• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.93-99
• /
• 2019

In this paper, we propose a smart meter that uses GRU model, which is one of artificial neural networks, for the efficient energy management. We collected power consumption data that train GRU model through the proposed smart meter. The implemented smart meter has automatic power measurement and real-time observation function and load control function through power consumption prediction. We determined a reference value to control the load by using Root Mean Squared Error (RMS), which is one of performance evaluation indexes, with 20% margin. We confirmed that the smart meter with automatic load control increases the efficiency of energy management.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.203-208
• /
• 2021

At the manufacturing site, workers have been operating by inputting materials into the manufacturing process and leaving input records according to the work instructions, but product LOT tracking has been not possible due to many omissions. Recently, it is being carried out as a system to automatically input materials using RFID-Tag. In particular, the initial automatic recognition rate was good at 97 percent by automatically generating input information through RACK (TAG) ID and RACK input time analysis, but the automatic recognition rate continues to decrease due to multi-material RACK, TAG loss, and new product input issues. It is expected that it will contribute to increasing speed and yield (normal product ratio) in the overall production process by improving automatic recognition rate and real-time monitoring through the establishment of artificial intelligent smart factory datasets.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.595-602
• /
• 2021

Marine accidents are mostly caused by medium and small ships, and are continuously increasing. In this paper, we propose an architecture of the speech synthesis based automatic safety navigation support service providing system for small ships that equiped onboard systems compared with vessels. The main purpose of the system is to prevent marine accidents by providing synthesized voice safety messages to nearby ships. The safety navigation support service is operated by connecting GPS and AIS to synthesize voice safety messages, automatically broadcast through VHF. Therefore, we developed a data processing module, a staged risk analysis module, a voice synthesis safety message generation module, and a VHF broadcasting equipment control module, which are components of the system. In addition, we conducted laboratory-level and sea-trial demonstration tests using the developed the system, which verified usefulness of the proposed service.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.182-192
• /
• 2022

This study analyzed the effects of the all-in-one automatic fire shutter (hereinafter referred to as "all-in-one shutter") installed along the fire compartment in a five-story high school building on the evacuation time by using the Pathfinder simulation program. When the all-in-one shutter was added as a new variable, the evacuation time was delayed, indicating insufficient evacuation safety. The evacuation time exceeded the appropriate standard when the evacuation exit was designated to the students in the present state of being placed on the 2nd, 3rd, and 4th floors and the all-in-one shutter was activated. When students were placed on the 1st, 2nd and 3rd floors under the same conditions, the evacuation time was also greatly exceeded. However, when the width of the entrance was set to 130cm, the evacuation time was almost the same as when the all-in-one shutter was not installed. In high-rise school buildings, the bottleneck caused by all-in-one shutters is becoming a major factor in evacuation barriers. To ensure the evacuation safety of school buildings, it has been judged that evacuation education and training to predict the evacuation time required through the all-in-one shutter entrance and induce an evacuation procedure suitable for the standard evacuation time should be carried out in parallel. The implications of this study and suggestions for effective fire compartments and follow-up studies were discussed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.292-294
• /
• 2018

Recently, damage caused by natural disasters such as fire, earthquake, heavy rains and heavy snow is increasing. In addition, traffic accidents due to freezing, fog and fire in tunnels and bridges are frequently occurring. In such a disaster situation, it is very important to take prompt action by the person in charge of managing the facility and area.To this end, a disaster broadcasting system is used, but in the existing system, the broadcasting room and the speaker are connected by a wired connection. Also, the person in charge has to be in the broadcasting room to broadcast, which has a problem of delaying the time. In this paper, we design a disaster broadcasting system using LTE modem. The designed system enables a broadcasting person to make a call to a broadcasting system from anywhere using a cellular phone and a public telephone. Broadcasting via telephone is possible only with the telephone number pre-registered in the system and can be registered / deleted by the administrator. The registered telephone number, incoming voice file, and announcement voice for automatic broadcasting are stored in the system internal SD memory for convenient management. This disaster broadcasting system is expected to contribute to quick and convenient disaster broadcasting.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.8-14
• /
• 2020

