• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.212-220
• /
• 2024

A recently the advancement of society, AI technology has made significant strides, especially in the fields of computer vision and voice recognition. This study introduces a system that leverages these technologies to recognize users through a camera and relay commands within a vehicle based on voice commands. The system uses the YOLO (You Only Look Once) machine learning algorithm, widely used for object and entity recognition, to identify specific users. For voice command recognition, a machine learning model based on spectrogram voice analysis is employed to identify specific commands. This design aims to enhance security and convenience by preventing unauthorized access to vehicles and IoT devices by anyone other than registered users. We converts camera input data into YOLO system inputs to determine if it is a person, Additionally, it collects voice data through a microphone embedded in the device or computer, converting it into time-domain spectrogram data to be used as input for the voice recognition machine learning system. The input camera image data and voice data undergo inference tasks through pre-trained models, enabling the recognition of simple commands within a limited space based on the inference results. This study demonstrates the feasibility of constructing a device management system within a confined space that enhances security and user convenience through a simple real-time system model. Finally our work aims to provide practical solutions in various application fields, such as smart homes and autonomous vehicles.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.465-470
• /
• 2017

This paper designs and implements a smart garden system using probabilistic filter algorithm using SLAM that can be used in apartment or veranda. To do this, we used Arduino and environtal sensors, which are open hardware controllers, and designed to control and observe automatic water supply, lighting, and growth monitoring with three wireless systems (Bluetooth, Ethernet, WiFi). This system has been developed to make it possible to use it in an indoor space such as an apartment, rather than a large-scale cultivation system such as a conventional plant factory which has already been widely used. The developed system collects environmental data by using soil sensor, illuminance sensor, humidity sensor and temperature sensor as well as control through smartphone app, analyzes the collected data, and controls water pump, LED lamp, air ventilation fan and so on. As a wireless remote control method, we implemented Bluetooth, Ethernet and WiFi. Finally, it is designed for users to enable remote control and monitoring when the user is not in the house.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.23-28
• /
• 2018

In this work, we developed a platform that can monitor status and manage events of factory workplaces by providing events and data collected from various types of multi-touch technology based sensors installed in the workplace. By using the image recognition technology, faces of the people in the factory workplace are recognized and the customized contents for each worker are provided, and security of contents is enhanced by the authenticating an individual worker through face recognition. Contents control function through gesture recognition is constructed, so that workers can easily search documents. Also, it is possible to provide contents for workers by implementing face recognition function in mobile devices. The result of this work can be used to improve workplace safety, convenience of workers, contents security and can be utilized as a base technology for future smart factory construction.

• Journal of the Korea Convergence Society
• /
• v.9 no.7
• /
• pp.63-68
• /
• 2018

Research on smart farms centering on greenhouse cultivation is actively under way due to the decrease in agriculture population and aging, but in the case of vegetables such as vegetables, outdoor cultivation is 70%. Therefore, there is a need to improve productivity and prevent soil contamination by automating, cultivating, and intelligentizing the outdoor cultivation of agriculture crops. In this paper, we show the case of establishing a outdoor production system using the Internet of things and define the environmental variables in the outdoor production system. By measuring soil temperature, water content, electrical conductivity and acidity through sensors, LoRa communication module transmits the information to the outdoor production system. The outdoor production system controls the amount of fertilizer and the volume of water based on this sensor data. We have developed a system that manages a wide range of crops using LoRa technology, which is a suitable communication method for cultivating crops, and manages production volume and sales performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.373-378
• /
• 2017

While on-line shopping markets are growing, consumer's procurement processes are being confused regardless of on or off line market and, smart consumers who want intelligent tailored services have emerged. Depending on the changeable pattern of consumer, most of related companies provide various Omni channel and O2O service. However, reactions of the fashion companies are tend to be late. Recently, the IoT environment has changed to standards-based open platform and it requires a variety of intelligent services depending on the type of environment and objects. This thesis proposes fashion O2O system using smart fitting display that is adaptable to fashion companies. This proposed system provides fitting information which is performed on off-line by users after constructing the database, it also support the works as on-line status, thus, it makes users' procurements to maintain continuously. For the more, customer oriented intelligent fitting service would be expected by the information connection with the shop and delivery systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.10
• /
• pp.1256-1262
• /
• 2016

