Pub Date : 2018-07-01DOI: 10.1109/ICCIA.2018.00041
Young-Min Kim
The recent success of deep neural network in computer vision provided a new framework to detect visual features of painting styles. However, most deep learning-based approaches analyzing artworks are not interested in popular arts such as comics. In this works, we investigate the artistic styles of comics with deep neural networks. First, we classify comic book pages into five different artists using Convolutional Neural Networks. And the internal features of comic styles are then captured via a feature visualization technique. Second, a style transfer algorithm is applied to several comic book pages drawn by three different artists. We verify how the visual property of a style is transferred to a page using several examples. This is one of the first attempts to analyze in detail the styles of comics with deep neural networks.
{"title":"What Makes the Difference in Visual Styles of Comics: From Classification to Style Transfer","authors":"Young-Min Kim","doi":"10.1109/ICCIA.2018.00041","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00041","url":null,"abstract":"The recent success of deep neural network in computer vision provided a new framework to detect visual features of painting styles. However, most deep learning-based approaches analyzing artworks are not interested in popular arts such as comics. In this works, we investigate the artistic styles of comics with deep neural networks. First, we classify comic book pages into five different artists using Convolutional Neural Networks. And the internal features of comic styles are then captured via a feature visualization technique. Second, a style transfer algorithm is applied to several comic book pages drawn by three different artists. We verify how the visual property of a style is transferred to a page using several examples. This is one of the first attempts to analyze in detail the styles of comics with deep neural networks.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128255524","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00055
Jaehoon Kim
In anomaly detection, as threshold, we typically use the 1.5 times or more of the interquartile range (IQR) in the parametric statistical method or 3σ in normal distribution. However, this criterion is not suitable for our application domain. Because the threshold value is so high that the IQR or 3σ is not secure. Therefore, we consider using median value as a threshold. Using the median value is more secure than using the IQR or 3σ as the number is smaller. In this paper, we first introduce our application domain and then verify that using the median value is more suitable in our application domain. In addition, we conclude that, depending on the situation, other measurements such as σ, 2σ, mean, and mode can be suitable criteria.
{"title":"Using Median as a Threshold in Determining Anomaly in Back-End Authentication","authors":"Jaehoon Kim","doi":"10.1109/ICCIA.2018.00055","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00055","url":null,"abstract":"In anomaly detection, as threshold, we typically use the 1.5 times or more of the interquartile range (IQR) in the parametric statistical method or 3σ in normal distribution. However, this criterion is not suitable for our application domain. Because the threshold value is so high that the IQR or 3σ is not secure. Therefore, we consider using median value as a threshold. Using the median value is more secure than using the IQR or 3σ as the number is smaller. In this paper, we first introduce our application domain and then verify that using the median value is more suitable in our application domain. In addition, we conclude that, depending on the situation, other measurements such as σ, 2σ, mean, and mode can be suitable criteria.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123843061","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 : 2018-07-01DOI: 10.1109/iccia.2018.00060
{"title":"Publisher's Information","authors":"","doi":"10.1109/iccia.2018.00060","DOIUrl":"https://doi.org/10.1109/iccia.2018.00060","url":null,"abstract":"","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116178005","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00038
Bingzhen Lei, Xiuqing Li, Jun Zhang, Junhai Wen
The iterative reconstruction algorithms can get better reconstruction result by adding constraints in the case of incomplete or uneven projection. In the iterative reconstruction algorithm, how to obtain the relationship between the reconstructed image and the projected data, namely, projection matrix, is the key to the image reconstruction. In this paper, the neural network algorithm is used to calculate the projection matrix, which gives a solution to a class of problems. In simulation, we use the projection matrix trained by the neural network to achieve the reconstruction, and the results show that the original image can be well reconstructed.
{"title":"Calculation of Projection Matrix in Image Reconstruction Based on Neural Network","authors":"Bingzhen Lei, Xiuqing Li, Jun Zhang, Junhai Wen","doi":"10.1109/ICCIA.2018.00038","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00038","url":null,"abstract":"The iterative reconstruction algorithms can get better reconstruction result by adding constraints in the case of incomplete or uneven projection. In the iterative reconstruction algorithm, how to obtain the relationship between the reconstructed image and the projected data, namely, projection matrix, is the key to the image reconstruction. In this paper, the neural network algorithm is used to calculate the projection matrix, which gives a solution to a class of problems. In simulation, we use the projection matrix trained by the neural network to achieve the reconstruction, and the results show that the original image can be well reconstructed.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132537043","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00044
Z. Ibrahim, Kamil Zakwan Mohd Azmi, Nor Azlina Ab. Aziz, Nor Hidayati Abdul Aziz, B. Muhammad, Mohd Falfazli Mat Jusof, M. I. Shapiai
Simulated Kalman filter (SKF) is a recent metaheuristic optimization algorithm established in 2015. In the present study, we introduce a prediction operator in SKF to prolong its exploration and to avoid premature convergence. The proposed prediction operator is based on oppositional learning. The results show that using CEC2014 as benchmark problems, the SKF algorithm with oppositional learning prediction operator outperforms the original SKF algorithm in most cases.
