Shih-Lin Hung

Followers

Following

Public Views

Uploads

Papers by Shih-Lin Hung

Constrained K-means and Genetic Algorithm-based Approaches for Optimal Placement of Wireless Structural Health Monitoring Sensors

Civil Engineering Journal

Optimal placement of wireless structural health monitoring (SHM) sensors has to consider modal id... more Optimal placement of wireless structural health monitoring (SHM) sensors has to consider modal identification accuracy and power efficiency. In this study, two-tier wireless sensor network (WSN)-based SHM systems with clusters of sensors are investigated to overcome this difficulty. Each cluster contains a number of sensor nodes and a cluster head (CH). The lower tier is composed of sensors communicating with their associated CHs, and the upper tier is composed of the network of CHs. The first step is the optimal placement of sensors in the lower tier via the effective independence method by considering the modal identification accuracy. The second step is the optimal placement of CHs in the upper tier by considering power efficiency. The sensors in the lower tier are partitioned into clusters before determining the optimal locations of CHs in the upper tier. Two approaches, a constrained K-means clustering approach and a genetic algorithm (GA)-based clustering approach, are propose...

Download

Fuzzy Neural Network Learning Model for Image Recognition

Integrated Computer-Aided Engineering, 1993

An unsupervised fuzzy neural network classification algorithm has been developed and applied to p... more An unsupervised fuzzy neural network classification algorithm has been developed and applied to perform feature abstraction and classify a large number of training instances into a small number of clusters. A fuzzy neural network learning model has been developed by integrating the unsupervised fuzzy neural network classification algorithm with a genetic algorithm and an adaptive conjugate gradient neural network learning algorithm. The learning model has been applied to the domain of image recognition. The performance of the model has been evaluated by applying it to a large-scale training example with 2304 training instances. An average computational speedup of eight is achieved by the new algorithm.

Object-oriented backpropagation and its application to structural design

Neurocomputing, 1994

... The generalized delta rule with backpropagation learn-ing strategy associated with a multilay... more

Parallel backpropagation learning algorithms on CRAY Y-MP8/864 supercomputer

Neurocomputing, 1993

ABSTRACT Parallel backpropagation neural networks learning algorithms have been developed employi... more ABSTRACT Parallel backpropagation neural networks learning algorithms have been developed employing the vectorization and microtasking capabilities of vector MIMD machines. They have been implemented in C on CRAY Y-MP/864 supercomputer under UNICOS operating system. The algorithms have been applied to two different domains: engineering design and image recognition, and their performance has been investigated. A maximum speedup of about 6.7 is achieved using eight processors for a large network with 5950 links due to microtasking only. When vectorization is combined with microtasking, a maximum speedup of about 33 is realized using eight processors.

Machine learning in engineering design-an unsupervised fuzzy neural network case-based learning model

Proceedings Intelligent Information Systems. IIS'97, 1997

ABSTRACT Engineering design is a creative and experience oriented process. Facing a new design ca... more ABSTRACT Engineering design is a creative and experience oriented process. Facing a new design case, an experienced designer will recall the similar cases in a case base which have been solved before. Then, the designer will attempt to find the solution from these similar cases in a way of adaptation or synthesis. An unsupervised fuzzy neural network (UFN) case-based learning model has been developed to perform the aforementioned design process and implemented in two steps. The UFN learning model has been applied to the domain of engineering design. The learning results show that the learning performance of the new learning model is superior to that of a supervised learning model only in complicated or discrete domains. Also, the unsupervised fuzzy neural network learning model can learn complicated design problems within a reasonable CPU time

Wireless Sensor Networks for Monitoring Indoor Environment: An Application to Hospital Buildings

variabless of the nodes connected to it by the incoming links. This function is

A model of perceptron learning with a hidden layer for engineering design

Neurocomputing, 1991

ABSTRACT A model of machine learning in engineering design, called PERHID, is presented based on ... more ABSTRACT A model of machine learning in engineering design, called PERHID, is presented based on the concept of perceptron learning algorithm with a two-layer neural network. PERHID has been constructed by combining the perceptron with a single-layer AND neural net. The problem of structural design is cast in a form that can be described by a two-layer neural network. Some results from PERHID learning model are presented in tabular form. The paper is concluded by a comparison of the learning by the previously developed single-layer perceptron and PERHID.

An Object-Oriented Model for Processing Earthquake Engineering Knowledge

Computer-Aided Civil and Infrastructure Engineering, 2008

Thi, article presents an object-oriented model for processing the knowledge of earthquake damage ... more Thi, article presents an object-oriented model for processing the knowledge of earthquake damage and structural behavior electronically. The model has been implemented in C+ + in a prototype system. called OQUAKE, on a SUN workstation. Knowledge representation in OQUA KE is through a combination of frames and scripts. Two generalpurpose object classes provide support for developing and managing frame and script knowledge bases. Frames and scripts integrated into an objectoriented model provide the most effective way of representing stereotypical sequences of knowledge in d text-based knowledge domain.

Download

The study of combining hive-grid target with sub-pixel analysis for measurement of structural experiment

This study presents a digital image processing technique, by integrating sub-pixel analysis using... more This study presents a digital image processing technique, by integrating sub-pixel analysis using digital image correlation method with a novel hive-grid target, for the measurement of structural experiment data. First, a numerical simulation of photography experiment at short range is employed to validate the feasibility of proposed approach. Herein, the simulation image caught from digital speckle and hive-grid target are compared, and the measured time-history displacement of simulation image is computed by the digital image correlation and edge detection methods. The results reveal that, via the digital image correlation method with hive-grid target, the measured time-history displacement at specific position can be analyzed accurately. Following, the experimental data gained from LVDT and digital camera for a six-storey steel frame at National Center for Research on Earthquake Engineering (NCREE) in Taiwan is used to verify the performance of the proposed approach. The measured time-history displacements of the steel frame are converted into frequency domain via Fourier Transform and Wavelet Transform schemes. The results revealed that the relative error between data from LVDT and analyzed data from digital image correlation is below 1% on frequency domain. Herein, the sampling rate of digital camera is lower than LVDT, because high sampling rate led to underexposure and large data storage. The frame rate of common digital camera is about 30 frames/sec nowadays, however the high speed digital camera can overcome this restriction. The limitation of high sampling rate is exposure time and data storage. The experimental results of numerical simulation and shaking table test revealed that digital image correlation method with hive-grid target is accurate in high resolution images.

A hybrid learning algorithm for distributed memory multicomputers

Neural network and genetic learning algorithms for computer-aided design and pattern recognition

Four different technologies, object-oriented programming, genetic algorithms, mathematical progra... more Four different technologies, object-oriented programming, genetic algorithms, mathematical programming, and fuzzy set theory, have been employed for developing effective serial or concurrent neural network learning algorithms. First, a multi-layer neural network development environment (ANNDE) has been developed for implementing machine learning algorithms for the domain of engineering design using the object-oriented programming paradigm and implemented in C++ and G++ languages. An object-oriented momentum backpropagation learning algorithm has been implemented in ANNDE. Second, two concurrent backpropagation neural network learning algorithms have been developed employing the vectorization and microtasking capabilities of vector MIMD machines. The algorithms have been applied to two different domains: engineering design and image recognition. A maximum speedup of about 6.7 is achieved using eight processors for a large network with 5950 links due to microtasking only. Due to vectorization only, an average speedup of about 5.5 is achieved. Third, a new adaptive conjugate gradient neural network learning algorithm for training multi-layer feedforward neural network has been developed and implemented on a vector MIMD machine. The program of trial-and-error selection of learning and momentum ratios encountered in the momentum backpropagation learning algorithm is circumvented in the new adaptive learning algorithm. Due to microtasking only on a Cray Y-MP8/864 supercomputer, a maximum speedup of about 7.9 is achieved for a large network with 5950 links using eight processors. Four, a new concurrent hybrid genetic/neural network learning algorithm has been developed by integrating a genetic algorithm with the adaptive conjugate gradient neural network learning algorithm and implemented on a Cray Y-MP8/864 supercomputer. Finally, an unsupervised fuzzy neural network classification algorithm has been developed and applied to perform feature abstraction and classify a large number of training instances into a small number of clusters. A fuzzy neural network learning model has been developed by integrating the unsupervised fuzzy neural network classification algorithm with a genetic algorithm and an adaptive conjugate gradient neural network learning algorithm. The learning algorithm has been applied to the domain of image recognition. An average computational speedup of eight is achieved by the new algorithm.

Application of m-CNTs/NaClO< sub> 4</sub>/Ppy to a fast response, room working temperature ethanol sensor

A Concurrent Adaptive Conjugate Gradient Learning Algorithm On Mimd Shared-Memory Machines

The International Journal of Supercomputing Applications, 1993

A concurrent adaptive conjugate gradient learning al gorithm has been developed for training of m... more A concurrent adaptive conjugate gradient learning al gorithm has been developed for training of multilayer feed-forward neural networks and implemented in C on a MIMD shared-memory machine (CRAY Y-MP/8- 864 supercomputer). The learning algorithm has been applied to the domain of image recognition. The per formance of the algorithm has been evaluated by ap plying it to two large-scale training examples with 2,304 training instances. The concurrent adaptive neural networks algorithm has superior convergence property compared with the concurrent momentum back-propagation algorithm. A maximum speedup of about 7.9 is achieved using eight processors for a large network with 4,160 links as a result of microtask ing only. When vectorization is combined with micro tasking, a maximum speedup of about 44 is realized using eight processors.

A Knowledge-based Assistant for Earthquake Resistant Design

Artificial Intelligence Tools and Techniques for Civil and Structural Engineers

Pilot Study of Wireless Sensor Platform for Existing Tunnel Environment Monitoring

Computing in Civil Engineering (2007), 2007

Recently, monitoring of existing tunnel environment has been increasingly more important due to t... more Recently, monitoring of existing tunnel environment has been increasingly more important due to the progressively risen public concerns, especially in extreme long tunnel like Hsuehshan tunnel in Taiwan. Such extreme long tunnel can easily cause significant hazard due to automobile accident. Therefore, developing an efficient and robust monitoring system to inspect the circumstances of tunnel is the momentous research. Capabilities of wireless sensor devices and networks have significantly more advantages over those of conventional monitoring instruments, which are wire-based systems for acquisitioning and transferring. Motivated by this, a study of design and integrating of wireless sensing system for monitoring existing tunnel situation is presented in this paper. The overall system design comprises two major units, a wireless sensing unit and a wireless receiving unit. Wireless sensing unit contains two functional modules, (1) sensing and data acquisition module; (2) microprocessor with wireless communication module. Only humidity, temperature, gas, light and photo sensors are investigated in this work, but any preferred sensor can be easily adopted with this smart transmitting scheme to realize a wireless sensor network system. Wireless receiving unit also consists of two functional modules, microprocessor with wireless communication module and a gateway. Experimental study was conducted to investigate the proposed prototype. Investigational results revealed that the feasibility of wireless sensor network in existing tunnel environment monitoring and maintaining.

