• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3197-3218
• /
• 2012

Compared with traditional itinerary planning, intention-oriented itinerary recommendations can provide more flexible activity planning without requiring the user's predetermined destinations and is especially helpful for those in unfamiliar environments. The rank and classification of points of interest (POI) from location-based social networks (LBSN) are used to indicate different user intentions. The mining of vehicles' physical trajectories can provide exact civil traffic information for path planning. This paper proposes a POI category-based itinerary recommendation framework combining physical trajectories with LBSN. Specifically, a Voronoi graph-based GPS trajectory analysis method is utilized to build traffic information networks, and an ant colony algorithm for multi-object optimization is implemented to locate the most appropriate itineraries. We conduct experiments on datasets from the Foursquare and GeoLife projects. A test of users' satisfaction with the recommended items is also performed. Our results show that the satisfaction level reaches an average of 80%.

• Language and Information
• /
• v.6 no.1
• /
• pp.91-103
• /
• 2002

The temporal structure of events on the discourse level has long been of great interest in both theoretical and computational linguistics. In this paper, we offer a unified approach to the temporal relationships related to a hierarchical discourse structure. We apply the method of pronoun resolution to the interpretation of tense. It is based on an analysis within the framework of the controlled information packaging theory. A unique aspect of our account is that temporal interpretation across discourse segments in global discourse is subject to the same principles as the interpretation of global anaphora, and that there is thus no need to postulate independent principles to account for the discourse behaviour of tense. In this way, we can neatly explain the general view that tense parallels the anaphoric nature of pronouns.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.441-452
• /
• 2021

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task's similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.

• Asia pacific journal of information systems
• /
• v.28 no.3
• /
• pp.183-203
• /
• 2018

In the era of Web 2.0, social media advertising can simultaneously stimulate consumers' brand purchase intention and brand information sharing intention. Product sales and brand information diffusion are equally important for a company that conducts advertising. This study investigates how features of brand content influence social media advertising effectiveness by integrating the stimulus-organism-response model and classic advertising effectiveness models. An analysis of 267 survey questionnaires shows that brand content-related cues, including perceived uniqueness, perceived vividness, and perceived interactivity have significant effects on consumers' affective and cognitive involvement, which then affect their attitude toward brand content. As a result, the consumers' attitude toward the brand and their brand purchase intention, as well as their brand content sharing intention, are positively affected by attitude toward brand content. This study contributes to a better understanding of how social advertising works, which suggests that managers should effectively use social media to conduct advertising.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.3
• /
• pp.695-706
• /
• 2018

In recent years, industrial convergence centered on ICBM (internet of things (IoT), cloud, big data, mobile) has been experiencing rapid development in various fields such as agriculture and the financial industry. In order to prepare for cyber threats, one of the biggest problems facing the convergence industry in the future, the development of the industry must proceed in tandem with a framework of information security. In this study, we analyze the details of the current industrial development policy and related information protection policies using cross impact analysis and present policy priorities through the expert questionnaire. The aim of the study was to clarify the priorities and interrelationships within information security policy as a first step in suggesting effective policy direction. As a result, all six information security policy tasks derived from this study belong to key drivers. Considering the importance of policies, policies such as improving the constitution of the security industry and strengthening of support, training of information protection talent, and investing in the information security industry need to be implemented relatively first.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.6
• /
• pp.1377-1383
• /
• 2015

As the cloud services users' increase, there are important files created by individual in cloud storage. Thus, investigation of cloud artifact should be conducted. There are two methods of analyzing cloud service, one is that investigates cloud server provider (CSP), and another is that investigates client. In this paper, we presents an automated framework to detect the altered artifact and developes a tool that detects the cloud artifact. We also developed Cloud Artifact Tool that can investigate client computer. Cloud Artifact Tool provides feature of collection and analysis for the services such as Google Drive, Dropbox, Evernote, NDrive, DaumCloud, Ucloud, LG Cloud, T Cloud and iCloud.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.3
• /
• pp.263-287
• /
• 2006

With the rapid and broad changes of information media and information environment the traditional libraries have been evolving into the digital libraries. An analysis for the Planning and realization of the electronic resource management system was carried out to establish the various electronic resources in the digital library, the first in Korea. The study targeted from electronic journals, web-based databases, e-books, and to open access resources. The focus of the analysis lies in the Providing practical integrated electronic resource management for digital librarian based on the framework of effective Electronic Resource Management Initiative(ERMI) of Digital Library Federation(DLF) with network and electronic resource description. The analyses included life-cycle, subscription models, coverages. types of information provider for electronic resources. and system organization for implementation of electronic resource management system.

• Journal of the Korean Society for information Management
• /
• v.26 no.4
• /
• pp.277-298
• /
• 2009

This study discussed on production, procedures of collection, accessibility, copyright of archival records for designing oral history archive information system, and aimed to suggest practical standards by developing guidelines for evaluation and building of web oral history archives. For this, based on evaluation framework, guidelines for evaluation designed by researchers were applied to five domestic and foreign web oral history archives as case study analysis. Base on the results of the analysis, some possible suggestions were made for building successful web oral history archive information system in Korea.

• Spatial Information Research
• /
• v.22 no.2
• /
• pp.45-52
• /
• 2014

In recent years, The importance of the river pollution management has increased and central and local governments are making constant effort to work out river pollution problems. Accordingly, this paper is to take a closer look at applications of spatial data and river pollution information(aerial photograph, parcel information, pollution source, GPS data et al.). More exactly, the purpose of the present paper is to offer an applications of spatial information for development of the river pollution management system. In order to provide a framework for more detailed consideration of the quantitative analysis of river pollution source and management plan by apply GPS and GIS. For that reason, this paper was to build pollution management system of river by spatial analysis. It is to be hoped that this paper will contribute to establish the management policy for urban stream pollution source preservation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.