• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.41-47
• /
• 2024

When there were disparities in performance between models trained in the time and frequency domains, even after conducting an ensemble, we observed that the performance of the ensemble was compromised due to imbalances in the individual model performances. Therefore, this paper proposes a leakage detection technique to enhance the accuracy of pipeline leakage detection through a step-wise learning approach that extracts features from both the time and frequency domains and integrates them. This method involves a two-step learning process. In the Stage 1, independent model training is conducted in the time and frequency domains to effectively extract crucial features from the provided data in each domain. In Stage 2, the pre-trained models were utilized by removing their respective classifiers. Subsequently, the features from both domains were fused, and a new classifier was added for retraining. The proposed transfer learning-based feature fusion technique in this paper performs model training by integrating features extracted from the time and frequency domains. This integration exploits the complementary nature of features from both domains, allowing the model to leverage diverse information. As a result, it achieved a high accuracy of 99.88%, demonstrating outstanding performance in pipeline leakage detection.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.77-86
• /
• 2022

The Republic of Korea is a country in which coastal surveillance is an imperative national task as it is surrounded by seas on three sides under the confrontation between South and North Korea. However, due to Defense Reform 2.0, the number of R/D (Radar) operating personnel has decreased, and the period of service has also been shortened. Moreover, there is always a possibility that a human error will occur. This paper presents specific guidelines for developing an AI learning model for the intelligent coastal surveillance system. We present a three-step strategy to realize the guidelines. The first stage is a typical stage of building an AI learning model, including data collection, storage, filtering, purification, and data transformation. In the second stage, R/D signal analysis is first performed. Subsequently, AI learning model development for classifying real and false images, coastal area analysis, and vulnerable area/time analysis are performed. In the final stage, validation, visualization, and demonstration of the AI learning model are performed. Through this research, the first achievement of making the existing weapon system intelligent by applying the application of AI technology was achieved.

• Journal of Internet Computing and Services
• /
• v.4 no.5
• /
• pp.69-76
• /
• 2003

In this paper we show a new learning algorithm for pattern classification. This algorithm considered a scheme to find a solution to a problem of incremental learning algorithm when the structure becomes too complex by noise patterns included in learning data set. Our approach for this problem uses a pruning method which terminates the learning process with a predefined criterion. In this process, an iterative model with 3 layer feedforward structure is derived from the incremental model by an appropriate manipulations. Notice that this network structure is not full-connected between upper and lower layers. To verify the effectiveness of pruning method, this network is retrained by EBP. From this results, we can find out that the proposed algorithm is effective, as an aspect of a system performence and the node number included in network structure.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.445-448
• /
• 2009

DSS 응용들의 대용량 집계 데이터 집중 시스템에서는 효율적이고 즉각적인 의사결정 지원을 위한 근사 질의응답의 연구가 필요하다. 따라서 본 연구에서는 FCM 클러스터링 기법과 ANFIS을 이용한 기법을 제안한다. 제안된 기법은 다차원 데이터 큐브의 데이터 특성을 가지며 질의에 대한 근사적인 응답을 제공할 수 있는 모델을 생성한다. 제안된 기법을 통해 학습된 모델은 기존의 기법보다 근사 질의응답의 정확성이 향상되었음을 비교 실험을 통하여 확인한다. 따라서 제안된 기법은 기존의 기법보다 저장 공간과 시간을 줄일 수 있으며 또한 근사 응답의 정확도를 향상시킬 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.376-378
• /
• 2022

Artificial intelligence technology is widely used in various fields such as artificial intelligence speakers, artificial intelligence chatbots, and autonomous vehicles. Among these AI application fields, the image processing field shows various uses such as detecting objects or recognizing objects using artificial intelligence. In this paper, data synthesized by a virtual human is used as a method to analyze images taken in a specific space.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.53-62
• /
• 2010

