• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.435-447
• /
• 2017

Associative and bidirectional associative memories are examples of associative structures studied intensively in the literature. The underlying idea is to realize associative mapping so that the recall processes (one-directional and bidirectional ones) are realized with minimal recall errors. Associative and fuzzy associative memories have been studied in numerous areas yielding efficient applications for image recall and enhancements and fuzzy controllers, which can be regarded as one-directional associative memories. In this study, we revisit and augment the concept of associative memories by offering some new design insights where the corresponding mappings are realized on the basis of a related collection of landmarks (prototypes) over which an associative mapping becomes spanned. In light of the bidirectional character of mappings, we have developed an augmentation of the existing fuzzy clustering (fuzzy c-means, FCM) in the form of a so-called collaborative fuzzy clustering. Here, an interaction in the formation of prototypes is optimized so that the bidirectional recall errors can be minimized. Furthermore, we generalized the mapping into its granular version in which numeric prototypes that are formed through the clustering process are made granular so that the quality of the recall can be quantified. We propose several scenarios in which the allocation of information granularity is aimed at the optimization of the characteristics of recalled results (information granules) that are quantified in terms of coverage and specificity. We also introduce various architectural augmentations of the associative structures.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.41 no.2
• /
• pp.117-124
• /
• 2017

The performance of the colored Gauss-Seidel solver on CPU and GPU was investigated for the two- and three-dimensional heat conduction problems by using different mesh sizes. The heat conduction equation was discretized by the finite difference method and finite element method. The CPU yielded good performance for small problems but deteriorated when the total memory required for computing was larger than the cache memory for large problems. In contrast, the GPU performed better as the mesh size increased because of the latency hiding technique. Further, GPU computation by the colored Gauss-Siedel solver was approximately 7 times that by the single CPU. Furthermore, the colored Gauss-Seidel solver was found to be approximately twice that of the Jacobi solver when parallel computing was conducted on the GPU.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.5
• /
• pp.124-130
• /
• 2017

Character encoding is the method used to represent characters or symbols on a computer, and there are many encoding detection software tools. For the widely used encoding detection software"uchardet", the accuracy of encoding detection of unmodified normal text document is 91.39%, but the accuracy of language detection is only 32.09%. Also, if a text document is encrypted by substitution, the accuracy of encoding detection is 3.55% and the accuracy of language detection is 0.06%. Therefore, in this paper, we propose encoding and language detection of text document using the deep learning algorithm called LSTM(Long Short-Term Memory). The results of LSTM are better than encoding detection software"uchardet". The accuracy of encoding detection of normal text document using the LSTM is 99.89% and the accuracy of language detection is 99.92%. Also, if a text document is encrypted by substitution, the accuracy of encoding detection is 99.26%, the accuracy of language detection is 99.77%.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.12
• /
• pp.1177-1187
• /
• 2010

Flash memory becomes popular storage for small devices due to its efficiency, portability, low power consumption and large capacity. Unlike on hard disks, however, write operation on flash memory is much more expensive than read operation, so that it is critical for performance enhancement to reduce the number of executions of write operation. This paper proposes static analysis to rewrite a program to reduce the total number of write operations by merging writable data in a minimum number of pages. To achieve this, we collect information about writable areas by static analysis, and about frequently executed paths by profiling for practicality, and combine both to rewrite the application program to reallocate data. The performance enhancement gained from the proposed methods is shown using a FAST simulator.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.1
• /
• pp.1-7
• /
• 2012

A Smartphone has an ability accessing Internet by URL stored in NFC(Near Field Communication) Tag for storing the information of items, blogs and web pages. Because the system works through the Internet with URL, however, it needs to pay some costs like communication fee and time. If we can store the web page on the tags, we can save the communication overhead. But they have too small memory to store it. In this paper, we introduce the Micro-Webpage technology which can be stored in NFC tag or QR(Quick Response) code. To make a Micro-Webpage, we remove control tags from the web page to leave a user original content. The removed control tags are stored in our smartphone application as a template. The user content is also compressed to a smaller one by an lossless compression algorithm. When a tag is read, the stored content is decompressed and, it is combined with the template to make the original web page. We have implemented a prototype of Micro-Webpage system on Android platform and confirmed that the prototype has reasonable performance improvements in saving memory and loading web page time.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.67-73
• /
• 2020

