• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.29-34
• /
• 2022

We propose a novel network architecture and build dataset for recognizing clickable objects on mobile device screens. The data was collected based on clickable objects on the mobile device screen that have numerous resolution, and a total of 24,937 annotation data were subdivided into seven categories: text, edit text, image, button, region, status bar, and navigation bar. We use the Deconvolution Single Shot Detector as a baseline, the backbone network with Squeeze-and-Excitation blocks, the Single Shot Detector layer structure to derive inference results and the Feature pyramid networks structure. Also we efficiently extract features by changing the input resolution of the existing 1:1 ratio of the network to a 1:2 ratio similar to the mobile device screen. As a result of experimenting with the dataset we have built, the mean average precision was improved by up to 101% compared to baseline.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.87-92
• /
• 2022

Image-based application testing proposes an application testing method via image structure comparison. This test method allows testing on various devices without relying on various types of device operating systems or GUI. Traditional studies required the creation of a tester for each variant in the existing case, because it differs from the correct image for operating system changes, screen animation execution, and resolution changes. The study determined that the screen is the same for variations. The tester compares the underlying structure of the objects in the two images and extracts the regions in which the differences exist in the images, and compares image similarity as characteristic points of the Faster D2-Net. The development of the Faster D2-Net reduced the number of operations and spatial losses compared to the D2-Net, making it suitable for extracting features from application images and reducing test performance time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1469-1476
• /
• 2022

Recently, many researches have been conducted to estimate blood pressure using ECG(Electrocardiogram) and PPG(Photoplentysmography) signals. In this paper, we designed and implemented a mobile system to monitor blood pressure in real time by using 1-D convolutional neural networks. The proposed model consists of deep 11 layers which can learn to extract various features of ECG and PPG signals. The simulation results show that the more the number of convolutional kernels the learned neural network has, the more detailed characteristics of ECG and PPG signals resulted in better performance with reduced mean square error compared to linear regression model. With receiving measurement signals from wearable ECG and PPG sensor devices attached to the body, the developed system receives measurement data transmitted through Bluetooth communication from the devices, estimates systolic and diastolic blood pressure values using a learned model and displays its graph in real time.

• Journal of Aerospace System Engineering
• /
• v.16 no.5
• /
• pp.70-77
• /
• 2022

This paper proposes database generation and management system for small-pixelized airborne target recognition. The proposed system has five main features: 1) image extraction from in-flight test video frames, 2) automatic image archiving, 3) image data labeling and Meta data annotation, 4) virtual image data generation based on color channel convert conversion and seamless cloning and 5) HOG/LBP-based tiny-pixelized target augmented image data. The proposed framework is Python-based PyQt5 and has an interface that includes OpenCV. Using video files collected from flight tests, an image dataset for airborne target recognition on generates by using the proposed system and system input.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.933-943
• /
• 2022

As the Internet develops and the utilization rate of computers increases, the threats posed by malware keep increasing. This leads to the demand for a system to automatically analyzes a large amount of malware. In this paper, an automatic malware analysis technique using a deep learning algorithm is introduced. Our proposed method uses CNN (Convolutional Neural Network) to analyze the malicious features represented as images. To reflect semantic information of malware for detection, our method uses the opcode frequency data of binary for image generation, rather than using bytes of binary. As a result of the experiments using the datasets consisting of 20,000 samples, it was found that the proposed method can detect malicious codes with 91% accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.662-667
• /
• 2022

Semantic role labeling task(SRL) is to extract predicate and arguments such as agent, patient, place, time. In the previously SRL task studies, a pipeline method extracting linguistic features of sentence has been proposed, but in this method, errors of each extraction work in the pipeline affect semantic role labeling performance. Therefore, methods using End-to-End neural network model have recently been proposed. In this paper, we propose a neural network model using the Biaffine Average Attention model for SRL task. The proposed model consists of a structure that can focus on the entire sentence information regardless of the distance between the predicate in the sentence and the arguments, instead of LSTM model that uses the surrounding information for prediction of a specific token proposed in the previous studies. For evaluation, we used F1 scores to compare two models based BERT model that proposed in existing studies using F1 scores, and found that 76.21% performance was higher than comparison models.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.21-29
• /
• 2022

Based on the importance of dialect research, preservation, and communication, this paper conducted a study on machine translation of Korean dialects for dialect users who may be marginalized. For the dialect data used, AIHUB dialect data distributed based on the highest administrative district was used. We propose a many-to-one dialect machine translation that promotes the efficiency of model distribution and modeling research to improve the performance of the dialect machine translation by applying Copy mechanism. This paper evaluates the performance of the one-to-one model and the many-to-one model as a BLEU score, and analyzes the performance of the many-to-one model in the Korean dialect from a linguistic perspective. The performance improvement of the one-to-one machine translation by applying the methodology proposed in this paper and the significant high performance of the many-to-one machine translation were derived.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.35-43
• /
• 2023

Emotion recognition while driving is an essential task to prevent accidents. Furthermore, in the era of autonomous driving, automobiles are the subject of mobility, requiring more emotional communication with drivers, and the emotion recognition market is gradually spreading. Accordingly, in this research plan, the driver's emotions are classified into seven categories using psychological and behavioral data, which are relatively easy to collect. The latent vectors extracted through the auto-encoder model were also used as features in this classification model, confirming that this affected performance improvement. Furthermore, it also confirmed that the performance was improved when using the framework presented in this paper compared to when the existing EEG data were included. Finally, 81% of the driver's emotion classification accuracy and 80% of F1-Score were achieved only through psychological, personal information, and behavioral data.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.2
• /
• pp.134-142
• /
• 2022

As industry and technology go through advancement, it is hard to search new materials which satisfy various standards through conventional trial-and-error based research methods. Crystal Graph Convolutional Neural Network(CGCNN) is a neural network which uses material's features as train data, and predicts the material properties(formation energy, bandgap, etc.) much faster than first-principles calculation. This report introduces how to train the CGCNN model which predicts the formation energy using open database. It is anticipated that with a simple programming skill, readers could construct a model using their data and purpose. Developing machine learning model for materials science is going to help researchers who should explore large chemical and structural space to discover materials efficiently.