Unsupervised fuzzy neural networks for damage detection of structures

Structural Control and Health Monitoring, 2007

This work presents an artificial neural network (ANN) approach for detecting structural damage. I... more This work presents an artificial neural network (ANN) approach for detecting structural damage. In place of the commonly used supervised neural network, this work adopts an unsupervised neural network which incorporates the fuzzy concept (named the unsupervised fuzzy neural network, UFN) to detect localized damage. The structural damage is assumed to take the form of reduced elemental stiffness. The damage site is demonstrated to correlate with the changes in the modal parameters of the structure. Therefore, a feature representing the damage location, termed the damage localization feature (DLF) is presented. When the structure experiences damage or change in the structural member, the measured DLF is obtained by analyzing the recorded dynamic responses of the structure. The location of the structural damage then can be identified using the UFN according to the measured DLF information. This study verifies the proposed model using an example involving a five-storey frame building. Both single-and multiple-damaged sites are considered. The effects of measured noise and the use of incomplete modal data are introduced to inspect the capability of the proposed detection approach. Additionally, the simulation results of well-known back-propagation network (BPN) and UFN are compared. The analysis results indicated that the use of fuzzy relationship in UFN made the detection of structural damage more robust and flexible than the BPN.

Download

Towards Development of Wireless Sensor System for Monitoring Anesthetic Agents

Sensor Letters, 2010

Abstract: In this paper, the design and development of sensing system for volatile anesthetic age... more Abstract: In this paper, the design and development of sensing system for volatile anesthetic agent based on wireless sensor network is proposed. The proposed system include smart sensor chip fabricated by dip coating conducting polymer for sensing sevoflurane, the most commonly used inhalational anesthetic agent. This paper also discusses the total sensor system design including hardware design, software design and sensor integration. Present sensor system consists of both wireless sensing unit and a wireless receiving unit. The ...

Detection of Damage Location Using a Novel Substructure-Based Frequency Response Function Approach with a Wireless Sensing System

International Journal of Structural Stability and Dynamics, 2012

This paper intends to detect the damage locations for building structures under an earthquake exc... more This paper intends to detect the damage locations for building structures under an earthquake excitation using a novel substructure-based FRF approach with a damage location index (SubFRFDI). An Imote2.NET-based wireless structural health monitoring system was developed and employed in the experimental studies for the sake of deployment flexibility, low maintenance cost, low power consumption, self-organization capability, and wireless communication capability. The feasibility of the proposed approach for damage detection was examined using the numerical response of a six-storey shear plane frame structure subjected to a base excitation. The results demonstrate that the SubFRFDI can be successfully used to identify the damage of different levels at a single site or multiple sites. The SubFRFDI is independent of the responses to various input earthquake excitations. Even with the addition of noises, the SubFRFDI still functions well. The feasibility and robustness of the proposed Imo...

Locating damaged storeys in a shear building based on its sub-structural natural frequencies

Engineering Structures, 2012

Vibration-based damage detection methods are simple and conventionally adopted to monitor the str... more Vibration-based damage detection methods are simple and conventionally adopted to monitor the structural health of buildings. This work proposes a simple and efficient approach to locating the storeys whose properties (stiffness and mass) change in the life cycle of a shear building. The storeys that may be damaged are determined by comparing the natural frequencies of sub-structures in different stages in the life cycle of a building. An appropriate ARX (autoregressive with exogenous input) model of a sub-structure of a shear building is established from the sub-structural dynamic responses in terms of acceleration or velocity. The parameters in an ARX model of a sub-structure are identified through the continuous wavelet transform, and the natural frequency and damping ratio of the sub-structure are estimated directly through these identified parameters. The effectiveness of the proposed procedure is verified using the numerically simulated earthquake acceleration responses and ambient vibration responses of a six-storey shear building that is damaged at one or two storeys with different damage levels. The effect of noise on the accuracy of the proposed approach is also examined. The proposed scheme is demonstrated to be superior to COMAC (Coordinate Modal Assurance Criterion) and the frequency response function curvature method in identifying damaged storeys. The proposed method is also applied to process the dynamic responses of three five-storey steel frames, which are not shear buildings, in shaking table tests. The differences in the floor mass or storey stiffness among these frames are accurately reflected in the sub-structural natural frequencies that are obtained by the proposed approach.

Download

Shih-Lin Hung

Uploads

Papers by Shih-Lin Hung

Log In