A Comparison of Pattern Classification Approaches for Structural Damage Identification

Zhou Qingqing; Zhou Qifeng; Ning Yongpeng; Yang Fan; Lei Jiayan; Tian Run; Liu Minda
April 2012
Journal of Digital Information Management;Apr2012, Vol. 10 Issue 2, p126
Academic Journal
A structural damage identification approach based on wavelet packet decomposition (WPD) and random forests (RF) was proposed and compared with other pattern classification approachs. The main procedure involves extracting energy features from vibration acceleration data through wavelet packet decomposition and then using these features as input for a RF classifier. The experiment was carried on an 8-storey steel shear building model in the case verification. The results show that the proposed method is effective for structure damage detection and can achieve a higher accuracy than other commonly used methods.


Related Articles

  • Study on Synthesis Evaluation of Intensive Land Use and Growth Pattern Transformation of Towns. Hai-Chao Luo; Xiao-Min Li; Shu-Jing Zheng; Mei Li; Li-Li Song // Journal of Computers;Aug2012, Vol. 7 Issue 8, p1959 

    It is very important that the scientific and reasonable evaluation on the intensive utilization of urban land and transformation of growth modes. It can enhance the levels of consolidation and management for urban land, maximize the intensive use efficiency of the land, and ensure sustainable...

  • Comparison of flow patterns of dual rushton and CD-6 impellers. Devi, T.; Kumar, B. // Theoretical Foundations of Chemical Engineering;Jul2013, Vol. 47 Issue 4, p344 

    The flow patterns (parallel, merging and diverging) of dual CD-6 impeller has been modeled using computational fluid dynamics simulation in FLUENT software compared with dual Rushton impeller. Simulated results have been verified with experimental observations on Rushton impeller. Comparison of...

  • Paper Similarity Detection Method Based on Distance Matrix Model with Row-Column Order Penalty Factor. Li Jun; Han Yaqing; Pan Junshan // Journal of Multimedia;Aug2014, Vol. 9 Issue 8, p998 

    Paper similarity detection depends on grammatical and semantic analysis, word segmentation, similarity detection, document summarization and other technologies, involving multiple disciplines. However, there are some problems in the existing main detection models, such as incomplete segmentation...

  • Finding Language-Independent Contextual Supernodes on Coreference Networks. Devezas, José; Figueira, Álvaro // IAENG International Journal of Computer Science;2012, Vol. 39 Issue 2, p200 

    We propose a method for creating news context by taking advantage of a folksonomy of web clipping based on online news. We experiment with an ontology-based named entity recognition process, describing two alternate implementation approaches, and we study two different ways of modeling the...

  • Distributed Recognition of Reference Nodes for Wireless Sensor Network Localization. Simek, Milan; Moravek, Patrik; Komosny, Dan; Dusik, Matej // Radioengineering;Apr2012, Vol. 21 Issue 1, p89 

    All known localization techniques for wireless sensor and ad-hoc networks require certain set of reference nodes being used for position estimation. The anchor-free techniques in contrast to anchor-based do not require reference nodes called anchors to be placed in the network area before...

  • CroNER: Recognizing Named Entities in Croatian Using Conditional Random Fields. Karan, Mladen; Glavaš, Goran; Šarić, Frane; Šnajder, Jan; Mijić, Jure; Šilić, Artur; Bašić, Bojana Dalbelo // Informatica (03505596);Jun2013, Vol. 37 Issue 2, p165 

    In this paper we present CroNER, a named entity recognition and classification system for Croatian language based on supervised sequence labeling with conditional random fields (CRF). We use a rich set of lexical and gazetteer-based features and different methods for enforcing document-level...

  • Comparative Analysis of Text Categorizer on Science and Technology Intelligence. Peipei Sun; Quanyin Zhu; Lei Zhou; Yongjun Zhang // Applied Mechanics & Materials;2014, Issue 530-531, p502 

    In order to more effectively classify the science and technology intelligence text, the idea that classifying science and technology intelligence text categorization based on different classifiers is proposed. The experiment is done with two thousand Chinese texts based on three different...

  • Pain Expression Recognition Based on Fuzzy Classification Approach. Shaoping Zhu // Journal of Computers;Aug2014, Vol. 9 Issue 8, p1975 

    Human activity analysis and expressions recognition play a central role in pervasive health care. Expressions recognition is an active research field in computer vision. In this paper, We propose an approach for automatically recognizing the pain expression from video sequences, in which pain is...

  • Vehicle Type Recognition in Sensor Networks Using Improved Time Encoded Signal Processing Algorithm. Yan Wang; Xi Wu; Xiaohua Li; Jiliu Zhou // Mathematical Problems in Engineering;2014, p1 

    Vehicle type recognition is a demanding application of wireless sensor networks (WSN). In many cases, sensor nodes detect and recognize vehicles from their acoustic or seismic signals using wavelet based or spectral feature extraction methods. Such methods, while providing convincing results,...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics