• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1053-1056
• /
• 2004

In this article we have applied Schweizer & Sklars t-norm based similarity measures to classification task. We will compare results to fuzzy similarity measure based classification and show that sometimes better results can be found by using these measures than fuzzy similarity measure. We will also show that classification results are not so sensitive to p values with Schweizer & Sklars measures than when fuzzy similarity is used. This is quite important when one does not have luxury of tuning these kind of parameters but needs good classification results fast.

• 대한인간공학회지
• /
• 제15권1호
• /
• pp.27-38
• /
• 1996

A total of 77 unanticipated trip cases induced by human errors in Korean nuclear power plants were collected from the nuclear power plant trip event reports and analyzed to investigate the areas of high priority for human error reduction. Prior to this analysis, a classification system was made on the four task-related categories including plant systems, work situations, task types, and error types. The erroneous actions affecting the unanticipated plant trips were indentified by reviewing carefully the description of trip events. Then, the events with erroneous action were analyzed by using the classification system. Based on the results for the individual cases, human error occurrences were counted for each of the four categories, also for the selected pairs of categories, to find out the relationships between the two categories in aspects of human errors. As a result, the plant systems, work situations, and task types, and error types which are dominant in human error occurrences were identified.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.408-410
• /
• 2021

In the NLP field, the pre-training model BERT launched by the Google team in 2018 has shown amazing results in various tasks in the NLP field. Subsequently, many variant models have been derived based on the original BERT, such as RoBERTa, ERNIEBERT and so on. In this paper, the WWMBERT (Whole Word Masking BERT) model suitable for Chinese text tasks was used as the baseline model of our experiment. The experiment is mainly for "Text-level Chinese text classification tasks" are improved, which mainly combines Tapt (Task-Adaptive Pretraining) and "Multi-Sample Dropout method" to improve the model, and compare the experimental results, experimental data sets and model scoring standards Both are consistent with the official WWMBERT model using Accuracy as the scoring standard. The official WWMBERT model uses the maximum and average values of multiple experimental results as the experimental scores. The development set was 97.70% (97.50%) on the "text-level Chinese text classification task". and 97.70% (97.50%) of the test set. After comparing the results of the experiments in this paper, the development set increased by 0.35% (0.5%) and the test set increased by 0.31% (0.48%). The original baseline model has been significantly improved.

• ETRI Journal
• /
• 제42권1호
• /
• pp.67-77
• /
• 2020

Image captioning has received significant interest in recent years, and notable results have been achieved. Most previous approaches have focused on generating visual descriptions from images, whereas a few approaches have exploited visual descriptions for image classification. This study demonstrates that a good performance can be achieved for both description generation and image classification through an end-to-end joint learning approach with a loss function, which encourages each task to reach a consensus. When given images and visual descriptions, the proposed model learns a multimodal intermediate embedding, which can represent both the textual and visual characteristics of an object. The performance can be improved for both tasks by sharing the multimodal embedding. Through a novel loss function based on class activation mapping, which localizes the discriminative image region of a model, we achieve a higher score when the captioning and classification model reaches a consensus on the key parts of the object. Using the proposed model, we established a substantially improved performance for each task on the UCSD Birds and Oxford Flowers datasets.

• 한국초등과학교육학회지:초등과학교육
• /
• 제34권1호
• /
• pp.142-152
• /
• 2015

The purpose of this study was to identify the differences in eye movement pattern shown in shown in classification process between the scientifically gifted and general students in elementary schools. The subjects for the research consisted of 16 gifted students in special education center for the gifted at Seoul National University of Education and 22 general students at G elementary schools. The tasks consisted of four hierarchical biology classification tasks and one non-hierarchical tasks. SMI's Eye Tracker (iView $X^{TM}$ RED) was used to collect eye movement data while the Begaze software analyzed the task performing process and eye movements. The findings of this study were twofold. First, there was a significant difference in students' fixation duration by students' academic achievement level. Gifted students spent little time on scanning details and found the features successfully. Second, the process of the classification is different by students' academic achievement. General students spent more time to gaze the salient features not relevant features. They had a difficulty to find the element to classify.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권10호
• /
• pp.1412-1417
• /
• 2004

