• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.832-842
• /
• 2020

The coordination control of multiple Underactuated Underwater Vehicles (UUVs) moving in three dimensional space is investigated in this paper. The coordinated path following control task is decomposed into two sub tasks, that is, path following control and coordination control. In the spatial curve path following control task, path following error dynamics is build in the Serret-Frenet coordinate frame. The virtual reference object can be chosen freely on the desired spatial path. Considering the speed of the UUV, the line-of-sight navigation is introduced to help the path following errors quickly converge to zero. In the coordination control sub task, the communication topology of multiple UUVs is described by the graph theory. The speed of each UUV is adjusted to achieve the coordination. The path following system and the coordination control system are viewed as the feedback connection system. Input-to-state stable of the coordinated path following system can be proved by small gain theorem. The simulation experiments can further demonstrate the good performance of the control method.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.61-81
• /
• 2023

This study presents an ensemble learning based Bayesian model updating approach for structural damage diagnosis. In the developed framework, the structure is initially decomposed into a set of substructures. The autoregressive moving average (ARMAX) model is established first for structural damage localization based structural motion equation. The wavelet packet decomposition is utilized to extract the damage-sensitive node energy in different frequency bands for constructing structural surrogate models. Four methods, including Kriging predictor (KRG), radial basis function neural network (RBFNN), support vector regression (SVR), and multivariate adaptive regression splines (MARS), are selected as candidate structural surrogate models. These models are then resampled by bootstrapping and combined to obtain an ensemble model by probabilistic ensemble. Meanwhile, the maximum entropy principal is adopted to search for new design points for sample space updating, yielding a more robust ensemble model. Through the iterations, a framework of surrogate ensemble learning based model updating with high model construction efficiency and accuracy is proposed. The specificities of the method are discussed and investigated in a case study.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.3
• /
• pp.159-166
• /
• 2007

This paper evaluates the soundness of structural elements using Wavelet Packet Transform (WPT). WPT is applied to the response acceleration of a framed structure which is subjected to earthquake load to decompose the response acceleration, then the energy of each component is calculated. The first five largest components in energy magnitude among the decomposed components are selected as input to an ANN to identify the damage location and severity. Two nodes in output layer yield damaged element and damage severity respectively. This method successfully evaluates the amount of damage and its location in the structure.

• Asian review of World Histories
• /
• v.4 no.1
• /
• pp.3-34
• /
• 2016

This introduction is both a statement of a research problem and an account of the first research results for its solution. As more historical databases come online and overlap in coverage, we need to discuss the two main issues that prevent 'big' results from emerging so far. Firstly, historical data are seen by computer science people as unstructured, that is, historical records cannot be easily decomposed into unambiguous fields, like in population (birth and death records) and taxation data. Secondly, machine-learning tools developed for structured data cannot be applied as they are for historical research. We propose a complex network, narrative-driven approach to mining historical databases. In such a time-integrated network obtained by overlaying records from historical databases, the nodes are actors, while thelinks are actions. In the case study that we present (the world as seen from Venice, 1205-1533), the actors are governments, while the actions are limited to war, trade, and treaty to keep the case study tractable. We then identify key periods, key events, and hence key actors, key locations through a time-resolved examination of the actions. This tool allows historians to deal with historical data issues (e.g., source provenance identification, event validation, trade-conflict-diplomacy relationships, etc.). On a higher level, this automatic extraction of key narratives from a historical database allows historians to formulate hypotheses on the courses of history, and also allow them to test these hypotheses in other actions or in additional data sets. Our vision is that this narrative-driven analysis of historical data can lead to the development of multiple scale agent-based models, which can be simulated on a computer to generate ensembles of counterfactual histories that would deepen our understanding of how our actual history developed the way it did. The generation of such narratives, automatically and in a scalable way, will revolutionize the practice of history as a discipline, because historical knowledge, that is the treasure of human experiences (i.e. the heritage of the world), will become what might be inherited by machine learning algorithms and used in smart cities to highlight and explain present ties and illustrate potential future scenarios and visionarios.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.1-7
• /
• 2007

