• Journal of KIISE:Information Networking
• /
• v.30 no.2
• /
• pp.167-178
• /
• 2003

In mobile computing environments, queries based on the location of mobile clients (MCs) may cause different results. We say that the data of these results are location dependent data (LDD). Location-dependent queries to LDD need to be processed in conjunction with the geographical distance. The efficiency of query processing may also be increased by LDD relationship, etc. But there is the problem of fuzziness about how the distance used in location-dependent queries is evaluated and the data regions are organized. In this paper, we quantify the fuzziness of a location-dependent fuery on LDD. And we propose data regions for LDD, called LDD regions, by relationship of accessed data and the degree of distance between data objects and MCs' locations. In simulation studies we show that the number of database access for location-dependent queries, which have several settings on MCs' favor and two granularity of regions, can be smaller in proposed LDD regions than that in geographical regions.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.649-658
• /
• 1997

Database management systems(DMBS)using bolatile memory shluld have a recovery function to protect data against system failutes.Recovery requires much overhead in transaction proessing and is one of the great factors that deteriorate the system performance.Recently, there have been a lot of studies on database systems with nonbolatile memory to enhance the performance.A nonbolatile memory called DFeRAM is one of the promising memory devices of the future technology, but this device does not support fine-franularity licking.In this paper, we present a dual plane FeRAM(DFeRAM)architecture to support the fine-granularity locking.We also propose a recovery algorithm for the database system with the DFeRAM based on a shadow paging methed.In order to analze the performance of the proposed algorithm, we present an analytical model and analyze the performance using the moedl.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.3
• /
• pp.202-209
• /
• 2002

This paper deals with simplification of classification rules for data mining and rule bases for control systems. Datamining that extracts useful information from such a large amount of data is one of important issues. There are various ways in classification methodologies for data mining such as the decision trees and neural networks, but the result should be explicit and understandable and the classification rules be short and clear. The rough sets theory is an effective technique in extracting knowledge from incomplete and inconsistent data and provides a good solution for classification and approximation by using various attributes effectively This paper investigates granularity of knowledge for reasoning of uncertain concopts by using rough set approximations and uses a hierarchical classification structure that is more effective technique for classification by applying core to upper level. The proposed classification methodology makes analysis of an information system eary and generates minimal classification rules.

• Journal of KIISE:Databases
• /
• v.32 no.1
• /
• pp.100-110
• /
• 2005

The update transactions to be executed in spatial databases usually have been known as interactive and long duration works. To improve the parallelism of concurrent updates, it needs multiple transactions concurrently update a large spatial object which has a spatial extensions larger than workspace of a client. However, under the existing locking protocols, it is not possible to concurrently update a large spatial object because of conflict of a write lock This paper proposes a partial locking scheme of enabling a transaction to set locks on parts of a big object. The partial locking scheme which is an exclusive locking scheme set by user, acquires locks for a part of the big object to restrict the unit of concurrency control to a partial object of a big object. The scheme gives benefits of improving the concurrency of un updating job for a large object because it makes the lock control granularity finer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3274-3297
• /
• 2021

Permission delegation is an important research issue in access control. It allows a user to delegate some of his permissions to others to reduce his workload, or enables others to complete some tasks on his behalf when he is unavailable to do so. As an ideal solution for controlling read access on outsourced data objects on the cloud, Ciphertext-Policy Attribute-Based Encryption (CP-ABE) has attracted much attention. Some existing CP-ABE schemes handle the read permission delegation through the delegation of the user's private key to others. Still, these schemes lack the further consideration of granularity and traceability of the permission delegation. To this end, this article proposes a flexible and fine-grained CP-ABE key delegation approach that supports white-box traceability. In this approach, the key delegator first examines the relations between the data objects, read permission thereof that he intends to delegate, and the attributes associated with the access policies of these data objects. Then he chooses a minimal attribute set from his attributes according to the principle of least privilege. He constructs the delegation key with the minimal attribute set. Thus, we can achieve the shortest delegation key and minimize the time of key delegation under the premise of guaranteeing the delegator's access control requirement. The Key Generation Center (KGC) then embeds the delegatee's identity into the key to trace the route of the delegation key. Our approach prevents the delegatee from combining his existing key with the new delegation key to access unauthorized data objects. Theoretical analysis and test results show that our approach helps the KGC transfer some of its burdensome key generation tasks to regular users (delegators) to accommodate more users.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.4
• /
• pp.87-99
• /
• 2009

