• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.147-156
• /
• 2023

Efforts to employ smart home sensors to monitor the indoor activities of elderly single residents have been made to assess the feasibility of a safe and healthy lifestyle. However, the bathroom remains an area of blind spot. In this study, we have developed and evaluated a new edge computer device that can automatically detect water usage activities in the bathroom and record the activity log on a cloud server. Three kinds of sound as flushing, showering, and washing using wash basin generated during water usage were recorded and cut into 1-second scenes. These sound clips were then converted into a 2-dimensional image using MEL-spectrogram. Sound data augmentation techniques were adopted to obtain better learning effect from smaller number of data sets. These techniques, some of which are applied in time domain and others in frequency domain, increased the number of training data set by 30 times. A deep learning model, called CRNN, combining Convolutional Neural Network and Recurrent Neural Network was employed. The edge device was implemented using Raspberry Pi 4 and was equipped with a condenser microphone and amplifier to run the pre-trained model in real-time. The detected activities were recorded as text-based activity logs on a Firebase server. Performance was evaluated in two bathrooms for the three water usage activities, resulting in an accuracy of 96.1% and 88.2%, and F1 Score of 96.1% and 87.8%, respectively. Most of the classification errors were observed in the water sound from washing. In conclusion, this system demonstrates the potential for use in recording the activities as a lifelog of elderly single residents to a cloud server over the long-term.

• Journal of Internet Computing and Services
• /
• v.18 no.2
• /
• pp.21-30
• /
• 2017

IoT(Internet of Things) can enable networking and computing using any devices is rapidly proliferated. In the existing IoT environment, bottlenecks and service delays can occur because it processes data and provides services to users using central processing based on Cloud. For this reason, Edge Computing processes data directly in IoT nodes and networks to provide the services to the users has attracted attention. Also, numerous researchers have been attracted to intelligent service efficiently based on Edge Computing. In this paper, expert system-based context awareness scheme for Edge Computing in IoT environment is proposed. The proposed scheme can provide customized services to the users using context awareness and process data in real-time using the expert system based on efficient cooperations of resource limited IoT nodes. The context awareness services can be modified by the users according to the usage purpose. The three service modes in the security system based on smart home are used to test the proposed scheme and the stability of the proposed scheme is proven by a comparison of the resource consumptions of the servers between the proposed scheme and the PC-based expert system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.3
• /
• pp.46-55
• /
• 2012

Recently, the concept of PES(Personal Environment Service) is being widely discussed on various standardization organizations such as ITU-R, ETSI, 3GPP, TTA and etc. The purpose of PES is to introduce the services which can dynamically, automatically and intelligently reconfigures the electronic, electrical, and mechanical equipment surrounding the user according to the user preferences included in a user's profile by using a smartphone embedding WPAN radio technologies such as bluetooth and WiFi. This research introduces an Android Platform-based PES system which consists of a PES app, PES devices and a PES server. A smartphone platform is Android 2.2(Froyo) version and 4 simulated PES devices were implemented by using Galaxy Tab. It has shown that the PES would be a killer application of M2M(Machine-to-Machine) or D2D(Device-to-Device) in the future and it would need to study how to update a user's profile based on analyzing user's behaviour for enhancing the PES user's satisfaction.

• The Journal of the Korea Contents Association
• /
• v.18 no.4
• /
• pp.305-313
• /
• 2018

With the explosive growth of smart phones and efficiency, the Android of an open mobile operating system is gradually increasing in the use and the availability. Android systems has proven its availability and stability in the mobile devices, the home appliances's operating systems, the IoT products, and the mechatronics. However, as the usability increases, the malicious code based on Android also increases exponentially. Unlike ordinary PCs, if malicious codes are infiltrated into mobile products, mobile devices can not be used as a lock and can be leaked a large number of personal contacts, and can be lead to unnecessary billing, and can be cause a huge loss of financial services. Therefore, we proposed a method to detect and delete malicious files in real time in order to solve this problem. In this paper, we also designed a method to detect and delete malicious codes in a more effective manner through the process of installing Android-based applications and signature-based malicious code detection method. The method we proposed and designed can effectively detect malicious code in a limited resource environment, such as mobile environments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.211-218
• /
• 2017

In this study, we implemented IoT Sensor Network using Mobius Platform and implemented four kinds of Z-wave sensors applicable to smart home service to verify its performance. The 12 common service functions (CSF) provided by Mobius enable application services including status monitoring of sensors to be implemented quickly. The standard service procedures and protocols have eliminated the design process of the system and shortened the meeting time for establishing protocol between application software developer, gateway developer and sensor developer, and discussion time for adjustment of opinion. We confirmed that the application service based on the implemented sensor network and the implementation of IoT sensor can shorten the development schedule, and confirmed that most of the products purchased in the market can be accommodated without change. We hope that such speediness and openness will be able to meet the demands of various services and contribute to expanding services and creating new markets.

• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.25-39
• /
• 2016

The drone is an unmanned aerial vehicle which has no human pilot. Drones can be classified into military drones, commercial drones, and personal drones by usage. Also, drones can be classified from large-sized to nano-sized drone by size and autonomous, remote controlled drone by control type. Especially, military drones can be classified into low-altitude drones, medium-altitude, and high-altitude drones by altitude. Recently, the drone industry is one of the fast growing industries in the world. As drone technologies have become more advanced and cost-effective, Korean government has set its goal to become a top-level country in drone business. However, the government's strict regulation for drone operations is one of the biggest hurdles for the development of the related technologies in Korea and other countries. For example, critical problems for drone delivery can be classified into technical issues and institutional issues. Technical issues include durability, conditional awareness, grasp and release mechanisms, collision avoidance systems, drone operating system. Institutional issues include pilot and operator licensing, privacy rules, noise guidelines, security rules, education for drone police. This study analyzes the trends of the drone industry from the viewpoint of technology and regulation. Also, we define the business areas of drone utilization. Especially, the drone business types or models for public sector are proposed. Drone services or functions promoting public interests need to be aligned with the business reference model of Korean government. To define ten types of drone uses for public sector, we combine the business types of government with the future uses of drones that are proposed by futurists and business analysts. Future uses of drones can be divided into three sectors or services. First, drone services for public or military sectors include early warning systems, emergency services, news reporting, police drones, library drones, healthcare drones, travel drones. Second, drone services for commercial or industrial services include parcel delivery drones, gaming drones, sporting drones, farming and agriculture drones, ranching drones, robotic arm drones. Third, drone services for household sector include smart home drones.

• The KIPS Transactions:PartA
• /
• v.13A no.4 s.101
• /
• pp.351-362
• /
• 2006

This paper proposes an adaptive inter-agent communication protocol to considerably reduce the amount of agent location information maintained by each service node and the message delivery time while avoiding the dependency of the home node of a mobile agent. To satisfy this goal, the protocol enables each mobile agent to autonomously leave its location information only on some few of its visiting nodes. Also, it may significantly reduce the agent cache updating frequency of each service node by keeping the identifier of the location manager of each agent in the smart agent location cache of the node. Simulation results show that the proposed protocol reduces about $76%{\sim}80%$ of message delivery overhead and about $76%{\sim}79%$ of the amount of agent location information each service node should maintain compared with the traditional one.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1256-1258
• /
• 2012

본 논문에서는 스마트 일렉트로 에코 시스템(Smart Electro-Eco System)의 일환으로 상황인지기반 가전 제품 원격 제어 및 관리 솔루션에 대해 기술한다. 본 솔루션 중 각 세대에 배치되는 홈 관리시스템은 n개의 특정기업 가전제품군과 원격 제어 애플리케이션, 홈 서버 시스템으로 구성된다. 또한 이러한 홈서버 시스템 m개로부터 데이터를 전송받아 분석 처리하는 빅데이터 서버 시스템이 있다. 홈 관리시스템에서는 가전제품에 부착된 센서의 센싱 데이터를 홈 서버 시스템으로 전송한다. 홈 서버 시스템에서는 실시간 가전제품 정보를 모니터링 및 원격 제어를 하고 설정된 상황이 인식되면 자동 제어 및 알림을 준다. 원격 제어 애플리케이션과 홈 서버 시스템의 통신으로 스마트 폰을 통해 가전제품 정보 및 원격 제어, NFC Tag를 이용한 원터치 제어를 할 수 있다. 빅데이터 서버 시스템에서는 대량의 데이터를 분석 및 통계를 내어 지역별, 시간대별 전류 소모량, 판매 실적 등을 측정하여 다음 버전에 나올 제품을 실제 데이터 통계로 인해 개선할 수 있다. 본 논문에서 기술하는 솔루션을 통하여 장소, 시간에 관계없이 홈을 스마트하게 관리할 수 있으며 가전제품 사용관련 빅데이터 처리를 통해 에너지의 효용성을 높일 수 있다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2021

In this paper, we propose a non-intrusive load monitoring(NILM) system which can find the power of each home appliance from the aggregated total power as the activation in the trading market of the distributed resource and the increasing importance of energy management. We transform the amount of appliances' power into a power on-off state by preprocessing. We use LSTM as a model for predicting states based on these data. Accuracy is measured by comparing predicted states with real ones after postprocessing. In this paper, the accuracy is measured with the different number of electronic products, data postprocessing method, and Time step size. When the number of electronic products is 6, the data postprocessing method using the Round function is used, and Time step size is set to 6, the maximum accuracy can be obtained.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.824-827
• /
• 2011

Needs for Smart Grid development are increasing all over the world as a solution to its problem according to depletion of energy resources, climatic and environmental rapidly change and growing demand for electrical power. Especially decentralized power is attracting world's attention. In this mood a new era for a unit scale of decentralized power environment is on its way in building. However there is a problem to have to be solved in the uniformity of power quality because the amount of power generated from renewable energy resources such as wind power and solar light is very sensitive to climate fluctuation. And thus this paper tries to suggest an energy management algorithm on basis of real time monitoring for meteorological data. The proposed EMS model embodies the method for predicting the power generation by monitoring and analyzing the climatic data and controling the efficient power distribution between the renewable energy and the existing power. The ultimate goal of this paper is to provide the technological basis for achieving zero-energy house.