Hyun Ko

A Method for Optimal Moving Pattern Mining using Frequency of Moving Sequence

Since the traditional pattern mining methods only probe unspecified moving patterns that seem to satisfy users` requests among diverse patterns within the limited scopes of time and space, they are not applicable to problems involving the mining of optimal moving patterns, which contain complex time and space constraints, such as 1) searching the optimal path between two specific points, and 2) scheduling a path within the specified time. Therefore, in this paper, we illustrate some problems on mining the optimal moving patterns with complex time and space constraints from a vast set of historical data of numerous moving objects, and suggest a new moving pattern mining method that can be used to search patterns of an optimal moving path as a location-based service. The proposed method, which determines the optimal path(most frequently used path) using pattern frequency retrieved from historical data of moving objects between two specific points, can efficiently carry out pattern mining tasks using by space generalization at the minimum level on the moving object`s location attribute in consideration of topological relationship between the object`s location and spatial scope. Testing the efficiency of this algorithm was done by comparing the operation processing time with Dijkstra algorithm and algorithm which are generally used for searching the optimal path. As a result, although there were some differences according to heuristic weight on algorithm, it showed that the proposed method is more efficient than the other methods mentioned.

Location Generalization of Moving Objects for the Extraction of Significant Patterns

Abstract In order to provide the optimal location based services such as the optimal moving path search or the scheduling pattern prediction, the extraction of significant moving pattern which is considered the temporal and spatial properties of the location-based historical data of the moving objects is essential. In this paper, for the extraction of significant moving pattern we propose the location generalization method which translates the location attributes of moving object into the spatial scope information based on R * -tree for more efficient patterning the continuous changes of the location of moving objects and for indexing to the 2-dimensional spatial scope. The proposed method generates the moving sequences which is satisfied the constraints of the time interval between the spatial scopes using the generalized spatial data, and extracts the significant moving patterns using them. And it can be an efficient method for the temporal pattern mining or the analysis of moving transition of the moving objects to provide the optimal location based services.Key Words : Moving Object, Moving Pattern, Location Generalization, Extraction of Significant Moving Pattern

A study on strategic partership-based cutoff time adjustment for express package deliveries

The market competition of express package deliveries in Korea is severe because a large number of companies have entered into the market. Under the competitive business environment, it is helpful for a company to consider how to economically operate the consolidation terminal and its corresponding service centers. In general, each company owns and operates a number of service centers in order to achieve high level service for the country-wide coverage even though some service centers cannot create profits due to low volume and under-utilization as cost centers. Such strategy is not good option for companies involved so that strategic partnership particularly in the same service districts can be an alternative way to get win-win goals while maximizing the overall operating efficiency of express service networks. Therefore, this study suggests an approach to the reconfiguration of express service networks with respect to strategy partnership of closing/keeping service centers among companies involved and adjustments of their cutoff times. For this we propose an integer programming model and a genetic algorithm based solution procedure for allowing companies involved to maximize their incremental profit. An illustrative numerical example in Korea is presented to demonstrate the practicality and efficiency of the proposed model.

Compromised network design model for the strategic alliance of service centers and consolidation terminals in express courier services

A direct shipment via express courier is expected to be an area with huge sales potential in the near future. In Korean market, many domestic companies of various sizes have been fiercely competing to extend their own market share. Currently offering only international delivery services, moreover, foreign companies with a higher level of customer services are expected to escalate the competition by entering the market of domestic delivery. These competitive rivalry and price pressure have made market conditions tough and margins under severe pressure. To cope with these substantial competition pressures, we propose strategic alliance as an effective solution to the challenges faced by small and medium express courier service companies. An integer programming model for compromised network design and its solution procedure based on maxmin and maxsum criteria are developed respectively. The applicability and efficiency of the proposed model are demonstrated through an illustrative numerical example.

The Efficient Spatio-Temporal Moving Pattern Mining using Moving Sequence Tree

ABSTRACT Recently, based on dynamic location or mobility of moving object, many researches on pattern mining methods actively progress to extract more available patterns from various moving patterns for development of location based services. The performance of moving pattern mining depend on how analyze and process the huge set of spatio-temporal data. Some of traditional spatio-temporal pattern mining methods[1-6,8-11]have proposed to solve these problem, but they did not solve properly to reduce mining execution time and minimize required memory space. Therefore, in this paper, we propose new spatio-temporal pattern mining method which extract the sequential and periodic frequent moving patterns efficiently from the huge set of spatio-temporal moving data. The proposed method reduces mining execution time of 83%∼93% rate on frequent moving patterns mining using the moving sequence tree which generated from historical data of moving objects based on hash tree. And also, for minimizing the required memory space, it generalize the detained historical data including spatio-temporal attributes into the real world scope of space and time using spatio-temporal concept hierarchy.Keywords:Moving Object, Spatio-Temporal Pattern Mining, Data Generalization, Moving Sequence Tree

Efficient STMPM (Spatio-Temporal Moving Pattern Mining) Using Moving Sequence Tree

Recently, based on the dynamic location or mobility of a moving object, many researches on pattern mining methods actively progress to extract more available patterns from various moving patterns for the development of location based services. The performance of moving pattern mining depends on how to analyze and process the huge set of spatio-temporal data. Some of the traditional spatio-temporal pattern mining methods[1,2,3,4,13] have proposed to solve these problems, but they did not solve properly to reduce mining execution time and minimize required memory space. Therefore, in this paper, we propose a new STMPM (spatio-temporal moving pattern mining) method which efficiently extracts the periodical or sequential moving patterns from the huge set of spatio-temporal moving data. The proposed method reduces frequent moving patterns mining execution time, using the moving sequence tree which is generated from the historical data of moving objects based on hash tree. And also, to minimize the required memory space, the method generalizes detained historical data, including spatio-temporal attributes, into the real world scopes of space and time by using spatio-temporal concept hierarchy.