• Smart Structures and Systems
• /
• v.12 no.3_4
• /
• pp.363-379
• /
• 2013

Dynamic displacement of structures is an important index for in-service structural condition and behavior assessment, but accurate measurement of structural displacement for large-scale civil structures such as long-span bridges still remains as a challenging task. In this paper, a vision-based dynamic displacement measurement system with the use of digital image processing technology is developed, which is featured by its distinctive characteristics in non-contact, long-distance, and high-precision structural displacement measurement. The hardware of this system is mainly composed of a high-resolution industrial CCD (charge-coupled-device) digital camera and an extended-range zoom lens. Through continuously tracing and identifying a target on the structure, the structural displacement is derived through cross-correlation analysis between the predefined pattern and the captured digital images with the aid of a pattern matching algorithm. To validate the developed system, MTS tests of sinusoidal motions under different vibration frequencies and amplitudes and shaking table tests with different excitations (the El-Centro earthquake wave and a sinusoidal motion) are carried out. Additionally, in-situ verification experiments are performed to measure the mid-span vertical displacement of the suspension Tsing Ma Bridge in the operational condition and the cable-stayed Stonecutters Bridge during loading tests. The obtained results show that the developed system exhibits an excellent capability in real-time measurement of structural displacement and can serve as a good complement to the traditional sensors.

• Smart Structures and Systems
• /
• v.12 no.3_4
• /
• pp.251-269
• /
• 2013

Measurement of deflections of certain bridges is usually hampered by corruption of the GPS signal by multipath associated with passing vehicles, resulting to unrealistically large apparent displacements. Field data from the Gorgopotamos train bridge in Greece and systematic experiments revealed that such bias is due to superimposition of two major effects, (i) changes in the geometry of satellites because of partial masking of certain satellites by the passing vehicles (this effect can be faced with solutions excluding satellites that get temporarily blocked by passing vehicles) and (ii) dynamic multipath caused from reflection of satellite signals on the passing trains, a high frequency multipath effect, different from the static multipath. Dynamic multipath seems to have rather irregular amplitude, depending on the geometry of measured satellites, but a typical pattern, mainly consisting of a baseline offset, wide base peaks correlating with the sequence of main reflective surfaces of the vehicles passing next to the antenna. In cases of limited corruption of GPS signal by dynamic multipath, corresponding to scale distortion of the short-period component of the GPS waveforms, we propose an algorithm which permits to reconstruct the waveform of bridge deflections using a weak fusion of GPS and RTS data, based on the complementary characteristics of the two instruments. By application of the proposed algorithm we managed to extract semi-static and dynamic displacements and oscillation frequencies of a historical railway bridge under train loading by using noisy GPS and RTS recordings. The combination of GPS and RTS is possible because these two sensors can be fully collocated and have complementary characteristics, with RTS and GPS focusing on the long- and short-period characteristics of the displacement, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.10
• /
• pp.483-488
• /
• 2016

In this paper, we propose a prototype-based classification learning by using the nearest-neighbor rule. The nearest-neighbor is applied to segment the class area of all the training data with hyperspheres, and a hypersphere must cover the data from the same class. The radius of a hypersphere is computed by the mid point of the two distances to the farthest same class point and the nearest other class point. And we transform the prototype selection problem into a set covering problem in order to determine the smallest set of prototypes that cover all the training data. The proposed prototype selection method is designed by a greedy algorithm and applicable to process a large-scale training set in parallel. The prediction rule is the nearest-neighbor rule and the new training data is the set of prototypes. In experiments, the generalization performance of the proposed method is superior to existing methods.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.5_6
• /
• pp.258-264
• /
• 2003

VLIW architecture has emerged as one of the most effective architectures in dealing with multimedia applications. In multimedia applications, there is ample potential for parallelizing the execution of multiple operations because such applications typically have data intensive processing which often has limited data and/or control dependencies. As the degree of instruction-level parallelism increases, non-clustered VLIW architectures scale poorly because of the tremendous register port pressure. Therefore, clustered VLIW architecture is definitely preferred over non-clustered VLIW architecture when a higher degree of parallelizing is possible as in the case of multimedia processing However, having multiple clusters in an architecture implies that the amount of hardware is quite large, and therefore, power consumption becomes a very crucial issue. In this paper, we propose an algorithm to minimize the peak power consumption without incurring little or no delay penalty. The effectiveness of our algorithm has been verified by various sets of experiments, and up to 30.7% reduction in the peak power consumption is observed compared with the results that is optimized to minimize resources only.