The top-down method for SOA delivery is recommended as a best way to take advantage of SOA. The core step of SOA delivery is the step of service modeling including service analysis and design based on ontology. Most enterprises know that the top-down approach is the best but they are hesitant to employ it because it requires them to invest a great deal of time and money without it showing any immediate results, particularly because they use well-defined component based systems. In this paper, we propose a service identification method to use a well-defined components maximally as a bottom-up approach. We assume that user's inputs generates events on a GUI and the approximate business process can be obtained from concatenating the event paths. We first find the core GUIs which have many outgoing event calls and form event paths by concatenating the event calls between the GUIs. Next, we adapt sequential pattern mining algorithms to find the maximal frequent event paths. As an experiment, we obtained business services with various granularity by applying a cohesion metric to extracted frequent event paths.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.3
• /
• pp.169-172
• /
• 2015

Dalvik is a virtual machine (VM) that is designed to run Java-based Android applications. A trace-based just-in-time (JIT) compilation technique is currently employed to improve performance of the Dalvik VM. However, due to runtime compilation overhead, the trace-based JIT compiler provides only a few simple optimizations. Moreover, because each trace contains only a few instructions, the trace-based JIT compiler inherently exploits fewer optimization and parallelization opportunities than a method-based JIT compiler that compiles method-by-method. So we propose a new method-based JIT compiler, named DEX2C, in order to improve performance by finding more opportunities for both optimization and parallelization in Android applications. We employ C code as an intermediate product in order to find more optimization opportunities by using the GNU C Compiler (GCC), and we will detect parallelism by using the Intel C/C++ parallel compiler and the AESOP compiler in our future work. In this paper, we introduce our DEX2C compiler, which dynamically translates Dalvik bytecodes (DEX) into C code with method granularity. We also describe a new method-based JIT interface in the Dalvik VM for the DEX2C compiler. Our experiment results show that our compiler and its interface achieve significant performance improvement by up to 15.2 times and 3.7 times on average, in Element Benchmark, and up to 2.8 times for FFT in Smartbench.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.711-716
• /
• 2006

Since the introduction of digital camera to the mass market, the number of digital photos owned by an individual is growing at an alarming rate. This phenomenon naturally leads to the issues of difficulties while searching and browsing in the personal digital photo archive. Traditional approach typically involves content-based image retrieval using computer vision algorithms. However, due to the performance limitations of these algorithms, at least on the casual digital photos taken by non-professional photographers, more recent approaches are centered on time-based clustering algorithms, analyzing the shot times of photos. These time-based clustering algorithms are based on the insight that when these photos are clustered according to the shot-time similarity, we have "event clusters" that will help the user browse through her photo archive. It is also reported that one of the remaining problems with the time-based approach is that people perceive events in different scales. In this paper, we present an adaptive time-based clustering algorithm that exploits the usage history of digital photos in order to infer the user's preference on the event granularity. Experiments show significant performance improvements in the clustering accuracy.

• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.728-740
• /
• 2004

The increasing complexity and shorter life cycle of software have made it necessary to reuse software. Object-oriented development had not provided extensive reuse and computing infrastructures are evolving from mainframe to distributed environments. However, components provide more advanced means of structuring, describing and developing system, because they are more coarse-grained and have more domain-specific aspects than objects. And they are also suited for distributed environment due to their reusability and granularity. In this paper, we present a process including the static metrics and guidelines that can be applied to transform object-oriented systems into component-based systems. Our process consists of two parts: First, basic components are created based upon composition and inheritance relationships between classes. Second, intermediate system is refined into component-based system with the static metrics and guidelines we propose.

• Advances in Computational Design
• /
• v.2 no.4
• /
• pp.293-311
• /
• 2017

There are several claimed benefits for the impact of design patterns (DPs) on software quality. However, the association between design patterns and fault-proneness has been a controversial issue. In this work, we evaluate the fault-proneness of design patterns at four levels: the design level, category level, pattern level, and role level. We used five subject systems in our empirical study. As a result, we found that, at the design level, the classes that participate in the design patterns are less fault-prone than the non-participant classes. At the category level, we found that the classes that participate in the behavioral and structural categories are less fault-prone than the non-participant classes. In addition, we found that the classes that participate in the structural design patterns are less fault-prone than the classes that participate in the other categories. At the pattern level, we found that only five patterns show significant associations with fault-proneness: builder, factory method, adapter, composite, and decorator. All of these patterns except for builder show that the classes that participate in each one of them are less fault-prone than the non-participant classes in that pattern. The classes that participate in the builder design pattern were more fault-prone than the non-participant classes and the classes that participate in several patterns: the adapter, the composite, and the decorator design patterns. At the role level, the most significant differences were between the classes that participate in some roles and the non-participant classes. Only three pairs of design pattern roles show significant differences. These roles are concrete-product vs. concrete-creator, adapter vs. adaptee, and adapter vs. client. The results recommend the use of design patterns because they are less fault-prone in general except for the builder design pattern, which should be applied with care and addressed with more test cases.