This paper introduces a classification algorithm which can be applied to a learning problem with incomplete data sets, missing variable values or a class value. This algorithm uses a data expansion method which utilizes weighted values and probability techniques. It operates by extending a classifier which are considered to be in the optimal projection plane based on Fisher's formula. To do this, some equations are derived from the procedure to be applied to the data expansion. To evaluate the performance of the proposed algorithm, results of different measurements are iteratively compared by choosing one variable in the data set and then modifying the rate of missing and non-missing values in this selected variable. And objective evaluation of data sets can be achieved by comparing, the result of a data set with non-missing variable with that of C4.5 which is a known knowledge acquisition tool in machine learning.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.53-60
• /
• 2008

This paper proposes a new multiobjective optimization method for discriminative training of hidden Markov models (HMMs) used as the recognizer for automatic lipreading. While the conventional Baum-Welch algorithm for training HMMs aims at maximizing the probability of the data of a class from the corresponding HMM, we define a new training criterion composed of two minimization objectives and develop a global optimization method of the criterion based on simulated annealing. The result of a speaker-dependent recognition experiment shows that the proposed method improves performance by the relative error reduction rate of about 8% in comparison to the Baum-Welch algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.358-360
• /
• 2001

본 논문에서는 의미분석을 위해서 구문관계와 의미관계를 자동으로 사상하는 규칙을 구축한다. 5 만개의 패턴을 수작업으로 사상해서 학습데이터로 만들고 이의 분석을 통해 규칙을 구축했다. 규칙에서는 의미역 결정을 위해서 가도까와 시소러스를 이용하는데, 본 논문에서는 한일 기계번역사전을 이용하여 추출한 구문 패턴을 대상으로 실험한 결과, 정확률 90%, 적용율 93.5%를 얻었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.268-273
• /
• 2008

의견(Opinion) 분석은 도전적인 분야로 언어 자원 구축, 문서의 Sentiment 분류, 문장 내의 의견 어구 추출 등의 다양한 문제를 다룬다. 이 중 의견 어구 추출문제는 단순히 문장이나 문서 단위로 분류하는 수준을 뛰어 넘는 문장 내 의견 어구를 추출하는 문제로 최근 많은 관심을 받고 있는 연구 주제이다. 그러나 의견 어구 추출에 대한 기존 연구는 문장 내 의견 어구부분이 태깅(tagging)된 학습 데이터와 의견 어휘 자원을 이용한 지도(Supervised)학습을 이용한 접근이 대부분으로 실제 적용 상의 한계를 갖는다. 본 논문은 문장 내 의견 어구 부분이 태깅된 학습 데이터와 의견 어휘 자원이 없는 환경에서도 문장단위의 극성 정보를 이용하여 의견 어구를 추출하는 부분 지도(Semi-Supervised)학습 장법을 제안한다. 본 논문의 방법은 Baseline에 비하여 정확률(Precision)은 33%, F-Measure는 14% 가량 높은 성능을 냈다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.666-668
• /
• 2018

최근 반려동물을 키우는 가구 수의 증가와 함께, 반려묘에 대한 관심도 상당히 증가하고 있다. 특히 반려인은 반려묘와의 원활한 의사소통과 교감을 바라지만 반려묘의 세세한 감정 상태를 24시간 내내 파악하는 것은 어려운 일이다. 본 논문에서는 반려묘의 울음소리에 많은 감정 및 상태 정보가 담겨있는 것에 착안하여, 반려묘의 울음소리를 기반으로 감정을 분류하는 시스템을 제안한다. 제안된 시스템은 먼저, 이미 수집된 소리 데이터를 데이터 증폭 방법론을 이용하여 데이터를 확장 한 후, 해당 소리들의 멜 스펙트로그램 정보를 추출한다. 이를 시계열 정보 처리에 효과적인 LSTM에 적용하여 반려묘의 감정 상황을 식별할 수 있도록 학습을 수행한다. 실험 결과, 반려묘의 감정 상태 분류의 가능성을 확인하였다.