• Structural Monitoring and Maintenance
• /
• v.9 no.2
• /
• pp.179-200
• /
• 2022

This paper proposes a data-driven methodology for online early damage identification under changing environmental conditions. The proposed method relies on two data analysis methods: feature-based method and hybrid principal component analysis (PCA) and kernel PCA to separate damage from environmental influences. First, spectral sub-band features, namely, spectral sub-band centroids (SSCs) and log spectral sub-band energies (LSSEs), are proposed as damage-sensitive features to extract damage information from measured structural responses. Second, hybrid modeling by integrating PCA and kernel PCA is performed on the spectral sub-band feature matrix for data normalization to extract both linear and nonlinear features for nonlinear procedure monitoring. After feature normalization, suppressing environmental effects, the control charts (Hotelling T² and SPE statistics) is implemented to novelty detection and distinguish damage in structures. The hybrid PCA-KPCA technique is compared to KPCA by applying support vector machine (SVM) to evaluate the effectiveness of its performance in detecting damage. The proposed method is verified through numerical and full-scale studies (a Bridge Health Monitoring (BHM) Benchmark Problem and a cable-stayed bridge in China). The results demonstrate that the proposed method can detect the structural damage accurately and reduce false alarms by suppressing the effects and interference of environmental variations.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.185-195
• /
• 2018

As machines have been automated in the field of industries in recent years, it is a paramount importance to manage and maintain the automation machines. When a fault occurs in sensors attached to the machine, the machine may malfunction and further, a huge damage will be caused in the process line. To prevent the situation, the fault of sensors should be monitored, diagnosed and classified in a proper way. In the paper, we propose a sensor fault detection scheme based on SVM and CNN to detect and classify typical sensor errors such as erratic, drift, hard-over, spike, and stuck faults. Time-domain statistical features are utilized for the learning and testing in the proposed scheme, and the genetic algorithm is utilized to select the subset of optimal features. To classify multiple sensor faults, a multi-layer SVM is utilized, and ensemble technique is used for CNN. As a result, the SVM that utilizes a subset of features selected by the genetic algorithm provides better performance than the SVM that utilizes all the features. However, the performance of CNN is superior to that of the SVM.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.3
• /
• pp.23-29
• /
• 2015

Due to the characteristics of landslide disasters including debris flow, the rapid speed to downward and difficulty to respond or evacuate from them, it is imperative to identify their potential hazards and prepare the reduction plans. However, the current landslide hazards generated by a variety of methods has been raised its accuracy because of the complexity of input data and their analyses, and the simplification of the landslide model. The main objective of this study is, therefore, to evaluate the preliminary landslide hazard based on the identification of geomorphological features. Especially, two methodologies based on the statistics of the directional data, Vector dispersion and Planarity analyses, are used to find some relationships between geomorphological characteristics and the landslide hazard. Results show that both methods well discriminate geomorphological features between stable and unstable domains in the landslide areas. Geomorphological features are closely related to the landslide hazard and it is imperative to maximize their characteristics by adapting multiple models rather than individual model only. In conclusions, the mechanism of landslide is not determined solely by a simple cause but the complex natural phenomenon caused by the interactions of the numerous factors and it is of primary importance to require additional researches for the outbreaking mechanism that are based on various methodologies.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.55-64
• /
• 2013

Due to the popularization of digital high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy for anyone to make a high-quality counterfeit money. However, the probability of detecting a counterfeit money to the general public is extremely low. In this paper, we propose a counterfeit money detection algorithm using a general purpose scanner. This algorithm determines counterfeit money based on the different features in the printing process. After the non-local mean value is used to analyze the noises from each money, we extract statistical features from these noises by calculating a gray level co-occurrence matrix. Then, these features are applied to train and test the support vector machine classifier for identifying either original or counterfeit money. In the experiment, we use total 324 images of original money and counterfeit money. Also, we compare with noise features from previous researches using wiener filter and discrete wavelet transform. The accuracy of the algorithm for identifying counterfeit money was over 94%. Also, the accuracy for identifying the printing source was over 93%. The presented algorithm performs better than previous researches.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.3
• /
• pp.136-142
• /
• 2007

