• 대한임베디드공학회논문지
• /
• 제17권1호
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• 디지털산업정보학회논문지
• /
• 제17권3호
• /
• pp.9-15
• /
• 2021

In this paper, the Embedded MEMS system to the power apparatus used Edge Impulse machine learning tools and therefore an improved predictive system design is implemented. The proposed MEMS embedded system is developed based on nRF52840 system and the sensor with 3-Axis Digital Magnetometer, I2C interface and magnetic measurable range ±120 uT, BM1422AGMV which incorporates magneto impedance elements to detect magnetic field and the ARM M4 32-bit processor controller circuit in a small package. The MEMS embedded platform is consisted with Edge Impulse Machine Learning and system driver implementation between hardware and software drivers using SensorQ which is special queue including user application temporary sensor data. In this paper by experimenting, TensorFlow machine learning training output is applied to the power apparatus for analyzing the status such as "Normal, Warning, Hazard" and predicting the performance at level of 99.6% accuracy and 0.01 loss.

• 대한임베디드공학회논문지
• /
• 제15권6호
• /
• pp.307-316
• /
• 2020

Machine learning model data is highly affected by performance. preprocessing is needed to enable analysis of various types of data, such as letters, numbers, and special characters. This paper proposes a development environment that aims to process categorical and continuous data according to the type of missing values in stage 1, implementing the function of selecting the best performing algorithm in stage 2 and automating the process of checking model performance in stage 3. Using this model, machine learning models can be created without prior knowledge of data preprocessing.

• 대한임베디드공학회논문지
• /
• 제14권4호
• /
• pp.207-218
• /
• 2019

The purpose of this study is to develop a model that can systematically study the whole learning process of machine learning. Since the existing model describes the learning process with minimum coding, it can learn the progress of machine learning sequentially through the new model, and can visualize each process using the tensor flow. The new model used all of the existing model algorithms and confirmed the importance of the variables that affect the target variable, survival. The used to classification training data into training and verification, and to evaluate the performance of the model with test data. As a result of the final analysis, the ensemble techniques is the all tutorial model showed high performance, and the maximum performance of the model was improved by maximum 5.2% when compared with the existing model using. In future research, it is necessary to construct an environment in which machine learning can be learned regardless of the data preprocessing method and OS that can learn a model that is better than the existing performance.

• 대한임베디드공학회논문지
• /
• 제15권1호
• /
• pp.1-8
• /
• 2020

A derivation method for a quantized gradient for machine learning on an embedded system is proposed, in this paper. The proposed differentiation method induces the quantized gradient vector to an objective function and provides that the validation of the directional derivation. Moreover, mathematical analysis shows that the sequence yielded by the learning equation based on the proposed quantization converges to the optimal point of the quantized objective function when the quantized parameter is sufficiently large. The simulation result shows that the optimization solver based on the proposed quantized method represents sufficient performance in comparison to the conventional method based on the floating-point system.

• 대한임베디드공학회논문지
• /
• 제17권2호
• /
• pp.93-100
• /
• 2022

In this paper, we propose a machine learning-based method for supporting resource management of IoT software platforms in a multi-modal sensing scenario. We assume that an IoT device installed with a oneM2M-compatible software platform is connected with various sensors such as PIR, sound, dust, ambient light, ultrasonic, accelerometer, through different embedded system interfaces such as general purpose input output (GPIO), I2C, SPI, USB. Based on a collected dataset including CPU usage and user-defined priority, a machine learning model is trained to estimate the level of nice value required to adjust according to the resource usage patterns. The proposed method is validated by comparing with a rule-based control strategy, showing its practical capability in a multi-modal sensing scenario of IoT devices.

• 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.

• 한국전자통신학회논문지
• /
• 제19권2호
• /
• pp.417-426
• /
• 2024

일반적으로 머신러닝을 수행하기 위해서는 딥러닝 모델에 대한 사전 지식과 경험이 필요하고, 데이터를 연산하기 위해 고성능 하드웨어와 많은 시간이 필요하게 된다. 이러한 이유로 머신러닝은 임베디드 프로세서에서 실행하기에는 많은 제약이 있다.본 논문에서는 이러한 문제를 해결하기 위해 머신러닝의 과정 중 콘볼루션 연산(Convolution operation)에 유전 알고리즘을 적용하여 선택적 콘볼루션 연산(Selective convolution operation)과 학습 방법을 제안한다. 선택적 콘볼루션 연산에서는 유전 알고리즘에 의해 추출된 픽셀에 대해서만 콘볼루션을 수행하는 방식이다. 이 방식은 유전 알고리즘에서 지정한 비율만큼 픽셀을 선택하여 연산하는 방식으로 연산량을 지정된 비율만큼 줄일 수 있다. 본 논문에서는 유전 알고리즘을 적용한 머신러닝 연산의 심화학습을 진행하여 해당 세대의 적합도가 목표치에 도달하는지 확인하고 기존 방식의 연산량과 비교한다. 적합도가 충분히 수렴할 수 있도록 세대를 반복하여 학습하고, 적합도가 높은 모델을 유전 알고리즘의 교배와 돌연변이를 통해 다음 세대의 연산에 활용한다.

• 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.

• 디지털융복합연구
• /
• 제17권10호
• /
• pp.265-271
• /
• 2019

국민 소득의 증가로 인해 문화 생활에 대한 관심이 크게 증가하면서 전국 미술관의 수도 함께 증가하고 있다. 하지만 다른 서비스에 비해 미술관 만족도는 상대적으로 낮은 편이다. 본 논문에서는 미술관 만족도를 높이기 위해 임베디드 시스템 환경에서 머신러닝에 기반한 관중들의 선호도에 관련된 정보를 제공하는 서비스를 제안한다. 제안된 알고리즘은 라즈베리 파이를 이용하여 임베디드 시스템을 구현했다. 관람자가 선호하는 작품과 유사한 작품을 찾아내기 위해 머신러닝을 이용하였고 여러 머신러닝 모델을 비교하여 임베디드 시스템에 적용 가능한 모델을 선정했다. 관람자의 취향에 맞는 정보를 활용하여 갤러리 전시 내용을 효과적으로 구성하여 전시 만족도를 높이고 이는 미술관 재 방문율을 높일 수 있을 것이다.