• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.23-30
• /
• 2021

Sentiment Analysis has become very important field of research because posting of reviews is becoming a trend. Supervised, unsupervised and semi supervised machine learning methods done lot of work to mine this data. Feature engineering is complex and technical part of machine learning. Deep learning is a new trend, where this laborious work can be done automatically. Many researchers have done many works on Deep learning Convolutional Neural Network (CNN) and Long Shor Term Memory (LSTM) Neural Network. These requires high processing speed and memory. Here author suggested two models simple & bidirectional deep leaning, which can work on text data with normal processing speed. At end both models are compared and found bidirectional model is best, because simple model achieve 50% accuracy and bidirectional deep learning model achieve 99% accuracy on trained data while 78% accuracy on test data. But this is based on 10-epochs and 40-batch size. This accuracy can also be increased by making different attempts on epochs and batch size.

• Journal of Oriental Neuropsychiatry
• /
• v.9 no.2
• /
• pp.37-44
• /
• 1998

Purpose: This study was conducted to find out the effects od Sahyangsohapwon on learning and memory of rats.Method: In the experiment, rats were divided two groups. One was control group which was adminstered Sahyangsohapwon and the other was sample group administered placebo. Numbers of each group were 13 rats. 8-arm radial maze task was used in it, and working memory test and retention(reference memory) test were done.Before the beginning of the test, the rats were deprived of water for 24hrs.In the frist test, each of eight arm was baited with water and a rat was permitted to remain on the maze until all eight arms were entered. A working memory error was defined as revisit of any previously entered arm. When a rat made an error not exceeding one time in consecutive 3 days-performance, it was regarded as learning criteria and the test was ended. The reference memory was evaluated with total days which it took rats to pass the learning crtirtia.The second test was performed after 24 hours when the first test was over. When a rat entered 4 arms, the entrance of arm was cut off during 30 seconds.Here the number if errors which was produced during a rat find remaining 4 tracks was regarded as the index of memory.This experiment compared the number of error at the control group with that of the sample group.Result: 1. In the first test, it was shown that the sample group took 7.69${\pm}$1.11 days and the control group 9.31${\pm}$1.97 days to pass the learning criteria.There was statistically significant reference mernory development at the sample group.2. In the second test, the frequency of errors made by the two groups were 0.92${\pm}$1.32 times for the control group and 1.23${\pm}$1.59 times for the Sahyangsohapwon group. There was no difference between the groups in frequency of errors.Conclusion: It is suggested that Sahyangsohapwon has effects on the improvement of learning and memory.

• Sleep Medicine and Psychophysiology
• /
• v.3 no.1
• /
• pp.15-24
• /
• 1996

After rapid eye movement(REM) sleep was idenified in 1953, a lively interest developed concerning a possible role of this kind of sleep in memory processes. The author reviewed studies relating REM to memory/learning. Many studies in animals and humans gave substantial evidence for relating REM sleep to memory function. The evidence supporting the position taken in this paper comes from experiments showing that : (1) learning session is followed by the significant augmentation of REM sleep : (2) REM sleep deprivation, prior to learning or immediately thereafter, impairs the formation of a permanent memory/learning : (3) there is a vulnerable period of time(eg, REM sleep "window") following succussful learning, during which REM sleep deprivation results in memory impairment : (4) theta rhythm which develops during REM sleep induces long-term potentiation in hippocampus : (5) there are some evidences providing the relationship of neurotransmitter systems to the maintenance of REM sleep and memory storage processes.

• School Mathematics
• /
• v.6 no.4
• /
• pp.373-388
• /
• 2004

This paper is to develop teaching procedures of low achievers in mathematics by using mindmaps. For this, we firstly set the teaching process on basis of literature research. And then we choose four subjects who had serious problems of both memory and mathematics achievement. we also choose the several topics of geometry and measure which could be a big burden of memory as stuff for mindmap activities. The results led us to that using mindmap activities in learning and teaching mathematics could effect on that kind of students' mathematical achievement and mathematical attitude as well as retention of mathematical concepts. It implied that we could develop individual programs for students who have different problems in learning mathematics.

• The Journal of Pediatrics of Korean Medicine
• /
• v.18 no.1
• /
• pp.207-220
• /
• 2004

Objective: This study was conducted to find out the effect of saruktanggamibang(SRT) on memory and learning of rats. Methods: The mon·is water maze was used. It was performed Acquisition test, Retention test of water maze. After Behavioral test, it was investigated AChE cell numbers of CAI and CA3 on hippocampus. Results: of water maze revealed that acqusitive abilities of SAP+SRT group significantly improved on 3, 4, 5th day compared with SAP+Saline group. Retention test of water maze didn't reveal that retentive abilities of SAP+SRT group significantly improved comparing with another group. ChAT cell numbers of medial septum of SAP+SRT group significantly increased compared with SAP+Saline group. AChE cell numbers of CAl and CA3 on hippocampus of Sham+SRT group significantly increased compared with Sham group. And AChE cell numbers of CAl and CA3 on hippocampus of SAP+SRT group significantly increased compared with SAP+Saline group. Conclusion: Saruktanggamibang(SRT) has an effect on memory and learning of rats.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.16 no.6
• /
• pp.1236-1242
• /
• 2002

