Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982409
H. Al-Ash, Mutia Fadhila Putri, P. Mursanto, A. Bustamam
The news is information about a recently changed situation or a recent event. Serving as popular media information the internet has the power spread the news not only real news but fake news as well. We propose an ensemble learning approach on Indonesian fake news in order to separate fake news from the real one and to tackle imbalanced data problem which we face on the given dataset. Our experiment result shows that random forest classifier as the ensemble classifier which obtained 0.98 f1-score is superior to multinomial naive bayes and support vector machine as non-ensemble classifiers which achieve 0.43 and 0.74 f1-score respectively across 660 evaluation documents. We also compare our result against other research that using the same data and our approach achieved better results.
{"title":"Ensemble Learning Approach on Indonesian Fake News Classification","authors":"H. Al-Ash, Mutia Fadhila Putri, P. Mursanto, A. Bustamam","doi":"10.1109/ICICoS48119.2019.8982409","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982409","url":null,"abstract":"The news is information about a recently changed situation or a recent event. Serving as popular media information the internet has the power spread the news not only real news but fake news as well. We propose an ensemble learning approach on Indonesian fake news in order to separate fake news from the real one and to tackle imbalanced data problem which we face on the given dataset. Our experiment result shows that random forest classifier as the ensemble classifier which obtained 0.98 f1-score is superior to multinomial naive bayes and support vector machine as non-ensemble classifiers which achieve 0.43 and 0.74 f1-score respectively across 660 evaluation documents. We also compare our result against other research that using the same data and our approach achieved better results.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130268526","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982470
S. R. Juwita, S. Endah
Music has a variety of genres, namely pop, rock, jazz, and so on. Indonesia has its own music that other countries do not have, including campursari, dangdut, and keroncong music. The three types of music have musical instruments that are almost similar, which makes it difficult for listeners to distinguish the genre of music, especially the younger generation, so we need a tool called classification. This study uses a mel-spectogram and the Convolutional Neural Network (CNN) method to classify Indonesian music. The CNN parameters and architecture tested in this study were batch normalization, ReLU activation, dropout, activation of sigmoid and softmax output, epoch value, learning rate value, and dense layer value. The entire parameter is tested using input with two different data sharing methods, namely stratified split and k-fold cross validation. The highest accuracy of 82% was obtained by using the stratified split data distribution method and using batch normalization parameters, ReLU activation, activation of outputs sigmoid and softmax, 30 epoch values, 0.05 learning rate values, and 200 layer dense values. The model with the highest accuracy value is used as the basis for classifying Indonesian music into campursari, dangdut, or keroncong classes
{"title":"Classification of Indonesian Music Using the Convolutional Neural Network Method","authors":"S. R. Juwita, S. Endah","doi":"10.1109/ICICoS48119.2019.8982470","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982470","url":null,"abstract":"Music has a variety of genres, namely pop, rock, jazz, and so on. Indonesia has its own music that other countries do not have, including campursari, dangdut, and keroncong music. The three types of music have musical instruments that are almost similar, which makes it difficult for listeners to distinguish the genre of music, especially the younger generation, so we need a tool called classification. This study uses a mel-spectogram and the Convolutional Neural Network (CNN) method to classify Indonesian music. The CNN parameters and architecture tested in this study were batch normalization, ReLU activation, dropout, activation of sigmoid and softmax output, epoch value, learning rate value, and dense layer value. The entire parameter is tested using input with two different data sharing methods, namely stratified split and k-fold cross validation. The highest accuracy of 82% was obtained by using the stratified split data distribution method and using batch normalization parameters, ReLU activation, activation of outputs sigmoid and softmax, 30 epoch values, 0.05 learning rate values, and 200 layer dense values. The model with the highest accuracy value is used as the basis for classifying Indonesian music into campursari, dangdut, or keroncong classes","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128973269","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982528
Rismiyati, H. A. Wibawa
