• ETRI Journal
• /
• v.22 no.2
• /
• pp.11-19
• /
• 2000

If the right and left signals of a binaural sound recording are reproduced through loudspeakers instead of a headphone, they are inevitably mixed during their transmission to the ears of the listener. This degrades the desired realism in the sound reproduction system, which is commonly called 'cross-talk.' A 'cross-talk canceler' that filters binaural signals before they are sent to the sound sources is needed to prevent cross-talk. A cross-talk canceler equalizes the resulting sound around the listener's ears as if the original binaural signal sound is reproduced next to the ears of listener. A cross-talk canceler is also a solution to the problem-how binaural sound is distributed to more than 2 channels that drive sound sources. This paper presents an effective way of building a cross-talk canceler in which geometric information, including locations of the listener and multiple loudspeakers, is divided into angular information and distance information. The presented method makes a database in an off-line way using an adaptive filtering technique and Head Related Transfer Functions. Though the database is mainly concerned about the situation where loudspeakers are located on a standard radius from the listener, it can be used for general radius cases after a distance compensation process, which requires a small amount of computation. Issues related to inverting a system to build a cross-talk canceler are discussed and numerical results explaining the preferred configuration of a sound reproduction system for stereo loudspeakers are presented.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.5
• /
• pp.1252-1271
• /
• 2013

Automatic image annotation has become an increasingly important research topic owing to its key role in image retrieval. Simultaneously, it is highly challenging when facing to large-scale dataset with large variance. Practical approaches generally rely on similarity measures defined over images and multi-label prediction methods. More specifically, those approaches usually 1) leverage similarity measures predefined or learned by optimizing for ranking or annotation, which might be not adaptive enough to datasets; and 2) predict labels separately without taking the correlation of labels into account. In this paper, we propose a method for image annotation through collaborative similarity metric learning from dataset and modeling the label correlation of the dataset. The similarity metric is learned by simultaneously optimizing the 1) image ranking using structural SVM (SSVM), and 2) image annotation using correlated label propagation, with respect to the similarity metric. The learned similarity metric, fully exploiting the available information of datasets, would improve the two collaborative components, ranking and annotation, and sequentially the retrieval system itself. We evaluated the proposed method on Corel5k, Corel30k and EspGame databases. The results for annotation and retrieval show the competitive performance of the proposed method.

• Advances in nano research
• /
• v.11 no.6
• /
• pp.595-606
• /
• 2021

This paper conducted mainly for forecasting the behavior of the shear connectors in steel-concrete composite beams based on the different factors. The main goal was to analyze the influence of variable parameters on the shear strength of C-shaped and L-shaped angle shear connectors. The method of ANFIS (adaptive neuro fuzzy inference system) was applied to the data in order to select the most influential factors for the mentioned shear strength forecasting. Five inputs are considered: height, length, thickness of shear connectors together with concrete strength and respective slip of the shear connectors after testing. The ANFIS process for variable selection was also implemented in order to detect the predominant factors affecting the forecasting of the shear strength of C-shaped and L-shaped angle shear connectors. The results show that the forecasting methodology developed in this research is useful for enhancing the multiple performances characterizing in the shear strength prediction of C and L shaped angle shear connectors analyzing.

• Steel and Composite Structures
• /
• v.43 no.5
• /
• pp.625-637
• /
• 2022

Axial compression capacity (P_u) is a significant yet complex parameter of concrete-filled steel tube (CFST) columns. This study offers a novel ensemble tool, adaptive neuro-fuzzy inference system (ANFIS) supervised by equilibrium optimization (EO), for accurately predicting this parameter. Moreover, grey wolf optimization (GWO) and Harris hawk optimizer (HHO) are considered as comparative supervisors. The used data is taken from earlier literature provided by finite element analysis. ANFIS is trained by several population sizes of the EO, GWO, and HHO to detect the best configurations. At a glance, the results showed the competency of such ensembles for learning and reproducing the P_u behavior. In details, respective mean absolute errors along with correlation values of 4.1809% and 0.99564, 10.5947% and 0.98006, and 4.8947% and 0.99462 obtained for the EO-ANFIS, GWO-ANFIS, and HHO-ANFIS, respectively, indicated that the proposed EO-ANFIS can analyze and predict the behavior of CFST columns with the highest accuracy. Considering both time and accuracy, the EO provides the most efficient optimization of ANFIS and can be a nice substitute for experimental approaches.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.749-752
• /
• 2024

