請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48408
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 張瑞益(Ray-I Chang) | |
dc.contributor.author | Chien-Chang Huang | en |
dc.contributor.author | 黃建彰 | zh_TW |
dc.date.accessioned | 2021-06-15T06:55:39Z | - |
dc.date.available | 2014-08-22 | |
dc.date.copyright | 2011-08-22 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-08-19 | |
dc.identifier.citation | [1] R.V. Kulkarni, A. Forster, and G.K. Venayagamoorthy, “Computational intelligence in wireless sensor networks: A survey,” IEEE Communications Surveys & Tutorials, vol. 13, issue 1, 2011.
[2] G. Werner-Allen, K. Lorincz, J. Johnson, J. Lees, and M. Welsh, “Fidelity and Yield in a Volcano Monitoring Sensor Network,” ACM Symposium on Operating systems design and implementation, pp. 381-396, 2006. [3] A. Shakoor, 'Soft computing based feature selection for environmental sound classification,” Blekinge Institute of Technology, Apr. 2010 [4] G. Padmavathi, D. Shanmugapriya and M. Kalaivani, “Acoustic Signal based Feature extraction for Vehicular Classification,” International Conference on Advanced Computer Theory and Engineering, vol. 2, pp. 11-14, 2010. [5] M.Vasantha and V. S. Bharathy, “Evaluation of Attribute Selection Methods with Tree based Supervised Classification-A Case Study with Mammogram Images,” International Journal of Computer Applications, vol. 8, no.12, Oct. 2010. [6] G. Bulbuller, “Recognition of In-Ear Microphone Speech Data Using Multi-Layer Neural Networks,” Naval Postgraduate School, 2006. [7] T.T. Swee, S.H.S. Salleh, and M.R. Jamaludin, “Speech Pitch Detection Using Short-Time Energy,” International Conference on Computer and Communication Engineering, pp. 327-332, 2010. [8] S. Gabarda and G. Cristo’bal, “Detection of events in seismic time series by time–frequency methods,” IET Signal Processing, vol. 4, pp. 413-420, 2010. [9] A. Ramalingam and S. Krishnan, “Gaussian Mixture Modeling Using Short Time Fourier Transform Features for Audio Fingerprinting,” IEEE International Conference on Multimedia and Expo, ( ICME '05), pp. 1146 – 1149, Jul. 2005. [10] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H.Witten, “The WEKA Data Mining Software: An Update,” in SIGKDDExplor. Newsl., vol. 11, no. 1. ACM, pp. 10–18, 2009. [11] M.A. Hall, “Correlation-based Feature Selection for Machine Learning,” Apr. 1999. [12] J-L. Lassez, R. Rossi, S. Sheel and S. Mukkamala, “Signature Based Intrusion Detection System using Latent Semantic Analysis,” IJCNN, pp. 1068-1074, 2008. [13] A. Malhi and G.X. Robert, “PCA-based feature selection scheme for machine defect classification,” IEEE Trans. Instrumentation and Measurement, vol. 53, pp.1517-1525, 2004. [14] R. Kohavi and G.H. John, “Wrappers for feature subset selection,” Artificial Intelligence, vol. 97, pp. 273-324, 1997. [15] X. Zhu, X. Wu, and Y. Yang, “Effective classification of noisy data streams with attribute-oriented dynamic classifier selection,” Knowledge and Information Systems, vol. 9,no. 3, pp. 339-363, Mar. 2006. [16] J.N. Hwang, J.J. Choi, S. Oh and R.J. Marks II, “Query-based learning applied to partially trained multilayer perceptrons,” IEEE Trans. on Neural Networks, vol. 2, pp.131-136, 1991. [17] V. Turchenko, V. Demchuk and A. Sachenko, “Interplanetary Shock Arrival Time Prediction Using Multi-Layer Perceptron,” Proceedings of the 4th IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Dortmund (Germany), pp. 185-190, Sep 6-8, 2007. [18] L. Liszka, “Infrasound—A Summary of 35 Years of Infrasound Research,” IRF Scientific Report, vol. 291, Jan. 2008. [19] L.-B. Lai, R.-I. Chang* and J.-S. Kouh, 'Mining Data by Query-Based Error-Propagation,' LECT NOTES COMPUT SC, Vol. 3610, pp. 1224 – 1233, 2005. [20] C. Lee and D.A. Landgrebe, “Feature Extraction Based on Decision Boundaries,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 4, pp. 388-400, Apr. 1993. [21] D. Marsh, “Fostering Innovation in a Small Open Economy: The Case of the New Zealand Biotechnology Sector,” Manchester, UK: Eighth International Joseph A. Schumpeter Society Conference, 28 Jun. 2000 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48408 | - |
