• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.13-21
• /
• 1996

The necessity and usefulness of higher-order neural networks have been well-known since early days of neurocomputing. However the explosive number of terms has hampered the design and training of such networks. In this paper we present an evolutionary learning method for efficiently constructing problem-specific higher-order neural models. The crux of the method is the neural tree representation employing both sigma and pi units, in combination with the use of an MDL-based fitness function for learning minimal models. We provide experimental results in classification and prediction problems which demonstrate the effectiveness of the method. I. Introduction topology employs one hidden layer with full connectivity between neighboring layers. This structure has One of the most popular neural network models been very successful for many applications. However, used for supervised learning applications has been the they have some weaknesses. For instance, the fully mutilayer feedforward network. A commonly adopted connected structure is not necessarily a good topology unless the task contains a good predictor for the full *d*dWs %BH%W* input space.

• The Journal of Korean Physical Therapy
• /
• v.25 no.5
• /
• pp.343-351
• /
• 2013

Purpose: This study was designed to measure the level of professional autonomy regarding physical therapists and to determine the association of organizational and occupational characteristics of the profession with its professional autonomy. Methods: We utilized a structured questionnaire survey of physical therapists (280 persons) in Jeju province. Data were collected from June 25 to July 14 in 2012. An additional 173 (63%) of them were used in the final analysis. Using PASW 18.0, descriptive and Hierarchical Linear Model were performed. Results: Regression analysis Result of Factors influencing Physiotherapist Professionalism, refresher training course (t=4.27), formalization (t=3.13), task significance (t=3.39), and autonomy (t=4.17) had a positive effect. Autonomy (${\beta}$=0.33) and formalization (${\beta}$=0.33) exerted the greatest influence. Conclusion: The survey regarding organizational and job characteristics showeds that occupational reeducation, formalization, and self- regulation constitute a positive part of what the professional autonomy is to be upheld. Results of the survey imply that in order to establish professional autonomy for the profession of physical therapist, the organization must make various efforts to beef up the exclusive knowledge and technology, and professional norms of the occupation that are considered essential for specific problem solving.

• Physical Therapy Korea
• /
• v.2 no.2
• /
• pp.73-84
• /
• 1995

Spasticity has been defined as a motor disorder characterised by a velocity-dependent increase in tonic stretch reflexes with exaggerated tendon jerks resulting in hyperexcitability of the stretch reflexes as one component of the upper motor neuron syndrome. Weakness and loss of dexterity, however, are considered to be more disabling to the patient than changes in muscle tone. The discussion includes the important role that alterations in the physiology of motor units, notably changes in firing rates and muscle fiber atrophy, play in the manifestation of muscle weakness. This paper considers both the neural and mechanical components of spasticity and discusses, in terms of clinical intervention, the implications arising from recent research. Investigations suggest that the resistance to passive movement in individuals with spasticity is due not only to neural mechanisms but also to changes in mechanical properties of muscle. The emphasis is on training the individual to gain control over the muscles required for different tasks, and on preventing secondary and adaptive soft tissue changes and ineffective adaptive motor behaviours.

• Smart Structures and Systems
• /
• v.6 no.3
• /
• pp.335-347
• /
• 2010

Recent advances in hardware and instrumentation technology have allowed the possibility of deploying very large sensor arrays on structures. Exploiting the huge amount of data that can result in order to perform vibration-based structural health monitoring (SHM) is not a trivial task and requires research into a number of specific problems. In terms of pressing problems of interest, this paper discusses: the design and optimisation of appropriate sensor networks, efficient data reduction techniques, efficient and automated feature extraction methods, reliable methods to deal with environmental and operational variability, efficient training of machine learning techniques and multi-scale approaches for dealing with very local damage. The paper is a result of the ESF-S3T Eurocores project "Smart Sensing For Structural Health Monitoring" (S3HM) in which a consortium of academic partners from across Europe are attempting to address issues in the design of automated vibration-based SHM systems for structures.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.904-907
• /
• 2014

In this work we present a robust and fast approach to estimate 3D vehicle pose that can provide results under a specific traffic surveillance conditions. Such limitations are expressed by single fixed CCTV camera that is located relatively high above the ground, its pitch axes is parallel to the reference plane and the camera focus assumed to be known. The benefit of our framework that it does not require prior training, camera calibration and does not heavily rely on 3D model shape as most common technics do. Also it deals with a bad shape condition of the objects as we focused on low resolution surveillance scenes. Pose estimation task is presented as PnP problem to solve it we use well known "POSIT" algorithm [1]. In order to use this algorithm at least 4 non coplanar point's correspondence is required. To find such we propose a set of techniques based on model and scene geometry. Our framework can be applied in real time video sequence. Results for estimated vehicle pose are shown in real image scene.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.199-208
• /
• 2021

Automatic Post Editing(APE) is the study that automatically correcting errors included in the machine translated sentences. The goal of APE task is to generate error correcting models that improve translation quality, regardless of the translation system. For training these models, source sentence, machine translation, and post edit, which is manually edited by human translator, are utilized. Especially in the recent APE research, multilingual pretrained language models are being adopted, prior to the training by APE data. This study deals with multilingual pretrained language models adopted to the latest APE researches, and the specific application method for each APE study. Furthermore, based on the current research trend, we propose future research directions utilizing translation model or mBART model.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.16 no.5
• /
• pp.1025-1034
• /
• 2002

