• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.381-390
• /
• 2015

One of the fundamental requirements of entertainment applications is interactivity with users. The mobile device such as the smartphone, however, does not guarantee it due to the limit of the application processor's computing power, memory size and available electric power of the battery. This paper proposes a methodology to boost responsiveness of interactive applications by taking advantage of the parallel architecture of mobile devices which, for instance, have dual-core, quad-core or octa-core. To harness the multi-core architecture, it exploits the POSIX thread, a platform-independent thread library to be able to be used in various mobile platforms such as Android, iOS, etc. As a useful application example of the methodology, a heavy matrix calculation function was transformed to a parallelized version which showed around 2.5 ~ 3 times faster than the original version in a real-world usage environment.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.367-380
• /
• 2015

This paper proposes a hybrid rendering method which combines pre-computed global illumination results and interactive local illumination techniques and thus could interactively produce photo-realistic visual effects for mobile entertainment applications. The proposed method uses the programmable shading capability of OpenGL, a de facto standard for computer graphics library so that it can be deployed in a real-world development environment. Also, it increases the rendering time by a negligible amount compared to normal rendering time since the pre-computed results are used as operands of plain arithmetic operations. Therefore it is expected to be applicable in practice for mobiles games which require real-time responsiveness to users.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.4
• /
• pp.41-50
• /
• 2012

Network life time is very important issue for wireless sensor network(WSN). It is very important to design sensor networks for sensors to utilize their energies in effective ways. A-PEGASIS that basically bases on PEGASIS and enhances in two aspects-an elegant chain generation algorithm and periodical update of chains. However, it has problems in the chain generation mechanism and some possibility of network partitioning or sensing hole problem in the network, in LEACH related protocols. This dissertation proposes a new clustering protocol to solve the co-shared problems in the previous protocols. The basic idea of our scheme is using the table for node connectivity. The results show that the network life time would be extended in about 1.8 times longer than LEACH and 1.5 times longer than PEGASIS-A.

• Journal of KIISE
• /
• v.41 no.10
• /
• pp.792-798
• /
• 2014

In spatial databases, R-tree is one of the most widely used indexing structures and many variants have been proposed for its performance improvement. Among these variants, Hilbert R-tree is a representative method using Hilbert curve to process large amounts of data without high cost split techniques to construct the R-tree. This Hilbert R-tree, however, is hardly applicable to large-scale applications in practice mainly due to high pre-processing costs and slow bulk-load time. To overcome the limitations of Hilbert R-tree, we propose a novel approach for parallelizing Hilbert mapping and thus accelerating bulk-loading of Hilbert R-tree on GPU memory. Hilbert R-tree based on GPU improves bulk-loading performance by applying the inversed-cell method and exploiting parallelism for packing the R-tree structure. Our experimental results show that the proposed scheme is up to 45 times faster compared to the traditional CPU-based bulk-loading schemes.

• Journal of Advanced Navigation Technology
• /
• v.24 no.5
• /
• pp.438-443
• /
• 2020

To transfer files between nodes on network based on Ethernet, file transfer protocol (FTP) on TCP/IP and trivial file transfer protocol (TFTP) on UDP/IP are mostly used. Due to the lack of resources (processor, memory and so on) in the embedded system where we generally use for simple works with small firmware like ones; many of the systems implement only UDP/IP for their network stacks. Thus, TFTP is greatly to be preferred. For examples, environmental sensor devices for sensor networks, Boot Loader for general embedded device and preboot execution environment (PXE) boot for PC provide the TFTP. The logic of TFTP is simple for file transmission but, there is Stop-And-Wait problem during the process which occurs long blocking time. In this paper, we propose an algorithm which called QuTFTP(Quick UDP Trivial File Transfer Protocol) to reduce the length of the blocking time and to be compatible with the legacy TFTP.

• The Journal of the Korea Contents Association
• /
• v.17 no.1
• /
• pp.662-672
• /
• 2017

Recently, with the development of mobile devices and near field communication, mobile P2P networks have been actively studied to improve the limits of the existing centralized processing system. A peer has limited components such as batteries, memory and storage spaces in mobile P2P networks. The trust of a peer should be discriminated in order to share reliable contents in mobile P2P networks. In this paper, we propose a trust discrimination scheme considering limited resources in mobile P2P environments. The proposed scheme discriminates the trust of a peer by direct rating values using the rating information of the peer and indirect rating values by the other peers. The recent update time is included in the rating information. The proposed scheme reduces the redundant rating information by comparing the recent update times of the rating information. It is shown through performance evaluation that the proposed scheme reduces the number of messages and improves the accuracy of trust over the existing scheme.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.427-431
• /
• 2010

Multidimensional scaling (MDS) is a widely used method for dimensionality reduction, of which purpose is to represent high-dimensional data in a low-dimensional space while preserving distances among objects as much as possible. MDS has mainly been applied to data visualization and feature selection. Among various MDS methods, the classical MDS is not readily applicable to data which has large numbers of objects, on normal desktop computers due to its computational complexity. More precisely, it needs to solve eigenpair problems on dissimilarity matrices based on Euclidean distance. Thus, running time and required memory of the classical MDS highly increase as n (the number of objects) grows up, restricting its use in large-scale domains. In this paper, we propose an efficient approximation algorithm for the classical MDS based on divide-and-conquer and CUDA. Through a set of experiments, we show that our approach is highly efficient and effective for analysis and visualization of data consisting of several thousands of objects.

• KIISE Transactions on Computing Practices
• /
• v.20 no.9
• /
• pp.507-512
• /
• 2014

Recently, Distributed computing processing begins using both CPU(Central processing unit) and GPU(Graphic processing unit) to improve the performance to overcome darksilicon problem which cannot use all of the transistors because of the electric power limitation. There is an integrated graphics processor that CPU and GPU share memory and Last level cache(LLC). But, There is no LLC access rules between CPU and GPU, so if GPU and CPU processes run together at the same time, performance of both processes gets worse because of the contention on the LLC. This Paper gives evidence to prove the need of the Cache Partitioning and is mentioned about the cache partitioning design using page coloring to allocate the L3 Cache space only for the GPU process to guarantee GPU process performance.

• The KIPS Transactions:PartD
• /
• v.19D no.2
• /
• pp.147-150
• /
• 2012

While LDA is a supervised dimension reduction method which finds projective directions to maximize separability between classes, the performance of LDA is severely degraded when the number of labeled data is small. Recently semi-supervised dimension reduction methods have been proposed which utilize abundant unlabeled data and overcome the shortage of labeled data. However, matrix computation usually used in statistical dimension reduction methods becomes hindrance to make the utilization of a large number of unlabeled data difficult, and moreover too much information from unlabeled data may not so helpful compared to the increase of its processing time. In order to solve these problems, we propose an ensemble approach for semi-supervised dimension reduction. Extensive experimental results in text classification demonstrates the effectiveness of the proposed method.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.6
• /
• pp.255-260
• /
• 2017

The limitation of real-time video conferencing system is that the delay of network and buffering and the transmission of user information are not efficiently performed between systems, so real - time performance is not guaranteed completely. In order to overcome this problem, the study on the extension of the network infrastructure and the jitter delay is actively carried out, but the study on the buffering delay is insufficient. In this paper, we propose a frame-rate control buffer management (FRCB) scheme to solve the problem caused by buffering delay. The FRCB is used to prevent overflow and underflow of the buffer by adopting the two-stage buffer threshold of Fast-play THreshold (FTH) and Slow-play THreshold (STH). Therefore, it showed better performance than jitter buffer even under high CPU load, and showed that it is suitable for high quality real time video conferencing.