2019 11th International Conference on Knowledge and Systems Engineering (KSE)最新文献_第6页

An Efficient Machine Learning Method to Solve Imbalanced Data in Metabolic Disease Prediction 一种解决代谢性疾病预测数据不平衡的高效机器学习方法

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919337

Vânia Cecchini, T. Nguyen, Thomas Pfau, S. D. Landtsheer, T. Sauter

{"title":"An Efficient Machine Learning Method to Solve Imbalanced Data in Metabolic Disease Prediction","authors":"Vânia Cecchini, T. Nguyen, Thomas Pfau, S. D. Landtsheer, T. Sauter","doi":"10.1109/KSE.2019.8919337","DOIUrl":"https://doi.org/10.1109/KSE.2019.8919337","url":null,"abstract":"The increase of obesity, its related diseases and the high incidence of metabolic diseases as a whole, constitute a major public health problem on a global scale. New strategies that allow for the discovery of novel metabolic disease-related genes are necessary to develop new treatments. In this paper, we proposed an efficient method to predict metabolic disease genes, solving the problem of imbalanced data. The method combined protein-protein interactions and miRNA-target interactions to construct integrated networks, whose topological properties can be used as features to train machine learning classifiers. We applied different strategies to optimize imbalanced class. The best model of gradient boosting achieved a significant F1-score of 0.82. When testing the model with non-disease genes, we predicted 549 candidates, out of which 123 were validated indirectly from literature to be related to metabolic diseases. The remaining genes’ functions were investigated by gene enrichment analysis, revealing their association with diseases known to co-occur with metabolic diseases, such as cancer and cardiovascular conditions. These results indicated that this method contributed to the identification of novel metabolic disease-related genes.","PeriodicalId":439841,"journal":{"name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128780606","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}

引用次数: 3

Annotation Intent Identification toward Enhancement of Marketing Campaign Performance 面向营销活动绩效提升的注释意图识别

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919386

Sorratat Sirirattanajakarin, B. Suntisrivaraporn

引用次数: 2

Less Visually Different Objects Recognition with Aggregated Residual Siamese Network 基于聚集残差暹罗网络的视觉差异较小的目标识别

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919487

A. Nguyen, A. Yoshitaka

{"title":"Less Visually Different Objects Recognition with Aggregated Residual Siamese Network","authors":"A. Nguyen, A. Yoshitaka","doi":"10.1109/KSE.2019.8919487","DOIUrl":"https://doi.org/10.1109/KSE.2019.8919487","url":null,"abstract":"Deep learning has been increasingly achieved advanced success in recent years and becomes a robust technique in the field of computer vision and image processing. However, massive data sets are required to obtain such power when training deep neural networks. On the other hand, many studies succeed in the task of general object recognition, for example, ImageNet Large Scale Visual Recognition Challenge, but there are very few studies that directly deal with the problem of less visually different objects. In this paper, we introduce a challenging problem of visual classification, in which objects are very similar and out-reaching of human’s ability, based on a proposed definition of similarity / less visual difference. Besides, the research also focuses on the backbone drawback of deep learning that is data limitation. A challenging data set, which we call HAM10K-limited, is collected with very few samples and imbalance between classes for evaluating methods. To tackle those issues, a convolutional neural network is proposed, named Aggregated Residual Siamese Network. The empirical results show that the proposed architecture achieves a significant improvement from previous works.","PeriodicalId":439841,"journal":{"name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129133499","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}

引用次数: 0

A Fast Denoising Algorithm for X-Ray Images with Variance Stabilizing Transform 基于方差稳定变换的x射线图像快速去噪算法

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919364

N. H. Hai, D. N. Thanh, N. Hien, H. Premachandra, V. Prasath

引用次数: 4

KSE 2019 Technical Program Committee KSE 2019技术计划委员会

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/kse.2019.8919402

引用次数: 0

Extraction process of conceptual model from a document-oriented NoSQL database 面向文档NoSQL数据库中概念模型的提取过程

