• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.531-536
• /
• 2002

In this paper, we have applied Genetic Algorithms(GAs) to Intrusion Detection System(TDS), and then proposed and simulated the misuse detection model firstly. We have implemented with the KBD contest data, and tried to simulated in the same environment. In the experiment, the set of record is regarded as a chromosome, and GAs are used to produce the intrusion patterns. That is, the intrusion rules are generated. We have concentrated on the simulation and analysis of classification among the Data Mining techniques and then the intrusion patterns are produced. The generated rules are represented by intrusion data and classified between abnormal and normal users. The different rules are generated separately from three models "Time Based Traffic Model", "Host Based Traffic Model", and "Content Model". The proposed system has generated the update and adaptive rules automatically and continuously on the misuse detection method which is difficult to update the rule generation. The generated rules are experimented on 430M test data and almost 94.3% of detection rate is shown.3% of detection rate is shown.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.1-14
• /
• 2007

Character images for the background screen of cell phones are one of the fast growing sectors of the mobile content market. However, character image buyers currently experience tremendous difficulties in searching for desired images due to the awkward image search process. Content-based image retrieval (CBIR) widely used for image retrieval could be a good candidate as a solution to this problem, but it needs to overcome the limitation of the mobile Internet environment where an initial query set (IQS) cannot be easily provided as in the PC-based environment. We propose a new approach, IQS-AutoGen, which automatically generates an initial query set for CBIR on the mobile Internet. The approach applies the collaborative filtering (CF), a well-known recommendation technique, to the CBIR process by using users' preference information collected during the relevance feedback process of CBIR. The results of the experiment using a PC-based prototype system show that the proposed approach successfully satisfies the initial query requirement of CBIR in the mobile Internet environment, thereby outperforming the current image search process on the mobile Internet.

• Journal of Broadcast Engineering
• /
• v.2 no.2
• /
• pp.146-155
• /
• 1997

The new video coding standard Iv1PEG-4 is enabling content-based functionalities. It requires a prior decomposition of sequences into video object planes (VOP's) so that each VOP represents moving objets. This paper addresses an image segmentation method for separating moving objects from still background (non-moving area) in video sequences using a statistical hypothesis test. In the proposed method. three consecutive image frames are exploited and a hypothesis testing is performed by comparing two means from two consecutive difference images. which results in a T-test. This hypothesis test yields a change detection mask that indicates moving areas (foreground) and non-moving areas (background), Moreover. an effective method for extracting

• Journal of the Korean Society for information Management
• /
• v.29 no.4
• /
• pp.191-208
• /
• 2012

Two fundamental aspects of speech summary generation are the extraction of key speech content and the style of presentation of the extracted speech synopses. We first investigated whether acoustic features (speaking rate, pitch pattern, and intensity) are equally important and, if not, which one can be effectively modeled to compute the significance of segments for lecture summarization. As a result, we found that the intensity (that is, difference between max DB and min DB) is the most efficient factor for speech summarization. We evaluated the intensity-based method of using the difference between max-DB and min-DB by comparing it to the keyword-based method in terms of which method produces better speech summaries and of how similar weight values assigned to segments by two methods are. Then, we investigated the way to present speech summaries to the viewers. As such, for speech summarization, we suggested how to extract key segments from a speech video efficiently using acoustic features and then present the extracted segments to the viewers.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.2
• /
• pp.365-370
• /
• 2014

For real-time monitoring of colloidal nanoparticles (NPs) in aqueous media, a light sheet type dark-field microscopy system combined with a microfluidic concentration gradient generator (${\mu}FCGG$-LSDFM) was developed. Various concentrations of colloidal Au NPs were simultaneously generated with the iFCGG and characterized with the LSDFM setup. The number concentrations and hydrodynamic size distributions were measured via particle counting and tracking analysis (PCA and PTA, respectively) approaches. For the 30 nm Au NPs used in this study, the lower detection limit of the LSDFM setup was 3.6 ng/mL, which is about 400 times better than that of optical density measurements under the same ${\mu}FCGG$ system. Additionally, the hydrodynamic diameter distribution of Au NPs was estimated as $39.7{\pm}12.2nm$ with the PTA approach, which agrees well with DLS measurement as well as the manufacturer's specification. We propose this ${\mu}FCGG$-LSDFM setup with features of automatic generation of NP concentration gradient and real-time monitoring of their physicochemical characteristics (e.g., number concentration, and hydrodynamic size distribution) as an important component of future high-throughput screening or high-content analysis platforms of nanotoxicity.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.1-8
• /
• 2021

