• Journal of The Korean Association of Information Education
• /
• v.17 no.1
• /
• pp.23-31
• /
• 2013

Elementary students can easy access to the smartphones and also can have been interested with them. Elementary learning tools to use smartphones are effective at the learning. So, Smartphones learning tools used in scientific experiments, the learning effect would be nice. Elementary school students to learn speed learning areas is a difficult concept. Therefore, the speed of learning application for smartphones is required. In this study, we develop a module for learning speed. This module that use the acceleration sensors of smart phones extract data from a given point in time, calculated by integrating speed. In addition, the distance is calculated. Students experiment at speed so that you can immediately see the changes in the module proposed in this study has the advantage. Measure the speed of the existing tools students again need to calculate the speed of a hassle to experiment and measured data values are separated. That the module proposed in this study is expected to be able to overcome the disadvantage.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.369-376
• /
• 2006

This paper presents a new method of significantly improving conventional Bayesian statistical text classifier by incorporating accelerated EM(Expectation Maximization) algorithm. EM algorithm experiences a slow convergence and performance degrade in its iterative process, especially when real online-textual documents do not follow EM's assumptions. In this study, we propose a new accelerated EM algorithm with uncertainty-based selective sampling, which is simple yet has a fast convergence speed and allow to estimate a more accurate classification model on Naive Bayesian text classifier. Experiments using the popular Reuters-21578 document collection showed that the proposed algorithm effectively improves classification accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.535-537
• /
• 2022

AI 가속기는 머신 러닝 및 딥 러닝을 포함한 인공 지능 및 기계 학습 응용 프로그램의 연산을 더 빠르게 수행하도록 설계된 일종의 하드웨어 가속기 또는 컴퓨터 시스템이다. 가속기를 설계하기 위해선 설계 영역 탐색(Design Space Exploration)을 하여야 하고 여러 인공지능 중에서도 합성 곱 신경망(CNN)에 대한 설계 영역 탐색을 소개한다.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.559-565
• /
• 2017

A lot of studies have been conducted to recognize the motion state or behavior of the user using the acceleration sensor built in the smartphone. In this paper, we applied the neural networks to the 3-axis acceleration information of smartphone to study human behavior. There are performance issues in applying time series data to neural networks. We proposed a multi-temporal neural networks which have trained three neural networks with different time windows for feature extraction and uses the output of these neural networks as input to the new neural network. The proposed method showed better performance than other methods like SVM, AdaBoot and IBk classifier for real acceleration data.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.3
• /
• pp.216-220
• /
• 2009

In this paper we propose a motion recognition method for handheld controller 3-D acceleration signals, generated by 3 axis accelerometer in the controller, are transmitted to the computer by Bluetooth communication. We extract motion segments from continuous acceleration signals and apply to each motion model, which is trained in training phase. Hidden Markov Model was used to model each motion. We applied proposed method to three motion sets, the recognition result was good enough to practical use.

• The Journal of Korean Society for Radiation Therapy
• /
• v.20 no.2
• /
• pp.123-130
• /
• 2008

Purpose: To provide practical education, most universities should be equipped with medical appliances in need. As compensatory measures, Gimcheon College has produced in-house dummy linac and dummy accessories, we are going to report efficiency and its usage. Materials and Methods: Dummy linear accelerator (DLINAC-001) has the same mechanical functions as rotation of gantry and collimation in linear accelerator. In addition, to maximize practical education, we have produced and utilized in-house custom blocks, wedge filters, electron cones and head rests. Results: The in-house produced linear accelerator with the same mechanical functions as the linear accelerator, DLINAC-001 can be effectively used in practicing diverse medical instruments. Conclusion: We have produced dummy linear accelerators and dummy accessories and utilized them in practice classes, which can provide the students with clinical training in diverse fields. Consequently, the students exposed to the maximized educational effectiveness can be easily equipped with the practical competence required in real clinical fields.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.245-250
• /
• 2008

최근 동작 및 행동 인식에 대한 연구가 활발하다. 특히, 센서가 소형화되고 저렴해지면서 그 활용을 위한 관심이 증가하고 있다. 기존의 많은 행동 인식 연구에서 사용되어 온 정적 분류 기술 기반 동작 인식 방법은 연속적인 데이터 분류 기술에 비해 유연성 및 활용성이 부족할 수 있다. 본 논문에서는 연속적인 데이터의 패턴 분류 및 인식에 효과적인 확률적 추론 기법인 은닉 마르코프 모델(Hidden Markov Model)과 사전 지식 없이도 자동 학습이 가능하며 의미 깊은 궤적 패턴을 클러스터링하고 효과적인 양자화가 가능한 자기구성지도(Self Organizing Map)를 이용한 동작 인식 기술을 소개한다. 또한, 그 유용성을 입증하기 위해 실제 가속도 센서를 이용하여 다양한 동작에 대한 데이터를 수집하고 분류 성능을 분석 및 평가한다. 실험에서는 실제 가속도 센서를 통해 수집된 숫자를 그리는 동작의 성능 평가 결과를 보이고, 행동 인식기 별 성능과 전체 인식기별 성능을 비교한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.92-94
• /
• 2016

저해상도 영상을 고해상도 영상으로 복원하기 위한 다양한 방법의 초해상도 기법이 존재한다. 다양한 기법들 중에서도 ELBP 분류기를 이용한 초해상도 기법[1]은 단일 영상 기반의 초해상도 기법으로 사전에 학습된 필터를 이용하여 고해상도 영상을 획득하는 기법이다. 그러나 해당 알고리즘을 일반적인 CPU 환경에서 수행할 경우 실시간으로 영상을 획득하는데 어려움이 존재한다. 본 논문에서는 지역메모리를 이용한 GPU 환경에서의 최적화를 수행하여 ELBP 분류기를 이용한 초해상도 기법의 가속성을 보인다. 먼저, 알고리즘에 대하여 간단히 설명하고 CUDA 가속화 기법[2]을 차례로 적용했을 때 얻을 수 있는 가속 성능을 확인한다. 최종적으로 본 논문은 CPU 환경과 비교했을 때 5 배의 가속 효과를 얻을 수 있다.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.771-779
• /
• 2010

Sketch-based interface is used more and more in developing animation contents. Particularly, there has been a system where the user's sketch inputs are interpreted and presented as live motions. In this study¸ it is to design an animated flight learning system using sketch-based interface. Most of the flights include movements in three-dimensional space and have unique and complex flight patterns. In other words, the actual flight movements not only include acceleration and deceleration, rising and falling, straight or circular flying, but also may include combinations of two or more movements as they simultaneously occur such as accelerating while falling, or slowing down while rising, and so forth. And, currently existing flight learning animation system cannot present such complex flight patterns to the pilots of aircrafts or to those personnel for air-traffic controllers. Hence, it is to be shown in this study that unit-path sketch animation method can support quicker ways to create animations to present those complex flight movements, and requires lesser inputs compared to the existing frame-based animation method. Also, the flight learning system suggested uses the flight-route realization tasks to reflect complex flight patterns, and therefore creates animations close to real as possible.

• The Journal of the Korea Contents Association
• /
• v.5 no.6
• /
• pp.57-64
• /
• 2005

LBL(Layer-By-Layer) algorithms have been proposed to accelerate the training speed of MLPs(Multilayer Perceptrons). In this LBL algorithms, each layer needs a error function for optimization. Especially, error function for hidden layer has a great effect to achieve good performance. In this sense, this paper proposes a new hidden layer error function for improving the performance of LBL algorithm for MLPs. The hidden layer error function is derived from the mean squared error of output layer. Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.