the proposed term similarity measures in term expansion using two short text corpora. The experimental results show that those weighted term similarity measures, when choosing an appropriate weight value, outperform the prior methods.
{"title":"On Term Similarity Measures for Short Text Classification","authors":"H. Seki, Shuhei Toriyama","doi":"10.1109/IWCIA47330.2019.8955045","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955045","url":null,"abstract":"We study term expansion (or document expansion), which is used for classifying documents, especially for short documents such as twitter and blogs on the Web. Term expansion enables us to augment the sparse information in those short documents. Carpineto et al. have proposed a term expansion method based on FCA (Formal Concept Analysis), while Rogers et al. have proposed another term expansion method based on LDA (Latent Dirichlet Allocation). In this paper, we take the notion of weighted term similarity measures in FCA, and examine its effectiveness used for term expansion. We also study the effectiveness of some correlation measures in the field of association rule mining. We perform some experimental study on the effects of the proposed term similarity measures in term expansion using two short text corpora. The experimental results show that those weighted term similarity measures, when choosing an appropriate weight value, outperform the prior methods.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124611953","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955083
Manabu Okawa
This study proposes a novel single-template strategy that uses mean templates and local stability-weighted dynamic time warping (LS-DTW) as a means of improving the speed and accuracy of online signature verification. Specifically, we adopt a recent time-series averaging method, Euclidean barycenter-based DTW barycenter averaging, to obtain effective mean templates while preserving intra-user variability among reference samples. Then, we estimate the local stability of the mean template set using multiple matching points that detect significant distorted trajectories in the warping paths of DTW. Subsequently, to boost discriminative power in the verification phase, we use the LS-DTW distances that incorporate the local stability sequence as the weights for the cost function of DTW warping between the set of mean templates and a test sample. Experimental results confirm the effectiveness of the proposed method using a common SVC2004 Task2 dataset.
{"title":"Online Signature Verification Using a Single-template Strategy with Mean Templates and Local Stability-weighted Dynamic Time Warping","authors":"Manabu Okawa","doi":"10.1109/IWCIA47330.2019.8955083","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955083","url":null,"abstract":"This study proposes a novel single-template strategy that uses mean templates and local stability-weighted dynamic time warping (LS-DTW) as a means of improving the speed and accuracy of online signature verification. Specifically, we adopt a recent time-series averaging method, Euclidean barycenter-based DTW barycenter averaging, to obtain effective mean templates while preserving intra-user variability among reference samples. Then, we estimate the local stability of the mean template set using multiple matching points that detect significant distorted trajectories in the warping paths of DTW. Subsequently, to boost discriminative power in the verification phase, we use the LS-DTW distances that incorporate the local stability sequence as the weights for the cost function of DTW warping between the set of mean templates and a test sample. Experimental results confirm the effectiveness of the proposed method using a common SVC2004 Task2 dataset.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"603 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116363965","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 : 2019-11-01DOI: 10.1109/IWCIA47330.2019.8955064
Yusuke Tanimoto, Tomohiro Hayashida, Toru Yamamoto, S. Wakitani, T. Kinoshita, I. Nishizaki, Shinya Sekizaki
This study presents about a new procedure for extraction and classification of learners in a class using the neural networks. It is necessary to provide learning support corresponding to the understanding degree of each learner to improve learning process efficiency. For this purpose, this study develops a procedure to predict the achievement level of learners at the end of the class and classify them. A Multi-Context Recurrent Neural Network (MCRNN) is used for predicting achievement level and classifying learners. By providing additional education for the learners who are classified as a low degree by the proposed method, it is expected to be able to take countermeasures for not becoming dropout in early stage. In this study, numerical experiments are executed to verify the usefulness of the proposed method. To gather enough number of learners' data, this study generates the learners' growth process data that used as training and test data of MCRNN. The experimental result indicates that the proposed method succeeded in classifying learners into three groups based on the understanding degree at the end of a class.
{"title":"Feature extraction and Classification of Learners using Multi-Context Recurrent Neural Networks","authors":"Yusuke Tanimoto, Tomohiro Hayashida, Toru Yamamoto, S. Wakitani, T. Kinoshita, I. Nishizaki, Shinya Sekizaki","doi":"10.1109/IWCIA47330.2019.8955064","DOIUrl":"https://doi.org/10.1109/IWCIA47330.2019.8955064","url":null,"abstract":"This study presents about a new procedure for extraction and classification of learners in a class using the neural networks. It is necessary to provide learning support corresponding to the understanding degree of each learner to improve learning process efficiency. For this purpose, this study develops a procedure to predict the achievement level of learners at the end of the class and classify them. A Multi-Context Recurrent Neural Network (MCRNN) is used for predicting achievement level and classifying learners. By providing additional education for the learners who are classified as a low degree by the proposed method, it is expected to be able to take countermeasures for not becoming dropout in early stage. In this study, numerical experiments are executed to verify the usefulness of the proposed method. To gather enough number of learners' data, this study generates the learners' growth process data that used as training and test data of MCRNN. The experimental result indicates that the proposed method succeeded in classifying learners into three groups based on the understanding degree at the end of a class.","PeriodicalId":139434,"journal":{"name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116229216","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：