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919400

A. A. Brahim, Rabah Tighilt Ferhat, G. Zurfluh

引用次数: 1

Learning to Transform Vietnamese Natural Language Queries into SQL Commands 学习将越南语自然语言查询转换为SQL命令

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919393

Thi-Hai-Yen Vuong, Thi-Thu-Trang Nguyen, Nhu-Thuat Tran, Le-Minh Nguyen, X. Phan

{"title":"Learning to Transform Vietnamese Natural Language Queries into SQL Commands","authors":"Thi-Hai-Yen Vuong, Thi-Thu-Trang Nguyen, Nhu-Thuat Tran, Le-Minh Nguyen, X. Phan","doi":"10.1109/KSE.2019.8919393","DOIUrl":"https://doi.org/10.1109/KSE.2019.8919393","url":null,"abstract":"In the field of data management, users traditionally manipulates their data using structured query language (SQL). However, this method requires an understanding of relational database, data schema, and SQL syntax as well as the way it works. Database manipulation using natural language, therefore, is much more convenient since any normal user can interact with their data without a background of database and SQL. This is, however, really tough because transforming natural language commands into SQL queries is a challenging task in natural language processing and understanding. In this paper, we propose a novel two–phase approach to automatically analyzing and converting natural language queries into the corresponding SQL forms. In our approach, the first phase is component segmentation which identifies primary clauses in SQL such as SELECT, FROM, WHERE, ORDER BY, etc. The second phase is slot– filling that helps extract sub–components for each primary clause such as SELECT column(s), SELECT aggregation operation, etc. We carefully conducted an empirical evaluation for our method using conditional random fields (CRFs) on a medium–sized corpus of natural language queries in Vietnamese, and have achieved promising results with an average accuracy of more than 90%.","PeriodicalId":439841,"journal":{"name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132896662","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}

引用次数: 1

A Combinatorial Technique for Mobile Applications Software Testing 移动应用软件测试的组合技术

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919456

H. Thang, Duc-Man Nguyen, Nhu-Hang Ha, Trung-Kien Pham, Phuong-Thao Nguyen, Van-Dao Tran

引用次数: 1

Abstract Argumentation for Summarizing Product Reviews: A Case Study in Shopee Thailand 摘要:产品评论总结的论证:以泰国Shopee为例

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919483

Teeradaj Racharak

引用次数: 0

A Novel Recovery Data Technique on MLC NAND Flash Memory 一种新的MLC NAND闪存数据恢复技术

2019 11th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2019-10-01 DOI: 10.1109/KSE.2019.8919382

Tran Van Dai, Jingi Park, Dong-Joo Park

{"title":"A Novel Recovery Data Technique on MLC NAND Flash Memory","authors":"Tran Van Dai, Jingi Park, Dong-Joo Park","doi":"10.1109/KSE.2019.8919382","DOIUrl":"https://doi.org/10.1109/KSE.2019.8919382","url":null,"abstract":"Flash memory today is more popular because of its advantages, such as low power consumption, high mobility and fast data access. In NAND flash memory, a solution called Flash Translation Layer (FTL) was proposed to solve its disadvantages like erase-before-write and unsymmetrical read or write response time. During the process of using the data, the data might be lost on the power failure in the systems. In some systems, the data is very important. Hence, recovery of data in the event of the system crash or a sudden power outage is of prime importance. One of the methods to fix is the error code correction (ECC), supplied with the flash device by the manufacturer. In the process of power off failure recovery, there have been previous schemes such as In-Page Backup, In-Block Backup, Hybrid Backup, A-PLR (Accumulation based Power Loss Recovery), HYFLUR (Hybrid FLUsh Recovery), and C-HYFLUR (Compression scheme for HYFLUR). In this paper, we introduce a technique based on the page leveling mapping using the spare area in FTL divided into ECC, map information, and reserved. To estimate the performance of this technique, we compare the recovery time and mapping information management cost of our approach with those of previous schemes such as In-Block Backup and In-Page Backup.","PeriodicalId":439841,"journal":{"name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123843274","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}

引用次数: 3