Recently, there was an increasing demand for an integrated access control system which is capable of user recognition, door control, and facility operations control for smart buildings automation. The market available door lock access control solutions need to be improved from the current level security of door locks operations where security is compromised when a password or digital keys are exposed to the strangers. At present, the access control system solution providers focusing on developing an automatic access control system using (RF) based technologies like bluetooth, WiFi, etc. All the existing automatic door access control technologies required an additional hardware interface and always vulnerable security threads. This paper proposes the user identification and authentication solution for automatic door lock control operations using camera based visible light communication (VLC) technology. This proposed approach use the cameras installed in building facility, user smart devices and IoT open source controller based LED light sensors installed in buildings infrastructure. The building facility installed IoT LED light sensors transmit the authorized user and facility information color grid code and the smart device camera decode the user informations and verify with stored user information then indicate the authentication status to the user and send authentication acknowledgement to facility door lock integrated camera to control the door lock operations. The camera based VLC receiver uses the artificial intelligence (AI) methods to decode VLC data to improve the VLC performance. This paper implements the testbed model using IoT open-source based LED light sensor with CCTV camera and user smartphone devices. The experiment results are verified with custom made convolutional neural network (CNN) based AI techniques for VLC deciding method on smart devices and PC based CCTV monitoring solutions. The archived experiment results confirm that proposed door access control solution is effective and robust for automatic door access control.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.135-140
• /
• 2009

본 논문은 한국어 8 단모음을 인식하는 자동 독화 신경망 시스템을 구축한 것이다. 얼굴의 특정들은 휘도와 채도 성분으로 인하여 다양한 색 공간에서 다양한 표현 값을 갖는다. 이를 이용하여 각 표현 값들을 증폭하거나 축소, 대비시킴으로서 얼굴 특정들을 추출되게 하였다. 눈과 코, 안쪽 입의 외곽선, 이의 외곽선을 찾았고, 그 후 한국어 8모음 발화시 구분되게 변화는 값들을 파라미터로 설정하였다. 한국어 8모음을 발화하는 2400개의 자료를 모아 분석하고 이 분석을 바탕으로 신경망 시스템을 구축하여 실험하였다. 이 실험에 정상인 5명이 동원되었고, 사람들 사이에 있는 관찰 오차를 정규화를 통하여 수정하였다. 5명으로 분석하였고, 5명으로 인식 실험하여 좋은 결과를 얻었다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.19-24
• /
• 2017

In this paper, we propose an automatic segmentation method of left and right heart in computed tomography angiography (CTA) using separating energy function. First, we smooth the images by applying anisotropic diffusion filter to remove noise. Then, the volume of interest (VOI) is detected by using k-means clustering. Finally, we extract the left and right heart with separating energy function which we proposed to split the heart. We tested our method in ten CT images and they were obtained from a different patient. For the evaluation of the computational performance of the proposed method, we measured the total processing time. The average of total processing time, from first step to third step, was $14.39{\pm}1.17s$. We expect for our method to be used in cardiac diagnosis for cardiologist.

• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.19-24
• /
• 2018

Recently, people can create small content by themselves and it improved into a form that can be promoted. Also, as active small business owners increase, they produce the content for promotion by themselves without external professional help and they utilize it. This paper studies the method to make Mobile Apps, Mobile Web and homepage services available by automatically generating the mobile based mini content. The automated content creation system suggests the method that small business owners and groups can easily communicate with new people by bringing Single Page Application, hybrid mobile web app, N-Screen based content building, private cloud-based PaaS building technology, P2P network based file sharing and multimedia thread technologies together and creating the content.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.45-50
• /
• 2020

A Language model with neural networks commonly trained with likelihood loss. Such that the model can learn the sequence of human text. State-of-the-art results achieved in various language generation tasks, e.g., text summarization, dialogue response generation, and text generation, by utilizing the language model's next token output probabilities. Monotonous and boring outputs are a well-known problem of this model, yet only a few solutions proposed to address this problem. Several decoding techniques proposed to suppress repetitive tokens. Unlikelihood training approached this problem by penalizing candidate tokens probabilities if the tokens already seen in previous steps. While the method successfully showed a less repetitive generated token, the method has a large memory consumption because of the training need a big vocabulary size. We effectively reduced memory footprint by encoding words as sequences of subword units. Finally, we report competitive results with token level unlikelihood training in several automatic evaluations compared to the previous work.