• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.1-9
• /
• 2013

Even though the multiple pages TLB are effective in improving the performance, a conventional method with OS support cannot utilize multiple page sizes in user application. Thus, we propose a new multiple-TLB structure supporting multiple page sizes for high performance and low power consumption without any operating system support. The proposed TLB is organised as two parts of a S-TLB(Small TLB) with a small page size and a L-TLB(Large TLB) with a large page size. Both are designed as fully associative bank structures. The S-TLB stores small pages are evicted from the L-TLB, and the L-TLB stores large pages including a small page generated by the CPU. Each one bank module of S-TLB and L-TLB can be selectively accessed base on particular one and two bits of the virtual address generated from CPU, respectively. Energy savings are achieved by reducing the number of entries accessed at a time. Also, this paper proposed the simple 1-bit LRU policy to improve the performance. The proposed LRU policy can present recently referenced block by using an additional one bit of each entry on TLBs. This method can simply select a least recently used page from the L-TLB. According to the simulation results, the proposed TLB can reduce Energy * Delay by about 76%, 57%, and 6% compared with a fully associative TLB, a ARM TLB, and a Dual TLB, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.1
• /
• pp.95-112
• /
• 1998

The Error Backpropagation algorithm is widely used in various areas such as associative memory, speech recognition, pattern recognition, robotics and so on. However, if and when a new leaning pattern has to be added in order to drill, it will have to accomplish a new learning with all previous learning pattern and added pattern from the very beginning. Somehow, it brings about a result which is that the more it increases the number of pattern, the longer it geometrically progress the time required by leaning. Therefore, a so-called Incremental Learning Method has to be solved the point at issue all by means in case of situation which is periodically and additionally learned by numerous data. In this study, not only the existing neural network construction is still remained, but it also suggests a method which means executing through added leaning by a model pattern. Eventually, for a efficiency of suggested technique, both Monk's data and Iris data are applied to make use of benchmark on machine learning field.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2968-2974
• /
• 2015

Method for finding the attractors is the important object to investigate in the linear/additive CA because it is a primary interest in applications like pattern recognition, pattern classification, design of associative memory and query processing etc. But the research has been so far mostly concentrated around linear/additive CA and it is not enough to modelize the complex real life problem. So nonlinear CA is demanded to devise effective models of the problem and solutions around CA model. In this paper we introduce CLT as an upgraded version of RMT and provide the process for finding the attractors and nonreachable states effectively through the CLT.

• Journal of Korean Society of Transportation
• /
• v.17 no.3
• /
• pp.117-130
• /
• 1999

Earthquakes damage roadway bridges and structures, resulting in significant impacts on transportation system Performance and regional economy. Seismic risk analysis (SRA) procedures establish retrofit priorities for vulnerable highway bridges. SRA procedures use average daily traffic volumes to determine the relative importance of a bridge. This research develops a cost-effective transportation network analysis (TAN) procedure for evaluating numerous traffic flow analyses in terms of the additional system cost due to failure. An important feature of the TNA Procedure is the use of an associative memory (AM) approach in the artificial intelligence held. A simple seven-zone network is developed and used to evaluate the TNA procedure. A subset of link failure system states is randomly selected to simulate synthetic post-earthquake network flows. The performance of different AM model is evaluated. Results from numerous link-failure scenarios demonstrate the applicability of the AM models to traffic flow estimation.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.8 no.2
• /
• pp.217-231
• /
• 1997

This paper first reviewed the current neurological theories concerning the etiology of ADHD and secondly, examined results of studies that applied neuropsychological assessment methods in the examination of ADHD children both here in Korea and abroad. ADHD children were found to exhibit characteristic responses indicating deficits in vigilance, sustained attention, distractibility, allocation and regulation of attention in many assessments of attention, in addition to deficits in executive functioning, working and associative memory. Such neuropsychological assessment results suggest that in addition to dysfunction in the frontal lobe and the reticular activation system, dysfunction may exist in other neural pathways involving many areas of the brain. However, because a substantial number of neuropsychological assessment tools being employed in Korea for ADHD children had been developed abroad, a Korean standardization project involving ADHD and normal control children, in addition to other child psychiatric population pools must be conducted in order to obtain appropriate age norms and test validity, and in order to make possible a more accurate and precise comparison and interpretation in the assessment of ADHD children.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.259-266
• /
• 2002

