• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.7A
• /
• pp.697-705
• /
• 2010

In Wireless Sensor Networks (WSNs), blanket (area) coverage analysis is generally carried to find the minimum number of active sensor nodes required to cover a monitoring interest area with the desired fractional coverage-threshold. Normally, the coverage analysis is performed using the stochastic geometry as a tool. The major component of such coverage analysis is the assumed sensing model. Hence, the accuracy of such analysis depends on the underlying assumption of the sensing model: how well the assumed sensing model characterizes the real sensing phenomenon. In this paper, we review the coverage analysis for different deterministic and probabilistic sensing models like Boolean and Shadow-fading model; and extend the analysis for Exponential and hybrid Boolean-Exponential model. From the analytical performance comparison, we demonstrate the redundancy (in terms of number of sensors) that could be resulted due to the coverage analysis based on the detection capability mal-characterizing sensing models.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• Journal of Mechanical Science and Technology
• /
• v.16 no.3
• /
• pp.310-319
• /
• 2002

This paper deals with the analytical modeling, and the experimental verification of the strain rate self-sensing method using a hybrid adaptive filter for a cantilevered piezoelectric beam. The piezoelectric beam consists of two laminated lead zirconium titanates (PZT) on a metal shim. A mathematical model of the beam dynamics is derived by Hamilton's principle and the accuracy of the modeling is verified through the comparison with experimental results. For the strain rate estimation of the cantilevered piezoelectric beam, a self-sensing mechanism using a hybrid adaptive filter is considered. The discrete parts of this mechanism are realized by the DS1103 DSP board manufactured by dSPACE$\^$TM/. The efficacy of this method is investigated through the comparison of experimental results with the predictions from the derived analytical model.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.1
• /
• pp.1-6
• /
• 2013

Variety of smart devices including smart phone have become and essential item in user's daily life. This means that smart devices are good mediators to get collecting user's behavior by sensors mounted on the devices. The information from smart devices is important clues to identify by analyzing the user's preferences and needs. Through this, the intelligent service which is fitted to the user is possible. This paper propose a smart service recommendation model based on user scenario using fusion context-awareness. The information for recommendation services is collected to make the scenario depending on time, location, action based on the Fusion process. The scenarios can help predict a user's situation and provide the services in advance. Also, content categories as well as the content types are determined depending on the scenario. The scenario is a method for providing the best service as well as a basis for the user's situation. Using this method, proposing a smart service model with the fusion context-awareness based on the hybrid sensing is the goal of this paper.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• pp.699-707
• /
• 2015

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.13-24
• /
• 2014

Satellite remote sensing data have been valuable tool for volcanic ash monitoring. In this study, we present the results of application of satellite remote sensing data for monitoring of volcanic ash for three major volcanic eruption cases (2008 Chait$\acute{e}$n, 2010 Eyjafjallaj$\ddot{o}$kull, and 2011 Shinmoedake volcanoes). Volcanic ash detection products based on the Moderate Resolution Imaging Spectro-radiometer (MODIS) observation data using infrared brightness temperature difference technique were compared to the forward air mass trajectory analysis by the HYbrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model. There was good correlation between MODIS volcanic ash image and trajectory lines after the volcanic eruptions, which support the feasibility of using the integration of satellite observed and model derived data for volcanic ash forecasting.

• Journal of Korea Multimedia Society
• /
• v.16 no.12
• /
• pp.1439-1445
• /
• 2013

We present a Taekwondo training system using a hybrid sensing technique of a body sensor and a visual sensor. Using a body sensor (accelerometer), rotational and inertial motion data are captured which are important for Taekwondo motion detection and evaluation. A visual sensor (camera) captures and records the sequential images of the performance. Motion chunk is proposed to structuralize Taekwondo motions and design HMM (Hidden Markov Model) for motion recognition. Trainees can evaluates their trial motions numerically by computing the distance to the standard motion performed by a trainer. For motion training video, the real-time video images captured by a camera is overlayed with a visualized body sensor data so that users can see how the rotational and inertial motion data flow.

• Journal of Satellite, Information and Communications
• /
• v.12 no.3
• /
• pp.98-102
• /
• 2017

In this paper, we study RF-powered backscatter cognitive radio networks to improve the performance for the secondary user which is backscatter radio based wireless sensors. In our proposed model, we consider an avoiding the doubly round-trip attenuation to add a carrier emitter and utilization of spectrum sensing information. When the primary channel is busy, the secondary user is able to harvest RF energy from the channel through a hybrid-access point (H-AP) and a carrier emitter. When the channel becomes idle, the secondary user will be use the harvested energy to operate wireless sensors, to use the sensing and to backscatter through the carrier emitter. We model mathematically the deterministic and multisource elements of a number of tagged channels. In the proposed communication environment, we show the BER performance of the backscatter communication using WiFi signal.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.271-280
• /
• 1999

The topographical effect resulted from rugged terrains and inhomogeneous spectral characteristics due to the complexly mixed land cover condition of Korea substantially lower the remotely sensed land cover classification accuracy In this study, a topographic correction method using digital elevation model to alleviate the topographic effects. To deal with inhomogeneous spectral characteristic, a hybrid classifier with inclusion of prior probabilities was introduced. This investigation concluded that the topographical normalization and hybrid classification with prior probabilities are effective on rugged landscape. The overall and average classification accuracies were improved by 0.92％ and 1.016％ respectively. The most substantial and noticeable accuracy improvement was observed in forest areas.