{"title":"An Oppositional Learning Prediction Operator for Simulated Kalman Filter","authors":"Z. Ibrahim, Kamil Zakwan Mohd Azmi, Nor Azlina Ab. Aziz, Nor Hidayati Abdul Aziz, B. Muhammad, Mohd Falfazli Mat Jusof, M. I. Shapiai","doi":"10.1109/ICCIA.2018.00044","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00044","url":null,"abstract":"Simulated Kalman filter (SKF) is a recent metaheuristic optimization algorithm established in 2015. In the present study, we introduce a prediction operator in SKF to prolong its exploration and to avoid premature convergence. The proposed prediction operator is based on oppositional learning. The results show that using CEC2014 as benchmark problems, the SKF algorithm with oppositional learning prediction operator outperforms the original SKF algorithm in most cases.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114636582","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 : 2018-07-01DOI: 10.1109/iccia.2018.00043
Yongpeng Zhang, Chao Gao
In order to meet the needs of equipment in the modern micro system, such as cost, power, efficiency and so on, this paper studies a design of wireless transceiver system based on micro-satellite. By analyzing the actual requirements of the system, the design of the reliability and quality of the system in hardware design and software design is optimized. An efficient, low-cost and reliable wireless transceiver system for small satellites.
{"title":"Incomparable Wireless Transceiver System Design for Micro-Satellite","authors":"Yongpeng Zhang, Chao Gao","doi":"10.1109/iccia.2018.00043","DOIUrl":"https://doi.org/10.1109/iccia.2018.00043","url":null,"abstract":"In order to meet the needs of equipment in the modern micro system, such as cost, power, efficiency and so on, this paper studies a design of wireless transceiver system based on micro-satellite. By analyzing the actual requirements of the system, the design of the reliability and quality of the system in hardware design and software design is optimized. An efficient, low-cost and reliable wireless transceiver system for small satellites.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117087091","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00036
Richard K. Sipes, Dan Li
Acute lymphoblastic leukemia can be diagnosed through a series of tests which include the minimally invasive microscopic examination of a stained peripheral blood smear. Manual microscopy is a slow process with variable accuracy depending on the laboratorian's skill level. Thus automating microscopy is a goal in cell biology. Current methods involve hand-selecting features from cell images as inputs to a variety of standard machine learning classifiers. Underrepresented in this filed, yet successful in practice, is the convolutional neural network that learns features from fine-grained images. This paper compares the performance of a convolutional neural network model with other models to determine the validity of using whole cell images rather than hand-selected features for acute lymphoblastic leukemia classification.
{"title":"Using Convolutional Neural Networks for Automated Fine Grained Image Classification of Acute Lymphoblastic Leukemia","authors":"Richard K. Sipes, Dan Li","doi":"10.1109/ICCIA.2018.00036","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00036","url":null,"abstract":"Acute lymphoblastic leukemia can be diagnosed through a series of tests which include the minimally invasive microscopic examination of a stained peripheral blood smear. Manual microscopy is a slow process with variable accuracy depending on the laboratorian's skill level. Thus automating microscopy is a goal in cell biology. Current methods involve hand-selecting features from cell images as inputs to a variety of standard machine learning classifiers. Underrepresented in this filed, yet successful in practice, is the convolutional neural network that learns features from fine-grained images. This paper compares the performance of a convolutional neural network model with other models to determine the validity of using whole cell images rather than hand-selected features for acute lymphoblastic leukemia classification.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"41 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120820943","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00028
Fulian Yin, Yanyan Wang, Xingyi Pan, Pei Su
Based on word embedding method, this paper presents a word vector based review vector method for sentiment analysis of movie reviews. As a result, it is achieved that 86.18% classification accuracy using the method. Meanwhile, the method is applicable to multiple languages such as Chinese and English, and it is extensible for larger scale contents as well. What’s more, the influence of word vector dimensions on the sentiment analysis accuracy and the method’s applicability on sentences of varied lengths are also discussed in this paper. The experimental result proved that the word vector based review method for sentiment analysis is not only an efficient and simple way to analyze emotional expression, but also has extensibility and applicability for comments in varied lengths and multiple languages.
