• 제어로봇시스템학회논문지
• /
• 제21권6호
• /
• pp.565-570
• /
• 2015

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.

• 한국통신학회논문지
• /
• 제38C권9호
• /
• pp.797-801
• /
• 2013

Visible light communication (VLC) is a rapidly growing area of research and applications, due to the potential and predicted high efficiency of bandwidth. One of the key challenges in VLC technology is the choice of devices which are going to be deployed VLC features. Smartphone rationally uses the most widely deployed visible light sensor i.e. image sensor in camera, which could be used to receive the intensity modulated data. Image sensor based VLC system would be the most deployable scenario but initially the capacity was not much attractive compared with photodetector based VLC system. Here, the spatial multiplexing is proposed in MIMO based VLC system to increase the system capacity by utilizing the property of spatial separation of optical light sources in smartphone's camera module. The active pixels of imaging plane act as the multiple receivers which could be able to use on MIMO spatial multiplexing to enhance the system performance.

• International Journal of Advanced Culture Technology
• /
• 제5권2호
• /
• pp.98-105
• /
• 2017

Smartphones are fast growing in the IT market and are the most influential devices in our daily life. Smartphones are being studied for their use in body sensor networks with excellent processing power and wireless communication technology. In this paper, we propose a coordinator design that provides data collection, classification, and display using based on Android-smartphone in multiple sensor nodes. The coordinator collects data of sensor nodes that measure biological patterns using wireless communication technologies such as Bluetooth and NFC. The coordinator constructs a network using a multiple-level scheduling algorithm for efficient data collection at multiple sensor nodes. Also, to support different protocols between heterogeneous sensors, a data sheet recording wireless communication protocol information is used. The designed coordinator used Arduino to test the performance of multiple sensor node environments.

• 센서학회지
• /
• 제27권1호
• /
• pp.6-12
• /
• 2018

In this paper, a 32-variable pulse position modulation (32-VPPM) scheme is proposed to support a red-green-blue light-emitting-diode (RGB-LED)-based optical camera communication (OCC) system. Our proposed modulation scheme is designed to enhance the OCC data transmission rate, which is targeted for the wearable biomedical data monitoring system. The OCC technology has been utilized as an alternative solution to the radio frequency (RF) wireless system for long-term self-healthcare monitoring. Different biomedical signals, such as electrocardiograms, photoplethysmograms, and respiration signals are being monitored and transmitted wirelessly from the wearable biomedical device to the smartphone receiver. A common 30 frames per second (fps) smartphone camera with a CMOS image sensor is used to record a transmitted optical signal. Moreover, the overall proposed system architecture, modulation scheme, and data demodulation are discussed in this paper. The experimental result shows that the proposed system is able to achieve > 9 kbps using only a common smartphone camera receiver.

• 한국안전학회지
• /
• 제30권3호
• /
• pp.93-99
• /
• 2015

Economic burden of work-related musculoskeletal disorder(WMDs) is increasing. Known causes of WMDs include improper posture, repetition, load, and temperature of workplace. Among them, improper postures play an important role. A smart sensor called SensorTag is employed to estimate the trunk postures including flexion-extension, lateral bend, and the trunk rotational speeds. Measuring gravitational acceleration vector in the smart sensor along the tri-orthogonal axes offers an orientation of the object with the smart sensor attached to. The smart sensor is light in weight and has small form factor, making it an ideal wearable sensor for body posture measurement. Measured data from the smart senor is wirelessly transferred for analysis to a smartphone which has enough computing power, data storage and internet-connectivity, removing need for additional hardware for data post-processing. Based on the estimated body postures, WMDs risks can be conviently gauged by using existing WMDs risk assesment methods such as OWAS, RULA, REBA, etc.

• 디지털융복합연구
• /
• 제12권1호
• /
• pp.333-338
• /
• 2014

Zigbee는 무선 센서 네트워크 환경에 최적화된 무선 통신 기술 중의 하나이다. 무선 센서 네트워크에서 게이트웨이는 센서 노드들을 제어하고 송수신된 데이터를 전송하는데 사용된다. 하지만 고정된 형태의 게이트웨이는 무선 센서 네트워크의 유연성을 제한한다. 고성능 프로세서가 탐재된 스마트폰과 안드로이드 OS를 이용하면 쉽게 스마트폰을 모바일 게이트웨이로 사용할 수 있다. 이에 본 논문에서는 안드로이드 스마트폰을 이용한 모바일 게이트웨이를 제안하였다. 제안한 시스템에서 Zigbee 통신 모듈은 USB 포트를 이용하여 스마트폰과 연결된다. 또한 모바일 게이트웨이를 위한 안드로이드 어플리케이션도 구현하였다.

