Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00012
Yong Huang, Mingzhen Zhang, Yue He
The RFM model used for customer segmentation in the traditional retail industry is not suitable for the industry with distinct attributes of social groups, so the RFMC model is created by introducing the parameter C of social relations. Educational e-commerce enterprise M is selected for empirical study, and k-means algorithm is used for cluster analysis of valid customers of enterprise M, which resulted in 5 distinct customer groups and verified the effectiveness of the model.
{"title":"Research on improved RFM customer segmentation model based on K-Means algorithm","authors":"Yong Huang, Mingzhen Zhang, Yue He","doi":"10.1109/ICCIA49625.2020.00012","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00012","url":null,"abstract":"The RFM model used for customer segmentation in the traditional retail industry is not suitable for the industry with distinct attributes of social groups, so the RFMC model is created by introducing the parameter C of social relations. Educational e-commerce enterprise M is selected for empirical study, and k-means algorithm is used for cluster analysis of valid customers of enterprise M, which resulted in 5 distinct customer groups and verified the effectiveness of the model.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134034507","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 : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00040
Xinfeng Ye, Mu Zhang, Zhaobin Liu
When people search for flight ticket online, they interact with a web site by selecting the ticket information from a set of drop-down menus. This paper proposes a scheme that is more natural for people to interact with the flight ticket server. The scheme integrates a natural language interface with a flight ticket searching system. It allows the users to interact with the flight searching system using natural language. The system is based on the BERT model. Compared with the existing scheme, the proposed scheme achieves good accuracy.
{"title":"A Natural Language-based Flight Searching System","authors":"Xinfeng Ye, Mu Zhang, Zhaobin Liu","doi":"10.1109/ICCIA49625.2020.00040","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00040","url":null,"abstract":"When people search for flight ticket online, they interact with a web site by selecting the ticket information from a set of drop-down menus. This paper proposes a scheme that is more natural for people to interact with the flight ticket server. The scheme integrates a natural language interface with a flight ticket searching system. It allows the users to interact with the flight searching system using natural language. The system is based on the BERT model. Compared with the existing scheme, the proposed scheme achieves good accuracy.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"390 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133948725","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 : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00013
Wentao Wang, Chengxu Ye, Ping Yang, Zhikun Miao
In order to further improve the accuracy of movie recommendation, while considering the characteristics of user data and movie data, this paper studies and proposes a combined recommendation model of LSTM and CNN. The model uses LSTM to capture the context dependency of user ratings data, and at the same time extracts the local relevant features of the movie title with CNN, and then fuse each feature to calculate the predicted ratings, through model training and optimization, the movie recommendation to the user is finally obtained according to the predicted ratings. The MovieLens data set is used to verify the effectiveness of the model, and the results show that compared with the traditional recommendation model and other recommendation models based on deep learning, the combined recommendation model of LSTM and CNN proposed in this paper have a MSE loss reduction of 4.4%~18.7% and a MAE loss reduction of 3.0%~52.2%.
{"title":"Research on Movie Recommendation Model Based on LSTM and CNN","authors":"Wentao Wang, Chengxu Ye, Ping Yang, Zhikun Miao","doi":"10.1109/ICCIA49625.2020.00013","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00013","url":null,"abstract":"In order to further improve the accuracy of movie recommendation, while considering the characteristics of user data and movie data, this paper studies and proposes a combined recommendation model of LSTM and CNN. The model uses LSTM to capture the context dependency of user ratings data, and at the same time extracts the local relevant features of the movie title with CNN, and then fuse each feature to calculate the predicted ratings, through model training and optimization, the movie recommendation to the user is finally obtained according to the predicted ratings. The MovieLens data set is used to verify the effectiveness of the model, and the results show that compared with the traditional recommendation model and other recommendation models based on deep learning, the combined recommendation model of LSTM and CNN proposed in this paper have a MSE loss reduction of 4.4%~18.7% and a MAE loss reduction of 3.0%~52.2%.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127938352","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 : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00022
Xiaozhen Han, Ran Jin
With the vigorous development of artificial intelligence big data era and the advent of 5G era, the amount of network information shows a blowout-like growth. As a result, the accurate query of information is faced with unprecedented challenges. The image as a material reproduction of visual perception, has a large number of retrieval requests all the time, but the traditional image target recognition annotation is mainly based on pixel-level supervised learning. In the face of massive high-quality image recognition, it is very difficult for users to query the target content accurately and quickly. Therefore, this paper studies the animal classification model based on Convolutional Neural Network (CNN), using transfer learning to pre-train the characteristics of the network and combined with the hybrid classification model of CNN. In the experiment, CATS/DOGS were used as the data set, and PyTorch was used to train the network model. Experimental research shows that the accuracy of 96.43% is achieved by using CNN+ transfer learning algorithm, which is significantly higher than that of traditional methods. For small-scale data sets, it effectively solves the non-transferability of manual feature extraction, and improves the accuracy and robustness.