Recent researches in the recognition system have shown that SVM (Support Vector Machine) classifiers often have superior recognition rates in comparison to other classifiers. In this paper, we present the handwritten numeral recognition algorithm using SVM classifiers. The numeral features used in our algorithm are mesh features, directional features by Kirsch operators and concavity features, where first two features represent the foreground information of numerals and the last feature represents the background information of numerals. These features are complements each of the other. Since SVM is basically a binary classifier, it is required to construct and combine several binary SVMs to get the multi-class classifiers. We use two strategies for implementing multi-class SVM classifiers: "one against one" and "one against the rest", and examine their performances on the features used. The efficiency of our method is tested by the CENPARMI handwritten numeral database, and the recognition rate of 98.45% is achieved.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.3
• /
• pp.149-157
• /
• 2011

In this paper, we propose a new cardiac disorder classification method using an support vector machine (SVM) to combine hidden Markov model (HMM) and murmur existence information. Using cepstral features and the HMM Viterbi algorithm, we segment input heart sound signals into HMM states for each cardiac disorder model and compute log-likelihood (score) for every state in the model. To exploit the temporal position characteristics of murmur signals, we divide the input signals into two subbands and compute murmur probability of every subband of each frame, and obtain the murmur score for each state by using the state segmentation information obtained from the Viterbi algorithm. With an input vector containing the HMM state scores and the murmur scores for all cardiac disorder models, SVM finally decides the cardiac disorder category. In cardiac disorder classification experimental results, the proposed method shows the relatively improvement rate of 20.4 % compared to the HMM-based classifier with the conventional cepstral features.

• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.808-816
• /
• 2004

This paper proposes the method of implementation of practical online face verification system based on multiple feature combination and a similarity space. The main issue in face verification is to deal with the variability in appearance. It seems difficult to solve this issue by using a single feature. Therefore, combination of mutually complementary features is necessary to cope with various changes in appearance. From this point of view, we describe the feature extraction approaches based on multiple principal component analysis and edge distribution. These features are projected on a new intra-person/extra-person similarity space that consists of several simple similarity measures, and are finally evaluated by a support vector machine. From the experiments on a realistic and large database, an equal error rate of 0.029 is achieved, which is a sufficiently practical level for many real- world applications.

• Korean Chemical Engineering Research
• /
• v.48 no.4
• /
• pp.450-456
• /
• 2010

This study was conducted in order to design a piston, part of a shock absorber, and the findings after examining the features of the velocity distribution and the static pressure distribution of oil on a low-velocity piston are as follow. The compression speed of oil passing through an 0.9 mm orifice was 0.0156~0.0642 m/s, and the velocity vector of the velocity distribution and the static pressure distribution had a greater tendency to rotate when the velocity increased. In case of the velocity vector of the velocity distribution and the static pressure distribution with an 0.8mm orifice, the speed changed secondarily, the second pressure-drop was observed and as for the distribution of the streamline around the orifice, a vortex was produced around the center. As for the velocity distribution of oil passing from the compression cylinder to the compact pipe, the velocity was greater in orifice of small diameter. Also, the greater the pressure difference was between the compression cylinder and the compact cylinder, the greater the force it was upon the piston.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.1
• /
• pp.1-7
• /
• 2012

In general, currently developed ECG(electrocardiogram) based biometrics approaches are not suitable for real market applications since they require high cost ECG monitoring device and their measurement methods showed poor usability. In this paper, we developed lead I signal based biometrics system using special purpose ECG measurement hardware. To guarantee signal quality for biometrics from various signal measurement environment in our ordinary life, several filters are applied. In addition, to enhance usability, only two skin on electrodes without reference point are used for measurement. Lead I signals of seventeen candidates are measured from developed hardware and features are extracted. Extracted features are applied to support vector machine (SVM) pattern classifier for biometrics, and the experimental results showed 98.59% of sensitivity (SN) and 97.21% of accuracy (ACC). Compare to conventional ECG biometrics approaches, proposed system showed enhanced usability with low-cost measurement hardware.