• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.777-784
• /
• 2019

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.1-8
• /
• 2019

This paper estimated communication parameters according to underwater channel environment of lake for underwater acoustic communication. This paper calculated coherence time and coherence bandwidth through two experiments in actual lake environments. In both experiments, the chirp signal for channel estimation and the BPSK (Binary Phase Shift Keying) signal for calculating the bit error rate were transmitted. In each experiment, the distance between transmitter and receiver was 300 m to 400 m, and 500 m to 600 m. The coherence times calculated in experiment 1 and experiment 2 are 175 msec and 340 msec, and the coherence bandwidths are 10 Hz and 5.71 Hz, respectively. It is confirmed that the experimental results are more appropriate because the synchronization and the bit error rate performance are better only when the length of the synchronization signal and the interval of the pilot signal in the frame are shorter than the coherence time.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.97-110
• /
• 2022

Federated learning is a learning method capable of performing model learning without transmitting learning data. The IoT or healthcare field is sensitive to information leakage as it deals with users' personal information, so a lot of attention should be paid to system design, but when using federated-learning, data does not move from devices where data is collected. Accordingly, many federated-learning implementations have been developed, but detailed research on system design for the development and operation of systems using federated learning is insufficient. This study shows that measures for the life cycle, code version management, model serving, and device monitoring of federated learning are needed to be applied to actual projects and distributed to IoT devices, and we propose a design for a development environment that complements these points. The system proposed in this paper considered uninterrupted model-serving and includes source code and model version management, device state monitoring, and server-client learning schedule management.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.751-757
• /
• 2021

In this paper, we proposed a pipeline system for holographic image production in a web server-based environment. There are time and spatial constraints for the existing holographic image production. The purpose of the proposed system is to obtain high-quality holographic images by reducing accessibility to users. It is a structure in which a video captured by a user in a web environment is transmitted to a server and converted into a frame for holographic image production through post-production. For high-quality holographic image acquisition, post-processing uses a deep learning-based algorithm. The proposed system provides various service tools in the web environment for user convenience. Through this method, the user's accessibility is improved when producing holographic images because images are taken in a web environment rather than in a limited space.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.150-158
• /
• 2022

This paper presents the results of a sea trial for very long range spread spectrum underwater acoustic communication conducted in the East Sea in September 2021. Signals were collected through 8 vertical sensors, and the range between the transmitter and receiver was about 160 km. 30 bps Multi-Code Spread Spectrum (MCSS) method and 100 bps Chirp Spread Spectrum method were used for the transmitting signal generation. The results show that when the channel coding technique was not used in a single channel, the uncoded bit error rate was high, but when the Equal Gain Combining (EGC) diversity technique was used after frame synchronization in each receiving channel, the uncoded bit error rate was reduced to 0.1 or less.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.379-392
• /
• 2024

With the rapid increase in data, saving storage space and improving the efficiency of data transmission have become critical issues, making the research on the efficiency of data compression technologies increasingly important. Lossless algorithms can precisely restore original data but have limited compression ratios, whereas lossy algorithms provide higher compression rates at the expense of some data loss. There has been active research in data compression using deep learning-based algorithms, especially the autoencoder model. This study proposes a new side-channel analysis data compressor utilizing autoencoders. This compressor achieves higher compression rates than Deflate while maintaining the characteristics of side-channel data. The encoder, using locally connected layers, effectively preserves the temporal characteristics of side-channel data, and the decoder maintains fast decompression times with a multi-layer perceptron. Through correlation power analysis, the proposed compressor has been proven to compress data without losing the characteristics of side-channel data.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.91-105
• /
• 2024

Car accidents occur as a result of collisions between vehicles, leading to both vehicle damage and personal and material losses. This study developed a vehicle accident detection model based on 2,550 image frames extracted from car accident videos uploaded to YouTube, captured by CCTV. To preprocess the data, bounding boxes were annotated using roboflow.com, and the dataset was augmented by flipping images at various angles. The You Only Look Once version 8 (YOLOv8) model was employed for training, achieving an average accuracy of 0.954 in accident detection. The proposed model holds practical significance by facilitating prompt alarm transmission in emergency situations. Furthermore, it contributes to the research on developing an effective and efficient mechanism for vehicle accident detection, which can be utilized on devices like smartphones. Future research aims to refine the detection capabilities by integrating additional data including sound.

• Journal of the Health Care and Life Science
• /
• v.10 no.2
• /
• pp.361-367
• /
• 2022

This study provides several methods to minimize dead zone and to detect missing person using combined DRONE and AI especially called 4 th Industrial Revolution. That is composed of image acquisition for a person who is in needed of support. The procedure is DRONE that is made of image acquisition and transfer system. after that can be shown GPS information. Currently representative AI algorithm is YOLO (You Only Look Once) that can be adopted to find manikin or real image by learning with dataset. The output was reached in reliable and efficient results. As the trends of DRONE is expanded widely that will provide various roll. This paper was composed of three parts. the first is DRONE specification, the second is the definition of AI and procedures, the third is the methods of image acquisition using DRONE, the last is the future of DRONE with AI.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.129-135
• /
• 2024

In this paper, we design and implement a worker musculoskeletal assessment platform. The three core components of this platform are the Mobile App, the Modeling Server, and the Web Platform. The Mobile App is an Android application developed in Kotlin, targeting Android platform 12 (S) and Android API Level 31 devices. The app utilizes the camera to capture various worker motion data and transmits it to the Modeling Server. The Modeling Server is implemented using Node.js. This server converts the worker's motion data-such as points, skeleton, and x, y, z coordinate data, measured by the mobile app-into multidimensional arrays. It then applies machine learning frameworks like TensorFlow and Keras to predict the worker's posture. The worker posture learning model is built using Teachable Machine. The Web Platform is developed using React and visualizes the worker's movements as 3D animations along a timeline. The machine learning-based worker musculoskeletal assessment platform developed in this paper aims to contribute to minimizing musculoskeletal disorders in workers at industrial sites.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.109-115
• /
• 2015

The new medical device technologies for bio-signal information and medical information which developed in various forms have been increasing. Information gathering techniques and the increasing of the bio-signal information device are being used as the main information of the medical service in everyday life. Hence, there is increasing in utilization of the various bio-signals, but it has a problem that does not account for security reasons. Furthermore, the medical image information and bio-signal of the patient in medical field is generated by the individual device, that make the situation cannot be managed and integrated. In order to solve that problem, in this paper we integrated the QR code signal associated with the medial image information including the finding of the doctor and the bio-signal information. bio-signal. System implementation environment for medical imaging devices and bio-signal acquisition was configured through bio-signal measurement, smart device and PC. For the ROI extraction of bio-signal and the receiving of image information that transfer from the medical equipment or bio-signal measurement, .NET Framework was used to operate the QR server module on Window Server 2008 operating system. The main function of the QR server module is to parse the DICOM file generated from the medical imaging device and extract the identified ROI information to store and manage in the database. Additionally, EMR, patient health information such as OCS, extracted ROI information needed for basic information and emergency situation is managed by QR code. QR code and ROI management and the bio-signal information file also store and manage depending on the size of receiving the bio-singnal information case with a PID (patient identification) to be used by the bio-signal device. If the receiving of information is not less than the maximum size to be converted into a QR code, the QR code and the URL information can access the bio-signal information through the server. Likewise, .Net Framework is installed to provide the information in the form of the QR code, so the client can check and find the relevant information through PC and android-based smart device. Finally, the existing medical imaging information, bio-signal information and the health information of the patient are integrated over the result of executing the application service in order to provide a medical information service which is suitable in medical field.