• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.223-230
• /
• 2007

The purpose of developing an automated scoring system for English composition is to score the tests for writing English sentences and to give feedback on them without human's efforts. This paper presents an automated system to score English composition, whose input is a single sentence, not an essay. Dealing with a single sentence as an input has some advantages on comparing the input with the given answers by human teachers and giving detailed feedback to the test takers. The system has been developed and tested with the real test data collected through English tests given to the third grade students in junior high school. Two steps of the process are required to score a single sentence. The first process is analyzing the input sentence in order to detect possible errors, such as spelling errors, syntactic errors and so on. The second process is comparing the input sentence with the given answer to identify the differences as errors. The results produced by the system were then compared with those provided by human raters.

• The KIPS Transactions:PartB
• /
• v.18B no.1
• /
• pp.45-50
• /
• 2011

Unknown morpheme errors in Korean morphological analysis are divided into two types: The one is the errors that a morphological analyzer entirely fails to return any morpheme sequences, and the other is the errors that a morphological analyzer returns incorrect combinations of known morphemes. Most previous unknown morpheme estimation techniques have been focused on only the former errors. This paper proposes a unknown morpheme estimation method which can handle both of the unknown morpheme errors. The proposed method detects Eojeols (Korean spacing units) that may include unknown morpheme errors using SVM (Support Vector Machine). Then, using CRFs (Conditional Random Fields), it segments morphemes from the detected Eojeols and annotates the segmented morphemes with new POS tags. In the experiments, the proposed method outperformed the conventional method based on the longest matching of functional words. Based on the experimental results, we knew that the second type errors should be dealt with in order to increase the performance of Korean morphological analysis.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.115-122
• /
• 2017

This paper proposes a deep learning algorithm based sign detection and recognition system for the blind. The proposed system is composed of sign detection stage and sign recognition stage. In the sign detection stage, aggregated channel features are extracted and AdaBoost classifier is applied to detect regions of interest of the sign. In the sign recognition stage, convolutional neural network is applied to recognize the regions of interest of the sign. In this paper, the AdaBoost classifier is designed to decrease the number of undetected signs, and deep learning algorithm is used to increase recognition accuracy and which leads to removing false positives which occur in the sign detection stage. Based on our experiments, proposed method efficiently decreases the number of false positives compared with other methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.9C
• /
• pp.853-858
• /
• 2006

TMHMM(Tied Mixture Hidden Markov Model) is an important approach to reduce the number of free parameters in speech recognition. However, this model suffers from a degradation in recognition accuracy due to its GPDF (Gaussian Probability Density Function) clustering error. This paper proposes a clustering algorithm, called HCNN(Homogeneous Centroid Neural network), to cluster acoustic feature vectors in TMHMM. Moreover, the HCNN uses the heterogeneous distance measure to allocate more code vectors in the heterogeneous areas where probability densities of different states overlap each other. When applied to Korean digit isolated word recognition, the HCNN reduces the error rate by 9.39% over CNN clustering, and 14.63% over the traditional K-means clustering.

• Journal of Korean Academy of Nursing
• /
• v.42 no.4
• /
• pp.568-578
• /
• 2012

Purpose: The purpose of this cross-sectional study was to examine current status of IT-based medication error prevention system construction and the relationships among system construction, medication error management climate and perception for system use. Methods: The participants were 124 patient safety chief managers working for 124 hospitals with over 300 beds in Korea. The characteristics of the participants, construction status and perception of systems (electric pharmacopoeia, electric drug dosage calculation system, computer-based patient safety reporting and bar-code system) and medication error management climate were measured in this study. The data were collected between June and August 2011. Descriptive statistics, partial Pearson correlation and MANCOVA were used for data analysis. Results: Electric pharmacopoeia were constructed in 67.7% of participating hospitals, computer-based patient safety reporting systems were constructed in 50.8%, electric drug dosage calculation systems were in use in 32.3%. Bar-code systems showed up the lowest construction rate at 16.1% of Korean hospitals. Higher rates of construction of IT-based medication error prevention systems resulted in greater safety and a more positive error management climate prevailed. Conclusion: The supportive strategies for improving perception for use of IT-based systems would add to system construction, and positive error management climate would be more easily promoted.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.286-289
• /
• 2003