In order to recognize a vehicle license plate, the region of the license plate should be extracted from a vehicle image. Then, character region should be separated from the background image and characters are recognized using some neural networks with selected feature vectors. Of course, choice of feature vectors which serve as the basis of the character recognition has an important effect on recognition result as well as reduction of data amount. In this paper, we propose a novel feature extraction method in which number images are decomposed into linear combination of eigennumbers and show the validity of this method by applying to the recognition of numeric characters in license plates. The experimental results show the recognition rate of 95.3% for about 500 vehicle images with multi-layer perceptron neural network in the eigennumber space. Compared with the conventional mesh feature, it shows a better recognition rate by 5%.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2016.02a
• /
• pp.430.1-430.1
• /
• 2016

We present the concept of reducible fugitive material that conformally surrounds core Cu nanowire (NW) to fabricate transparent conducting electrode (TCE). Reducing atmosphere can corrodes/erodes the underlying/surrounding layers and might cause undesirable reactions such impurity doing and contamination, so that hydrogen-/forming gas based annealing is impractical to make device. In this regards, we introduce novel reducible shell conformally surrounding indivial CuNW to provide a protection against the oxidation when exposed to both air and solvent. Uniform copper lactate shell formation is readily achievable by injecting lactic acid to the CuNW dispersion as the acid reacts with the surface oxide/hydroxide or pure copper. Cu lactate shell prevents the core CuNW from the oxidation during the storage and/or film formation, so that the core-shell CuNW maintains without signficant oxidation for long time. Upon simple thermal annealing under vacuum or in nitrogen atmosphere, the Cu lactate shell is easily decomposed to pure Cu, providing an effective way to produce pure CuNW network TCE with typically sheet resistance of $19.8{\Omega}/sq$ and optical transmittance of 85.5% at 550 nm. Our reducible copper lactate core-shell Cu nanowires have the great advantage in fabrication of device such as composite transparent electrodes or solar cells.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.51-57
• /
• 1999

In this paper, an adaptive thresholding of the nonuniformly contrasted images is proposed through using the contrast pre-enhancement of the local regions and the bilinear interpolation between the local threshold values. The nonuniformly contrasted image is decomposed into 9${\times}$9 sized local regions, and the contrast is enhanced by intensifying the gray level difference of each low contrasted or blurred region. Optimal threshold values are obtained by iterative method from the gray level distribution of each contrast-enhanced local region. Discontinuities are reduced at the region of interest or at the characters by using bilinear interpolation between the neighboring threshold surfaces. Character recognition experiments are conducted using backpropagation neural network on the characters extracted from the nonuniformly contrasted document, PCB, and wafer images binarized through using the proposed thresholding and the conventional thresholding methods, and the results prove the relative effectiveness of the proposed scheme.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.861-869
• /
• 2003

The rapid growth of multimedia network systems has caused overflowing illegal copies of digital contents. Among digital contents, watermarking technique can be used to protect ownership about the image. Copyright protection involves the authentication of image ownership and the identification of illegal copies of image. In this paper, a new digital watermarking technique using HVS and adaptive scale factor based on the wavelet transform is proposed to use the binary image watermark. The original image is decomposed by 3-level wavelet transform. It is embedded to baseband and high frequency band. The embedding in the baseband is considered robustness, the embedding in the high frequency band is concerned about HVS and invisibility. The watermarking of a visually recognizable binary image used the HVS and random permutation to protect the copyright. From the experimental results, we confirm that the proposed technique is strong to various attacks such as joint photographic experts ground(JPEG) compression, cropping, collusion, and inversion of lines.

• Journal of electromagnetic engineering and science
• /
• v.11 no.4
• /
• pp.282-289
• /
• 2011

GHz electromagnetic interference (EMI) characteristics are analyzed for a 3dimensional (3D) stacked chip power distribution network (PDN) with through silicon via (TSV) connections. The EMI problem is mostly raised by P/G (power/ground) noise due to high switching current magnitudes and high PDN impedances. The 3D stacked chip PDN is decomposed into P/G TSVs and vertically stacked capacitive chip PDNs. The TSV inductances combine with the chip PDN capacitances produce resonances and increase the PDN impedance level in the GHz frequency range. These effects depend on stacking configurations and P/G TSV designs and are analyzed using the P/G TSV model and chip PDN model. When a small size chip PDN and a large size chip PDN are stacked, the small one's impedance is more seriously affected by TSV effects and shows higher levels. As a P/G TSV location is moved to a corner of the chip PDNs, larger PDN impedances appear. When P/G TSV numbers are enlarged, the TSV effects push the resonances to a higher frequency range. As a small size chip PDN is located closer to the center of a large size chip PDN, the TSV effects are enhanced.