• Journal of Information Technology Services
• /
• v.11 no.4
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.51-59
• /
• 2019

Due to the exponential growth of access information on the web, the need for predicting web users' next access has increased. Various models such as markov models, deep neural networks, support vector machines, and fuzzy inference models were proposed to handle web access prediction. For deep learning based on neural network models, training time on large-scale web usage data is very huge. To address this problem, deep neural network models are trained on cluster of computers in parallel. In this paper, we investigated impact of several important spark parameters related to data partitions, shuffling, compression, and locality (basic spark parameters) for training Multi-Layer Perceptron model on Spark standalone cluster. Then based on the investigation, we tuned basic spark parameters for training Multi-Layer Perceptron model and used it for tuning Spark when training Multi-Layer Perceptron model for web access prediction. Through experiments, we showed the accuracy of web access prediction based on our proposed web access prediction model. In addition, we also showed performance improvement in training time based on our spark basic parameters tuning for training Multi-Layer Perceptron model over default spark parameters configuration.

• Journal of the Korean Institute of Gas
• /
• v.25 no.5
• /
• pp.88-96
• /
• 2021

Advanced Internet of Things (IoT) technology is being used in various ways for the safety of the energy industry. At the center of safety measures, drones play various roles on behalf of humans. Drones are playing a role in reaching places that are difficult to reach due to large-scale facilities and space restrictions that are difficult for humans to inspect. In this study, the accuracy and completeness of movement of dangerous facilities were tested using drone images, and it was confirmed that the movement recognition accuracy was 100%, the average data analysis accuracy was 95.8699%, and the average completeness was 100%. Based on the experimental results, a future-oriented facility risk analysis system combined with ICT technology was implemented and presented. Additional experiments with diversified conditions are required in the future, and ICT convergence analysis system implementation is required.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.224-230
• /
• 2019

In this paper, a new multiple servers conference service system using media control channel/distributed conference manipulation architecture has been presented. This conference service system can handle loads effectively from many conference participants. In this suggested architecture, media control channels are established between conference server, and distributed conference manipulation messages for distributing system loads are exchanged through this channels. These messages are transported between servers using media control channel created after stable transport sessions, and can be used to process server loads according to participants effectively. So this method can be used to implement large scale conference service system. For these purposes, formats of distributed conference manipulation messages which transmitted through media control channels are designed. and messages exchange procedures between conference servers are also presented. The performance of the proposed conference service system has been analysed by experiments, and the results show that the performances are improved according to participants.

• Journal of Convergence for Information Technology
• /
• v.9 no.3
• /
• pp.8-15
• /
• 2019

Recently, the importance of pre-shipment quality inspection has been emphasized due to the increase of STB supply. In this paper, we propose a method to support automation of quality inspection through simultaneous multi-channel input of STB video signal. The proposed method extracts a fingerprint using the center scan line of the image after stable video shot boundary detection using CeLDP combining color information and LDP code and performs synchronization between input video channels. The proposed method shows stronger shot boundary detection performance than the conventional shot detection method. Through the experiments applied to the real environment, it is possible to secure reliability and real-time quality check for synchronization between multi-channel inputs required for STB quality inspection. Also, based on the proposed method, we intend to study a large-scale quality inspection method in the future and propose a more effective quality inspection system.

• Microbiology and Biotechnology Letters
• /
• v.47 no.1
• /
• pp.116-124
• /
• 2019

The rapid development of the poultry industry has led to the production of large amounts of manure, which produce substances like hydrogen sulfide ($H_2S$) that contribute to odor pollution. $H_2S$ is a highly undesirable gas component and its removal from the environment is therefore necessary. Sulfur-oxidizing bacteria (SOB) are widely known to remove contaminating $H_2S$ due to their ability to oxidize reduced sulfur compounds. In this study, three potential SOB (designated AH18, AH25, and AH28) that were previously isolated from a hot spring in Malaysia were identified by 16S rRNA gene analysis. Laboratory-scale biological deodorization experiments were conducted to test the performance of the three isolates-in the form of pure or mixed cultures, with the cells immobilized onto alginate as a carrier-in reducing the $H_2S$ from chicken manure. On the basis of 16S rRNA phylogenetic analysis, isolate AH18 was identified as Pseudomonas sp., whereas isolates AH25 and AH28 were identified as Achromobacter sp. The most active deodorizing isolate was AH18, with an $H_2S$ reduction rate of 74.7% (p < 0.05). Meanwhile, the reduction rates for isolates AH25 and AH28 were 54.2% and 60.8% (p > 0.05), respectively. However, the $H_2S$ removal performance was enhanced in the mixed culture, with a reduction rate of 81.9% (p < 0.05). In conclusion, the three potential SOB isolates were capable of reducing the $H_2S$ from chicken manure in the form of a pure culture immobilized on alginate, and the reduction performance was enhanced in the mixed culture.