• 대한임베디드공학회논문지
• /
• 제18권2호
• /
• pp.59-65
• /
• 2023

Currently, polysomnography is essential to diagnose sleep-related breathing disorders. However, there are several disadvantages to polysomnography, such as the requirement for multiple sensors and a long reading time. In this paper, we propose a system for predicting the severity of sleep-related breathing disorders at home utilizing measurable elements in a wearable device. To predict severity, the variables were refined through a three-step variable selection process, and the refined variables were used as inputs into three machine-learning models. As a result of the study, random forest models showed excellent prediction performance throughout. The best performance of the model in terms of F1 scores for the three threshold criteria of 5, 15, and 30 classified as the AHI index was about 87.3%, 90.7%, and 90.8%, respectively, and the maximum performance of the model for the three threshold criteria classified as the RDI index was approx 79.8%, 90.2%, and 90.1%, respectively.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권11호
• /
• pp.449-456
• /
• 2019

본 논문은 진공을 이용한 흡착방식과 바퀴형 이동방식을 사용하는 벽면 이동로봇의 구성과 이러한 임베디드 환경에 적합하고 기계학습에 기반한 벽면 균열 자동 검출 알고리즘의 성능 비교에 관한 연구이다. 임베디드 시스템 환경에서 객체 학습을 위해 YOLO 등 최근에 시도된 학습 방법들을 적용하여 성능을 비교, 검토하였으며 기존의 에지 검출 알고리즘들과도 성능을 비교하였다. 결국, 본 연구에서는 균열검출을 잘하며 임베디드 환경에도 적합한 최적의 기계학습방법을 선택하고 기존 방법과 성능을 비교하여 우수성을 제시하였다. 또한, 검출된 균열의 영상을 저장하고 위치 정보를 추정하여 균열에 대한 정보를 관리자 기기로 전송하는 지능적인 문제해결 기능을 구축하였다.

• 한국멀티미디어학회논문지
• /
• 제24권4호
• /
• pp.528-537
• /
• 2021

Face recognition has gained significant notice because of its application in many businesses: security, healthcare, and marketing. In this paper, we will present the recognition method using the combination of correlation filters (CF) and Support Vector Machine (SVM). Firstly, we evaluate the performance and compared four different correlation filters: minimum average correlation energy (MACE), maximum average correlation height (MACH), unconstrained minimum average correlation energy (UMACE), and optimal-tradeoff (OT). Secondly, we propose the machine learning approach by using the OT correlation filter for features extraction and SVM for classification. The numerical results on National Cheng Kung University (NCKU) and Pointing'04 face database show that the proposed method OT-SVM gets higher accuracy in face recognition compared to other machine learning methods. Our approach doesn't require graphics card to train the image. As a result, it could run well on a low hardware system like an embedded system.

• 대한임베디드공학회논문지
• /
• 제14권5호
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권8호
• /
• pp.578-584
• /
• 2004

The CSVM(Current Support Vector Machine) that is a digital architecture performing all phases of recognition process including kernel computing, learning, and recall of SVM(Support Vector Machine) on a chip is proposed. Concurrent operation by parallel architecture of elements generates high speed and throughput. The classification problems of bio data having high dimension are solved fast and easily using the CSVM. Quadratic programming in original SVM learning algorithm is not suitable for hardware implementation, due to its complexity and large memory consumption. Hardware-friendly SVM learning algorithms, kernel adatron and kernel perceptron, are embedded on a chip. Experiments on fixed-point algorithm having quantization error are performed and their results are compared with floating-point algorithm. CSVM implemented on FPGA chip generates fast and accurate results on high dimensional cancer data.

• 문화기술의 융합
• /
• 제7권1호
• /
• pp.615-619
• /
• 2021

이 연구는 사물인터넷, 클라우드 컴퓨팅 그리고 에지 컴퓨팅 등 많은 임베디드 시스템에서 성능 및 에너지 효율을 높이고자 최적화하는 메모리 시스템에 초점을 맞추어 그 성능 개선 기법을 제안한다. 제안하는 기법은 최근 많이 이용되고 있는 머신 러닝 알고리즘을 기반으로 메모리 시스템 성능을 도모한다. 머신 러닝 기법은 학습을 통하여 다양한 응용에 사용될 수 있는데, 메모리 시스템 성능 개선에서 사용되는 데이터의 분류 태스크에 적용될 수 있다. 정확도 높은 머신 러닝 기법 기반 데이터 분류는 데이터의 사용 패턴에 따라 데이터를 적절하게 배치할 수 있게 하여 전체 시스템 성능 개선을 도모할 수 있게 한다.

• 한국소프트웨어감정평가학회 논문지
• /
• 제16권2호
• /
• pp.127-133
• /
• 2020

인공지능의 활용성이 다양해지면서 소형 휴대용기기에 알고리즘을 탑재하려는 요구가 증가하고 있다. 또한 임베디드 시스템이 고성능화하면서 운영체제는 물론 고속연산 및 머신러닝의 알고리즘 구현이 가능해 지고 있다. 그러나 반복연산과 방대한 학습데이터를 처리하는 머신러닝알고리즘의 특성으로 네트워크 연결에 의한 클라우드 환경에 의존하고 있다. 임베디드 시스템에서의 독자적인 운영을 위해서는 저 전력화 및 최적화 알고리즘에 의한 빠른 실행이 요구된다. 본 연구에서는 스마트 제어를 목적으로 임베디드 시스템에 에너지 측정용 센서를 연결하고, 실시간 측정 및 모니터링 시스템으로 측정정보를 데이터베이스로 저장하는 장치를 구현하였다. 연속적으로 측정되어 저장된 데이터는 학습 알고리즘에 적용하여, 최적화 전력제어에 활용가능하며, 에너지 측정에 요구되는 다양한 센서의 인터페이스가 가능한 시스템을 구성하였다.

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.47-55
• /
• 2023

The automotive industry is undergoing a paradigm shift due to the convergence of IT and rapid digital transformation. Various components, including embedded structures and systems with complex architectures that incorporate IC semiconductors, are being integrated and modularized. As a result, there has been a significant increase in vehicle defects, raising expectations for the quality of automotive parts. As more and more data is being accumulated, there is an active effort to go beyond traditional reliability analysis methods and apply machine learning models based on the accumulated big data. However, there are still not many cases where machine learning is used in product development to identify factors of defects in performance and durability of products and incorporate feedback into the design to improve product quality. In this paper, we applied a prediction algorithm to the defects of automotive door devices equipped with automatic responsive sensors, which are commonly installed in recent electric and hydrogen vehicles. To do so, we selected test items, built a measurement emulation system for data acquisition, and conducted comparative evaluations by applying different machine learning algorithms to the measured data. The results in terms of R² score were as follows: Ordinary multiple regression 0.96, Ridge regression 0.95, Lasso regression 0.89, Elastic regression 0.91.

• 대한임베디드공학회논문지
• /
• 제19권3호
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• 대한임베디드공학회논문지
• /
• 제3권2호
• /
• pp.119-125
• /
• 2008

This paper presents the polygon-based Q-leaning and Cascade Support Vector Machine algorithm for object search with multiple robots. We organized an experimental environment with ten mobile robots, twenty five obstacles, and an object, and then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning and dodecagon-based Q-learning and Cascade SVM to enhance the fusion model with DBAM and ABAM process.