• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.145-165
• /
• 2006

Information filtering systems, which are designed fur users' needs, do not satisfy user's diverse requests as their filtering accuracy is unstable sometimes. This study suggests an information filtering system based on cognitive brain mapping by simulating the processes of information in human brain. Compared to traditional filtering systems, which use specific words or pattern in their filtering systems, the method suggested in this article uses both key words and relationships among these words. The significance of this study is on simulating information storing processes in human brain by mapping both key words and their relationships among them together. To combine these two methods, this study finds balances in representing two methods by searching optimal weights of each of them.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.323-332
• /
• 2000

인터넷을 등장으로, 끊임없이 늘어나는 정보의 양은 오히려 사용자의 정보 습득을 어렵게 만들었다. 이를 해결하기 위한 방법으로 검색된 정보에 우선 순위를 부여함으로써 사용자가 원하는 정보를 선별할 수 있는 방법이 등장하였다. 하지만, 이는 사용자의 일시적인 질의만을 가지고 정보의 우선 순위를 결정하기 때문에 사용자가 다시 판단해야 하는 부담을 안게 되었다. 이러한 문제점을 해결하기 위해, 본 논문에서는 내용 기반의 정보 검색(Content-Based Information Retrieval) 방법과 더불어 사용자의 기호를 반영하는 사용자 선호도 기반의 정보 여과(Information Filtering) 방법, 그룹 선호도 기반의 협동적 정보 여과(Collaborative Filtering) 방법을 사용하여 사용자의 요구에 선결조건으로 하며, 구축된 선호도는 벡터로써 표현되어 정보와의 유사도(degree of similarity) 계산에 사용된다. 제안된 방법을 실험하기 위해 MFC(Microsoft Foundation Class) 관련 학습 사이트를 구현하여 사용자 등록을 받았다. 이 과정에서 사용자에게 여러 가지 프로파일을 요구하였으며, 변화하는 사용자의 기호를 반영하기 위해 지속적으로 사용자의 행동을 관찰하였다. 이렇게 구축된 사용자 선호도를 바탕으로 제안된 방법을 실험하고 사용자의 feedback을 통해 결과에 대한 평가를 받아, 논문에서 제안된 방법의 타당성을 입증하였다.

• Journal of Information Technology Services
• /
• v.13 no.2
• /
• pp.173-184
• /
• 2014

As social network services has become one of the most successful web-based business, recommendation in social network sites that assist people to choose various products and services is also widely adopted. Collaborative Filtering is one of the most widely adopted recommendation approaches, but recommendation technique that use explicit or implicit social network information from social networks has become proposed in recent research works. In this paper, we reviewed and compared research works about recommendation using social network analysis and collaborative filtering in social network sites. As the results of the analysis, we suggested the trends and implications for future research of recommendation in SNSs. It is expected that graph-based analysis on the semantic social network and systematic comparative analysis on the performances of social filtering and collaborative filtering are required.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.807-813
• /
• 2001

본 논문에서는 기업교육에 있어서 e-Learning을 효과적으로 실현하기 위해 Information Filtering을 제안하고자 한다. 사용자 profile에 기반하여 지식 경영상 시스템을 기업교육에 도입함으로써 정보 검색 시 term space에서 모든 단어를 vector로 나타내어, 사용자 profile과 비교 측정하여 다음 유사한 측정을 통해서 원하는 정보 문서를 사용자에게 제공한다. Information Filtering의 도입으로 사용자의 흥미 변화에 맞춰 다이나믹하게 공급되는 학습 문서속에서 기업을 위한 e-Learning으로 경영성과를 높이는 하나의 전력을 제시한다.

• Journal of Korea Multimedia Society
• /
• v.19 no.10
• /
• pp.1767-1774
• /
• 2016

In this paper, we propose the adaptation filtering for correcting the movement path of the recognized object by the depth information. When we recognize the object by the depth information, the path error should be occurred because of the noises in the depth information. The path error is corrected by appling the lowpass filtering, but the lowpass filtering is not efficient when the changes of the object's movement are rapid. In this paper, we apply the adaptation filtering that it gives weights adaptively as the difference between the predicted location and the measured location. To apply the adaptation filtering, we can see that the proposed method can correct accurately the path error of the radical change from simulation results.

• ETRI Journal
• /
• v.28 no.4
• /
• pp.509-512
• /
• 2006

In a real environment, sound recordings are commonly distorted by channel and background noise, and the performance of audio identification is mainly degraded by them. Recently, Philips introduced a robust and efficient audio fingerprinting scheme applying a differential (high-pass filtering) to the frequency-time sequence of the perceptual filter-bank energies. In practice, however, the robustness of the audio fingerprinting scheme is still important in a real environment. In this letter, we introduce alternatives to the frequency-temporal filtering combination for an extension method of Philips' audio fingerprinting scheme to achieve robustness to channel and background noise under the conditions of a real situation. Our experimental results show that the proposed filtering combination improves noise robustness in audio identification.

• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.101-108
• /
• 2017

The study proposed a system that filters the data that is entered when analyzing big data such as SNS and BLOG. Personal information includes impersonal personal information, but there is also personal information that distinguishes it from personal information, such as religious institution, personal feelings, thoughts, or beliefs. Define these personally identifiable information as sensitive information. In order to prevent this, Article 23 of the Privacy Act has clauses on the collection and utilization of the information. The proposed system structure is divided into two stages, including Big Data Processing Processes and Sensitive Information Filtering Processes, and Big Data processing is analyzed and applied in Big Data collection in four stages. Big Data Processing Processes include data collection and storage, vocabulary analysis and parsing and semantics. Sensitive Information Filtering Processes includes sensitive information questionnaires, establishing sensitive information DB, qualifying information, filtering sensitive information, and reliability analysis. As a result, the number of Big Data performed in the experiment was carried out at 84.13%, until 7553 of 8978 was produced to create the Ontology Generation. There is considerable significan ce to the point that Performing a sensitive information cut phase was carried out by 98%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.516-518
• /
• 2012

본 논문은 Particle Filtering과 계층적인 Boosting 알고리즘을 이용한 다중 객체 추적 기법을 제안한다. Particle Filtering을 이용하여 각 객체를 단일 객체로 추적하고 Boosting 기반의 데이터 연관 알고리즘을 사용하여 영상에서 움직이는 물체들을 추적한다. 본 제안한 알고리즘에서는 객체들의 이동경로 정확한 감지를 위해 Particle Filtering을 통해 각 객체가 움직이는 예측 정보를 이용하고, Boosting 알고리즘을 계측적인 형태로 설계함에 따라 데이터 물체의 추적 정확도를 높일 수 있도록 하였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.333-337
• /
• 2000

성공적인 사이트를 위한 필수적인 요소로 각광받고 있는 collaborative filtering 기술은 정보의 과부하를 줄일 수 있고 고객에 대한 충성도를 높여주는 효과로 인해 많은 사이트에 적용되어 운용되고 있다. 이 논문에서는 collaborative filtering 적용 포기에 발생하는 정보의 부족으로 인한 정확도 저하를 막기 위해 상품간 연관성을 이용한 결측티 예측 방안을 제안한다.