As the population of camping is increased in campsites and auto camp sites, the electrical equipment can safely supply electricity to users in a variety of electricity bill policy is required in the campsite. In this paper, we develop the vending machine for electricity that can control the outdoor electrical outlet from the management server using the Z-Wave WPAN and android mobile application. The developed vending machine for electricity consists of the management server, the controller, the outdoor outlet box, and the mobile application. The management server provides reservation and electricity bill payment to users. The management server controls the electrical outlet box through the controller to safely supply electricity to users. The controller that is a relay device between the management server and the switch controls switches based on Z-Wave mesh network. Outdoor electrical outlet box has 2 meter switches. We receive the relevant authorization to provide commercial electricity services using the outdoor electrical outlet box in the campsite.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.47-53
• /
• 2019

Safety accidents at industrial sites can occur anytime, anywhere. Recently, research on the industrial safety management system based on the IoT has been actively conducted. However, most of the studies are studies of actions after safety accidents or simply monitoring. In this paper, the safety equipment was introduced before safety accidents occurred, and the subjects could be managed not only by workers but also by visitors. Also, it implements a system to prevent the accident by detecting the user's motion and situation periodically before a safety accident occurs. The implemented system is a system that attaches the device for safety management to the hard hat and can identify the safety situation by using the Bluetooth beacon device attached to the user's smartphone and the industrial site.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.53-56
• /
• 2019

본 논문에서는 화력을 이용하는 대형 파워 플랜트 설비의 미세먼지 발생량을 저감시키고 능동적으로 제어 할 수 있는 효율적인 시스템을 제안한다. 이 시스템은 기존의 고정형으로 설계된 집진기 방식의 고정부하량 한계점과 극복하고 초미세먼지 PM2.5, 미세먼지 PM10의 발생량에 따라 IoT센서 감지에 의해 지능형 알고리즘으로 효율적으로 저감 제어 처리량을 극대화하고, 미세먼지 발생량을 최소화한다. 또한 이 시스템의 차별성은 기존의 집진기에서 잡혀지지 않는 초미세먼지를 새로운 형태의 물질인 FAA(Fine-dust Adsorption Agent)를 통해 연료 연소 시 발생되는 초미세먼지 미세입자 자체를 크게 만들어 기존 설비 집진기 필터에 포집되게 하는 혁신적인 방식이다. 이번 연구를 통해 350도~1000도 열원에서 작용할 수 있는 화학물질 FAA 용액(Agent)을 개발 하였으며 지능형 AI 분사장치를 통해 연료에 첨가되어 연소 시 미세먼지를 20배~50배까지 볼륨을 확대시켜 기존 집진필터에 포집될 수 있게 동작된다. 이때, 기존 설계된 집진기의 한계(부하)용량에 상관없이 미세먼지 발생량을 상황인식 반응형 알고리즘(AI제어) 통해 분사량을 능동적으로 조절하여 미세먼지 발생량을 저감하는 진보적 혁신성을 지닌다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.891-892
• /
• 2016

Recent research has become a smart home for operating the joining operation of the relationships between the device progress. However, Existing systems, there is a problem that the efficiency of the work can be degrade by the interference occurs when the operation of the other device, and triggered if the device is operating. In this paper, we designed a priority automatically set algorithm according to a user selection device to solve this problem. The user selects the device used by the application and by comparing between devices, select whether or not to set the priority of the tasks in. This allows the user can configure the working environment of only the desired device, and less chance of interference from other devices that are not selected during the work in progress can expect a more efficient productivity.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.381-393
• /
• 2019

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.