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 59

Epileptic Seizure Prediction With Multi-View Convolutional Neural Networks
(2019-01-01)
Liu, Chien-Liang
;
Xiao, Bin
;
Hsaio, Wen-Hoar
;
Tseng, Vincent S.
;
交大名義發表
The unpredictability of seizures is often considered by patients to be the most problematic aspect of epilepsy, so this work aims to develop an accurate epilepsy seizure predictor, making it possible to enable devices to warn patients of impeding seizures. To develop a model for seizure prediction, most studies relied on Electroencephalograms (EEGs) to capture physiological measurements of epilepsy. This work uses the two domains of EEGs, including frequency domain and time domain, to provide two different views for the same data source. Subsequently, this work proposes a multi-view convolutional neural network framework to predict the occurrence of epilepsy seizures with the goal of acquiring a shared representation of time-domain and frequency-domain features. By conducting experiments on Kaggle data set, we demonstrated that the proposed method outperforms all methods listed in the Kaggle leader board. Additionally, our proposed model achieves average area under the curve (AUCs) of 0.82 and 0.89 on two subjects of CHB-MIT scalp EEG data set. This work serves as an effective paradigm for applying deep learning approaches to the crucial topic of risk prediction in health domains.
Large-scale Classification of 12-lead ECG with Deep Learning
(2019-01-01)
Chen, Yu-Jhen
;
Liu, Chien-Liang
;
Tseng, Vincent S.
;
Hu, Yu-Feng
;
Chen, Shih-Ann
The 12-lead Electrocardiography(ECG) is the gold standard in diagnosing cardiovascular diseases, but most previous studies focused on 1-lead or 2-lead ECG. This work uses a large data set, comprising 7,704 12-lead ECG samples, as the data source, and the goal is to develop a classification model for six common types of urgent arrhythmias. We consider the characteristics of multivariate time-series data to design a novel deep learning model, combining convolutional neural network (CNN) and long short-term memory (LSTM) to learn feature representations as well as the temporal relationship between the latent features. The experimental results indicate that the proposed model achieves promising results and outperforms the other alternatives. We also provide brief analysis about the proposed model.
Epileptic Seizure Prediction With Multi-View Convolutional Neural Networks
(2019-01-01)
Liu, Chien-Liang
;
Xiao, Bin
;
Hsaio, Wen-Hoar
;
Tseng, Vincent S.
;
交大名義發表
The unpredictability of seizures is often considered by patients to be the most problematic aspect of epilepsy, so this work aims to develop an accurate epilepsy seizure predictor, making it possible to enable devices to warn patients of impeding seizures. To develop a model for seizure prediction, most studies relied on Electroencephalograms (EEGs) to capture physiological measurements of epilepsy. This work uses the two domains of EEGs, including frequency domain and time domain, to provide two different views for the same data source. Subsequently, this work proposes a multi-view convolutional neural network framework to predict the occurrence of epilepsy seizures with the goal of acquiring a shared representation of time-domain and frequency-domain features. By conducting experiments on Kaggle data set, we demonstrated that the proposed method outperforms all methods listed in the Kaggle leader board. Additionally, our proposed model achieves average area under the curve (AUCs) of 0.82 and 0.89 on two subjects of CHB-MIT scalp EEG data set. This work serves as an effective paradigm for applying deep learning approaches to the crucial topic of risk prediction in health domains.
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.
Robust Sensor-based Human Activity Recognition with Snippet Consensus Neural Networks
(2019-01-01)
Huang, Yu
;
Lee, Meng-Chieh
;
Tseng, Vincent S.
;
Hsiao, Ching-Jui
;
Huang, Chi-Chiang
Sensor-based human activity recognition is an important problem in pervasive computing, which has attracted lots of attention from the research community in the past few years. The existing relevant studies focused on using handcrafted features or machine learning-based methods to tackle this problem. However, these methods are usually limited to specific datasets, such that the generality is limited. Some methods are also limited to strict experimental environments, which do not take stability into consideration. In this paper, we propose a robust and novel deep learning-based framework, named Snippet Consensus Neural Networks (SCNet), which aims to conquer these challenges. Through a series of experiments, the proposed framework is verified to outperform seven state-of-the-art methods on five datasets in terms of not only accuracy but also generality and stability, averagely improving 10% on mean accuracy.
FrauDetector: A Graph-Mining-based Framework for Fraudulent Phone Call Detection
(2015-01-01)
Tseng, Vincent S.
