Kyunglag Kwon

A real time process management system using RFID data mining

Abstract Recently, there have been numerous efforts to fuse the latest Radio Frequency Identification (RFID) technology with the Enterprise Information System (EIS). However, in most cases these attempts are centered mainly on the simultaneous multiple reading capability of RFID technology, and thus neglect the management of massive data generated from the RFID reader. As a result, it is difficult to obtain flow information for RFID data mining related to real time process control. In this paper, we propose an advanced process management method, called ‘Procedure Tree’ (PT), for RFID data mining. Using the suggested PT, we are able to manage massive RFID data effectively, and perform real time process management efficiently. Then we evaluate the efficiency of the proposed method, after applying it to a real time process control system connected to the RFID-based EIS. For the verification of the suggested system, we collect an enormous amount of data in the Enterprise Resource Planning (ERP) database, analyze characteristics of the collected data, and then compute the elapsed time on each stage in process control. The suggested system was able to perform what the traditional RFID-based process control systems failed to do, such as predicting and tracking of real time process and inventory control.

Community Topical “Fingerprint” Analysis Based on Social Semantic Networks

Community analysis of social networks is a widely used technique in many fields. There have been many studies on community detection where the detected communities are attached to a single topic. However, an overall topical analysis for a community is required since community members are often concerned with multiple topics. In this paper, we propose a semantic method to analyze the topical community “fingerprint” in a social network. We represent the social network data as an ontology, and integrate with two other ontologies, creating a Social Semantic Network (SSN) context. Then, we take advantage of previous topological algorithms to detect the communities and retrieve the topical “fingerprint” using SPARQL. We extract about 210,000 Twitter profiles, detect the communities, and demonstrate the topical “fingerprint”. It shows human-friendly as well as machine-readable results, which can benefit us when retrieving and analyzing communities according to their interest degrees in various domains.

Content Recommendation Method Using FOAF and SNA

With the rapid growth of user-created contents and wide use of community-based websites, content recommendation systems have attracted the attention of users. However, most recommendation systems have limitations in properly reflecting each user’s characteristics, and difficulty in recommending appropriate contents to users. Therefore, we propose a content recommendation method using Friend-Of-A-Friend (FOAF) and Social Network Analysis (SNA). First, we extract user tags and characteristics using FOAF, and generate graphs with the collected data, with the method. Next, we extract common characteristics from the contents, and hot tags using SNA, and recommend the appropriate contents for users. For verification of the method, we analyzed an experimental social network with the method. From the experiments, we verified that the more users that are added into the social network, the higher the quality of recommendation increases, with comparison to an item-based method. Additionally, we can provide users with more relevant recommendation of contents.

Sentiment trend analysis in social web environments

In this paper, we propose a novel method for sentiment trend analysis using Ant Colony Optimization (ACO) algorithm and SentiWordNet. We first collect social data in the form of Resource Description Framework (RDF) triples, and then use ACO algorithm to digitize the amassed RDF triples. Using ACO algorithm, we then compute pheromone values to extract the trends of the users sentiments with the modified equations. Next, we compute the users sentiment scores for the computed pheromone values with respect to the sentiment words with SentiWordNet. Finally, we analyze the sentiment trend of the online user by time. For verification of the proposed method, we conduct experiments, and compare the analyzed sentiment trends with their real daily lives. The results show that the proposed method performs satisfactory sentiment trend analysis on real data.

Collaborative Ontology Generation Method Using an Ant Colony Optimization Model

Ontology has been regarded as the core technology of the semantic web. However, non-experts still have difficulties in participating in ontology generation. So, the growing need for public participation in ontology generation has arisen. We propose a method in which the public may participate in ontology generation by adopting the ACO (Ant Colony Optimization) algorithm. We demonstrate that the ontology generated by the proposed method is satisfactory to justify our method: precision and recall of the ontology are about 94.44 and 99.6 % respectively. The suggested method enables the construction of the semantic web environment with non-experts in the field of ontology engineering.

