• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.457-461
• /
• 2007

In many applications, received signal strength indicator is used for location tracking and sensor nodes localization. For location finding, the distances between sensor nodes can be estimated by converting received signal's power into distance using path loss prediction model. Many researches have done the analysis of power-distance relationship for radio channel characterization. In indoor environment, the general conclusion is the non-linear variation of RSSI values as distance varied linearly. This has been one of the difficulties for indoor localization. This paper presents works on indoor RSSI characterization based on statistical methods to find the overall trend of RSSI variation at different places and times within the same room From experiments, it has been shown that the variation of RSSI values can be determined by both spatial and temporal factors. This two factors are directly indicated by the two main parameters of path loss prediction model. The results show that all sensor nodes which are located at different places share the same characterization value for the temporal parameter whereas different values for the spatial parameters. Using this relationship, the characterization for location estimation can be more efficient and accurate.

• Journal of Communications and Networks
• /
• v.16 no.4
• /
• pp.465-474
• /
• 2014

Wireless sensor network (WSN) is considered to be one of the most important research fields for ubiquitous healthcare (u-healthcare) applications. Healthcare systems combined with WSNs have only been introduced by several pioneering researchers. However, most researchers collect physiological data from medical nodes located at static locations and transmit them within a limited communication range between a base station and the medical nodes. In these healthcare systems, the network link can be easily broken owing to the movement of the object nodes. To overcome this issue, in this study, the fast link exchange minimum cost forwarding (FLE-MCF) routing protocol is proposed. This protocol allows real-time multi-hop communication in a healthcare system based on WSN. The protocol is designed for a multi-hop sensor network to rapidly restore the network link when it is broken. The performance of the proposed FLE-MCF protocol is compared with that of a modified minimum cost forwarding (MMCF) protocol. The FLE-MCF protocol shows a good packet delivery rate from/to a fast moving object in a WSN. The designed wearable platform utilizes an adaptive linear prediction filter to reduce the motion artifacts in the original electrocardiogram (ECG) signal. Two filter algorithms used for baseline drift removal are evaluated to check whether real-time execution is possible on our wearable platform. The experiment results shows that the ECG signal filtered by adaptive linear prediction filter recovers from the distorted ECG signal efficiently.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.21 no.4
• /
• pp.601-607
• /
• 2012

The magnetic abrasive polishing (MAP), for online monitoring with AE sensor attachment, was performed in this study. To predict the surface roughness after the magnetic abrasive polishing of NAK80, the signal data acquired from the AE sensor were analyzed. A dimensionless coefficient, which consisted of average of AErms and standard deviation of AE signal, was defined as a characteristic of the MAP and a prediction model was obtained using least square method. A neural network, which had multiple input parameters from AE signals and polishing conditions, was applied for predicting the surface roughness. As a result of this study, it was seen that there was very close correlation between the AE signal and the surface roughness in the MAP. And then on-line prediction of the surface roughness after the MAP of the NAK80 was possible by the developed prediction model.

• Journal of the Korean Solar Energy Society
• /
• v.37 no.2
• /
• pp.23-33
• /
• 2017

Accurate prediction of stochastic behavior of occupants is a well known problem for improving prediction performance of building energy use. Many researchers have been tried various sensors that have information on the status of occupant such as $CO_2$ sensor, infrared motion detector, RFID etc. to predict occupants, while others have been developed some algorithm to find occupancy probability with those sensors or some indirect monitoring data such as energy consumption in spaces. In this research, various sensor data and energy consumption data are utilized for decision tree algorithms (C4.5 & CART) for estimation of sub-hourly occupancy status. Although the experiment is limited by space (private room) and period (cooling season), the prediction result shows good agreement of above 95% accuracy when energy consumption data are used instead of measured $CO_2$ value. This result indicates potential of IoT data for awareness of indoor environmental status.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.7
• /
• pp.241-244
• /
• 2014

Wireless Sensor Network(WSN) has been attracting lots of interest in recent years for smart surveillance systems. WSN-based surveillance systems need to figure out the occurrence or existence of events or objects and to find out where the events have occurred or the objects are present. In our surveillance system, it is needed to give an alarm only when the detected object is human (not pets or rodents) for reducing false alarms and improving the system reliability. In this paper, we propose a height prediction mechanism to determine if the detected object is human using Heron's formula. Finally, we verify the performance of our proposed mechanism through various experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1398-1405
• /
• 2016

As wireless sensor networks become eligible as well as useful in several controled systems where surrounding environments are likely to be monitored, their stabilization become important research challenge. Generally, stabilization is mostly dependent on reliability of sensing value. To achieve such reliability in wireless sensor networks, the most of previous research work have tendency to deploy the same type of multiple sensor units on one node. However, these mechanisms lead to deployment problem by increasing cost of sensor node. Moreover, it may decrease reliability in the operation due to complex design. In order to solve this problem, in this paper, we propose a new validation scheme which is based on prediction and frequency value. In the proposed scheme, we take into exceptional cases account, for example, outbreak of fire. Finally, we demonstrate that the proposed scheme can detect abnormal sensing value more than 13 percent as compared to previous work through diverse simulation scenarios.

