• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.407-415
• /
• 2012

In this paper, we propose a new stereo matching algorithm by using color information especially for stereo images containing human beings in the applications such as tele-presence system. In the proposed algorithm, we first remove the background regions by using a threshold value for stereo images obtained by stereo camera and then find an initial disparity map and segment a given image into R, G, B and white color components. We also obtain edges in the segmented image and estimate the disparity from the extract boundary regions. Finally, we generate the final disparity map by properly combining the disparity map of each color component. Experiment results show better performance compared with the window based method and the dynamic programing method especially for stereo images with human being.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.11
• /
• pp.1071-1077
• /
• 2012

Low frequency noises(up to about 200 Hz) such as booming are mainly caused by particular modes, and in general the solutions may be found based on mode controls where conventional methods such as FEM can be used. However, at higher frequencies between 0.3~1 kHz, as the number of modes rapidly increases, radiation characteristics from structures, performances of damping sheets and sound packages may be more crucial rather than particular modes, and consequently the conventional FEM may be less practical in dealing with this kinds of structure-borne problems. In this context, so-called 'mid-frequency simulation model' based on FE-SEA hybrid method is studied and validated to reduce noise in this frequency region. Energy transmission loss(i.e. air borne noise) is also studied. A dash panel component is chosen for this study, which is an important path that transmits both structure-borne and air borne energies into the cavity. Design modifications including structural modifications, attachment of damping sheets and application of different sound packages are taken into account and the corresponding noise characteristics are experimentally identified. It is found that the dash member behaves as a noise path. The damping sheet and sound packages have similar influences on both sound radiation and transmission loss. The comparison between experiments and simulations shows that this model could be used to predict the tendency of noise improvement.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.503-514
• /
• 2021

Reverberation in speech signals tends to significantly degrade the performance of the Blind Source Separation (BSS) system. Especially in online systems, the performance degradation becomes severe. Methods based on joint diagonalizability constraints have been recently developed to tackle the problem. To improve the quality of separated speech, in this paper, we add the proposed de-reverberation method to the online BSS algorithm based on the constraints in reverberant environments. Through experiments on the WSJCAM0 corpus, the proposed method was compared with the existing online BSS algorithm. The performance evaluation by the Signal-to-Distortion Ratio and the Perceptual Evaluation of Speech Quality demonstrated that SDR improved from 1.23 dB to 3.76 dB and PESQ improved from 1.15 to 2.12 on average.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.151-160
• /
• 2023

The Hadith is the second source of Islamic jurisprudence after Qur'an. Both sources are indispensable for muslims to practice Islam. All Ahadith are collected and are written. But most books of Hadith contain Ahadith that can be weak or rejected. So, quite a long time, scholars of Hadith have defined laws, rules and principles of Hadith to know the correct Hadith (Sahih) from the fair (Hassen) and weak (Dhaif). Unfortunately, the application of these rules, laws and principles is done manually by the specialists or students until now. The work presented in this paper is part of the automatic treatment of Hadith, and more specifically, it aims to automatically process the chain of narrators (Hadith Isnad) to find its different components and affect for each component its own tag using a statistical method: the Hidden Markov Models (HMM). This method is a power abstraction for times series data and a robust tool for representing probability distributions over sequences of observations. In this paper, we describe an important tool in the Hadith isnad processing: A chunker with HMM. The role of this tool is to decompose the chain of narrators (Isnad) and determine the tag of each part of Isnad (POI). First, we have compiled a tagset containing 13 tags. Then, we have used these tags to manually conceive a corpus of 100 chains of narrators from "Sahih Alboukhari" and we have extracted a lexicon from this corpus. This lexicon is a set of XML documents based on HPSG features and it contains the information of 134 narrators. After that, we have designed and implemented an analyzer based on HMM that permit to assign for each part of Isnad its proper tag and for each narrator its features. The system was tested on 2661 not duplicated Isnad from "Sahih Alboukhari". The obtained result achieved F-scores of 93%.

• Hip & pelvis
• /
• v.36 no.2
• /
• pp.87-100
• /
• 2024

Total hip arthroplasty (THA) is an effective treatment for osteoarthritis, and the popularity of the direct anterior approach has increased due to more rapid recovery and increased stability. Instability, commonly caused by component malposition, remains a significant concern. The dynamic relationship between the pelvis and lumbar spine, deemed spinopelvic motion, is considered an important factor in stability. Various parameters are used in evaluating spinopelvic motion. Understanding spinopelvic motion is critical, and executing a precise plan for positioning the implant can be difficult with manual instrumentation. Robotic and/or navigation systems have been developed in the effort to enhance THA outcomes and for implementing spinopelvic parameters. These systems can be classified into three categories: X-ray/fluoroscopy-based, imageless, and computed tomography (CT)-based. Each system has advantages and limitations. When using CT-based systems, preoperative CT scans are used to assist with preoperative planning and intraoperative execution, providing feedback on implant position and restoration of hip biomechanics within a functional safe zone developed according to each patient's specific spinopelvic parameters. Several studies have demonstrated the accuracy and reproducibility of robotic systems with regard to implant positioning and leg length discrepancy. Some studies have reported better radiographic and clinical outcomes with use of robotic-assisted THA. However, clinical outcomes comparable to those for manual THA have also been reported. Robotic systems offer advantages in terms of accuracy, precision, and potentially reduced rates of dislocation. Additional research, including conduct of randomized controlled trials, will be required in order to evaluate the long-term outcomes and cost-effectiveness of robotic-assisted THA.