;
Ying, Josh Jia-Ching
;
Huang, Che-Wei
;
Kao, Yimin
;
Chen, Kuan-Ta
In recent years, fraud is increasing rapidly with the development of modern technology and global communication. Although many literatures have addressed the fraud detection problem, these existing works focus only on formulating the fraud detection problem as a binary classification problem. Due to limitation of information provided by telecommunication records, such classifier-based approaches for fraudulent phone call detection normally do not work well. In this paper, we develop a graph-mining-based fraudulent phone call detection framework for a mobile application to automatically annotate fraudulent phone numbers with a "fraud" tag, which is a crucial prerequisite for distinguishing fraudulent phone calls from normal phone calls. Our detection approach performs a weighted HITS algorithm to learn the trust value of a remote phone number. Based on telecommunication records, we build two kinds of directed bipartite graph: i) CPU and ii) UPG to represent telecommunication behavior of users. To weight the edges of CPU and UPG, we extract features for each pair of user and remote phone number in two different yet complementary aspects: I) duration relatedness (DR) between user and phone number; and 2) frequency relatedness (FR) between user and phone number. Upon weighted CPG and UPG, we determine a trust value for each remote phone number. Finally, we conduct a comprehensive experimental study based on a dataset collected through an anti-fraud mobile application, Whoscall. The results demonstrate the effectiveness of our weighted HITS-based approach and show the strength of taking both DR and FR into account in feature extraction.
Effective Risk Assessment of Type 2 Diabetes Using Diagnostic Information Retrieval
(2018-01-01)
Chin, Chu-Yu
;
Hsieh, Sun-Yuan
;
Tseng, Vincent S.
;
交大名義發表
;
資訊工程學系
Data in electronic medical records (EMRs) have been widely employed owing to rapid advances in disease assessment technologies. Accordingly, the challenging issue of how to effectively retrieve meaningful data from large-scale medical databases for disease assessment has risen. Furthermore, the manner in which early disease risk assessment models can detect disease symptoms is an issue of concern because early detection leads to early treatment. In this paper, with the aim of detecting diseases sooner and more effectively, a novel early disease risk assessment method is proposed, and type 2 diabetes mellitus (T2DM) is used as a case study. The proposed method is to improve the quality and meaning of diagnostic data using novel features and early strategy. To apply EMRs to construct a relationship matrix between patients and diseases, a retrieval method for generalized diagnostic coded information with extracted occurrence numbers was proposed. In order to identify diseases earlier, a disease risk assessment strategy from 7, 60, and 120 days before the onset of T2DM was established. The experimental results showed that the proposed method to improve disease risk assessment achieved high accuracy in terms of AUC-ROC and AUC-PR values. These results also demonstrate that the EMR information retrieval methods play an important role for disease assessment, and assessments can be performed at an earlier stage based on large-scale diagnostic databases.
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.
Discovering negative comments by sentiment analysis on web forum
(2019-05-01)
Hsu, Wei-Yun
;
Hsu, Hui-Huang
;
Tseng, Vincent S.
;
資訊工程學系
;
Department of Computer Science
Social media enables people to communicate with each other on the Internet in real-time and rich styles. In other words, there is a lot of information on the social media. If we can extract negative opinions of some brands, enterprises or politics, we can use these opinions to know the market demands and solve problems. In this paper, we propose a novel approach to extract negative-sentiment-oriented features and identify negative opinions in social media with text mining and machine learning techniques, support vector machine and neural network, as well as data collection with Web crawler. The experimental results show that our proposed methods can work effectively.
Long-Term User Location Prediction Using Deep Learning and Periodic Pattern Mining
(2017-01-01)
Wong, Mun Hou
;
Tseng, Vincent S.
;
Tseng, Jerry C. C.
;
Liu, Sun-Wei
;
Tsai, Cheng-Hung
In recent years, with the advances in mobile communication and growing popularity of the fourth-generation mobile network along with the enhancement in location positioning techniques, mobile devices have generated extensive spatial trajectory data, which represent the mobility of moving objects. New services are emerged to serve mobile users based on their predicted locations. Most of the existing studies on location prediction were focused on predicting the next location of a user, which is regarded as short-term next location prediction. While more advanced location-based services could be enabled for the users if long-term location prediction could be achieved, the existing methods constrained in next-location prediction are not applicable for long-term prediction scenario. In this paper, we propose a novel prediction framework named LSTM-PPM that utilises deep learning and periodic pattern mining for long-term prediction of user locations. Our framework devises the ideology from natural language model and uses multi-step recursive strategy to perform long-term prediction. Furthermore, the periodic pattern mining technique is utilized to reduce the accumulated loss in the multi-step strategy. Through empirical evaluation on a real-life trajectory dataset, our proposed approach is shown to provide effective performance in long-term location prediction. To the best of our knowledge, this is the first work addressing the research topic on long-term user location prediction.

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