• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.57-64
• /
• 2021

In this paper, we propose a device that can control the primary control surface of an aircraft by recognizing speech commands. The speech command consists of 19 commands, and a learning model is constructed based on a total of 2,500 datasets. The training model is composed of a CNN model using the Sequential library of the TensorFlow-based Keras model, and the speech file used for training uses the MFCC algorithm to extract features. The learning model consists of two convolution layers for feature recognition and Fully Connected Layer for classification consists of two dense layers. The accuracy of the validation dataset was 98.4%, and the performance evaluation of the test dataset showed an accuracy of 97.6%. In addition, it was confirmed that the operation was performed normally by designing and implementing a Raspberry Pi-based control device. In the future, it can be used as a virtual training environment in the field of voice recognition automatic flight and aviation maintenance.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.291-301
• /
• 2021

OPC UA at the control and field level does not provide enough performance to replace the field bus. The OPC Foundation aims for a real-time and connection-less mechanism, and has added the OPC UA publish-subscribe model, a new specification that supports broker functions such as MQTT and AMQP, as the OPC UA Part 14 standard. This paper is about a gateway for interoperability between OPC UA publisher with the addition of OPC UA Part14 standard and DDS subscribers. Raspberry Pi 4 is used for the gateway proposed in this paper, and OpenDDS, an open source, is used for DDS. OPC UA publish-subscribe module used A-Open62541 publish-subscribe module, which additionally implements functions not provided by the corresponding source based on Open62541 publish-subscribe open source.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.546-549
• /
• 2022

In recent years, to prevent the increase in accidents at industrial sites, various innovative technologies from the 4th industrial era have been incorporated into the construction administration to promote the advancement of safety management. As a result, smart safety management systems using intelligent monitoring that prevent and manage risks in industrial sites in real time are attracting attention. Smart safety management systems provide users with real-time, remote monitoring of factors such as noise, gas concentration fine dust concentration, building material quality, building tilt, and RFID-based worker access through sensors located everywhere. This paper presents a method for collecting and monitoring various data for smart safety management systems via Zigbee communication using Raspberry Pi.

• Journal of Korea Entertainment Industry Association
• /
• v.10 no.4
• /
• pp.303-310
• /
• 2016

Due to population explosion and develop of the industry, expressways, national roads and railways has been developed a lot. But it increased the disconnection of the ecosystem. The phenomenon of wild animals' habitat simplification has been increased. The damage appeared in succession because of the harmful wild animal. Our country is making efforts relief of some affected farming household's financial compensation. But the affected populations can't sleep at night or they are suffering in their basic life because of this kind of night patrol. This research is based on the study of wild animal's ecosystem and their habits, generate and regenerate supersonic waves and infrasound, prevent wild animal's approach to some extent and stop the approximation effectively, focusing on develop a quadcopter about discrete pulses system.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.107-116
• /
• 2024

In this paper, we analyze the performance of MicroVM when running AI applications on an edge computing environment and whether it can replace current container technology and traditional virtual machines. To achieve this, we set up Docker container, Firecracker MicroVM and KVM virtual machine environments on a Raspberry Pi 4 and executed representative AI applications in each environment. We analyze the inference time, total CPU usage and trends over time and file I/O performance on each environment. The results show that there is no significant performance difference between MicroVM and container when running AI applications. Moreover, on average, a stable inference time over multiple trials was observed on MicroVM. Therefore, we can confirm that executing AI applications using MicroVM instead of container or heavy-weight virtual machine is suitable for an edge computing.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.331-338
• /
• 2016

In this paper, we propose a system for transmitting army hand signals using motion sensors. The proposed system consists of a squad commander device, squad member devices, and a server. The squad command device and squad member device have been implemented using a micro arduino, an accelerometer sensor, and a gyroscope sensor, and the server has been implemented using a Rasberry Pi 3. Because the devices are made in the form of band, they are lightweight and portable. The proposed system can transmit the hand signals through vibration in conditions of poor visibility. We have designed and implemented the squad member device to be able to recognize four military hand signals. Through experiments, the proposed system have shown 88.82% of correct recognition. In conclusion, we expect to increase effectiveness of army operations and survival rate of soldiers.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.576-582
• /
• 2016

Currently, every person possesses a smart phone due to the development of the IT industry. However, crosswalk pedestrian accidents have been sharply increasing due to smart phone use. If a traffic light can recognize smart phones when a smart-phone user approaches and arrives at a given sign, many accidents could be reduced by using beacon signals. Before the era of smart phones, the accident rate involving cell phone use was relatively low. Nevertheless, when considering the development of IT equipment that produces a threat to human life, government cannot regulate smart phone use outside. The purpose of this paper is to indirectly warn a smart phone user in order to reduce the accident rates.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.413-416
• /
• 2017

The development of the internet, which is due to the advent of the fourth industrial revolution, has been slowly affecting our lives. Based on this trend, various products have recently emerged, and have yet to be developed in the context of identifying the dangers of infant babies. Increasingly, children are experiencing problems with detecting and responding to children's lives because of their daily living noise and housekeeping activities. This project attempts to develop a raspberry pie and an audiovisual sensor module to avoid the risk of preventing unwanted behavior from tripping the child's sudden behavior in everyday life. Further, it was designed to provide convenience to the guardian's convenience by implementing the smartphone app with the Wifi signal.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.117-126
• /
• 2019

The data generated in the IoT environment is very diverse. Especially, the development of the fourth industrial revolution has made it possible to increase the number of fixed and unstructured data generated in manufacturing facilities such as Smart Factory. With Big Data related solutions, it is possible to collect, store, process, analyze and visualize various large volumes of data quickly and accurately. Therefore, in this paper, we will directly generate data using Raspberry Pi used in IoT environment, and analyze using various Big Data solutions. Collected by using an Sqoop solution collected and stored in the database to the HDFS, and the process is to process the data by using the solutions available Hive parallel processing is associated with Hadoop. Finally, the analysis and visualization of the processed data via the R programming will be used universally to end verification.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.67-73
• /
• 2018

There are many types of power facilities such as transformers, switches, and energy storage devices in the micro grid environment. However, with the development of IoT technology, opportunities to acquire sensor information such as temperature, pressure, and humidity are provided. In the existing micro grid environment, the communication protocols such as MMS transport protocol in IEC 61850 standard is applied in accordance with the integrated operation between the power facilities and the platform. Therefore, to accommodate IoT data, a gateway technology that can link IoT data to a data collection device (FEP) based on IEC 61850 is required. In this paper, we propose IEC 61850 based IoT gateway platform prototype for microgrid operating system linkage. The gateway platform consists of an IoT protocol interface module (MQTT, CoAP, AMQP) and database, IEC 61850 server. For databases, We used open source based NoSQL databases, Hbase and MongoDB, to store JSON data. We verified the interoperability between the IoT protocol and the IEC 61850 protocol using Sisco's MMS EASY Lite.