• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.625-632
• /
• 2021

This paper studies the effect of the number of filters in the CNN (Convolutional Neural Network) layer on the performance of a noise attenuator. Speech is estimated from a noised speech signal using a 64-neuron, 16-kernel CNN filter and an error back-propagation algorithm. In this study, in order to verify the performance of the noise attenuator with respect to the number of filters, a program using Keras library was written and simulation was performed. As a result of simulation, it can be seen that this system has the smallest MSE (Mean Squared Error) and MAE (Mean Absolute Error) values when the number of filters is 16, and the performance is the lowest when there are 4 filters. And when there are more than 8 filters, it was shown that the MSE and MAE values do not differ significantly depending on the number of filters. From these results, it can be seen that about 8 or more filters must be used to express the characteristics of the speech signal.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.45-52
• /
• 2022

In the field of UAM, which is attracting attention as a next-generation transportation system, technology developments for using UAVs have been actively conducted in recent years. Since UAVs adopted with these technologies are mainly operated in urban areas, it is imperative that accidents are prevented. However, it is not easy to predict the abnormal flight state of an UAV causing a crash, because of its strong non-linearity. In this paper, we propose a method for predicting a flight state of an UAV, based on a CNN-LSTM hybrid model. To predict flight state variables at a specific point in the future, the proposed model combines the CNN model extracting temporal and spatial features between flight data, with the LSTM model extracting a short and long-term temporal dependence of the extracted features. Simulation results show that the proposed method has better performance than the prediction methods, which are based on the existing artificial neural network model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.981-988
• /
• 2022

The intelligent production plant called smart factories that apply information and communication technology (ICT) are collecting data in real time through various sensors. Recently, researches that effectively applying to these collected data have gained a lot of attention. This paper proposes a method for the tool condition monitoring based on the sound signal generated in machining process. First, it not only detects a fault tool, but also presents various tool states according to idle and active operation. The second, it's to represent the power spectrum of the sounds as images and apply some transformations on them in order to reveal, expose, and emphasize the health patterns that are hidden inside them. Finally, the contrast-enhanced PSD image obtained is diagnosed by using CNN. The results of the experiments demonstrate the high discrimination potential afforded by the proposed sound PSD image + CNN and show high diagnostic results according to the tool status.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.279-282
• /
• 2022

Acute lymphoblastic leukemia is an acute leukemia caused by suppression of bone marrow function due to overgrowth of immature lymphocytes in the bone marrow. It accounts for 30% of acute leukemia in adults, and children show a cure rate of over 80% with chemotherapy, while adults show a low survival rate of 20% to 50%. However, research on a machine learning algorithm based on medical image data for the diagnosis of acute lymphoblastic leukemia is in the initial stage. In this paper, we compare and analyze CNN algorithm models for quick and accurate diagnosis. Using four models, an experimental environment for comparative analysis of acute lymphoblastic leukemia diagnostic models was established, and the algorithm with the best accuracy was selected for the given medical image data. According to the experimental results, among the four CNN models, the InceptionV3 model showed the best performance with an accuracy of 98.9%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.222-227
• /
• 2022

In this paper, we implemented a Korean text generation and classification model based on a deep learning algorithm that can be applied to various industries. It consists of two implemented GAN-based Korean handwriting generation models and CNN-based Korean handwriting classification models. The GAN model consists of a generator model for generating fake Korean handwriting data and a discriminator model for discriminating fake handwritten data. In the case of the CNN model, the model was trained using the 'PHD08' dataset, and the learning result was 92.45. It was confirmed that Korean handwriting was classified with % accuracy. As a result of evaluating the performance of the classification model by integrating the Korean cursive data generated through the implemented GAN model and the training dataset of the existing CNN model, it was confirmed that the classification performance was 96.86%, which was superior to the existing classification performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.150-153
• /
• 2022

This paper reports a technique that automatically extracts object shapes through Dense-Net, and subsequently, detects the objects using Mask R-CNN in a manufacturing site, in which workers and objects are mixed. It is based on the customized factory dataset by targeting workers, machines, tools, control boxes, and products as the objects. Mask R-CNN supports multi-object recognition as a well-known object recognition method, while Dense-Net effectively extracts a feature from multiple and overlapping objects. After immediate implementation using the two technologies, the object is naturally extracted from a still image of the manufacturing site to describe image. Afterwards, the result is planned to be used to detect workers' abnormal behavior by adding a label on the objects.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.19-28
• /
• 2024

This paper proposes a method to improve the performance of ship identification through lofargram analysis of ship noise by applying the Hough Transform to a Convolutional Neural Network (CNN) model. When processing the signals received by a passive sonar, the time-frequency domain representation known as lofargram is generated. The machinery noise radiated by ships appears as tonal signals on the lofargram, and the class of the ship can be specified by analyzing it. However, analyzing lofargram is a specialized and time-consuming task performed by well-trained analysts. Additionally, the analysis for target identification is very challenging because the lofargram also displays various background noises due to the characteristics of the underwater environment. To address this issue, the Hough Transform is applied to the lofargram to add lines, thereby emphasizing the tonal signals. As a result of identification using CNN models on both the original lofargrams and the lofargrams with Hough transform, it is shown that the application of the Hough transform improves lofargram identification performance, as indicated by increased accuracy and macro F1 scores for three different CNN models.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.271-278
• /
• 2021

As the current cyber attacks become more intelligent, the existing Intrusion Detection System is difficult for detecting intelligent attacks that deviate from the existing stored patterns. In an attempt to solve this, a model of a deep learning-based intrusion detection system that analyzes the pattern of intelligent attacks through data learning has emerged. Intrusion detection systems are divided into host-based and network-based depending on the installation location. Unlike network-based intrusion detection systems, host-based intrusion detection systems have the disadvantage of having to observe the inside and outside of the system as a whole. However, it has the advantage of being able to detect intrusions that cannot be detected by a network-based intrusion detection system. Therefore, in this study, we conducted a study on a host-based intrusion detection system. In order to evaluate and improve the performance of the host-based intrusion detection system model, we used the host-based Leipzig Intrusion Detection-Data Set (LID-DS) published in 2018. In the performance evaluation of the model using that data set, in order to confirm the similarity of each data and reconstructed to identify whether it is normal data or abnormal data, 1D vector data is converted to 3D image data. Also, the deep learning model has the drawback of having to re-learn every time a new cyber attack method is seen. In other words, it is not efficient because it takes a long time to learn a large amount of data. To solve this problem, this paper proposes the Siamese Convolutional Neural Network (Siamese-CNN) to use the Few-Shot Learning method that shows excellent performance by learning the little amount of data. Siamese-CNN determines whether the attacks are of the same type by the similarity score of each sample of cyber attacks converted into images. The accuracy was calculated using Few-Shot Learning technique, and the performance of Vanilla Convolutional Neural Network (Vanilla-CNN) and Siamese-CNN was compared to confirm the performance of Siamese-CNN. As a result of measuring Accuracy, Precision, Recall and F1-Score index, it was confirmed that the recall of the Siamese-CNN model proposed in this study was increased by about 6% from the Vanilla-CNN model.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.