Pub Date : 2017-11-01DOI: 10.1109/ISKE.2017.8258773
Yu Wang, Bin Xia, Zheng Liu, Yun Li, Tao Li
Named Entity Recognition (NER) is a basic task in Natural Language Processing (NLP), which extracts the meaningful named entities from the text. Compared with the English NER, the Chinese NER is more challenge, since there is no tense in the Chinese language. Moreover, the omissions and the Internet catchwords in the Chinese corpus make the NER task more difficult. Traditional machine learning methods (e.g., CRFs) cannot address the Chinese NER effectively because they are hard to learn the complicated context in the Chinese language. To overcome the aforementioned problem, we propose a deep learning model Char2Vec+Bi-LSTMs for Chinese NER. We use the Chinese character instead of the Chinese word as the embedding unit, and the Bi-LSTMs is used to learn the complicated semantic dependency. To evaluate our proposed model, we construct the corpus from the China TELECOM FAQs. Experimental results show that our model achieves better performance than other baseline methods and the character embedding is more appropriate than the word embedding in the Chinese language.
{"title":"Named entity recognition for Chinese telecommunications field based on Char2Vec and Bi-LSTMs","authors":"Yu Wang, Bin Xia, Zheng Liu, Yun Li, Tao Li","doi":"10.1109/ISKE.2017.8258773","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258773","url":null,"abstract":"Named Entity Recognition (NER) is a basic task in Natural Language Processing (NLP), which extracts the meaningful named entities from the text. Compared with the English NER, the Chinese NER is more challenge, since there is no tense in the Chinese language. Moreover, the omissions and the Internet catchwords in the Chinese corpus make the NER task more difficult. Traditional machine learning methods (e.g., CRFs) cannot address the Chinese NER effectively because they are hard to learn the complicated context in the Chinese language. To overcome the aforementioned problem, we propose a deep learning model Char2Vec+Bi-LSTMs for Chinese NER. We use the Chinese character instead of the Chinese word as the embedding unit, and the Bi-LSTMs is used to learn the complicated semantic dependency. To evaluate our proposed model, we construct the corpus from the China TELECOM FAQs. Experimental results show that our model achieves better performance than other baseline methods and the character embedding is more appropriate than the word embedding in the Chinese language.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128181990","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258814
Yuanyuan Wang, Jian Zhou, Ke-Jia Chen, Yunyun Wang, Linfeng Liu
Water quality prediction has more practical significance not only for the management of water resources but also for the prevention of water pollution. It's a time series prediction problem which the traditional neural network isn't suitable. A new water quality prediction method based on long and short term memory neural network (LSTM NN) for water quality prediction is proposed in this paper. Firstly, a prediction model based on LSTM NN is established. Secondly, as the training data, the data set of water quality indicators in Taihu Lake which measured monthly from 2000 to 2006 years is used for training model. Thirdly, to improve the predictive accuracy of the model, a series of simulations and parameters selection are carried out. Finally, the proposed method is compared with two methods: one is based on back propagation neural network, the other is based on online sequential extreme learning machine. The results show that the method is more accurate and more generalized.
{"title":"Water quality prediction method based on LSTM neural network","authors":"Yuanyuan Wang, Jian Zhou, Ke-Jia Chen, Yunyun Wang, Linfeng Liu","doi":"10.1109/ISKE.2017.8258814","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258814","url":null,"abstract":"Water quality prediction has more practical significance not only for the management of water resources but also for the prevention of water pollution. It's a time series prediction problem which the traditional neural network isn't suitable. A new water quality prediction method based on long and short term memory neural network (LSTM NN) for water quality prediction is proposed in this paper. Firstly, a prediction model based on LSTM NN is established. Secondly, as the training data, the data set of water quality indicators in Taihu Lake which measured monthly from 2000 to 2006 years is used for training model. Thirdly, to improve the predictive accuracy of the model, a series of simulations and parameters selection are carried out. Finally, the proposed method is compared with two methods: one is based on back propagation neural network, the other is based on online sequential extreme learning machine. The results show that the method is more accurate and more generalized.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127177838","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258842
Fan Yang, Peng Piao, Yongxuan Lai, Liu Pei
Permutation based variable importance measure (VIM) has been widely used in various research fields. For example, in gene expression studies, it has been regarded as a screening tool to select a subset of relevant genes for subsequent analysis or better predictive performance. However, little effort has been devoted to the stability of variable importance measures. In this paper, margin based permutation variable importance measures (VIM-MDs) are proposed, which utilize the similarity between margin distribution before and after random permutation to evaluate the importance of variables. Experiments on six benchmark datasets show that the VIM-MDs outperform permutation based variable importance measure in terms of both global stability and predictive accuracy, which indicates that the proposed method could be used as an effective and stable variable importance measure for random forest.