Snake fruit, or most famous as Salak, is Indonesian local fruit. Salak is also one of fruit commodity from Indonesia. To perform export on Salak, rigid sortation is performed. The sortation is usually done manually. This study will implement digital image processing technique to differentiate Salak quality for export purpose. Salak sample were taken from Magelang district, one of the largest Salak producer. The feature used in this study is Histogram of Oriented Gradient. The classification used is Extreme Learning Machine (ELM). It is shown in this study that by using ELM, the highest accuracy can be achieved is 95%. A comparison classifier, SVM, is also used in this study. In this case SVM is able to achieve highest accuracy of 97.3%, which is still higher than ELM result
{"title":"Snake Fruit Classification by Using Histogram of Oriented Gradient Feature and Extreme Learning Machine","authors":"Rismiyati, H. A. Wibawa","doi":"10.1109/ICICoS48119.2019.8982528","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982528","url":null,"abstract":"Snake fruit, or most famous as Salak, is Indonesian local fruit. Salak is also one of fruit commodity from Indonesia. To perform export on Salak, rigid sortation is performed. The sortation is usually done manually. This study will implement digital image processing technique to differentiate Salak quality for export purpose. Salak sample were taken from Magelang district, one of the largest Salak producer. The feature used in this study is Histogram of Oriented Gradient. The classification used is Extreme Learning Machine (ELM). It is shown in this study that by using ELM, the highest accuracy can be achieved is 95%. A comparison classifier, SVM, is also used in this study. In this case SVM is able to achieve highest accuracy of 97.3%, which is still higher than ELM result","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124415732","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982529
Andi Suciati, A. Wibisono, P. Mursanto
The campaign that was done in social media has high correlation to the supporters who disseminating the information deliberately, which called as buzzer. However, data that were generated by buzzer accounts can be considered as noise and need to be removed. In this research we performed task for detecting the buzzer accounts in Twitter by observing the impact of features we used which we selected based on their Mutual Information scores. We examined the performance of four machine learning algorithms which are Ada Boost (AB), Gradient Boosting (GB), Extreme Gradient Boosting (XGB), and Histogram-based Gradient Boosting (HGB). The algorithms were evaluated using 10 folds cross validation and the results show that the best accuracy and precision achieved by AB which are 62.3% and 61.3% respectively with 25 features while the recall attained by XGB (67.9%) which the score same with its recall result with 20 features.
{"title":"Twitter Buzzer Detection for Indonesian Presidential Election","authors":"Andi Suciati, A. Wibisono, P. Mursanto","doi":"10.1109/ICICoS48119.2019.8982529","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982529","url":null,"abstract":"The campaign that was done in social media has high correlation to the supporters who disseminating the information deliberately, which called as buzzer. However, data that were generated by buzzer accounts can be considered as noise and need to be removed. In this research we performed task for detecting the buzzer accounts in Twitter by observing the impact of features we used which we selected based on their Mutual Information scores. We examined the performance of four machine learning algorithms which are Ada Boost (AB), Gradient Boosting (GB), Extreme Gradient Boosting (XGB), and Histogram-based Gradient Boosting (HGB). The algorithms were evaluated using 10 folds cross validation and the results show that the best accuracy and precision achieved by AB which are 62.3% and 61.3% respectively with 25 features while the recall attained by XGB (67.9%) which the score same with its recall result with 20 features.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128753759","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982397
Priyamvada Pushkar Huddar, S. Sontakke
Infant cardiac distress is the leading cause of neonatal deaths in the world. Cardiotocography (CTG) is a diagnostic tool used for recording fetal heartbeat and uterine contractions during pregnancy to determine cardiac distress. To avoid the need of continuous monitoring by on-site medical personnel, researchers have been working on several machine learning tools to automate the process. Most of these approaches discover statistical trends in data to predict target variables. However, being reliant on these trends makes them prone to overfitting and other statistical perils. In this paper, we demonstrate the usage of a modified deep neural network to learn about 2 seemingly disjointed tasks in the field of cardiotocography. The proposed model acquires predictive power in one task whilst being trained on a separate yet related task in the same field. Further, it establishes that regularization facilitates the sharing of knowledge across tasks. The resulting model mimics the human learning process by demonstrating the ability to acquire domain knowledge.
