• Convergence Security Journal
• /
• v.12 no.1
• /
• pp.49-54
• /
• 2012

Special applications designed for smart phone, so called "Apps" are rapidly emerging as unique and effective sources of environmental monitoring tools. Using the advantages of Information and Communication Technology (ICT), this paper propose an application that provides Indoor Gas Monitoring System. In this paper, use four wireless gas sensor modules to acquire sensors data wirelessly coupled with the advantages of existing portable smart device based on Android platform to display the real-time data from the sensor modules. Additionally, this paper adapts a simple gas classification algorithm to inform in-door Gas for users real-time based.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.321-323
• /
• 2012

스마트폰 사용의 보편화와 센서기술의 발달로 이를 응용하는 다양한 연구가 진행되고 있다. 특히 가속도, GPS, 조도, 방향센서 등의 센서들이 스마트폰에 부착되어 출시되고 있어서, 이를 이용한 상황인지, 행동인식 등의 관련 연구들이 활발하다. 하지만 다양한 클래스를 분류하면서 높은 인식률을 유지하는 것은 어려운 문제이다. 본 논문에서는 인식률 향상을 위해 계층적 구조의 순환 신경망을 이용하여 제스처를 인식한다. 스마트폰의 가속도 센서를 이용하여 사용자의 제스처 데이터를 수집하고 BLSTM(Bidirectional Long Short-Term Memory) 구조의 순환신경망을 계층적으로 사용하여, 20가지 사용자의 제스처와 비제스처를 분류한다. 약 24,850개의 시퀀스 데이터를 사용하여 실험한 결과, 기존 BLSTM은 평균 89.17%의 인식률을 기록한 반면 계층적 BLSTM은 평균 91.11%의 인식률을 나타내었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.233-234
• /
• 2010

본 논문에서는 스마트폰 기반의 차량 원격제어 시스템을 제안한다. 스마트폰에는 G센서가 탑재되어 모션을 제어하는데 사용되고 있으며, G센서는 X, Y, Z축으로 되어 있어 여러 방향과 속도의 동작들을 제어할 수 있으며, G센서는 Wi-Fi통신과 블루투스 모듈의 RS232통신 방식을 이용하여 여러 분야의 모바일 단말기에 응용 할 수 있다. 본 연구에서는 모바일 단말기에서 G센서 장착된 휴대용 단말기 iPhone을 사용하여 영상으로 차량원격제어시스템을 구현 및 개발하여 운전자들이 휴대용 단말기에서 실시간 영상으로 좀 더 편하게 차량을 원격제어, 관리할 수 있는 어플리케이션을 제안한다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.148-155
• /
• 2017

In this paper, we develop a new system to estimate the step count for a smartphone user. The system analyzes data obtained from the accelerometer, magnetic sensor, and gyroscope of an android smartphone to extract pattern information of human steps. We conduct an experiment and evaluation to confirm that the proposed system successfully estimates the number of steps with 96% accuracy when hand-held and 95.5% accuracy when in-pocket. In addition, we found that detection errors were caused by human motions such as touching the screen, shaking the device up and down, sitting up and sitting down, and waving the phone around.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.87-92
• /
• 2014

In this paper, we present a two-phase activity recognition system using smartphone's accelerometers. To consider the unique temporal pattern of accelerometer data for each activity, our system executes the decision-tree(DT) learning in the first phase, and then, in the second phase, executes the hidden Markov model(HMM) learning based on the sequences of classification results of the first phase classifier. Moreover, to build a robust recognizer for each activity, we trained our system using a large amount of data collected from different users, different positions and orientations of smartphone. Through experiments using 6720 examples collected for 6 different indoor activities, our system showed high performance based on its novel design.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.4
• /
• pp.1017-1023
• /
• 2015

The amount of smart phones has increased exponentially. Due to the periodic release of high-performance smart phones and upgraded operating system, new smart phones become out-dated over 1 or 2 years. In order to solve environmental constraints of these smart phones, virtualization technology using Thin-Client terminal has been developed. However, in the case of Virtual Machine(VM), the applications associated with sensors and a GPS device can not run because they are not included. In this paper, by implementing the device driver for Android running in a virtual machine in the x86-based systems, it is to provide Android virtualization capabilities such as using the latest smart phones in the virtual machine environment. It would like to propose a method that the virtual device driver receives sensors and GPS information from the old Android smart phones(Thin-Client) that actually work and run as if the real device exists.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.6
• /
• pp.1343-1349
• /
• 2014

Recently feature phones are being replaced by smartphones. Because smartphones have various sensors, there are many applications and research works that utilize them. Very few feature phones have GPS modules but all smartphones are equipped with a GPS sensor. One of the hot issues for smartphone research and development is point interest research. In this paper, we will develop an application which protects children using GPS and WiFi.. If a child gets out of the interest-area which is established by parents or guardian, our system sends them messages.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.12
• /
• pp.497-506
• /
• 2017

There have been previous researches about user authentication by analyzing the user's gait or behavior or action using the accelerometer sensor of smartphone, but there was a lack of user convenience to apply PIN entry. In this paper, we propose the technique for PIN entry without a touch on smartphone, the technique uses an accelerometer sensor and a vibration sensor built in the smartphone to enter the PIN. We conducted a usability experiment using the proposed technique and confirmed that the usability can be increased according to users become accustomed to this technique and that the users can enter PIN with 12.9 seconds and a probability of 100% on average. Also we conducted a security experiment and confirmed that an attack success rate is 0% when an attacker attacked the user using the recording attack and that it is more secure than the previous PIN entry technique. As a result, we was able to confirm that this technique can be used sufficiently.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.37-43
• /
• 2020

Smartphone-based localization has been widely studied in many different scenarios. But as far as we know, few work has addressed the problem of localization in underground public transportation systems, where GPS signal and wireless infrastructure are not always available. Knowing the location of a train is necessary to develop a useful service for subway passengers. And so, estimation of motion state and stop station by using sensors on a smartphone is being studied for subway passengers. This paper proposes a localization method that uses a barometer and a magnetic sensor on a smartphone. The method proposed in this paper first estimates whether the train runs or stops according to the change in air pressure and the strength of the magnetic field. The altitude value and the magnetic field value are then used to estimate the exact stop station of the train. We evaluated the proposed method using data from the Seoul's subway line 5. Compared with previous methods, the proposed method achieves higher accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.71-76
• /
• 2019

Research on indoor location tracking technology using smartphone is actively being carried out. Especially, the movement distance of the smartphone should be accurately measured and the movement route of the user should be displayed on the map. Location tracking technology using sensors mounted on smart phones has been used for a long time, but accuracy is not good enough to measure the moving distance of the user using only the sensor. Therefore, when the user moves the smartphone in a certain posture, it must research and develop an appropriate algorithm to measure the distance accurately. In this paper, we propose a method to reduce moving distance estimation error by removing user 's foot shape by limiting the screen of smartphone in pyramid - based optical flow estimation method.