The herbal extract (YMT_02) is a modified herbal extracts from Yukmijihwang-tang (YMJ) to promote memory-enhancing. The YMJ extracts has been widely used as an anti-aging herbal medicine for hundred years in Asian countries. The purpose of this study is to; 1) quantitatively evaluate the memory-enhancing effect of YMT_02 by behavior task, 2) identify candidate genes responsible for enhancing memory by cDNA microarray and 3) assess the anti-oxidant effect of YMT_02 on PC12 cell. Memory retention abilities are addressed by passive avoidance task with Sprague-Dawley (SD) male rat. Before the training session, the rats are subdivided into four groups and administrated with YMT_02, Ginkgo biloba, Soya lecithin and normal saline for 10 days. The retention test was performed. 24 hours after the training session. The retention time of the YMT_02 group was significantly (p<0.05) delayed (～100%), whereas Ginkgo biloba and Soya lecithin treatment delayed 20% and 10% respectively. The hippocampi of YMT_02 and control group were dissected and mANA was further purified. After synthesizing cDNA using oligo-dT primer, the cDNA were applied to Incyte rat GEMTM 2 cDNA microarray. The microarray results show that prealbumin(transthyretin), phosphotidylethanolamine N-methyltransferase, and PEP-19 are expressed abundantly in the YMT_02 treated group. Especially, PEP-19 is a neuron-specific protein, which inhibits apoptotic processes in neuronal cell. On the other hand, transcripts of RAB15, glutamate receptor subunit 2 and CDK108 are abundant in control group. Besides, neuronal genes involved in neuronal death or neurodegeneration such as neuronal-pentraxin and spectrin are abundantly expressed in control group. Additionally, the YMT_02 shows an anti oxidative effect in the PC12 cell. The list of differentially expressed genes may implicate further insight on the action and mechanism behind the memory-enhancing effect of herbal extracts YMT_02, for example, anti-apoptotic, anti-oxidative, and neuroprotective effects.

• Journal of the Korean Society of Safety
• /
• v.39 no.3
• /
• pp.1-6
• /
• 2024

Polyester round slings are widely utilized in various work environments due to their lightweight, flexible nature and smooth surface that minimizes the risk of cargo abrasion or damage. However, specific guidelines intended to protect round slings from the damage caused by the sharp edges of cargo, thus preventing accidents in case the cargo falls, are lacking in South Korea. In this study, a comparative analysis was conducted on the regulations and guidelines related to round slings in South Korea and the United States. Further, experiments were carried out to determine the relationship between round slings and lifting accessories. The research identified specific shortcomings in the user manuals provided by round-sling manufacturers. Accordingly, certain measures were proposed for enhancing the operational safety of round slings: 1) establish criteria for edge protection of polyester round slings and 2) recommend standardization of the information provided by manufacturers. As developing new standards is a time-consuming task, this study proposes a method for enhancing the operational safety of round slings in the short term by introducing established safety standards from the United States-where safety has been proven over a considerable period of time-into the domestic context. In addition, it is recommended that edge criteria be permanently printed on the labels of round slings.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.237-262
• /
• 2022

There has been a growing interest in IPOs (Initial Public Offerings) due to the profitable returns that IPO stocks can offer to investors. However, IPOs can be speculative investments that may involve substantial risk as well because shares tend to be volatile, and the supply of IPO shares is often highly limited. Therefore, it is crucially important that IPO investors are well informed of the issuing firms and the market before deciding whether to invest or not. Unlike institutional investors, individual investors are at a disadvantage since there are few opportunities for individuals to obtain information on the IPOs. In this regard, the purpose of this study is to provide individual investors with the information they may consider when making an IPO investment decision. This study presents a model that uses machine learning and text analysis to predict whether an IPO stock price would move up or down after the first 5 trading days. Our sample includes 691 Korean IPOs from June 2009 to December 2020. The input variables for the prediction are three tone variables created from IPO prospectuses and quantitative variables that are either firm-specific, issue-specific, or market-specific. The three prospectus tone variables indicate the percentage of positive, neutral, and negative sentences in a prospectus, respectively. We considered only the sentences in the Risk Factors section of a prospectus for the tone analysis in this study. All sentences were classified into 'positive', 'neutral', and 'negative' via text analysis using TF-IDF (Term Frequency - Inverse Document Frequency). Measuring the tone of each sentence was conducted by machine learning instead of a lexicon-based approach due to the lack of sentiment dictionaries suitable for Korean text analysis in the context of finance. For this reason, the training set was created by randomly selecting 10% of the sentences from each prospectus, and the sentence classification task on the training set was performed after reading each sentence in person. Then, based on the training set, a Support Vector Machine model was utilized to predict the tone of sentences in the test set. Finally, the machine learning model calculated the percentages of positive, neutral, and negative sentences in each prospectus. To predict the price movement of an IPO stock, four different machine learning techniques were applied: Logistic Regression, Random Forest, Support Vector Machine, and Artificial Neural Network. According to the results, models that use quantitative variables using technical analysis and prospectus tone variables together show higher accuracy than models that use only quantitative variables. More specifically, the prediction accuracy was improved by 1.45% points in the Random Forest model, 4.34% points in the Artificial Neural Network model, and 5.07% points in the Support Vector Machine model. After testing the performance of these machine learning techniques, the Artificial Neural Network model using both quantitative variables and prospectus tone variables was the model with the highest prediction accuracy rate, which was 61.59%. The results indicate that the tone of a prospectus is a significant factor in predicting the price movement of an IPO stock. In addition, the McNemar test was used to verify the statistically significant difference between the models. The model using only quantitative variables and the model using both the quantitative variables and the prospectus tone variables were compared, and it was confirmed that the predictive performance improved significantly at a 1% significance level.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.