In order to make an efficient prescription and cope with dementia, learning and memory functions of Sprague-Dawley model rats were tested with Morris water maze. And to evaluate the effect of the sample drug(CHM) on choline acetyltranferase and acetylcholine esterase, immunoreactive measurement and enzymatic activity measuring were carried out. Rats were injected with ibotenic acid through hippocampus CA1 and CA3 area. The results are as following. CHM improves the learning ability in the acquisition test and memory function in the retention test significantly. And CHM increases the level of AChE which is resolving acetylcholine. Though it doesn't increase the level of ChAT significantly which is synthesizing acetylcholine, but it shows the tendency of increase. So these results show that CHM improve the cholinergic catabolism and anabolism, and the increment of metabolic activity of cholinergic system. Thus it can be concluded that CHM will be helpful to cholinergic brain disease induced by primary or senile reduction of acetylcholine secretive activity.

• Archives of Pharmacal Research
• /
• v.24 no.3
• /
• pp.234-239
• /
• 2001

Three types of learning and memory tests (Morris water maze, active and passive avoidance) were performed in rats following intracerebroventricular infusion of ethylcholine aziridium (AF64A). In Morris water maze, AF64A-treated rats showed the delayed latencies to find the platform iron 6th day after the infusion. In pretrained rats, AF64A caused the significant delay of latency at 7th days but not 8th day. In the active avoidance for the pretrained rats, the escape latency was significantly delayed in AF64A-treatment. The percentages of avoidance in AF64A-treated rats were less increased than those in the control. Especially, the percentage of no response in the AF64A-treated rats was markedly increased in the first half trials. In the passive avoidance, AF64A-treated rats shortened the latency 1.5 h after the electronic shock, but not 24 h. AF64A also caused the pretrained rats to shorten the latency 7th day after the infusion, but not 8th day. These results indicate that AF64A might impair the learning and memory. However, these results indicate that the disturbed memory by AF64A might rapidly recover after the first retrain. Furthermore, these results suggest that AF64A may be a useful agent for the animal model of learning for Spatial cognition .

• The Korea Journal of Herbology
• /
• v.24 no.4
• /
• pp.165-171
• /
• 2009

Objectives : In the present study, we assessed the effects of the ethanolic extract of Crataegus pinnatifida Bunge on the learning and memory impairments induced by scopolamine using the passive avoidance and the Morris water maze tasks in mice. Methods : The cognition-enhancing effect of C. pinnatifida was investigated using a passive avoidance test, the Morris water maze test and Y-maze test in mice. Drug-induced amnesia was induced by treating animals with scopolamine (1 mg/kg, i.p.). Results : The ethanolic extract of C. pinnatifida (100, and 200 mg/kg) significantly reversed the scopolamine-induced cognitive impairments in the passive avoidance test (p < 0.05). Moreover, C. pinnatifida (200 mg/kg) also improved escape latencies in training trials and increased swimming times and distances within the target zone of the Morris water maze (p < 0.05). On the Y-maze test, C. pinnatifida (100, and 200 mg/kg) also significantly reversed scopolamine- induced cognitive impairments in mice (p < 0.05). Conclusions : The ethanolic extract of Crataegus pinnatifida dramatically possesses the anti-amnestic and cognitive-enhancing activities related to the memory processes, and these activities were parallel to treatment duration and dependent on the learning models.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.31 no.5
• /
• pp.270-276
• /
• 2017

The aim of this study was to investigate the effects of the water extract of Albizziae Cortex (AC) on the learning and memory impairments. AC was administered to normal mouse and scopolamine-injected amnesia mouse model. Passive avoidance test, Y-maze test, and Morris water maze test were conducted to confirm the cognitive-enhancing activities of AC. Acetylcholinesterase (AChE) activity and acetylcholine (Ach) content were measured after oral administration of AC. On the passive avoidance test, AC (200 mg/kg) significantly increased latency time and recovered scopolamine-impaired learning and memory in mice. In addition, AC (200 mg/kg) reduced Exploration time in target quadrant and reversed the scopolamine-induced cognitive impairments in the Y-maze test. Moreover, AC (200 mg/kg) increased exploration time in target quadrant and improved scopolamine-reduced escape latencies in the Morris water maze test. These effects were presented by regulatory effects of AC on AChE activity and Ach content. Taken together, AC increases cognitive-enhancing activities and ameliorates scopolamine-induced learning and memory impairment. AC might be a potential agent for prevention and treatment of amnesia and dementia.