• Journal of Information Technology Services
• /
• v.20 no.1
• /
• pp.131-143
• /
• 2021

Commercial transactions, one of the pillars of the capitalist economy, are occurring countless times every day, especially small and medium-sized businesses. However, small and medium-sized enterprises are bound to be the legal underdogs in contracts for commercial transactions and do not receive legal support for contracts for fair and legitimate commercial transactions. When subcontracting contracts are concluded among small and medium-sized enterprises, 58.2% of them do not apply standard contracts and sign contracts that have not undergone legal review. In order to support small and medium-sized enterprises' fair and legitimate contracts, small and medium-sized enterprises can be protected from legal threats if they can reduce the risk of signing contracts by analyzing various risks in the contract and analyzing and informing them of toxic clauses and omitted contracts in advance. We propose a risk prediction model for the machine reading-based legal contract to minimize legal damage to small and medium-sized business owners in the legal blind spots. We have established our own set of legal questions and answers based on the legal data disclosed for the purpose of building a model specialized in legal contracts. Quantitative verification was carried out through indicators such as EM and F1 Score by applying pine tuning and hostile learning to pre-learned machine reading models. The highest F1 score was 87.93, with an EM value of 72.41.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.505-508
• /
• 2005

This paper presents the high speed noise reduction processing system using the MDFT on the frequency domain. The proposed system use the linear prediction coefficients of the AR method based on the SLMS(sign least mean square). The signals with a random noise tracking per-formance are examined through computer simu-lations. It is confirmed that the high speed adaptive noise reduction processing system is realized by the SLMS algorithms with rapid convergence on the FD(frequency domain).

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2E
• /
• pp.39-44
• /
• 1996

The performance of two-channel adaptive noise canceller is ofter degraded by the weights perturbation due to the speech signal. In this paper, an adaptive noise canceller employing a speech detector and two adaptation algorithms which are switched according to the speech detector is proposed. When highly correlated speech signal is detected, the tap weights of the adaptive filter are adapted by the sign algorithm. On the other hand, the weights are adapted by the NLMS algorithm when silence is detected or when the characteristics of the noise propagation channel is changed. The employed speech detector utilizes the power ratio of the input and the output of an adaptive linear prediction-error filter. According to the computer simulation, the proposed method yields better performance than conventional ones.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.386-392
• /
• 2007

최근 들어 손 제스처를 인간-기계 인터페이스에 활용하는 연구가 많아지고 있다. 그 중에서 수화 인식은 청각장애인과 일반인 사이의 원활한 의사 소통을 하게 해 주는 인터페이스로서 중요성이 날로 더해가고 있다. 하지만 기존의 수화 인식 연구는 사용자 개개인의 수화 동작의 차이를 고려하지 않고 다수 사용자를 위한 모델을 사용하기 때문에 사용자에 따라 인식률이 낮아지게 된다. 이러한 점을 보완하기 위해 본 논문에서는 개개인의 수화 동작 특성을 반영하여 시스템이 사용자에게 적응해 가는 과정을 다루고자 한다. 특히 점진적인 사용자 적응에 있어서 가장 문제가 되는 것은 어떻게 비관측된 상태(unobserved state)의 파라미터를 수정할 것인가 하는 것이다. 이를 위해서 본 논문에서는 동작 유사도와 적응 추이에 의한 추정을 통해 비관측된 상태의 모델 파라미터를 수정한다. 실제 청각 장애인들로부터 획득한 데이터베이스를 사용하여 제안한 방법이 기존 방법에 비해 더욱 빠르게 사용자의 특성을 시스템에 반영하고 인식률을 향상시킨다는 것을 실험을 통해 보인다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.1017-1022
• /
• 1996

This paper presents results of dynamic analysis of the missile initial motion arising from the missile detent force. Using ADAMS (Automatic Dynamic Analysis of Mechanical System) software, a non-linear 46-DOF (Degree of Freedom) model is developed for the launcher system including missile and launch tube contact problem. From the dynamic analysis, it is found that initial angular velocity of the missile increases when the missile detent force increases (more than 18 g) and also rocket exhaust plume is taken into account. To achieve the missile launching s ability, it needs to reduce the missile initial detent force and exhaust plume area of the launcher. Results of the dynamic analysis on the system natural frequency agree well with those obtained from experimental modal tests. The overall results suggest that the proposed method is a useful tool for prediction of initial missile stability as well as d :sign of the missile launcher system.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.18 no.2
• /
• pp.7-20
• /
• 1981

A method to predict the three-dimensional turbulent boundary layer on ship forms is introduced. The present differential method is in the scope of thin boundary layer theory and adopting the eddy-viscosity turbulence model. Two different numerical schemes are taken in this paper to handle the sign-changing cross-flows. The method is applied to predict the boundary layer development on real ship forms; SSPA Model 720($C_B$=0.675) and HSVA Tanker Model($C_B$=0.85). The results are qualitatively in good agreements with measurements except at the very stern. Therefore the method seems to be very promising if further developments are accomplished to handle the thick stern boundary layer effectively.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.352-368
• /
• 2021

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.755-756
• /
• 2020

부호가 있는 소셜 네트워크는 친구, 호감, 동의의 긍정적인 관계와 적, 불호, 반대의 부정적인 관계가 함께 표현된 네트워크이다. 이러한 네트워크를 활용한 대표적인 애플리케이션으로, 각 사용자의 관계가 긍정적인 관계인지 부정적인 관계인지 예측하는 부호 예측 문제가 있다. 이러한 부호 예측 문제를 해결하는 대표적인 방안은 네트워크의 구조적 특징들을 활용하는 것이다. 본 논문에서는, 실세계 데이터 집합들을 활용한 실험을 통해 기존 부호 예측 방법들에서 활용하는 각 특징이 부호 예측 문제의 정확도에 얼마나 기여하는지 분석하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.468-469
• /
• 2023

실세계 네트워크 데이터에서 노드들 간의 관계는 종종 친구/적 혹은 지지/반대와 같이 대조적인 부호를 갖는다. 이러한 네트워크를 분석하기 위해, 부호가 있는 네트워크 임베딩 (signed network embedding, 이하 SNE) 문제에 대한 관심이 급증하고 있다. 특히, 최근 들어 그래프 합성곱 네트워크 기술을 기반으로 하는 SNE 방법들에 대한 연구가 활발히 수행되어 오고 있다. 본 논문에서는, 부호가 있는 네트워크의 희소성 정도가 기존 SNE 방법들의 성능에 어떻게 영향을 미치는 지에 대해 분석하고자 한다. 4 개의 실세계 데이터 집합들을 이용한 실험을 통해, 우리는 기존 방법들의 부호 예측 정확도가 희소한 네트워크들에서는 상당히 감소하는 것을 확인하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.801-809
• /
• 2007

LDPC Low Density Parity Check) code, which is an error correcting code determined to be applied to the 4th generation mobile communication systems, requires a heavy computational complexity due to iterative decodings to achieve a high BER performance. This paper proposes an algorithm to reduce the number of decoding iterations to increase performance of the decoder in decoding latency and power consumption. Measuring changes between the current decoded LLR values and previous ones, the proposed algorithm predicts directions of the value changes. Based on the prediction, the algorithm inverts the sign bits of the LLR values to speed up convergence, which means parity check equation is satisfied. Simulation results show that the number of iterations has been reduced by about 33% without BER performance degradation in the proposed decoder, and the power consumption has also been decreased in proportional to the amount of the reduced decoding iterations.