• Journal of KIISE:Software and Applications
• /
• v.34 no.6
• /
• pp.549-561
• /
• 2007

Vision-based scene understanding is to infer and interpret the context of a scene based on the evidences by analyzing the images. A probabilistic approach using Bayesian networks is actively researched, which is favorable for modeling and inferencing cause-and-effects. However, it is difficult to gather meaningful evidences sufficiently and design the model by human because the real situations are dynamic and uncertain. In this paper, we propose a learning method of Bayesian network that reduces the computational complexity and enhances the accuracy by searching an efficient BN structure in spite of insufficient evidences and training data. This method represents the domain knowledge as ontology and builds an efficient hierarchical BN structure under constraint rules that come from the ontology. To evaluate the proposed method, we have collected 90 images in nine types of circumstances. The result of experiments indicates that the proposed method shows good performance in the uncertain environment in spite of few evidences and it takes less time to learn.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2C
• /
• pp.238-246
• /
• 2004

In this paper, an estimator that take advantages of time and frequency correlation within an OFDM symbol is investigated. OFDM systems using the proposed estimator can be very effective in detecting signals under non-sampled space and time-varying channels. Also, under same complexity, the proposed estimator outperforms the previously proposed estimator. Since even if there are no assumption about channel correlation, the linear interpolation method instead of optimal interpolation using correct channel correlation is proposed in case the receiver does not know the channel correlation function in time domain. Therefore the proposed channel estimator help improving the performance of OFDM systems under non-sampled spaced and fast time-varying channels.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4A
• /
• pp.307-314
• /
• 2010

In this paper, a receive diversity combining technique is proposed for single-carrier frequency division multiple access (SC-FDMA)-based cooperative relay systems when discrete Fourier transform (DFT) spreading sizes for mobile station (MS) and relay station (RS) are different. The proposed technique is composed of a DFT spreading size adjustment block, a phase rotation compensation block, a channel phase compensation block, and a receive diversity combining block. The proposed technique is robust to multipath channels and can be operated with a relatively small computational complexity because receive diversity combining is performed with scalar operations in the frequency-domain. It is shown by computer simulation that the proposed receive diversity combining techniques achieve a performance gain over the conventional maximal ratio combining (MRC) techniques for SC-FDMA-based cooperative relay systems.

• International Journal of Fluid Machinery and Systems
• /
• v.8 no.4
• /
• pp.264-273
• /
• 2015

This presentation describes an experimental approach for the detection of cavitation in hydraulic machines by use of ultrasonic signal analysis. Instead of using the high frequency pulses (typically 1MHz) only for transit time measurement different other signal characteristics are extracted from the individual signals and its correlation function with reference signals in order to gain knowledge of the water conditions. As the pulse repetition rate is high (typically 100Hz), statistical parameters can be extracted of the signals. The idea is to find patterns in the parameters by a classifier that can distinguish between the different water states. This classification scheme has been applied to different cavitation sections: a sphere in a water flow in circular tube at the HSLU in Lucerne, a NACA profile in a cavitation tunnel and two Francis model test turbines all at LMH in Lausanne. From the signal raw data several statistical parameters in the time and frequency domain as well as from the correlation function with reference signals have been determined. As classifiers two methods were used: neural feed forward networks and decision trees. For both classification methods realizations with lowest complexity as possible are of special interest. It is shown that two to three signal characteristics, two from the signal itself and one from the correlation function are in many cases sufficient for the detection capability. The final goal is to combine these results with operating point, vibration, acoustic emission and dynamic pressure information such that a distinction between dangerous and not dangerous cavitation is possible.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.3 no.1
• /
• pp.27-36
• /
• 2011

In the proposed paper numerical calculations are carried out using two versions of a three-dimensional, timedomain panel method developed by the group of Prof. P. Sclavounos at MIT, i.e. the linear code SWAN2, enabling optionally the use of the instantaneous non-linear Froude-Krylov and hydrostatic forces and the fully non-linear SWAN4. The analytical results are compared with experimental results for three hull forms with increasing geometrical complexity, the Series 60, a reefer vessel with stern bulb and a modern fast ROPAX hull form with hollow bottom in the stern region. The details of the geometrical modeling of the hull forms are discussed. In addition, since SWAN4 does not support transom sterns, only the two versions of SWAN2 were evaluated over experimental results for the parent hull form of the NTUA double-chine, wide-transom, high-speed monohull series. The effect of speed on the numerical predictions was investigated. It is concluded that both versions of SWAN2 the linear and the one with the non-linear Froude-Krylov and hydrostatic forces provide a more robust tool for prediction of the dynamic response of the vessels than the non-linear SWAN4 code. In general, their results are close to what was expected on the basis of experience. Furthermore, the use of the option of non-linear Froude-Krylov and hydrostatic forces is beneficial for the accuracy of the predictions. The content of the paper is based on the Diploma thesis of the second author, supervised by the first one and further refined by the third one.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.1
• /
• pp.46-53
• /
• 1996