• Journal of Drive and Control
• /
• v.21 no.2
• /
• pp.36-43
• /
• 2024

The yield is basic and necessary information in precision agriculture that reduces input resources and enhances productivity. Yield information is important because it can be used to set up farming plans and evaluate farming results. Yield monitoring systems are commercialized in the United States and Japan but not in Korea. Therefore, such a system must be developed. This study was conducted to develop a yield monitoring system that improved performance by correcting a previously developed flow sensor using a grain tank-weighing system. An impact-plated type flow sensor was installed in a grain tank where grains are placed, and grain tank-weighing sensors were installed under the grain tank to estimate the weight of the grain inside the tank. The grain flow rate and grain weight prediction models showed high correlations, with coefficient of determinations (R2) of 0.9979 and 0.9991, respectively. A main controller of the yield monitoring system that calculated the real-time yield using a sensor output value was also developed and installed in a combine harvester. Field tests of the combine harvester yield monitoring system were conducted in a rice paddy field. The developed yield monitoring system showed high accuracy with an error of 0.13%. Therefore, the newly developed yield monitoring system can be used to predict grain weight with high accuracy.

• The KIPS Transactions:PartD
• /
• v.13D no.6 s.109
• /
• pp.775-788
• /
• 2006

Many disaster monitoring systems are constantly studied to prevent disasters such as environmental pollution, the breaking of a tunnel and a building, flooding, storm earthquake according to the progress of wireless telecommunication, the miniaturization of terminal devices, and the spread of sensor network. A disaster monitoring system can extract information of a remote place, process sensor data with rules to recognize disaster situation, and provide work for preventing disaster. However existing monitoring systems are not enough to predict and prevent disaster, because they can only process current sensor data through utilizing simple aggregation function and operators. In this paper, we design and implement a disaster prevention system to predict near future dangerous area through using outside sensor network and spatial Information. The provided prediction technique considers the change of spatial information over time with current sensor data, and indicates the place that could be dangerous in near future. The system can recognize which place would be dangerous and prepare the disaster prevention. Therefore, damage of disaster and cost of recovery would be reduced. The provided disaster prevention system and prediction technique could be applied to various disaster prevention systems and be utilized for preventing disaster and reducing damages.

• Journal of KSNVE
• /
• v.8 no.6
• /
• pp.1023-1029
• /
• 1998

When one attempts to construct a hologram. one finds that there are many sources of measurement errors. These errors are even amplified if one predicts the pressures close to the sources. The pressure estimation errors depend on the following parameters: the measurement spacing on the hologram plane. the prediction spacing on the prediction plane. and the distance between the hologram and the prediction plane. This raper analyzes quantitatively the errors when these are distributed irregularly on the hologram plane The sensor mismatch and inaccurate measurement location. position mismatch. are mainly addressed. In these cases. one can assume that the measurement is a sample of many measurement events. The bias and random error are derived theoretically. Then the relationship between the random error amplification ratio and the parameters mentioned above is examined quantitatively in terms of energy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.210-210
• /
• 2000

In this paper, we have investigated the properties of multi-layer perceptron (MLP) for odour patterns classification and concentration estimation simultaneously. When the MLP may be has a fast convergence speed with small error and excellent mapping ability for classification, it can be possible to use for classification and concentration prediction of volatile chemicals simultaneously. However, the conventional MLP, which is back-Propagation of error based on the steepest descent method, was difficult to use for odour classification and concentration estimation simultaneously, because it is slow to converge and may fall into the local minimum. We adapted the Levenberg-Marquardt(LM) algorithm [4,5] having advantages both the steepest descent method and Gauss-Newton method instead of the conventional steepest descent method for the simultaneous classification and concentration estimation of odours. And, We designed the artificial odour sensing system(Electronic Nose) and applied LM-BP algorithm for classification and concentration prediction of VOC gases.