{"title":"A Small Sample Image Recognition Method Based on ResNet and Transfer Learning","authors":"Xiaozhen Han, Ran Jin","doi":"10.1109/ICCIA49625.2020.00022","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00022","url":null,"abstract":"With the vigorous development of artificial intelligence big data era and the advent of 5G era, the amount of network information shows a blowout-like growth. As a result, the accurate query of information is faced with unprecedented challenges. The image as a material reproduction of visual perception, has a large number of retrieval requests all the time, but the traditional image target recognition annotation is mainly based on pixel-level supervised learning. In the face of massive high-quality image recognition, it is very difficult for users to query the target content accurately and quickly. Therefore, this paper studies the animal classification model based on Convolutional Neural Network (CNN), using transfer learning to pre-train the characteristics of the network and combined with the hybrid classification model of CNN. In the experiment, CATS/DOGS were used as the data set, and PyTorch was used to train the network model. Experimental research shows that the accuracy of 96.43% is achieved by using CNN+ transfer learning algorithm, which is significantly higher than that of traditional methods. For small-scale data sets, it effectively solves the non-transferability of manual feature extraction, and improves the accuracy and robustness.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"3 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128777259","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 : 2020-06-01DOI: 10.1109/iccia49625.2020.00004
Iccia, Zhikun Miao, Yongbin Wang
Artificial Neural Network for Forecasting of Daily Reservoir Inflow: Case Study of the Kotmale Reservoir in Sri Lanka 8 Udaya Dampage (General Sir John Kotelawala Defence University), Yasiru Gunaratne (General Sir John Kotelawala Defence University), Ovindi Bandara (General Sir John Kotelawala Defence University), Samitha De Silva (General Sir John Kotelawala Defence University), and Vinushi Waraketiya (General Sir John Kotelawala Defence University)
人工神经网络预测每日水库入库流量：Udaya Dampage（约翰-科特拉瓦拉将军国防大学）、Yasiru Gunaratne（约翰-科特拉瓦拉将军国防大学）、Ovindi Bandara（约翰-科特拉瓦拉将军国防大学）、Samitha De Silva（约翰-科特拉瓦拉将军国防大学）和 Vinushi Waraketiya（约翰-科特拉瓦拉将军国防大学）。
{"title":"ICCIA 2020 TOC","authors":"Iccia, Zhikun Miao, Yongbin Wang","doi":"10.1109/iccia49625.2020.00004","DOIUrl":"https://doi.org/10.1109/iccia49625.2020.00004","url":null,"abstract":"Artificial Neural Network for Forecasting of Daily Reservoir Inflow: Case Study of the Kotmale Reservoir in Sri Lanka 8 Udaya Dampage (General Sir John Kotelawala Defence University), Yasiru Gunaratne (General Sir John Kotelawala Defence University), Ovindi Bandara (General Sir John Kotelawala Defence University), Samitha De Silva (General Sir John Kotelawala Defence University), and Vinushi Waraketiya (General Sir John Kotelawala Defence University)","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128375954","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 : 2020-06-01DOI: 10.1109/iccia49625.2020.00007
{"title":"ICCIA 2020 List Reviewer Page","authors":"","doi":"10.1109/iccia49625.2020.00007","DOIUrl":"https://doi.org/10.1109/iccia49625.2020.00007","url":null,"abstract":"","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133857011","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 : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00014
Ehsan Futuhi, Shayan Karimi
Puzzle solving with AI is becoming one of the hot topic fields in computer science. The algorithmic challenges that are laid behind this topic , make it more attractive. One of these NP-complete puzzles that is hard to solve for human being is Nurikabe Puzzle . few methods have been developed for solving this puzzle that have a poor performance in time and memory. Monte-Carlo Tree Search(MCTS) is a famous reinforcement algorithm that have been used in many Logical games .In this article we use Monte-Carlo Tree Search method for creating the efficient method that performs well on time that it takes for solving the puzzle .no one have ever used this method for solving this problem and also we test our algorithm with a wide range of test cases from easy to hardest ones.