{"title":"A Word Vector Based Review Vector Method for Sentiment Analysis of Movie Reviews Exploring the Applicability of the Movie Reviews","authors":"Fulian Yin, Yanyan Wang, Xingyi Pan, Pei Su","doi":"10.1109/ICCIA.2018.00028","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00028","url":null,"abstract":"Based on word embedding method, this paper presents a word vector based review vector method for sentiment analysis of movie reviews. As a result, it is achieved that 86.18% classification accuracy using the method. Meanwhile, the method is applicable to multiple languages such as Chinese and English, and it is extensible for larger scale contents as well. What’s more, the influence of word vector dimensions on the sentiment analysis accuracy and the method’s applicability on sentences of varied lengths are also discussed in this paper. The experimental result proved that the word vector based review method for sentiment analysis is not only an efficient and simple way to analyze emotional expression, but also has extensibility and applicability for comments in varied lengths and multiple languages.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128449490","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00034
D. G. Caetano, F. Fambrini, Y. Iano, Rangel Arthur, R. Ferrarezi, Frank C. Cabello, João von Zuben, Abel A. D. Rodriguez, E. Carrara, Guilherme Mazoni, C. Moya, Daniel Cavalcante de Menezes, Guilherme Ferretti Grissi
In this paper, the authors describe the design, development and implementation of a deep-learning based system mounted on a terrestrial vehicle roof-top. The main objective is to capture images of overheat elements from the distribution powergrid network during the travel. Initially the vehicle was equipped with nine cameras to cover inspection in both side of the road and also covers the front view. This solution results in the capability to inspect hundreds of miles of power distribution lines without the need to stop the vehicle and without the need for a human operator. In the near future autonomous vehicles could be equipped with such a system to perform a full automatic inspection.
{"title":"Design and Implementation of an Automatic Vehicle for Thermographic Inspections in Electric Distribution Network Using Deep Learning Based Software","authors":"D. G. Caetano, F. Fambrini, Y. Iano, Rangel Arthur, R. Ferrarezi, Frank C. Cabello, João von Zuben, Abel A. D. Rodriguez, E. Carrara, Guilherme Mazoni, C. Moya, Daniel Cavalcante de Menezes, Guilherme Ferretti Grissi","doi":"10.1109/ICCIA.2018.00034","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00034","url":null,"abstract":"In this paper, the authors describe the design, development and implementation of a deep-learning based system mounted on a terrestrial vehicle roof-top. The main objective is to capture images of overheat elements from the distribution powergrid network during the travel. Initially the vehicle was equipped with nine cameras to cover inspection in both side of the road and also covers the front view. This solution results in the capability to inspect hundreds of miles of power distribution lines without the need to stop the vehicle and without the need for a human operator. In the near future autonomous vehicles could be equipped with such a system to perform a full automatic inspection.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130866391","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 : 2018-07-01DOI: 10.1109/ICCIA.2018.00024
Jinbin Zhang, Heng Wang
Chinese word usage errors often occur in non-native Chinese learners' writing. It is very helpful for non-native Chinese learners to detect them automatically when learning writing. In this paper, we propose a novel approach, which takes advantages of different auxiliary tasks, such as POS-tagging prediction and word log frequency prediction, to help the task of Chinese word usage error detection. With the help of these auxiliary tasks, we achieve the state-of-the-art results on the performances on the HSK corpus data, without any other extra data.
{"title":"Multi-Task Learning for Chinese Word Usage Errors Detection","authors":"Jinbin Zhang, Heng Wang","doi":"10.1109/ICCIA.2018.00024","DOIUrl":"https://doi.org/10.1109/ICCIA.2018.00024","url":null,"abstract":"Chinese word usage errors often occur in non-native Chinese learners' writing. It is very helpful for non-native Chinese learners to detect them automatically when learning writing. In this paper, we propose a novel approach, which takes advantages of different auxiliary tasks, such as POS-tagging prediction and word log frequency prediction, to help the task of Chinese word usage error detection. With the help of these auxiliary tasks, we achieve the state-of-the-art results on the performances on the HSK corpus data, without any other extra data.","PeriodicalId":297098,"journal":{"name":"2018 3rd International Conference on Computational Intelligence and Applications (ICCIA)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123109735","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：