• Title/Summary/Keyword: Training set

Search Result 1,601, Processing Time 0.031 seconds

A Study on the Exposure Parameter and the Patient Dose for Digital Radiography System in Dae Goo (디지털 방사선의학에서의 조사선량 설정과 인지에 대한 실태 - 대구 경북지역을 중심으로 -)

  • Jo, Gwang-Ho;Kang, Yeong-Han;Kim, Bu-Sun
    • Journal of radiological science and technology
    • /
    • v.31 no.2
    • /
    • pp.177-182
    • /
    • 2008
  • Digital imaging for general rediography has many advantages over the film/screen systems, including a wider dynamic range and the ability to manipulate the images produced. The wider range means that acceptable images may by acquired at a range of dose levels, and therefore repeat exposures can be reduced. Digital imaging can result in the over use of radiation, however, because there is a tendency can be reduced. Digital imaging can result in the over use of radiation, however, because there is a tendency for images to be acquired at too high a dose. We investigated the actual exposure dose conditions on general radiography and a questionnaire survey was conducted with radiotechnologiest at medical institutions using digital radiology system. As a results, the dose of exposure was not controlled with patient's figure and dose optimization but was controlled by worker's convenience and image quality. Radio-technologiests often set up the exposure dose regardless of patient figure and body part to be examined. Many organizations, such as the International Commission on Radiological Protection, recommend to keep the dose as low as possible. In addition, they strongly recommend to keep the optimal but minimal dosage by proper training programs and constant quality control, including frequent patient dose evaluations and education.

  • PDF

Energy efficiency improvements in part load for a marine auxiliary diesel engine (선박발전기용 디젤엔진의 부분부하에서 에너지 효율 개선에 관한연구)

  • Jung, Kyun-Sik
    • Journal of Advanced Marine Engineering and Technology
    • /
    • v.38 no.7
    • /
    • pp.877-882
    • /
    • 2014
  • The reduction of CO2 emission has been discussed in the Marine Environment Protection committee in the International Maritime Organization as the biggest causes of GHG for the purpose of indexing CO2 amounts released into the atmosphere from ships. Accordingly, various methods including the change in the hull design to improve energy efficiency, the coating development to reduce friction resistances, the additives development for improving thermal efficiency in an engine, the low-speed operation to reduce fuel consumptions, and etc. have been applied. The main engine of a ship is an electronic engine for improving the efficiency of the whole load area. However, marine generator engines still use mechanical drive engines in intake, exhaust, and fuel injection valve drive cams. In addition, most of marine generator engines in ships apply a part-load operation of less then 80% due to an overload protection system. Therefore, marine auxiliary diesel engine set at 100% load is necessary to readjust in order to efficient operation because of part-load operation. The objective of this study is to report the results of the part-load fuel consumption improvement by injection timing readjust to identifying the operational characteristics of a marine generator engine currently operated in a ship.

Forecasting of Customer's Purchasing Intention Using Support Vector Machine (Support Vector Machine 기법을 이용한 고객의 구매의도 예측)

  • Kim, Jin-Hwa;Nam, Ki-Chan;Lee, Sang-Jong
    • Information Systems Review
    • /
    • v.10 no.2
    • /
    • pp.137-158
    • /
    • 2008
  • Rapid development of various information technologies creates new opportunities in online and offline markets. In this changing market environment, customers have various demands on new products and services. Therefore, their power and influence on the markets grow stronger each year. Companies have paid great attention to customer relationship management. Especially, personalized product recommendation systems, which recommend products and services based on customer's private information or purchasing behaviors in stores, is an important asset to most companies. CRM is one of the important business processes where reliable information is mined from customer database. Data mining techniques such as artificial intelligence are popular tools used to extract useful information and knowledge from these customer databases. In this research, we propose a recommendation system that predicts customer's purchase intention. Then, customer's purchasing intention of specific product is predicted by using data mining techniques using receipt data set. The performance of this suggested method is compared with that of other data mining technologies.

Development of Web Application Based on N-screen for Play Activities of Children with Developmental Disorder (발달장애 아동의 놀이 활동을 위한 N-스크린 기반의 웹앱 개발)

  • Kang, Jung Bae;Kim, Jin Hee;Kim, Chang Geol;Song, Beong Seop
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.18 no.4
    • /
    • pp.1-8
    • /
    • 2013
  • In the modern society, instructional methods using diverse media have appeared thanks to the development of Information & Communication Technology, and applicability of such instructional methods has been fully corroborated. However, customized contents allowing for disabled children's environment are still insufficient. Hence, this study produced educational contents of play activities for children with developmental disability, through applying N-screen technology, IT technology that can provide the same contents via a variety of digital media. The produced contents allow programs to be set up according to a child's individual characteristics and be carried out anywhere and anytime via an Internet-enabled digital device. Further, the developed contents were produced so that they could be accessed from a child's various environment (home, school, etc.) via a PC, a smart phone, a portable from a child's various environment (home, school, etc.) via a PC, a smart phone, a portable device, etc. and that the same educational program could be conducted in linkage at home, school, etc. Three children with Intellectual disability and autism spectrum disorder were applied to the manufactured content. As a result, Content interaction between interaction between teachers and students in play training could use as a medium.In addition, the children's ability to select the appropriate components and reinforcements, special education professionals have used the content of the interviews are helpful in mediation than the existing content.

An Emotion Scanning System on Text Documents (텍스트 문서 기반의 감성 인식 시스템)

  • Kim, Myung-Kyu;Kim, Jung-Ho;Cha, Myung-Hoon;Chae, Soo-Hoan
    • Science of Emotion and Sensibility
    • /
    • v.12 no.4
    • /
    • pp.433-442
    • /
    • 2009
  • People are tending to buy products through the Internet rather than purchasing them from the store. Some of the consumers give their feedback on line such as reviews, replies, comments, and blogs after they purchased the products. People are also likely to get some information through the Internet. Therefore, companies and public institutes have been facing this situation where they need to collect and analyze reviews or public opinions for them because many consumers are interested in other's opinions when they are about to make a purchase. However, most of the people's reviews on web site are too numerous, short and redundant. Under these circumstances, the emotion scanning system of text documents on the web is rising to the surface. Extracting writer's opinions or subjective ideas from text exists labeled words like GI(General Inquirer) and LKB(Lexical Knowledge base of near synonym difference) in English, however Korean language is not provided yet. In this paper, we labeled positive, negative, and neutral attribute at 4 POS(part of speech) which are noun, adjective, verb, and adverb in Korean dictionary. We extract construction patterns of emotional words and relationships among words in sentences from a large training set, and learned them. Based on this knowledge, comments and reviews regarding products are classified into two classes polarities with positive and negative using SO-PMI, which found the optimal condition from a combination of 4 POS. Lastly, in the design of the system, a flexible user interface is designed to add or edit the emotional words, the construction patterns related to emotions, and relationships among the words.

  • PDF

A New Model for Forecasting Inundation Damage within Watersheds - An Artificial Neural Network Approach (인공신경망을 이용한 유역 내 침수피해 예측모형의 개발)

  • Chung, Kyung-Jin;Chen, Huaiqun;Kim, Albert S.
    • Journal of the Korean Society of Hazard Mitigation
    • /
    • v.5 no.2 s.17
    • /
    • pp.9-16
    • /
    • 2005
  • This paper presents the use of an Artificial Neural Network (ANN) as a viable means of forecasting Inundation Damage Area (IDA) in many watersheds. In order to develop the forecasting model with various environmental factors, we selected 108 watershed areas in South Korea and collected 49 damage data sets from 1990 to 2000, of which each set is composed of 27 parameters including the IDA, rainfall amount, and land use. After successful training processes of the ANN, a good agreement (R=0.92) is obtained (under present conditions) between the measured values of the IDA and those predicted by the developed ANN using the remaining 26 data sets as input parameters. The results indicate that the inundation damage is affected by not only meteorological information such as the rainfall amount, but also various environmental characteristics of the watersheds. So, the ANN proves its present ability to predict the IDA caused by an event of complex factors in a specific watershed area using accumulated temporal-spatial information, and it also shows a potential capability to handle complex non-linear dynamic phenomena of environmental changes. In this light, the ANN can be further harnessed to estimate the importance of certain input parameters to an output (e.g., the IDA in this study), quantify the significance of parameters involved in pre-existing models, and contribute to the presumption, selection, and calibration of input parameters of conventional models.

Design and Implementation of Web-based Problem Management System for CT Radiological Technologist Education (CT 전문방사선사 교육을 위한 웹기반 문항관리 시스템의 설계 및 구현)

  • Shin Yong-Won;Koo Bong-Oh;Shim Choon-Bo
    • The Journal of the Korea Contents Association
    • /
    • v.5 no.1
    • /
    • pp.27-35
    • /
    • 2005
  • Recently, despite of the rapid progress of information technology in the medical and health fields, the development and management of problem sets about medical and education contents related with radiological technologist has been still achieved by manual and offline method using document editor. In this study, the unique web-based problem management system is designed and implemented. That system can efficiently manage and present various kind of problem set about integrated education and personal license without time and space limitations in order to improve the efficiency of supplementary training and to obtain the professional license for CT radiological technologist. The proposed system is composed of administration module and user module. The former supports several functions such as problem creation, problem categorization, user management, and adjustment of leveled assessment. On the other hand, the latter functions examination applying , problem retrieval, personal score retrieval, and interpretation viewing, and so on. In addition, our system is expected as a useful and practical system which provides problem interpretation and analysis of score results after applying for the examination. It can elevate ability of learning and information interchange among them preparing for CT professional radiological technologist licensing examination

