Sang Sung Park

Technology forecasting using matrix map and patent clustering

Purpose – The purpose of this paper is to propose an objective method for technology forecasting (TF). For the construction of the proposed model, the paper aims to consider new approaches to patent mapping and clustering. In addition, the paper aims to introduce a matrix map and K‐medoids clustering based on support vector clustering (KM‐SVC) for vacant TF.Design/methodology/approach – TF is an important research and development (R&D) policy issue for both companies and government. Vacant TF is one of the key technological planning methods for improving the competitive power of firms and governments. In general, a forecasting process is facilitated subjectively based on the researchers knowledge, resulting in unstable TF performance. In this paper, the authors forecast the vacant technology areas in a given technology field by analyzing patent documents and employing the proposed matrix map and KM‐SVC to forecast vacant technology areas in the management of technology (MOT).Findings – The paper examines...

Document clustering method using dimension reduction and support vector clustering to overcome sparseness

This study proposes new method to overcome sparsity problem of document clustering.We build combined method using dimension reduction, K-means clustering, and SVC.In particular, we attempt to overcome the sparseness in patent document clustering.First, we conduct experiment using news data from UCI machine learning repository.Second, using retrieved patent documents, we carry out patent clustering. Many studies on developing technologies have been published as articles, papers, or patents. We use and analyze these documents to find scientific and technological trends. In this paper, we consider document clustering as a method of document data analysis. In general, we have trouble analyzing documents directly because document data are not suitable for statistical and machine learning methods of analysis. Therefore, we have to transform document data into structured data for analytical purposes. For this process, we use text mining techniques. The structured data are very sparse, and hence, it is difficult to analyze them. This study proposes a new method to overcome the sparsity problem of document clustering. We build a combined clustering method using dimension reduction and K-means clustering based on support vector clustering and Silhouette measure. In particular, we attempt to overcome the sparseness in patent document clustering. To verify the efficacy of our work, we first conduct an experiment using news data from the machine learning repository of the University of California at Irvine. Second, using patent documents retrieved from the United States Patent and Trademark Office, we carry out patent clustering for technology forecasting.

Examining technological innovation of Apple using patent analysis

Purpose – Apple is a representative company of technological innovation (TI) and management. It has launched new and innovative products since 1977, and many companies and business schools around the world have attempted to learn about the success story of Apples innovation. However, most previous research works on Apples innovation have been based on qualitative approaches such as experts opinions. Such studies offer a subjective point of view. By contrast, in this paper the authors aim to study the TI and forecasting of Apple by analyzing its patent applications, which is an objective approach to examining the innovation of Apple from a technological perspective.Design/methodology/approach – TI is an important issue concerning technology management for companies and governments. To examine Apples TI, the authors analyze all applied patents and construct analytical models according to three approaches. First, they build statistical models using the time series regression and multiple linear regressio...

Forecasting Diffusion of Technology by using Bass Model

Generally, researching method of technology forecasting has been depended on intuition of expert until now. So there were many defects like consuming much time and money and so on. In this paper, we forecast diffusion of technology by using Bass model that is one of the quantitative analysis methods. We applied this model at technology market. And for input data of experiment, we use patent data that is representing each technology in technology market. We expect this research will be suggest new possibility that patent data can be applied in Bass model.

A Comparison of Forecasting the Index of the Korean Stock Market

According to the increase of an impact foreigner investor have on the Korean stock market, it is very importance to analyze the investment pattern of the foreigner investors in order to predict the movement of the Korean stock market. Firstly, in this study we collected various factors which influence the Korean stock market in the previous literatures about the movement of stock market. Secondly, Factors which influence significantly to KOPSI 200 Index among the collected factors are extracted through the stepwise selection used in regression analysis. Finally we predicted the movement of the Korean stock market using Back‐Propagation Neural Network (BPN) and Support Vector Machine (SVM). And we have done a comparison analysis of obtained results through these methods. As a result of the experiments, prediction accuracy using SVM showed better result than using BPN.

Document Form and Character Recognition using SVM

Because of development of computer and information communication, EDI (Electronic Data Interchange) has been developing. There is OCR (Optical Character Recognition) of Pattern recognition technology for EDI. OCR contributed to changing many manual in the past into automation. But for the more perfect database of document, much manual is needed for excluding unnecessary recognition. To resolve this problem, we propose document form based character recognition method in this study. Proposed method is divided into document form recognition part and character recognition part. Especially, in character recognition, change character into binarization by using SVM algorithm and extract more correct feature value.

Digital Coin Business Model Using the Coin ATM

Because about 83.6 billion won worth coins are not collected annually, 35 billion won of government money is being wasted for producing new coins in Korea. In order to improve unnecessary government money leakage, we now have to develop a proper way of managing small valued money such as coins. We have already developed the coin ATM to solve such problem in the previous study. In this study, we proposed business model, which enables users to deposit or consume such small amount of money with the coin ATM. The proposed business model has advantages that enable to connect various payment system and is efficient to consume such small amount of money. This business model improves not only the way of managing small valued money but also the way of consuming small valued money. Furthermore, our business model can contribute to activating circulation of coins as well as preventing leakage of government money.