{"title":"Solving Nurikabe with Monte-Carlo Tree Serach","authors":"Ehsan Futuhi, Shayan Karimi","doi":"10.1109/ICCIA49625.2020.00014","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00014","url":null,"abstract":"Puzzle solving with AI is becoming one of the hot topic fields in computer science. The algorithmic challenges that are laid behind this topic , make it more attractive. One of these NP-complete puzzles that is hard to solve for human being is Nurikabe Puzzle . few methods have been developed for solving this puzzle that have a poor performance in time and memory. Monte-Carlo Tree Search(MCTS) is a famous reinforcement algorithm that have been used in many Logical games .In this article we use Monte-Carlo Tree Search method for creating the efficient method that performs well on time that it takes for solving the puzzle .no one have ever used this method for solving this problem and also we test our algorithm with a wide range of test cases from easy to hardest ones.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132519057","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 : 2020-06-01DOI: 10.1109/iccia49625.2020.00001
{"title":"[Half-title page]","authors":"","doi":"10.1109/iccia49625.2020.00001","DOIUrl":"https://doi.org/10.1109/iccia49625.2020.00001","url":null,"abstract":"","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130050822","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}
With the rapid development of Internet social media, twitter has gradually become the most mainstream information release and information sharing platform. A large number of twitter users use the platform to express their views, emotions and opinions. However, it is still a challenge on twitter semantic classification based on the observation that Twitters are short, noisy, arbitrary, etc. Thus, we seek in the mainstream NLP algorithms to find out which algorithm performs best in this problem. After that, we analysis the ensemble methods on the former encode expand to get a better result. However, we find that it dosen’t work well as we expected. we analysis the reason and give the potential explain. The extensive experiments have shown that the LCF-BERT based model performs best over the mainstream algorithms and the ensemble model on the Twitter dataset.
{"title":"Does ensemble really work when facing the twitter semantic classification?","authors":"Wenqiang Luo, Sheng Yi, Jiaxin Chen, Shuqing Weng, Zengwen Dong","doi":"10.1109/ICCIA49625.2020.00015","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00015","url":null,"abstract":"With the rapid development of Internet social media, twitter has gradually become the most mainstream information release and information sharing platform. A large number of twitter users use the platform to express their views, emotions and opinions. However, it is still a challenge on twitter semantic classification based on the observation that Twitters are short, noisy, arbitrary, etc. Thus, we seek in the mainstream NLP algorithms to find out which algorithm performs best in this problem. After that, we analysis the ensemble methods on the former encode expand to get a better result. However, we find that it dosen’t work well as we expected. we analysis the reason and give the potential explain. The extensive experiments have shown that the LCF-BERT based model performs best over the mainstream algorithms and the ensemble model on the Twitter dataset.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114514252","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 : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00029
Yi Lin, Bin Wang
This paper makes an attempt to develop an automated facial complexion recognition method for objective and quantitative facial diagnosis. In TCM diagnosis, some regions of the face like Ting, Jia and Mingtang, can provide the most valuable information, so we use deep learning technique to determine the 68 landmarks of face and use their location to segment the regions of interest (ROI). The statistical characteristics of color histograms in multiple color space and texture features, lip color features are then introduced to describe the facial complexion. Finally, several machine learning methods including KNN, SVM and BPNN are used for classification. To verify the validity of our method, we collected a dataset of 575 face images from professional TCM medical institutions. The results show that the process of ROIs’ segmentation can improve the accuracy efficiently, higher than unsegmented image. The proposed method by fusing all three features achieves an accuracy of 91.03% which is higher than the existing methods and proves the effectiveness of the proposed method for facial complexion recognition. We confirm that extracting the complexion features particularly from the regions of interest of the face image achieves higher classification accuracy than characterizing the overall complexion directly from the unsegmented images. We show that the facial color features provide the most important clues for complexion classification among all the used features, which is consistent with the TCM diagnosis. Finally, we prove that the facial texture feature and lip color feature can be used as complementary clues and fused with the facial color features for further improving the complexion classification accuracy.
{"title":"Facial Complexion Recognition of Traditional Chinese Medicine Based on Computer Vision","authors":"Yi Lin, Bin Wang","doi":"10.1109/ICCIA49625.2020.00029","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00029","url":null,"abstract":"This paper makes an attempt to develop an automated facial complexion recognition method for objective and quantitative facial diagnosis. In TCM diagnosis, some regions of the face like Ting, Jia and Mingtang, can provide the most valuable information, so we use deep learning technique to determine the 68 landmarks of face and use their location to segment the regions of interest (ROI). The statistical characteristics of color histograms in multiple color space and texture features, lip color features are then introduced to describe the facial complexion. Finally, several machine learning methods including KNN, SVM and BPNN are used for classification. To verify the validity of our method, we collected a dataset of 575 face images from professional TCM medical institutions. The results show that the process of ROIs’ segmentation can improve the accuracy efficiently, higher than unsegmented image. The proposed method by fusing all three features achieves an accuracy of 91.03% which is higher than the existing methods and proves the effectiveness of the proposed method for facial complexion recognition. We confirm that extracting the complexion features particularly from the regions of interest of the face image achieves higher classification accuracy than characterizing the overall complexion directly from the unsegmented images. We show that the facial color features provide the most important clues for complexion classification among all the used features, which is consistent with the TCM diagnosis. Finally, we prove that the facial texture feature and lip color feature can be used as complementary clues and fused with the facial color features for further improving the complexion classification accuracy.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132260929","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：