  • PDF

The Effects of Low Intensity Resisted and Aerobic Exercise Training on Blood Lipid in Chronic Stroke Patients (저강도의 저항운동과 유산소 운동 훈련이 만성 뇌졸중 환자의 혈중지질에 미치는 효과)

  • Lee, Dong-Yeop;Cho, Nam-Jeong
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.12 no.2
    • /
    • pp.753-758
    • /
    • 2011
  • The purpose of this study was to investigate effect of low intensity resistance exercise and aerobic exercise on serum lipid level in chronic stroke patients. A total of 37 chronic stroke patients were enrolled in this study. The participants were allocated randomly to 2 groups: the low intensity resistance exercise group(n=19) and aerobic exercise group(n=18). Low intensity resistance exercise group took exercise with low intensity resistance for 50minutes, 5 times per week over a 8 week period. Aerobic exercise group received only aerobic exercise. We measured serum lipid level to compare of effectiveness both exercises. Paired t test was executed to determine differences between pre and post exercise. For all analyses, a significant level set at p<.05. The low intensity resistance exercise group showed significant increase in TG, TC HDL-C and LDL-C(p<.05). The aerobic exercise group had significantly higher TC and LDL-C (p<.05). Theses results suggest that low intensity resistance exercise and aerobic exercise are feasible for stroke patients by improving motivation and interest. Further studies is necessary to clinical implication classified by onset time and disability level.

Analysis of cognitive factors affecting stroke patient's activity of daily living performance -Using the computerized neurocognitive function test- (뇌졸중 환자의 일상 활동 수행에 영향을 미치는 인지요인 분석 -전산화 신경인지기능검사 중심으로-)

  • Kim, Ji-Youn
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.12 no.12
    • /
    • pp.5715-5721
    • /
    • 2011
  • This research analyzed the cognitive factors affecting stroke patient's activity of daily living performance and suggests the approaches which can contribute to the effective activity of daily living performance in the rehabilitation treatment of stroke patients. In this study, Seoul Computerized NeuroCognitive Function Test (SCNT) and MBI have been performed for 21 patients under extensive rehabilitation treatments, hospitalized in the rehabilitation clinic of A hospital after being diagnosed as a stroke caused by cerebrovascular disorders. To assess the effectiveness of the cognitive factors which affect the stroke patient's activity of daily living performance, activity of daily living performance values were set as dependent variables and 10 cognitive factors were included in the model to carry out analysis of the multiple regression analysis. The results show that stroke patient's activity of daily living performance have statistically significant correlations with divided attention, motor control and selectivir attention. In addition, cognitive factors explained 69.8% of the stroke patient's activity of daily living performance. Consequently, if divided attention and motor control are considered as a focal point of training in the rehabilitation treatment of stroke patients, we can effectively promote the improvement of the activity of daily living performanceroutine activities.

Cavitation Analysis on Ship Seawater Pump Using CFD (CFD를 이용한 선박용 해수펌프의 공동현상에 대한 분석)

  • Kim, Bu-Gi;Kim, Hong-Ryeol;Yang, Chang-Jo;Kim, Jun-Ho
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.23 no.4
    • /
    • pp.400-406
    • /
    • 2017
  • The model used in this study was reversed to analyze the cause of excessive damage that occurred inside the rotating system and pipe system of a centrifugal-type seawater pump on a ship. For this purpose, internal flow analysis on a cooling seawater pump was performed using CFD. As a result, the shape and boundary conditions of the target pump were set by reverse engineering, and pump efficiency at a design operating point of $125m^3/h$ was calculated as 85.3 % with a head of 32.0 m. The maximum efficiency point of the target pump was estimated to be 86.2 % at $150m^3/h$, but this differed from the actual operating point. At $112.5m^3/h$, which was the lowest flow point, flow was unstable due to the characteristics of the low flow point and analysis convergence was not good. The purpose of this study was to clarify the cause of ongoing cavitation in seawater pumps and piping systems in operation. Future research will be needed to clarify causes for pipe systems in the future by performing calculations for the total piping system of an inlet and outlet, in addition to measuring the flow rate of each branch pipe.