• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.123-124
• /
• 2019

This paper proposes an improved deep learning method based on small data sets for animal image classification. Firstly, we use a CNN to build a training model for small data sets, and use data augmentation to expand the data samples of the training set. Secondly, using the pre-trained network on large-scale datasets, such as VGG16, the bottleneck features in the small dataset are extracted and to be stored in two NumPy files as new training datasets and test datasets. Finally, training a fully connected network with the new datasets. In this paper, we use Kaggle famous Dogs vs Cats dataset as the experimental dataset, which is a two-category classification dataset.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1167-1174
• /
• 2022

Cast austenitic stainless steels (CASSs) are widely used as structural materials in the nuclear industry. The main drawback of CASSs is the reduction in fracture toughness due to long-term exposure to operating environment. Even though ultrasonic non-destructive testing has been conducted in major nuclear components and pipes, the detection of cracks is difficult due to the scattering and attenuation of ultrasonic waves by the coarse grains and the inhomogeneity of CASS materials. In this study, the ultrasonic signals measured in thermally aged CASS were discriminated for the first time with the simple ultrasonic technique (UT) and machine learning (ML) models. Several different ML models, specifically the K-nearest neighbors (KNN), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) models, were used to classify the ultrasonic signals as thermal aging condition of CASS specimens. We identified that the ML models can predict the category of ultrasonic signals effectively according to the aging condition.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.639-646
• /
• 2022

In this paper, to solve the large dataset problem, we collect images through an image collection method called web crawling and build datasets for use in image classification models through a data preprocessing process. We also propose a lightweight model that can automatically classify images by adding category values by incorporating transfer learning into the image classification model and an image classification model that reduces training time and achieves high accuracy.

• Journal of Internet Computing and Services
• /
• v.9 no.5
• /
• pp.9-21
• /
• 2008

In theory, within ubiquitous learning environment, education is happening all around the student but the student may not even be conscious of the learning process. But, in this study, we consider the ubiquitous learning environment where PMP (Personal Multimedia Player) is being used for delivering the learning-contents. And the purpose of this study is to identify the problematic factors recognized by PMP users in u-learning environment. A need analysis was used to identify and evaluate needs of 74 PMP users as well non-users. Based on the interviews of participants, we give a brief summary results on motivation for using PMP, purchasing and operating costs, category of contents being used, dissatisfying and problematic factors with using PMP in u-learning environment. Therefore, we present six categories of factors preventing the u-learning with PMP from being diffused such as lacks of awareness, loss of confidence, side-effects, lacks of education and support, costs, and lacks of contents. In conclusion, we suggest a set of guidelines which might help remove these the resistance factors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2683-2702
• /
• 2015

A Content-based Image Retrieval (CBIR) system employs visual features rather than manual annotation of images. The selection of optimal features used in classification of images plays a key role in its performance. Category proliferation problem has a huge impact on performance of systems using Fuzzy Artmap (FAM) classifier. The proposed CBIR system uses a modified version of FAM called Non-Proliferation Fuzzy Artmap (NPFAM). This is developed by introducing significant changes in the learning process and the modified algorithm is evaluated by extensive experiments. Results have proved that NPFAM classifier generates a more compact rule set and performs better than FAM classifier. Accordingly, the CBIR system with NPFAM classifier yields good retrieval.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.4
• /
• pp.251-258
• /
• 2005

Automatic document classification may differ significantly according to the characteristics of documents that are subject to classification, as well as classifier's performance. This research identifies e-mail document's characteristics to apply a three-step preprocessing algorithm that can minimize e-mail document's atypical characteristics. In the first 5go, uncertain based sampling algorithm that used Mean Absolute Deviation(MAD), is used to address the question of selection learning document for the rule generation at the time of classification. In the subsequent stage, Weighted vlaue assigning method by attribute is applied to increase the discriminating capability of the terms that appear on the title on the e-mail document characteristic level. in the third and last stage, accuracy level during classification by each category is increased by using Naive Bayesian Presumptive Algorithm's Dynamic Threshold. And, we implemented an E-Mail Recommendtion System using a three-step preprocessing algorithm the enable users for direct and optimal classification with the recommendation of the applicable category when a mail arrives.

• Child Studies in Asia-Pacific Contexts
• /
• v.5 no.1
• /
• pp.21-38
• /
• 2015

This paper reviews Grammatical Mapping theory, a recently proposed theoretical paradigm for understanding children's acquisition of syntax, and ventures to apply the theory to the acquisition of semantics. Particularly, we focused on the domain of space, and proposed how children might acquire a unique system of spatial words in their mother tongue. Based on our review of evidence, we propose that there may be universal semantic primitives that serve as foundations of word meanings. We also propose that children must learn their mother tongue's semantic category system of spatial relations, from real time data. Finally, we argue that children's learning of word meanings may involve creation of a theory that makes sense to the child, and that this process of theory creation is possibly guided by universal principles and parameters.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.11-15
• /
• 2020

In a typical initial setup of a PCB component inspection system, operators should manually input various information such as category, position, and inspection area for each component to be inspected, thus causing much inconvenience and longer setup time. Although there are many deep learning based object detectors, RetinaNet is regarded as one of best object detectors currently available. In this paper, a method using an extended RetinaNet is proposed that automatically detects its component category and position for each component mounted on PCBs from a high-resolution color input image. We extended the basic RetinaNet feature pyramid network by adding a feature pyramid layer having higher spatial resolution to the basic feature pyramid. It was demonstrated by experiments that the extended RetinaNet can detect successfully very small components that could be missed by the basic RetinaNet. Using the proposed method could enable automatic generation of inspection areas, thus considerably reducing the setup time of PCB component inspection systems.

• Educational Technology International
• /
• v.14 no.1
• /
• pp.1-26
• /
• 2013

This study is to identify whether three types of online instruction (text-based, video-based, and video-based instruction without text) and age category have a different influence on students' comprehension and motivation. Online students were randomly assigned to one of six groups, and they attended two-week online lectures via Course Management System. The comprehension test and the short form of IMMS were implemented when 114 participants accomplished two-week online lectures. The results revealed that using instructional video in online instruction is more effective instructional medium than text only in order to promote learner's motivation. Besides, older adults aged 41-60 are significantly different from younger adults (21-40 years old) in terms of students' comprehension. Furthermore, three types of online instructions are likely to be influenced by age category.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.107-112
• /
• 2023

라벨 데이터 수집의 어려움에 따라 라벨이 없는 데이터로 학습하는 준지도학습, 비지도학습에 대한 연구가 활발하게 진행되고 있다. 본 논문에서는 그의 일환으로 Novel Intent Category Discovery(NICD) 문제를 제안하고 NICD 연구의 베이스라인이 될 모델을 소개한다. NICD 문제는 라벨이 있는 데이터와 라벨이 없는 데이터의 클래스 셋이 겹치지 않는다는 점에서 기존 준지도학습의 문제들과 차이가 있다. 제안 모델은 RoBERTa를 기반으로 두 개의 분류기를 추가하여 구성되며 라벨이 있는 데이터셋과 라벨이 없는 데이터셋에서 각각 다른 분류기를 사용하여 라벨을 예측한다. 학습방법은 2단계로 먼저 라벨이 있는 데이터셋으로 요인표현을 학습한다. 두 번째 단계에서는 교차 엔트로피, 이항교차 엔트로피, 평균제곱오차, 지도 대조 손실함수를 NICD 문제에 맞게 변형하여 학습에 사용한다. 논문에서 제안된 모델은 라벨이 없는 데이터셋에 대해 이미지 최고성능 모델보다 24.74 더 높은 정확도를 기록했다.