In online meetings and classes using webcams, the chromakey technique is a very necessary part to produce content. We proposed a technology that enables background synthesis without using a cloth for chromakey. The proposed method consists of three steps: an HSI image conversion step, a step of detecting a region changed from a background, and a step of replacing the background region with a chromakey and applying it. In the input video, the block average image of each frame is calculated, and the difference between the block average image of the background image and the block average image of the input image is used to detect the change area. The developed chromakey effect technology uses a technique of acquiring a background image without an object from a single camera and extracting only an object by distinguishing the moving object and the background. The proposed method is not only capable of processing even if the background has a variety of colors, but also has the seamless processing of the boundary lines of objects.

• Korean Journal of Cognitive Science
• /
• v.34 no.3
• /
• pp.197-226
• /
• 2023

Generative Text Summarization is one of the Natural Language Processing tasks. It generates a short abbreviated summary while preserving the content of the long text. ROUGE is a widely used lexical-overlap based metric for text summarization models in generative summarization benchmarks. Although it shows very high performance, the studies report that 30% of the generated summary and the text are still inconsistent. This paper proposes a methodology for evaluating the performance of the summary model without using the correct summary. AggreFACT is a human-annotated dataset that classifies the types of errors in neural text summarization models. Among all the test candidates, the two cases, generation summary, and when errors occurred throughout the summary showed the highest correlation results. We observed that the proposed evaluation score showed a high correlation with models finetuned with BART and PEGASUS, which is pretrained with a large-scale Transformer structure.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.309-318
• /
• 2005

In order to present wireless Internet users with previously created HTML contents and applications, it is essential to research and develop the technology to efficiently convert HTML documents into documents and further provide a way to edit the WML documents. This paper describes the design and development of a WML converter and WML editor The WML converter can convert HTML pages in real time into WML documents that are suitable for the WAP environment. The WML editor enables creation and modification of WML documents in a WYSIWYG fashion. These tools enable the previous services based on HTML documents to be easily adapted to the wireless environment. The developed WML converter can be installed on a proxy server to support real time conversion of Web contents. It is superior to other converters in terms of the various image formats it supports and the improvements on the conversion of the link and frame tags. Users can continuously browse via links and also view frames. Automatic dividing of large WML documents into WML cards md user defined conversion rules are also supported. The WML editor is also integrated with the converter and provides an integrated WYSIWYG environment for creating, converting and publishing WML documents.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.12
• /
• pp.3052-3062
• /
• 1997

An Information Retrieval (IR) is to retrieve relevant information that satisfies user's information needs. However a major role of IR systems is not just the generation of sets of relevant documents, but to help determine which documents are most likely to be relevant to the given requirements. Various attempts have been made in the recent past to use syntactic analysis methods for the generation of complex construction that are essential for content identification in various automatic text analysis systems. Unfortunately, it is known that methods based on syntactic understanding alone are not sufficiently powerful to Produce complete analyses of arbitrary text samples. In this paper, we present a document ranking method based on two-level ranking. The first level is used to retrieve the documents, and the second level to reorder the retrieved documents. The main keywords used in the first level can be defined as nouns and/or compound nouns that possess good document discrimination powers. The sub-keywords used in the second level can be also defined as adjectives, adverbs, and/or verbs that are not main keywords, and function words. An empirical study was conducted from a Korean encyclopedia with 23,113 entries and 161 Korean natural language queries collected by end users. 850% of the natural language queries contained sub-keywords. The two-level document ranking methods provides significant improvement in retrieval effectiveness over traditional ranking methods.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.28-41
• /
• 2006

Due to the rapid development of multimedia appliances, the increasing amount of multimedia data enforces the development of automatic video analysis techniques. In this paper, a method of ToC generation is proposed for educational video contents. The proposed method consists of two parts: scene segmentation followed by scene annotation. First, video sequence is divided into scenes by the proposed scene segmentation algorithm utilizing the characteristics of educational video. Then each shot in the scene is annotated in terms of scene type, existence of enclosed caption and main speaker of the shot. The ToC generated by the proposed method represents the structure of a video by the hierarchy of scenes and shots and gives description of each scene and shot by extracted features. Hence the generated ToC can help users to perceive the content of a video at a glance and. to access a desired position of a video easily. Also, the generated ToC automatically by the system can be further edited manually for the refinement to effectively reduce the required time achieving more detailed description of the video content. The experimental result showed that the proposed method can generate ToC for educational video with high accuracy.