• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.965-978
• /
• 2006

This paper implements an automatic Korean word-spacing system based on word-recognition using morpheme unigrams and the pattern that the categories of those morpheme unigrams share within a candidate word. Although previous work on Korean word-spacing models has produced the advantages of easy construction and time efficiency, there still remain problems, such as data sparseness and critical memory size, which arise from the morpho-typological characteristics of Korean. In order to cope with both problems, our implementation uses the stochastic information of morpheme unigrams, and their category patterns, instead of word unigrams. A word's probability in a sentence is obtained based on morpheme probability and the weight for the morpheme's category within the category pattern of the candidate word. The category weights are trained so as to minimize the error means between the observed probabilities of words and those estimated by words' individual-morphemes' probabilities weighted according to their categories' powers in a given word's category pattern.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.563-569
• /
• 2004

A set of Zernike moments has been successfully used for object recognition or content-based image retrieval systems. Real time applications using Zernike moments, however, have been limited due to its complicated definition. Conventional methods to compute Zernike moments fast have focused mainly on the radial components of the moments. In this paper, utilizing symmetric/anti-symmetric properties of Zernike basis functions, we propose a fast and efficient method for Zernike moments. By reducing the number of operations to one quarter of the conventional methods in the proposed method, the computation time to generate Zernike basis functions was reduced to about 20% compared with conventional methods. In addition, the amount of memory required for efficient computation of the moments is also reduced to a quarter. We also showed that the algorithm can be extended to compute the similar classes of rotational moments, such as pseudo-Zernike moments, and ART descriptors in same manner.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1765-1794
• /
• 2019

Genetic Programming (GP) is an intelligence technique whereby computer programs are encoded as a set of genes which are evolved utilizing a Genetic Algorithm (GA). In other words, the GP employs novel optimization techniques to modify computer programs; imitating the way humans develop programs by progressively re-writing them for solving problems automatically. Trial programs are frequently altered in the search for obtaining superior solutions due to the base is GA. These are evolutionary search techniques inspired by biological evolution such as mutation, reproduction, natural selection, recombination, and survival of the fittest. The power of GAs is being represented by an advancing range of applications; vector processing, quantum computing, VLSI circuit layout, and so on. But one of the most significant uses of GAs is the automatic generation of programs. Technically, the GP solves problems automatically without having to tell the computer specifically how to process it. To meet this requirement, the GP utilizes GAs to a "population" of trial programs, traditionally encoded in memory as tree-structures. Trial programs are estimated using a "fitness function" and the suited solutions picked for re-evaluation and modification such that this sequence is replicated until a "correct" program is generated. GP has represented its power by modifying a simple program for categorizing news stories, executing optical character recognition, medical signal filters, and for target identification, etc. This paper reviews existing literature regarding the GPs and their applications in different scientific fields and aims to provide an easy understanding of various types of GPs for beginners.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Korean Journal of Environmental Agriculture
• /
• v.40 no.1
• /
• pp.1-12
• /
• 2021

BACKGROUND: G protein-coupled receptors (GPCRs) are widely distributed in various organisms. Insect GPCRs shown as in vertebrate GPCRs are membrane receptors that coordinate or involve in various physiological processes such as learning/memory, development, locomotion, circadian rhythm, reproduction, etc. This study aimed to identify GPCRs expressed in fat body and compare the expression pattern of GPCRs in different temperature conditions. METHODS AND RESULTS: To identify GPCRs genes and compare their expression in different temperature conditions, total RNAs of fat body in Plutella xylostella larva were extracted and the transcriptomes have been analyzed via next generation sequencing method. From the fat body transcriptomes, genes that belong to GPCR Family A, B, and F were identified such as opsin, gonadotropin-releasing hormone receptor, neuropeptide F (NPF) receptor, muthuselah (Mth), diuretic hormone receptor, frizzled, etc. Under low temperature, expressions of GPCRs such as C-C chemokine receptor (CCR), opsin, prolactin-releasing peptide receptor, substance K receptor, Mth-like receptor, diuretic hormone receptor, frizzled and stan were higher than those at 25℃. They are involved in immunity, feeding, movement, odorant recognition, diuresis, and development. In contrast to the control (25℃), at high temperature GPCRs including CCR, gonadotropin-releasing hormone receptor, moody, NPF receptor, neuropeptide B1 receptor, frizzled and stan revealed higher expression whose biological functions are related to immunity, blood-brain barrier formation, feeding, learning, and reproduction. CONCLUSION: Transcriptome of fat body can provide understanding the pools of GPCRs. Identifications of fat body GPCRs may contribute to develop new targets for the control of insect pests.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.850-858
• /
• 2022

To deploy Gate Recurrent Units (GRU) on resource-constrained embedded devices, this paper presents a reconfigurable FPGA-based GRU accelerator that enables structured compression. Firstly, a dense GRU model is significantly reduced in size by hybrid quantization and structured top-k pruning. Secondly, the energy consumption on external memory access is greatly reduced by the proposed reuse computing pattern. Finally, the accelerator can handle a structured sparse model that benefits from the algorithm-hardware co-design workflows. Moreover, inference tasks can be flexibly performed using all functional dimensions, sequence length, and number of layers. Implemented on the Intel DE1-SoC FPGA, the proposed accelerator achieves 45.01 GOPs in a structured sparse GRU network without batching. Compared to the implementation of CPU and GPU, low-cost FPGA accelerator achieves 57 and 30x improvements in latency, 300 and 23.44x improvements in energy efficiency, respectively. Thus, the proposed accelerator is utilized as an early study of real-time embedded applications, demonstrating the potential for further development in the future.