{"title":"Acquiring Domain Knowledge for Cardiotocography: A Deep Learning Approach","authors":"Priyamvada Pushkar Huddar, S. Sontakke","doi":"10.1109/ICICoS48119.2019.8982397","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982397","url":null,"abstract":"Infant cardiac distress is the leading cause of neonatal deaths in the world. Cardiotocography (CTG) is a diagnostic tool used for recording fetal heartbeat and uterine contractions during pregnancy to determine cardiac distress. To avoid the need of continuous monitoring by on-site medical personnel, researchers have been working on several machine learning tools to automate the process. Most of these approaches discover statistical trends in data to predict target variables. However, being reliant on these trends makes them prone to overfitting and other statistical perils. In this paper, we demonstrate the usage of a modified deep neural network to learn about 2 seemingly disjointed tasks in the field of cardiotocography. The proposed model acquires predictive power in one task whilst being trained on a separate yet related task in the same field. Further, it establishes that regularization facilitates the sharing of knowledge across tasks. The resulting model mimics the human learning process by demonstrating the ability to acquire domain knowledge.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127343615","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982524
R. Ferdhiana, K. Amri, T. Abidin
This study aims to cluster 513 districts in Indonesia using the results of High School National Examination or “Ujian Nasional (UN)” in Indonesian language majoring in social sciences to map the learning outcomes in the districts. The attributes consist of 6 subjects which are Bahasa Indonesia, English, Mathematics, Economics, Sociology, and Geography. The clustering methods used are Complete-linkage and K-Means. The clustering results are compared with the District Human Development Index (HDI) of the clusters. The results show that the districts in Indonesia are grouped into 5 clusters and there is a slight dissimilarity between the scores of UN and HDI.
{"title":"Clustering of Districts in Indonesia using the 2015 High School Social Sciences National Examination Results","authors":"R. Ferdhiana, K. Amri, T. Abidin","doi":"10.1109/ICICoS48119.2019.8982524","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982524","url":null,"abstract":"This study aims to cluster 513 districts in Indonesia using the results of High School National Examination or “Ujian Nasional (UN)” in Indonesian language majoring in social sciences to map the learning outcomes in the districts. The attributes consist of 6 subjects which are Bahasa Indonesia, English, Mathematics, Economics, Sociology, and Geography. The clustering methods used are Complete-linkage and K-Means. The clustering results are compared with the District Human Development Index (HDI) of the clusters. The results show that the districts in Indonesia are grouped into 5 clusters and there is a slight dissimilarity between the scores of UN and HDI.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129437446","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982407
Usman Sudibyo, Cinantya Paramita
Information is categorized as precious thing when only current specific people have the opportunity to gain it, or it is so called confidential. Confidential information is secure if it contains Cryptograph method which contains process of encryption and decryption since their function is to present data and to process it into confidential information. The aim is to keep the information confidential for current people, and they are the ones who can understand and reveal the information. The multi-layered encryption process itself makes the level of difficulties in analysing the information hard to predict. According to that, this process is best applied on securing information which contains alphabetic on plaintext. The quality of multilayered encryption is evaluated with avalanche effect parameter which results value 34% in which a bit variation on a plaintext keeps the consistent of an encryption. Aftermath comparison to the method layer of multi-layered encryption avalanche effect it produce values lower at 33% obtained by change the structure decryption is being encryption layer.
{"title":"Multi-Layered Encryption Method","authors":"Usman Sudibyo, Cinantya Paramita","doi":"10.1109/ICICoS48119.2019.8982407","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982407","url":null,"abstract":"Information is categorized as precious thing when only current specific people have the opportunity to gain it, or it is so called confidential. Confidential information is secure if it contains Cryptograph method which contains process of encryption and decryption since their function is to present data and to process it into confidential information. The aim is to keep the information confidential for current people, and they are the ones who can understand and reveal the information. The multi-layered encryption process itself makes the level of difficulties in analysing the information hard to predict. According to that, this process is best applied on securing information which contains alphabetic on plaintext. The quality of multilayered encryption is evaluated with avalanche effect parameter which results value 34% in which a bit variation on a plaintext keeps the consistent of an encryption. Aftermath comparison to the method layer of multi-layered encryption avalanche effect it produce values lower at 33% obtained by change the structure decryption is being encryption layer.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132900775","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982471
W. Hidayat, A. E. Permanasari, P. Santosa, N. Arfian, L. Choridah
Learning medicine not only requires students to master a variety of abilities but also must follow some doctoral standards. In general, the learning process within the Faculty of Medicine students is still conducted by using cadaver. However, several obstacles were encountered when using that media. To overcome the limitations, the use of Augmented Reality (AR) technology has become a medium used for learning. A systematic review method of the study and research of human anatomy on AR in the field of medicine is presented. Based on this review, a model for developing human anatomy learning media using AR that uses 3D printing object marker puzzles was created. The concept model is expected to be able to overcome some of the problems. Potential challenges in developing human anatomy learning models using 3D printing puzzle markers present more specific information and location of a part of human anatomy.
