• 전자통신동향분석
• /
• 제34권4호
• /
• pp.23-31
• /
• 2019

Deep learning is a hot topic in both academic and industrial fields. Deep learning applications can be categorized into two areas. The first category involves applications such as Google Alpha Go using interfaces with human operators to run complicated inference engines in high-performance servers. The second category includes embedded applications for mobile Internet-of-Things devices, automotive vehicles, etc. Owing to the characteristics of the deployment environment, applications in the second category should be bounded by certain H/W and S/W restrictions depending on their running environment. For example, image recognition in an autonomous vehicle requires low latency, while that on a mobile device requires low power consumption. In this paper, we describe issues faced by embedded applications and review popular inference engines. We also introduce a project that is being development to satisfy the H/W and S/W requirements.

• 문화기술의 융합
• /
• 제8권6호
• /
• pp.553-560
• /
• 2022

고등교육기관의 역량 중심 교육과정 운영을 위해서는 교과목 수준에서 교과 학습목표(성과기준)의 성취수준을 다각도로 평가하여 학습자의 역량 함양 정도를 파악하는 교과기반 학습평가 방법에 대한 연구가 지속적으로 필요하다. 본 연구에서는 교과목 학습성과, 학습주제, 학습개념 기반의 학습평가 모델 및 성취수준에 따른 개인화된 학습 피드백 모델을 제안한다. 먼저 데이터 모델링 과정에서 교과목의 계층화된 학습성과, 학습주제 및 학습개념 그래프 및 학습성과-평가 매트릭스 모델을 정의하고 이를 기반으로 학습성과별, 학습주제별, 학습자별 등 다각도의 학습성취 수준을 측정하고 피드백하는 알고리즘을 제안한다. 제안한 학습성취평가 모델의 유효성을 검증하기 위해 자바프로그래밍 교과목에 적용하여 실제 데이터를 기반으로 실험을 진행하였으며 그 결과 성취수준의 산출 및 학습 피드백이 가능함을 보였다.

• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.797-802
• /
• 2016

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• 문화기술의 융합
• /
• 제7권1호
• /
• pp.668-673
• /
• 2021

4차산업혁명이 본격화됨에 따라 관련 기술들이 화두가 되고 있다. 고속 무선통신과 같은 기술을 최대한으로 활용하기 위한 하드웨어 개발이 가속화되고 있으며, 관련 기업들이 급격히 성장하고 있다. 인공지능의 경우 관련 연구를 위해서 일반적으로 데스크톱을 사용하는 경우가 많지만, 주로 딥러닝의 학습 과정을 위해 사용되고 있으며 생성된 모델을 프로그램 등에 포함하여 사용할 기기에 이식하는 경우가 많다. 하지만, 학습량이 과도하거나 데스크톱의 성능만큼 제작된 모델을 사용하게 되어 전원공급이 따로 이루어지지 않는 기기의 경우 전력이 부족하거나 성능이 충분하지 못하기 때문에 제 결과를 내기 어렵다. 본 논문에서는 딥러닝의 성능을 임베디드 보드에 맞추어 개발하기 전에 판매되고 있는 몇 가지 Neural Process Unit을 탑재한 보드와 USB로 딥러닝 수행 성능을 높일 수 있는 딥러닝 액셀러레이터를 사용하여 효율성을 비교하여 임베디드 보드로 가능한 개발 방향을 제시한다.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• 방송공학회논문지
• /
• 제25권2호
• /
• pp.157-165
• /
• 2020

본 논문에서는 임베디드 시스템에서의 양자화 기계학습을 수행할 경우 발생하는 양자화 오차를 효과적으로 보상하기 위한 방법론을 제안한다. 경사 도함수(Gradient)를 사용하는 기계학습이나 비선형 신호처리 알고리즘에서 양자화 오차는 경사 도함수의 조기 소산(Early Vanishing Gradient)을 야기하여 전체적인 알고리즘의 성능 하락을 가져온다. 이를 보상하기 위하여 경사 도함수의 최대 성분에 대하여 직교하는 방향의 보상 탐색 벡터를 유도하여 양자화 오차로 인한 성능 하락을 보상하도록 한다. 또한, 기존의 고정 학습률 대신, 내부 순환(Inner Loop) 없는 비선형 최적화 알고리즘에 기반한 적응형 학습률 결정 알고리즘을 제안한다. 실험 결과 제안한 방식의 알고리즘을 로젠블록 함수를 통한 비선형 최적화 문제에 적용할 시 양자화 오차로 인한 성능 하락을 최소화시킬 수 있음을 확인하였다.

• International Journal of Contents
• /
• 제11권1호
• /
• pp.1-6
• /
• 2015

The development of information and technology has brought plenty of changes to the educational environment. The prevalence of smart phones is particularly playing a huge role in shaping learning methods. Smart phones provide the opportunity to scan QR codes, which can greatly ease access to information. Due to a high recognition speed, recognition rate, and restoration rate, they can be useful tools for English teachers to use in their class. In this study, we suggest using QR codes for writing and picture descriptions. Based on this study, more research should invest in Technology Embedded English teaching models to create better English classes for students.

• 드라이브 ㆍ 컨트롤
• /
• 제11권4호
• /
• pp.1-7
• /
• 2014

This paper presents the development of a compact position generator to be used for industrial purposes based on a pump controlled Electro-Hydraulic Actuator (EHA), which is closed-loop controlled by an embedded based Iterative PID controller. The controller is designed by combining the PID controller and the iterative learning scheme to perform tracking control for periodically desired references. Control algorithm is implemented on an embedded computer (AD 7011-EVA) which makes the implementation and application in industrial environments easier.

• 대한임베디드공학회논문지
• /
• 제16권1호
• /
• pp.17-27
• /
• 2021

In this paper, we develop a galaxy image classification method based on hand-crafted features and machine learning techniques. Additionally, we provide an empirical analysis to reveal which combination of the techniques is effective for galaxy image classification. To achieve this, we developed a framework which consists of four modules such as preprocessing, feature extraction, feature post-processing, and classification. Finally, we found that the best technique for galaxy image classification is a method to use a median filter, ORB vector features and a voting classifier based on RBF SVM, random forest and logistic regression. The final method is efficient so we believe that it is applicable to embedded environments.