In this paper we implemented various image processing filtering using the format converter. This design method is based on realized the large processor-per-pixel array by integrated circuit technology. These two types of integrated structure are can be classify associative parallel processor and parallel process DRAM (or SRAM) cell. Layout pitch of one-bit-wide logic is Identical memory cell pitch to array high density PEs in integrate structure. This format converter design has control path implementation efficiently, and can be utilize the high technology without complicated controller hardware. Sequence of array instruction are generated by host computer before process start, and instructions are saved on unit controller. Host computer is executed the pixel-parallel operation starting at saved instructions after processing start. As a result, we obtained three result that 1) simple smoothing suppresses higher spatial frequencies, reducing noise but also blurring edges, 2) a smoothing and segmentation process reduces noise while preserving sharp edges, and 3) median filtering may be applied to reduce image noise. Median filtering eliminates spikes while maintaining sharp edges and preserving monotonic variations in pixel values.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.611-618
• /
• 2003

In this paper, we describe a fuzzy inference approach for detecting and classifying shot transitions in video sequences. Our approach basically extends FAM (Fuzzy Associative Memory) to detect and classify shot transitions, including cuts, fades and dissolves. We consider a set of feature values that characterize differences between two consecutive frames as input fuzzy sets, and the types of shot transitions as output fuzzy sets. The inference system proposed in this paper is mainly composed of a learning phase and an inferring phase. In the learning phase, the system initializes its basic structure by determining fuzzy membership functions and constructs fuzzy rules. In the inferring phase, the system conducts actual inference using the constructed fuzzy rules. In order to verify the performance of the proposed shot transition detection method experiments have been carried out with a video database that includes news, movies, advertisements, documentaries and music videos.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1759-1769
• /
• 1997

The Error BackPropagation (EBP) algorithm for multi-layered neural networks is widely used in various areas such as associative memory, speech recognition, pattern recognition and robotics, etc. Nevertheless, many researchers have continuously published papers about improvements over the original EBP algorithm. The main reason for this research activity is that EBP is exceeding slow when the number of neurons and the size of training set is large. In this study, we developed new learning speed acceleration methods using variable learning rate, variable momentum rate and variable slope for the sigmoid function. During the learning process, these parameters should be adjusted continuously according to the total error of network, and it has been shown that these methods significantly reduced learning time over the original EBP. In order to show the efficiency of the proposed methods, first we have used binary data which are made by random number generator and showed the vast improvements in terms of epoch. Also, we have applied our methods to the binary-valued Monk's data, 4, 5, 6, 7-bit parity checker and real-valued Iris data which are famous benchmark training sets for machine learning.

• Journal of English Language & Literature
• /
• v.57 no.1
• /
• pp.107-127
• /
• 2011

Don DeLillo has shown considerable interest in terror, frequently depicting extreme dread of something terrible to happen, in his literary texts. Since more than three thousand innocent people in New York were killed by the 9-11 terrorist attack in 2001, the anticipation about what kind of fiction he would write as a New Yorker was high. DeLillo's novel Falling Man (2007) in fragmentary detail represents the scene of the terrorism from the perspective of Keith Neudecker, a lawyer who escapes the collapsing world trader center. Neudecker's post-traumatic stress disorder in the first chapter is followed by the free-associative portrayal of various impacts of the 9-11 terror on Neudecker's wife Lienne in the second chapter. The random mixture of the first person narratives from such diverse view-point characters as Neudecker's son Justin, relatives and friends, with dialogues and recollections yields a very close picture of the consequences of terrorism. Reading DeLillo's Falling Man in juxtaposition with a Japanese Canadian novel Obasan by Joy Kogawa, reminiscences of the maltreatment of Japanese Canadians during and after the second world war, surfaces the authorial intention of the two novels. They as trauma literature emerge to aim at curing the readers and proposing post-traumatic ethics. Laurie Vickroy's theory of trauma narrative and cure, E. Ann Kaplan's theory of trauma witness narrative and responsibility, and Emmanuel Levinas's theory of trauma memory and ethics offer theoretical grounds for the convincing analysis of the two texts.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.155-161
• /
• 2020

In general, optimization problems are difficult to solve simply. The reason is that the given problem is solved as soon as it is simple, but the more complex it is, the very large number of cases. This study is about the optimization of AI neural network. What we are dealing with here is the relief method for constructing AI network. The main topics deal with non-deterministic issues such as the stability and unstability of the overall network state, cost down and energy down. For this one, we discuss associative memory models, that is, a method in which local minimum memory information does not select fake information. The simulated annealing, this is a method of estimating the direction with the lowest possible value and combining it with the previous one to modify it to a lower value. And nonlinear planning problems, it is a method of checking and correcting the input / output by applying the appropriate gradient descent method to minimize the very large number of objective functions. This research suggests a useful approach to relief method as a theoretical approach to solving optimization problems. Therefore, this research will be a good proposal to apply efficiently when constructing a new AI neural network.