• Title/Summary/Keyword: recall memory

Search Result 163, Processing Time 0.022 seconds

Improving the Performance of Korean Text Chunking by Machine learning Approaches based on Feature Set Selection (자질집합선택 기반의 기계학습을 통한 한국어 기본구 인식의 성능향상)

  • Hwang, Young-Sook;Chung, Hoo-jung;Park, So-Young;Kwak, Young-Jae;Rim, Hae-Chang
    • Journal of KIISE:Software and Applications
    • /
    • v.29 no.9
    • /
    • pp.654-668
    • /
    • 2002
  • In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

Preliminary Study of Neurocognitive Dysfunction in Adult Moyamoya Disease and Improvement after Superficial Temporal Artery-Middle Cerebral Artery Bypass

  • Baek, Hyun Joo;Chung, Seung Young;Park, Moon Sun;Kim, Seong Min;Park, Ki Suk;Son, Hee Un
    • Journal of Korean Neurosurgical Society
    • /
    • v.56 no.3
    • /
    • pp.188-193
    • /
    • 2014
  • Objective : Moyamoya disease (MMD) is a chronic cerebrovascular occlusive disease of unknown etiology. In addition, the neurocognitive impairment of adults with MMD is infrequently reported and, to date, has not been well described. We attempted to determine both the neurocognitive profile of adult moyamoya disease and whether a superficial temporal artery-middle cerebral artery (STA-MCA) anastomosis can improve the neurocognitive impairment in exhibiting hemodynamic disturbance without stroke. Methods : From September 2010 through November 2012, 12 patients with angiographically diagnosed MMD underwent STA-MCA anastomosis for hemodynamic impairment. Patients with hypoperfusion and impaired cerebrovascular reserve (CVR) capacity but without evidence of ischemic stroke underwent a cognitive function test, the Seoul Neuropsychological Screening Battery (SNSB). Five patients agreed to undergo a follow-up SNSB test. Data from preoperative and postoperative neurocognitive function tests were compared and analyzed. Results : Five of 12 patients were enrolled. The median age was 45 years (range, 24-55 years). A comparison of preoperative to postoperative status of SNSB, memory domain, especially delayed recall showed significant improvement. Although most of the domains showed improvement after surgery, the results were not statistically significant. Conclusion : In our preliminary study, large proportions of adult patients with MMD demonstrate disruption of cognitive function. This suggests the possibility of chronic hypoperfusion as a primary cause of the neurocognitive impairment. When preoperative and postoperative status of cognitive function was compared, memory domain showed remarkable improvement. Although further study is needed, neurocognitive impairment may be an indication for earlier intervention with reperfusion procedures that can improve cognitive function.

Korean Sentence Boundary Detection Using Memory-based Machine Learning (메모리 기반의 기계 학습을 이용한 한국어 문장 경계 인식)

  • Han Kun-Heui;Lim Heui-Seok
    • The Journal of the Korea Contents Association
    • /
    • v.4 no.4
    • /
    • pp.133-139
    • /
    • 2004
  • This paper proposes a Korean sentence boundary detection system which employs k-nearest neighbor algorithm. We proposed three scoring functions to classify sentence boundary and performed comparative analysis. We uses domain independent linguistic features in order to make a general and robust system. The proposed system was trained and evaluated on the two kinds of corpus; ETRI corpus and KAIST corpus. As experimental results, the proposed system shows about $98.82\%$ precision and $99.09\%$ recall rate even though it was trained on relatively small corpus.

  • PDF

Effectiveness Measurement of TV Advertisement for Fashion Goods with EEG and Affective Responses as Determined by the Types of Appeal (뇌파와 감정반응 평가를 통한 패션제품의 TV 광고효과 연구)

  • Choi Ju-Young;Kim Mi-Sook
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.29 no.9_10 s.146
    • /
    • pp.1230-1240
    • /
    • 2005
  • The purpose of this study was to apply a scientific and systematic method for assessing fashion goods' TV ads effects by EEG and questionnaires as determined by the type of ads appeal. Ads stimulants used in the survey were limited to underwear and sportswear that were advertised during $2000{\sim}2002$ on TV: 4 information-transferring and 4 emotion-evoking ads were used. Subjects were thirty healthy male and female college students. EEG was extracted from six lobes and the recorded EEG was analyzed by the range of frequency of ${\theta},\;{\alpha}\;and\;{\beta}$ waves. Data were analyzed by SPSS 11.0 with reliability test, $x^2$-analysis, t-test and frequency analysis. The emotion-evoking ads showed higher scores in memory, recall and attitude towards the ads. The responses of ${\theta}\;and\;{\alpha}$ wave were active throughout the ads but the response of ${\beta}$ wave was not. The results by the survey and the EEG test showed high similarities, indicating the EEG tests could be used as the supplementary tool for measuring ads effects.

The Effects of Walking and Yoga Exercise on the Cognitive Functions in the Elderly Women (걷기와 요가가 포함된 복합운동이 여성노인의 인지기능에 미치는 영향)

  • Kim, Yong-Geon;Han, Dong-Wook;Lee, Byoung-Kwon
    • Journal of the Korean Society of Physical Medicine
    • /
    • v.5 no.2
    • /
    • pp.211-221
    • /
    • 2010
  • Purpose : The purpose of this study is to find out the effects of combined exercise including walking and yoga on cognitive functions in the elderly women. Methods : Sixteen elderly women aged above 65 are invited in this study. Each subject participated in exercise three times a week for eight weeks from July 14th to September 13th in 2008. The changes between pre and post exercise are analyzed by Wilcoxon sign rank test and repeated ANOVA test with SPSS (ver 17.0) package program. Results : After exercise, In the below 23 points group, only interference STROOP test (p<.05) among sub items of Cognition Scale for Older Adults (CSOA) is improved significantly. In the above 24 points group, words memory (p<.05), delayed recall (p<.05), and picture naming (p<.05) among sub items of CSOA are improved significantly. But it is no different to the change patterns among two groups. Conclusion : These results show that combined exercise including walking and yoga is helpful to improve cognitive functions. And we find that exercise is helpful in the above 24 points elderly women more than in the below 23 points.

