Pub Date : 2023-01-01DOI: 10.18178/ijke.2023.9.1.138
Artamevia Salsabila Rizaldi, L. Andrawina, A. Rumanti
—At this time, knowledge becomes a competitive advantage for companies. The importance of knowledge dissemination so that missing knowledge does not occur in the organization. The object of this research is natural tourism in determining indicators of natural tourism potential to assist the Tourism and Culture Office of Rembang Regency. This organization requires knowledge management to achieve its goals. The purpose of this research is to design a taxonomic model which is part of knowledge management in helping organizations deal with the problems they are facing by managing and using information and knowledge in the form of indicators to determine the potential for nature tourism in Rembang Regency.
{"title":"Knowledge Taxonomy Model for Determining Indicators of Natural Tourism Potential","authors":"Artamevia Salsabila Rizaldi, L. Andrawina, A. Rumanti","doi":"10.18178/ijke.2023.9.1.138","DOIUrl":"https://doi.org/10.18178/ijke.2023.9.1.138","url":null,"abstract":"—At this time, knowledge becomes a competitive advantage for companies. The importance of knowledge dissemination so that missing knowledge does not occur in the organization. The object of this research is natural tourism in determining indicators of natural tourism potential to assist the Tourism and Culture Office of Rembang Regency. This organization requires knowledge management to achieve its goals. The purpose of this research is to design a taxonomic model which is part of knowledge management in helping organizations deal with the problems they are facing by managing and using information and knowledge in the form of indicators to determine the potential for nature tourism in Rembang Regency.","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"2016 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86370612","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 : 2023-01-01DOI: 10.1504/ijkesdp.2023.10057725
H. Wakaki, H. Yanagihara, M. Ohishi, M. Ono
{"title":"Stable Estimation of the Slant Parameter in Skew Normal Regression via an MM Algorithm and Ridge Shrinkage","authors":"H. Wakaki, H. Yanagihara, M. Ohishi, M. Ono","doi":"10.1504/ijkesdp.2023.10057725","DOIUrl":"https://doi.org/10.1504/ijkesdp.2023.10057725","url":null,"abstract":"","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67228079","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}
—To respond to the needs of platform users on mobile devices in recent years, several types of web and mobile application software design patterns, including responsive web design (RWD), adaptive website design (AWD), Separate URLs (M.dot), and mobile application software (APP) have been proposed. However, it is difficult for platform owners and developers to decide which design pattern is suitable for them. Therefore, this study explored the literature on the quality assessment indicators of websites and web applications and proposed three quality facets based on the quality inspection project of the website of the National Development Council (NDC). There were three quality facets and a total of 14 quality indicators. This study further chose six sample platforms of three types of social media, news media, and e-commerce based on the network traffic analysis platform. After evaluation and testing, this study analyzed the evaluation results of different design patterns for each sample platform and then discussed each design pattern and its overall comparison. According to the analysis results of an individual design pattern, APP design patterns are recommended for the platforms whose quality requirements are functional applications, loading response speed, and user experience. AWD design patterns are recommended for the platforms whose quality requirements are information connectivity and interface design and layout. RWD design patterns are recommended for the platforms whose quality requirements are platform visibility and information connectivity. If an existing platform has already developed traditional web design and it’s difficult to adjust greatly, the alternative of increasing the development of M.dot is recommended.
