學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 10 of 65

Model-Based Synthetic Sampling for Imbalanced Data
(2020-08-01)
Liu, Chien-Liang
;
Hsieh, Po-Yen
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Imbalanced data is characterized by the severe difference in observation frequency between classes and has received a lot of attention in data mining research. The prediction performances usually deteriorate as classifiers learn from imbalanced data, as most classifiers assume the class distribution is balanced or the costs for different types of classification errors are equal. Although several methods have been devised to deal with imbalance problems, it is still difficult to generalize those methods to achieve stable improvement in most cases. In this study, we propose a novel framework called model-based synthetic sampling (MBS) to cope with imbalance problems, in which we integrate modeling and sampling techniques to generate synthetic data. The key idea behind the proposed method is to use regression models to capture the relationship between features and to consider data diversity in the process of data generation. We conduct experiments on 13 datasets and compare the proposed method with 10 methods. The experimental results indicate that the proposed method is not only comparative but also stable. We also provide detailed investigations and visualizations of the proposed method to empirically demonstrate why it could generate good data samples.
Mining the preferences of patients for ubiquitous clinic recommendation
(2020-06-01)
Chen, Tin-Chih Toly
;
Chiu, Min-Chi
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
A challenge facing all ubiquitous clinic recommendation systems is that patients often have difficulty articulating their requirements. To overcome this problem, a ubiquitous clinic recommendation mechanism was designed in this study by mining the clinic preferences of patients. Their preferences were defined using the weights in the ubiquitous clinic recommendation mechanism. An integer nonlinear programming problem was solved to tune the values of the weights on a rolling basis. In addition, since it may take a long time to adjust the values of weights to their asymptotic values, the back propagation network (BPN)-response surface method (RSM) method is applied to estimate the asymptotic values of weights. The proposed methodology was tested in a regional study. Experimental results indicated that the ubiquitous clinic recommendation system outperformed several existing methods in improving the successful recommendation rate.
A Method of Driving Characteristics Recognition on Vehicle Operation Sequence
(2019-01-01)
Zhang, Yu
;
Shen, Bo
;
Kao, Yi-Chih
;
Chou, Hsin-Hung
;
資訊技術服務中心
Driving behavior has been proved to have a great influence on road safety. Recognizing driving characteristic is an essential part of reducing traffic fatalities and developing intelligent traffic system. In this paper, we propose a method of driving characteristics recognition through mining vehicle operation data such as GPS, velocity and direction collected by the On-Board Diagnostic (OBD) port of vehicles. Based on the feature extracted from the vehicle operation sequence, we employ K-means algorithm to cluster and recognize different driving characteristics after reasonable normalization and dimensionality reduction of the features. Analysis and experimental results indicate that the proposed method has good application significance on mining effective information in vehicle operation data sequence.
Efficient methods for mining weighted clickstream patterns
(2020-03-15)
Huynh, Huy M.
;
Nguyen, Loan T. T.
;
Vo, Bay
;
Anh Nguyen
;
Tseng, Vincent S.
Pattern mining has been an attractive topic for many researchers since its first introduction. Clickstream mining, a specific version of sequential pattern mining, has been shown to be important in the age of the Internet. However, most previous works have simply exploited and applied existing sequential pattern algorithms to the mining of clickstream patterns, and few have studied clickstreams with weights, which also have a wide range of application. In this paper, we address this problem by proposing an approach based on the average weight measure for clickstream pattern mining and adapting a previous state-of-the-art algorithm to deal with the problem of weighted clickstream pattern mining. Following this, we propose an improved method named Compact-SPADE to enhance both the efficiency and memory consumption. Through various tests on both real-life and synthetic databases, we show that our proposed algorithms outperform state-of-the-art alternatives in terms of efficiency, memory requirements and scalability. (C) 2019 Elsevier Ltd. All rights reserved.
Merging anomalous data usage in wireless mobile telecommunications: Business analytics with a strategy-focused data-driven approach for sustainability
(2020-03-16)
Chen, Yi-Ting
;
Sun, Edward W.
;
Lin, Yi-Bing
;
資訊工程學系
;
Department of Computer Science
Mobile internet usage has exploded with the mass popularity of smartphones that offer more convenient and efficient ways of doing anything from watching movies, playing games, and streaming music. Understanding the patterns of data usage is thus essential for strategy-focused data-driven business analytics. However, data usage has several unique stylized facts (such as high dimensionality, heteroscedasticity, and sparsity) due to a great variety of user behaviour. To manage these facts, we propose a novel density-based subspace clustering approach (i.e., a three-stage iterative optimization procedure) for intelligent segmentation of consumer data usage/demand. We discuss the characteristics of the proposed method and illustrate its performance in both simulation with synthetic data and business analytics with real data. In a field experiment of wireless mobile telecommunications for data-driven strategic design and managerial implementation, we show that our method is adequate for business analytics and plausible for sustainability in search of business value. (C) 2019 Published by Elsevier B.V.
Mining high-utility itemsets in dynamic profit databases
(2019-07-01)
Nguyen, Loan T. T.
;
Phuc Nguyen
;
Nguyen, Trinh D. D.
