• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.677-687
• /
• 2022

We propose a detection algorithm based on tree-structured convolutional neural networks (TsCNNs) that finds pornography, propaganda, or other inappropriate content on a social media network. The algorithm sequentially applies the typical convolutional neural network (CNN) algorithm in a tree-like structure to minimize classification errors in similar classes, and thus improves accuracy. We implemented the detection system and conducted experiments on a data set comprised of 6 ordinary classes and 11 inappropriate classes collected from the Korean military social network. Each model of the proposed algorithm was trained, and the performance was then evaluated according to the images and videos identified. Experimental results with 20,005 new images showed that the overall accuracy in image identification achieved a high-performance level of 99.51%, and the effectiveness of the algorithm reduced identification errors by the typical CNN algorithm by 64.87 %. By reducing false alarms in video identification from the domain, the TsCNNs achieved optimal performance of 98.11% when using 10 minutes frame-sampling intervals. This indicates that classification through proper sampling contributes to the reduction of computational burden and false alarms.

• Journal of Information Science Theory and Practice
• /
• v.11 no.3
• /
• pp.1-15
• /
• 2023

The present study examines the impact of value co-creation on satisfaction and intention to adopt of e-resources among users. Four components of the DART model have been adopted to describe value co-creation. These components are dialogue, access, risk-assessment, and transparency. Ph.D. scholars and faculty members from National Capital Region, India, were requested to respond on a five-point Likert scale. A total of 220 responses were collected with the help of a structured questionnaire from respondents of the top 50 business schools according to National Institute Ranking Framework. These responses have been analysed by means of structured equation modelling on Adanco 2.2 software. Findings of the study reported the insignificant impact of access and risk-assessment, and positive impact of dialogue and transparency on satisfaction. Further, satisfaction has been identified, creating significant impact on adoption of e-resources. Such findings reflect the real picture of customer experience with respect to their role in co-creation of e-resources. Respondents have conveyed their dissatisfaction with the co-creation process of e-resources, as companies do not provide all the information and access to their customers beforehand. Consequently, customers fail to make informed decisions and also find themselves unable to show trust in the service providers of e-resources.

• International Journal of Knowledge Content Development & Technology
• /
• v.14 no.4
• /
• pp.101-111
• /
• 2024

Multilingual Knowledge Graphs (MKGs) have emerged as a crucial component in various natural language processing tasks, enabling efficient representation and utilization of structured knowledge across multiple languages. One can get data, information, and knowledge from various sectors, like libraries, archives, institutional repositories, etc. Variable quality of metadata, multilingualism, and semantic diversity make it a challenge to create a digital library and multilingual search facility. To accept these challenges, there is a need to design a framework to integrate various structured and unstructured data sources for integration, unification, and sharing databases. These are controlled using linked data and semantic web approaches. In future, multilingual knowledge graph overcomes all the linguistic nuances, technical barriers like semantic interoperability, data harmonization etc and enhance cooperation and collaboration throughout the world. Through a comprehensive analysis of the current state-of-the-art techniques and ongoing research efforts, this paper aims to offer insights into the future directions and potential advancements in the field of Multilingual Knowledge Graphs. This paper deals with a multilingual knowledge graph and how to build up a multilingual knowledge graph. It also focuses on the various challenges and opportunities for designing multilingual knowledge graphs.

• The KIPS Transactions:PartC
• /
• v.13C no.1 s.104
• /
• pp.129-136
• /
• 2006

Information Retrieval System aims towards providing fast and accurate information to users. However, current search systems are based on plain svntactic analysis which makes it difficult for the user to find the exact required information. This paper proposes the SW-IRS (Semantic Web-based Information Retrieval System) using an Ontology Server. The proposed system is purposed to maximize efficiency and accuracy of information retrieval of unstructured and semi-structured documents by using an agent-based automatic classification technology and semantic web based information retrieval methods. For interoperability and easy integration, RDF based repository system is supported, and the newly developed ranking algorithm was applied to rank search results and provide more accurate and reliable information. Finally, a new ranking algorithm is suggested to be used to evaluate performance and verify the efficiency and accuracy of the proposed retrieval system.

