• KIISE Transactions on Computing Practices
• /
• v.21 no.5
• /
• pp.387-392
• /
• 2015

MapReduce is a framework used to process large data sets in parallel on a large cluster. A group-by query is a query that partitions the input data into groups based on the values of the specified attributes, and then evaluates the value of the specified aggregate function for each group. In this paper, we propose an efficient method for processing multiple group-by queries using MapReduce. Instead of computing each group-by query independently, the proposed method computes multiple group-by queries in stages with one or more MapReduce jobs in order to reduce the total execution cost. We compared the performance of this method with the performance of a less sophisticated method that computes each group-by query independently. This comparison showed that the proposed method offers better performance in terms of execution time.

• Journal of Korean Society of Transportation
• /
• v.28 no.1
• /
• pp.25-38
• /
• 2010

In this study, the real on-road driving data were analyzed to draw the various characteristics related to idling of vehicles. The results revealed that the average idling time of a city bus corresponds to 30.9% of the total daily driving time. Among this, for about 21.6% of the total daily driving time, it is available that an engine can be halted while the vehicle stops. It is a daytime when the portion of time, for which idling stop is available, is peak. Due to idling stop, an increase of turnaround was not found throughout this analysis. When a city bus stops at a traffic right, idling periods were long enough to execute the idling stop, during which an engine halts. Whereas, during the idling time for bus stops, the idling periods were not so long enough to execute idling stop. Deceleration periods among the total turnarounds of a city bus occupies about 24.7%, during which, for about 30%, a deceleration maintains for more than four seconds. Thus, using the energy during deceleration period, which then can be recovered from braking energy, it was also found that a hybrid system can be effectively implemented to a city bus.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.8
• /
• pp.367-376
• /
• 2007

In this paper, we introduce an application-specific and adaptive power management technique for portable systems that support dynamic voltage scaling (DVS). We exploit both the idle time of multitasking systems running soft real-time tasks as well as memory- or CPU-bound code regions. Detailed power and execution time profiles guide an adaptive power manager (APM) that is linked to the operating system. A post-pass optimizer marks candidate regions for DVS by inserting calls to the APM. At runtime, the APM monitors the CPU's performance counters to dynamically determine the affinity of the each marked region. for each region, the APM computes the optimal voltage and frequency setting in terms of energy consumption and switches the CPU to that setting during the execution of the region. Idle time is exploited by monitoring system idle time and switching to the energy-wise most economical setting without prolonging execution. We show that our method is most effective for periodic workloads such as video or audio decoding. We have implemented our method in a multitasking operating system (Microsoft Windows CE) running on an Intel XScale-processor. We achieved up to 9% of total system power savings over the standard power management policy that puts the CPU in a low Power mode during idle periods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2687-2696
• /
• 2011

A Clustering problem is one of the organizational problems to improve network lifetime and scalability in underwater acoustic sensor networks. This paper propose an algorithm to obtain an optimal clustering solution to be able to minimize a total transmission power for all deployed nodes to transmit data to the sink node through its clusterhead. In general, as the number of nodes increases, the amount of calculation for finding the solution would be too much increased. To obtain the optimal solution within a reasonable computation time, we propose a genetic algorithm to obtain the optimal solution of the cluster configuration. In order to make a search more efficient, we propose some efficient neighborhood generating operations of the genetic algorithm. We evaluate those performances through some experiments in terms of the total transmission power of nodes and the execution time of the proposed algorithm. The evaluation results show that the proposed algorithm is efficient for the cluster configuration in underwater acoustic sensor networks.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2158-2170
• /
• 1999

It has been required more reliable communication on processes and improvement of system performance as distributed systems using multicast protocol became widespread. In distributed environment maintaining data consistency through asynchronous execution of processes and coordinating the activities of them would occurs. This paper proposes a total ordering algorithm, TORMP, in order to resolve these problems. TORMP takes advantage of multicast protocol and uses an effective token passing method. It reduces a process delaying time before transmitting its message by multicasting a token simultaneously to every process that initiates the request of the message. Moreover, the processes receiving the token start multicasting the message at the same time, which causes to cut down the overall transmission dely. In case that one process sends a message, TORMP hardly uses the procedure of controlling for ordering. It gives fairly the right of sending messages to all processes in a group with utilizing vector clock. In TORMP, unlike other algorithms, the number of packets generated during ordering process does not depend on the number of processes.