;
Vo, Bay
;
Fournier-Viger, Philippe
High-Utility Itemset (HUI) mining is an important data-mining task which has gained popularity in recent years due to its applications in numerous fields. HUI mining aims at discovering itemsets that have high utility (e.g., yield a high profit) in transactional databases. Although several algorithms have been designed to enumerate all Mils, an important issue is that they assume that the utilities (e.g., unit profits) of items are static. But this simplifying assumption does not hold in real-life situations. For example, the unit profits of items often vary over time in a retail store due to fluctuating supply costs and promotions. Ignoring this important characteristic of real-life transactional databases makes current HUI-mining algorithms inapplicable in many real-world applications. To address this critical limitation of current HUI-mining techniques, this paper studies the novel problem of mining HUls in databases having dynamic unit profits. To accurately assess the utility of any itemset in this context, a redefined utility measure is introduced. Furthermore, a novel algorithm named MEFIM (Modified EFficient high-utility Itemset Mining), which relies on a novel compact database format to discover the desired itemsets efficiently, is designed. An improved version of the MEFIM algorithm, named iMEFIM, is also introduced. This algorithm employs a novel structure called P-set to reduce the number of transaction scans and to speed up the mining process. Experimental results show that the proposed algorithms considerably outperform the state-of-the-art HUI-mining algorithms on dynamic profit databases in terms of runtime, memory usage, and scalability. (C) 2019 Elsevier B.V. All rights reserved.
An Augmented Reality Question Answering System Based on Ensemble Neural Networks
(2017-01-01)
Chen, Chi-Hua
;
Wu, Chen-Ling
;
Lo, Chi-Chun
;
Hwang, Feng-Jang
;
資訊管理與財務金融系註：原資管所+財金所
This paper proposes a classification algorithm based on ensemble neural networks. In the training phase, the proposed algorithm uses a random number of training data to develop multiple random artificial neural network (ANN) models until those ANN models converge. Those models with lower accuracy than the threshold are filtered out. The remaining highly accurate models will be used to predict the output in the testing phase. Meanwhile, the accuracy of ANN models is presented as a weighting value in the testing phase. In the testing phase, the testing data are loaded into the selected ANN models to predict the output class. The output values are multiplied by the corresponding weighting values of ANN models. Then the weighted average of the outputs can be obtained. Finally, the predicted output is converted into the predicted class. We design an augmented reality question answering system (AR-QAS) applying and implementing the proposed algorithm on mobile devices. AR-QAS offers an interactive user interface and automatically replies according to user's queries. By comparing with the logistic regression method and the ANN method, the experiment results demonstrate that the proposed algorithm offers the highest accuracy.
Mining Trending High Utility Itemsets from Temporal Transaction Databases
(2018-01-01)
Hackman, Acquah
;
Huang, Yu
;
Tseng, Vincent S.
;
交大名義發表
;
資訊工程學系
In this paper, we address a novel and important topic in the area of HUI mining, named Trending High Utility Itemset (TrendHUI) mining, with the promise of expanding the applications of HUI mining with the power of trend analytics. We introduce formal definitions for TrendHUI mining and highlighted the importance of the TrendHUI output. Moreover, we develop two algorithms, Two-Phase Trending High Utility Itemset (TP-THUI) miner and Two-Phase Trending High Utility Itemset Guided (TP-THUI-Guided) miner. Both are two-phase algorithms that mine a complete set of TrendHUI. TP-THUI-Guided miner utilizes a remainder utility to calculate the temporal trend of a given itemset to reduce the search space effectively, such that the execution efficiency can be enhanced substantially. Through a series of experiments, using three different datasets, the proposed algorithms prove to be excellent for validity and efficiency. To the best of our knowledge, this is the first work addressing the promising topic on Trending High Utility Itemset mining, which is expected to facilitate numerous applications in data mining fields.
Distinguishing friends from strangers in location-based social networks using co-location
(2018-10-01)
Njoo, Gunarto Sindoro
;
Hsu, Kuo-Wei
;
Peng, Wen-Chih
;
交大名義發表
;
National Chiao Tung University
This paper particularly focuses on using the spatiotemporal data in the location-based social networks (LBSNs) to infer the social tie between two users. To do so, we first generate a co-location dataset by simulating the meeting event between users based on the time difference and spatial distance. Subsequently, we extract four key features from the generated dataset: diversity, popularity, duration, and stability. We propose a framework called SCI (Social Connection Inference) that integrates all derived features to distinguish real friends' meetings from strangers' coincidental meetings. Experiment results based on the three LBSN datasets prove the effectiveness of the proposed SCI framework by outperforming the state-of-the-art methods. In addition, various discussions on different aspects of the data are presented in this paper to yield insights into using generated co-location datasets. (C) 2018 Elsevier B.V. All rights reserved.
Distributed and scalable sequential pattern mining through stream processing
(2017-11-01)
Chen, Chun-Chieh
;
Shuai, Hong-Han
;
Chen, Ming-Syan
;
電機工程學系
;
Department of Electrical and Computer Engineering
Scalability is a primary issue in existing sequential pattern mining algorithms for dealing with a large amount of data. Previous work, namely sequential pattern mining on the cloud (SPAMC), has already addressed the scalability problem. It supports the MapReduce cloud computing architecture for mining frequent sequential patterns on large datasets. However, this existing algorithm does not address the iterative mining problem, which is the problem that reloading data incur additional costs. Furthermore, it did not study the load balancing problem. To remedy these problems, we devised a powerful sequential pattern mining algorithm, the sequential pattern mining in the cloud-uniform distributed lexical sequence tree algorithm (SPAMC-UDLT), exploiting MapReduce and streaming processes. SPAMC-UDLT dramatically improves overall performance without launching multiple MapReduce rounds and provides perfect load balancing across machines in the cloud. The results show that SPAMC-UDLT can significantly reduce execution time, achieves extremely high scalability, and provides much better load balancing than existing algorithms in the cloud.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results