• Spatial Information Research
• /
• v.22 no.6
• /
• pp.55-65
• /
• 2014

By combining the role of current GIS technology and design behaviors from the cognitive perspective, spatial conceptualization can be extended efficiently and creatively for ill-structured problems. This study elaborates the model of a conceptualization-oriented SDSS(Spatial Decision Support System) for a landscape design problem. Current information-oriented GIS technology plays a minor role in planning and design. The three attributes in planning and design problems describe how the deficiencies of current GIS technology can be seen as a failure of the technology. These are summarized: (1) Information Explosion/Information Ignorance (2) Dilemma of Rigor and Relevance (3) Ill-structured Nature of planning and Design. In order to implement the conceptualization idea in the current GIS environment, it will be necessary to shift from traditional, information-oriented GISs to conceptualization-oriented SDSSs. The conceptualization-oriented SDSS model reflects the key elements of six important theories and techniques. The six useful theories and techniques are as follows; (1) Human Information Processing (2) Tool/Theory Interaction (3) The Sciences of the Artificial and Epistemology of Practice (4) Decision Support Systems (DSSs) (5) Human-Computer Interaction (HCI) (6) Creative Thinking. The future conceptualization-oriented SDSS can provide capabilities for planners and designers to figure out some "hidden organizations" in spatial planning and design, and develop new ideas through its conceptualization capability. The facilitation of conceptualization has been demonstrated by presenting three key ideas for the framework of the SDSS model: (1) bubble-oriented design support system (2) prototypes as an extension of semantic memory, and (3) scripts as an extension of episodic memory in a cognitive pschology perspective. The three ideas can provide a direction for the future GIS technology in planning and design.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.657-668
• /
• 2001

It is difficult that web documents are classified with exact user intention because existing document classification systems are based on word frequency number using single keyword. To improve this defect, first, we use keyword, a query, domain knowledge. Like explanation based learning, first, query is analyzed with knowledge based information and then structured user intention information is extracted. We use this intention tree in the course of existing word frequency number based document classification as user information and constraints. Thus, we can classify web documents with more exact user intention. In classifying document, structured user intention information is helpful to keep more documents and information which can be lost in the system using single keyword information. Our hybrid approach integrating user intention information with existing statistics and probability method is more efficient to decide direction and range of document category than existing word frequency approach.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.151-155
• /
• 2005

Recently, systems biology has been increasingly applied to gain insights into the complexity of living organisms. Many inaccessible biological information and hidden evidences fur example flux distribution of the metabolites are simply revealed by investigation of artificial cell behaviors. Most bio-models are models of single cell organisms that cannot handle the multi-cellular organisms like plants. Herein, a structured and multi-cellular model of potato was developed to comprehend the root starch biosynthesis. On the basis of simplest plant cell biology, a potato structured model on the platform of Berkley Madonna was divided into three parts: photosynthetic (leaf), non-photosynthetic (tuber) and transportation (phloem) cells. The model of starch biosynthesis begins with the fixation of CO$_2$ from atmosphere to the Calvin cycle. Passing through a series of reactions, triose phosphate from Calvin cycle is converted to sucrose which is transported to sink cells and is eventually formed the amylose and amylopectin (starch constituents). After validating the model with data from a number of literatures, the results show that the structured model is a good representative of the studied system. The result of triose phosphate (DHAP and GAP) elevation due to lessening the aldolase activity is an illustration of the validation. Furthermore, the representative model was used to gain more understanding of starch production process such as the effect of CO$_2$ uptake on qualitative and quantitative aspects of starch biosynthesis.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.2
• /
• pp.77-82
• /
• 2015

Big Data technology has been attracted much attention in aspect of fast data processing. Research of practicing Big Data technology is also ongoing to process large-scale structured data much faster in Relatioinal Database(RDB). Although there are lots of studies about measuring analyzing performance, studies about structured data loading performance, prior step of analyzing, is very rare. Thus, in this study, structured data in RDB is tested the performance that loads distributed processing platform Hadoop using Apache sqoop. Also in order to analyze the influence factors of data loading, it is tested repeatedly with different options of data loading and compared with data loading performance among RDB based servers. Although data loading performance of Apache Sqoop in test environment was low, but in large-scale Hadoop cluster environment we can expect much better performance because of getting more hardware resources. It is expected to be based on study improving data loading performance and whole steps of performance analyzing structured data in Hadoop Platform.

• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.297-306
• /
• 2002

This paper handles the design and implementation of the system for transforming the XML document bated on XML Schema being different in syntax but similar in logic, with using structured differences analysis. In the system, the merge data is generated from the source and destination documents by utilizing data registry and structured differences analysis, and then XML document is generated from the generated merge data. The XML document transformation system is designed that transformation process to the present application system from the different application system gains advantage in the aspect of time, cost, and reliability. The implementation environment of the system is that it is run on IBM compatible PC and it is developed using the software of visual basic 6.0 with the Platform of Windows 2000.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.35-39
• /
• 2011

Error correcting codes with easy variability in code rate and codeword length in addition to powerful error correcting capability are required for present and future mobile multimedia communication systems. And low complexity is also needed for the compact mobile terminals. In general, the irregular random LDPC(low-density parity-check) code is known to have the superior performance among various LDPC codes. But it has inefficiency since the various parity check matrices for various services should be stored for encoding and decoding. The structured LDPC codes which can easily provide various rates and lengths are studied recently. Therefore, the flexibility, memory size, and error performance of various structured LDPC codes are compared and analyzed in this paper. And the most appropriate structured LDPC code is also suggested.