• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.10-12
• /
• 2003

Recommender systems help consumers to find the useful products from the overloaded information. Researchers have developed content-based recommenders, collaborative recommenders, and a few hybrid systems. In this research, we extend the classic collaborative recommenders by clustering method to form a hybrid recommender system. Using the clustering method, we can recommend the products based on not only the user ratings but also other useful information from user profiles or attributes of items. Through our experiments on well-known MovieLens data set, we found that the information provided by the attributes of item on the item-based collaborative filter shows advantage over the information provided by user profiles on the user-based collaborative filter.

• Science of Emotion and Sensibility
• /
• v.7 no.4
• /
• pp.57-65
• /
• 2004

In this paper, we present a hybrid approach which incorporates color, texture and shape in content-based image retrieval. Colors in each image are clustered into a small number of representative colors. The feature descriptor consists of the representative colors and their percentages in the image. A similarity measure similar to the cumulative color histogram distance measure is defined for this descriptor. The co-occurrence matrix as a statistical method is used for texture analysis. An optimal set of five statistical functions are extracted from the co-occurrence matrix of each image, in order to render the feature vector for eachimage maximally informative. The edge information captured within edge histograms is extracted after a pre-processing phase that performs color transformation, quantization, and filtering. The features where thus extracted and stored within feature vectors and were later compared with an intersection-based method. The content-based retrieval system is tested to be effective in terms of retrieval and scalability through experimental results and precision-recall analysis.

• Journal of Information Technology Services
• /
• v.2 no.2
• /
• pp.53-62
• /
• 2003

Current P2P (Peer-to-Peer) applications have the limited functions such as file search and transfer between peers and have the limitations such as trust problem on search results, copyright problem, and profitable business model problem. For a P2P application to be used as a business platform for the distribution of various multimedia contents, this paper proposes an extended P2P application architecture and its prototype system including distributed collaborative filtering, automated price negotiation system, and payment mechanism.

• International journal of advanced smart convergence
• /
• v.10 no.1
• /
• pp.62-74
• /
• 2021

We compare Over-the-Tops (OTTs), Netflix and Amazon Prime Video (APV) with five success factors of innovation. Firstly, Netflix offers better personalized service than APV, because APV has collaborative filtering algorithms to recommend safe bets, not the customers really want. Secondly, APV' user interface is undercooked to lock the members in, even if it has more content and better price offer than Netflix retaining its loyal customers despite the price increase. Thirdly, Netflix has simple subscription model with three tiering, but APV has complicated pricing model having annual and monthly, APV and Prime Video (AV) app, Amazon subscription and extra payment of Amazon Prime Channels (APCs). Fourthly, Amazon has fewer partnership than Netflix especially when it comes to local TV series. Instead, Amazon has live TV channel collaboration including sports content. Lastly, both have strategic and operational agility in their organization well.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.13-34
• /
• 2012

The Paper Explores The Problem Of Recommending Talks To Attend At International Research Conferences. When Researchers Participate In Conferences, Finding Interesting Talks To Attend Is A Real Challenge. Given That Several Presentation Sessions And Social Activities Are Typically Held At A Time, And There Is Little Time To Analyze All Alternatives, It Is Easy To Miss Important Talks. In Addition, Compared With Recommendations Of Products Such As Movies, Books, Music, Etc. The Recipients Of Talk Recommendations (i.e. Conference Attendees) Already Formed Their Own Research Community On The Center Of The Conference Topics. Hence, Recommending Conference Talks Contains Highly Social Context. This Study Suggests That This Domain Would Be Suitable For Social Network-Based Recommendations. In Order To Find Out The Most Effective Recommendation Approach, Three Sources Of Information Were Explored For Talk Recommendation-Whateach Talk Is About (Content), Who Scheduled The Talks (Collaborative), And How The Users Are Connected Socially (Social). Using These Three Sources Of Information, This Paper Examined Several Direct And Hybrid Recommendation Algorithms To Help Users Find Interesting Talks More Easily. Using A Dataset Of A Conference Scheduling System, Conference Navigator, Multiple Approaches Ranging From Classic Content-Based And Collaborative Filtering Recommendations To Social Network-Based Recommendations Were Compared. As The Result, For Cold-Start Users Who Have Insufficient Number Of Items To Express Their Preferences, The Recommendations Based On Their Social Networks Generated The Best Suggestions.

• Journal of Information Management
• /
• v.41 no.4
• /
• pp.227-249
• /
• 2010

Scholarly information has increased tremendously according to the development of IT, especially the Internet. However, simultaneously, people have to spend more time and exert more effort because of information overload. There have been many research efforts in the field of expert systems, data mining, and information retrieval, concerning a system that recommends user-expected information items through presumption. Recently, the hybrid system combining a content-based recommendation system and collaborative filtering or combining recommendation systems in other domains has been developed. In this paper we resolved the problem of the current recommendation system and suggested a new system combining collaborative filtering and Naive Bayes Classification. In this way, we resolved the over-specialization problem through collaborative filtering and lack of assessment information or recommendation of new contents through Naive Bayes Classification. For verification, we applied the new model in NDSL's paper service of KISTI, especially papers from journals about Sitology and Electronics, and witnessed high satisfaction from 4 experimental participants.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.12
• /
• pp.4568-4587
• /
• 2014