• Convergence Security Journal
• /
• v.24 no.3
• /
• pp.41-49
• /
• 2024

A tokenizer, which is a key component of the Transformer model, lacks the ability to effectively comprehend numerical data. Therefore, to develop a Transformer-based intrusion detection model that can operate within a real-world network environment by training packet payloads as sentences, it is necessary to convert the hexadecimal packet payloads into a character-based format. In this study, we applied three character encoding methods to convert packet payloads into numeric or character format and analyzed how detection performance changes when training them on transformer architecture. The experimental dataset was generated by extracting packet payloads from PCAP files included in the UNSW-NB15 dataset, and the RoBERTa was used as the training model. The experimental results demonstrate that the ISO-8859-1 encoding scheme achieves the highest performance in both binary and multi-class classification. In addition, when the number of tokens is set to 512 and the maximum number of epochs is set to 15, the multi-class classification accuracy is improved to 88.77%.

• Fashion & Textile Research Journal
• /
• v.7 no.4
• /
• pp.445-451
• /
• 2005

Up to the present, fabric finishing methods have been mainly employed for the application of chitosan. However, the coated chitosan acid salt is prone to be detached from the fabric during the laundering process. In order to improve the wash fastness, chitosan treated fabrics are being subjected to thermal curing. In this study, chemical crosslinking reaction by epichlorohydrin was introduced to improve the problem of the thermal curing. An improvement of the wash fastness is expected since the coated chitosan component on the fabric become insoluble by the introduction of the crosslinking. The demerit of the single chitosan treatment (inferior handle due to the excessive stiffness, etc.) was supplemented by the application of chitosan-polyurethane mixture solution. The mixture ratios were adjusted to 1 : 0, 1 : 0.25, 1 : 0.5, 1 : 1, and 1 : 2 for the chitosan/PU mixture. Physical and mechanical properties of the finished fabric specimens were measured using the Kawabata Evaluation System(KES), and hand values were calculated accordingly based on the translational formulas.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.5
• /
• pp.767-773
• /
• 2013

A high-pressure, high-pressure drop control valve, which transforms the power transfer of a system by reducing the inlet pressure of 345bartothe outlet pressure of 112bar, is a fundamental component in an offshore plant process. With the increasingly growing market share of the maritime industry, this valve has been expected to be a high-value-added product. This study not only analyzes the relation between pressure drop and fluid velocity in a trim by using fluid analysis, but also examines the possibility of cavitation in a valve in addition to the plot for the extension of lifespan. Based on the analysis results, the design and production method of the valve are established, and accordingly, performance evaluation is carried out. It is demonstrated that the pressure drop from 345bar to 112bar is more feasible in the presence of the trim, which can induce a continuous and diminutive pressure drop in order to prevent cavitation in a high-pressure drop control valve. Furthermore, despite the fluid velocity near a seatring being found to be over 30m/s, the lifespan of the valve is determined to be adequate considering the operation condition of a prototype valve of 80%.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.06a
• /
• pp.236.1-236.1
• /
• 2010

Due to global warming, the need to secure an alternative resource has become more important nationally. Due to the high tidal range of up to 9.7m on the west coast of Korea, numerous tidal current projects are being planned and constructed. The rotor, which initially converts the energy, is a very important component because it affects the efficiency of the entire system, and its performance is determined by various design variables. In this paper, a design guideline of current generating HAT rotor and acceptable field rotor in offshore environment is proposed. To design HAT rotor model, wind mill rotor design principles and turbine theories were applied based on a field HAT rotor experimental data. To verify the compatibility of the rotor design method and to analyze the properties of design factors, 3D CFD model was designed and analysed by ANSYS CFX. The analysis results and findings are summarized in the paper.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.35-49
• /
• 2004

This paper proposes a new glasses removal method from color frontal facial image to generate gray glassless facial image. The proposed method is based on recursive PCA reconstruction. For the generation of glassless images, the occluded region by glasses should be found, and a good reconstructed image to compensate with should be obtained. The recursive PCA reconstruction Provides us with both of them simultaneously, and finally produces glassless facial images. This paper shows the effectiveness of the proposed method by some experimental results. We believe that this method can be applied to removing other type of occlusion than the glasses with some modification and enhancing the performance of a face recognition system.