• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.23-30
• /
• 2021

Sentiment Analysis has become very important field of research because posting of reviews is becoming a trend. Supervised, unsupervised and semi supervised machine learning methods done lot of work to mine this data. Feature engineering is complex and technical part of machine learning. Deep learning is a new trend, where this laborious work can be done automatically. Many researchers have done many works on Deep learning Convolutional Neural Network (CNN) and Long Shor Term Memory (LSTM) Neural Network. These requires high processing speed and memory. Here author suggested two models simple & bidirectional deep leaning, which can work on text data with normal processing speed. At end both models are compared and found bidirectional model is best, because simple model achieve 50% accuracy and bidirectional deep learning model achieve 99% accuracy on trained data while 78% accuracy on test data. But this is based on 10-epochs and 40-batch size. This accuracy can also be increased by making different attempts on epochs and batch size.

• 한국산업융합학회 논문집
• /
• 제23권3호
• /
• pp.515-521
• /
• 2020

Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we compared the quality of CNN features for traditional texture feature extraction methods. Experimental results demonstrate the superiority of the CNN features. Additionally, the recognition process and result of a pioneering CNN on MNIST database are presented.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1387-1395
• /
• 2018

Core algorithm of deep learning Convolutional Neural Network(CNN) shows better performance than other machine learning algorithms. However, if there is not sufficient data, CNN can not achieve satisfactory performance even if the classifier is excellent. In this situation, it has been proven that the use of transfer learning can have a great effect. In this paper, we apply two transition learning methods(freezing, retraining) to three CNN models(ResNet-50, Inception-V3, DenseNet-121) and compare and analyze how the classification performance of CNN changes according to the methods. As a result of statistical significance test using various evaluation indicators, ResNet-50, Inception-V3, and DenseNet-121 differed by 1.18 times, 1.09 times, and 1.17 times, respectively. Based on this, we concluded that the retraining method may be more effective than the freezing method in case of transition learning in image classification problem.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.99-103
• /
• 2021

Warpage defect detecting of scaffold is very important in biosensor production. Because warpaged scaffold cause problem in cell culture. Currently, there is no detection equipment to warpaged scaffold. In this paper, we produced detection model for shape warpage detection using deep learning based CNN. We confirmed the shape of the scaffold that is widely used in cell culture. We produced scaffold specimens, which are widely used in biosensor fabrications. Then, the scaffold specimens were photographed to collect image data necessary for model manufacturing. We produced the detecting model of scaffold warpage defect using Densenet among CNN models. We evaluated the accuracy of the defect detection model with mAP, which evaluates the detection accuracy of deep learning. As a result of model evaluating, it was confirmed that the defect detection accuracy of the scaffold was more than 95%.

• 한국산업정보학회논문지
• /
• 제23권4호
• /
• pp.41-53
• /
• 2018

최근 들어 머신 러닝 기술의 발달로 기존 영상 기반의 응용시스템에 딥러닝 기술을 적용하는 사례들이 늘고 있다. 이러한 맥락에서 화재 감지 분야에서도 CNN (Convolutional Neural Network)을 적용하는 시도들이 이루어지고 있다. 본 논문에서는 기존 전처리 방법과 특징 추출 방법이 CNN과 결합되었을 때 화재 탐지에 어떤 효과를 유발하는지를 검증하기 위해 인식 성능과 학습 시간을 평가해 보았다. VGG19 CNN 구조를 변경, 즉 컨볼루션층을 조금씩 늘리면서 실험을 진행한 결과, 일반적으로 전처리하지 않는 이미지를 사용한 경우가 성능이 훨씬 좋음을 확인할 수 있었다. 또한 성능적인 측면에서는 전처리 방법과 특징 추출 방법이 부정적인 영향을 미치지만 학습속도 측면에서는 많은 이득이 있음을 확인할 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.460-462
• /
• 2021

식품은 기본적으로 영양성과 안전성을 반드시 갖추어야 한다. 최근에 식품의 안정성이 의심이 되는 안산의 한 유치원에서 식중독성 유증상자가 다수 발생하였다. 그래서 식품의 안전성은 더욱 요구되는 사항이다. 본 논문에서는 식품의 안전성을 확보하기 위한 이물검출기의 딥러닝모델을 통해 검출율을 향상시키는 방법을 제안한다. 제안방법으로는 CNN(convolution neural network), Faster R-CNN(region convolution neural network)의 네트워크를 통해 학습하고 정상과 이물제품의 영상을 테스트 한다. 딥러닝 모델을 통해 테스트한 결과 기존 이물검출기의 알고리즘에 Faster R-CNN을 병행한 방법이 다른 방법보다 검출율이 좋은 성능을 보였다.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.1-7
• /
• 2019

Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.331-334
• /
• 2021

In the latest eras, there has been a significant amount of development and research is done on the usage of Deep Learning (DL) for speech emotion recognition (SER) based on Convolutional Neural Network (CNN). These techniques are usually focused on utilizing CNN for an application associated with emotion recognition. Moreover, numerous mechanisms are deliberated that is based on deep learning, meanwhile, it's important in the SER-based human-computer interaction (HCI) applications. Associating with other methods, the methods created by DL are presenting quite motivating results in many fields including automatic speech recognition. Hence, it appeals to a lot of studies and investigations. In this article, a review with evaluations is illustrated on the improvements that happened in the SER domain though likewise arguing the existing studies that are existence SER based on DL and CNN methods.