Agglomerative Hierarchical Clustering for Information Retrieval Using Latent Semantic Index

Web clustering has been a highly interesting research field in Information Retrieval (IR) for many years. Considering the amount of web sites listed with an ambiguous query on major search engines, many researchers opted for Search Results Clustering (SRC) aiming on grouping vast lists of results into topically comprehensible clusters. Although some well-known algorithms exist already, results show there is still more work to be done in many aspects. This paper proposes method integrating Latent Semantic Indexing (LSI) with Agglomerative Hierarchical Clustering (AHC). The approach behind combining these two methods is to counter the synonymy and polysemy that occurs when previous SRC methods use bag-of-words model. Moreover, we observe that clusters by previous SRC methods are not satisfied and can be further clustered. Thus, we give room for other hidden topics to be shown. For the verification of proposed method, we use two common datasets AMBIguous ENTries (AMBIENT) and MORE Sense-tagged QUEries (MORESQUE), showing significant improvement in terms of clustering quality.

An Intelligent Dynamic Context-Aware System Using Fuzzy Semantic Language

The prevalence of smart devices and the wireless Internet environment have enabled users to exploit environmental sensor data in a variety of fields. This has engendered various research issues in the development of context-awareness technology. In this paper, we propose a novel method where semantic web technology and the fuzzy concept are used to perform tasks that express and infer the user’s dynamic context, in distributed heterogeneous computing environments. The proposed method expresses environmental information using numerical values, and converts them into fuzzy OWL. Then, we make inferences based on the user context, using FiRE, a fuzzy inference engine. The suggested method allows us to describe user context information in heterogeneous environments. Because we use fuzzy concepts to represent contextual information, we can easily express its degree or status.

Rule-Based Topic Trend Analysis by Using Data Mining Techniques

Many users in social web environments share and publish user-generated contents such as tastes, opinions, and ideas in the form of text and multimedia data. Various research studies have been conducted on the analysis of such social data, which can be used for discovering users’ thoughts on specific topics. But, there are still challenging tasks to find out the meaningful patterns from the social data due to rapidly increasing amount of data. In this paper, we therefore propose a rule-based topic trend analysis by using On-Line-Analytical Processing (OLAP) and Association Rule Mining (ARM) to detect information such as previously unknown or abnormal events or situations. For the verification of the proposed method, we conduct experiments to demonstrate that the method is feasible to perform rule-based topic trend analysis.

An Approach for User Interests Extraction Using Decision Tree and Social Network Analysis

In this paper, we propose an effective extraction method for acquiring the interests of users from Social Network Services (SNSs). In the proposed approach, a domain ontology generated by a decision tree is first used to classify domain webpages and each user. A Social Network Analysis (SNA) method is then used to analyze the tags from the Friend-Of-A-Friend (FOAF) profiles of each user; after which, we obtained the interests of the users. The results of an experiment conducted to obtain the interests of 2012 USA presidential candidates indicate that the precision and accuracy of our approach are 91.5 and 93.1 % in classifying the users, respectively.

Intelligent Production Management System with the Enhanced PathTree

In recent years, there have been many attempts to connect the latest RFID (Radio Frequency Identification) technology with EIS (Enterprise Information System) and utilize them. However, in most cases the focus is only on the simultaneous multiple reading capability of the RFID technology neglecting the management of massive data created from the reader. As a result, it is difficult to obtain time-related information such as flow prediction and analysis in process control. In this paper, we suggest a new method called `procedure tree`, an enhanced and complementary version of PathTree which is one of RFID data mining techniques, to manage massive RFID data sets effectively and to perform a real-time process control efficiently. We will evaluate efficiency of the proposed system after applying real-time process management system connected with the RFID-based EIS. Through the suggested method, we are able to perform such tasks as prediction or tracking of process flow for real-time process control and inventory management efficiently which the existing RFID-based production system could not have done.