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 - 7 of 7

建築工程連續壁單元分割知識歸納學習系統之研究
(2000)
曾仁杰
;
DZENG REN-JYE
;
交通大學土木工程系
專家系統知識自動整合環境之研製
(1998)
曾憲雄
;
TSENG SHIAN-SHYONG
;
交通大學資訊科學系
發展一個成功的專家系統必須要有一個完整、一致且清晰的知識庫，所以，利用不同的知識擷取工具以獲取不同專家們的專業知識並加以整合，就成為建構專家系統的重要課題。然而，在知識的整合過程中，經常會產生知識庫內的規則不完整、不一致或重覆等問題。如何有效地整合不同的專家知識並降低彼此間的矛盾，就成為一個重要的研究方向。傳統的知識整合系統因為需要專家的介入而容易顯現出某些缺點，如：(1) 當知識之間有矛盾出現時，專家們必須介入解決，容易造成(但不一定會)不夠客觀的現象；(2) 整合過程所需時間很長；(3) 當專家愈多時，知識整合越困難、越複雜；這些缺點使得大型專家系統的發展變得非常費時。為了克服這些缺點，在本計畫中，我們提出一個知識自動整合方法。它運用了基因遺傳演算法的自我調整找尋技術，將不同專家所提供的知識或不同機器學習技術所推演得到的規則加以整合，並自動產生一個完整、一致且清晰的知識庫。我們的方法有以下之優點：(1) 只需要少許的整合時間；(2) 當專家所提供的知識愈豐富或機器學習技術所推演得到的規則愈多，知識整合愈有效率，知識庫愈準確；(3) 當知識之間有矛盾出現時，可不需要專家介入；(4) 整合過程中，可不需要專家介入，所以，它是客觀的；(5) 可以擴充至分散式知識整合環境。然而，本系統有一些限制，如:(1) 每一個欲整合之專家知識必須以規則集合形式表示；(2) 當欲整合之專家知識變少，系統必須產生一些仿冒知識(dummy knowledge)，而容易造成知識整合沒有效率；除了上述之優點及限制外，本系統具有很大的擴充性，一些常用的知識擷取工具及機器學習系統很容易整合於本系統中，來幫助系統獲取更多的領域知識。整個知識整合系統將與專家系統建構工具 CLIPS整合，為知識工程師提供完整的發展環境。有了環境的幫助，專家系統的發展將變得比較容易而有效率。本計畫中，我們預計完成一套專家系統的知識自動整合環境，包括 - 知識擷取模組、機器學習模組、知識整合模組以及知識修正模組。知識擷取模組收集了一些知識擷取工具，來幫助專家輸入領域知識。機器學習模組中儲存了一些著名的學習系統，可將過去發生過的案例歸納成一些規則。知識整合模組則負責整合由知識擷取模組所產生的領域知識及由機器學習模組所歸納產生的規則，並產生專家系統的知識庫。知識修正模組則運用於知識庫推理中，若有不適用之規則存在，則將自動找出並加以修正，隨時維持知識庫的一致性及準確性。在應用方面，我們將以醫學上腦瘤診斷及農業上�抻岳|種的實際應用領域進行實作。在應用領域中將邀請專門醫師及學者們作為專家，並依實際病歷及歷年紀錄的資料進行測試，以驗証計畫之成果。
Prediction of small non-coding RNA in bacterial genomes using support vector machines
(2010-08-01)
Chang, Tzu-Hao
;
Wu, Li-Ching
;
Lin, Jun-Hong
;
Huang, Hsien-Da
;
Liu, Baw-Jhiune
Small non-coding RNA genes have been shown to play important regulatory roles in a variety of cellular processes, but prediction of non-coding RNA genes is a great challenge, using either an experimental or a computational approach, due to the characteristics of sRNAs, which are that sRNAs are small in size, are not translated into proteins and show variable stability. Most known sRNAs have been identified in Escherichia coli and have been shown to be conserved in closely related organisms. We have developed an integrative approach that searches highly conserved intergenic regions among related bacterial genomes for combinations of characteristics that have been extracted from known E. coli sRNA genes. Support vector machines (SVM) were then used with these characteristics to predict novel sRNA genes. (c) 2010 Elsevier Ltd. All rights reserved.