A Network Intrusion Security Detection Method Using BiLSTM-CNN in Big Data Environment

  • Hong Wang
    • Journal of Information Processing Systems
    • /
    • v.19 no.5
    • /
    • pp.688-701
    • /
    • 2023
  • The conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.

Intelligence and Neuropsychological Tests Findings in Obsessive-Compulsive Disorder (강박장애 환자의 지능과 신경심리검사 소견)

  • Kim, Chan-Hyung;Lee, Sung-Hoon;Kim, Ji-Woong;Lee, Hee-Sang;Kim, Kyung-Hee;Lee, Hong-Shick
    • Sleep Medicine and Psychophysiology
    • /
    • v.5 no.2
    • /
    • pp.194-201
    • /
    • 1998
  • Objectives : This study was aimed to investigate the differences in intelligence and neuropsychological test findings between patients with obsessive-compulsive disorder(OCD) and normal controls, and to find out brain functions. Methods : To examine the brain functions, Halsted Reitan neuropsychological test, computerized neuropsychological test, Wechsler Memory scale and K-WAIS were applied. Subjects of this study consisted of 12 patients with OCD and 17 normal controls who were matched for age, handedness and education year. Results : The verbal intelligence of OCD was significantly higher than that of normal controls. But there was no significant difference in total and performance intelligence between groups. The total time of tactual performance test in OCD was significantly delayed than that in normal controls. Also the visual recall of Wechsler memory scale in OCD was more impaired than that in normal controls. Conclusion : These findings support that visual-spatial memory, which is related to basal ganglia, is impaired in OCD.

  • PDF

The Effect of Fumanet Exercise Program for Life care on Cognition Function, Depression in Dementia (라이프케어 증진을 위한 후마네트 운동프로그램이 치매노인의 인지기능, 우울기능에 미치는 영향)

  • Lee, Na Yun;Ahn, So Hyun;Yang, Yeong Ae
    • Journal of agricultural medicine and community health
    • /
    • v.45 no.3
    • /
    • pp.121-129
    • /
    • 2020
  • Purpose: As dementia progresses, cognitive function decreasing leads to memory loss, speech degradation, time and space degradation and judgment degradation, which causes difficulties in carrying out tasks related to daily life. It was said that community-based non-drug intervention therapy for early dementia patients was important to participate in entertainment treatment, including activities such as awareness and exercise therapy, exercise rehabilitation, aerobic exercise, and art. Methods: This study conducted 15 experimental and 15 control groups(experimental group : Fumanet exercise, control group : general occupational therapy) for eight weeks at the Daycare Center in Gyeonggi-do to find out the impact of the Fumanet exercise program on cognitive and depression functions of the elderly. The pre-post evaluation used KGDS, MMSE. Results: There were significant differences between the two groups in the function of menopause, memory recall, attention concentration and calculation, and depression, and no significant results were obtatined in memory registration, language function, understanding and fracture. The Fumanet movement was judged to be effective in improving cognitive function and reducing depression for the elderly with dementia. Conclisions: The Fumanet movement was judged to be effective in improving cognitive function and reducing depression for the elderly with dementia.

Experimental Comparison of Network Intrusion Detection Models Solving Imbalanced Data Problem (데이터의 불균형성을 제거한 네트워크 침입 탐지 모델 비교 분석)

  • Lee, Jong-Hwa;Bang, Jiwon;Kim, Jong-Wouk;Choi, Mi-Jung
    • KNOM Review
    • /
    • v.23 no.2
    • /
    • pp.18-28
    • /
    • 2020
  • With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

The effect of semantic categorization of episodic memory on encoding of subordinate details: An fMRI study (일화 기억의 의미적 범주화가 세부 기억의 부호화에 미치는 영향에 대한 자기공명영상 분석 연구)

  • Yi, Darren Sehjung;Han, Sanghoon
    • Korean Journal of Cognitive Science
    • /
    • v.28 no.4
    • /
    • pp.193-221
    • /
    • 2017
  • Grouping episodes into semantically related categories is necessary for better mnemonic structure. However, the effect of grouping on memory of subordinate details was not clearly understood. In an fMRI study, we tested whether attending superordinate during semantic association disrupts or enhances subordinate episodic details. In each cycle of the experiment, five cue words were presented sequentially with two related detail words placed underneath for each cue. Participants were asked whether they could imagine a category that includes the previously shown cue words in each cycle, and their confidence on retrieval was rated. Participants were asked to perform cued recall tests on presented detail words after the session. Behavioral data showed that reaction times for categorization tasks decreased and confidence levels increased in the third trial of each cycle, thus this trial was considered to be an important insight where a semantic category was believed to be successfully established. Critically, the accuracy of recalling detail words presented immediately prior to third trials was lower than those of followed trials, indicating that subordinate details were disrupted during categorization. General linear model analysis of the trial immediately prior to the completion of categorization, specifically the second trial, revealed significant activation in the temporal gyrus and inferior frontal gyrus, areas of semantic memory networks. Representative Similarity Analysis revealed that the activation patterns of the third trials were more consistent than those of the second trials in the temporal gyrus, inferior frontal gyrus, and hippocampus. Our research demonstrates that semantic grouping can cause memories of subordinate details to fade, suggesting that semantic retrieval during categorization affects the quality of related episodic memory.