{"title":"Margin based permutation variable importance: A stable importance measure for random forest","authors":"Fan Yang, Peng Piao, Yongxuan Lai, Liu Pei","doi":"10.1109/ISKE.2017.8258842","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258842","url":null,"abstract":"Permutation based variable importance measure (VIM) has been widely used in various research fields. For example, in gene expression studies, it has been regarded as a screening tool to select a subset of relevant genes for subsequent analysis or better predictive performance. However, little effort has been devoted to the stability of variable importance measures. In this paper, margin based permutation variable importance measures (VIM-MDs) are proposed, which utilize the similarity between margin distribution before and after random permutation to evaluate the importance of variables. Experiments on six benchmark datasets show that the VIM-MDs outperform permutation based variable importance measure in terms of both global stability and predictive accuracy, which indicates that the proposed method could be used as an effective and stable variable importance measure for random forest.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126550545","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258833
Julius Onyancha, V. Plekhanova
The rate at which web data is collected, stored and accessed by web users has led to high levels of noisiness. As the amount of noise in web data increases, it becomes difficult to find useful information based on a specific user interest. Current research works consider noise as any data that does not form part of the main web page, they propose machine learning algorithms aimed at protecting the main web page content from irrelevant data such as advertisements, banners, external links etc. Depending on what a user is interested on the web, noise web data can be useful data but on the other hand, useful data can be noisy. To learn noise data in a web user profile, a new machine learning algorithm/tool is proposed in this paper. An experimental design setup is presented to validate the performance of the proposed algorithms. The results obtained are compared with the currently available noise web data reduction tools. The experimental results show that the proposed algorithms not only eliminate noise from a web user profile but learn prior to elimination. Learning of noise data prior to elimination contributes to the quality of user profile which is not addressed by the currently available tools.
{"title":"A user-centric approach towards learning noise in web data","authors":"Julius Onyancha, V. Plekhanova","doi":"10.1109/ISKE.2017.8258833","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258833","url":null,"abstract":"The rate at which web data is collected, stored and accessed by web users has led to high levels of noisiness. As the amount of noise in web data increases, it becomes difficult to find useful information based on a specific user interest. Current research works consider noise as any data that does not form part of the main web page, they propose machine learning algorithms aimed at protecting the main web page content from irrelevant data such as advertisements, banners, external links etc. Depending on what a user is interested on the web, noise web data can be useful data but on the other hand, useful data can be noisy. To learn noise data in a web user profile, a new machine learning algorithm/tool is proposed in this paper. An experimental design setup is presented to validate the performance of the proposed algorithms. The results obtained are compared with the currently available noise web data reduction tools. The experimental results show that the proposed algorithms not only eliminate noise from a web user profile but learn prior to elimination. Learning of noise data prior to elimination contributes to the quality of user profile which is not addressed by the currently available tools.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124978470","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258778
Qinghua Liu, Yang Xu, Xingxing He
Many works are available in the literature to define dissimilarity metrics between expressions represented in the form of first-order logic, which is a powerful representation language. Generally speaking, first-order terms are basic logic expressions such that the first step in defining a valid metric between first-order expressions is to define a metric between terms. In this work, we introduce a new metric between terms which is an extension of the metric based on substitutions proposed by Alan Hutchinson. Our approach breaks the limitation of Alan Hutchinson's metric which is only suitable for ground terms and enhances the power of reflecting the dissimilarity in ground terms. In fact, both function symbols and variable symbols are the source of difference between terms. As a consequence, the new metric considers difference caused the two factors as J. Ramon et al. do, but in a different way which is based on substitutions. It is also defined in the form of 2-tuples, the first element of which is used for estimating difference caused by function symbols and another for estimating difference caused by variable symbols. Besides, some experimental results are also shown in the paper, which illustrates the effects and improvement compared with Alan Hutchinson's metric.