전체관적인 표현방법인 희소 코딩 또는 독릴 성분 분해(ICA)는 이전의 청각의 처리와 소리 분류의 작업을 해명하는데 성공적으로 적용되었다. 반대로 부분 기반 표현법은 뇌에서 물체를 인식하는 방법을 이해하는 또 다른 방법이다. 이 논문에서, 우리는 소리 분류의 작업에 부분기반 표현법을 학습시키는 비음수화 행렬 분해(NMF)(1) 방법을 적용하였다. 잡음이 존재할 때와 존재하지 않을 때 두 가지 상황에서, NMF를 이용하여 주파수-시간영역의 소리로부터 특징을 추출하는 방법을 설명한다. 실험결과에서는 NMF에 기반을 둔 특징이 ICA에 기반을 두어 추출한 특징보다 소리 분류의 성능을 향상시킴을 보여준다.

• 인터넷정보학회논문지
• /
• 제1권1호
• /
• pp.63-72
• /
• 2000

데이터마이닝은 방대한 데이터 자료로부터 숨어있는 지식이나 유용한 정보를 추출하는 과정이다. 이러한 데이터 마이닝 알고리즘은 통계학, 전자계산학, 그리고 기계학습 분야에서의 오랜 기간동안 이루어진 연구 결과의 산물이다. 어느 특정한 상황에 적용하는 특정한 기술들의 선택은 구현되어야 하는 데이터 마이닝 임무의 성격과 가용한 데이터의 성격에 의존한다. 데이터 마이닝에는 여러 임무가 있으며, 그 중에서 가장 대표적인 임무가 분류라고 (classification) 볼 수 있다. 분류는 인간 사고의 기본적인 요소이기 때문에 여러 응용 분야에서 많은 연구가 진행되어 왔으며, 문제 분석의 첫 단계라고 볼 수 있다. 본 논문에서는 학습문제에서 강건성(robust)을 갖는 유전자 알고리즘 기반의 분류시스템을 제안하고, 데이터 마이닝에서 중요한 분류기능에 관련된 문제인 nDmC에 응용해서 그 유효성을 검증한다.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2005년도 BIOINFO 2005
• /
• pp.85-90
• /
• 2005

In this paper, firstly we report experimental results on applying information extraction (IE) methodology to the task of summarizing clinical trial design information in focus on ‘Compared Treatment’, ‘Endpoint’ and ‘Patient Population’ from clinical trial MEDLINE abstracts. From these results, we have come to see this problem as one that can be decomposed into a sentence classification subtask and an IE subtask. By classifying sentences from clinical trial abstracts and only performing IE on sentences that are most likely to contain relevant information, we hypothesize that the accuracy of information extracted from the abstracts can be increased. As preparation for testing this theory in the next stage, we conducted an experiment applying state-of-the-art sentence classification techniques to the clinical trial abstracts and evaluated its potential in the original task of the summarization of clinical trial design information.

• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.633-640
• /
• 2001

In this paper we examine the machine learning issues raised by the domain of the Intrusion Detection Systems(IDS), which have difficulty successfully classifying intruders. There systems also require a significant amount of computational overhead making it difficult to create robust real-time IDS. Machine learning techniques can reduce the human effort required to build these systems and can improve their performance. Genetic algorithms are used to improve the performance of search problems, while data mining has been used for data analysis. Data Mining is the exploration and analysis of large quantities of data to discover meaningful patterns and rules. Among the tasks for data mining, we concentrate the classification task. Since classification is the basic element of human way of thinking, it is a well-studied problem in a wide variety of application. In this paper, we propose a classifier system based on genetic algorithm, and the proposed system is evaluated by applying it to IDS problem related to classification task in data mining. We report our experiments in using these method on KDD audit data.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.945-950
• /
• 1990

An automatic visual classification system is introduced which provides for measuring the length and diameter of coilform cores and dividing them into 5 different classed in terms of how far their length be from the desired length. This task is fully automated by controlling two STEP motors and by using image processing techniques. The classification procedure is broken into three logical parts, First, cores in the form of randomly stacked bundle are lined up one by one so as to be well captured by a camera. The second part involves capturing core image. Then, it enters the measuring process. Finally, this machine would retain all the information relating to the length. According to the final result, cores are sent to the corresponding bin. This considerably simplifies the selecting task and facilitates a greatly improved reliablity in precision. The average classifying capability is about 2 pieces per second.