• 한국인터넷방송통신학회논문지
• /
• 제10권4호
• /
• pp.17-22
• /
• 2010

최근 언제 어디서나 다양한 서비스를 제공받을 수 있는 유비쿼터스 환경이 많은 분야에서 개발되고 있으며 u-Healthcare의 관심이 급속도로 증가하고 있다. 본 논문에서는 기존의 유비쿼터스 센서네트워크 환경에서 ECG 센서와 Zigbee 통신모듈로 BAN(Body Area Network)를 이용하여 사용자의 생체신호를 측정하였다, 측정된 생체신호를 3G(WCDMA) 통신을 이용하여 전문가나 의사가 모니터링 할 수 있는 시스템을 구현하였다. 또한, 환자에게 응급상황 발생시 스마트폰의 GPS모듈을 이용한 위치 검색까지 설계하였다. 센서 모듈간 데이터 필드를 정의하고 설계된 시스템 구조를 기반으로, 최근 스마트폰 중에 각광받고 있는 iPhone 플랫폼에서 구현하였다.

• 한국인터넷방송통신학회논문지
• /
• 제14권4호
• /
• pp.141-147
• /
• 2014

최근 스마트 폰 주요 기능의 급속한 발전과 더불어 스마트 폰과 연계된 많은 응용들이 속속 개발되고 있으며, 다양한 관련 기술과의 융합을 통해 획기적인 모바일 응용들이 개발되어 빠르게 확산되고 있는 실정이다. 본 논문에서는 이러한 스마트 폰의 다양한 기능들을 효과적으로 활용할 수 있도록 주변의 센서와 같은 장치들과 연동한 스마트한 모바일 응용의 설계를 제안한다. 본 논문에서 제안한 모바일 응용은 스마트 폰의 블루투스 모듈을 이용하여 주변의 다양한 상황정보 센서들과 일시적인 애드 혹 망을 형성하고 사용자의 생체 상황정보를 실시간으로 수집하여, 사용자가 효과적인 다이어트를 수행하는데 반영하여 건강한 다이어트를 수행할 수 있도록 하는 스마트 폰을 위한 센서 기반 건강 다이어트 어플을 설계하고 구현하였다.

• 한국통신학회논문지
• /
• 제39C권9호
• /
• pp.811-819
• /
• 2014

상황 인식은 유비쿼터스컴퓨팅 환경에 대한 진화를 변화시켰고 무선 센서네트워크 기술은 많은 응용기기에 대한 새로운 방법을 제시하였다. 특히, 행동 인식은 사람의 응용서비스를 제공하는데 있어 특정 사용자의 상황을 인식하는 핵심 요소로 의학, 취미, 군사 분야에서 폭넓은 응용분야를 갖고 있고 사용반경의 확대에서도 효율과 정확도를 높이는 방법에 크게 기여한다. 스마트폰 센서로부터 나오는 데이터로부터 프레임이 512인셈플 데이터를 얻어, 프레임간50%의 오버랩을 갖도록 하고 Machine Learning Algorithm 인 WEKA Experimenter (University of Waikato, Version 3.6.10)을 써서 데이더로부터 시간영역 특징값을 추출함으로써 행동 인식에 대한 99.33%의 정확도를 얻을 수 있었다. 또한, WEKA Experimenter의 사용기법인 C4.5 Decision Tree과 다른 방법인 BN, NB, SMO or Logistic Regression간의 비교실험을 하였다.

• Journal of Multimedia Information System
• /
• 제2권2호
• /
• pp.233-240
• /
• 2015

Mobile devices are becoming increasingly sophisticated and the latest generation of smartphones now incorporates many diverse and powerful sensors. These sensors include acceleration sensor, magnetic field sensor, light sensor, proximity sensor, gyroscope sensor, pressure sensor, rotation vector sensor, gravity sensor and orientation sensor. The availability of these sensors in mass-marketed communication devices creates exciting new opportunities for data mining and data mining applications. In this paper, we describe and evaluate a system that uses phone-based accelerometers to perform activity recognition, a task which involves identifying the physical activity that a user is performing. To implement our system, we collected labeled accelerometer data from 10 users as they performed daily activities such as "phone detached", "idle", "walking", "running", and "jumping", and then aggregated this time series data into examples that summarize the user activity 5-minute intervals. We then used the resulting training data to induce a predictive model for activity recognition. This work is significant because the activity recognition model permits us to gain useful knowledge about the habits of millions of users-just by having them carry cell phones in their pockets.