{"title":"New terms metric based on substitutions","authors":"Qinghua Liu, Yang Xu, Xingxing He","doi":"10.1109/ISKE.2017.8258778","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258778","url":null,"abstract":"Many works are available in the literature to define dissimilarity metrics between expressions represented in the form of first-order logic, which is a powerful representation language. Generally speaking, first-order terms are basic logic expressions such that the first step in defining a valid metric between first-order expressions is to define a metric between terms. In this work, we introduce a new metric between terms which is an extension of the metric based on substitutions proposed by Alan Hutchinson. Our approach breaks the limitation of Alan Hutchinson's metric which is only suitable for ground terms and enhances the power of reflecting the dissimilarity in ground terms. In fact, both function symbols and variable symbols are the source of difference between terms. As a consequence, the new metric considers difference caused the two factors as J. Ramon et al. do, but in a different way which is based on substitutions. It is also defined in the form of 2-tuples, the first element of which is used for estimating difference caused by function symbols and another for estimating difference caused by variable symbols. Besides, some experimental results are also shown in the paper, which illustrates the effects and improvement compared with Alan Hutchinson's metric.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128311557","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258808
Tian Zhang, Changchuan Yin, Lin Pan
In order to help students improve their performance in college, this paper discovered the association rules among the scores of different courses, and introduced the parameter "Interest" to help filtering the rules. In order to meet the demand for score discretization in association rules mining, this paper analyzed score distribution characteristics, and proposed an initial cluster center optimized and isolated point pre-processed K-means clustering algorithm based on sample distribution density. This algorithm can reduce the sensitivity of K-means algorithm to initial cluster centers and isolated points. The numerical results and evaluation index show that this algorithm can meet the requirements of score discretization. The result of association rules mining using this improved K-means algorithm for score discretization can efficiently reduce the invalid and wrong rules.
{"title":"Improved clustering and association rules mining for university student course scores","authors":"Tian Zhang, Changchuan Yin, Lin Pan","doi":"10.1109/ISKE.2017.8258808","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258808","url":null,"abstract":"In order to help students improve their performance in college, this paper discovered the association rules among the scores of different courses, and introduced the parameter \"Interest\" to help filtering the rules. In order to meet the demand for score discretization in association rules mining, this paper analyzed score distribution characteristics, and proposed an initial cluster center optimized and isolated point pre-processed K-means clustering algorithm based on sample distribution density. This algorithm can reduce the sensitivity of K-means algorithm to initial cluster centers and isolated points. The numerical results and evaluation index show that this algorithm can meet the requirements of score discretization. The result of association rules mining using this improved K-means algorithm for score discretization can efficiently reduce the invalid and wrong rules.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116485735","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258772
Gollapudi V. R. J. Sai Prasad, M. S. Soumya, Venkatesh Choppella
In this paper we focus on the human users and aid them in better knowledge formation. We suggest that users face accessibility challenges in gathering information, especially when it is in a different representation system than they are used to. We identify this as a semantic gap. To overcome this we propose a client-side, browser based information modification tool called Renarration UI. We focus on both the design and implementation aspects of this tool and validate it by conducting an empirical study (n=10). Results are encouraging and suggest that renarration of web pages has potential to address these information accessibility issues.
{"title":"Renarrating web pages for improving information accessibility","authors":"Gollapudi V. R. J. Sai Prasad, M. S. Soumya, Venkatesh Choppella","doi":"10.1109/ISKE.2017.8258772","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258772","url":null,"abstract":"In this paper we focus on the human users and aid them in better knowledge formation. We suggest that users face accessibility challenges in gathering information, especially when it is in a different representation system than they are used to. We identify this as a semantic gap. To overcome this we propose a client-side, browser based information modification tool called Renarration UI. We focus on both the design and implementation aspects of this tool and validate it by conducting an empirical study (n=10). Results are encouraging and suggest that renarration of web pages has potential to address these information accessibility issues.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"442 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125779284","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258732
Ya-Ming Wang, Huawen Liu, F. Qin
The aim of this paper is mainly to solve the functional equations of distributivity for 2-uninorms over semit-operators. Our investigations are motivated by the couple of distributive logical connectives and their generalizations, one of which covering both uninorms and nullnorms are 2-uninorms. In this work, we discuss all possible cases of the distributivity equations for 2-uninorms over semi-t-operators, and give the sufficient and necessary conditions that 2-uninorms are distributive over semi-t-operators.