In turn-key projects, escalation of cost by design errors is not allowed because a contractor prepares the design. Therefore, cost escalation by design errors results in increasing the cost of the prime contractor. The rate of profit decreases finally. In addition, design errors bring not only schedule delay but also serious quality problem by unknown errors. This study tries to dissolve problems, that of cost increase. process delay and a falling-off in quality by investigating cause of design errors and presenting a scheme for reducing design errors.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.427-433
• /
• 2004

Information is increasing continuously in on-line, it is real condition that inaccurate informations are mass-produced but effort to keep accuracy of these informations is lacking. Already, research about government official of information in World Wide Web is consisting of various method and viewpoint, but problem for the importance of correct information offer and offer of mistake information in World Wide Web about specification target and administration way presentation are no research reward yet and system that can keep accuracy of information is not equiped properly. ss and accuracy whether mistake information in harbor and bay connection web site's administration influences how in authoritativeness security of site and present condition information of harbor and bay and operation information. In this study, we wish to present administration way about mistake informations that is required that recognize problem of mistake information and the administration's importance in on-line in this research, and supply phenomenon information in Web site. We made the right definition about mistake of information through priority literature investigation and virtued research for this, and sorted mistake information in type. And we investigated Pusan port connection information and offered present condition in on-line and research on actual state of mistake information offer and analysis. Reflecting type and special quality of examined mistake informations, We want to make people recognize the importance af freshness and accuracy whether mistake information in harbor and bay connection web site's administration influences how in authoritativeness security of site and present condition information of harbor and bay and operation information.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.537-542
• /
• 2021

This paper improves the possibility of recognizing fast-moving objects through the YOLO (You Only Look Once) deep learning recognition model in an application environment for object recognition in images. The purpose was to study the method of collecting semantic data through processing. In the recognition model, the moving object recognition error was identified as unrecognized because of the difference between the frame rate of the camera and the moving speed of the object and a misrecognition due to the existence of a similar object in an environment adjacent to the object. To minimize the recognition errors by compensating for errors, such as unrecognized and misrecognized objects through the proposed data collection method, and applying vision processing technology for the causes of errors that may occur in images acquired for sports (tennis games) that can represent real similar environments. The effectiveness of effective secondary data collection was improved by research on methods and processing structures. Therefore, by applying the data collection method proposed in this study, ordinary people can collect and manage data to improve their health and athletic performance in the sports and health industry through the simple shooting of a smart-phone camera.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.1119-1122
• /
• 2005

This paper describes the implementation methods of the MLP (mulilayer perteptrons) recognizers for numerals and non-nummerals. The MLP has known to be a very efficient classifier to recognize handwritten numerals in terms of recognition accuracy, speed, and memory requirements. The MLP in the previous researches, however, focuses on the only numeral inputs and does not pay attention to non-numeral inputs with respect to recognition accuracy, rejection rates, and other characteristics. In this paper, we present some implementation methods of the MLP in the environments that numeral and non-numerals are mixed. The MLP had been developed by three methods, and investigated with three error types introduced. The experiments had been conducted on a total of about 63,000 numerals and non-numerals. The promising method to recognize numeral and non-numerals is described in terms of the three error types.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.6
• /
• pp.109-117
• /
• 2014

A cold storage is a warehouse of a insulated building with cooling installations. It has many different types of cold rooms with temperatures below 0 degrees Celsius, and the sequential workflow such as receiving, picking and packing runs in that rooms. Recently, the cold storages have adopted RFID technology, and consequently, warehouse product management in them are becoming intelligent and network. However, information inconsistency in warehouses caused by physical and logical errors reduces reliability in the RFID cold storage management system and worsens their work efficiency. Therefore, it is necessary to develop an early detection system to identify errors. In this paper, we suggest a supervisory system detecting logical errors on business processes of the RFID cold storage. It is composed of a master supervisor and mobile supervisor. In the master supervisor, the manager can set the constraints conditions and get alerts, and in the mobile supervisor, the workers confirm and deal with these faults directly. The supervisory system improve reliability of the RFID cold storage management system by recognizing a failure to identify physically and logically using these constraint conditions. This paper shows that the supervisory system can reduce the average recovery time to improve reliability by decreasing the time for detecting and analyzing errors in the RFID cold storage management system.