{"title":"Conceptual Model for Human Anatomy Learning Based Augmented Reality on Marker Puzzle 3D Printing","authors":"W. Hidayat, A. E. Permanasari, P. Santosa, N. Arfian, L. Choridah","doi":"10.1109/ICICoS48119.2019.8982471","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982471","url":null,"abstract":"Learning medicine not only requires students to master a variety of abilities but also must follow some doctoral standards. In general, the learning process within the Faculty of Medicine students is still conducted by using cadaver. However, several obstacles were encountered when using that media. To overcome the limitations, the use of Augmented Reality (AR) technology has become a medium used for learning. A systematic review method of the study and research of human anatomy on AR in the field of medicine is presented. Based on this review, a model for developing human anatomy learning media using AR that uses 3D printing object marker puzzles was created. The concept model is expected to be able to overcome some of the problems. Potential challenges in developing human anatomy learning models using 3D printing puzzle markers present more specific information and location of a part of human anatomy.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132985169","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982416
Endang Suryawati, Vicky Zilvan, R. S. Yuwana, A. Heryana, D. Rohdiana, H. Pardede
Tea is a commodity has a strategic role in the Indonesian economy. The cultivation of tea plants becomes very important in order to maintain the superior commodity, with respect to increase the production and/or improve the quality of tea. In a tea plantation management system, it is essential to identify the types of tea clones planted in the field. But, it requires human experts to distinguish one types of clones with another. The existence of an automatic clones identification is expected to make the identification easy, fast, accurate, and easily accessible for common farmers. In this work, we propose an unsupervised feature learning algorithm derived from Deep Convolutional Generative Adversarial Network (DCGAN) for automatic tea clone identification. The use of unsupervised learning enable us to utilize unlabeled data. Our experiments suggest the effectiveness of our method for tea clones detection task.
{"title":"Deep Convolutional Adversarial Network-Based Feature Learning for Tea Clones Identifications","authors":"Endang Suryawati, Vicky Zilvan, R. S. Yuwana, A. Heryana, D. Rohdiana, H. Pardede","doi":"10.1109/ICICoS48119.2019.8982416","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982416","url":null,"abstract":"Tea is a commodity has a strategic role in the Indonesian economy. The cultivation of tea plants becomes very important in order to maintain the superior commodity, with respect to increase the production and/or improve the quality of tea. In a tea plantation management system, it is essential to identify the types of tea clones planted in the field. But, it requires human experts to distinguish one types of clones with another. The existence of an automatic clones identification is expected to make the identification easy, fast, accurate, and easily accessible for common farmers. In this work, we propose an unsupervised feature learning algorithm derived from Deep Convolutional Generative Adversarial Network (DCGAN) for automatic tea clone identification. The use of unsupervised learning enable us to utilize unlabeled data. Our experiments suggest the effectiveness of our method for tea clones detection task.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130252889","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982468
I. Siradjuddin, Wrida Adi Wardana, M. K. Sophan
This paper presents Autoencoder using Convolutional Neural Network for feature extraction in the Content-based Image Retrieval. Two type of layers are in the convolutional autoencoder architecture, they are encoder and decoder layer. The encoder layer extracts the important representation of the image using feature learning capability of the convolutional neural network, and reduces the dimension of the image. The decode layer reconstructs the representation, such that, the output of the autoencoder is close to the input data. The important representation of the image from the encoder layer in convolutional autoencoder, is used as the extracted features in the content-based image retrieval. Similarity distance between the extracted feature of the query image and the database is calculated to retrieve relevant images. The images in Corel dataset are used for the experiment and tested using the proposed model. The experiments show that the extracted features are representable for the images, and can be used to retrieve relevant images in the content-based image retrieval.
{"title":"Feature Extraction using Self-Supervised Convolutional Autoencoder for Content based Image Retrieval","authors":"I. Siradjuddin, Wrida Adi Wardana, M. K. Sophan","doi":"10.1109/ICICoS48119.2019.8982468","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982468","url":null,"abstract":"This paper presents Autoencoder using Convolutional Neural Network for feature extraction in the Content-based Image Retrieval. Two type of layers are in the convolutional autoencoder architecture, they are encoder and decoder layer. The encoder layer extracts the important representation of the image using feature learning capability of the convolutional neural network, and reduces the dimension of the image. The decode layer reconstructs the representation, such that, the output of the autoencoder is close to the input data. The important representation of the image from the encoder layer in convolutional autoencoder, is used as the extracted features in the content-based image retrieval. Similarity distance between the extracted feature of the query image and the database is calculated to retrieve relevant images. The images in Corel dataset are used for the experiment and tested using the proposed model. The experiments show that the extracted features are representable for the images, and can be used to retrieve relevant images in the content-based image retrieval.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124765059","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：