{"title":"Distributivity for 2-uninorms over semi-t-operators","authors":"Ya-Ming Wang, Huawen Liu, F. Qin","doi":"10.1109/ISKE.2017.8258732","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258732","url":null,"abstract":"The aim of this paper is mainly to solve the functional equations of distributivity for 2-uninorms over semit-operators. Our investigations are motivated by the couple of distributive logical connectives and their generalizations, one of which covering both uninorms and nullnorms are 2-uninorms. In this work, we discuss all possible cases of the distributivity equations for 2-uninorms over semi-t-operators, and give the sufficient and necessary conditions that 2-uninorms are distributive over semi-t-operators.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133769420","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}
Friction is quite common and inevitable in physical environments. During the process of friction, vibration and collision will bring large deviations to identification results. In this paper, friction process with the influence of vibration and collision as well as data collection are implemented. In terms of friction model, according to the theory of Fourier series, we can introduce sine filter terms into friction model to eliminate influence of vibration and collision on parameter identifications. To get a much more accurate and efficient algorithm of identification, we embed simulated annealing operator into a genetic algorithm to take the advantages of both genetic algorithm and simulated annealing algorithm. With the hybrid algorithm, the identification results of friction process under the influence of the vibration and collision can be determined effectively.
{"title":"Application of modified Stribeck model and simulated annealing genetic algorithm in friction parameter identification","authors":"Haichen Guo, Boyan Zhou, Pingping Yang, Xincheng Gu","doi":"10.1109/ISKE.2017.8258826","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258826","url":null,"abstract":"Friction is quite common and inevitable in physical environments. During the process of friction, vibration and collision will bring large deviations to identification results. In this paper, friction process with the influence of vibration and collision as well as data collection are implemented. In terms of friction model, according to the theory of Fourier series, we can introduce sine filter terms into friction model to eliminate influence of vibration and collision on parameter identifications. To get a much more accurate and efficient algorithm of identification, we embed simulated annealing operator into a genetic algorithm to take the advantages of both genetic algorithm and simulated annealing algorithm. With the hybrid algorithm, the identification results of friction process under the influence of the vibration and collision can be determined effectively.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134103449","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 : 2017-11-01DOI: 10.1109/ISKE.2017.8258810
Mehrdad Ziaee Nejad, Jie Lu, Vahid Behbood
Accurate prediction of Residential Property Sale Price is very important and significant in the operation of the real estate market. Property sellers and buyers/Investors wish to know a fair value for their properties in particular at the time of the sales transaction. The main reason to build an Automated Valuation Model is to be accurate enough to replace human. To select a most suitable model for the property sale price prediction, this paper examined seven Tree-based machine learning models including Dynamic Bayesian Tree (online learning method), Random Forest, Stochastic Gradient Boosting, CART, Bagged CART, Tree Bagged Ensembles and Boosted Tree (batch learning methods) by comparing their RMSE and MAE performances. The performance of these models are tested on 1967 records of unit sales from 19 suburbs of Sydney, Australia. The main purpose of this study is to compare the performance of batch models with the online model. The results demonstrated that Dynamic Bayesian Tree as an online model stands in the middle of batch models based on the root mean square error (RMSE) and mean absolute error (MAE). It shows using online model for estimating the property sale price is reasonable for real world application.
{"title":"Applying dynamic Bayesian tree in property sales price estimation","authors":"Mehrdad Ziaee Nejad, Jie Lu, Vahid Behbood","doi":"10.1109/ISKE.2017.8258810","DOIUrl":"https://doi.org/10.1109/ISKE.2017.8258810","url":null,"abstract":"Accurate prediction of Residential Property Sale Price is very important and significant in the operation of the real estate market. Property sellers and buyers/Investors wish to know a fair value for their properties in particular at the time of the sales transaction. The main reason to build an Automated Valuation Model is to be accurate enough to replace human. To select a most suitable model for the property sale price prediction, this paper examined seven Tree-based machine learning models including Dynamic Bayesian Tree (online learning method), Random Forest, Stochastic Gradient Boosting, CART, Bagged CART, Tree Bagged Ensembles and Boosted Tree (batch learning methods) by comparing their RMSE and MAE performances. The performance of these models are tested on 1967 records of unit sales from 19 suburbs of Sydney, Australia. The main purpose of this study is to compare the performance of batch models with the online model. The results demonstrated that Dynamic Bayesian Tree as an online model stands in the middle of batch models based on the root mean square error (RMSE) and mean absolute error (MAE). It shows using online model for estimating the property sale price is reasonable for real world application.","PeriodicalId":208009,"journal":{"name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131331596","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：