{"title":"Quality Assessment of Web and APP Design Patterns","authors":"Yi-Qi Chen, Sun-Jen Huang, Yu-Hsiang Chien, I-Ting Hsiao","doi":"10.18178/ijke.2023.9.1.139","DOIUrl":"https://doi.org/10.18178/ijke.2023.9.1.139","url":null,"abstract":"—To respond to the needs of platform users on mobile devices in recent years, several types of web and mobile application software design patterns, including responsive web design (RWD), adaptive website design (AWD), Separate URLs (M.dot), and mobile application software (APP) have been proposed. However, it is difficult for platform owners and developers to decide which design pattern is suitable for them. Therefore, this study explored the literature on the quality assessment indicators of websites and web applications and proposed three quality facets based on the quality inspection project of the website of the National Development Council (NDC). There were three quality facets and a total of 14 quality indicators. This study further chose six sample platforms of three types of social media, news media, and e-commerce based on the network traffic analysis platform. After evaluation and testing, this study analyzed the evaluation results of different design patterns for each sample platform and then discussed each design pattern and its overall comparison. According to the analysis results of an individual design pattern, APP design patterns are recommended for the platforms whose quality requirements are functional applications, loading response speed, and user experience. AWD design patterns are recommended for the platforms whose quality requirements are information connectivity and interface design and layout. RWD design patterns are recommended for the platforms whose quality requirements are platform visibility and information connectivity. If an existing platform has already developed traditional web design and it’s difficult to adjust greatly, the alternative of increasing the development of M.dot is recommended.","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79118245","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 : 2023-01-01DOI: 10.18178/ijke.2023.9.1.137
Tao Zhang, Yuqing He, Decai Li, Yuanye Xu
— The failure of traditional clustering methods on high-dimensional data has been a thorny problem. Therefore, we propose a simple but effective mean shift feature weighted deformation method (WDNS) to calculate the density value of high-dimensional data points by learning the weights of the features. The neighborhood search is then carried out using the density center in the decision diagram as the starting point, and the points of the same cluster are merged to finally complete the clustering. The experimental results show that the algorithm has higher clustering accuracy than the six existing clustering algorithms. In addition, it has the outstanding feature of automatic parameter setting, which is not available in its peers. In summary, this work can improve the state-of-the-art of clustering algorithms.
{"title":"Automatic Neighborhood Search Clustering Algorithm Based on Feature Weighted Density","authors":"Tao Zhang, Yuqing He, Decai Li, Yuanye Xu","doi":"10.18178/ijke.2023.9.1.137","DOIUrl":"https://doi.org/10.18178/ijke.2023.9.1.137","url":null,"abstract":"— The failure of traditional clustering methods on high-dimensional data has been a thorny problem. Therefore, we propose a simple but effective mean shift feature weighted deformation method (WDNS) to calculate the density value of high-dimensional data points by learning the weights of the features. The neighborhood search is then carried out using the density center in the decision diagram as the starting point, and the points of the same cluster are merged to finally complete the clustering. The experimental results show that the algorithm has higher clustering accuracy than the six existing clustering algorithms. In addition, it has the outstanding feature of automatic parameter setting, which is not available in its peers. In summary, this work can improve the state-of-the-art of clustering algorithms.","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"174 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74166140","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 : 2022-01-01DOI: 10.18178/ijke.2022.8.1.136
Toan Pham Van, T. Tung, Linh Bao Doan, Thanh Ta Minh
—Model pruning is an important technique in real-world machine learning problems, especially in deep learning. This technique has provided some methods for compressing a large model to a smaller model while retaining the most accuracy. However, a majority of these approaches require a full original training set. This might not always be possible in practice if the model is trained in a large-scale dataset or on a dataset whose release poses privacy. Although we cannot access the original training set in some cases, pre-trained models are available more often. This paper aims to solve the model pruning problem without the initial training set by finding the sub-networks in the initial pre-trained model. We propose an approach of using genetic algorithms (GA) to find the sub-networks systematically and automatically. Experimental results show that our algorithm can find good sub-networks efficiently. Theoretically, if we had unlimited time and hardware power, we could find the optimized sub-networks of any pre-trained model and achieve the best results in the future. Our code and pre-trained models are available at: https://github.com/sun-asterisk-research/ga_pruning_research.
