Joonmyun Cho

MovieMine: personalized movie content search by utilizing user comments

User comments are one of the common online resources that reflect users evaluative opinions about multimedia contents. The words used in user comments provide many clues about the users and about what they like or dislike. In this paper, we propose a novel query expansion method that utilizes user comments in order to consider users different preferences in finding movies. We propose a personalized search system, called MovieMine, built upon this proposed method to provide personalized search results by expanding queries on the basis of earlier comments left by the user. Using an actual movie review dataset obtained from a large movie portal, we show that our system produces a significant performance improvement compared to the baseline condition. We expect our approach to be readily applicable to personalized searching of multimedia contents.

Context-Aware Server Framework for Network-based Service Robots

URC (ubiquitous robotic companion) is a new concept for a network-based service robot system. In this paper, we introduce CAMUS (context-aware middleware for URC systems) which is a server framework to support context-aware services for network-based robots. We discuss two major components of CAMUS: CAMUS main server and service agent manager. The communication framework is also proposed to support the communication between robots and CAMUS. We expect that CAMUS will be utilized to develop ubiquitous computing applications for network based service robot, the smart space and the personal assistant software

Multi-document Summarization Exploiting Semantic Analysis Based on Tag Cluster

Multi-document summarization techniques aim to reduce the documents into a small set of words or paragraphs that convey the main meaning of the original documents. Many approaches for multi-document summarization have used probability based methods and machine learning techniques to summarize multiple documents sharing a common topic at the same time. However, these techniques fail to semantically analyze proper nouns and newly-coined words because most of them depend on old-fashioned dictionary or thesaurus. To overcome these drawbacks, we propose a novel multi-document summarization technique which employs the tag cluster on Flickr, a kind of folksonomy systems, for detecting key sentences from multiple documents. We first create a word frequency table for analyzing the semantics and contribution of words by using HITS algorithm. Then, by exploiting tag clusters, we analyze the semantic relationship between words in the word frequency table. The experimental results on TAC 2008, 2009 data sets demonstrate the improvement of our proposed framework over existing summarization systems.

Robotic computer as a mediator in smart environments

With the advance of IT technologies, a new type of computing device will be introduced for smart environments in the near future. In this paper, we outline our on-going development of the robotic computer that naturally interacts with users, understands the current situation of users and environments, and proactively provides users with services. The proposed robotic computer consists of a control unit and an agent unit. The control unit, which is a remote processing server connected to the host server of the smart environment, provides memory (high-level information) and processing (computing resources) capabilities to the agent unit. The agent unit is a portable device which is wirelessly connected to the control unit, and interacts with users and physical objects. We describe the system architecture and the implementation of a proof-of-concept prototype of the proposed robotic computer.

A proposal of semantic multimedia contents retrieval framework for Smart TV

The semantic search promises to provide more accurate results than the current keyword matching-based search by understanding user intent and the contextual meaning of terms based on knowledge base. However, the ordinary users have difficulty in using the complex formal query language and the knowledge base schema on Smart TV having the restricted UI/UX. So, it is needed to develop a semantic search system to interpret the meaning of simple user keywords and find the multimedia content users want for Smart TV. In this paper, we describe a framework for the semantic multimedia contents retrieval. It is ontological knowledge base-driven framework in the sense that the knowledge base plays a main role in the whole search process including keyword interpretation and contents search. We also present our prototype system developing to test our framework ideas.

Future robotic computer: a new type of computing device with robotic functions

With the advance of IT technologies, a new type of computing device will be introduced in our daily life in the near future. In this paper, we outline our on-going development of the robotic computer that naturally interacts with users, understands current situation about users and environments, and proactively provides users with services. We describe the system architecture and the implementation of a proof-of-concept prototype of the robotic computer proposed.

Implementing automated robot task planning and execution based on description logic KB

For a service robot to perform a given task without human intervention, the robot must be able to make a plan, i.e., a sequence of high-level actions and execute it autonomously. Recently, a few researchers have investigated Description Logic-based task planning techniques. In this paper we discuss our implementation methods of Description Logic-based task planning and execution. Some knowledge representation scheme is investigated and a simple planning algorithm is conceived. Some techniques are conceived to bridge the gap between the symbolic world and the program world in order to execute the task plan. We also explain our experiments and the results we have got.

Content-Oriented knowledge modeling for automated parts library ontology merging

The digital parts libraries or electronic parts catalogs have opened up a vast potential for new electronic forms of product components procurement. However, their seamless integration is impeded by the mismatches of their ontologies. The origin of the ontology mismatches is the differences in the way the given domain is interpreted (conceptualized). In this paper, we discuss content-oriented knowledge modeling of parts libraries. We propose a system of meta-concepts which have explicit ontological semantics. The explicit ontological semantics helps ontology developers to consistently and systematically interpret the parts library knowledge. We also discuss an experimental application of our proposal to a real case of mold and die parts libraries.

Ontology modeling framework for automated information integration of components libraries

In the ontology-based approaches for automated information integration, the problem of aligning or merging different ontologies is well-known. Ontologies which are developed independently have semantic mismatches that hinder the ontology integration. In this paper, we propose a well-founded ontology modeling framework for components libraries based on Guarinos theory of upper ontology. Using the framework, ontology developers can model the knowledge of components libraries systematically and consistently, so that the mismatches are confined within a manageable form which a software program can solve automatically. We also discuss an experimental application of our proposal to a real case of mold and die components libraries.