• The Journal of Korean Physical Therapy
• /
• v.21 no.1
• /
• pp.65-71
• /
• 2009

Purpose: Numerous investigators demonstrated that adaptative changes were induced by motor skill acquisition in the central nervous system. We investigated the changes of neuroelectric potential following motor learning with serial reaction time task in young healthy subjects, using electroencephalography (EEG). Methods: Twelve right-handed normal volunteers were recruited, who have no history of neurological dysfunction and were given to written the informed consent. All subjects were assigned to flex to extend the wrist joint or flex the thumb for pressing the matched button as quickly and accurately as possible, when one of five colored lights was displayed on computer screen (red, yellow, green, blue, white). EEG was measured, whenfive types simulations ware presented randomly with equal probabilities of 20% in total 200 times at the pre and post test. And they were scheduled for 30 minutes practice session during two consecutive days in the laboratory. Results: The results showed that the reaction time at the post test was significantly reduced, compared to one of the pre test in serial reaction time task. In EEG map analysis, the broaden bilateral activation tended to be changed to the focused contralateral activation in the frontoparietal area. Conclusion: These findings showed that acquisition of motor skill led to product more fast motor execution, and that motor learning could change cortical activation pattern, from the broaden bilateral activation to the focused contralateral activation. Thus we concluded that the adaptative change was induced by motor learning in healthy subjects.

• Journal of the Korea Society for Simulation
• /
• v.17 no.2
• /
• pp.21-29
• /
• 2008

The High Level Architecture(HLA) specifies a framework for interoperation between heterogeneous simulators, and Run-Time Infrastructure(RTI) is a implementation of the HLA Interface Specification. The Data Distribution Management(DDM) services, one category of IEEE 1516 HLA/RTI management services, control filters for data transmission and reception of data volume among simulators. In this paper, we propose design concept of DDM and show its implementation for light-weighted RTI. The design concept of DDM is to minimize total amount of message that each federate and a federation process generate using the rate of RTI service execution. The design of our proposed DDM follows that a data transfer mechanism is differently applied as the rate of RTI service execution. A federate usually publishes or subscribes data when it starts. The federate constantly updates the data and modifies associated regions while it continues to advance its simulation time. Therefore, the proposed DDM design provides fast update or region modification in exchange of complex publish and subscribe services. We describe how to process the proposed DDM in IEEE 1516 HLA/RTI and experiment variable scenarios while modifying region, changing overlap ratio, and increasing data volume.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.3
• /
• pp.1451-1458
• /
• 2013

This paper deals with the programs and algorithms that generate the full data set that satisfy the basic combinatorial requirement of combination, permutation, partial permutation or shortly r-permutation, which are used in the application of the total data testing or the simulation input. We search the programs able to meet the rules which is permutations and combinations, r-permutations, select the fastest program by field. With further study, we developed a new program reducing the time required to processing. Our research performs the following pre-study. Firstly, hundreds of algorithms and programs in the internet are collected and corrected to be executable. Secondly, we measure running time for all completed programs and select a few fast ones. Thirdly, the fast programs are analyzed in depth and its pseudo-code programs are provided. We succeeded in developing two programs that run faster. Firstly, the combination program can save the running time by removing recursive function and the r-permutation program become faster by combining the best combination program and the best permutation program. According to our performance test, the former and later program enhance the running speed by 22% to 34% and 62% to 226% respectively compared with the fastest collected program. The programs suggested in this study could apply to a particular cases easily based on Pseudo-code., Predicts the execution time spent on data processing, determine the validity of the processing, and also generates total data with minimum access programming.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1693-1713
• /
• 2018

An important technique used by database administrators (DBAs) is to improve performance in decision-support workloads associated with a Star schema is multi-level partitioning. Queries will then benefit from performance improvements via partition elimination, due to constraints on queries expressed on the dimension tables. As the task of multi-level partitioning can be overwhelming for a DBA we are proposing a wizard that facilitates the task by calculating a partitioning scheme for a particular workload. The system resides completely on a client and interacts with the costing estimation subsystem of the query optimizer via an API over the network, thereby eliminating any need to make changes to the optimizer. In addition, since only cost estimates are needed the wizard overhead is very low. By using a greedy algorithm for search space enumeration over the query predicates in the workload the wizard is efficient with worst-case polynomial complexity. The technology proposed can be applied to any clustering or partitioning scheme in any database management system that provides an interface to the query optimizer. Applied to the Teradata database the technology provides recommendations that outperform a human expert's solution as measured by the total execution time of the workload. We also demonstrate the scalability of our approach when the fact table (and workload) size increases.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1674-1683
• /
• 2016

In this paper, a Finite Control Set Model Predictive Control (FCS-MPC) for a five level cascaded multilevel inverter (CMLI) with reduced switch topology is proposed. Five switches are used here instead of conventionally used eight switches. The main contribution of this paper is to make the MPC controller work for the reduced switch topology using only 19 voltage vectors in place of conventional 61 voltage vectors for a five level CMLI. This simplifies the execution of the MPC algorithm, paving a way for the significant reduction in the computational time. The controller makes use of the excellent ability of MPC to multitask, by adding one more objective which is to reduce the average switching frequency in addition to controlling the load current. This is especially important, since switching losses and therefore switching frequency is significant for high-power applications. The trade-off of this MPC is that the current is not as smooth as the 61 vector scheme, but well within the limits of IEEE standards. The results shown prove that this MPC works well in steady state and dynamic conditions too.