dc.description.abstract | 無線感測網路已廣泛地應用在各種環境監測領域,包括火山爆發、地震偵測、洪水偵測、結構變形檢測和危險化學偵測。透過感測器,可以將即時收集的資訊傳回監測站,以隨時進行監控並進行資料分析與事件的預測。由於次聲波具有極強的穿透力且不容易衰減之特性,因此其傳輸的距離可以非常遠,是一種鑑別度極高且有利用價值的監測訊號。然而,在環境監測應用時,根據不同的環境所收集的資料特性也會有很大的不同,資料特性的差異程度增加了資料分析的複雜性,進而降低了分類和預測模式的正確率。為了克服這些問題,首先我們利用不同的特徵擷取的技術從次聲波訊號中擷取不同的特性,在此特徵擷取的技術又可分成時域和頻域的方法,根據所擷取的各種特徵再加上原本次聲波訊號的基本屬性,以整合為一個完整的特徵集合。下一階段,我們會提出一個特徵選取方法,以詢問式屬性評估(Query-Based Attribute Evaluator)來達到有效的特徵選取。目的是挑選出最佳的特徵子集合,一方面降低資料維度減少資料量,另一方面則提高了分類和辨識的正確率以及減少計算時間。最後我們會應用一個真實的火山噴發監測系統所偵測的次聲波訊號來做驗證,由實驗的結果顯示,我們提出的方法所挑選的特徵子集合比起傳統的方法,更能夠於分類時得到較佳的效能。也藉由QBAE特徵選取方法在挑選重要屬性的過程中,找到足以描述火山爆發所收集到的次聲波訊號之重要特性。由此可說明,我們的方法非常適合應用在環境監測的問題領域。 | zh_TW |
dc.description.abstract | Wireless sensor network has already been widely applied in different environmental monitoring include volcano eruption, earthquake detection, flooding detection, structures deformations detection, and chemical hazardous detection. The base station collects the information from the sensor nodes and transforms the collected information into the requested form to cater for different applications. Infrasound is used to monitor big events at large distances. It has noticeable features such as powerful capability of through objects with small attenuation in transmission and may propagate at a long distance. However, the signals' data collected will have various characteristics because of the different environmental conditions increasing the complexity of data analysis and dropping the accuracy rate of the classification or prediction module. To overcome the challenge, we utilized various feature extraction techniques in both time domain and frequency domain to extract the different properties and then integrate the attributes of the original signals into the complete set of features. In the second stage, we put forward a feature selection method, with Query-Based Attribute Evaluator (QBAE) to reach an effective feature selection, aiming at find out optimum feature sub-set, on the one hand, reduced data dimensions and data volume, on the other hand, enhanced the accuracy of classification and identification and reduced calculation time. Finally, we applied a practical case of detected signals from a volcanic eruption monitoring system for verification, as the experiment results shown, the selected features sub-set with the method we put forward, had better efficacy at classification than traditional methods. And through QBAE feature selection method, in the process of selecting important attributions, the important features of collected infrasonic wave signals of volcanic eruption were found and sufficient to describe the scenario. Thereby, the method we raised is suitable to be applied in the problem area of environment monitoring was verified. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T06:55:39Z (GMT). No. of bitstreams: 1 ntu-100-R98525099-1.pdf: 1587711 bytes, checksum: 0c15fb7542dd58e937683f42a042db94 (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 口試委員審定書 I
致謝 II 中文摘要 III Abstract IV LIST OF FIGURES VIII LIST OF TABLES X Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Background 1 1.3 Feature extraction, selection and classification 5 1.4 Architecture of this report 8 Chapter 2 Related Work 10 2.1 Feature extraction 10 2.2 Feature selection 23 2.3 Classification 25 Chapter 3 Proposed Method 28 3.1 Dataset of Infrasound 28 3.2 Feature extraction 29 3.2.1 Micro-view 30 3.2.2 Macro-view 30 3.2.3 Data format 31 3.3 Feature selection 33 3.3.1 QBL feature selection 33 3.3.2 Framework 36 3.3.3 Proposed QBL algorithm flow 37 3.4 Classification 38 3.4.1 Multilayer Perceptron 38 Chapter 4 Experiment Results and Discussion 41 4.1 The experimental results 41 4.1.1 Design of experiments 41 4.1.2 Feature extraction 42 4.1.3 Evaluation procedure of the QBL feature selection 46 4.1.4 Conventional feature selection method for WEKA 54 4.2 Performance comparison and feature analysis 55 4.2.1 Performance Comparison by MLP 55 4.2.2 Infrasonic signal analysis 58 Chapter 5 Summary and Conclusions 61 REFERENCE 62 | |
dc.language.iso | en | |
dc.title | 無線感測網路之次聲訊號分析 | zh_TW |
dc.title | The analysis of infrasonic signals from Wireless Sensor Networks | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 丁肇隆,黃乾綱,王家輝,林正偉 | |
dc.subject.keyword | 無線感測網路,次聲波訊號,特徵擷取,詢問式特徵選取,多層感知器類神經網路, | zh_TW |
dc.subject.keyword | Wireless sensor networks,Infrasonic signals,Feature extraction,Query-based Feature selection,Multilayer perceptron neural network, | en |
dc.relation.page | 64 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2011-08-19 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 工程科學及海洋工程學研究所 | zh_TW |
顯示於系所單位: | 工程科學及海洋工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-100-1.pdf 目前未授權公開取用 | 1.55 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。