A fall detection system using k-nearest neighbor classifier
(2010-10-01)
Liu, Chien-Liang
;
Lee, Chia-Hoang
;
Lin, Ping-Min
;
資訊工程學系
;
Department of Computer Science
The main purpose of this paper is to use off-the-shelf devices to develop a fall detection system. In human body identification, human body silhouette is adopted to improve privacy protection, and vertical projection histograms of the silhouette image and statistical scheme are used to reduce the effect of human body upper limb activities. The kNN classification algorithm is used to classify the postures using the ratio and difference of human body silhouette bounding box height and width. Meanwhile, since time difference is a vital factor to differentiate fall incident event and lying down event, the critical time difference is obtained from the experiment and verified by statistical hypothesis testing. With the help of the kNN classifier and the critical time difference, a fall incident detection system is developed to detect fall incident events. The experiment shows that it could reduce the effect of upper limb activities and the system has a correct rate of 84.44% on fall detection and lying down event detection. (C) 2010 Elsevier Ltd. All rights reserved.
Network security management with traffic pattern clustering
(2014-09-01)
Chiou, Tao-Wei
;
Tsai, Shi-Chun
;
Lin, Yi-Bing
;
資訊工程學系
;
Department of Computer Science
Profiling network traffic pattern is an important approach for tackling network security problem. Based on campus network infrastructure, we propose a new method to identify randomly generated domain names and pinpoint the potential victim groups. We characterize normal domain names with the so called popular 2gram (2 consecutive characters in a word) to distinguish between active and nonexistent domain names. We also track the destination IPs of sources IPs and analyze their similarity of connection pattern to uncover potential anomalous group network behaviors. We apply the Hadoop technique to deal with the big data of network traffic and classify the clients as victims or not with the spectral clustering method.
Determining the optimal re-sampling strategy for a classification model with imbalanced data using design of experiments and response surface methodologies
(2011-04-01)
Tong, Lee-Ing
;
Chang, Yung-Chia
;
Lin, Shan-Hui
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Imbalanced data are common in many machine learning applications. In an imbalanced data set, the number of instances in at least one class is significantly higher or lower than that in other classes. Consequently, when classification models with imbalanced data are developed, most classifiers are subjected to an unequal number of instances in each class, thus failing to construct an effective model. Balancing sample sizes for various classes using a re-sampling strategy is a conventional means of enhancing the effectiveness of a classification model for imbalanced data. Despite numerous attempts to determine the appropriate re-sampling proportion in each class by using a trial-and-error method in order to construct a classification model with imbalanced data (Barandela, Vadovinos, Sanchez, & Ferri, 2004; He, Han, & Wang, 2005; Japkowicz, 2000; McCarthy, Zabar, & Weiss, 2005), the optimal strategy for each class may be infeasible when using such a method. Therefore, this work proposes a novel analytical procedure to determine the optimal re-sampling strategy based on design of experiments (DOE) and response surface methodologies (RSM). The proposed procedure, S-RSM, can be utilized by any classifier. Also, C4.5 algorithm is adopted for illustration. The classification results are evaluated by using the area under the receiver operating characteristic curve (AUC) as a performance measure. Among the several desirable features of the AUC index include independence of the decision threshold and invariance to a priori class probabilities. Furthermore, five real world data sets demonstrate that the higher AUC score of the classification model based on the training data obtained from the S-RSM is than that obtained using oversampling approach or undersampling approach. (C) 2010 Elsevier Ltd. All rights reserved.
An expert system to predict protein thermostability using decision tree
(2009-07-01)
Wu, Li-Cheng
;
Lee, Jian-Xin
;
Huang, Hsien-Da
;
Liu, Baw-Juine
;
Horng, Jorng-Tzong
Protein thermostability information is closely linked to commercial production of many biomaterials. Recent developments have shown that amino acid composition, special sequence patterns and hydrogen bonds, disulfide bonds, salt bridges and so on are of considerable importance to thermostability. In this study, we present a system to integrate these various factors that predict protein thermostability. In this study, the features of proteins in the PGTdb are analyzed. We consider both structure and sequence features and correlation coefficients are incorporated into the feature selection algorithm. Machine learning algorithms are then used to develop identification systems and performances between the different algorithms are compared. In this research, two features, (E + F + M + R)/residue and charged/non-charged, are found to be critical to the thermostability of proteins. Although the sequence and structural models achieve a higher accuracy, sequence-only models provides sufficient accuracy for sequence-only thermostability prediction. (C) 2008 Elsevier Ltd. All rights reserved.

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