In this paper, we present a CNN-based gesture recognition approach which reduces the memory burden of input data. Most of the neural network-based gesture recognition methods have used a sequence of frame images as input data, which cause a memory burden problem. We use a motion history image in order to define a meaningful gesture. The motion history image is a grayscale image into which the temporal motion information is collapsed by synthesizing silhouette images of a user during the period of one meaningful gesture. In this paper, we first summarize the previous traditional approaches and neural network-based approaches for gesture recognition. Then we explain the data preprocessing procedure for making the motion history image and the neural network architecture with three convolution layers for recognizing the meaningful gestures. In the experiments, we trained five types of gestures, namely those for charging power, shooting left, shooting right, kicking left, and kicking right. The accuracy of gesture recognition was measured by adjusting the number of filters in each layer in the proposed network. We use a grayscale image with 240 × 320 resolution which defines one meaningful gesture and achieved a gesture recognition accuracy of 98.24%.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.1-9
• /
• 2019

Hard disks, which have long been used as secondary storage in computing systems, are increasingly being replaced by solid state drives (SSDs), due to their relatively fast data input / output speeds and small, light weight. SSDs that use NAND flash memory as a storage medium are significantly different from hard disks in terms of physical operation and internal operation. In particular, there is a feature that data overwrite can not be performed, which causes erase operation before writing. In order to solve this problem, a hot data for frequently updating a data for a specific page is distinguished from a cold data for a relatively non-hot data. Hot data identification helps to improve overall performance by identifying and managing hot data separately. Among the various hot data identification methods known so far, there is a technique of recording consecutive write requests by using a Bloom filter and judging the values by hot data. However, the Bloom filter technique has a problem that a new bit array must be generated every time a set of items is changed. In addition, since it is judged based on a continuous write request, it is possible to make a wrong judgment. In this paper, we propose a method using a counting filter for accurate hot data verification. The proposed method examines consecutive write requests. It also records the number of times consecutive write requests occur. The proposed method enables more accurate hot data verification.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.124-126
• /
• 2006

Mobile Ad hoc networking is an emerging technology and in these days many applications are being developed to run on these networks. In these networks lookup services are very important because all nodes do not have same resources in term of memory and computing power. Nodes need to use different services offered by different servers. Reliable and efficient scheme should be available for lookup services due to limited bandwidth and low computing power of devices in mobile ad hoc networks. Due to mobility and rapid change in network topology, lookup mechanism used in wired network is not appropriate. Service discovery mechanism can be divided into two main categories Centralized and Distributed. Centralized mechanism is not reliable as there is no central node in these networks. Secondly centralized mechanism leads toward single point failure. We can handle the service discovery mechanism by distributing server's information to each node. But this approach is also not appropriate due to limited bandwidth and rapid change in network. In this paper, we present reliable lookup service scheme which is based on distributed mechanism. We are not using replication approach as well due to low bandwidth of wireless networks. In this scheme service discovery mechanism will be handled through different lookup servers. Reliability is the key feature of our proposed scheme.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.411-417
• /
• 2016

Since the development of Graphic Processing Unit (GPU) in 1999, the development speed of GPUs has become much faster than that of CPUs and currently, the computational power of GPUs exceeds CPUs dozens and hundreds times in terms of decimal calculations and costs much less. Owing to recent technological development of hardwares, general-purpose computing and utilization using GPUs are on the rise. Thus, in this paper, we have identified the elements to be considered for the Smart Grid Security. Focusing on a Performance Improvement of the Basic Algorithm for the Stateful Inspection to Detect DDoS Attacks using CUDA. In the program, we compared the search speeds of GPU against CPU while they search for the suffix trees. For the computation, the system constraints and specifications were made identical during the experiment. We were able to understand from the results of the experiment that the problem-solving capability improves when GPU is used. The other finding was that performance of the system had been enhanced when shared memory was used explicitly instead of a global memory as the volume of data became larger.

• Journal of Computing Science and Engineering
• /
• v.4 no.3
• /
• pp.207-224
• /
• 2010

This paper presents a compression scheme for mesh geometry, which is suitable for mobile graphics. The main focus is to enable real-time decoding of compressed vertex positions while providing reasonable compression ratios. Our scheme is based on local quantization of vertex positions with mesh partitioning. To prevent visual seams along the partitioning boundaries, we constrain the locally quantized cells of all mesh partitions to have the same size and aligned local axes. We propose a mesh partitioning algorithm to minimize the size of locally quantized cells, which relates to the distortion of a restored mesh. Vertex coordinates are stored in main memory and transmitted to graphics hardware for rendering in the quantized form, saving memory space and system bus bandwidth. Decoding operation is combined with model geometry transformation, and the only overhead to restore vertex positions is one matrix multiplication for each mesh partition. In our experiments, a 32-bit floating point vertex coordinate is quantized into an 8-bit integer, which is the smallest data size supported in a mobile graphics library. With this setting, the distortions of the restored meshes are comparable to 11-bit global quantization of vertex coordinates. We also apply the proposed approach to compression of vertex attributes, such as vertex normals and texture coordinates, and show that gains similar to vertex geometry can be obtained through local quantization with mesh partitioning.