{"title":"An Evolution Approach for Pre-trained Neural Network Pruning without Original Training Dataset","authors":"Toan Pham Van, T. Tung, Linh Bao Doan, Thanh Ta Minh","doi":"10.18178/ijke.2022.8.1.136","DOIUrl":"https://doi.org/10.18178/ijke.2022.8.1.136","url":null,"abstract":"—Model pruning is an important technique in real-world machine learning problems, especially in deep learning. This technique has provided some methods for compressing a large model to a smaller model while retaining the most accuracy. However, a majority of these approaches require a full original training set. This might not always be possible in practice if the model is trained in a large-scale dataset or on a dataset whose release poses privacy. Although we cannot access the original training set in some cases, pre-trained models are available more often. This paper aims to solve the model pruning problem without the initial training set by finding the sub-networks in the initial pre-trained model. We propose an approach of using genetic algorithms (GA) to find the sub-networks systematically and automatically. Experimental results show that our algorithm can find good sub-networks efficiently. Theoretically, if we had unlimited time and hardware power, we could find the optimized sub-networks of any pre-trained model and achieve the best results in the future. Our code and pre-trained models are available at: https://github.com/sun-asterisk-research/ga_pruning_research.","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90860028","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 : 2021-01-01DOI: 10.18178/ijke.2021.7.2.135
Deepti Lamba, W. Hsu
This paper presents the results of constraint-based automatic question generation for paragraphs from privacy policy documents. Existing work on question generation uses sequence-to-sequence and transformer-based approaches. This work introduces constraints to sequence-to-sequence and transformer based T5 model. The notion behind this work is that providing the deep learning models with additional background domain information can aid the system in learning useful patterns. This work presents three kinds of constraints – logical, empirical, and data-based constraint. The constraints are incorporated in the deep learning models by introducing additional penalty or reward terms in the loss function. Automatic evaluation results show that our approach significantly outperforms the state-of-the-art models.
{"title":"Constraint-Based Neural Question Generation Using Sequence-to-Sequence and Transformer Models for Privacy Policy Documents","authors":"Deepti Lamba, W. Hsu","doi":"10.18178/ijke.2021.7.2.135","DOIUrl":"https://doi.org/10.18178/ijke.2021.7.2.135","url":null,"abstract":"This paper presents the results of constraint-based automatic question generation for paragraphs from privacy policy documents. Existing work on question generation uses sequence-to-sequence and transformer-based approaches. This work introduces constraints to sequence-to-sequence and transformer based T5 model. The notion behind this work is that providing the deep learning models with additional background domain information can aid the system in learning useful patterns. This work presents three kinds of constraints – logical, empirical, and data-based constraint. The constraints are incorporated in the deep learning models by introducing additional penalty or reward terms in the loss function. Automatic evaluation results show that our approach significantly outperforms the state-of-the-art models.","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"98 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84537769","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 : 2019-01-01DOI: 10.18178/IJKE.2019.5.2.122
Eugene S. Valeriano
{"title":"Improving Data Integrity within Relational Database Using Distinct Function","authors":"Eugene S. Valeriano","doi":"10.18178/IJKE.2019.5.2.122","DOIUrl":"https://doi.org/10.18178/IJKE.2019.5.2.122","url":null,"abstract":"","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87615681","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 : 2019-01-01DOI: 10.18178/ijke.2019.5.2.118
Quang-Phuoc Nguyen
{"title":"Word-Sense Annotation Preprocessor for Improving Neural Machine Translation","authors":"Quang-Phuoc Nguyen","doi":"10.18178/ijke.2019.5.2.118","DOIUrl":"https://doi.org/10.18178/ijke.2019.5.2.118","url":null,"abstract":"","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73413524","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 : 2019-01-01DOI: 10.18178/ijke.2019.5.1.110
R. N. PolyakovandL
{"title":"Key Components of the Educational Environment in Training Engineers of the XXI Century","authors":"R. N. PolyakovandL","doi":"10.18178/ijke.2019.5.1.110","DOIUrl":"https://doi.org/10.18178/ijke.2019.5.1.110","url":null,"abstract":"","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76769304","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 : 2019-01-01DOI: 10.18178/ijke.2019.5.1.108
Takayuki Hoshino
{"title":"A Graph-Based Model for Experiential Knowledge","authors":"Takayuki Hoshino","doi":"10.18178/ijke.2019.5.1.108","DOIUrl":"https://doi.org/10.18178/ijke.2019.5.1.108","url":null,"abstract":"","PeriodicalId":88527,"journal":{"name":"International journal of knowledge engineering and soft data paradigms","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75303045","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：