연합학습은 클라이언트가 중앙 서버에 원본 데이터를 주지 않고도 학습할 수 있도록 설계된 분산된 머신러닝 방법이다. 그러나 클라이언트와 중앙 서버 사이에 모델 업데이트 정보를 공유한다는 점에서 여전히 추론 공격(Inference Attack)과 오염 공격(Poisoning Attack)의 위험에 노출되어 있다. 이러한 공격을 방어하기 위해 연합학습에 차분프라이버시(Differential Privacy)를 적용하는 방안이 연구되고 있다. 차분 프라이버시는 데이터에 노이즈를 추가하여 민감한 정보를 보호하면서도 유의미한 통계적 정보 쿼리는 공유할 수 있도록 하는 기법으로, 노이즈를 추가하는 위치에 따라 전역적 차분프라이버시(Global Differential Privacy)와 국소적 차분 프라이버시(Local Differential Privacy)로 나뉜다. 이에 본 논문에서는 차분 프라이버시를 적용한 연합학습의 최신 연구 동향을 전역적 차분 프라이버시를 적용한 방향과 국소적 차분 프라이버시를 적용한 방향으로 나누어 검토한다. 또한 이를 세분화하여 차분 프라이버시를 발전시킨 방식인 적응형 차분 프라이버시(Adaptive Differential Privacy)와 개인화된 차분 프라이버시(Personalized Differential Privacy)를 응용하여 연합학습에 적용한 방식들에 대하여 특징과 장점 및 한계점을 분석하고 향후 연구방향을 제안한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.4
• /
• pp.235-243
• /
• 2021

River surveying is conducted to acquire basic geographic data for river master plans and various river maintenance, and it is also used to predict changes after river maintenance construction. ABL (Airborne Bathymetric LiDAR) system is a cutting-edge surveying technology that can simultaneously observe the water surface and river bed using a green laser, and has many advantages in river surveying. In order to use the ABL data for river surveying, it is prerequisite step to segment and extract the water surface and river bed points from the original point cloud data. In this study, point cloud segmentation was performed by applying the ground filtering technique, ATIN (Adaptive Triangular Irregular Network) to the ABL data and then, the water surface and riverbed point clouds were extracted sequentially. In the Gokgyocheon river area, Chungcheongnam-do, the experiment was conducted with the dataset obtained using the Leica Chiroptera 4X sensor. As a result of the study, the overall classification accuracy for the water surface and riverbed was 88.8%, and the Kappa coefficient was 0.825, confirming that the ABL data can be effectively used for river surveying.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.11
• /
• pp.1495-1504
• /
• 2013

Renewable energy integration and increased system complexities make system operator maintain supply and demand balance harder than before. To keep the grid frequency in a stable range, an appropriate spinning reserve margin should be procured with consideration of ever-changing system situation, such as demand, wind power output and generator failure. This paper propose a novel concept of dynamic reserve, which arrange different spinning reserve margin depending on time. To investigate the effectiveness of the proposed dynamic reserve, we developed a new short-term reliability criterion that estimates the probability of a spinning reserve shortage events, thus indicating grid frequency stability. Uncertainties of demand forecast error, wind generation forecast error and generator failure have been modeled in probabilistic terms, and the proposed spinning reserve has been applied to generation scheduling. This approach has been tested on the modified IEEE 118-bus system with a wind farm. The results show that the required spinning reserve margin changes depending on the system situation of demand, wind generation and generator failure. Moreover the proposed approach could be utilized even in case of system configuration change, such as wind generation extension.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.6
• /
• pp.111-117
• /
• 2009

In the wideband code division access (WCDMA) systems, a pilot channel is used to determine WCDMA network coverage, cell identification, synchronization, timing acquisition and tracking, user-set handoff, channel estimation, and so on. A wireless repeater, which is deployed in the urban area for the WCDMA system to meet the growing demand on wireless communication services, has the possibility to receive several pilot signals from a large number of base stations, however, cannot distinguish its service base station's signal among them. This pilot interference results in frequent handoffs in the user equipment, which degrades the radio reception, transmission efficiency, quality of service, and channel capacity and increases the unwanted power consumption. In this paper, thus, we propose a pilot pollution interference cancellation scheme using one of the adaptive estimation algorithms, normalized least mean square (NLMS), which is applicable to a wireless repeater. We carried out link-level and network-level computer simulations to evaluate the performance of the proposed scheme in a wireless repeater. The simulation results verify the bit error rate (BER) improvement in the link level and the call drop probability improvement in the network level.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8228-8233
• /
• 2015

This study was examined for perception of introduction and adaptation stages focused on the tourist police in Seoul Metropolitan Police Agency. Seoul Metropolitan tourist police operates that is installed the first in Korea. Through in-depth interviews, we collected and analyzed data on the purpose of the tourist police, operating direction, the areas of activity, job characteristics, working environment. Awareness about activities of the tourist police members can have a significant impact on tourist police installations in the future. The survey was conducted for tourist police officers 16 people in the Seoul Metropolitan Police Agency, and analysis of the data was carried out through a qualitative research analysis program NVivo 10.0. Recognition was divided that Start step, Trial-and-error step, Skilled step, Completion step from the work experience of the tourist police and it analyzed the difference between each step. Each stage found difference in the individuals, working periods, also it was confirmed that difference of opinion about the settlement and completeness in the tourist police.