Authentication of videos and images based on the content is becoming an important problem in information security. Unfortunately, previous studies lack the consideration of Kerckhoffs's principle in order to achieve this (i.e., a cryptosystem should be secure even if everything about the system, except the key, is public knowledge). In this paper, a solution to the problem of finding a relationship between a frame's index and its content is proposed based on the creative utilization of a robust manifold feature. The proposed solution is based on a novel semi-fragile watermarking scheme for H.264/AVC video content authentication. At first, the input I-frame is partitioned for feature extraction and watermark embedding. This is followed by the temporal feature extraction using the Isometric Mapping algorithm. The frame index is included in the feature to produce the temporal watermark. In order to improve security, the spatial watermark will be encrypted together with the temporal watermark. Finally, the resultant watermark is embedded into the Discrete Cosine Transform coefficients in the diagonal positions. At the receiver side, after watermark extraction and decryption, temporal tampering is detected through a mismatch between the frame index extracted from the temporal watermark and the observed frame index. Next, the feature is regenerate through temporal feature regeneration, and compared with the extracted feature. It is judged through the comparison whether the extracted temporal watermark is similar to that of the original watermarked video. Additionally, for spatial authentication, the tampered areas are located via the comparison between extracted and regenerated spatial features. Experimental results show that the proposed method is sensitive to intentional malicious attacks and modifications, whereas it is robust to legitimate manipulations, such as certain level of lossy compression, channel noise, Gaussian filtering and brightness adjustment. Through a comparison between the extracted frame index and the current frame index, the temporal tempering is identified. With the proposed scheme, a solution to the Kerckhoffs's principle problem is specified.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.12
• /
• pp.1516-1528
• /
• 1999

월드 와이드 웹(World Wide Web)에 존재하는 음란성 유해 정보는 많은 국가에서 사회적인 문제를 일으키고 있다. 그러나 현재 음란성 유해 정보로부터 미성년자를 보호하는 실효성 있는 방법은 유해 정보 접근 차단 프로그램을 사용하는 방법뿐이다. 유해 정보 접근 차단 프로그램은 기본적으로 음란성 유해 정보를 포함한 유해 정보 주소 목록을 기반으로 사용자의 유해 정보에 대한 접근을 차단하는 방식으로 동작한다.그런데 대규모 유해 정보 주소 목록의 확보를 위해서는 월드 와이드 웹으로부터 음란성 유해 정보를 자동 색출하는 인터넷 정보 검색 시스템의 일종인 음란성 유해 정보 색출 시스템이 필요하다. 그런데 음란성 유해 정보 색출 시스템은 그 대상이 사람이 아닌 유해 정보 접근 차단 프로그램이기 때문에 일반 인터넷 정보 검색 시스템과는 달리, 대단히 높은 검색 정확성을 유지해야 하고, 유해 정보 접근 차단 프로그램에서 관리가 용이한 검색 목록을 생성해야 하는 요구 사항을 가진다.본 논문에서는 기존 인터넷 정보 검색 모델이 "문헌"에 대한 잘못된 가정 때문에 위 요구사항을 만족시키지 못하고 있음을 지적하고, 월드 와이드 웹 상의 문헌에 대한 새로운 정의와 이를 기반으로 위의 요구사항을 만족하는 검색 모델인 페이지 그룹 검색 모델을 제안한다. 또한 다양한 실험과 분석을 통해 제안하는 모델이 기존 인터넷 정보 검색 모델보다 높은 정확성과 빠른 검색 속도, 그리고 유해 정보 접근 차단 프로그램에서의 관리가 용이한 검색 목록을 생성함을 보인다.Abstract Illegal and Harmful Content on the Internet, especially content for adults causes a social problem in many countries. To protect children from harmful content, A filtering software, which blocks user's access to harmful content based on a blocking list, and harmful content search system, which is a special purpose internet search system to generate the blocking list, are necessary. We found that current internet search models do not satisfy the requirements of the harmful content search system: high accuracy in document analysis, fast search time, and low overhead in the filtering software.In this paper we point out these problems are caused by a mistake in a document definition of the current internet models and propose a new internet search model, Page Group Search Model. This model considers a document as a set of pages that are made for one subject. We suggest a Group Construction algorithm and a Group Evaluation algorithm. And we perform experiments to prove that Page Group Search Model satisfies the requirements.uirements.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.1049-1061
• /
• 2018

As mobile devices such as smartphones and tablet PCs become more popular, users are becoming accustomed to consuming a massive amount of multimedia content every day without time or space limitations. From the industry, the need for user satisfaction investigation has consequently emerged. Conventional methods to investigate user satisfaction usually employ user feedback surveys or interviews, which are considered manual, subjective, and inefficient. Therefore, the authors focus on a more objective method of investigating users' brainwaves to measure how much they enjoy their content. Particularly for multimedia content, it is natural that users will be immersed in the played content if they are satisfied with it. In this paper, the authors propose a method of using a portable and dry electroencephalogram (EEG) sensor device to overcome the limitations of the existing conventional methods and to further advance existing EEG-based studies. The proposed method uses a portable EEG sensor device that has a small, dry (i.e., not wet or adhesive), and simple sensor using a single channel, because the authors assume mobile device environments where users consider the features of portability and usability to be important. This paper presents how to measure attention, gauge and compute a score of user's content immersion level after addressing some technical details related to adopting the portable EEG sensor device. Lastly, via an experiment, the authors verified a meaningful correlation between the computed scores and the actual user satisfaction scores.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.367-370
• /
• 2005

This paper proposes a novel method for content-based watermarking based on feature points of an image. At each feature point, watermark is embedded after affine normalization according to the local characteristic scale and orientation. The characteristic scale is the scale at which the normalized scale-space representation of an image attains a maximum value, and the characteristic orientation is the angle of the principal axis of an image. By binding watermarking with the local characteristics of an image, resilience against affine transformations can be obtained. Experimental results show that the proposed method is robust against various image processing steps including affine transformations, cropping, filtering, and JPEG compression.