• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.143-153
• /
• 2011

The goal of Ubiquitous Sensor Network(USN) environments is to provide users high quality services based on a variety of sensors. In this environment, sensor devices, sensor nodes and sensor networks are heterogeneous and have various characteristics. Therefore it is important for interoperability to define a metadata for describing USN resources. The OGC(Open Geospatial Consortium) proposes SensorML(Sensor Model Language) as a standard language for modeling sensors. However, SensorML provides a framework for describing a processing model among sensors rather than describing information of sensors. Therefore, to describe a USN metadata is not main purposes of SensorML. This paper defines a USN metadata which describes information about sensor device, sensor node, and sensor network. Also the paper proposes a method for efficiently storing and searching the USN metadata and implements a USN metadata management system based on our method. We show that our metadata management system is reasonable for managing the USN metadata through performance evaluation. Our USN metadata keeps the interoperability in USN environments because the metadata is designed on SensorML. The USN metadata management system can be used directly for a USN middleware or USN application.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.247-249
• /
• 2014

Ubiquitous Sensor Network (USN) environments, sensors and sensor nodes, and coming from heterogeneous sensor networks consist of one another, the characteristics of each component are also very diverse. Thus the sensor and the sensor nodes to interoperability between metadata for a single definition, management is very important. For this, the standard language for modeling sensor SensorML (Sensor Model Language) has. In this paper, sensor devices, sensor nodes and sensor networks for information technology in the application stage XMDR-DAI -based metadata to define the USN. The proposed XMDR-DAI USN based store and retrieve metadata for a method for effectively agent technology. Metadata of the proposed sensor is based SensorML USN environment by maintaining interoperability 50-200 USN middleware or a metadata management system for managing metadata in applications can be utilized directly.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.768-771
• /
• 2006

In WSN(Wireless Sensor Network) environment, a large amount of sensors, which are small and heterogeneous, generates data stream successively in physical space. These sensors are composed of measured data and metadata. Metadata includes various features such as location, sampling time, measurement unit, and their types. Until now, wireless sensors have been managed with individual specification, not the explicit standardization of metadata, so it is difficult to collect and communicate between heterogeneous sensors. To solve this problem, OGC(Open Geospatial Consortium) has proposed a SensorML(Sensor Model Language) which can manage metadata of heterogeneous sensors with unique format. In this paper, we introduce a metadata model using SensorML specification to manage various sensors, which are distributed in a wide scope. In addition, we implement the metadata management module applied to the sensor data stream management system. We provide many functions, namely generating metadata file, registering and storing them according to definition of SensorML.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.96-103
• /
• 2022

In this paper, we define EMRA-based USN metadata to describe sensor device, sensor node, and sensor network information at the application level. And the proposed method for effectively storing and retrieving USN metadata based on EMRA uses agent technology. As the sensor metadata proposed in this paper is based on SensorML, interoperability can be maintained in the USN environment, and the metadata management system can be directly utilized for metadata management in USN middleware or applications.

• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.1-9
• /
• 2021

This mini review summarizes some of the recent advances in machine-learning (ML)-driven chemical and biological sensors. Specific focus is on field-effect-transistor (FET)-based sensors with a description of their structures and detection mechanisms. Key ML techniques are briefly reviewed for an audience not familiar with the basic principles. We mainly discuss two aspects: (1) data analysis based on ML and (2) ML applied to sensor design. In conclusion, the challenges and opportunities for the advancement of ML-based sensors are briefly considered.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.705-707
• /
• 2012

여러 형태의 재난, 방범, 사고로부터 사회의 가장 기본 조직인 가정의 안전을 보호하기위해 가정 내 홈 안전센서를 설치하여 모니터링하는 등의 안전서비스가 매우 중요해지고 있다. 또한 핵가족화의 확산으로 가정의 개념이 분산화됨에 따라 개방형 방식으로 이를 관리할 수 있는 방식인 OGC의 SWE 표준에 기반한 홈 안전서비스를 위한 SensorML를 설계한다.

• Journal of Photoscience
• /
• v.12 no.3
• /
• pp.137-141
• /
• 2005

The chemiluminescence reaction of lophine with $H_2O_2$ in alkaline solution has been investigated for use in determination of $Cu^{2+}$ ions. The observed chemiluminescence intensity is found to be a function of the concentration of $Cu^{2+}$. Under the optimum reagent concentrations such as $4{\times}10^{-4}M$ lophine, 0.8 M KOH, 0.2M $H_2O_2,{\lambda}_{em}$, 533nm, the linear range and the detection limit were found to be 0.048ug/ml-48.32ug/ml (R=0.99897) and 0.005ulg/ml respectively. Relative standard deviation for five determinations of 24.16ug/ml $Cu^{2+}$ is 2.35%. The interference from other species was investigated. The proposed method was applied to the determination of $Cu^{2+}$ in different water samples.

• Journal of Sensor Science and Technology
• /
• v.17 no.3
• /
• pp.195-202
• /
• 2008

A biosensor based on the measurement of capacitance changes has been designed and fabricated for simple and realtime detection of bacteria. Compared to an impedance measurement technique, the capacitance measurement can make additional measurement circuits simpler, which improves a compatability for integration between the sensor and circuit. The fabricated sensor was characterized by detecting Escherichia coli(E. coli). The capacitance changes measured by the sensor were proportional to E. coli cell density, and the proposed sensor could detect $1{\times}10^6$ cfu/ml E. coli at least. The real-time detection was verified by measuring the capacitance every 20 minutes. After 7 hours of E. coli growth experiment, the capacitance of the sensor in the micro volume well with $4.5{\times}10^5$ cfu/ml of initial E. coli density increased by 20 pF, and that in another wells with $1.5{\times}10^6$ cfu/ml and $8.5{\times}10^7$ cfu/ml initial E. coli density increased by 56 pF and 71 pF, respectively. The proposed sensor has a possibility of the real-time detection for bacterial growth, and can detect E. coli cells with $1.8{\times}10^5$ cfu in nutrient broth in 5 hours.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.5
• /
• pp.487-493
• /
• 2011

Alpha fetoprotein(AFP), which is serological marker for hepatocellular carcinoma, was quantitatively measured by its normal concentration, 10 ng/ml, with a label-free piezoelectric microcantilever mass sensor. The principle of detection is based on changes in the resonant frequency of the piezoelectric microcantilever before and after target molecules are attached to it, and its resonant frequency is measured electrically using a conductance spectrum. The resonant frequency of the developed sensor is approximately 1.34 MHz and the mass sensitivity is approximately 175 Hz/pg. The sensor has high reliability as mass sensor by reducing the effect of surface stress on resonant frequency due to attached proteins. 'Dip and dry' technique was used to react the sensor with reagents for immobilizing AFP antibody on the sensor and detecting AFP antigen. The measured mass of the detected AFP antigen was 6.02 pg at the concentration of 10 ng/ml, and 10.67 pg at 50 ng/ml when the immunoreaction time was 10 min.