• Nutrition Research and Practice
• /
• v.16 no.2
• /
• pp.173-193
• /
• 2022

BACKGROUND/OBJECTIVES: Alzheimer's disease (AD) is one of the most representative neurodegenerative disease mainly caused by the excessive production of amyloid beta (Aβ). Several studies on the antioxidant activity and protective effects of Populus tomentiglandulosa (PT) against cerebral ischemia-induced neuronal damage have been reported. Based on this background, the present study investigated the protective effects of PT against cognitive impairment in AD. MATERIALS/METHODS: We orally administered PT (50 and 100 mg/kg/day) for 14 days in an Aβ_25-35-induced mouse model and conducted behavioral experiments to test cognitive ability. In addition, we evaluated the levels of aspartate aminotransferase (AST) and alanine aminotransferase (ALT) in serum and measured the production of lipid peroxide, nitric oxide (NO), and reactive oxygen species (ROS) in tissues. RESULTS: PT treatment improved the space perceptive ability in the T-maze test, object cognitive ability in the novel object recognition test, and spatial learning/long-term memory in the Morris water-maze test. Moreover, the levels of AST and ALT were not significantly different among the groups, indicating that PT did not show liver toxicity. Furthermore, administration of PT significantly inhibited the production of lipid peroxide, NO, and ROS in the brain, liver, and kidney, suggesting that PT protected against oxidative stress. CONCLUSIONS: Our study demonstrated that administration of PT improved Aβ_25-35-induced cognitive impairment by regulating oxidative stress. Therefore, we propose that PT could be used as a natural agent for AD improvement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2991-3007
• /
• 2022

Two dimensional locality preserving projections (2D-LPP) is an improved algorithm of 2D image to solve the small sample size (SSS) problems which locality preserving projections (LPP) meets. It's able to find the low dimension manifold mapping that not only preserves local information but also detects manifold embedded in original data spaces. However, 2D-LPP is simple and elegant. So, inspired by the comparison experiments between two dimensional linear discriminant analysis (2D-LDA) and linear discriminant analysis (LDA) which indicated that matrix based methods don't always perform better even when training samples are limited, we surmise 2D-LPP may meet the same limitation as 2D-LDA and propose a novel matrix exponential method to enhance the performance of 2D-LPP. 2D-MELPP is equivalent to employing distance diffusion mapping to transform original images into a new space, and margins between labels are broadened, which is beneficial for solving classification problems. Nonetheless, the computational time complexity of 2D-MELPP is extremely high. In this paper, we replace some of matrix multiplications with multiple multiplications to save the memory cost and provide an efficient way for solving 2D-MELPP. We test it on public databases: random 3D data set, ORL, AR face database and Polyu Palmprint database and compare it with other 2D methods like 2D-LDA, 2D-LPP and 1D methods like LPP and exponential locality preserving projections (ELPP), finding it outperforms than others in recognition accuracy. We also compare different dimensions of projection vector and record the cost time on the ORL, AR face database and Polyu Palmprint database. The experiment results above proves that our advanced algorithm has a better performance on 3 independent public databases.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• Korean Journal of Psychosomatic Medicine
• /
• v.11 no.2
• /
• pp.118-136
• /
• 2003

Objective: This study is to examine the neuropsychological and developmental characteristics of the Computerized Neurocognitive Function Test among normal children in elementary school. Methods: K-ABC, K-PIC, and Computerized Neurocognitive Function Test were performed to the 120 body of normal children(10 of each male and female) from June, 2002 to January, 2003. Those children had over the average of intelligence and passed the rule out criteria. One-way ANOVA and Bonferroni were used for statistical analysis. Results: In sampling of normal children in elementary school, the control of intelligence level and strict rule out criteria were applied. As a result, although 21.1% were excluded from of total participants, the children that passed the rule out criteria had over the average of intelligence and not differ in the intelligence level among the graders. Comparing Computerized Neurocognitive Function Test results among the graders, almost of variables had significant difference among the graders and especially between the 1st to 2nd and the 5th to 6th graders. In the attention tests, as rising the graders, the performance of tests were improved. In the short-term memory tests, the difference between forward and backward tests were same as the previous research result. The verbal auditory learning test composed of recall task and visual figure memory test composed of recognition task were same as the previous research result using the individual power or achievement test and also as rising the graders, the performance of those tests were improved. The higher cognitive function tests had the same results with other tests. Conclusion: The Computerized Neurocognitive Function Test devised for adult can be used of assessing child neuropsychological characteristics. For this objective, more strict sampling criteria, control of the intelligence and psychopathology were needed.