Adaptive LMS algorithm has been used in many application areas due to its low complexity. In this paper input signal is transformed into the subbands with arbitrary bandwidth. In each subbands the dynamic range can be reduced, so that the independent filtering in each subbands has faster convergence rate than the full band system. The DCT transform domain LMS adaptive filtering has the whitening effect of input signal at each bands. This leads the convergence rate to very high speed owing to the decrease of eigen value spread Finally, the filtered signals in each subbands are synthesized for the output signal to have full frequency components. In this procedure wavelet filter bank guarantees the perfect reconstruction of signal without any interspectra interference. In simulation for the case of speech signal added additive white gaussian noise, the suggested algorithm shows better performance than that of conventional NLMS algorithm at high SNR.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.1085-1089
• /
• 2015

Text-mining technique in the past had difficulty in realizing the analysis algorithm due to text complexity and degree of freedom that variables in the text have. Although the algorithm demanded lots of effort to get meaningful result, mechanical text analysis took more time than human text analysis. However, along with the development of hardware and analysis algorithm, big data technology has appeared. Thanks to big data technology, all the previously mentioned problems have been solved while analysis through text-mining is recognized to be valuable as well. However, applying text-mining to Korean text is still at the initial stage due to the linguistic domain characteristics that the Korean language has. If not only the data searching but also the analysis through text-mining is possible, saving the cost of human and material resources required for text analysis will lead efficient resource utilization in numerous public work fields. Thus, in this paper, we compare and evaluate the public document classification by handwork to public document classification where word frequency(TF-IDF) in a text-mining-based text and Cosine similarity between each document have been utilized in big data environment.

• The Journal of Korea Robotics Society
• /
• v.6 no.3
• /
• pp.197-209
• /
• 2011

This paper presents a localization system using ceiling images in a large indoor environment. For a system with low cost and complexity, we propose a single camera based system that utilizes ceiling images acquired from a camera installed to point upwards. For reliable operation, we propose a method using hybrid features which include natural landmarks in a natural scene and artificial landmarks observable in an infrared ray domain. Compared with previous works utilizing only infrared based features, our method reduces the required number of artificial features as we exploit both natural and artificial features. In addition, compared with previous works using only natural scene, our method has an advantage in the convergence speed and robustness as an observation of an artificial feature provides a crucial clue for robot pose estimation. In an experiment with challenging situations in a real environment, our method was performed impressively in terms of the robustness and accuracy. To our knowledge, our method is the first ceiling vision based localization method using features from both visible and infrared rays domains. Our system can be easily utilized with a variety of service robot applications in a large indoor environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.496-512
• /
• 2007

In this paper, we propose a novel JPEG-2000 compressed image retrieval system using feature vector extracted through partial entropy decoding. Main idea of the proposed method is to utilize the context information that is generated during entropy encoding/decoding. In the framework of JPEG-2000, the context of a current coefficient is determined depending on the pattern of the significance and/or the sign of its neighbors in three bit-plane coding passes and four coding modes. The contexts provide a model for estimating the probability of each symbol to be coded. And they can efficiently describe texture images which have different pattern because they represent the local property of images. In addition, our system can directly search the images in the JPEG-2000 compressed domain without full decompression. Therefore, our proposed scheme can accelerate the work of retrieving images. We create various distortion and similarity image databases using MIT VisTex texture images for simulation. we evaluate the proposed algorithm comparing with the previous ones. Through simulations, we demonstrate that our method achieves good performance in terms of the retrieval accuracy as well as the computational complexity.

• Journal of the Ergonomics Society of Korea
• /
• v.25 no.3
• /
• pp.49-60
• /
• 2006

Technological encroachment provides human operators with flood of information that must be analyzed to understand the environment and make judgments that lead to strategic actions. Further, the environment is not static and therefore uncertain, changing its aspect dynamically. Complexity accompanied with its dynamics imposes substantial difficulty to human operators' task. Criticality of having situational understanding becomes more important than ever. Situationalunderstanding requires the human operators possessing tacit knowledge in order for them to make the sense out of the situation while interacting with information from many heterogeneous sources, the notion of sensemaking. Sensemaking refers to the process of developing mental framework to assemble pieces of information representing different aspects of the environment that can be used to develop one's own actionable knowledge to implement their judgments in the uncertain environment. Therefore, judgment process and performance is a key component of sensemaking process. Among many judgment and decision making models, the lens model with its extension can be utilized to partially describe the judgmental aspect of sensemaking. One of the lens model parameters, unmodeled knowledge, can be a corresponding quantitative measure for the tacit knowledge that plays an important role in sensemaking. In this paper, a comprehensive literature for sensemaking is provided to formally define the notion of sensemaking in the military domain. Also, it is proposed that there is a crucial link between the sensemaking and human judgment process and performance from the lens model perspective. Potential implications for experimental framework are also proposed.